linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [GIT PULL] perf fixes
@ 2019-05-05 12:47 Ingo Molnar
  2019-05-05 22:10 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-05-05 12:47 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 6f55967ad9d9752813e36de6d5fdbd19741adfc7 perf/x86/intel: Fix race in intel_pmu_disable_event()

I'd like to apologize for this very late pull request: I was dithering 
through the week whether to send the fixes, and then yesterday Jiri's 
crash fix for a regression introduced in this cycle clearly marked 
perf/urgent as 'must merge now'.

Most of the commits are tooling fixes, plus there's three kernel fixes 
via four commits:

 - race fix in the Intel PEBS code
 - fix an AUX bug and roll back a previous attempt
 - fix AMD family 17h generic HW cache-event perf  counters

The largest diffstat contribution comes from the AMD fix - a new event 
table is introduced, which is a fairly low risk change but has a large 
linecount.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (2):
      perf/ring_buffer: Fix AUX software double buffering
      perf/x86/intel/pt: Remove software double buffering PMU capability

Arnaldo Carvalho de Melo (5):
      tools uapi x86: Sync vmx.h with the kernel
      perf bench numa: Add define for RUSAGE_THREAD if not present
      tools build: Add -ldl to the disassembler-four-args feature test
      tools arch uapi: Copy missing unistd.h headers for arc, hexagon and riscv
      perf tools: Remove needless asm/unistd.h include fixing build in some places

Bo YU (1):
      perf bpf: Return value with unlocking in perf_env__find_btf()

Jiri Olsa (1):
      perf/x86/intel: Fix race in intel_pmu_disable_event()

Kim Phillips (2):
      perf/x86/amd: Update generic hardware cache events for Family 17h
      MAINTAINERS: Include vendor specific files under arch/*/events/*

Leo Yan (3):
      tools lib traceevent: Change tag string for error
      perf cs-etm: Don't check cs_etm_queue::prev_packet validity
      perf cs-etm: Always allocate memory for cs_etm_queue::prev_packet

Thadeu Lima de Souza Cascardo (1):
      perf annotate: Fix build on 32 bit for BPF annotation

Thomas Richter (1):
      perf report: Report OOM in status line in the GTK UI


 MAINTAINERS                                  |   1 +
 arch/x86/events/amd/core.c                   | 111 ++++++++++++++++++++++++++-
 arch/x86/events/intel/core.c                 |  10 ++-
 arch/x86/events/intel/pt.c                   |   3 +-
 include/linux/perf_event.h                   |   1 -
 kernel/events/ring_buffer.c                  |   3 +-
 tools/arch/arc/include/uapi/asm/unistd.h     |  51 ++++++++++++
 tools/arch/hexagon/include/uapi/asm/unistd.h |  40 ++++++++++
 tools/arch/riscv/include/uapi/asm/unistd.h   |  42 ++++++++++
 tools/arch/x86/include/uapi/asm/vmx.h        |   1 +
 tools/lib/traceevent/parse-utils.c           |   2 +-
 tools/perf/Makefile.config                   |   2 +-
 tools/perf/bench/numa.c                      |   4 +
 tools/perf/util/annotate.c                   |   8 +-
 tools/perf/util/cloexec.c                    |   1 -
 tools/perf/util/cs-etm.c                     |  14 +---
 tools/perf/util/env.c                        |   2 +-
 tools/perf/util/session.c                    |   8 +-
 18 files changed, 272 insertions(+), 32 deletions(-)
 create mode 100644 tools/arch/arc/include/uapi/asm/unistd.h
 create mode 100644 tools/arch/hexagon/include/uapi/asm/unistd.h
 create mode 100644 tools/arch/riscv/include/uapi/asm/unistd.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 5c38f21aee78..3a15b6d7584e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12176,6 +12176,7 @@ F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
 F:	arch/*/kernel/perf_callchain.c
 F:	arch/*/events/*
+F:	arch/*/events/*/*
 F:	tools/perf/
 
 PERSONALITY HANDLING
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index d45f3fbd232e..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -116,6 +116,110 @@ static __initconst const u64 amd_hw_cache_event_ids
  },
 };
 
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+		[C(RESULT_MISS)]   = 0xc860, /* L2$ access from DC Miss */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches  */
+		[C(RESULT_MISS)]   = 0x0081, /* Instruction cache misses   */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+		[C(RESULT_MISS)]   = 0xf045, /* L2 DTLB misses (PT walks) */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+		[C(RESULT_MISS)]   = 0xff85, /* L1 ITLB misses, L2 misses */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr.      */
+		[C(RESULT_MISS)]   = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+};
+
 /*
  * AMD Performance Monitor K7 and later, up to and including Family 16h:
  */
@@ -865,9 +969,10 @@ __init int amd_pmu_init(void)
 		x86_pmu.amd_nb_constraints = 0;
 	}
 
-	/* Events are common for all AMDs */
-	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
-	       sizeof(hw_cache_event_ids));
+	if (boot_cpu_data.x86 >= 0x17)
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+	else
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 
 	return 0;
 }
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f9451566cd9b..d35f4775d5f1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2091,15 +2091,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
+
+	/*
+	 * Needs to be called after x86_pmu_disable_event,
+	 * so we don't trigger the event without PEBS bit set.
+	 */
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fb3a2f13fc70..339d7628080c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1525,8 +1525,7 @@ static __init int pt_init(void)
 	}
 
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
-		pt_pmu.pmu.capabilities =
-			PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
 
 	pt_pmu.pmu.capabilities	|= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
 	pt_pmu.pmu.attr_groups		 = pt_attr_groups;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e47ef764f613..1f678f023850 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -240,7 +240,6 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_NO_NMI			0x02
 #define PERF_PMU_CAP_AUX_NO_SG			0x04
-#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5eedb49a65ea..674b35383491 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -610,8 +610,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 	 * PMU requests more than one contiguous chunks of memory
 	 * for SW double buffering
 	 */
-	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
-	    !overwrite) {
+	if (!overwrite) {
 		if (!max_order)
 			return -EINVAL;
 
diff --git a/tools/arch/arc/include/uapi/asm/unistd.h b/tools/arch/arc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5eafa1115162
--- /dev/null
+++ b/tools/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
+#define _UAPI_ASM_ARC_UNISTD_H
+
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls	__NR_syscalls
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
+/* ARC specific syscall */
+#define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#undef __SYSCALL
+
+#endif
diff --git a/tools/arch/hexagon/include/uapi/asm/unistd.h b/tools/arch/hexagon/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..432c4db1b623
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/unistd.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Syscall support for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+/*
+ *  The kernel pulls this unistd.h in three different ways:
+ *  1.  the "normal" way which gets all the __NR defines
+ *  2.  with __SYSCALL defined to produce function declarations
+ *  3.  with __SYSCALL defined to produce syscall table initialization
+ *  See also:  syscalltab.c
+ */
+
+#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/riscv/include/uapi/asm/unistd.h b/tools/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..0e2eeeb1fd27
--- /dev/null
+++ b/tools/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef __LP64__
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
+#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index 77e4ec6402dd..e99867111387 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -14,7 +14,7 @@
 void __vwarning(const char *fmt, va_list ap)
 {
 	if (errno)
-		perror("trace-cmd");
+		perror("libtraceevent");
 	errno = 0;
 
 	fprintf(stderr, "  ");
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fe3f97e342fa..6d65874e16c3 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -227,7 +227,7 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
-FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 98ad783efc69..a7784554a80d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -39,6 +39,10 @@
 #include <numa.h>
 #include <numaif.h>
 
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
 /*
  * Regular printout to the terminal, supressed if -q is specified:
  */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index c8b01176c9e1..09762985c713 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1714,8 +1714,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return -1;
 
-	pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
-		 sym->name, sym->start, sym->end - sym->start);
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
 
 	memset(tpath, 0, sizeof(tpath));
 	perf_exe(tpath, sizeof(tpath));
@@ -1740,7 +1740,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
-	info.buffer = (void *)(info_linear->info.jited_prog_insns);
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
 	info.buffer_length = info_linear->info.jited_prog_len;
 
 	if (info_linear->info.nr_line_info)
@@ -1776,7 +1776,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		const char *srcline;
 		u64 addr;
 
-		addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
 		count = disassemble(pc, &info);
 
 		if (prog_linfo)
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index ca0fff6272be..06f48312c5ed 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,7 +7,6 @@
 #include "asm/bug.h"
 #include "debug.h"
 #include <unistd.h>
-#include <asm/unistd.h>
 #include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 110804936fc3..de488b43f440 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -422,11 +422,9 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
 	if (!etmq->packet)
 		goto out_free;
 
-	if (etm->synth_opts.last_branch || etm->sample_branches) {
-		etmq->prev_packet = zalloc(szp);
-		if (!etmq->prev_packet)
-			goto out_free;
-	}
+	etmq->prev_packet = zalloc(szp);
+	if (!etmq->prev_packet)
+		goto out_free;
 
 	if (etm->synth_opts.last_branch) {
 		size_t sz = sizeof(struct branch_stack);
@@ -981,7 +979,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 	 * PREV_PACKET is a branch.
 	 */
 	if (etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
 	    etmq->prev_packet->last_instr_taken_branch)
 		cs_etm__update_last_branch_rb(etmq);
@@ -1014,7 +1011,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches && etmq->prev_packet) {
+	if (etm->sample_branches) {
 		bool generate_sample = false;
 
 		/* Generate sample for tracing on packet */
@@ -1071,9 +1068,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
-	if (!etmq->prev_packet)
-		return 0;
-
 	/* Handle start tracing packet */
 	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
 		goto swap_packet;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9494f9dc61ec..6a3eaf7d9353 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -115,8 +115,8 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 	}
 	node = NULL;
 
-	up_read(&env->bpf_progs.lock);
 out:
+	up_read(&env->bpf_progs.lock);
 	return node;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b17f1c9bc965..bad5f87ae001 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1928,12 +1928,14 @@ reader__process_events(struct reader *rd, struct perf_session *session,
 
 	size = event->header.size;
 
+	skip = -EINVAL;
+
 	if (size < sizeof(struct perf_event_header) ||
 	    (skip = rd->process(session, event, file_pos)) < 0) {
-		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       file_offset + head, event->header.size,
-		       event->header.type);
-		err = -EINVAL;
+		       event->header.type, strerror(-skip));
+		err = skip;
 		goto out;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-05-05 12:47 [GIT PULL] perf fixes Ingo Molnar
@ 2019-05-05 22:10 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-05-05 22:10 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
	Andrew Morton

The pull request you sent on Sun, 5 May 2019 14:47:46 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/7178fb0b239d1c037876301c116fc9a6c1bd2ac0

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2023-01-06 11:57 Ingo Molnar
@ 2023-01-06 21:19 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2023-01-06 21:19 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra, Borislav Petkov,
	Thomas Gleixner, Arnaldo Carvalho de Melo, Jiri Olsa,
	Alexander Shishkin, Mark Rutland, Namhyung Kim, Andrew Morton

The pull request you sent on Fri, 6 Jan 2023 12:57:48 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2023-01-06

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/d7a0853d650b381921732ff5bca618432a279033

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2023-01-06 11:57 Ingo Molnar
  2023-01-06 21:19 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2023-01-06 11:57 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Borislav Petkov, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Jiri Olsa, Alexander Shishkin,
	Mark Rutland, Namhyung Kim, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2023-01-06

   # HEAD: 57512b57dcfaf63c52d8ad2fb35321328cde31b0 perf/x86/rapl: Add support for Intel Emerald Rapids

Intel RAPL updates for new model IDs.

NOTE: technically this is hardware-enablement, but we generally make an 
exception for trivial expansions of model check tables that only affect 
those models. Let me know if it's a bridge too far for -rc3.

 Thanks,

	Ingo

------------------>
Chris Wilson (1):
      perf/x86/rapl: Treat Tigerlake like Icelake

Zhang Rui (2):
      perf/x86/rapl: Add support for Intel Meteor Lake
      perf/x86/rapl: Add support for Intel Emerald Rapids


 arch/x86/events/rapl.c | 5 +++++
 1 file changed, 5 insertions(+)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2022-10-02 16:47 ` Linus Torvalds
@ 2022-10-03 10:55   ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2022-10-03 10:55 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Mark Rutland, Alexander Shishkin, Jiri Olsa, Namhyung Kim


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Sun, Oct 2, 2022 at 3:56 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> >  - Fix KVM guest PEBS register handling.
> 
> I wondered why my diffstat wasn't the same as yours, but it turns out
> it's because I got this one from the kvm tree earlier.

Oh - indeed, didn't notice that.

> It all merged fine, just surprising.

Yeah. These are the two commits:

  [perf/urgent]     f2aeea57504c ("perf/x86/core: Completely disable guest PEBS via guest's global_ctrl")
  [KVM tree]        87693645ae89 ("perf/x86/core: Completely disable guest PEBS via guest's global_ctrl")

Just to make sure I double checked that they are identical:

  thule:~/tip> git log -1 -p f2aeea57504c | grep -A 100 "^@@" | tail +2 | sha1sum 
  e758bebe3046ef6a51d19d7b5498e165dc8e37be  -

  thule:~/tip> git log -1 -p 87693645ae89 | grep -A 100 "^@@" | tail +2 | sha1sum 
  e758bebe3046ef6a51d19d7b5498e165dc8e37be  -

Paolo applied the fix a couple of hours after Peter, but we
never noticed the overlap & the perf/urgent base didn't have
Paolo's commit so I didn't notice when sending the tree.

Sorry about that!

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2022-10-02 10:56 Ingo Molnar
  2022-10-02 16:47 ` Linus Torvalds
@ 2022-10-02 17:20 ` pr-tracker-bot
  1 sibling, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2022-10-02 17:20 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin,
	Jiri Olsa, Namhyung Kim

The pull request you sent on Sun, 2 Oct 2022 12:56:34 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-10-02

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/febae48afe6063105a0fad83d8e12a6addda7c6a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2022-10-02 10:56 Ingo Molnar
@ 2022-10-02 16:47 ` Linus Torvalds
  2022-10-03 10:55   ` Ingo Molnar
  2022-10-02 17:20 ` pr-tracker-bot
  1 sibling, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2022-10-02 16:47 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Mark Rutland, Alexander Shishkin, Jiri Olsa, Namhyung Kim

On Sun, Oct 2, 2022 at 3:56 AM Ingo Molnar <mingo@kernel.org> wrote:
>
>  - Fix KVM guest PEBS register handling.

I wondered why my diffstat wasn't the same as yours, but it turns out
it's because I got this one from the kvm tree earlier.

It all merged fine, just surprising.

            Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2022-10-02 10:56 Ingo Molnar
  2022-10-02 16:47 ` Linus Torvalds
  2022-10-02 17:20 ` pr-tracker-bot
  0 siblings, 2 replies; 376+ messages in thread
From: Ingo Molnar @ 2022-10-02 10:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Mark Rutland, Alexander Shishkin, Jiri Olsa, Namhyung Kim

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-10-02

   # HEAD: 6b959ba22d34ca793ffdb15b5715457c78e38b1a perf/core: Fix reentry problem in perf_output_read_group()

Misc fixes:

 - Fix a PMU enumeration/initialization bug on Intel Alder Lake CPUs.
 - Fix KVM guest PEBS register handling.
 - Fix race/reentry bug in perf_output_read_group() reading of PMU counters.

 Thanks,

	Ingo

------------------>
Kan Liang (1):
      perf/x86/intel: Fix unchecked MSR access error for Alder Lake N

Like Xu (1):
      perf/x86/core: Completely disable guest PEBS via guest's global_ctrl

Yang Jihong (1):
      perf/core: Fix reentry problem in perf_output_read_group()


 arch/x86/events/intel/core.c | 43 +++++++++++++++++++++++++++++++++++++++++--
 arch/x86/events/intel/ds.c   |  9 +++++++--
 arch/x86/events/perf_event.h |  2 ++
 kernel/events/core.c         |  9 +++++++++
 4 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cb98a05ee743..c20d8cd47c48 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(mem-loads,	mem_ld_grt,	"event=0xd0,umask=0x5,ldlat=3");
+EVENT_ATTR_STR(mem-stores,	mem_st_grt,	"event=0xd0,umask=0x6");
+
+static struct attribute *grt_mem_attrs[] = {
+	EVENT_PTR(mem_ld_grt),
+	EVENT_PTR(mem_st_grt),
+	NULL
+};
+
 static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
@@ -4052,8 +4061,9 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		/* Disable guest PEBS if host PEBS is enabled. */
 		arr[pebs_enable].guest = 0;
 	} else {
-		/* Disable guest PEBS for cross-mapped PEBS counters. */
+		/* Disable guest PEBS thoroughly for cross-mapped PEBS counters. */
 		arr[pebs_enable].guest &= ~kvm_pmu->host_cross_mapped_mask;
+		arr[global_ctrl].guest &= ~kvm_pmu->host_cross_mapped_mask;
 		/* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
 		arr[global_ctrl].guest |= arr[pebs_enable].guest;
 	}
@@ -5974,6 +5984,36 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
+	case INTEL_FAM6_ALDERLAKE_N:
+		x86_pmu.mid_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_grt_extra_regs;
+
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+		intel_pmu_pebs_data_source_grt();
+		x86_pmu.pebs_latency_data = adl_latency_data_small;
+		x86_pmu.get_event_constraints = tnt_get_event_constraints;
+		x86_pmu.limit_period = spr_limit_period;
+		td_attr = tnt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = nhm_format_attr;
+		pr_cont("Gracemont events, ");
+		name = "gracemont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
@@ -6316,7 +6356,6 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 		/*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index de1f55d51784..ac973c6f82ad 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem)
 	__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
 }
 
-static void __init intel_pmu_pebs_data_source_grt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source)
 {
 	data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
 	data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
 	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
 }
 
+void __init intel_pmu_pebs_data_source_grt(void)
+{
+	__intel_pmu_pebs_data_source_grt(pebs_data_source);
+}
+
 void __init intel_pmu_pebs_data_source_adl(void)
 {
 	u64 *data_source;
@@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
 
 	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
 	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
-	intel_pmu_pebs_data_source_grt(data_source);
+	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
 static u64 precise_store_data(u64 status)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba3d24a6a4ec..266143abcbd8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem);
 
 void intel_pmu_pebs_data_source_adl(void);
 
+void intel_pmu_pebs_data_source_grt(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2621fd24ad26..ff4bffc502c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6893,9 +6893,16 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
+	unsigned long flags;
 	u64 values[6];
 	int n = 0;
 
+	/*
+	 * Disabling interrupts avoids all counter scheduling
+	 * (context switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -6931,6 +6938,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 
 		__output_copy(handle, values, n * sizeof(u64));
 	}
+
+	local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2022-08-28 14:35 Ingo Molnar
@ 2022-08-28 18:18 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2022-08-28 18:18 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Mark Rutland,
	Alexander Shishkin, Namhyung Kim, linux-perf-users,
	Thomas Gleixner, Borislav Petkov, Andrew Morton

The pull request you sent on Sun, 28 Aug 2022 16:35:57 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/4459d800f71d01042b36326fd8ece1f823b9da16

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2022-08-28 14:35 Ingo Molnar
  2022-08-28 18:18 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2022-08-28 14:35 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Mark Rutland, Alexander Shishkin, Namhyung Kim,
	linux-perf-users, Thomas Gleixner, Borislav Petkov,
	Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-28

   # HEAD: 11745ecfe8fea4b4a4c322967a7605d2ecbd5080 perf/x86/intel/uncore: Fix broken read_counter() for SNB IMC PMU

Misc fixes: an Arch-LBR fix, a PEBS enumeration fix, an Intel DS fix,
PEBS constraints fix on Alder Lake CPUs and an Intel uncore PMU fix.

 Thanks,

	Ingo

------------------>
Kan Liang (2):
      perf/x86/lbr: Enable the branch type for the Arch LBR by default
      perf/x86/intel: Fix pebs event constraints for ADL

Peter Zijlstra (1):
      perf/x86/core: Set pebs_capable and PMU_FL_PEBS_ALL for the Baseline

Stephane Eranian (2):
      perf/x86/intel/ds: Fix precise store latency handling
      perf/x86/intel/uncore: Fix broken read_counter() for SNB IMC PMU


 arch/x86/events/intel/core.c       |  4 ----
 arch/x86/events/intel/ds.c         | 13 +++++++++++--
 arch/x86/events/intel/lbr.c        |  8 ++++++++
 arch/x86/events/intel/uncore_snb.c | 18 +++++++++++++++++-
 4 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2db93498ff71..cb98a05ee743 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6291,10 +6291,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
-		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 
@@ -6337,10 +6335,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
-		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 		x86_pmu.lbr_pt_coexist = true;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba60427caa6d..de1f55d51784 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -291,6 +291,7 @@ static u64 load_latency_data(struct perf_event *event, u64 status)
 static u64 store_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
 	u64 val;
 
 	dse.val = status;
@@ -304,7 +305,14 @@ static u64 store_latency_data(struct perf_event *event, u64 status)
 
 	val |= P(BLK, NA);
 
-	return val;
+	/*
+	 * the pebs_data_source table is only for loads
+	 * so override the mem_op to say STORE instead
+	 */
+	src.val = val;
+	src.mem_op = P(OP,STORE);
+
+	return src.val;
 }
 
 struct pebs_record_core {
@@ -822,7 +830,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 
 struct event_constraint intel_grt_pebs_event_constraints[] = {
 	/* Allow all events as PEBS with no flags */
-	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3),
 	INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
 	EVENT_CONSTRAINT_END
 };
@@ -2262,6 +2270,7 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_BRANCH_STACK |
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
+				x86_pmu.pebs_capable = ~0ULL;
 				pebs_qual = "-baseline";
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4f70fb6c2c1e..47fca6a7a8bc 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1097,6 +1097,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
 		reg->config = mask;
+
+		/*
+		 * The Arch LBR HW can retrieve the common branch types
+		 * from the LBR_INFO. It doesn't require the high overhead
+		 * SW disassemble.
+		 * Enable the branch type by default for the Arch LBR.
+		 */
+		reg->reg |= X86_BR_TYPE_SAVE;
 		return 0;
 	}
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index ce440011cc4e..1ef4f7861e2e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -841,6 +841,22 @@ int snb_pci2phy_map_init(int devid)
 	return 0;
 }
 
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * SNB IMC counters are 32-bit and are laid out back to back
+	 * in MMIO space. Therefore we must use a 32-bit accessor function
+	 * using readq() from uncore_mmio_read_counter() causes problems
+	 * because it is reading 64-bit at a time. This is okay for the
+	 * uncore_perf_event_update() function because it drops the upper
+	 * 32-bits but not okay for plain uncore_read_counter() as invoked
+	 * in uncore_pmu_event_start().
+	 */
+	return (u64)readl(box->io_addr + hwc->event_base);
+}
+
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
@@ -860,7 +876,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.disable_event	= snb_uncore_imc_disable_event,
 	.enable_event	= snb_uncore_imc_enable_event,
 	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= uncore_mmio_read_counter,
+	.read_counter	= snb_uncore_imc_read_counter,
 };
 
 static struct intel_uncore_type snb_uncore_imc = {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2022-08-06 19:10 Ingo Molnar
@ 2022-08-07  0:50 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2022-08-07  0:50 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin,
	Jiri Olsa, Namhyung Kim, linux-perf-users, Thomas Gleixner,
	Borislav Petkov, Andrew Morton

The pull request you sent on Sat, 6 Aug 2022 21:10:36 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-06

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/592d8362bc2526bbb08cf7d258661691e957b5ea

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2022-08-06 19:10 Ingo Molnar
  2022-08-07  0:50 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2022-08-06 19:10 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Mark Rutland, Alexander Shishkin, Jiri Olsa, Namhyung Kim,
	linux-perf-users, Thomas Gleixner, Borislav Petkov,
	Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-06

   # HEAD: 99643bab36b642be10bf09cd3285c37c9e5b597f perf/core: Fix ';;' typo

Misc fixes to kprobes and the faddr2line script, plus a cleanup.

 Thanks,

	Ingo

------------------>
Chen Zhongjin (1):
      kprobes: Forbid probing on trampoline and BPF code areas

Josh Poimboeuf (2):
      scripts/faddr2line: Fix vmlinux detection on arm64
      scripts/faddr2line: Add CONFIG_DEBUG_INFO check

Masami Hiramatsu (Google) (1):
      x86/kprobes: Update kcb status flag after singlestepping

Slark Xiao (1):
      perf/core: Fix ';;' typo


 arch/x86/kernel/kprobes/core.c | 18 +++++++++++-------
 kernel/events/core.c           |  2 +-
 kernel/kprobes.c               |  3 ++-
 scripts/faddr2line             |  7 ++++++-
 4 files changed, 20 insertions(+), 10 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2021-07-11 13:26 Ingo Molnar
@ 2021-07-11 18:22 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2021-07-11 18:22 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Mark Rutland, Thomas Gleixner,
	Andrew Morton

The pull request you sent on Sun, 11 Jul 2021 15:26:50 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-07-11

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/936b664fb20895277453c02be4f3a94d6ce2b3c8

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2021-07-11 13:26 Ingo Molnar
  2021-07-11 18:22 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2021-07-11 13:26 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Mark Rutland, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-07-11

   # HEAD: d4ba0b06306a70c99a43f9d452886a86e2d3bd26 perf/x86/intel/uncore: Clean up error handling path of iio mapping

A fix and a hardware-enablement addition:

 - Robustify uncore_snbep's skx_iio_set_mapping()'s error cleanup
 - Add cstate event support for Intel ICELAKE_X and ICELAKE_D

 Thanks,

	Ingo

------------------>
Kan Liang (1):
      perf/x86/intel/uncore: Clean up error handling path of iio mapping

Zhang Rui (1):
      perf/x86/cstate: Add ICELAKE_X and ICELAKE_D support


 arch/x86/events/intel/cstate.c       | 23 +++++++++++++++++------
 arch/x86/events/intel/uncore_snbep.c |  6 ++++--
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 433399069e27..c6262b154c3a 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,7 +40,7 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT,GLM,CNL,TNT,ADL
+ *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
@@ -50,8 +50,8 @@
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
- *						TNT,RKL,ADL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
+ *						TGL,TNT,RKL,ADL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -61,7 +61,7 @@
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL,TGL,TNT,RKL,ADL
+ *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
@@ -72,8 +72,8 @@
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
- *						TNT,RKL,ADL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
+ *						TGL,TNT,RKL,ADL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -566,6 +566,14 @@ static const struct cstate_model icl_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model icx_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
+};
+
 static const struct cstate_model adl_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES) |
@@ -664,6 +672,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&icx_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&icx_cstates),
+
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&icl_cstates),
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 3a75a2c601c2..1f7bb4898a9d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3789,11 +3789,11 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 	/* One more for NULL. */
 	attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL);
 	if (!attrs)
-		goto err;
+		goto clear_topology;
 
 	eas = kcalloc(uncore_max_dies(), sizeof(*eas), GFP_KERNEL);
 	if (!eas)
-		goto err;
+		goto clear_attrs;
 
 	for (die = 0; die < uncore_max_dies(); die++) {
 		sprintf(buf, "die%ld", die);
@@ -3814,7 +3814,9 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 	for (; die >= 0; die--)
 		kfree(eas[die].attr.attr.name);
 	kfree(eas);
+clear_attrs:
 	kfree(attrs);
+clear_topology:
 	kfree(type->topology);
 clear_attr_update:
 	type->attr_update = NULL;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2021-06-12 12:48 Ingo Molnar
@ 2021-06-12 19:09 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2021-06-12 19:09 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton

The pull request you sent on Sat, 12 Jun 2021 14:48:15 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-06-12

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/191aaf6cc4a7db907520f18af3a90b260e7dd091

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2021-06-12 12:48 Ingo Molnar
  2021-06-12 19:09 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2021-06-12 12:48 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-06-12

   # HEAD: a8383dfb2138742a1bb77b481ada047aededa2ba x86/nmi_watchdog: Fix old-style NMI watchdog regression on old Intel CPUs

Misc fixes:

 - Fix the NMI watchdog on ancient Intel CPUs

 - Remove a misguided, NMI-unsafe KASAN callback
   from the NMI-safe irq_work path used by perf.

 - Fix uncore events on Ice Lake servers.

 - Someone booted maxcpus=1 on an SNB-EP, and the
   uncore driver emitted warnings and was probably
   buggy. Fix it.

 - KCSAN found a genuine data race in the core perf
   code. Somewhat ironically the bug was introduced
   through a recent race fix. :-/ In our defense, the
   new race window was much more narrow. Fix it.

 Thanks,

	Ingo

------------------>
CodyYao-oc (1):
      x86/nmi_watchdog: Fix old-style NMI watchdog regression on old Intel CPUs

Kan Liang (2):
      perf/x86/intel/uncore: Fix a kernel WARNING triggered by maxcpus=1
      perf/x86/intel/uncore: Fix M2M event umask for Ice Lake server

Marco Elver (1):
      perf: Fix data race between pin_count increment/decrement

Peter Zijlstra (1):
      irq_work: Make irq_work_queue() NMI-safe again


 arch/x86/events/intel/uncore_snbep.c   | 9 ++++++---
 arch/x86/kernel/cpu/perfctr-watchdog.c | 4 ++--
 kernel/events/core.c                   | 2 ++
 kernel/irq_work.c                      | 3 ---
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 63f097289a84..3a75a2c601c2 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1406,6 +1406,8 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 						die_id = i;
 					else
 						die_id = topology_phys_to_logical_pkg(i);
+					if (die_id < 0)
+						die_id = -ENODEV;
 					map->pbus_to_dieid[bus] = die_id;
 					break;
 				}
@@ -1452,14 +1454,14 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 			i = -1;
 			if (reverse) {
 				for (bus = 255; bus >= 0; bus--) {
-					if (map->pbus_to_dieid[bus] >= 0)
+					if (map->pbus_to_dieid[bus] != -1)
 						i = map->pbus_to_dieid[bus];
 					else
 						map->pbus_to_dieid[bus] = i;
 				}
 			} else {
 				for (bus = 0; bus <= 255; bus++) {
-					if (map->pbus_to_dieid[bus] >= 0)
+					if (map->pbus_to_dieid[bus] != -1)
 						i = map->pbus_to_dieid[bus];
 					else
 						map->pbus_to_dieid[bus] = i;
@@ -5097,9 +5099,10 @@ static struct intel_uncore_type icx_uncore_m2m = {
 	.perf_ctr	= SNR_M2M_PCI_PMON_CTR0,
 	.event_ctl	= SNR_M2M_PCI_PMON_CTL0,
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.event_mask_ext	= SNR_M2M_PCI_PMON_UMASK_EXT,
 	.box_ctl	= SNR_M2M_PCI_PMON_BOX_CTL,
 	.ops		= &snr_m2m_uncore_pci_ops,
-	.format_group	= &skx_uncore_format_group,
+	.format_group	= &snr_m2m_uncore_format_group,
 };
 
 static struct attribute *icx_upi_uncore_formats_attr[] = {
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 3ef5868ac588..7aecb2fc3186 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -63,7 +63,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
-		fallthrough;
+		break;
 	case X86_VENDOR_ZHAOXIN:
 	case X86_VENDOR_CENTAUR:
 		return msr - MSR_ARCH_PERFMON_PERFCTR0;
@@ -96,7 +96,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
-		fallthrough;
+		break;
 	case X86_VENDOR_ZHAOXIN:
 	case X86_VENDOR_CENTAUR:
 		return msr - MSR_ARCH_PERFMON_EVENTSEL0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6fee4a7e88d7..fe88d6eea3c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4609,7 +4609,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
+		raw_spin_lock_irqsave(&ctx->lock, flags);
 		++ctx->pin_count;
+		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 
 		return ctx;
 	}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 23a7a0ba1388..db8c248ebc8c 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -70,9 +70,6 @@ bool irq_work_queue(struct irq_work *work)
 	if (!irq_work_claim(work))
 		return false;
 
-	/*record irq_work call stack in order to print it in KASAN reports*/
-	kasan_record_aux_stack(work);
-
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 	__irq_work_queue_local(work);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2021-03-21 10:56 Ingo Molnar
@ 2021-03-21 18:45 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2021-03-21 18:45 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sun, 21 Mar 2021 11:56:36 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-03-21

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/1c74516c2da40ead2c22c4ac07c117c20f9c31ec

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2021-03-21 10:56 Ingo Molnar
  2021-03-21 18:45 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2021-03-21 10:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-03-21

   # HEAD: 2dc0572f2cef87425147658698dce2600b799bd3 perf/x86/intel: Fix unchecked MSR access error caused by VLBR_EVENT

Boundary condition fixes for bugs unearthed by the perf fuzzer.

 Thanks,

	Ingo

------------------>
Kan Liang (2):
      perf/x86/intel: Fix a crash caused by zero PEBS status
      perf/x86/intel: Fix unchecked MSR access error caused by VLBR_EVENT


 arch/x86/events/intel/core.c | 3 +++
 arch/x86/events/intel/ds.c   | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7bbb5bb98d8c..37ce38403cb8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3659,6 +3659,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
+		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
+			return -EINVAL;
+
 		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ebae1826403..d32b302719fe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2010,7 +2010,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		 */
 		if (!pebs_status && cpuc->pebs_enabled &&
 			!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
-			pebs_status = cpuc->pebs_enabled;
+			pebs_status = p->status = cpuc->pebs_enabled;
 
 		bit = find_first_bit((unsigned long *)&pebs_status,
 					x86_pmu.max_pebs_events);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2020-08-15 11:21 Ingo Molnar
@ 2020-08-16  1:55 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2020-08-16  1:55 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sat, 15 Aug 2020 13:21:33 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-08-15

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/7f5faaaa5909bb0b26dcd309424da14bdf0c7e93

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2020-08-15 11:21 Ingo Molnar
  2020-08-16  1:55 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2020-08-15 11:21 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-08-15

   # HEAD: bcfd218b66790243ef303c1b35ce59f786ded225 perf/x86/rapl: Add support for Intel SPR platform

Misc fixes, an expansion of perf syscall access to CAP_PERFMON privileged tools,
plus a RAPL HW-enablement for Intel SPR platforms.

 Thanks,

	Ingo

------------------>
Alexey Budankov (1):
      perf/core: Take over CAP_SYS_PTRACE creds to CAP_PERFMON capability

Bhupesh Sharma (1):
      hw_breakpoint: Remove unused __register_perf_hw_breakpoint() declaration

Masami Hiramatsu (1):
      kprobes: Remove show_registers() function prototype

Zhang Rui (3):
      perf/x86/rapl: Fix missing psys sysfs attributes
      perf/x86/rapl: Support multiple RAPL unit quirks
      perf/x86/rapl: Add support for Intel SPR platform


 arch/x86/events/rapl.c        | 46 +++++++++++++++++++++++++++++++++----------
 include/linux/hw_breakpoint.h |  3 ---
 include/linux/kprobes.h       |  1 -
 kernel/events/core.c          |  4 ++--
 4 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 68b38820b10e..67b411f7e8c4 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -130,11 +130,17 @@ struct rapl_pmus {
 	struct rapl_pmu		*pmus[];
 };
 
+enum rapl_unit_quirk {
+	RAPL_UNIT_QUIRK_NONE,
+	RAPL_UNIT_QUIRK_INTEL_HSW,
+	RAPL_UNIT_QUIRK_INTEL_SPR,
+};
+
 struct rapl_model {
 	struct perf_msr *rapl_msrs;
 	unsigned long	events;
 	unsigned int	msr_power_unit;
-	bool		apply_quirk;
+	enum rapl_unit_quirk	unit_quirk;
 };
 
  /* 1/2^hw_unit Joule */
@@ -612,14 +618,28 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	for (i = 0; i < NR_RAPL_DOMAINS; i++)
 		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 
+	switch (rm->unit_quirk) {
 	/*
 	 * DRAM domain on HSW server and KNL has fixed energy unit which can be
 	 * different than the unit from power unit MSR. See
 	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
-	if (rm->apply_quirk)
+	case RAPL_UNIT_QUIRK_INTEL_HSW:
+		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		break;
+	/*
+	 * SPR shares the same DRAM domain energy unit as HSW, plus it
+	 * also has a fixed energy unit for Psys domain.
+	 */
+	case RAPL_UNIT_QUIRK_INTEL_SPR:
 		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		rapl_hw_unit[PERF_RAPL_PSYS] = 0;
+		break;
+	default:
+		break;
+	}
+
 
 	/*
 	 * Calculate the timer rate:
@@ -665,7 +685,7 @@ static const struct attribute_group *rapl_attr_update[] = {
 	&rapl_events_pkg_group,
 	&rapl_events_ram_group,
 	&rapl_events_gpu_group,
-	&rapl_events_gpu_group,
+	&rapl_events_psys_group,
 	NULL,
 };
 
@@ -698,7 +718,6 @@ static struct rapl_model model_snb = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -707,7 +726,6 @@ static struct rapl_model model_snbep = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -717,7 +735,6 @@ static struct rapl_model model_hsw = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -726,7 +743,7 @@ static struct rapl_model model_hsx = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= true,
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -734,7 +751,7 @@ static struct rapl_model model_hsx = {
 static struct rapl_model model_knl = {
 	.events		= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= true,
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -745,14 +762,22 @@ static struct rapl_model model_skl = {
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
-	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
+};
+
+static struct rapl_model model_spr = {
+	.events		= BIT(PERF_RAPL_PP0) |
+			  BIT(PERF_RAPL_PKG) |
+			  BIT(PERF_RAPL_RAM) |
+			  BIT(PERF_RAPL_PSYS),
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_SPR,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_amd_fam17h = {
 	.events		= BIT(PERF_RAPL_PKG),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
 	.rapl_msrs      = amd_rapl_msrs,
 };
@@ -787,6 +812,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
 	X86_MATCH_VENDOR_FAM(AMD,	0x17,		&model_amd_fam17h),
 	X86_MATCH_VENDOR_FAM(HYGON,	0x18,		&model_amd_fam17h),
 	{},
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index d7d4250cd1e4..78dd7035d1e5 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -72,7 +72,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    void *context);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
-extern int __register_perf_hw_breakpoint(struct perf_event *bp);
 extern void unregister_hw_breakpoint(struct perf_event *bp);
 extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
 
@@ -119,8 +118,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    void *context)		{ return NULL; }
 static inline int
 register_perf_hw_breakpoint(struct perf_event *bp)	{ return -ENOSYS; }
-static inline int
-__register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
 static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
 static inline void
 unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)	{ }
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 45b8cdc9fad7..9be1bff4f586 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
-extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 78e69e10482a..41e0cefb429b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11689,7 +11689,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_task;
 
 		/*
-		 * Reuse ptrace permission checks for now.
+		 * Preserve ptrace permission check for backwards compatibility.
 		 *
 		 * We must hold exec_update_mutex across this and any potential
 		 * perf_install_in_context() call for this new event to
@@ -11697,7 +11697,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * perf_event_exit_task() that could imply).
 		 */
 		err = -EACCES;
-		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+		if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
 			goto err_cred;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2020-04-25  9:19 Ingo Molnar
@ 2020-04-25 19:30 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2020-04-25 19:30 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sat, 25 Apr 2020 11:19:18 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-25

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/e18588005d79853c2d4101f9416e7c1e8c9584d2

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2020-04-25  9:19 Ingo Molnar
  2020-04-25 19:30 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2020-04-25  9:19 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-25

   # HEAD: f3bed55e850926614b9898fe982f66d2541a36a5 perf/core: fix parent pid/tid in task exit events

Two changes:

 - fix exit event records
 - extend x86 PMU driver enumeration to add Intel Jasper Lake CPU support.

 Thanks,

	Ingo

------------------>
Harry Pan (1):
      perf/x86/cstate: Add Jasper Lake CPU support

Ian Rogers (1):
      perf/core: fix parent pid/tid in task exit events


 arch/x86/events/intel/cstate.c |  1 +
 kernel/events/core.c           | 13 ++++++++++---
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e4aa20c0426f..442e1ed4acd4 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -643,6 +643,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&glm_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc9b98a9af9a..633b4ae72ed5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7491,10 +7491,17 @@ static void perf_event_task_output(struct perf_event *event,
 		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
-	task_event->event_id.ppid = perf_event_pid(event, current);
-
 	task_event->event_id.tid = perf_event_tid(event, task);
-	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	if (task_event->event_id.header.type == PERF_RECORD_EXIT) {
+		task_event->event_id.ppid = perf_event_pid(event,
+							task->real_parent);
+		task_event->event_id.ptid = perf_event_pid(event,
+							task->real_parent);
+	} else {  /* PERF_RECORD_FORK */
+		task_event->event_id.ppid = perf_event_pid(event, current);
+		task_event->event_id.ptid = perf_event_tid(event, current);
+	}
 
 	task_event->event_id.time = perf_event_clock(event);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2020-03-24  9:19 Ingo Molnar
@ 2020-03-24 17:15 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2020-03-24 17:15 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner

The pull request you sent on Tue, 24 Mar 2020 10:19:52 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/76ccd234269bd05debdbc12c96eafe62dd9a6180

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2020-03-24  9:19 Ingo Molnar
  2020-03-24 17:15 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2020-03-24  9:19 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 564200ed8e71d91327d337e46bc778cee02da866 tools headers uapi: Update linux/in.h copy

A handful of tooling fixes all across the map, no kernel changes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools headers uapi: Update linux/in.h copy

Ian Rogers (1):
      perf parse-events: Fix reading of invalid memory in event parsing

Ilie Halip (1):
      perf python: Fix clang detection when using CC=clang-version

Masami Hiramatsu (3):
      tools: Let O= makes handle a relative path with -C option
      perf probe: Fix to delete multiple probe event
      perf probe: Do not depend on dwfl_module_addrsym()

disconnect3d (1):
      perf map: Fix off by one in strncpy() size argument


 tools/include/uapi/linux/in.h  |  2 ++
 tools/perf/Makefile            |  2 +-
 tools/perf/util/map.c          |  2 +-
 tools/perf/util/parse-events.c | 46 +++++++++++++++++++++---------------------
 tools/perf/util/probe-file.c   |  3 +++
 tools/perf/util/probe-finder.c | 11 +++++++---
 tools/perf/util/setup.py       | 10 +++++----
 tools/scripts/Makefile.include |  4 ++--
 8 files changed, 46 insertions(+), 34 deletions(-)

diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 1521073b6348..8533bf07450f 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -74,6 +74,8 @@ enum {
 #define IPPROTO_UDPLITE		IPPROTO_UDPLITE
   IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
 #define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_ETHERNET = 143,	/* Ethernet-within-IPv6 Encapsulation	*/
+#define IPPROTO_ETHERNET	IPPROTO_ETHERNET
   IPPROTO_RAW = 255,		/* Raw IP packets			*/
 #define IPPROTO_RAW		IPPROTO_RAW
   IPPROTO_MPTCP = 262,		/* Multipath TCP connection		*/
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7902a5681fc8..b8fc7d972be9 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,7 +35,7 @@ endif
 # Only pass canonical directory names as the output directory:
 #
 ifneq ($(O),)
-  FULL_O := $(shell readlink -f $(O) || echo $(O))
+  FULL_O := $(shell cd $(PWD); readlink -f $(O) || echo $(O))
 endif
 
 #
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 95428511300d..b342f744b1fc 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 11)) {
+	if (!strncmp(filename, "/system/lib/", 12)) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a14995835d85..a7dc0b096974 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1213,7 +1213,7 @@ static int config_attr(struct perf_event_attr *attr,
 static int get_config_terms(struct list_head *head_config,
 			    struct list_head *head_terms __maybe_unused)
 {
-#define ADD_CONFIG_TERM(__type)					\
+#define ADD_CONFIG_TERM(__type, __weak)				\
 	struct perf_evsel_config_term *__t;			\
 								\
 	__t = zalloc(sizeof(*__t));				\
@@ -1222,18 +1222,18 @@ static int get_config_terms(struct list_head *head_config,
 								\
 	INIT_LIST_HEAD(&__t->list);				\
 	__t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;	\
-	__t->weak	= term->weak;				\
+	__t->weak	= __weak;				\
 	list_add_tail(&__t->list, head_terms)
 
-#define ADD_CONFIG_TERM_VAL(__type, __name, __val)		\
+#define ADD_CONFIG_TERM_VAL(__type, __name, __val, __weak)	\
 do {								\
-	ADD_CONFIG_TERM(__type);				\
+	ADD_CONFIG_TERM(__type, __weak);			\
 	__t->val.__name = __val;				\
 } while (0)
 
-#define ADD_CONFIG_TERM_STR(__type, __val)			\
+#define ADD_CONFIG_TERM_STR(__type, __val, __weak)		\
 do {								\
-	ADD_CONFIG_TERM(__type);				\
+	ADD_CONFIG_TERM(__type, __weak);			\
 	__t->val.str = strdup(__val);				\
 	if (!__t->val.str) {					\
 		zfree(&__t);					\
@@ -1247,62 +1247,62 @@ do {								\
 	list_for_each_entry(term, head_config, list) {
 		switch (term->type_term) {
 		case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
-			ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num);
+			ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
-			ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num);
+			ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_TIME:
-			ADD_CONFIG_TERM_VAL(TIME, time, term->val.num);
+			ADD_CONFIG_TERM_VAL(TIME, time, term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
-			ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str);
+			ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
-			ADD_CONFIG_TERM_STR(BRANCH, term->val.str);
+			ADD_CONFIG_TERM_STR(BRANCH, term->val.str, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 			ADD_CONFIG_TERM_VAL(STACK_USER, stack_user,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_INHERIT:
 			ADD_CONFIG_TERM_VAL(INHERIT, inherit,
-					    term->val.num ? 1 : 0);
+					    term->val.num ? 1 : 0, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 			ADD_CONFIG_TERM_VAL(INHERIT, inherit,
-					    term->val.num ? 0 : 1);
+					    term->val.num ? 0 : 1, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 			ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite,
-					    term->val.num ? 1 : 0);
+					    term->val.num ? 1 : 0, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 			ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite,
-					    term->val.num ? 0 : 1);
+					    term->val.num ? 0 : 1, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
-			ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str);
+			ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_PERCORE:
 			ADD_CONFIG_TERM_VAL(PERCORE, percore,
-					    term->val.num ? true : false);
+					    term->val.num ? true : false, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 			ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output,
-					    term->val.num ? 1 : 0);
+					    term->val.num ? 1 : 0, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
 			ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		default:
 			break;
@@ -1339,7 +1339,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 	}
 
 	if (bits)
-		ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits);
+		ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits, false);
 
 #undef ADD_CONFIG_TERM
 	return 0;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 0f5fda11675f..8c852948513e 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -206,6 +206,9 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
 		} else
 			ret = strlist__add(sl, tev.event);
 		clear_probe_trace_event(&tev);
+		/* Skip if there is same name multi-probe event in the list */
+		if (ret == -EEXIST)
+			ret = 0;
 		if (ret < 0)
 			break;
 	}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1c817add6ca4..e4cff49384f4 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -637,14 +637,19 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 		return -EINVAL;
 	}
 
-	/* Try to get actual symbol name from symtab */
-	symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+	if (dwarf_entrypc(sp_die, &eaddr) == 0) {
+		/* If the DIE has entrypc, use it. */
+		symbol = dwarf_diename(sp_die);
+	} else {
+		/* Try to get actual symbol name and address from symtab */
+		symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+		eaddr = sym.st_value;
+	}
 	if (!symbol) {
 		pr_warning("Failed to find symbol at 0x%lx\n",
 			   (unsigned long)paddr);
 		return -ENOENT;
 	}
-	eaddr = sym.st_value;
 
 	tp->offset = (unsigned long)(paddr - eaddr);
 	tp->address = (unsigned long)paddr;
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index aa344a163eaf..8a065a6f9713 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -2,11 +2,13 @@ from os import getenv
 from subprocess import Popen, PIPE
 from re import sub
 
+cc = getenv("CC")
+cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline()
+
 def clang_has_option(option):
-    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+    return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
 
-cc = getenv("CC")
-if cc == "clang":
+if cc_is_clang:
     from distutils.sysconfig import get_config_vars
     vars = get_config_vars()
     for var in ('CFLAGS', 'OPT'):
@@ -40,7 +42,7 @@ class install_lib(_install_lib):
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
-if cc != "clang":
+if not cc_is_clang:
     cflags += ['-Wno-cast-function-type' ]
 
 src_perf  = getenv('srctree') + '/tools/perf'
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ded7a950dc40..6d2f3a1b2249 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 ifneq ($(O),)
 ifeq ($(origin O), command line)
-	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
-	ABSOLUTE_O := $(shell cd $(O) ; pwd)
+	dummy := $(if $(shell cd $(PWD); test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+	ABSOLUTE_O := $(shell cd $(PWD); cd $(O) ; pwd)
 	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
 ifeq ($(objtree),)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2020-03-02  7:23 Ingo Molnar
@ 2020-03-03 23:35 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2020-03-03 23:35 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, linux-kernel

The pull request you sent on Mon, 2 Mar 2020 08:23:14 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/852fb4a72822b6c03bcf6cf1d51fb05b319d301e

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2020-03-02  7:23 Ingo Molnar
  2020-03-03 23:35 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2020-03-02  7:23 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Arnaldo Carvalho de Melo, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton, linux-kernel

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7977fed974d60a72733243cf54d7955cd6dccd91 Merge tag 'perf-urgent-for-mingo-5.6-20200228' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

No kernel side changes, the rest is tooling fixes plus two tooling 
cleanups that were committed late in the merge window alongside the perf 
annotate fixes, delayed by Arnaldo's European trip.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf arm-spe: Fix endless record after being terminated
      perf auxtrace: Add auxtrace_record__read_finish()

Arnaldo Carvalho de Melo (4):
      perf bpf: Remove bpf/ subdir from bpf.h headers used to build bpf events
      perf arch powerpc: Sync powerpc syscall.tbl with the kernel sources
      tools arch x86: Sync the msr-index.h copy with the kernel sources
      tools headers UAPI: Update tools's copy of kvm.h headers

He Zhe (1):
      perf probe: Check return value of strlist__add() for -ENOMEM

Ravi Bangoria (12):
      perf annotate/tui: Re-render title bar after switching back from script browser
      perf annotate: Fix --show-total-period for tui/stdio2
      perf annotate: Fix --show-nr-samples for tui/stdio2
      perf config: Introduce perf_config_u8()
      perf annotate: Make perf config effective
      perf annotate: Prefer cmdline option over default config
      perf annotate: Fix perf config option description
      perf config: Document missing config options
      perf annotate: Remove privsize from symbol__annotate() args
      perf annotate: Simplify disasm_line allocation and freeing code
      perf annotate: Align struct annotate_args
      perf annotate: Fix segfault with source toggle

Thomas Richter (1):
      perf test: Fix test trace+probe_vfs_getname.sh on s390

Wei Li (3):
      perf intel-pt: Fix endless record after being terminated
      perf intel-bts: Fix endless record after being terminated
      perf cs-etm: Fix endless record after being terminated


 tools/arch/x86/include/asm/msr-index.h             |   2 +
 tools/arch/x86/include/uapi/asm/kvm.h              |   1 +
 tools/perf/Documentation/perf-config.txt           |  74 +++++++-
 tools/perf/arch/arm/util/cs-etm.c                  |  18 +-
 tools/perf/arch/arm64/util/arm-spe.c               |  17 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |   2 +
 tools/perf/arch/x86/util/intel-bts.c               |  17 +-
 tools/perf/arch/x86/util/intel-pt.c                |  17 +-
 tools/perf/builtin-annotate.c                      |   4 +-
 tools/perf/builtin-probe.c                         |   6 +-
 tools/perf/builtin-report.c                        |   2 +-
 tools/perf/builtin-top.c                           |   4 +-
 tools/perf/include/bpf/pid_filter.h                |   2 +-
 tools/perf/include/bpf/stdio.h                     |   2 +-
 tools/perf/include/bpf/unistd.h                    |   2 +-
 tools/perf/tests/shell/lib/probe_vfs_getname.sh    |   2 +-
 tools/perf/ui/browsers/annotate.c                  |  19 +-
 tools/perf/ui/gtk/annotate.c                       |   2 +-
 tools/perf/util/annotate.c                         | 194 ++++++++-------------
 tools/perf/util/annotate.h                         |   9 +-
 tools/perf/util/auxtrace.c                         |  22 ++-
 tools/perf/util/auxtrace.h                         |   6 +
 tools/perf/util/config.c                           |  12 ++
 tools/perf/util/config.h                           |   1 +
 tools/perf/util/probe-file.c                       |  28 ++-
 25 files changed, 251 insertions(+), 214 deletions(-)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index ebe1685e92dd..d5e517d1c3dd 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -512,6 +512,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 503d3f42da16..3f3f780c8c65 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -390,6 +390,7 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index c4dd23c4b478..8ead55593984 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -239,7 +239,6 @@ buildid.*::
 		set buildid.dir to /dev/null. The default is $HOME/.debug
 
 annotate.*::
-	These options work only for TUI.
 	These are in control of addresses, jump function, source code
 	in lines of assembly code from a specific program.
 
@@ -269,6 +268,8 @@ annotate.*::
 		│        mov    (%rdi),%rdx
 		│              return n;
 
+		This option works with tui, stdio2 browsers.
+
         annotate.use_offset::
 		Basing on a first address of a loaded function, offset can be used.
 		Instead of using original addresses of assembly code,
@@ -287,6 +288,8 @@ annotate.*::
 
 		             368:│  mov    0x8(%r14),%rdi
 
+		This option works with tui, stdio2 browsers.
+
 	annotate.jump_arrows::
 		There can be jump instruction among assembly code.
 		Depending on a boolean value of jump_arrows,
@@ -306,6 +309,8 @@ annotate.*::
 		│1330:   mov    %r15,%r10
 		│1333:   cmp    %r15,%r14
 
+		This option works with tui browser.
+
         annotate.show_linenr::
 		When showing source code if this option is 'true',
 		line numbers are printed as below.
@@ -325,6 +330,8 @@ annotate.*::
 		│                     array++;
 		│             }
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_nr_jumps::
 		Let's see a part of assembly code.
 
@@ -335,6 +342,8 @@ annotate.*::
 
 		│1 1382:   movb   $0x1,-0x270(%rbp)
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_total_period::
 		To compare two records on an instruction base, with this option
 		provided, display total number of samples that belong to a line
@@ -348,11 +357,30 @@ annotate.*::
 
 		99.93 │      mov    %eax,%eax
 
+		This option works with tui, stdio2, stdio browsers.
+
+	annotate.show_nr_samples::
+		By default perf annotate shows percentage of samples. This option
+		can be used to print absolute number of samples. Ex, when set as
+		false:
+
+		Percent│
+		 74.03 │      mov    %fs:0x28,%rax
+
+		When set as true:
+
+		Samples│
+		     6 │      mov    %fs:0x28,%rax
+
+		This option works with tui, stdio2, stdio browsers.
+
 	annotate.offset_level::
 		Default is '1', meaning just jump targets will have offsets show right beside
 		the instruction. When set to '2' 'call' instructions will also have its offsets
 		shown, 3 or higher will show offsets for all instructions.
 
+		This option works with tui, stdio2 browsers.
+
 hist.*::
 	hist.percentage::
 		This option control the way to calculate overhead of filtered entries -
@@ -490,6 +518,12 @@ top.*::
 		column by default.
 		The default is 'true'.
 
+	top.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'top' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf top' to actually use it,
+		the command line option -g must be specified.
+
 man.*::
 	man.viewer::
 		This option can assign a tool to view manual pages when 'help'
@@ -517,6 +551,16 @@ record.*::
 		But if this option is 'no-cache', it will not update the build-id cache.
 		'skip' skips post-processing and does not update the cache.
 
+	record.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'record' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf record' to actually use it,
+		the command line option -g must be specified.
+
+	record.aio::
+		Use 'n' control blocks in asynchronous (Posix AIO) trace writing
+		mode ('n' default: 1, max: 4).
+
 diff.*::
 	diff.order::
 		This option sets the number of columns to sort the result.
@@ -566,6 +610,11 @@ trace.*::
 		"libbeauty", the default, to use the same argument beautifiers used in the
 		strace-like sys_enter+sys_exit lines.
 
+ftrace.*::
+	ftrace.tracer::
+		Can be used to select the default tracer. Possible values are
+		'function' and 'function_graph'.
+
 llvm.*::
 	llvm.clang-path::
 		Path to clang. If omit, search it from $PATH.
@@ -610,6 +659,29 @@ scripts.*::
 	The script gets the same options passed as a full perf script,
 	in particular -i perfdata file, --cpu, --tid
 
+convert.*::
+
+	convert.queue-size::
+		Limit the size of ordered_events queue, so we could control
+		allocation size of perf data files without proper finished
+		round events.
+
+intel-pt.*::
+
+	intel-pt.cache-divisor::
+
+	intel-pt.mispred-all::
+		If set, Intel PT decoder will set the mispred flag on all
+		branches.
+
+auxtrace.*::
+
+	auxtrace.dumpdir::
+		s390 only. The directory to save the auxiliary trace buffer
+		can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
+		If the directory does not exist or has the wrong file type,
+		the current directory is used.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2898cfdf8fe1..941f814820b8 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 	free(ptr);
 }
 
-static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct cs_etm_recording *ptr =
-			container_of(itr, struct cs_etm_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist,
-							     evsel, idx);
-	}
-
-	return -EINVAL;
-}
-
 struct auxtrace_record *cs_etm_record_init(int *err)
 {
 	struct perf_pmu *cs_etm_pmu;
@@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	}
 
 	ptr->cs_etm_pmu			= cs_etm_pmu;
+	ptr->itr.pmu			= cs_etm_pmu;
 	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
 	ptr->itr.recording_options	= cs_etm_recording_options;
 	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
@@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
 	ptr->itr.reference		= cs_etm_reference;
 	ptr->itr.free			= cs_etm_recording_free;
-	ptr->itr.read_finish		= cs_etm_read_finish;
+	ptr->itr.read_finish		= auxtrace_record__read_finish;
 
 	*err = 0;
 	return &ptr->itr;
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index eba6541ec0f1..8d6821d9c3f6 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
 	free(sper);
 }
 
-static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct arm_spe_recording *sper =
-			container_of(itr, struct arm_spe_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(sper->evlist, evsel) {
-		if (evsel->core.attr.type == sper->arm_spe_pmu->type)
-			return perf_evlist__enable_event_idx(sper->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *arm_spe_recording_init(int *err,
 					       struct perf_pmu *arm_spe_pmu)
 {
@@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	}
 
 	sper->arm_spe_pmu = arm_spe_pmu;
+	sper->itr.pmu = arm_spe_pmu;
 	sper->itr.recording_options = arm_spe_recording_options;
 	sper->itr.info_priv_size = arm_spe_info_priv_size;
 	sper->itr.info_fill = arm_spe_info_fill;
 	sper->itr.free = arm_spe_recording_free;
 	sper->itr.reference = arm_spe_reference;
-	sper->itr.read_finish = arm_spe_read_finish;
+	sper->itr.read_finish = auxtrace_record__read_finish;
 	sper->itr.alignment = 0;
 
 	*err = 0;
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 43f736ed47f2..35b61bfc1b1a 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -517,3 +517,5 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
+437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 27d9e214d068..26cee1052179 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -413,20 +413,6 @@ static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
 	return err;
 }
 
-static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_bts_recording *btsr =
-			container_of(itr, struct intel_bts_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(btsr->evlist, evsel) {
-		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
-			return perf_evlist__enable_event_idx(btsr->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_bts_recording_init(int *err)
 {
 	struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
@@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	}
 
 	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.pmu = intel_bts_pmu;
 	btsr->itr.recording_options = intel_bts_recording_options;
 	btsr->itr.info_priv_size = intel_bts_info_priv_size;
 	btsr->itr.info_fill = intel_bts_info_fill;
@@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	btsr->itr.find_snapshot = intel_bts_find_snapshot;
 	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
 	btsr->itr.reference = intel_bts_reference;
-	btsr->itr.read_finish = intel_bts_read_finish;
+	btsr->itr.read_finish = auxtrace_record__read_finish;
 	btsr->itr.alignment = sizeof(struct branch);
 	return &btsr->itr;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 20df442fdf36..7eea4fd7ce58 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
-static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_pt_recording *ptr =
-			container_of(itr, struct intel_pt_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->intel_pt_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
-							     idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
@@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	}
 
 	ptr->intel_pt_pmu = intel_pt_pmu;
+	ptr->itr.pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
 	ptr->itr.info_fill = intel_pt_info_fill;
@@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	ptr->itr.find_snapshot = intel_pt_find_snapshot;
 	ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
 	ptr->itr.reference = intel_pt_reference;
-	ptr->itr.read_finish = intel_pt_read_finish;
+	ptr->itr.read_finish = auxtrace_record__read_finish;
 	/*
 	 * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
 	 * should give at least 1 PSB per sample.
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ff61795a4d13..6c0a0412502e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		return ret;
 
+	annotation_config__init(&annotate.opts);
+
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
 		/*
@@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		goto out_delete;
 
-	annotation_config__init();
-
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 26bc5923e6b5..70548df2abb9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret = probe_file__del_strlist(kfd, klist);
 		if (ret < 0)
 			goto error;
-	}
+	} else if (ret == -ENOMEM)
+		goto error;
 
 	ret2 = probe_file__get_events(ufd, filter, ulist);
 	if (ret2 == 0) {
@@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret2 = probe_file__del_strlist(ufd, ulist);
 		if (ret2 < 0)
 			goto error;
-	}
+	} else if (ret2 == -ENOMEM)
+		goto error;
 
 	if (ret == -ENOENT && ret2 == -ENOENT)
 		pr_warning("\"%s\" does not hit any event.\n", str);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9483b3f0cae3..72a12b69f120 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1507,7 +1507,7 @@ int cmd_report(int argc, const char **argv)
 			symbol_conf.priv_size += sizeof(u32);
 			symbol_conf.sort_by_name = true;
 		}
-		annotation_config__init();
+		annotation_config__init(&report.annotation_opts);
 	}
 
 	if (symbol__init(&session->header.env) < 0)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8affcab75604..f6dd1a63f159 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -143,7 +143,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL);
+	err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
 	if (err == 0) {
 		top->sym_filter_entry = he;
 	} else {
@@ -1683,7 +1683,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
-	annotation_config__init();
+	annotation_config__init(&top.annotation_opts);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	status = symbol__init(NULL);
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 607189a315b2..6e61c4bdf548 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
 #ifndef _PERF_BPF_PID_FILTER_
 #define _PERF_BPF_PID_FILTER_
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 #define pid_filter(name) pid_map(name, bool)
 
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 7ca6fa5463ee..316af5b2ff35 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 struct bpf_map SEC("maps") __bpf_stdout__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index d1a35b6c649d..ca7877f9a976 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
 
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 7cb99b433888..c2cc42daf924 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -14,7 +14,7 @@ add_probe_vfs_getname() {
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
 		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
 	fi
 }
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index badbddbb30f8..9023267e5643 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -754,10 +754,9 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"?             Search string backwards\n");
 			continue;
 		case 'r':
-			{
-				script_browse(NULL, NULL);
-				continue;
-			}
+			script_browse(NULL, NULL);
+			annotate_browser__show(&browser->b, title, help);
+			continue;
 		case 'k':
 			notes->options->show_linenr = !notes->options->show_linenr;
 			break;
@@ -834,13 +833,13 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			map_symbol__annotation_dump(ms, evsel, browser->opts);
 			continue;
 		case 't':
-			if (notes->options->show_total_period) {
-				notes->options->show_total_period = false;
-				notes->options->show_nr_samples = true;
-			} else if (notes->options->show_nr_samples)
-				notes->options->show_nr_samples = false;
+			if (symbol_conf.show_total_period) {
+				symbol_conf.show_total_period = false;
+				symbol_conf.show_nr_samples = true;
+			} else if (symbol_conf.show_nr_samples)
+				symbol_conf.show_nr_samples = false;
 			else
-				notes->options->show_total_period = true;
+				symbol_conf.show_total_period = true;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'c':
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 22cc240f7371..35f9641bf670 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -174,7 +174,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (ms->map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL);
+	err = symbol__annotate(ms, evsel, &annotation__default_options, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ca73fb74ad03..0ea95be84b3b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1143,93 +1143,70 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 }
 
 struct annotate_args {
-	size_t			 privsize;
-	struct arch		*arch;
-	struct map_symbol	 ms;
-	struct evsel	*evsel;
+	struct arch		  *arch;
+	struct map_symbol	  ms;
+	struct evsel		  *evsel;
 	struct annotation_options *options;
-	s64			 offset;
-	char			*line;
-	int			 line_nr;
+	s64			  offset;
+	char			  *line;
+	int			  line_nr;
 };
 
-static void annotation_line__delete(struct annotation_line *al)
+static void annotation_line__init(struct annotation_line *al,
+				  struct annotate_args *args,
+				  int nr)
 {
-	void *ptr = (void *) al - al->privsize;
+	al->offset = args->offset;
+	al->line = strdup(args->line);
+	al->line_nr = args->line_nr;
+	al->data_nr = nr;
+}
 
+static void annotation_line__exit(struct annotation_line *al)
+{
 	free_srcline(al->path);
 	zfree(&al->line);
-	free(ptr);
 }
 
-/*
- * Allocating the annotation line data with following
- * structure:
- *
- *    --------------------------------------
- *    private space | struct annotation_line
- *    --------------------------------------
- *
- * Size of the private space is stored in 'struct annotation_line'.
- *
- */
-static struct annotation_line *
-annotation_line__new(struct annotate_args *args, size_t privsize)
+static size_t disasm_line_size(int nr)
 {
 	struct annotation_line *al;
-	struct evsel *evsel = args->evsel;
-	size_t size = privsize + sizeof(*al);
-	int nr = 1;
-
-	if (perf_evsel__is_group_event(evsel))
-		nr = evsel->core.nr_members;
 
-	size += sizeof(al->data[0]) * nr;
-
-	al = zalloc(size);
-	if (al) {
-		al = (void *) al + privsize;
-		al->privsize   = privsize;
-		al->offset     = args->offset;
-		al->line       = strdup(args->line);
-		al->line_nr    = args->line_nr;
-		al->data_nr    = nr;
-	}
-
-	return al;
+	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
 }
 
 /*
  * Allocating the disasm annotation line data with
  * following structure:
  *
- *    ------------------------------------------------------------
- *    privsize space | struct disasm_line | struct annotation_line
- *    ------------------------------------------------------------
+ *    -------------------------------------------
+ *    struct disasm_line | struct annotation_line
+ *    -------------------------------------------
  *
  * We have 'struct annotation_line' member as last member
  * of 'struct disasm_line' to have an easy access.
- *
  */
 static struct disasm_line *disasm_line__new(struct annotate_args *args)
 {
 	struct disasm_line *dl = NULL;
-	struct annotation_line *al;
-	size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+	int nr = 1;
 
-	al = annotation_line__new(args, privsize);
-	if (al != NULL) {
-		dl = disasm_line(al);
+	if (perf_evsel__is_group_event(args->evsel))
+		nr = args->evsel->core.nr_members;
 
-		if (dl->al.line == NULL)
-			goto out_delete;
+	dl = zalloc(disasm_line_size(nr));
+	if (!dl)
+		return NULL;
 
-		if (args->offset != -1) {
-			if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
-				goto out_free_line;
+	annotation_line__init(&dl->al, args, nr);
+	if (dl->al.line == NULL)
+		goto out_delete;
 
-			disasm_line__init_ins(dl, args->arch, &args->ms);
-		}
+	if (args->offset != -1) {
+		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+			goto out_free_line;
+
+		disasm_line__init_ins(dl, args->arch, &args->ms);
 	}
 
 	return dl;
@@ -1248,7 +1225,8 @@ void disasm_line__free(struct disasm_line *dl)
 	else
 		ins__delete(&dl->ops);
 	zfree(&dl->ins.name);
-	annotation_line__delete(&dl->al);
+	annotation_line__exit(&dl->al);
+	free(dl);
 }
 
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
@@ -2149,13 +2127,12 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize,
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 		     struct annotation_options *options, struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
-		.privsize	= privsize,
 		.evsel		= evsel,
 		.options	= options,
 	};
@@ -2644,6 +2621,8 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
 	struct annotation_line *al;
 
 	notes->max_line_len = 0;
+	notes->nr_entries = 0;
+	notes->nr_asm_entries = 0;
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		size_t line_len = strlen(al->line);
@@ -2790,7 +2769,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
 	struct symbol *sym = ms->sym;
 	struct rb_root source_line = RB_ROOT;
 
-	if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0)
+	if (symbol__annotate(ms, evsel, opts, NULL) < 0)
 		return -1;
 
 	symbol__calc_percent(sym, evsel);
@@ -2915,9 +2894,9 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			percent = annotation_data__percent(&al->data[i], percent_type);
 
 			obj__set_percent_color(obj, percent, current_entry);
-			if (notes->options->show_total_period) {
+			if (symbol_conf.show_total_period) {
 				obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
-			} else if (notes->options->show_nr_samples) {
+			} else if (symbol_conf.show_nr_samples) {
 				obj__printf(obj, "%6" PRIu64 " ",
 						   al->data[i].he.nr_samples);
 			} else {
@@ -2931,8 +2910,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			obj__printf(obj, "%-*s", pcnt_width, " ");
 		else {
 			obj__printf(obj, "%-*s", pcnt_width,
-					   notes->options->show_total_period ? "Period" :
-					   notes->options->show_nr_samples ? "Samples" : "Percent");
+					   symbol_conf.show_total_period ? "Period" :
+					   symbol_conf.show_nr_samples ? "Samples" : "Percent");
 		}
 	}
 
@@ -3070,7 +3049,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
-	err = symbol__annotate(ms, evsel, 0, options, parch);
+	err = symbol__annotate(ms, evsel, options, parch);
 	if (err)
 		goto out_free_offsets;
 
@@ -3094,69 +3073,46 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	return err;
 }
 
-#define ANNOTATION__CFG(n) \
-	{ .name = #n, .value = &annotation__default_options.n, }
-
-/*
- * Keep the entries sorted, they are bsearch'ed
- */
-static struct annotation_config {
-	const char *name;
-	void *value;
-} annotation__configs[] = {
-	ANNOTATION__CFG(hide_src_code),
-	ANNOTATION__CFG(jump_arrows),
-	ANNOTATION__CFG(offset_level),
-	ANNOTATION__CFG(show_linenr),
-	ANNOTATION__CFG(show_nr_jumps),
-	ANNOTATION__CFG(show_nr_samples),
-	ANNOTATION__CFG(show_total_period),
-	ANNOTATION__CFG(use_offset),
-};
-
-#undef ANNOTATION__CFG
-
-static int annotation_config__cmp(const void *name, const void *cfgp)
-{
-	const struct annotation_config *cfg = cfgp;
-
-	return strcmp(name, cfg->name);
-}
-
-static int annotation__config(const char *var, const char *value,
-			    void *data __maybe_unused)
+static int annotation__config(const char *var, const char *value, void *data)
 {
-	struct annotation_config *cfg;
-	const char *name;
+	struct annotation_options *opt = data;
 
 	if (!strstarts(var, "annotate."))
 		return 0;
 
-	name = var + 9;
-	cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs),
-		      sizeof(struct annotation_config), annotation_config__cmp);
-
-	if (cfg == NULL)
-		pr_debug("%s variable unknown, ignoring...", var);
-	else if (strcmp(var, "annotate.offset_level") == 0) {
-		perf_config_int(cfg->value, name, value);
-
-		if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
-			*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
-		else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
-			*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+	if (!strcmp(var, "annotate.offset_level")) {
+		perf_config_u8(&opt->offset_level, "offset_level", value);
+
+		if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+			opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
+		else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
+			opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else if (!strcmp(var, "annotate.hide_src_code")) {
+		opt->hide_src_code = perf_config_bool("hide_src_code", value);
+	} else if (!strcmp(var, "annotate.jump_arrows")) {
+		opt->jump_arrows = perf_config_bool("jump_arrows", value);
+	} else if (!strcmp(var, "annotate.show_linenr")) {
+		opt->show_linenr = perf_config_bool("show_linenr", value);
+	} else if (!strcmp(var, "annotate.show_nr_jumps")) {
+		opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value);
+	} else if (!strcmp(var, "annotate.show_nr_samples")) {
+		symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples",
+								value);
+	} else if (!strcmp(var, "annotate.show_total_period")) {
+		symbol_conf.show_total_period = perf_config_bool("show_total_period",
+								value);
+	} else if (!strcmp(var, "annotate.use_offset")) {
+		opt->use_offset = perf_config_bool("use_offset", value);
 	} else {
-		*(bool *)cfg->value = perf_config_bool(name, value);
+		pr_debug("%s variable unknown, ignoring...", var);
 	}
+
 	return 0;
 }
 
-void annotation_config__init(void)
+void annotation_config__init(struct annotation_options *opt)
 {
-	perf_config(annotation__config, NULL);
-
-	annotation__default_options.show_total_period = symbol_conf.show_total_period;
-	annotation__default_options.show_nr_samples   = symbol_conf.show_nr_samples;
+	perf_config(annotation__config, opt);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 455403e8fede..001258601a37 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -83,8 +83,6 @@ struct annotation_options {
 	     full_path,
 	     show_linenr,
 	     show_nr_jumps,
-	     show_nr_samples,
-	     show_total_period,
 	     show_minmax_cycle,
 	     show_asm_raw,
 	     annotate_src;
@@ -141,7 +139,6 @@ struct annotation_line {
 	u64			 cycles;
 	u64			 cycles_max;
 	u64			 cycles_min;
-	size_t			 privsize;
 	char			*path;
 	u32			 idx;
 	int			 idx_asm;
@@ -309,7 +306,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
 
 static inline int annotation__pcnt_width(struct annotation *notes)
 {
-	return (notes->options->show_total_period ? 12 : 7) * notes->nr_events;
+	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
 }
 
 static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
@@ -352,7 +349,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct map_symbol *ms,
-		     struct evsel *evsel, size_t privsize,
+		     struct evsel *evsel,
 		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct map_symbol *ms,
@@ -413,7 +410,7 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 }
 #endif
 
-void annotation_config__init(void);
+void annotation_config__init(struct annotation_options *opt);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index eb087e7df6f4..3571ce72ca28 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -629,8 +629,10 @@ int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct evlist *evlist,
 			     struct record_opts *opts)
 {
-	if (itr)
+	if (itr) {
+		itr->evlist = evlist;
 		return itr->recording_options(itr, evlist, opts);
+	}
 	return 0;
 }
 
@@ -664,6 +666,24 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 	return -EINVAL;
 }
 
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct evsel *evsel;
+
+	if (!itr->evlist || !itr->pmu)
+		return -EINVAL;
+
+	evlist__for_each_entry(itr->evlist, evsel) {
+		if (evsel->core.attr.type == itr->pmu->type) {
+			if (evsel->disabled)
+				return 0;
+			return perf_evlist__enable_event_idx(itr->evlist, evsel,
+							     idx);
+		}
+	}
+	return -EINVAL;
+}
+
 /*
  * Event record size is 16-bit which results in a maximum size of about 64KiB.
  * Allow about 4KiB for the rest of the sample record, to give a maximum
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 749d72cd9c7b..e58ef160b599 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -29,6 +29,7 @@ struct record_opts;
 struct perf_record_auxtrace_error;
 struct perf_record_auxtrace_info;
 struct events_stats;
+struct perf_pmu;
 
 enum auxtrace_error_type {
        PERF_AUXTRACE_ERROR_ITRACE  = 1,
@@ -322,6 +323,8 @@ struct auxtrace_mmap_params {
  * @read_finish: called after reading from an auxtrace mmap
  * @alignment: alignment (if any) for AUX area data
  * @default_aux_sample_size: default sample size for --aux sample option
+ * @pmu: associated pmu
+ * @evlist: selected events list
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
@@ -346,6 +349,8 @@ struct auxtrace_record {
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
 	unsigned int alignment;
 	unsigned int default_aux_sample_size;
+	struct perf_pmu *pmu;
+	struct evlist *evlist;
 };
 
 /**
@@ -537,6 +542,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
 				   struct auxtrace_mmap *mm,
 				   unsigned char *data, u64 *head, u64 *old);
 u64 auxtrace_record__reference(struct auxtrace_record *itr);
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx);
 
 int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
 				   off_t file_offset);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0bc9c4d7fdc5..ef38eba56ed0 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -374,6 +374,18 @@ int perf_config_int(int *dest, const char *name, const char *value)
 	return 0;
 }
 
+int perf_config_u8(u8 *dest, const char *name, const char *value)
+{
+	long ret = 0;
+
+	if (!perf_parse_long(value, &ret)) {
+		bad_config(name);
+		return -1;
+	}
+	*dest = ret;
+	return 0;
+}
+
 static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
 {
 	int ret;
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index bd0a5897c76a..c10b66dde2f3 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -29,6 +29,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 int perf_default_config(const char *, const char *, void *);
 int perf_config(config_fn_t fn, void *);
 int perf_config_int(int *dest, const char *, const char *);
+int perf_config_u8(u8 *dest, const char *name, const char *value);
 int perf_config_u64(u64 *dest, const char *, const char *);
 int perf_config_bool(const char *, const char *);
 int config_error_nonbool(const char *);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 5003ba403345..0f5fda11675f 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -301,10 +301,15 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
-			strlist__add(plist, ent->s);
+			ret = strlist__add(plist, ent->s);
+			if (ret == -ENOMEM) {
+				pr_err("strlist__add failed with -ENOMEM\n");
+				goto out;
+			}
 			ret = 0;
 		}
 	}
+out:
 	strlist__delete(namelist);
 
 	return ret;
@@ -511,7 +516,11 @@ static int probe_cache__load(struct probe_cache *pcache)
 				ret = -EINVAL;
 				goto out;
 			}
-			strlist__add(entry->tevlist, buf);
+			ret = strlist__add(entry->tevlist, buf);
+			if (ret == -ENOMEM) {
+				pr_err("strlist__add failed with -ENOMEM\n");
+				goto out;
+			}
 		}
 	}
 out:
@@ -672,7 +681,12 @@ int probe_cache__add_entry(struct probe_cache *pcache,
 		command = synthesize_probe_trace_command(&tevs[i]);
 		if (!command)
 			goto out_err;
-		strlist__add(entry->tevlist, command);
+		ret = strlist__add(entry->tevlist, command);
+		if (ret == -ENOMEM) {
+			pr_err("strlist__add failed with -ENOMEM\n");
+			goto out_err;
+		}
+
 		free(command);
 	}
 	list_add_tail(&entry->node, &pcache->entries);
@@ -853,9 +867,15 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 			break;
 		}
 
-		strlist__add(entry->tevlist, buf);
+		ret = strlist__add(entry->tevlist, buf);
+
 		free(buf);
 		entry = NULL;
+
+		if (ret == -ENOMEM) {
+			pr_err("strlist__add failed with -ENOMEM\n");
+			break;
+		}
 	}
 	if (entry) {
 		list_del_init(&entry->node);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2020-02-15  8:53 Ingo Molnar
@ 2020-02-15 21:25 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2020-02-15 21:25 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
	Andrew Morton

The pull request you sent on Sat, 15 Feb 2020 09:53:16 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/da99f9355b53ebc565747d0072ff038f3d9fa875

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2020-02-15  8:53 Ingo Molnar
  2020-02-15 21:25 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2020-02-15  8:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: dfb9b69e3b84791e4c6b954ac3cc0c4a545484f2 Merge tag 'perf-urgent-for-mingo-5.6-20200214' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Contains the following fixes and HW enablement patches:

 - Tooling fixes, most of which are tooling header synchronization with v5.6 changes

 - Fix kprobes fallout on ARM

 - Add Intel Elkhart Lake support and extend Tremont support, these are 
   relatively simple and should only affect those models

 - Fix the AMD family 17h generic event table

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (15):
      tools include UAPI: Sync x86's syscalls_64.tbl, generic unistd.h and fcntl.h to pick up openat2 and pidfd_getfd
      tools headers UAPI: Sync copy of arm64's asm/unistd.h with the kernel sources
      tools headers UAPI: Sync prctl.h with the kernel sources
      perf beauty prctl: Export the 'options' strarray
      perf trace: Resolve prctl's 'option' arg strings to numbers
      tools headers UAPI: Sync sched.h with the kernel
      tools headers uapi: Sync linux/fscrypt.h with the kernel sources
      tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
      tools headers UAPI: Sync asm-generic/mman-common.h with the kernel
      tools include UAPI: Sync sound/asound.h copy
      tools headers x86: Sync disabled-features.h
      tools arch x86: Sync asm/cpufeatures.h with the kernel sources
      tools headers kvm: Sync kvm headers with the kernel sources
      tools headers kvm: Sync linux/kvm.h with the kernel sources
      perf llvm: Fix script used to obtain kernel make directives to work with new kbuild

Jiri Olsa (4):
      perf maps: Mark module DSOs with kernel type
      perf maps: Mark ksymbol DSOs with kernel type
      perf maps: Fix map__clone() for struct kmap
      perf maps: Move kmap::kmaps setup to maps__insert()

John Garry (1):
      perf tools: Add arm64 version of get_cpuid()

Kan Liang (4):
      perf/x86/intel: Add Elkhart Lake support
      perf/x86/cstate: Add Tremont support
      perf/x86/msr: Add Tremont support
      perf/x86/intel: Fix inaccurate period in context switch for auto-reload

Kim Phillips (4):
      perf stat: Don't report a null stalled cycles per insn metric
      perf symbols: Update the list of kernel idle symbols
      perf symbols: Convert symbol__is_idle() to use strlist
      perf/x86/amd: Add missing L2 misses event spec to AMD Family 17h's event map

Peter Zijlstra (2):
      arm/ftrace: Fix BE text poking
      arm/patch: Fix !MMU compile


 arch/arm/kernel/ftrace.c                          |   7 +-
 arch/arm/kernel/patch.c                           |  19 ++-
 arch/x86/events/amd/core.c                        |   1 +
 arch/x86/events/intel/core.c                      |   1 +
 arch/x86/events/intel/cstate.c                    |  22 +--
 arch/x86/events/intel/ds.c                        |   2 +
 arch/x86/events/msr.c                             |   3 +-
 tools/arch/arm64/include/uapi/asm/kvm.h           |  12 +-
 tools/arch/arm64/include/uapi/asm/unistd.h        |   1 +
 tools/arch/x86/include/asm/cpufeatures.h          |   2 +
 tools/arch/x86/include/asm/disabled-features.h    |   8 +-
 tools/include/uapi/asm-generic/mman-common.h      |   2 +
 tools/include/uapi/asm-generic/unistd.h           |   7 +-
 tools/include/uapi/drm/i915_drm.h                 |  32 +++++
 tools/include/uapi/linux/fcntl.h                  |   2 +-
 tools/include/uapi/linux/fscrypt.h                |  14 +-
 tools/include/uapi/linux/kvm.h                    |   5 +
 tools/include/uapi/linux/openat2.h                |  39 ++++++
 tools/include/uapi/linux/prctl.h                  |   4 +
 tools/include/uapi/linux/sched.h                  |   6 +
 tools/include/uapi/sound/asound.h                 | 155 ++++++++++++++++++----
 tools/perf/arch/arm64/util/header.c               |  63 ++++++---
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl |   2 +
 tools/perf/builtin-trace.c                        |   4 +-
 tools/perf/check-headers.sh                       |   1 +
 tools/perf/trace/beauty/beauty.h                  |   2 +
 tools/perf/trace/beauty/prctl.c                   |   3 +-
 tools/perf/util/llvm-utils.c                      |   1 +
 tools/perf/util/machine.c                         |  26 ++--
 tools/perf/util/map.c                             |  17 ++-
 tools/perf/util/stat-shadow.c                     |   6 -
 tools/perf/util/symbol.c                          |  17 ++-
 32 files changed, 383 insertions(+), 103 deletions(-)
 create mode 100644 tools/include/uapi/linux/openat2.h

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 2a5ff69c28e6..10499d44964a 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -78,13 +78,10 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 {
 	unsigned long replaced;
 
-	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
 		old = __opcode_to_mem_thumb32(old);
-		new = __opcode_to_mem_thumb32(new);
-	} else {
+	else
 		old = __opcode_to_mem_arm(old);
-		new = __opcode_to_mem_arm(new);
-	}
 
 	if (validate) {
 		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index d0a05a3bdb96..e9e828b6bb30 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,10 +16,10 @@ struct patch {
 	unsigned int insn;
 };
 
+#ifdef CONFIG_MMU
 static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
-	__acquires(&patch_lock)
 {
 	unsigned int uintaddr = (uintptr_t) addr;
 	bool module = !core_kernel_text(uintaddr);
@@ -34,8 +34,6 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 
 	if (flags)
 		raw_spin_lock_irqsave(&patch_lock, *flags);
-	else
-		__acquire(&patch_lock);
 
 	set_fixmap(fixmap, page_to_phys(page));
 
@@ -43,15 +41,19 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 }
 
 static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
-	__releases(&patch_lock)
 {
 	clear_fixmap(fixmap);
 
 	if (flags)
 		raw_spin_unlock_irqrestore(&patch_lock, *flags);
-	else
-		__release(&patch_lock);
 }
+#else
+static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
+{
+	return addr;
+}
+static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { }
+#endif
 
 void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 {
@@ -64,8 +66,6 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 
 	if (remap)
 		waddr = patch_map(addr, FIX_TEXT_POKE0, &flags);
-	else
-		__acquire(&patch_lock);
 
 	if (thumb2 && __opcode_is_thumb16(insn)) {
 		*(u16 *)waddr = __opcode_to_mem_thumb16(insn);
@@ -102,8 +102,7 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 	if (waddr != addr) {
 		flush_kernel_vmap_range(waddr, twopage ? size / 2 : size);
 		patch_unmap(FIX_TEXT_POKE0, &flags);
-	} else
-		__release(&patch_lock);
+	}
 
 	flush_icache_range((uintptr_t)(addr),
 			   (uintptr_t)(addr) + size);
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1f22b6bbda68..39eb276d0277 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,6 +250,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
 	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3be51aa06e67..dff6623804c2 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4765,6 +4765,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e1daf4151e11..4814c964692c 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,17 +40,18 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT,GLM,CNL
+ *			 Available model: SLM,AMT,GLM,CNL,TNT
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
- *						CNL,KBL,CML
+ *						CNL,KBL,CML,TNT
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -60,17 +61,18 @@
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL,TGL
+ *						KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL,KBL,CML,ICL,TGL
+ *						GLM,CNL,KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -87,7 +89,8 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *
  */
@@ -640,8 +643,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT,   glm_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
-
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4b94ae4ae369..dc43cc124e09 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1714,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	old = ((s64)(prev_raw_count << shift) >> shift);
 	local64_add(new - old + count * period, &event->count);
 
+	local64_set(&hwc->period_left, -new);
+
 	perf_event_update_userpage(event);
 
 	return 0;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 6f86650b3f77..a949f6f55991 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data)
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:
-
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 820e5751ada7..ba85bb23f060 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -220,10 +220,18 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
 #define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
 
-/* EL0 Virtual Timer Registers */
+/*
+ * EL0 Virtual Timer Registers
+ *
+ * WARNING:
+ *      KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined
+ *      with the appropriate register encodings.  Their values have been
+ *      accidentally swapped.  As this is set API, the definitions here
+ *      must be used, rather than ones derived from the encodings.
+ */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 
 /* KVM-as-firmware specific pseudo-registers */
 #define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 4703d218663a..f83a70e07df8 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
 
 #include <asm-generic/unistd.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index e9b62498fe75..f3327cb56edf 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -220,6 +220,7 @@
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
+#define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -357,6 +358,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM		(18*32+ 4) /* Fast Short Rep Mov */
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 8e1d0bb46361..4ea8584682f9 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
  * cpu_feature_enabled().
  */
 
-#ifdef CONFIG_X86_INTEL_MPX
-# define DISABLE_MPX	0
-#else
-# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
-#endif
-
 #ifdef CONFIG_X86_SMAP
 # define DISABLE_SMAP	0
 #else
@@ -74,7 +68,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
+#define DISABLED_MASK9	(DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index c160a5354eb6..f94f65d429be 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -11,6 +11,8 @@
 #define PROT_WRITE	0x2		/* page can be written */
 #define PROT_EXEC	0x4		/* page can be executed */
 #define PROT_SEM	0x8		/* page may be used for atomic ops */
+/*			0x10		   reserved for arch-specific use */
+/*			0x20		   reserved for arch-specific use */
 #define PROT_NONE	0x0		/* page can not be accessed */
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 1fc8faa6e973..3a3201e4618e 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -851,8 +851,13 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 __SYSCALL(__NR_clone3, sys_clone3)
 #endif
 
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+
 #undef __NR_syscalls
-#define __NR_syscalls 436
+#define __NR_syscalls 439
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 5400d7e057f1..829c0a48577f 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -395,6 +395,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
 #define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
 #define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
 #define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
 #define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
 #define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
@@ -793,6 +794,37 @@ struct drm_i915_gem_mmap_gtt {
 	__u64 offset;
 };
 
+struct drm_i915_gem_mmap_offset {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/**
+	 * Fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+
+	/**
+	 * Flags for extended behaviour.
+	 *
+	 * It is mandatory that one of the MMAP_OFFSET types
+	 * (GTT, WC, WB, UC, etc) should be included.
+	 */
+	__u64 flags;
+#define I915_MMAP_OFFSET_GTT 0
+#define I915_MMAP_OFFSET_WC  1
+#define I915_MMAP_OFFSET_WB  2
+#define I915_MMAP_OFFSET_UC  3
+
+	/*
+	 * Zero-terminated chain of extensions.
+	 *
+	 * No current extensions defined; mbz.
+	 */
+	__u64 extensions;
+};
+
 struct drm_i915_gem_set_domain {
 	/** Handle for the object */
 	__u32 handle;
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 1f97b33c840e..ca88b7bce553 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -3,6 +3,7 @@
 #define _UAPI_LINUX_FCNTL_H
 
 #include <asm/fcntl.h>
+#include <linux/openat2.h>
 
 #define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
 #define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
@@ -100,5 +101,4 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
-
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 1beb174ad950..0d8a6f47711c 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -8,6 +8,7 @@
 #ifndef _UAPI_LINUX_FSCRYPT_H
 #define _UAPI_LINUX_FSCRYPT_H
 
+#include <linux/ioctl.h>
 #include <linux/types.h>
 
 /* Encryption policy flags */
@@ -109,11 +110,22 @@ struct fscrypt_key_specifier {
 	} u;
 };
 
+/*
+ * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by
+ * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw.
+ */
+struct fscrypt_provisioning_key_payload {
+	__u32 type;
+	__u32 __reserved;
+	__u8 raw[];
+};
+
 /* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
 struct fscrypt_add_key_arg {
 	struct fscrypt_key_specifier key_spec;
 	__u32 raw_size;
-	__u32 __reserved[9];
+	__u32 key_id;
+	__u32 __reserved[8];
 	__u8 raw[];
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f0a16b4adbbd..4b95f9a31a2f 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1473,6 +1474,10 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_ARM_SVE */
 #define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
 
+/* Available with  KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
+#define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
new file mode 100644
index 000000000000..58b1eb711360
--- /dev/null
+++ b/tools/include/uapi/linux/openat2.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_OPENAT2_H
+#define _UAPI_LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+	__u64 flags;
+	__u64 mode;
+	__u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+
+#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 7da1b37b27aa..07b4f8131e36 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -234,4 +234,8 @@ struct prctl_mm_map {
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
 
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER		57
+#define PR_GET_IO_FLUSHER		58
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 4a0217832464..2e3bc22c6f20 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -36,6 +36,12 @@
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
 
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME	0x00000080	/* New time namespace */
+
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index df1153cea0b7..535a7229e1d9 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -26,7 +26,9 @@
 
 #if defined(__KERNEL__) || defined(__linux__)
 #include <linux/types.h>
+#include <asm/byteorder.h>
 #else
+#include <endian.h>
 #include <sys/ioctl.h>
 #endif
 
@@ -154,7 +156,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 14)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 15)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -301,7 +303,9 @@ typedef int __bitwise snd_pcm_subformat_t;
 #define SNDRV_PCM_INFO_DRAIN_TRIGGER	0x40000000		/* internal kernel flag - trigger in drain */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 
-
+#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__
+#define __SND_STRUCT_TIME64
+#endif
 
 typedef int __bitwise snd_pcm_state_t;
 #define	SNDRV_PCM_STATE_OPEN		((__force snd_pcm_state_t) 0) /* stream is open */
@@ -317,8 +321,17 @@ typedef int __bitwise snd_pcm_state_t;
 
 enum {
 	SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
-	SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
-	SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000,
+#ifdef __SND_STRUCT_TIME64
+	SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW,
+#else
+	SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD,
+#endif
 };
 
 union snd_pcm_sync_id {
@@ -456,8 +469,13 @@ enum {
 	SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED
 };
 
+#ifndef __KERNEL__
+/* explicit padding avoids incompatibility between i386 and x86-64 */
+typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad;
+
 struct snd_pcm_status {
 	snd_pcm_state_t state;		/* stream state */
+	__time_pad pad1;		/* align to timespec */
 	struct timespec trigger_tstamp;	/* time when stream was started/stopped/paused */
 	struct timespec tstamp;		/* reference timestamp */
 	snd_pcm_uframes_t appl_ptr;	/* appl ptr */
@@ -473,17 +491,48 @@ struct snd_pcm_status {
 	__u32 audio_tstamp_accuracy;	/* in ns units, only valid if indicated in audio_tstamp_data */
 	unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */
 };
+#endif
+
+/*
+ * For mmap operations, we need the 64-bit layout, both for compat mode,
+ * and for y2038 compatibility. For 64-bit applications, the two definitions
+ * are identical, so we keep the traditional version.
+ */
+#ifdef __SND_STRUCT_TIME64
+#define __snd_pcm_mmap_status64		snd_pcm_mmap_status
+#define __snd_pcm_mmap_control64	snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr64		snd_pcm_sync_ptr
+#ifdef __KERNEL__
+#define __snd_timespec64		__kernel_timespec
+#else
+#define __snd_timespec64		timespec
+#endif
+struct __snd_timespec {
+	__s32 tv_sec;
+	__s32 tv_nsec;
+};
+#else
+#define __snd_pcm_mmap_status		snd_pcm_mmap_status
+#define __snd_pcm_mmap_control		snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr		snd_pcm_sync_ptr
+#define __snd_timespec			timespec
+struct __snd_timespec64 {
+	__s64 tv_sec;
+	__s64 tv_nsec;
+};
 
-struct snd_pcm_mmap_status {
+#endif
+
+struct __snd_pcm_mmap_status {
 	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
 	int pad1;			/* Needed for 64 bit alignment */
 	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
-	struct timespec tstamp;		/* Timestamp */
+	struct __snd_timespec tstamp;	/* Timestamp */
 	snd_pcm_state_t suspended_state; /* RO: suspended stream state */
-	struct timespec audio_tstamp;	/* from sample counter or wall clock */
+	struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */
 };
 
-struct snd_pcm_mmap_control {
+struct __snd_pcm_mmap_control {
 	snd_pcm_uframes_t appl_ptr;	/* RW: appl ptr (0...boundary-1) */
 	snd_pcm_uframes_t avail_min;	/* RW: min available frames for wakeup */
 };
@@ -492,14 +541,59 @@ struct snd_pcm_mmap_control {
 #define SNDRV_PCM_SYNC_PTR_APPL		(1<<1)	/* get appl_ptr from driver (r/w op) */
 #define SNDRV_PCM_SYNC_PTR_AVAIL_MIN	(1<<2)	/* get avail_min from driver */
 
-struct snd_pcm_sync_ptr {
+struct __snd_pcm_sync_ptr {
 	unsigned int flags;
 	union {
-		struct snd_pcm_mmap_status status;
+		struct __snd_pcm_mmap_status status;
+		unsigned char reserved[64];
+	} s;
+	union {
+		struct __snd_pcm_mmap_control control;
+		unsigned char reserved[64];
+	} c;
+};
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+typedef char __pad_after_uframe[0];
+#endif
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+typedef char __pad_before_uframe[0];
+typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+#endif
+
+struct __snd_pcm_mmap_status64 {
+	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
+	__u32 pad1;			/* Needed for 64 bit alignment */
+	__pad_before_uframe __pad1;
+	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
+	__pad_after_uframe __pad2;
+	struct __snd_timespec64 tstamp;	/* Timestamp */
+	snd_pcm_state_t suspended_state;/* RO: suspended stream state */
+	__u32 pad3;			/* Needed for 64 bit alignment */
+	struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */
+};
+
+struct __snd_pcm_mmap_control64 {
+	__pad_before_uframe __pad1;
+	snd_pcm_uframes_t appl_ptr;	 /* RW: appl ptr (0...boundary-1) */
+	__pad_before_uframe __pad2;
+
+	__pad_before_uframe __pad3;
+	snd_pcm_uframes_t  avail_min;	 /* RW: min available frames for wakeup */
+	__pad_after_uframe __pad4;
+};
+
+struct __snd_pcm_sync_ptr64 {
+	__u32 flags;
+	__u32 pad1;
+	union {
+		struct __snd_pcm_mmap_status64 status;
 		unsigned char reserved[64];
 	} s;
 	union {
-		struct snd_pcm_mmap_control control;
+		struct __snd_pcm_mmap_control64 control;
 		unsigned char reserved[64];
 	} c;
 };
@@ -584,6 +678,8 @@ enum {
 #define SNDRV_PCM_IOCTL_STATUS		_IOR('A', 0x20, struct snd_pcm_status)
 #define SNDRV_PCM_IOCTL_DELAY		_IOR('A', 0x21, snd_pcm_sframes_t)
 #define SNDRV_PCM_IOCTL_HWSYNC		_IO('A', 0x22)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct __snd_pcm_sync_ptr)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR64	_IOWR('A', 0x23, struct __snd_pcm_sync_ptr64)
 #define SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct snd_pcm_sync_ptr)
 #define SNDRV_PCM_IOCTL_STATUS_EXT	_IOWR('A', 0x24, struct snd_pcm_status)
 #define SNDRV_PCM_IOCTL_CHANNEL_INFO	_IOR('A', 0x32, struct snd_pcm_channel_info)
@@ -614,7 +710,7 @@ enum {
  *  Raw MIDI section - /dev/snd/midi??
  */
 
-#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 0)
+#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 1)
 
 enum {
 	SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
@@ -648,13 +744,16 @@ struct snd_rawmidi_params {
 	unsigned char reserved[16];	/* reserved for future use */
 };
 
+#ifndef __KERNEL__
 struct snd_rawmidi_status {
 	int stream;
+	__time_pad pad1;
 	struct timespec tstamp;		/* Timestamp */
 	size_t avail;			/* available bytes */
 	size_t xruns;			/* count of overruns since last status (in bytes) */
 	unsigned char reserved[16];	/* reserved for future use */
 };
+#endif
 
 #define SNDRV_RAWMIDI_IOCTL_PVERSION	_IOR('W', 0x00, int)
 #define SNDRV_RAWMIDI_IOCTL_INFO	_IOR('W', 0x01, struct snd_rawmidi_info)
@@ -667,7 +766,7 @@ struct snd_rawmidi_status {
  *  Timer section - /dev/snd/timer
  */
 
-#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 6)
+#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
 
 enum {
 	SNDRV_TIMER_CLASS_NONE = -1,
@@ -761,6 +860,7 @@ struct snd_timer_params {
 	unsigned char reserved[60];	/* reserved */
 };
 
+#ifndef __KERNEL__
 struct snd_timer_status {
 	struct timespec tstamp;		/* Timestamp - last update */
 	unsigned int resolution;	/* current period resolution in ns */
@@ -769,10 +869,11 @@ struct snd_timer_status {
 	unsigned int queue;		/* used queue size */
 	unsigned char reserved[64];	/* reserved */
 };
+#endif
 
 #define SNDRV_TIMER_IOCTL_PVERSION	_IOR('T', 0x00, int)
 #define SNDRV_TIMER_IOCTL_NEXT_DEVICE	_IOWR('T', 0x01, struct snd_timer_id)
-#define SNDRV_TIMER_IOCTL_TREAD		_IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_TREAD_OLD	_IOW('T', 0x02, int)
 #define SNDRV_TIMER_IOCTL_GINFO		_IOWR('T', 0x03, struct snd_timer_ginfo)
 #define SNDRV_TIMER_IOCTL_GPARAMS	_IOW('T', 0x04, struct snd_timer_gparams)
 #define SNDRV_TIMER_IOCTL_GSTATUS	_IOWR('T', 0x05, struct snd_timer_gstatus)
@@ -785,6 +886,15 @@ struct snd_timer_status {
 #define SNDRV_TIMER_IOCTL_STOP		_IO('T', 0xa1)
 #define SNDRV_TIMER_IOCTL_CONTINUE	_IO('T', 0xa2)
 #define SNDRV_TIMER_IOCTL_PAUSE		_IO('T', 0xa3)
+#define SNDRV_TIMER_IOCTL_TREAD64	_IOW('T', 0xa4, int)
+
+#if __BITS_PER_LONG == 64
+#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD
+#else
+#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \
+				 SNDRV_TIMER_IOCTL_TREAD_OLD : \
+				 SNDRV_TIMER_IOCTL_TREAD64)
+#endif
 
 struct snd_timer_read {
 	unsigned int resolution;
@@ -810,11 +920,15 @@ enum {
 	SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
 };
 
+#ifndef __KERNEL__
 struct snd_timer_tread {
 	int event;
+	__time_pad pad1;
 	struct timespec tstamp;
 	unsigned int val;
+	__time_pad pad2;
 };
+#endif
 
 /****************************************************************************
  *                                                                          *
@@ -822,7 +936,7 @@ struct snd_timer_tread {
  *                                                                          *
  ****************************************************************************/
 
-#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
+#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 8)
 
 struct snd_ctl_card_info {
 	int card;			/* card number */
@@ -860,7 +974,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
 #define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
 #define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP		(1<<3)	/* when was control changed */
+// (1 << 3) is unused.
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
@@ -926,11 +1040,7 @@ struct snd_ctl_elem_info {
 		} enumerated;
 		unsigned char reserved[128];
 	} value;
-	union {
-		unsigned short d[4];		/* dimensions */
-		unsigned short *d_ptr;		/* indirect - obsoleted */
-	} dimen;
-	unsigned char reserved[64-4*sizeof(unsigned short)];
+	unsigned char reserved[64];
 };
 
 struct snd_ctl_elem_value {
@@ -955,8 +1065,7 @@ struct snd_ctl_elem_value {
 		} bytes;
 		struct snd_aes_iec958 iec958;
 	} value;		/* RO */
-	struct timespec tstamp;
-	unsigned char reserved[128-sizeof(struct timespec)];
+	unsigned char reserved[128];
 };
 
 struct snd_ctl_tlv {
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index a32e4b72a98f..d730666ab95d 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,8 +1,10 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
+#include <util/cpumap.h>
 #include <internal/cpumap.h>
 #include <api/fs/fs.h>
+#include <errno.h>
 #include "debug.h"
 #include "header.h"
 
@@ -12,26 +14,21 @@
 #define MIDR_VARIANT_SHIFT      20
 #define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
 
-char *get_cpuid_str(struct perf_pmu *pmu)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 {
-	char *buf = NULL;
-	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
-	int cpu;
 	u64 midr = 0;
-	struct perf_cpu_map *cpus;
-	FILE *file;
+	int cpu;
 
-	if (!sysfs || !pmu || !pmu->cpus)
-		return NULL;
+	if (!sysfs || sz < MIDR_SIZE)
+		return EINVAL;
 
-	buf = malloc(MIDR_SIZE);
-	if (!buf)
-		return NULL;
+	cpus = perf_cpu_map__get(cpus);
 
-	/* read midr from list of cpus mapped to this pmu */
-	cpus = perf_cpu_map__get(pmu->cpus);
 	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+		char path[PATH_MAX];
+		FILE *file;
+
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
 				sysfs, cpus->map[cpu]);
 
@@ -57,12 +54,48 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 		break;
 	}
 
-	if (!midr) {
+	perf_cpu_map__put(cpus);
+
+	if (!midr)
+		return EINVAL;
+
+	return 0;
+}
+
+int get_cpuid(char *buf, size_t sz)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	int ret;
+
+	if (!cpus)
+		return EINVAL;
+
+	ret = _get_cpuid(buf, sz, cpus);
+
+	perf_cpu_map__put(cpus);
+
+	return ret;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+	char *buf = NULL;
+	int res;
+
+	if (!pmu || !pmu->cpus)
+		return NULL;
+
+	buf = malloc(MIDR_SIZE);
+	if (!buf)
+		return NULL;
+
+	/* read midr from list of cpus mapped to this pmu */
+	res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+	if (res) {
 		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
 		free(buf);
 		buf = NULL;
 	}
 
-	perf_cpu_map__put(cpus);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index c29976eca4a8..44d510bc9b78 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -357,6 +357,8 @@
 433	common	fspick			__x64_sys_fspick
 434	common	pidfd_open		__x64_sys_pidfd_open
 435	common	clone3			__x64_sys_clone3/ptregs
+437	common	openat2			__x64_sys_openat2
+438	common	pidfd_getfd		__x64_sys_pidfd_getfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 46a72ecac427..01d542007c8b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1065,7 +1065,9 @@ static struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "poll", .timeout = true, },
 	{ .name	    = "ppoll", .timeout = true, },
 	{ .name	    = "prctl",
-	  .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
+	  .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */
+			   .strtoul   = STUL_STRARRAY,
+			   .parm      = &strarray__prctl_options, },
 		   [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
 		   [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
 	{ .name	    = "pread", .alias = "pread64", },
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 68039a96c1dc..bfb21d049e6c 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -13,6 +13,7 @@ include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
 include/uapi/linux/mount.h
+include/uapi/linux/openat2.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 5a61043c2ff7..d6dfe68a7612 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -213,6 +213,8 @@ size_t syscall_arg__scnprintf_x86_arch_prctl_code(char *bf, size_t size, struct
 size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option
 
+extern struct strarray strarray__prctl_options;
+
 size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index ba2179abed00..6fe5ad5f5d3a 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -11,9 +11,10 @@
 
 #include "trace/beauty/generated/prctl_option_array.c"
 
+DEFINE_STRARRAY(prctl_options, "PR_");
+
 static size_t prctl__scnprintf_option(int option, char *bf, size_t size, bool show_prefix)
 {
-	static DEFINE_STRARRAY(prctl_options, "PR_");
 	return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", show_prefix, option);
 }
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index eae47c2509eb..b5af680fc667 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -288,6 +288,7 @@ static const char *kinc_fetch_script =
 "obj-y := dummy.o\n"
 "\\$(obj)/%.o: \\$(src)/%.c\n"
 "\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
+"\t\\$(CC) -c -o \\$@ \\$<\n"
 "EOF\n"
 "touch $TMPDIR/dummy.c\n"
 "make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c8c5410315e8..fb5c2cd44d30 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -686,6 +686,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 
 		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
+		dso->kernel = DSO_TYPE_KERNEL;
 	}
 
 	dso__get(dso);
@@ -726,9 +727,17 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr);
 
 	if (!map) {
-		map = dso__new_map(event->ksymbol.name);
-		if (!map)
+		struct dso *dso = dso__new(event->ksymbol.name);
+
+		if (dso) {
+			dso->kernel = DSO_TYPE_KERNEL;
+			map = map__new2(0, dso);
+		}
+
+		if (!dso || !map) {
+			dso__put(dso);
 			return -ENOMEM;
+		}
 
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
@@ -972,7 +981,6 @@ int machine__create_extra_kernel_map(struct machine *machine,
 
 	kmap = map__kmap(map);
 
-	kmap->kmaps = &machine->kmaps;
 	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
 
 	maps__insert(&machine->kmaps, map);
@@ -1082,9 +1090,6 @@ int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unu
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-	struct kmap *kmap;
-	struct map *map;
-
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
 
@@ -1093,14 +1098,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		return -1;
 
 	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
-	map = machine__kernel_map(machine);
-	kmap = map__kmap(map);
-	if (!kmap)
-		return -1;
-
-	kmap->kmaps = &machine->kmaps;
-	maps__insert(&machine->kmaps, map);
-
+	maps__insert(&machine->kmaps, machine->vmlinux_map);
 	return 0;
 }
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f67960bedebb..a08ca276098e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -375,8 +375,13 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 
 struct map *map__clone(struct map *from)
 {
-	struct map *map = memdup(from, sizeof(*map));
+	size_t size = sizeof(struct map);
+	struct map *map;
+
+	if (from->dso && from->dso->kernel)
+		size += sizeof(struct kmap);
 
+	map = memdup(from, size);
 	if (map != NULL) {
 		refcount_set(&map->refcnt, 1);
 		RB_CLEAR_NODE(&map->rb_node);
@@ -538,6 +543,16 @@ void maps__insert(struct maps *maps, struct map *map)
 	__maps__insert(maps, map);
 	++maps->nr_maps;
 
+	if (map->dso && map->dso->kernel) {
+		struct kmap *kmap = map__kmap(map);
+
+		if (kmap)
+			kmap->kmaps = maps;
+		else
+			pr_err("Internal error: kernel dso with non kernel map\n");
+	}
+
+
 	/*
 	 * If we already performed some search by name, then we need to add the just
 	 * inserted map and resort.
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2c41d47f6f83..90d23cc3c8d4 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -18,7 +18,6 @@
  * AGGR_NONE: Use matching CPU
  * AGGR_THREAD: Not supported?
  */
-static bool have_frontend_stalled;
 
 struct runtime_stat rt_stat;
 struct stats walltime_nsecs_stats;
@@ -144,7 +143,6 @@ void runtime_stat__exit(struct runtime_stat *st)
 
 void perf_stat__init_shadow_stats(void)
 {
-	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
 	runtime_stat__init(&rt_stat);
 }
 
@@ -853,10 +851,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
-		} else if (have_frontend_stalled) {
-			out->new_line(config, ctxp);
-			print_metric(config, ctxp, NULL, "%7.2f ",
-				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b379b1296f1..1077013d8ce2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -635,9 +635,12 @@ int modules__parse(const char *filename, void *arg,
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"acpi_idle_do_entry",
+		"acpi_processor_ffh_cstate_enter",
 		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
+		"idle_cpu",
 		"intel_idle",
 		"default_idle",
 		"native_safe_halt",
@@ -651,13 +654,17 @@ static bool symbol__is_idle(const char *name)
 		NULL
 	};
 	int i;
+	static struct strlist *idle_symbols_list;
 
-	for (i = 0; idle_symbols[i]; i++) {
-		if (!strcmp(idle_symbols[i], name))
-			return true;
-	}
+	if (idle_symbols_list)
+		return strlist__has_entry(idle_symbols_list, name);
 
-	return false;
+	idle_symbols_list = strlist__new(NULL, NULL);
+
+	for (i = 0; idle_symbols[i]; i++)
+		strlist__add(idle_symbols_list, idle_symbols[i]);
+
+	return strlist__has_entry(idle_symbols_list, name);
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2020-01-18 17:58 Ingo Molnar
@ 2020-01-18 21:05 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2020-01-18 21:05 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Andrew Morton, Thomas Gleixner

The pull request you sent on Sat, 18 Jan 2020 18:58:28 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b07b9e8d631856c9e42af79900527509449206f4

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2020-01-18 17:58 Ingo Molnar
  2020-01-18 21:05 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2020-01-18 17:58 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Andrew Morton, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 2167f1625c2f04a33145f325db0de285630f7bd1 perf/x86/intel/uncore: Remove PCIe3 unit for SNR

Tooling fixes, three Intel uncore driver fixes, plus an AUX events fix 
uncovered by the perf fuzzer.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf map: Set kmap->kmaps backpointer for main kernel map chunks

Hewenliang (1):
      tools lib traceevent: Fix memory leakage in filter_event

Jin Yao (1):
      perf report: Fix incorrectly added dimensions as switch perf data file

Kan Liang (3):
      perf/x86/intel/uncore: Add PCI ID of IMC for Xeon E3 V5 Family
      perf/x86/intel/uncore: Fix missing marker for snr_uncore_imc_freerunning_events
      perf/x86/intel/uncore: Remove PCIe3 unit for SNR

Mark Rutland (1):
      perf: Correctly handle failed perf_get_aux_event()

Yuya Fujita (1):
      perf hists: Fix variable name's inconsistency in hists__for_each() macro


 arch/x86/events/intel/uncore_snb.c   |  6 ++++++
 arch/x86/events/intel/uncore_snbep.c | 25 +------------------------
 kernel/events/core.c                 |  4 +++-
 tools/lib/traceevent/parse-filter.c  |  4 +++-
 tools/perf/builtin-report.c          |  5 ++++-
 tools/perf/util/hist.h               |  4 ++--
 tools/perf/util/symbol-elf.c         |  3 +++
 7 files changed, 22 insertions(+), 29 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index dbaa1b088a30..c37cb12d0ef6 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,7 @@
 #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC		0x1910
 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC		0x190f
 #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC		0x191f
+#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC		0x1918
 #define PCI_DEVICE_ID_INTEL_KBL_Y_IMC		0x590c
 #define PCI_DEVICE_ID_INTEL_KBL_U_IMC		0x5904
 #define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC		0x5914
@@ -657,6 +658,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* IMC */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
@@ -826,6 +831,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
 	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
 	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
+	IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver),  /* Xeon E3 V5 Gen Core processor */
 	IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core Y */
 	IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U */
 	IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U Quad Core */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b10a5ec79e48..ad20220af303 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -369,11 +369,6 @@
 #define SNR_M2M_PCI_PMON_BOX_CTL		0x438
 #define SNR_M2M_PCI_PMON_UMASK_EXT		0xff
 
-/* SNR PCIE3 */
-#define SNR_PCIE3_PCI_PMON_CTL0			0x508
-#define SNR_PCIE3_PCI_PMON_CTR0			0x4e8
-#define SNR_PCIE3_PCI_PMON_BOX_CTL		0x4e4
-
 /* SNR IMC */
 #define SNR_IMC_MMIO_PMON_FIXED_CTL		0x54
 #define SNR_IMC_MMIO_PMON_FIXED_CTR		0x38
@@ -4328,27 +4323,12 @@ static struct intel_uncore_type snr_uncore_m2m = {
 	.format_group	= &snr_m2m_uncore_format_group,
 };
 
-static struct intel_uncore_type snr_uncore_pcie3 = {
-	.name		= "pcie3",
-	.num_counters	= 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.perf_ctr	= SNR_PCIE3_PCI_PMON_CTR0,
-	.event_ctl	= SNR_PCIE3_PCI_PMON_CTL0,
-	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
-	.box_ctl	= SNR_PCIE3_PCI_PMON_BOX_CTL,
-	.ops		= &ivbep_uncore_pci_ops,
-	.format_group	= &ivbep_uncore_format_group,
-};
-
 enum {
 	SNR_PCI_UNCORE_M2M,
-	SNR_PCI_UNCORE_PCIE3,
 };
 
 static struct intel_uncore_type *snr_pci_uncores[] = {
 	[SNR_PCI_UNCORE_M2M]		= &snr_uncore_m2m,
-	[SNR_PCI_UNCORE_PCIE3]		= &snr_uncore_pcie3,
 	NULL,
 };
 
@@ -4357,10 +4337,6 @@ static const struct pci_device_id snr_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
 	},
-	{ /* PCIe3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
-	},
 	{ /* end: all zeroes */ }
 };
 
@@ -4536,6 +4512,7 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
 	INTEL_UNCORE_EVENT_DESC(write,		"event=0xff,umask=0x21"),
 	INTEL_UNCORE_EVENT_DESC(write.scale,	"3.814697266e-6"),
 	INTEL_UNCORE_EVENT_DESC(write.unit,	"MiB"),
+	{ /* end: all zeroes */ },
 };
 
 static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a1f8bde19b56..2173c23c25b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
+	if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) {
+		err = -EINVAL;
 		goto err_locked;
+	}
 
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index f3cbf86e51ac..20eed719542e 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1228,8 +1228,10 @@ filter_event(struct tep_event_filter *filter, struct tep_event *event,
 	}
 
 	filter_type = add_filter_type(filter, event->id);
-	if (filter_type == NULL)
+	if (filter_type == NULL) {
+		free_arg(arg);
 		return TEP_ERRNO__MEM_ALLOC_FAILED;
+	}
 
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 387311c67264..de988589d99b 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1076,6 +1076,7 @@ int cmd_report(int argc, const char **argv)
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
+	int last_key = 0;
 	bool branch_call_mode = false;
 #define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
 	static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
@@ -1450,7 +1451,8 @@ int cmd_report(int argc, const char **argv)
 		sort_order = sort_tmp;
 	}
 
-	if (setup_sorting(session->evlist) < 0) {
+	if ((last_key != K_SWITCH_INPUT_DATA) &&
+	    (setup_sorting(session->evlist) < 0)) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
 		if (field_order)
@@ -1530,6 +1532,7 @@ int cmd_report(int argc, const char **argv)
 	ret = __cmd_report(&report);
 	if (ret == K_SWITCH_INPUT_DATA) {
 		perf_session__delete(session);
+		last_key = K_SWITCH_INPUT_DATA;
 		goto repeat;
 	} else
 		ret = 0;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 45286900aacb..0aa63aeb58ec 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -339,10 +339,10 @@ static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
 	list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
 
 #define hists__for_each_format(hists, format) \
-	perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+	perf_hpp_list__for_each_format((hists)->hpp_list, format)
 
 #define hists__for_each_sort_list(hists, format) \
-	perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
+	perf_hpp_list__for_each_sort_list((hists)->hpp_list, format)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6658fbf196e6..1965aefccb02 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -920,6 +920,9 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		if (curr_map == NULL)
 			return -1;
 
+		if (curr_dso->kernel)
+			map__kmap(curr_map)->kmaps = kmaps;
+
 		if (adjust_kernel_syms) {
 			curr_map->start  = shdr->sh_addr + ref_reloc(kmap);
 			curr_map->end	 = curr_map->start + shdr->sh_size;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-12-21 16:16 Ingo Molnar
@ 2019-12-21 18:55 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-12-21 18:55 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Andrew Morton

The pull request you sent on Sat, 21 Dec 2019 17:16:24 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/c4ff10efe8e487cd35f4475ed2dd1e5e0c6f784a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-12-21 16:16 Ingo Molnar
  2019-12-21 18:55 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-12-21 16:16 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Andrew Morton


Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 9f0bff1180efc9ea988fed3fd93da7647151ac8b perf/core: Add SRCU annotation for pmus list walk

Misc fixes: a BTS fix, a PT NMI handling fix, a PMU sysfs fix and an SRCU 
annotation.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (2):
      perf/x86/intel/bts: Fix the use of page_private()
      perf/x86/intel: Fix PT PMI handling

Peter Zijlstra (1):
      perf/x86: Fix potential out-of-bounds access

Sebastian Andrzej Siewior (1):
      perf/core: Add SRCU annotation for pmus list walk


 arch/x86/events/core.c      | 19 +++++++++++++++----
 arch/x86/events/intel/bts.c | 16 +++++++++++-----
 kernel/events/core.c        |  2 +-
 3 files changed, 27 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9a89d98c55bd..f118af9f0718 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -376,7 +376,7 @@ int x86_add_exclusive(unsigned int what)
 	 * LBR and BTS are still mutually exclusive.
 	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
-		return 0;
+		goto out;
 
 	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
 		mutex_lock(&pmc_reserve_mutex);
@@ -388,6 +388,7 @@ int x86_add_exclusive(unsigned int what)
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 
+out:
 	atomic_inc(&active_events);
 	return 0;
 
@@ -398,11 +399,15 @@ int x86_add_exclusive(unsigned int what)
 
 void x86_del_exclusive(unsigned int what)
 {
+	atomic_dec(&active_events);
+
+	/*
+	 * See the comment in x86_add_exclusive().
+	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
 		return;
 
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
-	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)
@@ -1642,9 +1647,12 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = {
 
 ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
 {
-	struct perf_pmu_events_attr *pmu_attr = \
+	struct perf_pmu_events_attr *pmu_attr =
 		container_of(attr, struct perf_pmu_events_attr, attr);
-	u64 config = x86_pmu.event_map(pmu_attr->id);
+	u64 config = 0;
+
+	if (pmu_attr->id < x86_pmu.max_events)
+		config = x86_pmu.event_map(pmu_attr->id);
 
 	/* string trumps id */
 	if (pmu_attr->event_str)
@@ -1713,6 +1721,9 @@ is_visible(struct kobject *kobj, struct attribute *attr, int idx)
 {
 	struct perf_pmu_events_attr *pmu_attr;
 
+	if (idx >= x86_pmu.max_events)
+		return 0;
+
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
 	/* str trumps id */
 	return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 38de4a7f6752..6a3b599ee0fe 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -63,9 +63,17 @@ struct bts_buffer {
 
 static struct pmu bts_pmu;
 
+static int buf_nr_pages(struct page *page)
+{
+	if (!PagePrivate(page))
+		return 1;
+
+	return 1 << page_private(page);
+}
+
 static size_t buf_size(struct page *page)
 {
-	return 1 << (PAGE_SHIFT + page_private(page));
+	return buf_nr_pages(page) * PAGE_SIZE;
 }
 
 static void *
@@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages,
 	/* count all the high order buffers */
 	for (pg = 0, nbuf = 0; pg < nr_pages;) {
 		page = virt_to_page(pages[pg]);
-		if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1))
-			return NULL;
-		pg += 1 << page_private(page);
+		pg += buf_nr_pages(page);
 		nbuf++;
 	}
 
@@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages,
 		unsigned int __nr_pages;
 
 		page = virt_to_page(pages[pg]);
-		__nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1;
+		__nr_pages = buf_nr_pages(page);
 		buf->buf[nbuf].page = page;
 		buf->buf[nbuf].offset = offset;
 		buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4ff86d57f9e5..a1f8bde19b56 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10523,7 +10523,7 @@ static struct pmu *perf_init_event(struct perf_event *event)
 		goto unlock;
 	}
 
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
+	list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
 		ret = perf_try_init_event(pmu, event);
 		if (!ret)
 			goto unlock;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-12-17 19:06 ` Linus Torvalds
@ 2019-12-18  6:58   ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2019-12-18  6:58 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo, Jiri Olsa,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Tue, Dec 17, 2019 at 3:34 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Note that the large CPU count related fixes go beyond regression fixes -
> > but the IPI-flood symptoms are severe enough that I think justifies their
> > inclusion. If it's too much we'll redo the branch.
> 
> I'm much less sensitive to the perf _tooling_ changes than I am to 
> actual kernel code changes.
> 
> Of course, if you start having a history of breaking things during the 
> rc kernels, that may change, but at least for now, I tend to look at 
> diffstats and go "oh, this is perf tooling", and not worry too much 
> about it...

Thanks for pulling these in any case!

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-12-17 11:34 Ingo Molnar
  2019-12-17 19:06 ` Linus Torvalds
@ 2019-12-17 19:20 ` pr-tracker-bot
  1 sibling, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-12-17 19:20 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Arnaldo Carvalho de Melo,
	Jiri Olsa, Peter Zijlstra, Thomas Gleixner, Andrew Morton

The pull request you sent on Tue, 17 Dec 2019 12:34:25 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/89c683cd06e03dfd3186c4cab1e2a39982c42a48

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-12-17 11:34 Ingo Molnar
@ 2019-12-17 19:06 ` Linus Torvalds
  2019-12-18  6:58   ` Ingo Molnar
  2019-12-17 19:20 ` pr-tracker-bot
  1 sibling, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2019-12-17 19:06 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo, Jiri Olsa,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Tue, Dec 17, 2019 at 3:34 AM Ingo Molnar <mingo@kernel.org> wrote:
>
> Note that the large CPU count related fixes go beyond regression fixes -
> but the IPI-flood symptoms are severe enough that I think justifies their
> inclusion. If it's too much we'll redo the branch.

I'm much less sensitive to the perf _tooling_ changes than I am to
actual kernel code changes.

Of course, if you start having a history of breaking things during the
rc kernels, that may change, but at least for now, I tend to look at
diffstats and go "oh, this is perf tooling", and not worry too much
about it...

                     Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-12-17 11:34 Ingo Molnar
  2019-12-17 19:06 ` Linus Torvalds
  2019-12-17 19:20 ` pr-tracker-bot
  0 siblings, 2 replies; 376+ messages in thread
From: Ingo Molnar @ 2019-12-17 11:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Jiri Olsa,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 57e04eeda515ee979fec3bc3d64c408feae18acc Merge tag 'perf-urgent-for-mingo-5.5-20191216' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

These are all perf tooling changes: most of them are fixes.

Note that the large CPU count related fixes go beyond regression fixes - 
but the IPI-flood symptoms are severe enough that I think justifies their 
inclusion. If it's too much we'll redo the branch.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf inject: Fix processing of ID index for injected instruction tracing

Andi Kleen (10):
      perf cpumap: Maintain cpumaps ordered and without dups
      perf evlist: Maintain evlist->all_cpus
      perf evsel: Add iterator to iterate over events ordered by CPU
      perf evsel: Add functions to close evsel on a CPU
      perf stat: Use affinity for closing file descriptors
      perf stat: Factor out open error handling
      perf stat: Use affinity for opening events
      perf stat: Use affinity for reading
      perf evsel: Add functions to enable/disable for a specific CPU
      perf stat: Use affinity for enabling/disabling events

Arnaldo Carvalho de Melo (15):
      perf machine: Fill map_symbol->maps in append_inlines() to fix segfault
      perf bench: Update the copies of x86's mem{cpy,set}_64.S
      tools arch x86: Sync the msr-index.h copy with the kernel sources
      tools headers uapi: Sync linux/fscrypt.h with the kernel sources
      tools headers uapi: Sync linux/stat.h with the kernel sources
      tools headers kvm: Sync kvm headers with the kernel sources
      tools headers UAPI: Sync sched.h with the kernel
      perf beauty: Add CLEAR_SIGHAND support for clone's flags arg
      tools arch x86: Sync asm/cpufeatures.h with the kernel sources
      perf kvm: Clarify the 'perf kvm' -i and -o command line options
      tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
      tools headers UAPI: Update tools's copy of drm.h headers
      tools headers kvm: Sync linux/kvm.h with the kernel sources
      perf arch: Make the default get_cpuid() return compatible error
      perf top: Do not bail out when perf_env__read_cpuid() returns ENOSYS

Ed Maste (2):
      perf vendor events s390: Fix counter long description for DTLB1_GPAGE_WRITES
      perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description

Ian Rogers (1):
      perf jit: Move test functionality in to a test

Kajol Jain (1):
      perf metricgroup: Fix printing event names of metric group with multiple events

Michael Petlan (1):
      perf header: Fix false warning when there are no duplicate cache entries

Ravi Bangoria (4):
      perf report/top TUI: Replace pr_err() with ui__error()
      perf report: Make -F more strict like -s
      perf report: Bail out --mem-mode if mem info is not available
      perf/x86/pmu-events: Fix Kernel_Utilization metric

Sudip Mukherjee (3):
      libtraceevent: Fix lib installation with O=
      libtraceevent: Copy pkg-config file to output folder when using O=
      libtraceevent: Allow custom libdir path


 tools/arch/arm/include/uapi/asm/kvm.h              |   3 +-
 tools/arch/arm64/include/uapi/asm/kvm.h            |   5 +-
 tools/arch/powerpc/include/uapi/asm/kvm.h          |   3 +
 tools/arch/x86/include/asm/cpufeatures.h           |   3 +
 tools/arch/x86/include/asm/msr-index.h             |  18 ++
 tools/arch/x86/lib/memcpy_64.S                     |  20 +-
 tools/arch/x86/lib/memset_64.S                     |  16 +-
 tools/include/uapi/drm/drm.h                       |   3 +-
 tools/include/uapi/drm/i915_drm.h                  | 128 ++++++++-
 tools/include/uapi/linux/fscrypt.h                 |   3 +-
 tools/include/uapi/linux/kvm.h                     |  12 +
 tools/include/uapi/linux/sched.h                   |  60 +++--
 tools/include/uapi/linux/stat.h                    |   2 +-
 tools/lib/traceevent/Makefile                      |  11 +-
 tools/lib/traceevent/plugins/Makefile              |   5 +-
 tools/perf/Documentation/perf-kvm.txt              |   5 +-
 tools/perf/arch/arm/tests/regs_load.S              |   4 +-
 tools/perf/arch/arm64/tests/regs_load.S            |   4 +-
 tools/perf/arch/x86/tests/regs_load.S              |   8 +-
 tools/perf/builtin-inject.c                        |  13 +-
 tools/perf/builtin-record.c                        |   2 +-
 tools/perf/builtin-report.c                        |   8 +
 tools/perf/builtin-stat.c                          | 288 +++++++++++++++------
 tools/perf/builtin-top.c                           |  10 +-
 tools/perf/check-headers.sh                        |   4 +-
 tools/perf/lib/cpumap.c                            |  73 +++++-
 tools/perf/lib/evlist.c                            |   1 +
 tools/perf/lib/evsel.c                             |  76 ++++--
 tools/perf/lib/include/internal/evlist.h           |   1 +
 tools/perf/lib/include/perf/cpumap.h               |   2 +
 tools/perf/lib/include/perf/evsel.h                |   3 +
 .../perf/pmu-events/arch/s390/cf_z13/extended.json |   2 +-
 .../perf/pmu-events/arch/s390/cf_z14/extended.json |   2 +-
 .../pmu-events/arch/x86/broadwell/bdw-metrics.json |   2 +-
 .../arch/x86/broadwellde/bdwde-metrics.json        |   2 +-
 .../arch/x86/broadwellx/bdx-metrics.json           |   2 +-
 .../arch/x86/cascadelakex/clx-metrics.json         |   2 +-
 .../pmu-events/arch/x86/haswell/hsw-metrics.json   |   2 +-
 .../pmu-events/arch/x86/haswellx/hsx-metrics.json  |   2 +-
 .../pmu-events/arch/x86/ivybridge/ivb-metrics.json |   2 +-
 .../pmu-events/arch/x86/ivytown/ivt-metrics.json   |   2 +-
 .../pmu-events/arch/x86/jaketown/jkt-metrics.json  |   2 +-
 .../arch/x86/sandybridge/snb-metrics.json          |   2 +-
 .../pmu-events/arch/x86/skylake/skl-metrics.json   |   2 +-
 .../pmu-events/arch/x86/skylakex/skx-metrics.json  |   2 +-
 tools/perf/tests/Build                             |   1 +
 tools/perf/tests/builtin-test.c                    |   9 +
 tools/perf/tests/cpumap.c                          |  16 ++
 tools/perf/tests/event-times.c                     |   4 +-
 tools/perf/tests/genelf.c                          |  51 ++++
 tools/perf/tests/tests.h                           |   2 +
 tools/perf/trace/beauty/clone.c                    |   1 +
 tools/perf/util/cpumap.h                           |   1 +
 tools/perf/util/evlist.c                           | 113 +++++++-
 tools/perf/util/evlist.h                           |  11 +-
 tools/perf/util/evsel.c                            |  35 ++-
 tools/perf/util/evsel.h                            |   9 +-
 tools/perf/util/genelf.c                           |  46 ----
 tools/perf/util/header.c                           |  23 +-
 tools/perf/util/include/linux/linkage.h            |  89 ++++++-
 tools/perf/util/machine.c                          |   1 +
 tools/perf/util/metricgroup.c                      |   7 +-
 tools/perf/util/sort.c                             |  16 +-
 tools/perf/util/stat.c                             |   5 +-
 tools/perf/util/stat.h                             |   3 +-
 65 files changed, 976 insertions(+), 289 deletions(-)
 create mode 100644 tools/perf/tests/genelf.c


^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-12-01 22:15 Ingo Molnar
@ 2019-12-02  4:40 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-12-02  4:40 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Jiri Olsa, Thomas Gleixner, Andrew Morton

The pull request you sent on Sun, 1 Dec 2019 23:15:22 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b7fcf31f7036895ca8fc3a30eefffab0e82f75f6

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-12-01 22:15 Ingo Molnar
  2019-12-02  4:40 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-12-01 22:15 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e680a41fcaf07ccac8817c589fc4824988b48eac Merge tag 'perf-core-for-mingo-5.5-20191128' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly fixes:


 - Make /sys/devices/cpu/rdpmc based RDPMC enforcement more instantaneous

 - decoder: Update the Intel opcode map

 - Various tooling fixes, including a few late optimizations and cleanups.

 Thanks,

	Ingo

------------------>
Adrian Hunter (4):
      x86/insn: Add some more Intel instructions to the opcode map
      x86/insn: perf tools: Add some more instructions to the new instructions test
      perf script: Fix brstackinsn for AUXTRACE
      perf script: Fix invalid LBR/binary mismatch error

Andi Kleen (2):
      perf pmu: Use file system cache to optimize sysfs access
      perf affinity: Add infrastructure to save/restore affinity

Anthony Steinhauser (1):
      perf/x86: Implement immediate enforcement of /sys/devices/cpu/rdpmc value of 0

Arnaldo Carvalho de Melo (15):
      perf script: Move map__fprintf_srccode() to near its only user
      perf map: Ditch leftover map__reloc_vmlinux() prototype
      perf map: Remove needless struct forward declarations
      perf map: Remove unused functions
      perf maps: Merge 'struct maps' with 'struct map_groups'
      perf thread: Rename thread->mg to thread->maps
      perf addr_location: Rename al->mg to al->maps
      perf map_symbol: Rename ms->mg to ms->maps
      perf maps: Rename 'mg' variables to 'maps'
      perf maps: Rename map_groups.h to maps.h
      perf tests: Rename thread-mg-share to thread-maps-share
      perf tests: Rename tests/map_groups.c to tests/maps.c
      perf diff: Use llabs() with 64-bit values
      perf diff: Use llabs() with 64-bit values
      perf regs: Make perf_reg_name() return "unknown" instead of NULL

Jiri Olsa (1):
      perf tools: Allow to link with libbpf dynamicaly


 arch/x86/events/core.c                             |  18 +-
 arch/x86/include/asm/mmu_context.h                 |   4 +-
 arch/x86/lib/x86-opcode-map.txt                    |  44 +-
 tools/arch/x86/lib/x86-opcode-map.txt              |  44 +-
 tools/build/Makefile.feature                       |   3 +-
 tools/build/feature/Makefile                       |   4 +
 tools/build/feature/test-libbpf.c                  |   7 +
 tools/perf/Makefile.config                         |  10 +
 tools/perf/Makefile.perf                           |   6 +-
 tools/perf/arch/arm/tests/dwarf-unwind.c           |   4 +-
 tools/perf/arch/arm64/tests/dwarf-unwind.c         |   4 +-
 tools/perf/arch/powerpc/tests/dwarf-unwind.c       |   4 +-
 tools/perf/arch/s390/annotate/instructions.c       |   2 +-
 tools/perf/arch/x86/tests/dwarf-unwind.c           |   4 +-
 tools/perf/arch/x86/tests/insn-x86-dat-32.c        | 366 ++++++++++++
 tools/perf/arch/x86/tests/insn-x86-dat-64.c        | 484 +++++++++++++++
 tools/perf/arch/x86/tests/insn-x86-dat-src.c       | 655 +++++++++++++++++++++
 tools/perf/arch/x86/util/event.c                   |   5 +-
 tools/perf/builtin-diff.c                          |   6 +-
 tools/perf/builtin-report.c                        |   7 +-
 tools/perf/builtin-script.c                        |  46 +-
 tools/perf/tests/Build                             |   4 +-
 tools/perf/tests/builtin-test.c                    |   8 +-
 tools/perf/tests/code-reading.c                    |   2 +-
 tools/perf/tests/{map_groups.c => maps.c}          |  26 +-
 tools/perf/tests/tests.h                           |   4 +-
 .../{thread-mg-share.c => thread-maps-share.c}     |  36 +-
 tools/perf/tests/vmlinux-kallsyms.c                |   9 +-
 tools/perf/ui/browsers/annotate.c                  |   2 +-
 tools/perf/ui/stdio/hist.c                         |   4 +-
 tools/perf/util/Build                              |   2 +
 tools/perf/util/affinity.c                         |  73 +++
 tools/perf/util/affinity.h                         |  17 +
 tools/perf/util/annotate.c                         |   8 +-
 tools/perf/util/bpf-event.c                        |   4 +-
 tools/perf/util/callchain.c                        |   8 +-
 tools/perf/util/cs-etm.c                           |   2 +-
 tools/perf/util/db-export.c                        |  12 +-
 tools/perf/util/event.c                            |  14 +-
 tools/perf/util/fncache.c                          |  63 ++
 tools/perf/util/fncache.h                          |   7 +
 tools/perf/util/hist.c                             |   8 +-
 tools/perf/util/intel-pt.c                         |   2 +-
 tools/perf/util/machine.c                          |  80 ++-
 tools/perf/util/machine.h                          |  10 +-
 tools/perf/util/map.c                              | 223 ++-----
 tools/perf/util/map.h                              |  14 +-
 tools/perf/util/map_groups.h                       | 106 ----
 tools/perf/util/map_symbol.h                       |   4 +-
 tools/perf/util/maps.h                             |  87 +++
 tools/perf/util/perf_regs.h                        |   2 +-
 tools/perf/util/pmu.c                              |  34 +-
 tools/perf/util/probe-event.c                      |   4 +-
 tools/perf/util/python-ext-sources                 |   1 +
 .../util/scripting-engines/trace-event-python.c    |   2 +-
 tools/perf/util/srccode.c                          |   9 +-
 tools/perf/util/symbol-elf.c                       |  16 +-
 tools/perf/util/symbol.c                           |  91 ++-
 tools/perf/util/symbol.h                           |   6 +-
 tools/perf/util/synthetic-events.c                 |   2 +-
 tools/perf/util/thread-stack.c                     |   4 +-
 tools/perf/util/thread.c                           |  38 +-
 tools/perf/util/thread.h                           |   4 +-
 tools/perf/util/unwind-libdw.c                     |   4 +-
 tools/perf/util/unwind-libunwind-local.c           |  22 +-
 tools/perf/util/unwind-libunwind.c                 |  36 +-
 tools/perf/util/unwind.h                           |  27 +-
 tools/perf/util/vdso.c                             |   2 +-
 68 files changed, 2245 insertions(+), 625 deletions(-)
 create mode 100644 tools/build/feature/test-libbpf.c
 rename tools/perf/tests/{map_groups.c => maps.c} (83%)
 rename tools/perf/tests/{thread-mg-share.c => thread-maps-share.c} (64%)
 create mode 100644 tools/perf/util/affinity.c
 create mode 100644 tools/perf/util/affinity.h
 create mode 100644 tools/perf/util/fncache.c
 create mode 100644 tools/perf/util/fncache.h
 delete mode 100644 tools/perf/util/map_groups.h
 create mode 100644 tools/perf/util/maps.h

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-11-16 21:33 Ingo Molnar
@ 2019-11-17  0:35 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-11-17  0:35 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra, Alexander Shishkin,
	Thomas Gleixner, Arnaldo Carvalho de Melo, Jiri Olsa

The pull request you sent on Sat, 16 Nov 2019 22:33:33 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/5ffaf037e776fd5095561c27d879b4484549f7e4

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-11-16 21:33 Ingo Molnar
  2019-11-17  0:35 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-11-16 21:33 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Alexander Shishkin,
	Thomas Gleixner, Arnaldo Carvalho de Melo, Jiri Olsa

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d00dbd29814236ad128ff9517e8f7af6b6ef4ba0 perf/core: Fix missing static inline on perf_cgroup_switch()

Misc fixes: a handful of AUX event handling related fixes, a Sparse fix 
and two ABI fixes.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (4):
      perf/aux: Fix the aux_output group inheritance fix
      perf/core: Reattach a misplaced comment
      perf/aux: Disallow aux_output for kernel events
      perf/core: Consistently fail fork on allocation failures

Ben Dooks (Codethink) (1):
      perf/core: Fix missing static inline on perf_cgroup_switch()

Peter Zijlstra (1):
      perf/core: Disallow uncore-cgroup events


 kernel/events/core.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index aec8dba2bea4..00a014670ed0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 }
 
-void
+static inline void
 perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
 {
 }
@@ -10535,6 +10535,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_ns;
 	}
 
+	/*
+	 * Disallow uncore-cgroup events, they don't make sense as the cgroup will
+	 * be different on other CPUs in the uncore mask.
+	 */
+	if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) {
+		err = -EINVAL;
+		goto err_pmu;
+	}
+
 	if (event->attr.aux_output &&
 	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
 		err = -EOPNOTSUPP;
@@ -11323,8 +11332,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	int err;
 
 	/*
-	 * Get the target context (task or percpu):
+	 * Grouping is not supported for kernel events, neither is 'AUX',
+	 * make sure the caller's intentions are adjusted.
 	 */
+	if (attr->aux_output)
+		return ERR_PTR(-EINVAL);
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
 				 overflow_handler, context, -1);
@@ -11336,6 +11348,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = TASK_TOMBSTONE;
 
+	/*
+	 * Get the target context (task or percpu):
+	 */
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -11787,7 +11802,7 @@ inherit_event(struct perf_event *parent_event,
 						   GFP_KERNEL);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
@@ -11890,7 +11905,7 @@ static int inherit_group(struct perf_event *parent_event,
 		if (IS_ERR(child_ctr))
 			return PTR_ERR(child_ctr);
 
-		if (sub->aux_event == parent_event &&
+		if (sub->aux_event == parent_event && child_ctr &&
 		    !perf_get_aux_event(child_ctr, leader))
 			return -EINVAL;
 	}

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-11-01 20:30   ` Ingo Molnar
  2019-11-01 21:01     ` Ingo Molnar
@ 2019-11-01 22:15     ` Linus Torvalds
  1 sibling, 0 replies; 376+ messages in thread
From: Linus Torvalds @ 2019-11-01 22:15 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Alexander Shishkin,
	Mark Rutland, Thomas Gleixner

On Fri, Nov 1, 2019 at 1:30 PM Ingo Molnar <mingo@kernel.org> wrote:
>
> Firstly, non-existent fields are initialized to zero by default in the
> perf ABI: *even if user-space was built well before that new field was
> introduced in the kernel*.
>
> This is done in perf_copy_attr():
>
>         /* Zero the full structure, so that a short copy will be nice. */
>         memset(attr, 0, sizeof(*attr));
>
> The user-space structure that is passed in ('uattr' within that function)
> might indeed be short and not contain the new field - but we handle this
> via uattr->size, which is set by user-space - for example 'perf' sets it
> in event_attr_init() in tools/perf/util/util.c:
>
>         /* to capture ABI version */
>         attr->size = sizeof(*attr);
>
> Second, the kernel syscall then checks this size against the kernel's
> size of attr:
>
>  - if uattr->size < kattr_size: then old ABI user-space binary is
>    running on new kernel, and we zero out residual fields.

Very good. These were the two pieces I was missing - just readfing the
commit messages it wasn't clear that this was safe at all.

Thanks for following up on my worry,

               Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-11-01 20:30   ` Ingo Molnar
@ 2019-11-01 21:01     ` Ingo Molnar
  2019-11-01 22:15     ` Linus Torvalds
  1 sibling, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2019-11-01 21:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Alexander Shishkin,
	Mark Rutland, Thomas Gleixner


* Ingo Molnar <mingo@kernel.org> wrote:

> This actually works fine in practice. I just tried out a brand new kernel 
> with really old perf tooling in the v3.19 kernel, from 4.5 years ago:
> 
>   $ git checkout v3.19
>   $ cd tools/perf/
>   $ make install WERROR=0
> 
>   $ perf version
>   perf version 3.19.gbfa76d49
> 
>   $ perf top
> 
> This ancient version of 'perf top', 'perf record', 'perf report' works 
> just fine on the new kernel, despite passing in a smaller 'attr':
> 
>   [  558.408907] perf kABI size: 112
>   [  558.412855] perf uABI size: 104
> 
> when running new tooling on a new kernel the two sizes match:
> 
> [  331.598089] perf kABI size: 112
> [  331.602050] perf uABI size: 112
> 
> and everything works as usual.

Out of morbid curiosity I also tried out the v3.2 version of perf 
tooling, which is now more than 7.5 years old, and 'perf record' + 'perf 
report' is working fine on the latest kernel too:


  $ perf version
  perf version 3.2.dirty

  $ perf record ~/hackbench 20
  Time: 0.082
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.828 MB perf.data (~36166 samples) ]

  $ perf report --stdio
  ...
  # Overhead    Command      Shared Object                                      Symbol
  # ........  .........  .................  ..........................................
  #
     6.99%  hackbench  [kernel.kallsyms]  [k] queued_spin_lock_slowpath
     6.22%  hackbench  [kernel.kallsyms]  [k] entry_SYSENTER_compat
     4.06%  hackbench  [kernel.kallsyms]  [k] sysret32_from_system_call
     3.56%  hackbench  [kernel.kallsyms]  [k] do_fast_syscall_32
     3.40%  hackbench  [kernel.kallsyms]  [k] unix_stream_read_generic
     3.32%  hackbench  [kernel.kallsyms]  [k] _raw_spin_lock
     3.13%  hackbench  [kernel.kallsyms]  [k] __slab_free


It works despite 'perf record' using an ancient, 72 bytes long 'struct perf_attr' 
ABI:

  [ 3013.531125] perf kABI size: 112
  [ 3013.535097] perf uABI size: 72

If I'm reading the logs right then the perf ABI went through around ~15 
iterations in the v3.2..v5.4 timeframe that extended struct 
perf_event_attr - but binary compatibility was maintained with ancient 
tooling.

This is also useful for tooling bisectability: tooling should work on new 
and old kernels as well, even if a bisection point moves across ABI 
extension boundaries.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-11-01 18:48 ` Linus Torvalds
@ 2019-11-01 20:30   ` Ingo Molnar
  2019-11-01 21:01     ` Ingo Molnar
  2019-11-01 22:15     ` Linus Torvalds
  0 siblings, 2 replies; 376+ messages in thread
From: Ingo Molnar @ 2019-11-01 20:30 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Alexander Shishkin,
	Mark Rutland, Thomas Gleixner


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Fri, Nov 1, 2019 at 10:48 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Alexander Shishkin (1):
> >       perf/core: Start rejecting the syscall with attr.__reserved_2 set
> 
> This seems to quite possibly break existing apps. Is there any reason 
> to believe that existing users have actually cleared that field?

Yes, there's good reason to believe that the field ends up being zero 
within the kernel even if old user-space uses the old, smaller structure:

> It's suspect for another reason too: the commit that added that field
> just added it to the end of the structure, with the argument that
> "aux_watermark will only matter for new AUX-aware code, so the old
> code should still be fine".
> 
> So by *definition* those old kinds of users would never have cleared
> that field, because that field didn't exist.

Firstly, non-existent fields are initialized to zero by default in the 
perf ABI: *even if user-space was built well before that new field was 
introduced in the kernel*.

This is done in perf_copy_attr():

        /* Zero the full structure, so that a short copy will be nice. */
        memset(attr, 0, sizeof(*attr));

The user-space structure that is passed in ('uattr' within that function) 
might indeed be short and not contain the new field - but we handle this 
via uattr->size, which is set by user-space - for example 'perf' sets it 
in event_attr_init() in tools/perf/util/util.c:

        /* to capture ABI version */
        attr->size = sizeof(*attr);

Second, the kernel syscall then checks this size against the kernel's 
size of attr:

 - if uattr->size < kattr_size: then old ABI user-space binary is 
   running on new kernel, and we zero out residual fields.

 - if uattr->size = kattr_size, this is the normal case of matching ABI (sizes)

 - if uattr->size > kattr_size, then new ABI user-space binary is running 
   on an old kernel - in this case the kernel copies in a shortened 
   structure from the new tool and ignores the remaining fields. To not 
   surprise new user-space the kernel copies back the recognized size to 
   uattr->size and user-space can decide whether they want to run on this 
   kernel or not:

             put_user(sizeof(*attr), &uattr->size);

This way the perf ABI is *both* backwards and forward compatible, even 
across multiple ABI changes. We seemingly didn't "care" about the zeroing 
of the new field in old binaries in that changelog, because it's 
guaranteed by the syscall implementation.

[ Note that there *is* still potential for more subtle ABI breakage, see 
  further below. ]

This actually works fine in practice. I just tried out a brand new kernel 
with really old perf tooling in the v3.19 kernel, from 4.5 years ago:

  $ git checkout v3.19
  $ cd tools/perf/
  $ make install WERROR=0

  $ perf version
  perf version 3.19.gbfa76d49

  $ perf top

This ancient version of 'perf top', 'perf record', 'perf report' works 
just fine on the new kernel, despite passing in a smaller 'attr':

  [  558.408907] perf kABI size: 112
  [  558.412855] perf uABI size: 104

when running new tooling on a new kernel the two sizes match:

[  331.598089] perf kABI size: 112
[  331.602050] perf uABI size: 112

and everything works as usual.

> And the people involved should stop claiming this "fixes" anything,
> and should look hard at their random ABI expansions and "fixes".
> 
> The original code that said "old users would not be impacted" is
> correct. But this "fix" is very very very questionable indeed, and I
> get the feeling that somebody doesn't understand what ABI is, when
> they claim that this "fixes" anything.

So if your primary worry is about old user-space that didn't know about 
the new field passing in the new field with some random value, then if 
the perf ABI handling logic I outlined above is implemented correctly 
(and I believe it's correct), then this should not happen.

But arguably there's still a more subtle ABI breakage that this change 
might trigger: if due to some bug user-space *does* initialize this 
reserved field to non-zero, and the kernel ignored that non-zero field 
for 4 years and new kernels suddenly start rejecting these syscalls, 
that's an ABI bug and grounds for an immediate revert.

I don't expect this to happen though, due to the combination of how 
user-space and kernel-space handles the extension of the perf ABI - but 
if it happens then it's an insta-revert.

I'd also argue that because we didn't check this field for years, the 
next ABI extension should probably not use the __reserved_2 field - which 
is a good idea anyway as it has an unnatural __u16 size.

> Honestly, this all shows a worrying complete disregard for backwards
> compatibility. Calling this a "fix" is questionable, when it is much
> more likely to break some old user.
> 
> I've pulled it, but I need people to be aware that this is utter
> garbage, and that if anybody ever reports it, this needs to be
> immediately reverted.

In light of the above logic I'd like to push back against this 
characterization: this kind of ABI compatibility is actually one of the 
most important aspects of the perf ABI, and we very much take it 
seriously.

In fact we are proud of it: the perf ABI is one of the most iterated, yet 
also one of the most compatible and tooling-friendly ABIs in the kernel. :-)

The reason it wasn't even mentioned in the changelog is because we tried 
to design out this kind of mishap from the ABI, and all the main perf 
developers are aware of that design. Will try to include a more careful 
explanation next time.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-11-01 17:48 Ingo Molnar
  2019-11-01 18:48 ` Linus Torvalds
@ 2019-11-01 19:10 ` pr-tracker-bot
  1 sibling, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-11-01 19:10 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Alexander Shishkin,
	Mark Rutland, Thomas Gleixner

The pull request you sent on Fri, 1 Nov 2019 18:48:40 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/355f83c1d098c27b3d912c7a397c13be17de6476

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-11-01 17:48 Ingo Molnar
@ 2019-11-01 18:48 ` Linus Torvalds
  2019-11-01 20:30   ` Ingo Molnar
  2019-11-01 19:10 ` pr-tracker-bot
  1 sibling, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2019-11-01 18:48 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Alexander Shishkin,
	Mark Rutland, Thomas Gleixner

On Fri, Nov 1, 2019 at 10:48 AM Ingo Molnar <mingo@kernel.org> wrote:
>
> Alexander Shishkin (1):
>       perf/core: Start rejecting the syscall with attr.__reserved_2 set

This seems to quite possibly break existing apps. Is there any reason
to believe that existing users have actually cleared that field?

It's suspect for another reason too: the commit that added that field
just added it to the end of the structure, with the argument that
"aux_watermark will only matter for new AUX-aware code, so the old
code should still be fine".

So by *definition* those old kinds of users would never have cleared
that field, because that field didn't exist.

Honestly, this all shows a worrying complete disregard for backwards
compatibility. Calling this a "fix" is questionable, when it is much
more likely to break some old user.

I've pulled it, but I need people to be aware that this is utter
garbage, and that if anybody ever reports it, this needs to be
immediately reverted.

And the people involved should stop claiming this "fixes" anything,
and should look hard at their random ABI expansions and "fixes".

The original code that said "old users would not be impacted" is
correct. But this "fix" is very very very questionable indeed, and I
get the feeling that somebody doesn't understand what ABI is, when
they claim that this "fixes" anything.

      Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-11-01 17:48 Ingo Molnar
  2019-11-01 18:48 ` Linus Torvalds
  2019-11-01 19:10 ` pr-tracker-bot
  0 siblings, 2 replies; 376+ messages in thread
From: Ingo Molnar @ 2019-11-01 17:48 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Alexander Shishkin, Mark Rutland, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 652521d460cbfa24ef27717b4b28acfac4281be6 perf/headers: Fix spelling s/EACCESS/EACCES/, s/privilidge/privilege/

Misc fixes: an ABI fix for a reserved field, AMD IBS fixes, an Intel 
uncore PMU driver fix and a header typo fix.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Start rejecting the syscall with attr.__reserved_2 set

Geert Uytterhoeven (1):
      perf/headers: Fix spelling s/EACCESS/EACCES/, s/privilidge/privilege/

Kan Liang (1):
      perf/x86/uncore: Fix event group support

Kim Phillips (2):
      perf/x86/amd/ibs: Fix reading of the IBS OpData register and thus precise RIP validity
      perf/x86/amd/ibs: Handle erratum #420 only on the affected CPU family (10h)


 arch/x86/events/amd/ibs.c      |  8 +++++---
 arch/x86/events/intel/uncore.c | 44 ++++++++++++++++++++++++++++++++++++------
 arch/x86/events/intel/uncore.h | 12 ------------
 include/linux/perf_event.h     |  2 +-
 kernel/events/core.c           |  2 +-
 5 files changed, 45 insertions(+), 23 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 5b35b7ea5d72..26c36357c4c9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
 					  struct hw_perf_event *hwc, u64 config)
 {
 	config &= ~perf_ibs->cnt_mask;
-	wrmsrl(hwc->config_base, config);
+	if (boot_cpu_data.x86 == 0x10)
+		wrmsrl(hwc->config_base, config);
 	config &= ~perf_ibs->enable_mask;
 	wrmsrl(hwc->config_base, config);
 }
@@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = {
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
-	.cnt_mask		= IBS_OP_MAX_CNT,
+	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
+				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
 	.max_period		= IBS_OP_MAX_CNT << 4,
@@ -614,7 +616,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	if (event->attr.sample_type & PERF_SAMPLE_RAW)
 		offset_max = perf_ibs->offset_max;
 	else if (check_rip)
-		offset_max = 2;
+		offset_max = 3;
 	else
 		offset_max = 1;
 	do {
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 6fc2e06ab4c6..86467f85c383 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags)
 	local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
 	uncore_enable_event(box, event);
 
-	if (box->n_active == 1) {
-		uncore_enable_box(box);
+	if (box->n_active == 1)
 		uncore_pmu_start_hrtimer(box);
-	}
 }
 
 void uncore_pmu_event_stop(struct perf_event *event, int flags)
@@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags)
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
 
-		if (box->n_active == 0) {
-			uncore_disable_box(box);
+		if (box->n_active == 0)
 			uncore_pmu_cancel_hrtimer(box);
-		}
 	}
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
@@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	return ret;
 }
 
+static void uncore_pmu_enable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->enable_box)
+		uncore_pmu->type->ops->enable_box(box);
+}
+
+static void uncore_pmu_disable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->disable_box)
+		uncore_pmu->type->ops->disable_box(box);
+}
+
 static ssize_t uncore_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 		pmu->pmu = (struct pmu) {
 			.attr_groups	= pmu->type->attr_groups,
 			.task_ctx_nr	= perf_invalid_context,
+			.pmu_enable	= uncore_pmu_enable,
+			.pmu_disable	= uncore_pmu_disable,
 			.event_init	= uncore_pmu_event_init,
 			.add		= uncore_pmu_event_add,
 			.del		= uncore_pmu_event_del,
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index f36f7bebbc1b..bbfdaa720b45 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
 	return -EINVAL;
 }
 
-static inline void uncore_disable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->disable_box)
-		box->pmu->type->ops->disable_box(box);
-}
-
-static inline void uncore_enable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->enable_box)
-		box->pmu->type->ops->enable_box(box);
-}
-
 static inline void uncore_disable_event(struct intel_uncore_box *box,
 				struct perf_event *event)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 61448c19a132..68ccc5b1913b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -292,7 +292,7 @@ struct pmu {
 	 *  -EBUSY	-- @event is for this PMU but PMU temporarily unavailable
 	 *  -EINVAL	-- @event is for this PMU but @event is not valid
 	 *  -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported
-	 *  -EACCESS	-- @event is for this PMU, @event is valid, but no privilidges
+	 *  -EACCES	-- @event is for this PMU, @event is valid, but no privileges
 	 *
 	 *  0		-- @event is for this PMU and valid
 	 *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bb3748d29b04..aec8dba2bea4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10635,7 +10635,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	attr->size = size;
 
-	if (attr->__reserved_1)
+	if (attr->__reserved_1 || attr->__reserved_2)
 		return -EINVAL;
 
 	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-10-12 13:31 Ingo Molnar
@ 2019-10-12 22:35 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-10-12 22:35 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Andrew Morton

The pull request you sent on Sat, 12 Oct 2019 15:31:34 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/465a7e291fd4f056d81baf5d5ed557bdb44c5457

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-10-12 13:31 Ingo Molnar
  2019-10-12 22:35 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-10-12 13:31 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 52e92f409dede388b7dc3ee13491fbf7a80db935 perf/x86/cstate: Add Tiger Lake CPU support

Mostly tooling fixes, but also a couple of updates for new Intel models 
(which are technically hw-enablement, but to users it's a fix to perf 
behavior on those new CPUs - hope this is fine), an AUX inheritance fix, 
event time-sharing fix, and a fix for lost non-perf NMI events on AMD 
systems.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Fix inheritance of aux_output groups

Andi Kleen (2):
      perf script brstackinsn: Fix recovery from LBR/binary mismatch
      perf jevents: Fix period for Intel fixed counters

Arnaldo Carvalho de Melo (13):
      tools headers uapi: Sync drm/i915_drm.h with the kernel sources
      tools headers uapi: Sync asm-generic/mman-common.h with the kernel
      tools headers uapi: Sync linux/usbdevice_fs.h with the kernel sources
      tools headers uapi: Sync linux/fs.h with the kernel sources
      tools headers kvm: Sync kvm headers with the kernel sources
      perf tools: Propagate get_cpuid() error
      perf evsel: Fall back to global 'perf_env' in perf_evsel__env()
      perf annotate: Propagate perf_env__arch() error
      perf annotate: Fix the signedness of failure returns
      perf annotate: Propagate the symbol__annotate() error return
      perf annotate: Fix arch specific ->init() failure errors
      perf annotate: Return appropriate error code for allocation failures
      perf annotate: Don't return -1 for error when doing BPF disassembly

Ian Rogers (4):
      libsubcmd: Make _FORTIFY_SOURCE defines dependent on the feature
      perf tests: Avoid raising SEGV using an obvious NULL dereference
      perf docs: Allow man page date to be specified
      perf llvm: Don't access out-of-scope array

Kan Liang (8):
      perf/x86/intel: Add Comet Lake CPU support
      perf/x86/msr: Add Comet Lake CPU support
      perf/x86/cstate: Add Comet Lake CPU support
      perf/x86/msr: Add new CPU model numbers for Ice Lake
      perf/x86/cstate: Update C-state counters for Ice Lake
      perf/x86/intel: Add Tiger Lake CPU support
      perf/x86/msr: Add Tiger Lake CPU support
      perf/x86/cstate: Add Tiger Lake CPU support

Song Liu (2):
      perf/core: Rework memory accounting in perf_mmap()
      perf/core: Fix corner case in perf_rotate_context()

Steve MacLean (3):
      perf map: Fix overlapped map handling
      perf inject jit: Fix JIT_CODE_MOVE filename
      perf docs: Correct and clarify jitdump spec

Thomas Richter (2):
      perf vendor events s390: Add JSON transaction for machine type 8561
      perf vendor events s390: Use s390 machine name instead of type 8561

Tom Lendacky (1):
      perf/x86/amd: Change/fix NMI latency mitigation to use a timestamp


 arch/x86/events/amd/core.c                         |  30 ++--
 arch/x86/events/intel/core.c                       |   4 +
 arch/x86/events/intel/cstate.c                     |  44 +++--
 arch/x86/events/msr.c                              |   7 +
 kernel/events/core.c                               |  43 ++++-
 tools/arch/arm/include/uapi/asm/kvm.h              |   4 +-
 tools/arch/arm64/include/uapi/asm/kvm.h            |   4 +-
 tools/arch/s390/include/uapi/asm/kvm.h             |   6 +
 tools/arch/x86/include/uapi/asm/vmx.h              |   2 +
 tools/include/uapi/asm-generic/mman-common.h       |   3 +
 tools/include/uapi/drm/i915_drm.h                  |   1 +
 tools/include/uapi/linux/fs.h                      |  55 +------
 tools/include/uapi/linux/fscrypt.h                 | 181 +++++++++++++++++++++
 tools/include/uapi/linux/kvm.h                     |   3 +
 tools/include/uapi/linux/usbdevice_fs.h            |   4 +
 tools/lib/subcmd/Makefile                          |   8 +-
 tools/perf/Documentation/asciidoc.conf             |   3 +
 tools/perf/Documentation/jitdump-specification.txt |   4 +-
 tools/perf/arch/arm/annotate/instructions.c        |   4 +-
 tools/perf/arch/arm64/annotate/instructions.c      |   4 +-
 tools/perf/arch/powerpc/util/header.c              |   3 +-
 tools/perf/arch/s390/annotate/instructions.c       |   6 +-
 tools/perf/arch/s390/util/header.c                 |   9 +-
 tools/perf/arch/x86/annotate/instructions.c        |   6 +-
 tools/perf/arch/x86/util/header.c                  |   3 +-
 tools/perf/builtin-kvm.c                           |   7 +-
 tools/perf/builtin-script.c                        |   6 +-
 tools/perf/check-headers.sh                        |   1 +
 .../arch/s390/{cf_m8561 => cf_z15}/basic.json      |   0
 .../arch/s390/{cf_m8561 => cf_z15}/crypto.json     |   0
 .../arch/s390/{cf_m8561 => cf_z15}/crypto6.json    |   0
 .../arch/s390/{cf_m8561 => cf_z15}/extended.json   |   0
 .../pmu-events/arch/s390/cf_z15/transaction.json   |   7 +
 tools/perf/pmu-events/arch/s390/mapfile.csv        |   2 +-
 tools/perf/pmu-events/jevents.c                    |  12 +-
 tools/perf/tests/perf-hooks.c                      |   3 +-
 tools/perf/util/annotate.c                         |  35 +++-
 tools/perf/util/annotate.h                         |   4 +
 tools/perf/util/evsel.c                            |   3 +-
 tools/perf/util/jitdump.c                          |   6 +-
 tools/perf/util/llvm-utils.c                       |   6 +-
 tools/perf/util/map.c                              |   3 +
 tools/perf/util/python.c                           |   6 +
 43 files changed, 411 insertions(+), 131 deletions(-)
 create mode 100644 tools/include/uapi/linux/fscrypt.h
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/basic.json (100%)
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/crypto.json (100%)
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/crypto6.json (100%)
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/extended.json (100%)
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/transaction.json

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e7d35f60d53f..64c3e70b0556 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -5,12 +5,14 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/jiffies.h>
 #include <asm/apicdef.h>
 #include <asm/nmi.h>
 
 #include "../perf_event.h"
 
-static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp);
+static unsigned long perf_nmi_window;
 
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -641,11 +643,12 @@ static void amd_pmu_disable_event(struct perf_event *event)
  * handler when multiple PMCs are active or PMC overflow while handling some
  * other source of an NMI.
  *
- * Attempt to mitigate this by using the number of active PMCs to determine
- * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
- * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
- * number of active PMCs or 2. The value of 2 is used in case an NMI does not
- * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ * Attempt to mitigate this by creating an NMI window in which un-handled NMIs
+ * received during this window will be claimed. This prevents extending the
+ * window past when it is possible that latent NMIs should be received. The
+ * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has
+ * handled a counter. When an un-handled NMI is received, it will be claimed
+ * only if arriving within that window.
  */
 static int amd_pmu_handle_irq(struct pt_regs *regs)
 {
@@ -663,21 +666,19 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	handled = x86_pmu_handle_irq(regs);
 
 	/*
-	 * If a counter was handled, record the number of possible remaining
-	 * NMIs that can occur.
+	 * If a counter was handled, record a timestamp such that un-handled
+	 * NMIs will be claimed if arriving within that window.
 	 */
 	if (handled) {
-		this_cpu_write(perf_nmi_counter,
-			       min_t(unsigned int, 2, active));
+		this_cpu_write(perf_nmi_tstamp,
+			       jiffies + perf_nmi_window);
 
 		return handled;
 	}
 
-	if (!this_cpu_read(perf_nmi_counter))
+	if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp)))
 		return NMI_DONE;
 
-	this_cpu_dec(perf_nmi_counter);
-
 	return NMI_HANDLED;
 }
 
@@ -909,6 +910,9 @@ static int __init amd_core_pmu_init(void)
 	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
+	/* Avoid calulating the value each time in the NMI handler */
+	perf_nmi_window = msecs_to_jiffies(100);
+
 	switch (boot_cpu_data.x86) {
 	case 0x15:
 		pr_cont("Fam15h ");
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 27ee47a7be66..fcef678c3423 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4983,6 +4983,8 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_SKYLAKE:
 	case INTEL_FAM6_KABYLAKE_L:
 	case INTEL_FAM6_KABYLAKE:
+	case INTEL_FAM6_COMETLAKE_L:
+	case INTEL_FAM6_COMETLAKE:
 		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -5031,6 +5033,8 @@ __init int intel_pmu_init(void)
 		/* fall through */
 	case INTEL_FAM6_ICELAKE_L:
 	case INTEL_FAM6_ICELAKE:
+	case INTEL_FAM6_TIGERLAKE_L:
+	case INTEL_FAM6_TIGERLAKE:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f2f39003d96..e1daf4151e11 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -45,46 +45,49 @@
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
-						CNL
+ *						CNL,KBL,CML
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
- *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
+ *						ICL,TGL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
+ *						KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL
+ *						GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
+ *						KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,KBL,CNL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,KBL,CNL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *
  */
@@ -544,6 +547,19 @@ static const struct cstate_model cnl_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model icl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C7_RES) |
+				  BIT(PERF_CSTATE_PKG_C8_RES) |
+				  BIT(PERF_CSTATE_PKG_C9_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 static const struct cstate_model slm_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
@@ -614,6 +630,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE,   hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates),
 
@@ -625,8 +643,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b1afc77f0704..6f86650b3f77 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,7 +89,14 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_L:
 	case INTEL_FAM6_KABYLAKE:
+	case INTEL_FAM6_COMETLAKE_L:
+	case INTEL_FAM6_COMETLAKE:
 	case INTEL_FAM6_ICELAKE_L:
+	case INTEL_FAM6_ICELAKE:
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_D:
+	case INTEL_FAM6_TIGERLAKE_L:
+	case INTEL_FAM6_TIGERLAKE:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3f0cb82e4fbc..9ec0b0bfddbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3779,11 +3779,23 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event)
 	perf_event_groups_insert(&ctx->flexible_groups, event);
 }
 
+/* pick an event from the flexible_groups to rotate */
 static inline struct perf_event *
-ctx_first_active(struct perf_event_context *ctx)
+ctx_event_to_rotate(struct perf_event_context *ctx)
 {
-	return list_first_entry_or_null(&ctx->flexible_active,
-					struct perf_event, active_list);
+	struct perf_event *event;
+
+	/* pick the first active flexible event */
+	event = list_first_entry_or_null(&ctx->flexible_active,
+					 struct perf_event, active_list);
+
+	/* if no active flexible event, pick the first event */
+	if (!event) {
+		event = rb_entry_safe(rb_first(&ctx->flexible_groups.tree),
+				      typeof(*event), group_node);
+	}
+
+	return event;
 }
 
 static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
@@ -3808,9 +3820,9 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
 	if (task_rotate)
-		task_event = ctx_first_active(task_ctx);
+		task_event = ctx_event_to_rotate(task_ctx);
 	if (cpu_rotate)
-		cpu_event = ctx_first_active(&cpuctx->ctx);
+		cpu_event = ctx_event_to_rotate(&cpuctx->ctx);
 
 	/*
 	 * As per the order given at ctx_resched() first 'pop' task flexible
@@ -5668,7 +5680,8 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	 * undo the VM accounting.
 	 */
 
-	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked,
+			&mmap_user->locked_vm);
 	atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm);
 	free_uid(mmap_user);
 
@@ -5812,8 +5825,20 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
 
-	if (user_locked > user_lock_limit)
+	if (user_locked <= user_lock_limit) {
+		/* charge all to locked_vm */
+	} else if (atomic_long_read(&user->locked_vm) >= user_lock_limit) {
+		/* charge all to pinned_vm */
+		extra = user_extra;
+		user_extra = 0;
+	} else {
+		/*
+		 * charge locked_vm until it hits user_lock_limit;
+		 * charge the rest from pinned_vm
+		 */
 		extra = user_locked - user_lock_limit;
+		user_extra -= extra;
+	}
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
@@ -11862,6 +11887,10 @@ static int inherit_group(struct perf_event *parent_event,
 					    child, leader, child_ctx);
 		if (IS_ERR(child_ctr))
 			return PTR_ERR(child_ctr);
+
+		if (sub->aux_event == parent_event &&
+		    !perf_get_aux_event(child_ctr, leader))
+			return -EINVAL;
 	}
 	return 0;
 }
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a4217c1a5d01..2769360f195c 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -266,8 +266,10 @@ struct kvm_vcpu_events {
 #define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 9a507716ae2f..67c21f9bdbad 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -325,8 +325,10 @@ struct kvm_vcpu_events {
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 47104e5b47fd..436ec7636927 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -231,6 +231,12 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
 #define KVM_SYNC_ETOKEN (1UL << 11)
+
+#define KVM_SYNC_S390_VALID_FIELDS \
+	(KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \
+	 KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \
+	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN)
+
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..f01950aa7fae 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -31,6 +31,7 @@
 #define EXIT_REASON_EXCEPTION_NMI       0
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
+#define EXIT_REASON_INIT_SIGNAL			3
 
 #define EXIT_REASON_PENDING_INTERRUPT   7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -90,6 +91,7 @@
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
+	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
 	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 63b1f506ea67..c160a5354eb6 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -67,6 +67,9 @@
 #define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
 #define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
 
+#define MADV_COLD	20		/* deactivate these pages */
+#define MADV_PAGEOUT	21		/* reclaim these pages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 328d05e77d9f..469dc512cca3 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -521,6 +521,7 @@ typedef struct drm_i915_irq_wait {
 #define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
 #define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
 #define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
+#define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
 
 #define I915_PARAM_HUC_STATUS		 42
 
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 2a616aa3f686..379a612f8f1d 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -13,6 +13,9 @@
 #include <linux/limits.h>
 #include <linux/ioctl.h>
 #include <linux/types.h>
+#ifndef __KERNEL__
+#include <linux/fscrypt.h>
+#endif
 
 /* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
 #if !defined(__KERNEL__)
@@ -212,57 +215,6 @@ struct fsxattr {
 #define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
 #define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
 
-/*
- * File system encryption support
- */
-/* Policy provided via an ioctl on the topmost directory */
-#define FS_KEY_DESCRIPTOR_SIZE	8
-
-#define FS_POLICY_FLAGS_PAD_4		0x00
-#define FS_POLICY_FLAGS_PAD_8		0x01
-#define FS_POLICY_FLAGS_PAD_16		0x02
-#define FS_POLICY_FLAGS_PAD_32		0x03
-#define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAG_DIRECT_KEY	0x04	/* use master key directly */
-#define FS_POLICY_FLAGS_VALID		0x07
-
-/* Encryption algorithms */
-#define FS_ENCRYPTION_MODE_INVALID		0
-#define FS_ENCRYPTION_MODE_AES_256_XTS		1
-#define FS_ENCRYPTION_MODE_AES_256_GCM		2
-#define FS_ENCRYPTION_MODE_AES_256_CBC		3
-#define FS_ENCRYPTION_MODE_AES_256_CTS		4
-#define FS_ENCRYPTION_MODE_AES_128_CBC		5
-#define FS_ENCRYPTION_MODE_AES_128_CTS		6
-#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
-#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
-#define FS_ENCRYPTION_MODE_ADIANTUM		9
-
-struct fscrypt_policy {
-	__u8 version;
-	__u8 contents_encryption_mode;
-	__u8 filenames_encryption_mode;
-	__u8 flags;
-	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
-#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
-
-/* Parameters for passing an encryption key into the kernel keyring */
-#define FS_KEY_DESC_PREFIX		"fscrypt:"
-#define FS_KEY_DESC_PREFIX_SIZE		8
-
-/* Structure that userspace passes to the kernel keyring */
-#define FS_MAX_KEY_SIZE			64
-
-struct fscrypt_key {
-	__u32 mode;
-	__u8 raw[FS_MAX_KEY_SIZE];
-	__u32 size;
-};
-
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
  *
@@ -306,6 +258,7 @@ struct fscrypt_key {
 #define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
 #define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
 #define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_VERITY_FL			0x00100000 /* Verity protected inode */
 #define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
 #define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
 #define FS_NOCOW_FL			0x00800000 /* Do not cow file */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
new file mode 100644
index 000000000000..39ccfe9311c3
--- /dev/null
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * fscrypt user API
+ *
+ * These ioctls can be used on filesystems that support fscrypt.  See the
+ * "User API" section of Documentation/filesystems/fscrypt.rst.
+ */
+#ifndef _UAPI_LINUX_FSCRYPT_H
+#define _UAPI_LINUX_FSCRYPT_H
+
+#include <linux/types.h>
+
+/* Encryption policy flags */
+#define FSCRYPT_POLICY_FLAGS_PAD_4		0x00
+#define FSCRYPT_POLICY_FLAGS_PAD_8		0x01
+#define FSCRYPT_POLICY_FLAGS_PAD_16		0x02
+#define FSCRYPT_POLICY_FLAGS_PAD_32		0x03
+#define FSCRYPT_POLICY_FLAGS_PAD_MASK		0x03
+#define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
+#define FSCRYPT_POLICY_FLAGS_VALID		0x07
+
+/* Encryption algorithms */
+#define FSCRYPT_MODE_AES_256_XTS		1
+#define FSCRYPT_MODE_AES_256_CTS		4
+#define FSCRYPT_MODE_AES_128_CBC		5
+#define FSCRYPT_MODE_AES_128_CTS		6
+#define FSCRYPT_MODE_ADIANTUM			9
+#define __FSCRYPT_MODE_MAX			9
+
+/*
+ * Legacy policy version; ad-hoc KDF and no key verification.
+ * For new encrypted directories, use fscrypt_policy_v2 instead.
+ *
+ * Careful: the .version field for this is actually 0, not 1.
+ */
+#define FSCRYPT_POLICY_V1		0
+#define FSCRYPT_KEY_DESCRIPTOR_SIZE	8
+struct fscrypt_policy_v1 {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+};
+#define fscrypt_policy	fscrypt_policy_v1
+
+/*
+ * Process-subscribed "logon" key description prefix and payload format.
+ * Deprecated; prefer FS_IOC_ADD_ENCRYPTION_KEY instead.
+ */
+#define FSCRYPT_KEY_DESC_PREFIX		"fscrypt:"
+#define FSCRYPT_KEY_DESC_PREFIX_SIZE	8
+#define FSCRYPT_MAX_KEY_SIZE		64
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FSCRYPT_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * New policy version with HKDF and key verification (recommended).
+ */
+#define FSCRYPT_POLICY_V2		2
+#define FSCRYPT_KEY_IDENTIFIER_SIZE	16
+struct fscrypt_policy_v2 {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 __reserved[4];
+	__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */
+struct fscrypt_get_policy_ex_arg {
+	__u64 policy_size; /* input/output */
+	union {
+		__u8 version;
+		struct fscrypt_policy_v1 v1;
+		struct fscrypt_policy_v2 v2;
+	} policy; /* output */
+};
+
+/*
+ * v1 policy keys are specified by an arbitrary 8-byte key "descriptor",
+ * matching fscrypt_policy_v1::master_key_descriptor.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR	1
+
+/*
+ * v2 policy keys are specified by a 16-byte key "identifier" which the kernel
+ * calculates as a cryptographic hash of the key itself,
+ * matching fscrypt_policy_v2::master_key_identifier.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER	2
+
+/*
+ * Specifies a key, either for v1 or v2 policies.  This doesn't contain the
+ * actual key itself; this is just the "name" of the key.
+ */
+struct fscrypt_key_specifier {
+	__u32 type;	/* one of FSCRYPT_KEY_SPEC_TYPE_* */
+	__u32 __reserved;
+	union {
+		__u8 __reserved[32]; /* reserve some extra space */
+		__u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+		__u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+	} u;
+};
+
+/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
+struct fscrypt_add_key_arg {
+	struct fscrypt_key_specifier key_spec;
+	__u32 raw_size;
+	__u32 __reserved[9];
+	__u8 raw[];
+};
+
+/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */
+struct fscrypt_remove_key_arg {
+	struct fscrypt_key_specifier key_spec;
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY	0x00000001
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS	0x00000002
+	__u32 removal_status_flags;	/* output */
+	__u32 __reserved[5];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
+struct fscrypt_get_key_status_arg {
+	/* input */
+	struct fscrypt_key_specifier key_spec;
+	__u32 __reserved[6];
+
+	/* output */
+#define FSCRYPT_KEY_STATUS_ABSENT		1
+#define FSCRYPT_KEY_STATUS_PRESENT		2
+#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED	3
+	__u32 status;
+#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF   0x00000001
+	__u32 status_flags;
+	__u32 user_count;
+	__u32 __out_reserved[13];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT		_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY_EX		_IOWR('f', 22, __u8[9]) /* size + version */
+#define FS_IOC_ADD_ENCRYPTION_KEY		_IOWR('f', 23, struct fscrypt_add_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS	_IOWR('f', 25, struct fscrypt_remove_key_arg)
+#define FS_IOC_GET_ENCRYPTION_KEY_STATUS	_IOWR('f', 26, struct fscrypt_get_key_status_arg)
+
+/**********************************************************************/
+
+/* old names; don't add anything new here! */
+#ifndef __KERNEL__
+#define FS_KEY_DESCRIPTOR_SIZE		FSCRYPT_KEY_DESCRIPTOR_SIZE
+#define FS_POLICY_FLAGS_PAD_4		FSCRYPT_POLICY_FLAGS_PAD_4
+#define FS_POLICY_FLAGS_PAD_8		FSCRYPT_POLICY_FLAGS_PAD_8
+#define FS_POLICY_FLAGS_PAD_16		FSCRYPT_POLICY_FLAGS_PAD_16
+#define FS_POLICY_FLAGS_PAD_32		FSCRYPT_POLICY_FLAGS_PAD_32
+#define FS_POLICY_FLAGS_PAD_MASK	FSCRYPT_POLICY_FLAGS_PAD_MASK
+#define FS_POLICY_FLAG_DIRECT_KEY	FSCRYPT_POLICY_FLAG_DIRECT_KEY
+#define FS_POLICY_FLAGS_VALID		FSCRYPT_POLICY_FLAGS_VALID
+#define FS_ENCRYPTION_MODE_INVALID	0	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_XTS	FSCRYPT_MODE_AES_256_XTS
+#define FS_ENCRYPTION_MODE_AES_256_GCM	2	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CBC	3	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CTS	FSCRYPT_MODE_AES_256_CTS
+#define FS_ENCRYPTION_MODE_AES_128_CBC	FSCRYPT_MODE_AES_128_CBC
+#define FS_ENCRYPTION_MODE_AES_128_CTS	FSCRYPT_MODE_AES_128_CTS
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7	/* removed */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8	/* removed */
+#define FS_ENCRYPTION_MODE_ADIANTUM	FSCRYPT_MODE_ADIANTUM
+#define FS_KEY_DESC_PREFIX		FSCRYPT_KEY_DESC_PREFIX
+#define FS_KEY_DESC_PREFIX_SIZE		FSCRYPT_KEY_DESC_PREFIX_SIZE
+#define FS_MAX_KEY_SIZE			FSCRYPT_MAX_KEY_SIZE
+#endif /* !__KERNEL__ */
+
+#endif /* _UAPI_LINUX_FSCRYPT_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 5e3f12d5359e..233efbb1c81c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -243,6 +243,8 @@ struct kvm_hyperv_exit {
 #define KVM_INTERNAL_ERROR_SIMUL_EX	2
 /* Encounter unexpected vm-exit due to delivery event. */
 #define KVM_INTERNAL_ERROR_DELIVERY_EV	3
+/* Encounter unexpected vm-exit reason */
+#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -996,6 +998,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
index 78efe870c2b7..cf525cddeb94 100644
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -158,6 +158,7 @@ struct usbdevfs_hub_portinfo {
 #define USBDEVFS_CAP_MMAP			0x20
 #define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
 #define USBDEVFS_CAP_CONNINFO_EX		0x80
+#define USBDEVFS_CAP_SUSPEND			0x100
 
 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */
 
@@ -223,5 +224,8 @@ struct usbdevfs_streams {
  * extending size of the data returned.
  */
 #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
+#define USBDEVFS_FORBID_SUSPEND    _IO('U', 33)
+#define USBDEVFS_ALLOW_SUSPEND     _IO('U', 34)
+#define USBDEVFS_WAIT_FOR_RESUME   _IO('U', 35)
 
 #endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index ed61fb3a46c0..5b2cd5e58df0 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -20,7 +20,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libsubcmd.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -fPIC
+
+ifeq ($(DEBUG),0)
+  ifeq ($(feature-fortify-source), 1)
+    CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2
+  endif
+endif
 
 ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
diff --git a/tools/perf/Documentation/asciidoc.conf b/tools/perf/Documentation/asciidoc.conf
index 356b23a40339..2b62ba1e72b7 100644
--- a/tools/perf/Documentation/asciidoc.conf
+++ b/tools/perf/Documentation/asciidoc.conf
@@ -71,6 +71,9 @@ ifdef::backend-docbook[]
 [header]
 template::[header-declarations]
 <refentry>
+ifdef::perf_date[]
+<refentryinfo><date>{perf_date}</date></refentryinfo>
+endif::perf_date[]
 <refmeta>
 <refentrytitle>{mantitle}</refentrytitle>
 <manvolnum>{manvolnum}</manvolnum>
diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt
index 4c62b0713651..52152d156ad9 100644
--- a/tools/perf/Documentation/jitdump-specification.txt
+++ b/tools/perf/Documentation/jitdump-specification.txt
@@ -36,8 +36,8 @@ III/ Jitdump file header format
 Each jitdump file starts with a fixed size header containing the following fields in order:
 
 
-* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It is 0x4A695444 or 0x4454694a depending on the endianness. The field can be used to detect the endianness of the file
-* uint32_t version   : a 4-byte value representing the format version. It is currently set to 2
+* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It written is as 0x4A695444. The reader will detect an endian mismatch when it reads 0x4454694a.
+* uint32_t version   : a 4-byte value representing the format version. It is currently set to 1
 * uint32_t total_size: size in bytes of file header
 * uint32_t elf_mach  : ELF architecture encoding (ELF e_machine value as specified in /usr/include/elf.h)
 * uint32_t pad1      : padding. Reserved for future use
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index e1d4b484cc4b..2ff6cedeb9c5 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -37,7 +37,7 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 
 	arm = zalloc(sizeof(*arm));
 	if (!arm)
-		return -1;
+		return ENOMEM;
 
 #define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)"
 	err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED);
@@ -59,5 +59,5 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	regfree(&arm->call_insn);
 out_free_arm:
 	free(arm);
-	return -1;
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
 }
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 43aa93ed8414..037e292ecd8e 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -95,7 +95,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 
 	arm = zalloc(sizeof(*arm));
 	if (!arm)
-		return -1;
+		return ENOMEM;
 
 	/* bl, blr */
 	err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
@@ -118,5 +118,5 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	regfree(&arm->call_insn);
 out_free_arm:
 	free(arm);
-	return -1;
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
 }
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index b6b7bc7e31a1..3b4cdfc5efd6 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -30,7 +31,7 @@ get_cpuid(char *buffer, size_t sz)
 		buffer[nb-1] = '\0';
 		return 0;
 	}
-	return -1;
+	return ENOBUFS;
 }
 
 char *
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 89bb8f2c54ce..a50e70baf918 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -164,8 +164,10 @@ static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	if (!arch->initialized) {
 		arch->initialized = true;
 		arch->associate_instruction_ops = s390__associate_ins_ops;
-		if (cpuid)
-			err = s390__cpuid_parse(arch, cpuid);
+		if (cpuid) {
+			if (s390__cpuid_parse(arch, cpuid))
+				err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
+		}
 	}
 
 	return err;
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 8b0b018d896a..7933f6871c81 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -8,6 +8,7 @@
  */
 
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
@@ -54,7 +55,7 @@ int get_cpuid(char *buffer, size_t sz)
 
 	sysinfo = fopen(SYSINFO, "r");
 	if (sysinfo == NULL)
-		return -1;
+		return errno;
 
 	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
 		if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) {
@@ -89,7 +90,7 @@ int get_cpuid(char *buffer, size_t sz)
 
 	/* Missing manufacturer, type or model information should not happen */
 	if (!manufacturer[0] || !type[0] || !model[0])
-		return -1;
+		return EINVAL;
 
 	/*
 	 * Scan /proc/service_levels and return the CPU-MF counter facility
@@ -133,14 +134,14 @@ int get_cpuid(char *buffer, size_t sz)
 	else
 		nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type,
 				  model);
-	return (nbytes >= sz) ? -1 : 0;
+	return (nbytes >= sz) ? ENOBUFS : 0;
 }
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *buf = malloc(128);
 
-	if (buf && get_cpuid(buf, 128) < 0)
+	if (buf && get_cpuid(buf, 128))
 		zfree(&buf);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 44f5aba78210..7eb5621c021d 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -196,8 +196,10 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 	if (arch->initialized)
 		return 0;
 
-	if (cpuid)
-		err = x86__cpuid_parse(arch, cpuid);
+	if (cpuid) {
+		if (x86__cpuid_parse(arch, cpuid))
+			err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
+	}
 
 	arch->initialized = true;
 	return err;
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 662ecf84a421..aa6deb463bf3 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -58,7 +59,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 		buffer[nb-1] = '\0';
 		return 0;
 	}
-	return -1;
+	return ENOBUFS;
 }
 
 int
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 2227e2f42c09..58a9e0989491 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -705,14 +705,15 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
-	char buf[64], *cpuid;
+	char buf[128], *cpuid;
 	int err;
 
 	if (kvm->live) {
 		err = get_cpuid(buf, sizeof(buf));
 		if (err != 0) {
-			pr_err("Failed to look up CPU type\n");
-			return err;
+			pr_err("Failed to look up CPU type: %s\n",
+			       str_error_r(err, buf, sizeof(buf)));
+			return -err;
 		}
 		cpuid = buf;
 	} else
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 286fc70d7402..67be8d31afab 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1063,7 +1063,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			continue;
 
 		insn = 0;
-		for (off = 0;; off += ilen) {
+		for (off = 0; off < (unsigned)len; off += ilen) {
 			uint64_t ip = start + off;
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
@@ -1074,6 +1074,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 					printed += print_srccode(thread, x.cpumode, ip);
 				break;
 			} else {
+				ilen = 0;
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
 						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
 				if (ilen == 0)
@@ -1083,6 +1084,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				insn++;
 			}
 		}
+		if (off != (unsigned)len)
+			printed += fprintf(fp, "\tmismatch of LBR data and executable\n");
 	}
 
 	/*
@@ -1123,6 +1126,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		goto out;
 	}
 	for (off = 0; off <= end - start; off += ilen) {
+		ilen = 0;
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index e2e0f06c97d0..cea13cb987d0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -8,6 +8,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fadvise.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/fs.h
+include/uapi/linux/fscrypt.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/basic.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/extended.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index bd3fc577139c..61641a3480e0 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -4,4 +4,4 @@ Family-model,Version,Filename,EventType
 ^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
-^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_m8561,core
+^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 9e37287da924..e2837260ca4d 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -450,12 +450,12 @@ static struct fixed {
 	const char *name;
 	const char *event;
 } fixed[] = {
-	{ "inst_retired.any", "event=0xc0" },
-	{ "inst_retired.any_p", "event=0xc0" },
-	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
-	{ "cpu_clk_unhalted.thread", "event=0x3c" },
-	{ "cpu_clk_unhalted.core", "event=0x3c" },
-	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
+	{ "inst_retired.any", "event=0xc0,period=2000003" },
+	{ "inst_retired.any_p", "event=0xc0,period=2000003" },
+	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03,period=2000003" },
+	{ "cpu_clk_unhalted.thread", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.core", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1,period=2000003" },
 	{ NULL, NULL},
 };
 
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index dbc27199c65e..dd865e0bea12 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -19,12 +19,11 @@ static void sigsegv_handler(int sig __maybe_unused)
 static void the_hook(void *_hook_flags)
 {
 	int *hook_flags = _hook_flags;
-	int *p = NULL;
 
 	*hook_flags = 1234;
 
 	/* Generate a segfault, test perf_hooks__recover */
-	*p = 0;
+	raise(SIGSEGV);
 }
 
 int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e830eadfca2a..4036c7f7b0fb 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1631,6 +1631,19 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
 	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
 		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
 		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+			  dso->long_name);
+		break;
 	default:
 		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
 		break;
@@ -1662,7 +1675,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 
 	build_id_path = strdup(filename);
 	if (!build_id_path)
-		return -1;
+		return ENOMEM;
 
 	/*
 	 * old style build-id cache has name of XX/XXXXXXX.. while
@@ -1713,13 +1726,13 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	char tpath[PATH_MAX];
 	size_t buf_size;
 	int nr_skip = 0;
-	int ret = -1;
 	char *buf;
 	bfd *bfdf;
+	int ret;
 	FILE *s;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
-		return -1;
+		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
 
 	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
 		  sym->name, sym->start, sym->end - sym->start);
@@ -1732,8 +1745,10 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	assert(bfd_check_format(bfdf, bfd_object));
 
 	s = open_memstream(&buf, &buf_size);
-	if (!s)
+	if (!s) {
+		ret = errno;
 		goto out;
+	}
 	init_disassemble_info(&info, s,
 			      (fprintf_ftype) fprintf);
 
@@ -1742,8 +1757,10 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 
 	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
 						 dso->bpf_prog.id);
-	if (!info_node)
+	if (!info_node) {
+		return SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
 		goto out;
+	}
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
@@ -2071,11 +2088,11 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 	int err;
 
 	if (!arch_name)
-		return -1;
+		return errno;
 
 	args.arch = arch = arch__find(arch_name);
 	if (arch == NULL)
-		return -ENOTSUP;
+		return ENOTSUP;
 
 	if (parch)
 		*parch = arch;
@@ -2971,7 +2988,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 
 	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
 	if (notes->offsets == NULL)
-		return -1;
+		return ENOMEM;
 
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
@@ -2997,7 +3014,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 
 out_free_offsets:
 	zfree(&notes->offsets);
-	return -1;
+	return err;
 }
 
 #define ANNOTATION__CFG(n) \
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index d94be9140e31..d76fd0e81f46 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -370,6 +370,10 @@ enum symbol_disassemble_errno {
 
 	SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX	= __SYMBOL_ANNOTATE_ERRNO__START,
 	SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP,
+	SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE,
+	SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF,
 
 	__SYMBOL_ANNOTATE_ERRNO__END,
 };
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5591af81a070..abc7fda4a0fe 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -30,6 +30,7 @@
 #include "counts.h"
 #include "event.h"
 #include "evsel.h"
+#include "util/env.h"
 #include "util/evsel_config.h"
 #include "util/evsel_fprintf.h"
 #include "evlist.h"
@@ -2512,7 +2513,7 @@ struct perf_env *perf_evsel__env(struct evsel *evsel)
 {
 	if (evsel && evsel->evlist)
 		return evsel->evlist->env;
-	return NULL;
+	return &perf_env;
 }
 
 static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 1bdf4c6ea3e5..e3ccb0ce1938 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -395,7 +395,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	size_t size;
 	u16 idr_size;
 	const char *sym;
-	uint32_t count;
+	uint64_t count;
 	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
@@ -418,7 +418,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 			jd->dir,
 			pid,
 			count);
@@ -529,7 +529,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 	         jd->dir,
 	         pid,
 		 jr->move.code_index);
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 8d04e3d070b1..8b14e4a7f1dc 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -233,14 +233,14 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *prefix_dir = "";
 	const char *suffix_dir = "";
 
+	/* _UTSNAME_LENGTH is 65 */
+	char release[128];
+
 	char *autoconf_path;
 
 	int err;
 
 	if (!test_dir) {
-		/* _UTSNAME_LENGTH is 65 */
-		char release[128];
-
 		err = fetch_kernel_version(NULL, release,
 					   sizeof(release));
 		if (err)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 5b83ed1ebbd6..eec9b282c047 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
+#include <assert.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -850,6 +851,8 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 53f31053a27a..02460362256d 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,6 +14,7 @@
 #include "thread_map.h"
 #include "trace-event.h"
 #include "mmap.h"
+#include "util/env.h"
 #include <internal/lib.h>
 #include "../perf-sys.h"
 
@@ -53,6 +54,11 @@ int parse_callchain_record(const char *arg __maybe_unused,
 	return 0;
 }
 
+/*
+ * Add this one here not to drag util/env.c
+ */
+struct perf_env perf_env;
+
 /*
  * Support debug printing even though util/debug.c is not linked.  That means
  * implementing 'verbose' and 'eprintf'.

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-07-14 12:01 Ingo Molnar
@ 2019-07-14 18:45 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-07-14 18:45 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sun, 14 Jul 2019 14:01:02 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/1d039859330b874d48080885eb31f4f129c246f1

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-07-14 12:01 Ingo Molnar
  2019-07-14 18:45 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-07-14 12:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e4557c1a46b0d32746bd309e1941914b5a6912b4 perf/x86/intel: Fix spurious NMI on fixed counter

A number of PMU driver corner case fixes, a race fix, an event grouping 
fix, plus a bunch of tooling fixes/updates.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf scripts python: export-to-postgresql.py: Fix DROP VIEW power_events_view
      perf scripts python: export-to-sqlite.py: Fix DROP VIEW power_events_view

Alexander Shishkin (1):
      perf/core: Fix exclusive events' grouping

Arnaldo Carvalho de Melo (9):
      perf inject: The tool->read() call may pass a NULL evsel, handle it
      perf evsel: perf_evsel__name(NULL) is valid, no need to check evsel
      perf tools: Add missing headers, mostly stdlib.h
      perf namespaces: Move the conditional setns() prototype to namespaces.h
      perf tools: Move get_current_dir_name() cond prototype out of util.h
      tools lib: Adopt zalloc()/zfree() from tools/perf
      perf tools: Use zfree() where applicable
      perf tools: Use list_del_init() more thorougly
      perf metricgroup: Add missing list_del_init() when flushing egroups list

Kan Liang (1):
      perf/x86/intel: Fix spurious NMI on fixed counter

Kim Phillips (2):
      perf/x86/amd/uncore: Do not set 'ThreadMask' and 'SliceMask' for non-L3 PMCs
      perf/x86/amd/uncore: Set the thread mask for F17h L3 PMCs

Leo Yan (10):
      perf stat: Fix use-after-freed pointer detected by the smatch tool
      perf top: Fix potential NULL pointer dereference detected by the smatch tool
      perf annotate: Fix dereferencing freed memory found by the smatch tool
      perf trace: Fix potential NULL pointer dereference found by the smatch tool
      perf map: Fix potential NULL pointer dereference found by smatch tool
      perf session: Fix potential NULL pointer dereference found by the smatch tool
      perf cs-etm: Fix potential NULL pointer dereference found by the smatch tool
      perf hists browser: Fix potential NULL pointer dereference found by the smatch tool
      perf intel-bts: Fix potential NULL pointer dereference found by the smatch tool
      perf intel-pt: Fix potential NULL pointer dereference found by the smatch tool

Luke Mujica (2):
      perf parse-events: Remove unused variable 'i'
      perf parse-events: Remove unused variable: error

Numfor Mbiziwo-Tiapo (1):
      perf test mmap-thread-lookup: Initialize variable to suppress memory sanitizer warning

Peter Zijlstra (1):
      perf/core: Fix race between close() and fork()

Song Liu (1):
      perf script: Assume native_arch for pipe mode


 arch/x86/events/amd/uncore.c                       | 15 ++--
 arch/x86/events/intel/core.c                       |  8 +--
 include/linux/perf_event.h                         |  5 ++
 kernel/events/core.c                               | 83 ++++++++++++++++------
 tools/include/linux/zalloc.h                       | 12 ++++
 tools/lib/zalloc.c                                 | 15 ++++
 tools/perf/MANIFEST                                |  1 +
 tools/perf/arch/arm/annotate/instructions.c        |  1 +
 tools/perf/arch/arm/util/auxtrace.c                |  1 +
 tools/perf/arch/arm/util/cs-etm.c                  |  1 +
 tools/perf/arch/arm64/util/arm-spe.c               |  1 +
 tools/perf/arch/common.c                           |  3 +-
 tools/perf/arch/powerpc/util/perf_regs.c           |  4 +-
 tools/perf/arch/s390/util/auxtrace.c               |  1 +
 tools/perf/arch/s390/util/header.c                 |  3 +-
 tools/perf/arch/x86/util/event.c                   |  2 +-
 tools/perf/arch/x86/util/intel-bts.c               |  2 +-
 tools/perf/arch/x86/util/intel-pt.c                |  2 +-
 tools/perf/arch/x86/util/perf_regs.c               |  2 +-
 tools/perf/bench/futex-hash.c                      |  3 +-
 tools/perf/bench/futex-lock-pi.c                   |  3 +-
 tools/perf/bench/mem-functions.c                   |  2 +-
 tools/perf/bench/numa.c                            |  2 +-
 tools/perf/builtin-annotate.c                      |  2 +-
 tools/perf/builtin-bench.c                         |  2 +-
 tools/perf/builtin-c2c.c                           |  2 +-
 tools/perf/builtin-config.c                        |  1 +
 tools/perf/builtin-diff.c                          |  2 +-
 tools/perf/builtin-ftrace.c                        |  2 +-
 tools/perf/builtin-help.c                          |  2 +
 tools/perf/builtin-inject.c                        |  2 +-
 tools/perf/builtin-kmem.c                          |  2 +-
 tools/perf/builtin-kvm.c                           |  2 +-
 tools/perf/builtin-lock.c                          | 10 +--
 tools/perf/builtin-probe.c                         |  2 +-
 tools/perf/builtin-record.c                        |  4 +-
 tools/perf/builtin-report.c                        |  4 +-
 tools/perf/builtin-sched.c                         |  2 +-
 tools/perf/builtin-script.c                        |  5 +-
 tools/perf/builtin-stat.c                          |  8 +--
 tools/perf/builtin-timechart.c                     |  4 +-
 tools/perf/builtin-top.c                           |  8 ++-
 tools/perf/builtin-trace.c                         |  7 +-
 tools/perf/perf.c                                  |  2 +-
 tools/perf/pmu-events/jevents.c                    |  2 +-
 tools/perf/scripts/python/export-to-postgresql.py  |  2 +-
 tools/perf/scripts/python/export-to-sqlite.py      |  2 +-
 tools/perf/tests/dwarf-unwind.c                    |  5 +-
 tools/perf/tests/expr.c                            |  3 +-
 tools/perf/tests/llvm.c                            |  1 +
 tools/perf/tests/mem2node.c                        |  3 +-
 tools/perf/tests/mmap-thread-lookup.c              |  2 +-
 tools/perf/tests/sample-parsing.c                  |  1 +
 tools/perf/tests/switch-tracking.c                 |  3 +-
 tools/perf/tests/thread-map.c                      |  3 +-
 tools/perf/tests/vmlinux-kallsyms.c                |  1 +
 tools/perf/ui/browser.c                            |  2 +-
 tools/perf/ui/browser.h                            |  1 +
 tools/perf/ui/browsers/annotate.c                  |  2 +-
 tools/perf/ui/browsers/hists.c                     | 17 +++--
 tools/perf/ui/browsers/map.c                       |  1 +
 tools/perf/ui/browsers/res_sample.c                |  6 +-
 tools/perf/ui/browsers/scripts.c                   |  4 +-
 tools/perf/ui/gtk/annotate.c                       |  2 +-
 tools/perf/ui/gtk/util.c                           |  3 +-
 tools/perf/ui/stdio/hist.c                         |  2 +-
 tools/perf/ui/tui/setup.c                          |  1 +
 tools/perf/ui/tui/util.c                           |  2 +-
 tools/perf/util/Build                              |  5 ++
 tools/perf/util/annotate.c                         | 13 ++--
 tools/perf/util/arm-spe.c                          |  2 +-
 tools/perf/util/auxtrace.c                         | 11 ++-
 tools/perf/util/bpf-loader.c                       |  3 +-
 tools/perf/util/build-id.c                         |  1 +
 tools/perf/util/call-path.c                        |  5 +-
 tools/perf/util/callchain.c                        | 12 ++--
 tools/perf/util/cgroup.c                           |  4 +-
 tools/perf/util/comm.c                             |  2 +-
 tools/perf/util/config.c                           |  3 +-
 tools/perf/util/counts.c                           |  2 +-
 tools/perf/util/cpumap.c                           |  2 +-
 tools/perf/util/cputopo.c                          |  5 +-
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c    |  1 +
 tools/perf/util/cs-etm.c                           |  8 +--
 tools/perf/util/data-convert-bt.c                  |  4 +-
 tools/perf/util/data.c                             |  3 +-
 tools/perf/util/db-export.c                        |  7 +-
 tools/perf/util/debug.c                            |  1 +
 tools/perf/util/demangle-java.c                    |  3 +-
 tools/perf/util/dso.c                              |  5 +-
 tools/perf/util/dwarf-aux.c                        |  2 +-
 tools/perf/util/env.c                              | 11 +--
 tools/perf/util/event.c                            |  3 +-
 tools/perf/util/evlist.c                           |  2 +-
 tools/perf/util/evsel.c                            |  4 +-
 tools/perf/util/get_current_dir_name.c             |  6 +-
 tools/perf/util/get_current_dir_name.h             |  8 +++
 tools/perf/util/header.c                           |  8 +--
 tools/perf/util/help-unknown-cmd.c                 |  2 +
 tools/perf/util/hist.c                             | 20 +++---
 tools/perf/util/intel-bts.c                        |  7 +-
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  |  2 +-
 tools/perf/util/intel-pt.c                         | 15 ++--
 tools/perf/util/jitdump.c                          |  7 +-
 tools/perf/util/llvm-utils.c                       |  4 +-
 tools/perf/util/machine.c                          |  6 +-
 tools/perf/util/map.c                              |  9 ++-
 tools/perf/util/mem2node.c                         |  2 +-
 tools/perf/util/metricgroup.c                      | 10 +--
 tools/perf/util/mmap.c                             |  1 +
 tools/perf/util/namespaces.c                       |  3 +-
 tools/perf/util/namespaces.h                       |  4 ++
 tools/perf/util/ordered-events.c                   |  6 +-
 tools/perf/util/parse-branch-options.c             |  2 +-
 tools/perf/util/parse-events.c                     |  3 +-
 tools/perf/util/parse-events.y                     |  2 -
 tools/perf/util/parse-regs-options.c               |  8 ++-
 tools/perf/util/pmu.c                              |  4 +-
 tools/perf/util/probe-event.c                      | 55 +++++++-------
 tools/perf/util/probe-file.c                       |  2 +-
 tools/perf/util/probe-finder.c                     |  2 +-
 tools/perf/util/pstack.c                           |  2 +-
 tools/perf/util/python-ext-sources                 |  1 +
 tools/perf/util/s390-cpumsf.c                      | 11 ++-
 tools/perf/util/session.c                          |  7 +-
 tools/perf/util/setns.c                            |  4 +-
 tools/perf/util/srccode.c                          | 11 +--
 tools/perf/util/srcline.c                          |  2 +-
 tools/perf/util/stat-shadow.c                      |  3 +-
 tools/perf/util/stat.c                             |  3 +-
 tools/perf/util/strbuf.c                           |  3 +-
 tools/perf/util/strfilter.c                        |  3 +-
 tools/perf/util/strlist.c                          |  2 +-
 tools/perf/util/svghelper.c                        |  2 +-
 tools/perf/util/symbol-elf.c                       | 18 ++---
 tools/perf/util/symbol-minimal.c                   |  3 +-
 tools/perf/util/symbol.c                           |  1 +
 tools/perf/util/syscalltbl.c                       |  2 +-
 tools/perf/util/target.c                           |  2 +-
 tools/perf/util/thread-stack.c                     |  3 +-
 tools/perf/util/thread.c                           |  6 +-
 tools/perf/util/thread_map.c                       |  4 +-
 tools/perf/util/trace-event-info.c                 |  1 +
 tools/perf/util/trace-event-scripting.c            |  2 +-
 tools/perf/util/unwind-libdw.c                     |  1 +
 tools/perf/util/unwind-libunwind-local.c           |  3 +-
 tools/perf/util/usage.c                            |  3 +
 tools/perf/util/util.h                             | 17 -----
 tools/perf/util/values.c                           |  2 +-
 tools/perf/util/vdso.c                             |  1 +
 tools/perf/util/xyarray.c                          |  2 +-
 151 files changed, 457 insertions(+), 308 deletions(-)
 create mode 100644 tools/include/linux/zalloc.h
 create mode 100644 tools/lib/zalloc.c
 create mode 100644 tools/perf/util/get_current_dir_name.h

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-06-29  8:54 Ingo Molnar
@ 2019-06-29 11:45 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-06-29 11:45 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sat, 29 Jun 2019 10:54:39 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/57103eb7c6cad04c0611b7a5767a381b34b8b0ab

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-06-29  8:54 Ingo Molnar
  2019-06-29 11:45 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-06-29  8:54 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 8b12b812f5367c2469fb937da7e28dd321ad8d7b perf/x86/regs: Use PERF_REG_EXTENDED_MASK

Various fixes, most of them related to bugs perf fuzzing found in the x86 
code.

 Thanks,

	Ingo

------------------>
Kan Liang (5):
      perf/x86: Disable extended registers for non-supported PMUs
      perf/x86/regs: Check reserved bits
      perf/x86: Clean up PEBS_XMM_REGS
      perf/x86: Remove pmu->pebs_no_xmm_regs
      perf/x86/regs: Use PERF_REG_EXTENDED_MASK

Peter Zijlstra (1):
      perf/core: Fix perf_sample_regs_user() mm check

Ravi Bangoria (1):
      perf/ioctl: Add check for the sample_period value


 arch/x86/events/core.c                      |  6 +++---
 arch/x86/events/intel/ds.c                  |  9 ++++-----
 arch/x86/events/perf_event.h                | 21 +--------------------
 arch/x86/include/uapi/asm/perf_regs.h       |  3 +++
 arch/x86/kernel/perf_regs.c                 |  7 +++++--
 include/linux/perf_event.h                  |  1 +
 include/linux/perf_regs.h                   |  8 ++++++++
 kernel/events/core.c                        | 23 ++++++++++++++++++-----
 tools/arch/x86/include/uapi/asm/perf_regs.h |  3 +++
 tools/perf/arch/x86/include/perf_regs.h     |  1 -
 tools/perf/arch/x86/util/perf_regs.c        |  4 ++--
 11 files changed, 48 insertions(+), 38 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f315425d8468..52a97463cb24 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -561,14 +561,14 @@ int x86_pmu_hw_config(struct perf_event *event)
 	}
 
 	/* sample_regs_user never support XMM registers */
-	if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+	if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK))
 		return -EINVAL;
 	/*
 	 * Besides the general purpose registers, XMM registers may
 	 * be collected in PEBS on some platforms, e.g. Icelake
 	 */
-	if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
-		if (x86_pmu.pebs_no_xmm_regs)
+	if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) {
+		if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS))
 			return -EINVAL;
 
 		if (!event->attr.precise_ip)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7acc526b4ad2..505c73dc6a73 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -987,7 +987,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 		pebs_data_cfg |= PEBS_DATACFG_GP;
 
 	if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
-	    (attr->sample_regs_intr & PEBS_XMM_REGS))
+	    (attr->sample_regs_intr & PERF_REG_EXTENDED_MASK))
 		pebs_data_cfg |= PEBS_DATACFG_XMMS;
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -1964,10 +1964,9 @@ void __init intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
-	if (x86_pmu.version <= 4) {
+	if (x86_pmu.version <= 4)
 		x86_pmu.pebs_no_isolation = 1;
-		x86_pmu.pebs_no_xmm_regs = 1;
-	}
+
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		char *pebs_qual = "";
@@ -2020,9 +2019,9 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
 				pebs_qual = "-baseline";
+				x86_get_pmu()->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
 				/* Only basic record supported */
-				x86_pmu.pebs_no_xmm_regs = 1;
 				x86_pmu.large_pebs_flags &=
 					~(PERF_SAMPLE_ADDR |
 					  PERF_SAMPLE_TIME |
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a6ac2f4f76fc..4e346856ee19 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -121,24 +121,6 @@ struct amd_nb {
 	 (1ULL << PERF_REG_X86_R14)   | \
 	 (1ULL << PERF_REG_X86_R15))
 
-#define PEBS_XMM_REGS                   \
-	((1ULL << PERF_REG_X86_XMM0)  | \
-	 (1ULL << PERF_REG_X86_XMM1)  | \
-	 (1ULL << PERF_REG_X86_XMM2)  | \
-	 (1ULL << PERF_REG_X86_XMM3)  | \
-	 (1ULL << PERF_REG_X86_XMM4)  | \
-	 (1ULL << PERF_REG_X86_XMM5)  | \
-	 (1ULL << PERF_REG_X86_XMM6)  | \
-	 (1ULL << PERF_REG_X86_XMM7)  | \
-	 (1ULL << PERF_REG_X86_XMM8)  | \
-	 (1ULL << PERF_REG_X86_XMM9)  | \
-	 (1ULL << PERF_REG_X86_XMM10) | \
-	 (1ULL << PERF_REG_X86_XMM11) | \
-	 (1ULL << PERF_REG_X86_XMM12) | \
-	 (1ULL << PERF_REG_X86_XMM13) | \
-	 (1ULL << PERF_REG_X86_XMM14) | \
-	 (1ULL << PERF_REG_X86_XMM15))
-
 /*
  * Per register state.
  */
@@ -668,8 +650,7 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1,
-			pebs_no_xmm_regs	:1;
+			pebs_no_isolation	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	int		max_pebs_events;
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index ac67bbea10ca..7c9d2bb3833b 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -52,4 +52,7 @@ enum perf_event_x86_regs {
 	/* These include both GPRs and XMMX registers */
 	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
+
+#define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
+
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 07c30ee17425..bb7e1132290b 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -74,6 +74,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
+#define PERF_REG_X86_RESERVED	(((1ULL << PERF_REG_X86_XMM0) - 1) & \
+				 ~((1ULL << PERF_REG_X86_MAX) - 1))
+
 #ifdef CONFIG_X86_32
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
 		       (1ULL << PERF_REG_X86_R9) | \
@@ -86,7 +89,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & REG_NOSUPPORT))
+	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
 		return -EINVAL;
 
 	return 0;
@@ -112,7 +115,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & REG_NOSUPPORT))
+	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
 		return -EINVAL;
 
 	return 0;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0ab99c7b652d..2bca72f3028b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -241,6 +241,7 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_NO_NMI			0x02
 #define PERF_PMU_CAP_AUX_NO_SG			0x04
+#define PERF_PMU_CAP_EXTENDED_REGS		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 476747456bca..2d12e97d5e7b 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -11,6 +11,11 @@ struct perf_regs {
 
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
+
+#ifndef PERF_REG_EXTENDED_MASK
+#define PERF_REG_EXTENDED_MASK	0
+#endif
+
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
@@ -18,6 +23,9 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 			struct pt_regs *regs,
 			struct pt_regs *regs_user_copy);
 #else
+
+#define PERF_REG_EXTENDED_MASK	0
+
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
 	return 0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index abbd4b3b96c2..f85929ce13be 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5005,6 +5005,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (perf_event_check_period(event, value))
 		return -EINVAL;
 
+	if (!event->attr.freq && (value & (1ULL << 63)))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -5923,7 +5926,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
-	} else if (current->mm) {
+	} else if (!(current->flags & PF_KTHREAD)) {
 		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
@@ -10033,6 +10036,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
+static inline bool has_extended_regs(struct perf_event *event)
+{
+	return (event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK) ||
+	       (event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK);
+}
+
 static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 {
 	struct perf_event_context *ctx = NULL;
@@ -10064,12 +10073,16 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 		perf_event_ctx_unlock(event->group_leader, ctx);
 
 	if (!ret) {
+		if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) &&
+		    has_extended_regs(event))
+			ret = -EOPNOTSUPP;
+
 		if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE &&
-				event_has_any_exclude_flag(event)) {
-			if (event->destroy)
-				event->destroy(event);
+		    event_has_any_exclude_flag(event))
 			ret = -EINVAL;
-		}
+
+		if (ret && event->destroy)
+			event->destroy(event);
 	}
 
 	if (ret)
diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
index ac67bbea10ca..7c9d2bb3833b 100644
--- a/tools/arch/x86/include/uapi/asm/perf_regs.h
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -52,4 +52,7 @@ enum perf_event_x86_regs {
 	/* These include both GPRs and XMMX registers */
 	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
+
+#define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
+
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index b7cd91a9014f..b7321337d100 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -9,7 +9,6 @@
 void perf_regs_load(u64 *regs);
 
 #define PERF_REGS_MAX PERF_REG_X86_XMM_MAX
-#define PERF_XMM_REGS_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
 #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 7886ca5263e3..3666c0076df9 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -277,7 +277,7 @@ uint64_t arch__intr_reg_mask(void)
 		.type			= PERF_TYPE_HARDWARE,
 		.config			= PERF_COUNT_HW_CPU_CYCLES,
 		.sample_type		= PERF_SAMPLE_REGS_INTR,
-		.sample_regs_intr	= PERF_XMM_REGS_MASK,
+		.sample_regs_intr	= PERF_REG_EXTENDED_MASK,
 		.precise_ip		= 1,
 		.disabled 		= 1,
 		.exclude_kernel		= 1,
@@ -293,7 +293,7 @@ uint64_t arch__intr_reg_mask(void)
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 	if (fd != -1) {
 		close(fd);
-		return (PERF_XMM_REGS_MASK | PERF_REGS_MASK);
+		return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK);
 	}
 
 	return PERF_REGS_MASK;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-06-02 17:39 Ingo Molnar
@ 2019-06-02 18:15 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-06-02 18:15 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sun, 2 Jun 2019 19:39:53 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/6751b8d91af515a5dc5196fe305eee0a635e2ea2

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-06-02 17:39 Ingo Molnar
  2019-06-02 18:15 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-06-02 17:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 849e96f30068d4f6f8352715e02a10533a46deba Merge tag 'perf-urgent-for-mingo-5.2-20190528' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

On the kernel side there's a bunch of ring-buffer ordering fixes for a 
reproducible bug, plus a PEBS constraints regression fix - plus tooling 
fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (8):
      tools include UAPI: Update copy of files related to new fspick, fsmount, fsconfig, fsopen, move_mount and open_tree syscalls
      tools arch x86: Sync asm/cpufeatures.h with the with the kernel
      tools headers UAPI: Sync linux/sched.h with the kernel
      tools headers UAPI: Sync linux/fs.h with the kernel
      tools headers UAPI: Sync drm/i915_drm.h with the kernel
      tools headers UAPI: Sync drm/drm.h with the kernel
      perf test vmlinux-kallsyms: Ignore aliases to _etext when searching on kallsyms
      tools headers UAPI: Sync kvm.h headers with the kernel sources

Jiri Olsa (1):
      perf machine: Read also the end of the kernel

Namhyung Kim (2):
      perf namespace: Protect reading thread's namespace
      perf session: Add missing swap ops for namespace events

Peter Zijlstra (3):
      perf/ring_buffer: Add ordering to rb->nest increment
      perf/ring-buffer: Always use {READ,WRITE}_ONCE() for rb->user_page data
      perf/ring-buffer: Use regular variables for nesting

Shawn Landden (1):
      perf data: Fix 'strncat may truncate' build failure with recent gcc

Stephane Eranian (1):
      perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints

Thomas Richter (1):
      perf record: Fix s390 missing module symbol and warning for non-root users

Vitaly Chikunov (1):
      perf arm64: Fix mksyscalltbl when system kernel headers are ahead of the kernel

Yabin Cui (1):
      perf/ring_buffer: Fix exposing a temporarily decreased data_head


 arch/x86/events/intel/ds.c                        |  28 +--
 kernel/events/internal.h                          |   4 +-
 kernel/events/ring_buffer.c                       |  64 ++++--
 tools/arch/arm64/include/uapi/asm/kvm.h           |  43 ++++
 tools/arch/powerpc/include/uapi/asm/kvm.h         |  46 ++++
 tools/arch/s390/include/uapi/asm/kvm.h            |   4 +-
 tools/arch/x86/include/asm/cpufeatures.h          |   3 +
 tools/include/uapi/asm-generic/unistd.h           |  14 +-
 tools/include/uapi/drm/drm.h                      |  37 ++++
 tools/include/uapi/drm/i915_drm.h                 | 254 +++++++++++++++-------
 tools/include/uapi/linux/fcntl.h                  |   2 +
 tools/include/uapi/linux/fs.h                     |   3 +
 tools/include/uapi/linux/kvm.h                    |  15 +-
 tools/include/uapi/linux/mount.h                  |  62 ++++++
 tools/include/uapi/linux/sched.h                  |   1 +
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl |   2 +-
 tools/perf/arch/s390/util/machine.c               |   9 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl |   6 +
 tools/perf/tests/vmlinux-kallsyms.c               |   9 +-
 tools/perf/util/data-convert-bt.c                 |   2 +-
 tools/perf/util/machine.c                         |  27 ++-
 tools/perf/util/session.c                         |  21 ++
 tools/perf/util/thread.c                          |  15 +-
 23 files changed, 547 insertions(+), 124 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-05-16 16:05 Ingo Molnar
@ 2019-05-16 18:20 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-05-16 18:20 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Thu, 16 May 2019 18:05:18 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/c77ee64f8a04166236666dfd540ff684d2daa1c0

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-05-16 16:05 Ingo Molnar
  2019-05-16 18:20 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-05-16 16:05 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c7a286577d7592720c2f179aadfb325a1ff48c95 perf/x86/intel: Allow PEBS multi-entry in watermark mode

An x86 PMU constraint fix, an interface fix, and a Sparse fix.

 Thanks,

	Ingo

------------------>
Stephane Eranian (2):
      perf/x86/intel: Fix INTEL_FLAGS_EVENT_CONSTRAINT* masking
      perf/x86/intel: Allow PEBS multi-entry in watermark mode

Wang Hai (1):
      perf/x86/amd/iommu: Make the 'amd_iommu_attr_groups' symbol static


 arch/x86/events/amd/iommu.c  | 2 +-
 arch/x86/events/intel/core.c | 2 +-
 arch/x86/events/perf_event.h | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 7635c23f7d82..58a6993d7eb3 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -393,7 +393,7 @@ static __init int _init_events_attrs(void)
 	return 0;
 }
 
-const struct attribute_group *amd_iommu_attr_groups[] = {
+static const struct attribute_group *amd_iommu_attr_groups[] = {
 	&amd_iommu_format_group,
 	&amd_iommu_cpumask_group,
 	&amd_iommu_events_group,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ef763f535e3a..12ec402f4114 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3265,7 +3265,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
-		if (!(event->attr.freq || event->attr.wakeup_events)) {
+		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
 			      ~intel_pmu_large_pebs_flags(event)))
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 07fc84bb85c1..a6ac2f4f76fc 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -394,10 +394,10 @@ struct cpu_hw_events {
 
 /* Event constraint, but match on all event flags too. */
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
-	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
 
 #define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n)			\
-	EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
 
 /* Check only flags, but allow all event/umask */
 #define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-04-20  7:43 Ingo Molnar
@ 2019-04-20 19:25 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-04-20 19:25 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Andrew Morton, Jiri Olsa

The pull request you sent on Sat, 20 Apr 2019 09:43:53 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b25c69b9d5e41159b54ad7cb33f7d9ead8523d33

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-04-20  7:43 Ingo Molnar
  2019-04-20 19:25 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-04-20  7:43 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Andrew Morton, Jiri Olsa

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7579dfc42d2e3bef901991803efc81dc1ac65f2b Merge tag 'perf-urgent-for-mingo-5.1-20190419' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc fixes:

 - various tooling fixes
 - kretprobe fixes
 - kprobes annotation fixes
 - kprobes error checking fix
 - fix the default events for AMD Family 17h CPUs
 - PEBS fix
 - AUX record fix
 - address filtering fix

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf scripts python: export-to-sqlite.py: Fix use of parent_id in calls_view

Alexander Shishkin (2):
      perf/core: Fix the address filtering fix
      perf/ring_buffer: Fix AUX record suppression

Arnaldo Carvalho de Melo (1):
      tools include uapi: Sync sound/asound.h copy

Gustavo A. R. Silva (1):
      perf header: Fix lock/unlock imbalances when processing BPF/BTF info

Jiri Olsa (6):
      perf stat: Disable DIR_FORMAT feature for 'perf stat record'
      perf top: Always sample time to satisfy needs of use of ordered queuing
      perf bpf: Return NULL when RB tree lookup fails in perf_env__find_bpf_prog_info()
      perf evlist: Fix side band thread draining
      perf tools: Fix map reference counting
      perf bpf: Return NULL when RB tree lookup fails in perf_env__find_btf()

Kan Liang (1):
      perf/x86: Fix incorrect PEBS_REGS

Kim Phillips (1):
      perf/x86/amd: Add event map for AMD Family 17h

Mao Han (1):
      perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user)

Masami Hiramatsu (4):
      kprobes: Fix error check when reusing optimized probes
      x86/kprobes: Verify stack frame on kretprobe
      kprobes: Mark ftrace mcount handler functions nokprobe
      x86/kprobes: Avoid kretprobe recursion bug

Rikard Falkeborn (1):
      tools lib traceevent: Fix missing equality check for strcmp

Song Liu (1):
      perf tools: Check maps for bpf programs


 arch/x86/events/amd/core.c                    | 35 ++++++++++++++-----
 arch/x86/events/intel/core.c                  |  2 +-
 arch/x86/events/perf_event.h                  | 38 ++++++++++-----------
 arch/x86/kernel/kprobes/core.c                | 48 +++++++++++++++++++++++++--
 include/linux/kprobes.h                       |  1 +
 kernel/events/core.c                          | 37 ++++++++++++---------
 kernel/events/ring_buffer.c                   | 33 +++++++++---------
 kernel/kprobes.c                              |  6 ++--
 kernel/trace/ftrace.c                         |  6 +++-
 tools/include/uapi/sound/asound.h             |  1 +
 tools/lib/traceevent/event-parse.c            |  2 +-
 tools/perf/builtin-stat.c                     |  1 +
 tools/perf/builtin-top.c                      |  1 +
 tools/perf/scripts/python/export-to-sqlite.py |  2 +-
 tools/perf/util/env.c                         |  8 +++--
 tools/perf/util/evlist.c                      | 14 +++++---
 tools/perf/util/evsel.c                       | 12 +++----
 tools/perf/util/header.c                      | 22 +++++++-----
 tools/perf/util/map.c                         | 20 +++++++++--
 tools/perf/util/map.h                         |  4 ++-
 20 files changed, 195 insertions(+), 98 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 0ecfac84ba91..d45f3fbd232e 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -117,22 +117,39 @@ static __initconst const u64 amd_hw_cache_event_ids
 };
 
 /*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
  */
 static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
-  [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
-  [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x077d,
-  [PERF_COUNT_HW_CACHE_MISSES]			= 0x077e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
-  [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
-  [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
-  [PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x077d,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x077e,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x0187,
 };
 
 static u64 amd_pmu_event_map(int hw_event)
 {
+	if (boot_cpu_data.x86 >= 0x17)
+		return amd_f17h_perfmon_event_map[hw_event];
+
 	return amd_perfmon_event_map[hw_event];
 }
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f61dcbef20ff..f9451566cd9b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 		flags &= ~PERF_SAMPLE_TIME;
 	if (!event->attr.exclude_kernel)
 		flags &= ~PERF_SAMPLE_REGS_USER;
-	if (event->attr.sample_regs_user & ~PEBS_REGS)
+	if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
 		flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
 	return flags;
 }
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..1e98a42b560a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -96,25 +96,25 @@ struct amd_nb {
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
 	PERF_SAMPLE_PERIOD)
 
-#define PEBS_REGS \
-	(PERF_REG_X86_AX | \
-	 PERF_REG_X86_BX | \
-	 PERF_REG_X86_CX | \
-	 PERF_REG_X86_DX | \
-	 PERF_REG_X86_DI | \
-	 PERF_REG_X86_SI | \
-	 PERF_REG_X86_SP | \
-	 PERF_REG_X86_BP | \
-	 PERF_REG_X86_IP | \
-	 PERF_REG_X86_FLAGS | \
-	 PERF_REG_X86_R8 | \
-	 PERF_REG_X86_R9 | \
-	 PERF_REG_X86_R10 | \
-	 PERF_REG_X86_R11 | \
-	 PERF_REG_X86_R12 | \
-	 PERF_REG_X86_R13 | \
-	 PERF_REG_X86_R14 | \
-	 PERF_REG_X86_R15)
+#define PEBS_GP_REGS			\
+	((1ULL << PERF_REG_X86_AX)    | \
+	 (1ULL << PERF_REG_X86_BX)    | \
+	 (1ULL << PERF_REG_X86_CX)    | \
+	 (1ULL << PERF_REG_X86_DX)    | \
+	 (1ULL << PERF_REG_X86_DI)    | \
+	 (1ULL << PERF_REG_X86_SI)    | \
+	 (1ULL << PERF_REG_X86_SP)    | \
+	 (1ULL << PERF_REG_X86_BP)    | \
+	 (1ULL << PERF_REG_X86_IP)    | \
+	 (1ULL << PERF_REG_X86_FLAGS) | \
+	 (1ULL << PERF_REG_X86_R8)    | \
+	 (1ULL << PERF_REG_X86_R9)    | \
+	 (1ULL << PERF_REG_X86_R10)   | \
+	 (1ULL << PERF_REG_X86_R11)   | \
+	 (1ULL << PERF_REG_X86_R12)   | \
+	 (1ULL << PERF_REG_X86_R13)   | \
+	 (1ULL << PERF_REG_X86_R14)   | \
+	 (1ULL << PERF_REG_X86_R15))
 
 /*
  * Per register state.
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..fed46ddb1eef 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	unsigned long *sara = stack_addr(regs);
 
 	ri->ret_addr = (kprobe_opcode_t *) *sara;
+	ri->fp = sara;
 
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
@@ -748,26 +749,48 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
+static struct kprobe kretprobe_kprobe = {
+	.addr = (void *)kretprobe_trampoline,
+};
+
 /*
  * Called from kretprobe_trampoline
  */
 static __used void *trampoline_handler(struct pt_regs *regs)
 {
+	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 	kprobe_opcode_t *correct_ret_addr = NULL;
+	void *frame_pointer;
+	bool skipped = false;
+
+	preempt_disable();
+
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never run in kprobe handler, kprobe must not
+	 * be running at this point.
+	 */
+	kcb = get_kprobe_ctlblk();
+	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
+	/* On x86-64, we use pt_regs->sp for return address holder. */
+	frame_pointer = &regs->sp;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
 	regs->gs = 0;
+	/* On x86-32, we use pt_regs->flags for return address holder. */
+	frame_pointer = &regs->flags;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
@@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be poped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
 
 		if (orig_ret_address != trampoline_address)
 			/*
@@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		if (ri->fp != frame_pointer)
+			continue;
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
+			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 201f0f2683f2..9a897256e481 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -173,6 +173,7 @@ struct kretprobe_instance {
 	struct kretprobe *rp;
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
+	void *fp;
 	char data[0];
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 534e01e7bc36..dc7dead2d2cc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9077,26 +9077,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	if (task == TASK_TOMBSTONE)
 		return;
 
-	if (!ifh->nr_file_filters)
-		return;
-
-	mm = get_task_mm(event->ctx->task);
-	if (!mm)
-		goto restart;
+	if (ifh->nr_file_filters) {
+		mm = get_task_mm(event->ctx->task);
+		if (!mm)
+			goto restart;
 
-	down_read(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
+	}
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		event->addr_filter_ranges[count].start = 0;
-		event->addr_filter_ranges[count].size = 0;
+		if (filter->path.dentry) {
+			/*
+			 * Adjust base offset if the filter is associated to a
+			 * binary that needs to be mapped:
+			 */
+			event->addr_filter_ranges[count].start = 0;
+			event->addr_filter_ranges[count].size = 0;
 
-		/*
-		 * Adjust base offset if the filter is associated to a binary
-		 * that needs to be mapped:
-		 */
-		if (filter->path.dentry)
 			perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]);
+		} else {
+			event->addr_filter_ranges[count].start = filter->offset;
+			event->addr_filter_ranges[count].size  = filter->size;
+		}
 
 		count++;
 	}
@@ -9104,9 +9107,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	event->addr_filters_gen++;
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
-	up_read(&mm->mmap_sem);
+	if (ifh->nr_file_filters) {
+		up_read(&mm->mmap_sem);
 
-	mmput(mm);
+		mmput(mm);
+	}
 
 restart:
 	perf_event_stop(event, 1);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 2545ac08cc77..5eedb49a65ea 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		rb->aux_head += size;
 	}
 
-	if (size || handle->aux_flags) {
-		/*
-		 * Only send RECORD_AUX if we have something useful to communicate
-		 *
-		 * Note: the OVERWRITE records by themselves are not considered
-		 * useful, as they don't communicate any *new* information,
-		 * aside from the short-lived offset, that becomes history at
-		 * the next event sched-in and therefore isn't useful.
-		 * The userspace that needs to copy out AUX data in overwrite
-		 * mode should know to use user_page::aux_head for the actual
-		 * offset. So, from now on we don't output AUX records that
-		 * have *only* OVERWRITE flag set.
-		 */
-
-		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
-			perf_event_aux_event(handle->event, aux_head, size,
-			                     handle->aux_flags);
-	}
+	/*
+	 * Only send RECORD_AUX if we have something useful to communicate
+	 *
+	 * Note: the OVERWRITE records by themselves are not considered
+	 * useful, as they don't communicate any *new* information,
+	 * aside from the short-lived offset, that becomes history at
+	 * the next event sched-in and therefore isn't useful.
+	 * The userspace that needs to copy out AUX data in overwrite
+	 * mode should know to use user_page::aux_head for the actual
+	 * offset. So, from now on we don't output AUX records that
+	 * have *only* OVERWRITE flag set.
+	 */
+	if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
+		perf_event_aux_event(handle->event, aux_head, size,
+				     handle->aux_flags);
 
 	rb->user_page->aux_head = rb->aux_head;
 	if (rb_need_aux_wakeup(rb))
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c83e54727131..b1ea30a5540e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 static int reuse_unused_kprobe(struct kprobe *ap)
 {
 	struct optimized_kprobe *op;
-	int ret;
 
 	/*
 	 * Unused kprobe MUST be on the way of delayed unoptimizing (means
@@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap)
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
-	ret = kprobe_optready(ap);
-	if (ret)
-		return ret;
+	if (!kprobe_optready(ap))
+		return -EINVAL;
 
 	optimize_kprobe(ap);
 	return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 26c8ca9bd06b..b920358dd8f7 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -33,6 +33,7 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/rcupdate.h>
+#include <linux/kprobes.h>
 
 #include <trace/events/sched.h>
 
@@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr)
 	tr->ops->func = ftrace_stub;
 }
 
-static inline void
+static nokprobe_inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
@@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
 }
+NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
+NOKPROBE_SYMBOL(ftrace_ops_no_ops);
 #endif
 
 /*
@@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
+NOKPROBE_SYMBOL(ftrace_ops_assist_func);
 
 /**
  * ftrace_ops_get_func - get the function a trampoline should call
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 404d4b9ffe76..df1153cea0b7 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -32,6 +32,7 @@
 
 #ifndef __KERNEL__
 #include <stdlib.h>
+#include <time.h>
 #endif
 
 /*
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 87494c7c619d..981c6ce2da2c 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2233,7 +2233,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 		return val & 0xffffffff;
 
 	if (strcmp(type, "u64") == 0 ||
-	    strcmp(type, "s64"))
+	    strcmp(type, "s64") == 0)
 		return val;
 
 	if (strcmp(type, "s8") == 0)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 49ee3c2033ec..c3625ec374e0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1308,6 +1308,7 @@ static void init_features(struct perf_session *session)
 	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
 		perf_header__set_feat(&session->header, feat);
 
+	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
 	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1999d6533d12..fbbb0da43abb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1377,6 +1377,7 @@ int cmd_top(int argc, const char **argv)
 			 * */
 			.overwrite	= 0,
 			.sample_time	= true,
+			.sample_time_set = true,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index 3b71902a5a21..bf271fbc3a88 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -331,7 +331,7 @@ if perf_db_export_calls:
 			'return_id,'
 			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
 			'parent_call_path_id,'
-			'parent_id'
+			'calls.parent_id'
 		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
 
 do_query(query, 'CREATE VIEW samples_view AS '
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index c6351b557bb0..9494f9dc61ec 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -57,9 +57,11 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 		else if (prog_id > node->info_linear->info.id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
+out:
 	up_read(&env->bpf_progs.lock);
 	return node;
 }
@@ -109,10 +111,12 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
 	up_read(&env->bpf_progs.lock);
+out:
 	return node;
 }
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6689378ee577..51ead577533f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1868,12 +1868,12 @@ static void *perf_evlist__poll_thread(void *arg)
 {
 	struct perf_evlist *evlist = arg;
 	bool draining = false;
-	int i;
+	int i, done = 0;
+
+	while (!done) {
+		bool got_data = false;
 
-	while (draining || !(evlist->thread.done)) {
-		if (draining)
-			draining = false;
-		else if (evlist->thread.done)
+		if (evlist->thread.done)
 			draining = true;
 
 		if (!draining)
@@ -1894,9 +1894,13 @@ static void *perf_evlist__poll_thread(void *arg)
 					pr_warning("cannot locate proper evsel for the side band event\n");
 
 				perf_mmap__consume(map);
+				got_data = true;
 			}
 			perf_mmap__read_done(map);
 		}
+
+		if (draining && !got_data)
+			break;
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 66d066f18b5b..966360844fff 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2368,7 +2368,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->user_regs.abi) {
 			u64 mask = evsel->attr.sample_regs_user;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
@@ -2424,7 +2424,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
 			u64 mask = evsel->attr.sample_regs_intr;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->intr_regs.mask = mask;
 			data->intr_regs.regs = (u64 *)array;
@@ -2552,7 +2552,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2580,7 +2580,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2710,7 +2710,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			memcpy(array, sample->user_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
@@ -2746,7 +2746,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			*array++ = sample->intr_regs.abi;
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			memcpy(array, sample->intr_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b9e693825873..2d2af2ac2b1e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2606,6 +2606,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
+	up_write(&env->bpf_progs.lock);
 	return 0;
 out:
 	free(info_linear);
@@ -2623,7 +2624,9 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _
 static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 {
 	struct perf_env *env = &ff->ph->env;
+	struct btf_node *node = NULL;
 	u32 count, i;
+	int err = -1;
 
 	if (ff->ph->needs_swap) {
 		pr_warning("interpreting btf from systems with endianity is not yet supported\n");
@@ -2636,31 +2639,32 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 	down_write(&env->bpf_progs.lock);
 
 	for (i = 0; i < count; ++i) {
-		struct btf_node *node;
 		u32 id, data_size;
 
 		if (do_read_u32(ff, &id))
-			return -1;
+			goto out;
 		if (do_read_u32(ff, &data_size))
-			return -1;
+			goto out;
 
 		node = malloc(sizeof(struct btf_node) + data_size);
 		if (!node)
-			return -1;
+			goto out;
 
 		node->id = id;
 		node->data_size = data_size;
 
-		if (__do_read(ff, node->data, data_size)) {
-			free(node);
-			return -1;
-		}
+		if (__do_read(ff, node->data, data_size))
+			goto out;
 
 		perf_env__insert_btf(env, node);
+		node = NULL;
 	}
 
+	err = 0;
+out:
 	up_write(&env->bpf_progs.lock);
-	return 0;
+	free(node);
+	return err;
 }
 
 struct feature_ops {
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e32628cd20a7..ee71efb9db62 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map)
 	return kmap && kmap->name[0];
 }
 
+bool __map__is_bpf_prog(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return true;
+
+	/*
+	 * If PERF_RECORD_BPF_EVENT is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && (strstr(name, "bpf_prog_") == name);
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);
@@ -910,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map)
 		rc = strcmp(m->dso->short_name, map->dso->short_name);
 		if (rc < 0)
 			p = &(*p)->rb_left;
-		else if (rc  > 0)
-			p = &(*p)->rb_right;
 		else
-			return;
+			p = &(*p)->rb_right;
 	}
 	rb_link_node(&map->rb_node_name, parent, p);
 	rb_insert_color(&map->rb_node_name, &maps->names);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e20749f2c55..dc93787c74f0 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+	       !__map__is_bpf_prog(map);
 }
 
 bool map__has_symbols(const struct map *map);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-04-12 13:06 Ingo Molnar
@ 2019-04-13  4:05 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-04-13  4:05 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Jiri Olsa

The pull request you sent on Fri, 12 Apr 2019 15:06:42 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/73fdb2c908c64a32e11c72c029d636f556859c0d

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-04-12 13:06 Ingo Molnar
  2019-04-13  4:05 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-04-12 13:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Jiri Olsa

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 1d54ad944074010609562da5c89e4f5df2f4e5db perf/core: Fix perf_event_disable_inatomic() race

Six kernel side fixes: three related to NMI handling on AMD systems, a 
race fix, a kexec initialization fix and a PEBS sampling fix.

 Thanks,

	Ingo

------------------>
Lendacky, Thomas (3):
      x86/perf/amd: Resolve race condition when disabling PMC
      x86/perf/amd: Resolve NMI latency issues for active PMCs
      x86/perf/amd: Remove need to check "running" bit in NMI handler

Peter Zijlstra (2):
      perf/x86/intel: Initialize TFA MSR
      perf/core: Fix perf_event_disable_inatomic() race

Stephane Eranian (1):
      perf/x86/intel: Fix handling of wakeup_events for multi-entry PEBS


 arch/x86/events/amd/core.c   | 140 +++++++++++++++++++++++++++++++++++++++++--
 arch/x86/events/core.c       |  13 +---
 arch/x86/events/intel/core.c |   8 ++-
 kernel/events/core.c         |  52 +++++++++++++---
 kernel/events/ring_buffer.c  |   4 +-
 5 files changed, 190 insertions(+), 27 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 7d2d7c801dba..0ecfac84ba91 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -3,10 +3,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 #include <asm/apicdef.h>
+#include <asm/nmi.h>
 
 #include "../perf_event.h"
 
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -429,6 +433,132 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT	50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+	unsigned int i;
+	u64 counter;
+
+	/*
+	 * Wait for the counter to be reset if it has overflowed. This loop
+	 * should exit very, very quickly, but just in case, don't wait
+	 * forever...
+	 */
+	for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+		rdmsrl(x86_pmu_event_addr(idx), counter);
+		if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+			break;
+
+		/* Might be in IRQ context, so can't sleep */
+		udelay(1);
+	}
+}
+
+static void amd_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx;
+
+	x86_pmu_disable_all();
+
+	/*
+	 * This shouldn't be called from NMI context, but add a safeguard here
+	 * to return, since if we're in NMI context we can't wait for an NMI
+	 * to reset an overflowed counter value.
+	 */
+	if (in_nmi())
+		return;
+
+	/*
+	 * Check each counter for overflow and wait for it to be reset by the
+	 * NMI if it has overflowed. This relies on the fact that all active
+	 * counters are always enabled when this function is caled and
+	 * ARCH_PERFMON_EVENTSEL_INT is always set.
+	 */
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		amd_pmu_wait_on_overflow(idx);
+	}
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+	x86_pmu_disable_event(event);
+
+	/*
+	 * This can be called from NMI context (via x86_pmu_stop). The counter
+	 * may have overflowed, but either way, we'll never see it get reset
+	 * by the NMI if we're already in the NMI. And the NMI latency support
+	 * below will take care of any pending NMI that might have been
+	 * generated by the overflow.
+	 */
+	if (in_nmi())
+		return;
+
+	amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int active, handled;
+
+	/*
+	 * Obtain the active count before calling x86_pmu_handle_irq() since
+	 * it is possible that x86_pmu_handle_irq() may make a counter
+	 * inactive (through x86_pmu_stop).
+	 */
+	active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+	/* Process any counter overflows */
+	handled = x86_pmu_handle_irq(regs);
+
+	/*
+	 * If a counter was handled, record the number of possible remaining
+	 * NMIs that can occur.
+	 */
+	if (handled) {
+		this_cpu_write(perf_nmi_counter,
+			       min_t(unsigned int, 2, active));
+
+		return handled;
+	}
+
+	if (!this_cpu_read(perf_nmi_counter))
+		return NMI_DONE;
+
+	this_cpu_dec(perf_nmi_counter);
+
+	return NMI_HANDLED;
+}
+
 static struct event_constraint *
 amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -621,11 +751,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
 
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
+	.handle_irq		= amd_pmu_handle_irq,
+	.disable_all		= amd_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
+	.disable		= amd_pmu_disable_event,
 	.hw_config		= amd_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
@@ -732,7 +862,7 @@ void amd_pmu_enable_virt(void)
 	cpuc->perf_ctr_virt_mask = 0;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -750,7 +880,7 @@ void amd_pmu_disable_virt(void)
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..81911e11a15d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+	if (test_bit(hwc->idx, cpuc->active_mask)) {
 		x86_pmu.disable(event);
+		__clear_bit(hwc->idx, cpuc->active_mask);
 		cpuc->events[hwc->idx] = NULL;
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
@@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask)) {
-			/*
-			 * Though we deactivated the counter some cpus
-			 * might still deliver spurious interrupts still
-			 * in flight. Catch them:
-			 */
-			if (__test_and_clear_bit(idx, cpuc->running))
-				handled++;
+		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		}
 
 		event = cpuc->events[idx];
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8baa441d8000..f61dcbef20ff 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3185,7 +3185,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
-		if (!event->attr.freq) {
+		if (!(event->attr.freq || event->attr.wakeup_events)) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
 			      ~intel_pmu_large_pebs_flags(event)))
@@ -3575,6 +3575,12 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
+	if (x86_pmu.flags & PMU_FL_TFA) {
+		WARN_ON_ONCE(cpuc->tfa_shadow);
+		cpuc->tfa_shadow = ~0ULL;
+		intel_set_tfa(cpuc, false);
+	}
+
 	if (x86_pmu.version > 1)
 		flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72d06e302e99..534e01e7bc36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event,
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
+	if (READ_ONCE(event->pending_disable) >= 0) {
+		WRITE_ONCE(event->pending_disable, -1);
 		state = PERF_EVENT_STATE_OFF;
 	}
 	perf_event_set_state(event, state);
@@ -2198,7 +2198,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 
 void perf_event_disable_inatomic(struct perf_event *event)
 {
-	event->pending_disable = 1;
+	WRITE_ONCE(event->pending_disable, smp_processor_id());
+	/* can fail, see perf_pending_event_disable() */
 	irq_work_queue(&event->pending);
 }
 
@@ -5810,10 +5811,45 @@ void perf_event_wakeup(struct perf_event *event)
 	}
 }
 
+static void perf_pending_event_disable(struct perf_event *event)
+{
+	int cpu = READ_ONCE(event->pending_disable);
+
+	if (cpu < 0)
+		return;
+
+	if (cpu == smp_processor_id()) {
+		WRITE_ONCE(event->pending_disable, -1);
+		perf_event_disable_local(event);
+		return;
+	}
+
+	/*
+	 *  CPU-A			CPU-B
+	 *
+	 *  perf_event_disable_inatomic()
+	 *    @pending_disable = CPU-A;
+	 *    irq_work_queue();
+	 *
+	 *  sched-out
+	 *    @pending_disable = -1;
+	 *
+	 *				sched-in
+	 *				perf_event_disable_inatomic()
+	 *				  @pending_disable = CPU-B;
+	 *				  irq_work_queue(); // FAILS
+	 *
+	 *  irq_work_run()
+	 *    perf_pending_event()
+	 *
+	 * But the event runs on CPU-B and wants disabling there.
+	 */
+	irq_work_queue_on(&event->pending, cpu);
+}
+
 static void perf_pending_event(struct irq_work *entry)
 {
-	struct perf_event *event = container_of(entry,
-			struct perf_event, pending);
+	struct perf_event *event = container_of(entry, struct perf_event, pending);
 	int rctx;
 
 	rctx = perf_swevent_get_recursion_context();
@@ -5822,10 +5858,7 @@ static void perf_pending_event(struct irq_work *entry)
 	 * and we won't recurse 'further'.
 	 */
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
-		perf_event_disable_local(event);
-	}
+	perf_pending_event_disable(event);
 
 	if (event->pending_wakeup) {
 		event->pending_wakeup = 0;
@@ -10236,6 +10269,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 
 	init_waitqueue_head(&event->waitq);
+	event->pending_disable = -1;
 	init_irq_work(&event->pending, perf_pending_event);
 
 	mutex_init(&event->mmap_mutex);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a4047321d7d8..2545ac08cc77 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -392,7 +392,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = 1;
+			event->pending_disable = smp_processor_id();
 			perf_output_wakeup(handle);
 			local_set(&rb->aux_nest, 0);
 			goto err_put;
@@ -480,7 +480,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = 1;
+			handle->event->pending_disable = smp_processor_id();
 		perf_output_wakeup(handle);
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-02-17 10:10 Ingo Molnar
@ 2019-02-17 16:50 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-02-17 16:50 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sun, 17 Feb 2019 11:10:51 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/dd6f29da695dbfe5a8ff84ebfdd2110d68e8f511

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-02-17 10:10 Ingo Molnar
  2019-02-17 16:50 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-02-17 10:10 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 528871b456026e6127d95b1b2bd8e3a003dc1614 perf/core: Fix impossible ring-buffer sizes warning

Two fixes on the kernel side: fix an over-eager condition that failed 
larger perf ring-buffer sizes, plus fix crashes in the Intel BTS code for 
a corner case, found by fuzzing.

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      perf/core: Fix impossible ring-buffer sizes warning

Jiri Olsa (1):
      perf/x86: Add check_period PMU callback


 arch/x86/events/core.c       | 14 ++++++++++++++
 arch/x86/events/intel/core.c |  9 +++++++++
 arch/x86/events/perf_event.h | 16 ++++++++++++++--
 include/linux/perf_event.h   |  5 +++++
 kernel/events/core.c         | 16 ++++++++++++++++
 kernel/events/ring_buffer.c  |  2 +-
 6 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 374a19712e20..b684f0294f35 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2278,6 +2278,19 @@ void perf_check_microcode(void)
 		x86_pmu.check_microcode();
 }
 
+static int x86_pmu_check_period(struct perf_event *event, u64 value)
+{
+	if (x86_pmu.check_period && x86_pmu.check_period(event, value))
+		return -EINVAL;
+
+	if (value && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, value) > value)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2302,6 +2315,7 @@ static struct pmu pmu = {
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
+	.check_period		= x86_pmu_check_period,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index daafb893449b..730978dff63f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3587,6 +3587,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3667,6 +3672,8 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.cpu_dead		= intel_pmu_cpu_dead,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3711,6 +3718,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78d7b7031bfc..d46fd6754d92 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -646,6 +646,11 @@ struct x86_pmu {
 	 * Intel host/guest support (KVM)
 	 */
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period) (struct perf_event *event, u64 period);
 };
 
 struct x86_perf_task_context {
@@ -857,7 +862,7 @@ static inline int amd_pmu_init(void)
 
 #ifdef CONFIG_CPU_SUP_INTEL
 
-static inline bool intel_pmu_has_bts(struct perf_event *event)
+static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
@@ -868,7 +873,14 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return hw_event == bts_event && hwc->sample_period == 1;
+	return hw_event == bts_event && period == 1;
+}
+
+static inline bool intel_pmu_has_bts(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1d5c551a5add..e1a051724f7e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -447,6 +447,11 @@ struct pmu {
 	 * Filter events for PMU-specific reasons.
 	 */
 	int (*filter_match)		(struct perf_event *event); /* optional */
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period)		(struct perf_event *event, u64 value); /* optional */
 };
 
 enum perf_addr_filter_action_t {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5ede6918050..26d6edab051a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4963,6 +4963,11 @@ static void __perf_event_period(struct perf_event *event,
 	}
 }
 
+static int perf_event_check_period(struct perf_event *event, u64 value)
+{
+	return event->pmu->check_period(event, value);
+}
+
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	u64 value;
@@ -4979,6 +4984,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
+	if (perf_event_check_period(event, value))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -9391,6 +9399,11 @@ static int perf_pmu_nop_int(struct pmu *pmu)
 	return 0;
 }
 
+static int perf_event_nop_int(struct perf_event *event, u64 value)
+{
+	return 0;
+}
+
 static DEFINE_PER_CPU(unsigned int, nop_txn_flags);
 
 static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
@@ -9691,6 +9704,9 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 		pmu->pmu_disable = perf_pmu_nop_void;
 	}
 
+	if (!pmu->check_period)
+		pmu->check_period = perf_event_nop_int;
+
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 309ef5a64af5..5ab4fe3b1dcc 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -734,7 +734,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct ring_buffer);
 	size += nr_pages * sizeof(void *);
 
-	if (order_base_2(size) >= MAX_ORDER)
+	if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER)
 		goto fail;
 
 	rb = kzalloc(size, GFP_KERNEL);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-02-10  9:01 Ingo Molnar
@ 2019-02-10 18:30 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-02-10 18:30 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner

The pull request you sent on Sun, 10 Feb 2019 10:01:09 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/212146f0800e151bd61b98fb6fe4b8b6778a649a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-02-10  9:01 Ingo Molnar
  2019-02-10 18:30 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-02-10  9:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 3bb2600657dac78580e5b8fecc202eaaff5d4ced Merge tag 'perf-urgent-for-mingo-5.0-20190205' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

A couple of kernel side fixes:

 - Fix the Intel uncore driver on certain hardware configurations
 - Fix a CPU hotplug related memory allocation bug
 - Remove a spurious WARN()

Plus also a handful of perf tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf clang: Do not use 'return std::move(something)'
      tools headers uapi: Sync linux/in.h copy from the kernel sources
      perf symbols: Add fallback definitions for GELF_ST_VISIBILITY()
      perf trace: Support multiple "vfs_getname" probes

Gustavo A. R. Silva (1):
      perf tests evsel-tp-sched: Fix bitwise operator

Jiri Olsa (1):
      perf symbols: Filter out hidden symbols from labels

Kan Liang (1):
      perf/x86/intel/uncore: Add Node ID mask

Mark Rutland (1):
      perf/core: Don't WARN() for impossible ring-buffer sizes

Peter Zijlstra (1):
      perf/x86/intel: Delay memory deallocation until x86_pmu_dead_cpu()

Ravi Bangoria (1):
      perf mem/c2c: Fix perf_mem_events to support powerpc

Tony Jones (1):
      perf script python: Add Python3 support to tests/attr.py


 arch/x86/events/intel/core.c              | 16 +++++++++++-----
 arch/x86/events/intel/uncore_snbep.c      |  4 +++-
 kernel/events/ring_buffer.c               |  3 +++
 tools/include/uapi/linux/in.h             |  2 +-
 tools/perf/Documentation/perf-c2c.txt     | 16 ++++++++++++----
 tools/perf/Documentation/perf-mem.txt     |  2 +-
 tools/perf/arch/powerpc/util/Build        |  1 +
 tools/perf/arch/powerpc/util/mem-events.c | 11 +++++++++++
 tools/perf/builtin-trace.c                | 25 +++++++++++++++++-------
 tools/perf/tests/attr.py                  | 32 ++++++++++++++++++-------------
 tools/perf/tests/evsel-tp-sched.c         |  2 +-
 tools/perf/util/c++/clang.cpp             |  2 +-
 tools/perf/util/mem-events.c              |  2 +-
 tools/perf/util/symbol-elf.c              | 23 +++++++++++++++++++++-
 14 files changed, 105 insertions(+), 36 deletions(-)
 create mode 100644 tools/perf/arch/powerpc/util/mem-events.c

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 40e12cfc87f6..daafb893449b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3558,6 +3558,14 @@ static void free_excl_cntrs(int cpu)
 }
 
 static void intel_pmu_cpu_dying(int cpu)
+{
+	fini_debug_store_on_cpu(cpu);
+
+	if (x86_pmu.counter_freezing)
+		disable_counter_freeze();
+}
+
+static void intel_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	struct intel_shared_regs *pc;
@@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu)
 	}
 
 	free_excl_cntrs(cpu);
-
-	fini_debug_store_on_cpu(cpu);
-
-	if (x86_pmu.counter_freezing)
-		disable_counter_freeze();
 }
 
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3663,6 +3666,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3703,6 +3707,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
 };
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c07bee31abe8..b10e04387f38 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
 	.id_table	= snbep_uncore_pci_ids,
 };
 
+#define NODE_ID_MASK	0x7
+
 /*
  * build pci bus to socket mapping
  */
@@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 		err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
 		if (err)
 			break;
-		nodeid = config;
+		nodeid = config & NODE_ID_MASK;
 		/* get the Node ID mapping */
 		err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
 		if (err)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 4a9937076331..309ef5a64af5 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct ring_buffer);
 	size += nr_pages * sizeof(void *);
 
+	if (order_base_2(size) >= MAX_ORDER)
+		goto fail;
+
 	rb = kzalloc(size, GFP_KERNEL);
 	if (!rb)
 		goto fail;
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index f6052e70bf40..a55cb8b10165 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -268,7 +268,7 @@ struct sockaddr_in {
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
 #define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_BADCLASS(a)		(((long int) (a) ) == (long int)0xffffffff)
 #define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
 
 #define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 095aebdc5bb7..e6150f21267d 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -19,8 +19,11 @@ C2C stands for Cache To Cache.
 The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
 you to track down the cacheline contentions.
 
-The tool is based on x86's load latency and precise store facility events
-provided by Intel CPUs. These events provide:
+On x86, the tool is based on load latency and precise store facility events
+provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
+with thresholding feature.
+
+These events provide:
   - memory address of the access
   - type of the access (load and store details)
   - latency (in cycles) of the load access
@@ -46,7 +49,7 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency.
+	Configure mem-loads latency. (x86 only)
 
 -k::
 --all-kernel::
@@ -119,11 +122,16 @@ Following perf record options are configured by default:
   -W,-d,--phys-data,--sample-cpu
 
 Unless specified otherwise with '-e' option, following events are monitored by
-default:
+default on x86:
 
   cpu/mem-loads,ldlat=30/P
   cpu/mem-stores/P
 
+and following on PowerPC:
+
+  cpu/mem-loads/
+  cpu/mem-stores/
+
 User can pass any 'perf record' option behind '--' mark, like (to enable
 callchains and system wide monitoring):
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index f8d2167cf3e7..199ea0f0a6c0 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -82,7 +82,7 @@ RECORD OPTIONS
 	Be more verbose (show counter open errors, etc)
 
 --ldlat <n>::
-	Specify desired latency for loads event.
+	Specify desired latency for loads event. (x86 only)
 
 In addition, for report all perf report options are valid, and for record
 all perf record options.
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 2e6595310420..ba98bd006488 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
new file mode 100644
index 000000000000..d08311f04e95
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "mem-events.h"
+
+/* PowerPC does not support 'ldlat' parameter. */
+char *perf_mem_events__name(int i)
+{
+	if (i == PERF_MEM_EVENTS__LOAD)
+		return (char *) "cpu/mem-loads/";
+
+	return (char *) "cpu/mem-stores/";
+}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ed4583128b9c..b36061cd1ab8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
 
 static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
+	bool found = false;
+	struct perf_evsel *evsel, *tmp;
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, "probe:vfs_getname*", &err);
 
-	if (IS_ERR(evsel))
+	if (ret)
 		return false;
 
-	if (perf_evsel__field(evsel, "pathname") == NULL) {
+	evlist__for_each_entry_safe(evlist, evsel, tmp) {
+		if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
+			continue;
+
+		if (perf_evsel__field(evsel, "pathname")) {
+			evsel->handler = trace__vfs_getname;
+			found = true;
+			continue;
+		}
+
+		list_del_init(&evsel->node);
+		evsel->evlist = NULL;
 		perf_evsel__delete(evsel);
-		return false;
 	}
 
-	evsel->handler = trace__vfs_getname;
-	perf_evlist__add(evlist, evsel);
-	return true;
+	return found;
 }
 
 static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 44090a9a19f3..e952127e4fb0 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -1,6 +1,8 @@
 #! /usr/bin/python
 # SPDX-License-Identifier: GPL-2.0
 
+from __future__ import print_function
+
 import os
 import sys
 import glob
@@ -8,7 +10,11 @@ import optparse
 import tempfile
 import logging
 import shutil
-import ConfigParser
+
+try:
+    import configparser
+except ImportError:
+    import ConfigParser as configparser
 
 def data_equal(a, b):
     # Allow multiple values in assignment separated by '|'
@@ -100,20 +106,20 @@ class Event(dict):
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 return False
             if not data_equal(self[t], other[t]):
                 return False
         return True
 
     def optional(self):
-        if self.has_key('optional') and self['optional'] == '1':
+        if 'optional' in self and self['optional'] == '1':
             return True
         return False
 
     def diff(self, other):
         for t in Event.terms:
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 continue
             if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
@@ -134,7 +140,7 @@ class Event(dict):
 #   - expected values assignments
 class Test(object):
     def __init__(self, path, options):
-        parser = ConfigParser.SafeConfigParser()
+        parser = configparser.SafeConfigParser()
         parser.read(path)
 
         log.warning("running '%s'" % path)
@@ -193,7 +199,7 @@ class Test(object):
         return True
 
     def load_events(self, path, events):
-        parser_event = ConfigParser.SafeConfigParser()
+        parser_event = configparser.SafeConfigParser()
         parser_event.read(path)
 
         # The event record section header contains 'event' word,
@@ -207,7 +213,7 @@ class Test(object):
             # Read parent event if there's any
             if (':' in section):
                 base = section[section.index(':') + 1:]
-                parser_base = ConfigParser.SafeConfigParser()
+                parser_base = configparser.SafeConfigParser()
                 parser_base.read(self.test_dir + '/' + base)
                 base_items = parser_base.items('event')
 
@@ -322,9 +328,9 @@ def run_tests(options):
     for f in glob.glob(options.test_dir + '/' + options.test):
         try:
             Test(f, options).run()
-        except Unsup, obj:
+        except Unsup as obj:
             log.warning("unsupp  %s" % obj.getMsg())
-        except Notest, obj:
+        except Notest as obj:
             log.warning("skipped %s" % obj.getMsg())
 
 def setup_log(verbose):
@@ -363,7 +369,7 @@ def main():
     parser.add_option("-p", "--perf",
                       action="store", type="string", dest="perf")
     parser.add_option("-v", "--verbose",
-                      action="count", dest="verbose")
+                      default=0, action="count", dest="verbose")
 
     options, args = parser.parse_args()
     if args:
@@ -373,7 +379,7 @@ def main():
     setup_log(options.verbose)
 
     if not options.test_dir:
-        print 'FAILED no -d option specified'
+        print('FAILED no -d option specified')
         sys.exit(-1)
 
     if not options.test:
@@ -382,8 +388,8 @@ def main():
     try:
         run_tests(options)
 
-    except Fail, obj:
-        print "FAILED %s" % obj.getMsg();
+    except Fail as obj:
+        print("FAILED %s" % obj.getMsg())
         sys.exit(-1)
 
     sys.exit(0)
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 5f8501c68da4..5cbba70bcdd0 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
+	is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 89512504551b..39c0004f2886 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module)
 	}
 	PM.run(*Module);
 
-	return std::move(Buffer);
+	return Buffer;
 }
 
 }
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 93f74d8d3cdd..42c3e5a229d2 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
-char *perf_mem_events__name(int i)
+char * __weak perf_mem_events__name(int i)
 {
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 66a84d5846c8..dca7dfae69ad 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -19,6 +19,20 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+#ifndef ELF32_ST_VISIBILITY
+#define ELF32_ST_VISIBILITY(o)	((o) & 0x03)
+#endif
+
+/* For ELF64 the definitions are the same.  */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o)	ELF32_ST_VISIBILITY (o)
+#endif
+
+/* How to extract information held in the st_other field.  */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(val)	ELF64_ST_VISIBILITY (val)
+#endif
+
 typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
@@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 	return GELF_ST_TYPE(sym->st_info);
 }
 
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+	return GELF_ST_VISIBILITY(sym->st_other);
+}
+
 #ifndef STT_GNU_IFUNC
 #define STT_GNU_IFUNC 10
 #endif
@@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
 	return elf_sym__type(sym) == STT_NOTYPE &&
 		sym->st_name != 0 &&
 		sym->st_shndx != SHN_UNDEF &&
-		sym->st_shndx != SHN_ABS;
+		sym->st_shndx != SHN_ABS &&
+		elf_sym__visibility(sym) != STV_HIDDEN &&
+		elf_sym__visibility(sym) != STV_INTERNAL;
 }
 
 static bool elf_sym__filter(GElf_Sym *sym)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2019-01-11  7:44 Ingo Molnar
@ 2019-01-11 18:00 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2019-01-11 18:00 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

The pull request you sent on Fri, 11 Jan 2019 08:44:18 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/40a31da414c39e3cd8c4137c1ceedf59b7ffd4ce

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2019-01-11  7:44 Ingo Molnar
  2019-01-11 18:00 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2019-01-11  7:44 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4e72ee8872279a70ebe973172133b98e8acbf54e Merge tag 'perf-core-for-mingo-5.0-20190110' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling changes only: fixes and a few stray improvements.

Most of the diffstat is dominated by a PowerPC related fix of system call 
trace output beautification that allows us to (again) use the UAPI header 
version and sync up with the kernel's version of PowerPC system call 
names in the arch/powerpc/kernel/syscalls/syscall.tbl header.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (19):
      tools headers x86: Sync disabled-features.h
      tools headers uapi: Sync prctl.h with the kernel sources
      tools beauty: Make the prctl option table generator catch all PR_ options
      tools headers uapi: Update i915_drm.h
      tools headers uapi: Sync linux/in.h copy from the kernel sources
      tools headers uapi: Sync linux/kvm.h with the kernel sources
      tools headers uapi: Sync copy of asm-generic/unistd.h with the kernel sources
      tools headers x86: Sync asm/cpufeatures.h copy with the kernel sources
      perf python: Make sure the python binding output directory is in place
      perf test shell: Use a fallback to get the pathname in vfs_getname
      perf trace: Fix ')' placement in "interrupted" syscall lines
      perf trace: Fix alignment for [continued] lines
      perf top: Lift restriction on using callchains without "sym" in --sort
      tools include uapi: Grab a copy of linux/mount.h
      perf beauty: Switch from using uapi/linux/fs.h to uapi/linux/mount.h
      tools include uapi: Sync linux/fs.h copy with the kernel sources
      tools include uapi: Sync linux/vhost.h with the kernel sources
      tools include uapi: Sync linux/if_link.h copy with the kernel sources
      perf symbols: Add 'arch_cpu_idle' to the list of kernel idle symbols

Florian Fainelli (2):
      perf tools: Make find_vdso_map() more modular
      perf tests: Add a test for the ARM 32-bit [vectors] page

Ivan Krylov (1):
      perf annotate: Pass filename to objdump via execl

Jin Yao (2):
      perf stat: Fix endless wait for child process
      perf report: Fix wrong iteration count in --branch-history

Jiri Olsa (2):
      tools thermal tmon: Use -O3 instead of -O1 if available
      tools iio: Override CFLAGS assignments

Mattias Jacobsson (1):
      perf strbuf: Remove redundant va_end() in strbuf_addv()

Ravi Bangoria (2):
      perf powerpc: Rework syscall table generation
      tools headers powerpc: Remove unistd.h

Tzvetomir Stoyanov (7):
      tools lib traceevent: Introduce new libtracevent API: tep_override_comm()
      tools lib traceevent: Initialize host_bigendian at tep_handle allocation
      tools lib traceevent: Rename struct cmdline to struct tep_cmdline
      tools lib traceevent: Changed return logic of trace_seq_printf() and trace_seq_vprintf() APIs
      tools lib traceevent: Changed return logic of tep_register_event_handler() API
      tools lib traceevent: Rename tep_is_file_bigendian() to tep_file_bigendian()
      tools lib traceevent: Remove tep_data_event_from_type() API


 tools/arch/powerpc/include/uapi/asm/unistd.h       | 404 -------------------
 tools/arch/x86/include/asm/cpufeatures.h           |   2 +
 tools/arch/x86/include/asm/disabled-features.h     |   8 +-
 tools/include/uapi/asm-generic/unistd.h            |   4 +-
 tools/include/uapi/drm/i915_drm.h                  |   8 +
 tools/include/uapi/linux/fs.h                      |  60 +--
 tools/include/uapi/linux/if_link.h                 |  19 +
 tools/include/uapi/linux/in.h                      |  10 +-
 tools/include/uapi/linux/kvm.h                     |  19 +
 tools/include/uapi/linux/mount.h                   |  58 +++
 tools/include/uapi/linux/prctl.h                   |   8 +
 tools/include/uapi/linux/vhost.h                   | 113 +-----
 tools/lib/traceevent/event-parse-api.c             |   4 +-
 tools/lib/traceevent/event-parse-local.h           |   4 +-
 tools/lib/traceevent/event-parse.c                 | 129 ++++---
 tools/lib/traceevent/event-parse.h                 |  17 +-
 tools/lib/traceevent/plugin_kvm.c                  |   2 +-
 tools/lib/traceevent/trace-seq.c                   |  17 +-
 tools/perf/Makefile.perf                           |   8 +-
 tools/perf/arch/arm/tests/Build                    |   1 +
 tools/perf/arch/arm/tests/arch-tests.c             |   4 +
 tools/perf/arch/arm/tests/vectors-page.c           |  24 ++
 tools/perf/arch/powerpc/Makefile                   |  15 +-
 .../perf/arch/powerpc/entry/syscalls/mksyscalltbl  |  22 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 427 +++++++++++++++++++++
 tools/perf/builtin-stat.c                          |   3 +-
 tools/perf/builtin-top.c                           |   7 +-
 tools/perf/builtin-trace.c                         |  15 +-
 tools/perf/check-headers.sh                        |   2 +-
 tools/perf/perf-read-vdso.c                        |   6 +-
 tools/perf/tests/shell/lib/probe_vfs_getname.sh    |   3 +-
 tools/perf/tests/tests.h                           |   5 +
 tools/perf/trace/beauty/mount_flags.sh             |   4 +-
 tools/perf/trace/beauty/prctl_option.sh            |   2 +-
 tools/perf/util/annotate.c                         |   8 +-
 tools/perf/util/callchain.c                        |  32 +-
 tools/perf/util/callchain.h                        |   1 +
 tools/perf/util/{find-vdso-map.c => find-map.c}    |   7 +-
 tools/perf/util/machine.c                          |   2 +-
 tools/perf/util/strbuf.c                           |   1 -
 tools/perf/util/symbol.c                           |   1 +
 tools/perf/util/vdso.c                             |   6 +-
 tools/thermal/tmon/Makefile                        |   2 +-
 43 files changed, 797 insertions(+), 697 deletions(-)
 delete mode 100644 tools/arch/powerpc/include/uapi/asm/unistd.h
 create mode 100644 tools/include/uapi/linux/mount.h
 create mode 100644 tools/perf/arch/arm/tests/vectors-page.c
 create mode 100644 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
 rename tools/perf/util/{find-vdso-map.c => find-map.c} (71%)

diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
deleted file mode 100644
index 985534d0b448..000000000000
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,404 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*
- * This file contains the system call numbers.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#ifndef _UAPI_ASM_POWERPC_UNISTD_H_
-#define _UAPI_ASM_POWERPC_UNISTD_H_
-
-
-#define __NR_restart_syscall	  0
-#define __NR_exit		  1
-#define __NR_fork		  2
-#define __NR_read		  3
-#define __NR_write		  4
-#define __NR_open		  5
-#define __NR_close		  6
-#define __NR_waitpid		  7
-#define __NR_creat		  8
-#define __NR_link		  9
-#define __NR_unlink		 10
-#define __NR_execve		 11
-#define __NR_chdir		 12
-#define __NR_time		 13
-#define __NR_mknod		 14
-#define __NR_chmod		 15
-#define __NR_lchown		 16
-#define __NR_break		 17
-#define __NR_oldstat		 18
-#define __NR_lseek		 19
-#define __NR_getpid		 20
-#define __NR_mount		 21
-#define __NR_umount		 22
-#define __NR_setuid		 23
-#define __NR_getuid		 24
-#define __NR_stime		 25
-#define __NR_ptrace		 26
-#define __NR_alarm		 27
-#define __NR_oldfstat		 28
-#define __NR_pause		 29
-#define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
-#define __NR_access		 33
-#define __NR_nice		 34
-#define __NR_ftime		 35
-#define __NR_sync		 36
-#define __NR_kill		 37
-#define __NR_rename		 38
-#define __NR_mkdir		 39
-#define __NR_rmdir		 40
-#define __NR_dup		 41
-#define __NR_pipe		 42
-#define __NR_times		 43
-#define __NR_prof		 44
-#define __NR_brk		 45
-#define __NR_setgid		 46
-#define __NR_getgid		 47
-#define __NR_signal		 48
-#define __NR_geteuid		 49
-#define __NR_getegid		 50
-#define __NR_acct		 51
-#define __NR_umount2		 52
-#define __NR_lock		 53
-#define __NR_ioctl		 54
-#define __NR_fcntl		 55
-#define __NR_mpx		 56
-#define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
-#define __NR_umask		 60
-#define __NR_chroot		 61
-#define __NR_ustat		 62
-#define __NR_dup2		 63
-#define __NR_getppid		 64
-#define __NR_getpgrp		 65
-#define __NR_setsid		 66
-#define __NR_sigaction		 67
-#define __NR_sgetmask		 68
-#define __NR_ssetmask		 69
-#define __NR_setreuid		 70
-#define __NR_setregid		 71
-#define __NR_sigsuspend		 72
-#define __NR_sigpending		 73
-#define __NR_sethostname	 74
-#define __NR_setrlimit		 75
-#define __NR_getrlimit		 76
-#define __NR_getrusage		 77
-#define __NR_gettimeofday	 78
-#define __NR_settimeofday	 79
-#define __NR_getgroups		 80
-#define __NR_setgroups		 81
-#define __NR_select		 82
-#define __NR_symlink		 83
-#define __NR_oldlstat		 84
-#define __NR_readlink		 85
-#define __NR_uselib		 86
-#define __NR_swapon		 87
-#define __NR_reboot		 88
-#define __NR_readdir		 89
-#define __NR_mmap		 90
-#define __NR_munmap		 91
-#define __NR_truncate		 92
-#define __NR_ftruncate		 93
-#define __NR_fchmod		 94
-#define __NR_fchown		 95
-#define __NR_getpriority	 96
-#define __NR_setpriority	 97
-#define __NR_profil		 98
-#define __NR_statfs		 99
-#define __NR_fstatfs		100
-#define __NR_ioperm		101
-#define __NR_socketcall		102
-#define __NR_syslog		103
-#define __NR_setitimer		104
-#define __NR_getitimer		105
-#define __NR_stat		106
-#define __NR_lstat		107
-#define __NR_fstat		108
-#define __NR_olduname		109
-#define __NR_iopl		110
-#define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86		113
-#define __NR_wait4		114
-#define __NR_swapoff		115
-#define __NR_sysinfo		116
-#define __NR_ipc		117
-#define __NR_fsync		118
-#define __NR_sigreturn		119
-#define __NR_clone		120
-#define __NR_setdomainname	121
-#define __NR_uname		122
-#define __NR_modify_ldt		123
-#define __NR_adjtimex		124
-#define __NR_mprotect		125
-#define __NR_sigprocmask	126
-#define __NR_create_module	127
-#define __NR_init_module	128
-#define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
-#define __NR_quotactl		131
-#define __NR_getpgid		132
-#define __NR_fchdir		133
-#define __NR_bdflush		134
-#define __NR_sysfs		135
-#define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
-#define __NR_setfsuid		138
-#define __NR_setfsgid		139
-#define __NR__llseek		140
-#define __NR_getdents		141
-#define __NR__newselect		142
-#define __NR_flock		143
-#define __NR_msync		144
-#define __NR_readv		145
-#define __NR_writev		146
-#define __NR_getsid		147
-#define __NR_fdatasync		148
-#define __NR__sysctl		149
-#define __NR_mlock		150
-#define __NR_munlock		151
-#define __NR_mlockall		152
-#define __NR_munlockall		153
-#define __NR_sched_setparam		154
-#define __NR_sched_getparam		155
-#define __NR_sched_setscheduler		156
-#define __NR_sched_getscheduler		157
-#define __NR_sched_yield		158
-#define __NR_sched_get_priority_max	159
-#define __NR_sched_get_priority_min	160
-#define __NR_sched_rr_get_interval	161
-#define __NR_nanosleep		162
-#define __NR_mremap		163
-#define __NR_setresuid		164
-#define __NR_getresuid		165
-#define __NR_query_module	166
-#define __NR_poll		167
-#define __NR_nfsservctl		168
-#define __NR_setresgid		169
-#define __NR_getresgid		170
-#define __NR_prctl		171
-#define __NR_rt_sigreturn	172
-#define __NR_rt_sigaction	173
-#define __NR_rt_sigprocmask	174
-#define __NR_rt_sigpending	175
-#define __NR_rt_sigtimedwait	176
-#define __NR_rt_sigqueueinfo	177
-#define __NR_rt_sigsuspend	178
-#define __NR_pread64		179
-#define __NR_pwrite64		180
-#define __NR_chown		181
-#define __NR_getcwd		182
-#define __NR_capget		183
-#define __NR_capset		184
-#define __NR_sigaltstack	185
-#define __NR_sendfile		186
-#define __NR_getpmsg		187	/* some people actually want streams */
-#define __NR_putpmsg		188	/* some people actually want streams */
-#define __NR_vfork		189
-#define __NR_ugetrlimit		190	/* SuS compliant getrlimit */
-#define __NR_readahead		191
-#ifndef __powerpc64__			/* these are 32-bit only */
-#define __NR_mmap2		192
-#define __NR_truncate64		193
-#define __NR_ftruncate64	194
-#define __NR_stat64		195
-#define __NR_lstat64		196
-#define __NR_fstat64		197
-#endif
-#define __NR_pciconfig_read	198
-#define __NR_pciconfig_write	199
-#define __NR_pciconfig_iobase	200
-#define __NR_multiplexer	201
-#define __NR_getdents64		202
-#define __NR_pivot_root		203
-#ifndef __powerpc64__
-#define __NR_fcntl64		204
-#endif
-#define __NR_madvise		205
-#define __NR_mincore		206
-#define __NR_gettid		207
-#define __NR_tkill		208
-#define __NR_setxattr		209
-#define __NR_lsetxattr		210
-#define __NR_fsetxattr		211
-#define __NR_getxattr		212
-#define __NR_lgetxattr		213
-#define __NR_fgetxattr		214
-#define __NR_listxattr		215
-#define __NR_llistxattr		216
-#define __NR_flistxattr		217
-#define __NR_removexattr	218
-#define __NR_lremovexattr	219
-#define __NR_fremovexattr	220
-#define __NR_futex		221
-#define __NR_sched_setaffinity	222
-#define __NR_sched_getaffinity	223
-/* 224 currently unused */
-#define __NR_tuxcall		225
-#ifndef __powerpc64__
-#define __NR_sendfile64		226
-#endif
-#define __NR_io_setup		227
-#define __NR_io_destroy		228
-#define __NR_io_getevents	229
-#define __NR_io_submit		230
-#define __NR_io_cancel		231
-#define __NR_set_tid_address	232
-#define __NR_fadvise64		233
-#define __NR_exit_group		234
-#define __NR_lookup_dcookie	235
-#define __NR_epoll_create	236
-#define __NR_epoll_ctl		237
-#define __NR_epoll_wait		238
-#define __NR_remap_file_pages	239
-#define __NR_timer_create	240
-#define __NR_timer_settime	241
-#define __NR_timer_gettime	242
-#define __NR_timer_getoverrun	243
-#define __NR_timer_delete	244
-#define __NR_clock_settime	245
-#define __NR_clock_gettime	246
-#define __NR_clock_getres	247
-#define __NR_clock_nanosleep	248
-#define __NR_swapcontext	249
-#define __NR_tgkill		250
-#define __NR_utimes		251
-#define __NR_statfs64		252
-#define __NR_fstatfs64		253
-#ifndef __powerpc64__
-#define __NR_fadvise64_64	254
-#endif
-#define __NR_rtas		255
-#define __NR_sys_debug_setcontext 256
-/* Number 257 is reserved for vserver */
-#define __NR_migrate_pages	258
-#define __NR_mbind		259
-#define __NR_get_mempolicy	260
-#define __NR_set_mempolicy	261
-#define __NR_mq_open		262
-#define __NR_mq_unlink		263
-#define __NR_mq_timedsend	264
-#define __NR_mq_timedreceive	265
-#define __NR_mq_notify		266
-#define __NR_mq_getsetattr	267
-#define __NR_kexec_load		268
-#define __NR_add_key		269
-#define __NR_request_key	270
-#define __NR_keyctl		271
-#define __NR_waitid		272
-#define __NR_ioprio_set		273
-#define __NR_ioprio_get		274
-#define __NR_inotify_init	275
-#define __NR_inotify_add_watch	276
-#define __NR_inotify_rm_watch	277
-#define __NR_spu_run		278
-#define __NR_spu_create		279
-#define __NR_pselect6		280
-#define __NR_ppoll		281
-#define __NR_unshare		282
-#define __NR_splice		283
-#define __NR_tee		284
-#define __NR_vmsplice		285
-#define __NR_openat		286
-#define __NR_mkdirat		287
-#define __NR_mknodat		288
-#define __NR_fchownat		289
-#define __NR_futimesat		290
-#ifdef __powerpc64__
-#define __NR_newfstatat		291
-#else
-#define __NR_fstatat64		291
-#endif
-#define __NR_unlinkat		292
-#define __NR_renameat		293
-#define __NR_linkat		294
-#define __NR_symlinkat		295
-#define __NR_readlinkat		296
-#define __NR_fchmodat		297
-#define __NR_faccessat		298
-#define __NR_get_robust_list	299
-#define __NR_set_robust_list	300
-#define __NR_move_pages		301
-#define __NR_getcpu		302
-#define __NR_epoll_pwait	303
-#define __NR_utimensat		304
-#define __NR_signalfd		305
-#define __NR_timerfd_create	306
-#define __NR_eventfd		307
-#define __NR_sync_file_range2	308
-#define __NR_fallocate		309
-#define __NR_subpage_prot	310
-#define __NR_timerfd_settime	311
-#define __NR_timerfd_gettime	312
-#define __NR_signalfd4		313
-#define __NR_eventfd2		314
-#define __NR_epoll_create1	315
-#define __NR_dup3		316
-#define __NR_pipe2		317
-#define __NR_inotify_init1	318
-#define __NR_perf_event_open	319
-#define __NR_preadv		320
-#define __NR_pwritev		321
-#define __NR_rt_tgsigqueueinfo	322
-#define __NR_fanotify_init	323
-#define __NR_fanotify_mark	324
-#define __NR_prlimit64		325
-#define __NR_socket		326
-#define __NR_bind		327
-#define __NR_connect		328
-#define __NR_listen		329
-#define __NR_accept		330
-#define __NR_getsockname	331
-#define __NR_getpeername	332
-#define __NR_socketpair		333
-#define __NR_send		334
-#define __NR_sendto		335
-#define __NR_recv		336
-#define __NR_recvfrom		337
-#define __NR_shutdown		338
-#define __NR_setsockopt		339
-#define __NR_getsockopt		340
-#define __NR_sendmsg		341
-#define __NR_recvmsg		342
-#define __NR_recvmmsg		343
-#define __NR_accept4		344
-#define __NR_name_to_handle_at	345
-#define __NR_open_by_handle_at	346
-#define __NR_clock_adjtime	347
-#define __NR_syncfs		348
-#define __NR_sendmmsg		349
-#define __NR_setns		350
-#define __NR_process_vm_readv	351
-#define __NR_process_vm_writev	352
-#define __NR_finit_module	353
-#define __NR_kcmp		354
-#define __NR_sched_setattr	355
-#define __NR_sched_getattr	356
-#define __NR_renameat2		357
-#define __NR_seccomp		358
-#define __NR_getrandom		359
-#define __NR_memfd_create	360
-#define __NR_bpf		361
-#define __NR_execveat		362
-#define __NR_switch_endian	363
-#define __NR_userfaultfd	364
-#define __NR_membarrier		365
-#define __NR_mlock2		378
-#define __NR_copy_file_range	379
-#define __NR_preadv2		380
-#define __NR_pwritev2		381
-#define __NR_kexec_file_load	382
-#define __NR_statx		383
-#define __NR_pkey_alloc		384
-#define __NR_pkey_free		385
-#define __NR_pkey_mprotect	386
-#define __NR_rseq		387
-#define __NR_io_pgetevents	388
-
-#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 28c4a502b419..6d6122524711 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -281,9 +281,11 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_WBNOINVD		(13*32+ 9) /* WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 33833d1909af..a5ea841cc6d2 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_SMAP
+# define DISABLE_SMAP	0
+#else
+# define DISABLE_SMAP	(1<<(X86_FEATURE_SMAP & 31))
+#endif
+
 #ifdef CONFIG_X86_INTEL_UMIP
 # define DISABLE_UMIP	0
 #else
@@ -68,7 +74,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index c7f3321fbe43..d90127298f12 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -738,9 +738,11 @@ __SYSCALL(__NR_statx,     sys_statx)
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 #define __NR_rseq 293
 __SYSCALL(__NR_rseq, sys_rseq)
+#define __NR_kexec_file_load 294
+__SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
 
 #undef __NR_syscalls
-#define __NR_syscalls 294
+#define __NR_syscalls 295
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index a4446f452040..298b2e197744 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -412,6 +412,14 @@ typedef struct drm_i915_irq_wait {
 	int irq_seq;
 } drm_i915_irq_wait_t;
 
+/*
+ * Different modes of per-process Graphics Translation Table,
+ * see I915_PARAM_HAS_ALIASING_PPGTT
+ */
+#define I915_GEM_PPGTT_NONE	0
+#define I915_GEM_PPGTT_ALIASING	1
+#define I915_GEM_PPGTT_FULL	2
+
 /* Ioctl to query kernel params:
  */
 #define I915_PARAM_IRQ_ACTIVE            1
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index a441ea1bfe6d..121e82ce296b 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -14,6 +14,11 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#if !defined(__KERNEL__)
+#include <linux/mount.h>
+#endif
+
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
  * the file limit at runtime and only root can increase the per-process
@@ -101,57 +106,6 @@ struct inodes_stat_t {
 
 #define NR_FILE  8192	/* this can well be larger on a larger system */
 
-
-/*
- * These are the fs-independent mount-flags: up to 32 flags are supported
- */
-#define MS_RDONLY	 1	/* Mount read-only */
-#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
-#define MS_NODEV	 4	/* Disallow access to device special files */
-#define MS_NOEXEC	 8	/* Disallow program execution */
-#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
-#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
-#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
-#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
-#define MS_NOATIME	1024	/* Do not update access times. */
-#define MS_NODIRATIME	2048	/* Do not update directory access times */
-#define MS_BIND		4096
-#define MS_MOVE		8192
-#define MS_REC		16384
-#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
-				   MS_VERBOSE is deprecated. */
-#define MS_SILENT	32768
-#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
-#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
-#define MS_PRIVATE	(1<<18)	/* change to private */
-#define MS_SLAVE	(1<<19)	/* change to slave */
-#define MS_SHARED	(1<<20)	/* change to shared */
-#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
-#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
-#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
-#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
-#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
-
-/* These sb flags are internal to the kernel */
-#define MS_SUBMOUNT     (1<<26)
-#define MS_NOREMOTELOCK	(1<<27)
-#define MS_NOSEC	(1<<28)
-#define MS_BORN		(1<<29)
-#define MS_ACTIVE	(1<<30)
-#define MS_NOUSER	(1<<31)
-
-/*
- * Superblock flags that can be altered by MS_REMOUNT
- */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
-			 MS_LAZYTIME)
-
-/*
- * Old magic mount flag and mask
- */
-#define MS_MGC_VAL 0xC0ED0000
-#define MS_MGC_MSK 0xffff0000
-
 /*
  * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
  */
@@ -269,7 +223,8 @@ struct fsxattr {
 #define FS_POLICY_FLAGS_PAD_16		0x02
 #define FS_POLICY_FLAGS_PAD_32		0x03
 #define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAGS_VALID		0x03
+#define FS_POLICY_FLAG_DIRECT_KEY	0x04	/* use master key directly */
+#define FS_POLICY_FLAGS_VALID		0x07
 
 /* Encryption algorithms */
 #define FS_ENCRYPTION_MODE_INVALID		0
@@ -281,6 +236,7 @@ struct fsxattr {
 #define FS_ENCRYPTION_MODE_AES_128_CTS		6
 #define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
 #define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_ADIANTUM		9
 
 struct fscrypt_policy {
 	__u8 version;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 1debfa42cba1..d6533828123a 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -288,6 +288,7 @@ enum {
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
+	IFLA_BR_MULTI_BOOLOPT,
 	__IFLA_BR_MAX,
 };
 
@@ -533,6 +534,7 @@ enum {
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
+	IFLA_VXLAN_DF,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -542,6 +544,14 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+enum ifla_vxlan_df {
+	VXLAN_DF_UNSET = 0,
+	VXLAN_DF_SET,
+	VXLAN_DF_INHERIT,
+	__VXLAN_DF_END,
+	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
@@ -557,10 +567,19 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
+	IFLA_GENEVE_DF,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
 
+enum ifla_geneve_df {
+	GENEVE_DF_UNSET = 0,
+	GENEVE_DF_SET,
+	GENEVE_DF_INHERIT,
+	__GENEVE_DF_END,
+	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 48e8a225b985..f6052e70bf40 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -266,10 +266,14 @@ struct sockaddr_in {
 
 #define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
-#define IN_MULTICAST_NET	0xF0000000
+#define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
-#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
+
+#define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_CLASSE_NET		0xffffffff
+#define	IN_CLASSE_NSHIFT	0
 
 /* Address to accept any incoming messages. */
 #define	INADDR_ANY		((unsigned long int) 0x00000000)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 2b7a652c9fa4..6d4ea4b6c922 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -492,6 +492,17 @@ struct kvm_dirty_log {
 	};
 };
 
+/* for KVM_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+	__u32 slot;
+	__u32 num_pages;
+	__u64 first_page;
+	union {
+		void __user *dirty_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
 /* for KVM_SET_SIGNAL_MASK */
 struct kvm_signal_mask {
 	__u32 len;
@@ -975,6 +986,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
 #define KVM_CAP_EXCEPTION_PAYLOAD 164
 #define KVM_CAP_ARM_VM_IPA_SIZE 165
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166
+#define KVM_CAP_HYPERV_CPUID 167
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1421,6 +1434,12 @@ struct kvm_enc_region {
 #define KVM_GET_NESTED_STATE         _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
 #define KVM_SET_NESTED_STATE         _IOW(KVMIO,  0xbf, struct kvm_nested_state)
 
+/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */
+#define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
+
+/* Available with KVM_CAP_HYPERV_CPUID */
+#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
new file mode 100644
index 000000000000..3f9ec42510b0
--- /dev/null
+++ b/tools/include/uapi/linux/mount.h
@@ -0,0 +1,58 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only.  Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index b17201edfa09..b4875a93363a 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -220,4 +220,12 @@ struct prctl_mm_map {
 # define PR_SPEC_DISABLE		(1UL << 2)
 # define PR_SPEC_FORCE_DISABLE		(1UL << 3)
 
+/* Reset arm64 pointer authentication keys */
+#define PR_PAC_RESET_KEYS		54
+# define PR_PAC_APIAKEY			(1UL << 0)
+# define PR_PAC_APIBKEY			(1UL << 1)
+# define PR_PAC_APDAKEY			(1UL << 2)
+# define PR_PAC_APDBKEY			(1UL << 3)
+# define PR_PAC_APGAKEY			(1UL << 4)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 84c3de89696a..40d028eed645 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -11,94 +11,9 @@
  * device configuration.
  */
 
+#include <linux/vhost_types.h>
 #include <linux/types.h>
-#include <linux/compiler.h>
 #include <linux/ioctl.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ring.h>
-
-struct vhost_vring_state {
-	unsigned int index;
-	unsigned int num;
-};
-
-struct vhost_vring_file {
-	unsigned int index;
-	int fd; /* Pass -1 to unbind from file. */
-
-};
-
-struct vhost_vring_addr {
-	unsigned int index;
-	/* Option flags. */
-	unsigned int flags;
-	/* Flag values: */
-	/* Whether log address is valid. If set enables logging. */
-#define VHOST_VRING_F_LOG 0
-
-	/* Start of array of descriptors (virtually contiguous) */
-	__u64 desc_user_addr;
-	/* Used structure address. Must be 32 bit aligned */
-	__u64 used_user_addr;
-	/* Available structure address. Must be 16 bit aligned */
-	__u64 avail_user_addr;
-	/* Logging support. */
-	/* Log writes to used structure, at offset calculated from specified
-	 * address. Address must be 32 bit aligned. */
-	__u64 log_guest_addr;
-};
-
-/* no alignment requirement */
-struct vhost_iotlb_msg {
-	__u64 iova;
-	__u64 size;
-	__u64 uaddr;
-#define VHOST_ACCESS_RO      0x1
-#define VHOST_ACCESS_WO      0x2
-#define VHOST_ACCESS_RW      0x3
-	__u8 perm;
-#define VHOST_IOTLB_MISS           1
-#define VHOST_IOTLB_UPDATE         2
-#define VHOST_IOTLB_INVALIDATE     3
-#define VHOST_IOTLB_ACCESS_FAIL    4
-	__u8 type;
-};
-
-#define VHOST_IOTLB_MSG 0x1
-#define VHOST_IOTLB_MSG_V2 0x2
-
-struct vhost_msg {
-	int type;
-	union {
-		struct vhost_iotlb_msg iotlb;
-		__u8 padding[64];
-	};
-};
-
-struct vhost_msg_v2 {
-	__u32 type;
-	__u32 reserved;
-	union {
-		struct vhost_iotlb_msg iotlb;
-		__u8 padding[64];
-	};
-};
-
-struct vhost_memory_region {
-	__u64 guest_phys_addr;
-	__u64 memory_size; /* bytes */
-	__u64 userspace_addr;
-	__u64 flags_padding; /* No flags are currently specified. */
-};
-
-/* All region addresses and sizes must be 4K aligned. */
-#define VHOST_PAGE_SIZE 0x1000
-
-struct vhost_memory {
-	__u32 nregions;
-	__u32 padding;
-	struct vhost_memory_region regions[0];
-};
 
 /* ioctls */
 
@@ -186,31 +101,7 @@ struct vhost_memory {
  * device.  This can be used to stop the ring (e.g. for migration). */
 #define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
 
-/* Feature bits */
-/* Log all write descriptors. Can be changed while device is active. */
-#define VHOST_F_LOG_ALL 26
-/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
-#define VHOST_NET_F_VIRTIO_NET_HDR 27
-
-/* VHOST_SCSI specific definitions */
-
-/*
- * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
- *
- * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
- *            RFC-v2 vhost-scsi userspace.  Add GET_ABI_VERSION ioctl usage
- * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
- *            All the targets under vhost_wwpn can be seen and used by guset.
- */
-
-#define VHOST_SCSI_ABI_VERSION	1
-
-struct vhost_scsi_target {
-	int abi_version;
-	char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
-	unsigned short vhost_tpgt;
-	unsigned short reserved;
-};
+/* VHOST_SCSI specific defines */
 
 #define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
 #define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
index 8b31c0e00ba3..d463761a58f4 100644
--- a/tools/lib/traceevent/event-parse-api.c
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -194,13 +194,13 @@ void tep_set_page_size(struct tep_handle *pevent, int _page_size)
 }
 
 /**
- * tep_is_file_bigendian - get if the file is in big endian order
+ * tep_file_bigendian - get if the file is in big endian order
  * @pevent: a handle to the tep_handle
  *
  * This returns if the file is in big endian order
  * If @pevent is NULL, 0 is returned.
  */
-int tep_is_file_bigendian(struct tep_handle *pevent)
+int tep_file_bigendian(struct tep_handle *pevent)
 {
 	if(pevent)
 		return pevent->file_bigendian;
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
index 9a092dd4a86d..35833ee32d6c 100644
--- a/tools/lib/traceevent/event-parse-local.h
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -7,7 +7,7 @@
 #ifndef _PARSE_EVENTS_INT_H
 #define _PARSE_EVENTS_INT_H
 
-struct cmdline;
+struct tep_cmdline;
 struct cmdline_list;
 struct func_map;
 struct func_list;
@@ -36,7 +36,7 @@ struct tep_handle {
 	int long_size;
 	int page_size;
 
-	struct cmdline *cmdlines;
+	struct tep_cmdline *cmdlines;
 	struct cmdline_list *cmdlist;
 	int cmdline_count;
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 69a96e39f0ab..abd4fa5d3088 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -124,15 +124,15 @@ struct tep_print_arg *alloc_arg(void)
 	return calloc(1, sizeof(struct tep_print_arg));
 }
 
-struct cmdline {
+struct tep_cmdline {
 	char *comm;
 	int pid;
 };
 
 static int cmdline_cmp(const void *a, const void *b)
 {
-	const struct cmdline *ca = a;
-	const struct cmdline *cb = b;
+	const struct tep_cmdline *ca = a;
+	const struct tep_cmdline *cb = b;
 
 	if (ca->pid < cb->pid)
 		return -1;
@@ -152,7 +152,7 @@ static int cmdline_init(struct tep_handle *pevent)
 {
 	struct cmdline_list *cmdlist = pevent->cmdlist;
 	struct cmdline_list *item;
-	struct cmdline *cmdlines;
+	struct tep_cmdline *cmdlines;
 	int i;
 
 	cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
@@ -179,8 +179,8 @@ static int cmdline_init(struct tep_handle *pevent)
 
 static const char *find_cmdline(struct tep_handle *pevent, int pid)
 {
-	const struct cmdline *comm;
-	struct cmdline key;
+	const struct tep_cmdline *comm;
+	struct tep_cmdline key;
 
 	if (!pid)
 		return "<idle>";
@@ -208,8 +208,8 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
  */
 int tep_pid_is_registered(struct tep_handle *pevent, int pid)
 {
-	const struct cmdline *comm;
-	struct cmdline key;
+	const struct tep_cmdline *comm;
+	struct tep_cmdline key;
 
 	if (!pid)
 		return 1;
@@ -232,11 +232,13 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid)
  * we must add this pid. This is much slower than when cmdlines
  * are added before the array is initialized.
  */
-static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int add_new_comm(struct tep_handle *pevent,
+			const char *comm, int pid, bool override)
 {
-	struct cmdline *cmdlines = pevent->cmdlines;
-	const struct cmdline *cmdline;
-	struct cmdline key;
+	struct tep_cmdline *cmdlines = pevent->cmdlines;
+	struct tep_cmdline *cmdline;
+	struct tep_cmdline key;
+	char *new_comm;
 
 	if (!pid)
 		return 0;
@@ -247,8 +249,19 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 	cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
 		       sizeof(*pevent->cmdlines), cmdline_cmp);
 	if (cmdline) {
-		errno = EEXIST;
-		return -1;
+		if (!override) {
+			errno = EEXIST;
+			return -1;
+		}
+		new_comm = strdup(comm);
+		if (!new_comm) {
+			errno = ENOMEM;
+			return -1;
+		}
+		free(cmdline->comm);
+		cmdline->comm = new_comm;
+
+		return 0;
 	}
 
 	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
@@ -275,21 +288,13 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 	return 0;
 }
 
-/**
- * tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
- * @comm: the command line to register
- * @pid: the pid to map the command line to
- *
- * This adds a mapping to search for command line names with
- * a given pid. The comm is duplicated.
- */
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int _tep_register_comm(struct tep_handle *pevent,
+			      const char *comm, int pid, bool override)
 {
 	struct cmdline_list *item;
 
 	if (pevent->cmdlines)
-		return add_new_comm(pevent, comm, pid);
+		return add_new_comm(pevent, comm, pid, override);
 
 	item = malloc(sizeof(*item));
 	if (!item)
@@ -312,6 +317,40 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
 	return 0;
 }
 
+/**
+ * tep_register_comm - register a pid / comm mapping
+ * @pevent: handle for the pevent
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, -1 is returned and errno is set to EEXIST
+ */
+int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+{
+	return _tep_register_comm(pevent, comm, pid, false);
+}
+
+/**
+ * tep_override_comm - register a pid / comm mapping
+ * @pevent: handle for the pevent
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, the command string is udapted with the new one
+ */
+int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+{
+	if (!pevent->cmdlines && cmdline_init(pevent)) {
+		errno = ENOMEM;
+		return -1;
+	}
+	return _tep_register_comm(pevent, comm, pid, true);
+}
+
 int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
 {
 	pevent->trace_clock = strdup(trace_clock);
@@ -5226,18 +5265,6 @@ int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
 	return trace_parse_common_type(pevent, rec->data);
 }
 
-/**
- * tep_data_event_from_type - find the event by a given type
- * @pevent: a handle to the pevent
- * @type: the type of the event.
- *
- * This returns the event form a given @type;
- */
-struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type)
-{
-	return tep_find_event(pevent, type);
-}
-
 /**
  * tep_data_pid - parse the PID from record
  * @pevent: a handle to the pevent
@@ -5292,8 +5319,8 @@ const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
 	return comm;
 }
 
-static struct cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *next)
+static struct tep_cmdline *
+pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)next;
 
@@ -5305,7 +5332,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne
 	while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
 		cmdlist = cmdlist->next;
 
-	return (struct cmdline *)cmdlist;
+	return (struct tep_cmdline *)cmdlist;
 }
 
 /**
@@ -5321,10 +5348,10 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne
  * next pid.
  * Also, it does a linear search, so it may be slow.
  */
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
-				       struct cmdline *next)
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+					   struct tep_cmdline *next)
 {
-	struct cmdline *cmdline;
+	struct tep_cmdline *cmdline;
 
 	/*
 	 * If the cmdlines have not been converted yet, then use
@@ -5363,7 +5390,7 @@ struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *co
  * Returns the pid for a give cmdline. If @cmdline is NULL, then
  * -1 is returned.
  */
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
 
@@ -6593,6 +6620,12 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
  *
  * If @id is >= 0, then it is used to find the event.
  * else @sys_name and @event_name are used.
+ *
+ * Returns:
+ *  TEP_REGISTER_SUCCESS_OVERWRITE if an existing handler is overwritten
+ *  TEP_REGISTER_SUCCESS if a new handler is registered successfully
+ *  negative TEP_ERRNO_... in case of an error
+ *
  */
 int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
@@ -6610,7 +6643,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 
 	event->handler = func;
 	event->context = context;
-	return 0;
+	return TEP_REGISTER_SUCCESS_OVERWRITE;
 
  not_found:
 	/* Save for later use. */
@@ -6640,7 +6673,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 	pevent->handlers = handle;
 	handle->context = context;
 
-	return -1;
+	return TEP_REGISTER_SUCCESS;
 }
 
 static int handle_matches(struct event_handler *handler, int id,
@@ -6723,8 +6756,10 @@ struct tep_handle *tep_alloc(void)
 {
 	struct tep_handle *pevent = calloc(1, sizeof(*pevent));
 
-	if (pevent)
+	if (pevent) {
 		pevent->ref_count = 1;
+		pevent->host_bigendian = tep_host_bigendian();
+	}
 
 	return pevent;
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 35d37087d3c5..aec48f2aea8a 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -432,6 +432,7 @@ int tep_set_function_resolver(struct tep_handle *pevent,
 			      tep_func_resolver_t *func, void *priv);
 void tep_reset_function_resolver(struct tep_handle *pevent);
 int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
 int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
 int tep_register_function(struct tep_handle *pevent, char *name,
 			  unsigned long long addr, char *mod);
@@ -484,6 +485,11 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
 			 struct tep_event *event, const char *name,
 			 struct tep_record *record, int err);
 
+enum tep_reg_handler {
+	TEP_REGISTER_SUCCESS = 0,
+	TEP_REGISTER_SUCCESS_OVERWRITE,
+};
+
 int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context);
@@ -520,15 +526,14 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
 void tep_data_lat_fmt(struct tep_handle *pevent,
 		      struct trace_seq *s, struct tep_record *record);
 int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type);
 int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
 const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
-struct cmdline;
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
-				       struct cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
+struct tep_cmdline;
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+					   struct tep_cmdline *next);
+int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
 		     struct tep_format_field *field);
@@ -553,7 +558,7 @@ int tep_get_long_size(struct tep_handle *pevent);
 void tep_set_long_size(struct tep_handle *pevent, int long_size);
 int tep_get_page_size(struct tep_handle *pevent);
 void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_is_file_bigendian(struct tep_handle *pevent);
+int tep_file_bigendian(struct tep_handle *pevent);
 void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
 int tep_is_host_bigendian(struct tep_handle *pevent);
 void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 754050eea467..64b9c25a1fd3 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -389,7 +389,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 	 * We can only use the structure if file is of the same
 	 * endianness.
 	 */
-	if (tep_is_file_bigendian(event->pevent) ==
+	if (tep_file_bigendian(event->pevent) ==
 	    tep_is_host_bigendian(event->pevent)) {
 
 		trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index 8ff1d55954d1..8d5ecd2bf877 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -100,7 +100,8 @@ static void expand_buffer(struct trace_seq *s)
  * @fmt: printf format string
  *
  * It returns 0 if the trace oversizes the buffer's free
- * space, 1 otherwise.
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
  *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
@@ -129,9 +130,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 		goto try_again;
 	}
 
-	s->len += ret;
+	if (ret > 0)
+		s->len += ret;
 
-	return 1;
+	return ret;
 }
 
 /**
@@ -139,6 +141,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
  * @s: trace sequence descriptor
  * @fmt: printf format string
  *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
+ * *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
  * trace_seq_printf is used to store strings into a special
@@ -163,9 +169,10 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 		goto try_again;
 	}
 
-	s->len += ret;
+	if (ret > 0)
+		s->len += ret;
 
-	return len;
+	return ret;
 }
 
 /**
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ff29c3372ec3..0ee6795d82cc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -524,12 +524,14 @@ $(arch_errno_name_array): $(arch_errno_tbl)
 
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
+# Create python binding output directory if not already present
+_dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
+
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
 	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
         CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
-	mkdir -p $(OUTPUT)python && \
 	cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/
 
 please_set_SHELL_PATH_to_a_more_modern_shell:
@@ -660,12 +662,12 @@ $(OUTPUT)perf-%: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 ifndef NO_PERF_READ_VDSO32
-$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c
+$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-map.c
 	$(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 
 ifndef NO_PERF_READ_VDSOX32
-$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
+$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-map.c
 	$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 
diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build
index 883c57ff0c08..d9ae2733f9cc 100644
--- a/tools/perf/arch/arm/tests/Build
+++ b/tools/perf/arch/arm/tests/Build
@@ -1,4 +1,5 @@
 libperf-y += regs_load.o
 libperf-y += dwarf-unwind.o
+libperf-y += vectors-page.o
 
 libperf-y += arch-tests.o
diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c
index 5b1543c98022..6848101a855f 100644
--- a/tools/perf/arch/arm/tests/arch-tests.c
+++ b/tools/perf/arch/arm/tests/arch-tests.c
@@ -10,6 +10,10 @@ struct test arch_tests[] = {
 		.func = test__dwarf_unwind,
 	},
 #endif
+	{
+		.desc = "Vectors page",
+		.func = test__vectors_page,
+	},
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c
new file mode 100644
index 000000000000..7ffdd79971c8
--- /dev/null
+++ b/tools/perf/arch/arm/tests/vectors-page.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+#include <linux/compiler.h>
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "util/find-map.c"
+
+#define VECTORS__MAP_NAME "[vectors]"
+
+int test__vectors_page(struct test *test __maybe_unused,
+		       int subtest __maybe_unused)
+{
+	void *start, *end;
+
+	if (find_map(&start, &end, VECTORS__MAP_NAME)) {
+		pr_err("%s not found, is CONFIG_KUSER_HELPERS enabled?\n",
+		       VECTORS__MAP_NAME);
+		return TEST_FAIL;
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index a111239df182..e58d00d62f02 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -14,18 +14,25 @@ PERF_HAVE_JITDUMP := 1
 out    := $(OUTPUT)arch/powerpc/include/generated/asm
 header32 := $(out)/syscalls_32.c
 header64 := $(out)/syscalls_64.c
-sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h
-sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/
+syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header64): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	(diff -B $(sysdef) $(syskrn) >/dev/null) \
+	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@
 
 $(header32): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	(diff -B $(sysdef) $(syskrn) >/dev/null) \
+	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64)
diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
index ef52e1dd694b..6c58060aa03b 100755
--- a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
@@ -9,10 +9,9 @@
 # Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
 
 wordsize=$1
-gcc=$2
-input=$3
+SYSCALL_TBL=$2
 
-if ! test -r $input; then
+if ! test -r $SYSCALL_TBL; then
 	echo "Could not read input file" >&2
 	exit 1
 fi
@@ -20,18 +19,21 @@ fi
 create_table()
 {
 	local wordsize=$1
-	local max_nr
+	local max_nr nr abi sc discard
+	max_nr=-1
+	nr=0
 
 	echo "static const char *syscalltbl_powerpc_${wordsize}[] = {"
-	while read sc nr; do
-		printf '\t[%d] = "%s",\n' $nr $sc
-		max_nr=$nr
+	while read nr abi sc discard; do
+		if [ "$max_nr" -lt "$nr" ]; then
+			printf '\t[%d] = "%s",\n' $nr $sc
+			max_nr=$nr
+		fi
 	done
 	echo '};'
 	echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr"
 }
 
-$gcc -m${wordsize} -E -dM -x c  $input	       \
-	|sed -ne 's/^#define __NR_//p' \
-	|sort -t' ' -k2 -nu	       \
+grep -E "^[[:digit:]]+[[:space:]]+(common|spu|nospu|${wordsize})" $SYSCALL_TBL \
+	|sort -k1 -n                                                           \
 	|create_table ${wordsize}
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
new file mode 100644
index 000000000000..db3bbb8744af
--- /dev/null
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -0,0 +1,427 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# system call numbers and entry vectors for powerpc
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The <abi> can be common, spu, nospu, 64, or 32 for this file.
+#
+0	nospu	restart_syscall			sys_restart_syscall
+1	nospu	exit				sys_exit
+2	nospu	fork				ppc_fork
+3	common	read				sys_read
+4	common	write				sys_write
+5	common	open				sys_open			compat_sys_open
+6	common	close				sys_close
+7	common	waitpid				sys_waitpid
+8	common	creat				sys_creat
+9	common	link				sys_link
+10	common	unlink				sys_unlink
+11	nospu	execve				sys_execve			compat_sys_execve
+12	common	chdir				sys_chdir
+13	common	time				sys_time			compat_sys_time
+14	common	mknod				sys_mknod
+15	common	chmod				sys_chmod
+16	common	lchown				sys_lchown
+17	common	break				sys_ni_syscall
+18	32	oldstat				sys_stat			sys_ni_syscall
+18	64	oldstat				sys_ni_syscall
+18	spu	oldstat				sys_ni_syscall
+19	common	lseek				sys_lseek			compat_sys_lseek
+20	common	getpid				sys_getpid
+21	nospu	mount				sys_mount			compat_sys_mount
+22	32	umount				sys_oldumount
+22	64	umount				sys_ni_syscall
+22	spu	umount				sys_ni_syscall
+23	common	setuid				sys_setuid
+24	common	getuid				sys_getuid
+25	common	stime				sys_stime			compat_sys_stime
+26	nospu	ptrace				sys_ptrace			compat_sys_ptrace
+27	common	alarm				sys_alarm
+28	32	oldfstat			sys_fstat			sys_ni_syscall
+28	64	oldfstat			sys_ni_syscall
+28	spu	oldfstat			sys_ni_syscall
+29	nospu	pause				sys_pause
+30	nospu	utime				sys_utime			compat_sys_utime
+31	common	stty				sys_ni_syscall
+32	common	gtty				sys_ni_syscall
+33	common	access				sys_access
+34	common	nice				sys_nice
+35	common	ftime				sys_ni_syscall
+36	common	sync				sys_sync
+37	common	kill				sys_kill
+38	common	rename				sys_rename
+39	common	mkdir				sys_mkdir
+40	common	rmdir				sys_rmdir
+41	common	dup				sys_dup
+42	common	pipe				sys_pipe
+43	common	times				sys_times			compat_sys_times
+44	common	prof				sys_ni_syscall
+45	common	brk				sys_brk
+46	common	setgid				sys_setgid
+47	common	getgid				sys_getgid
+48	nospu	signal				sys_signal
+49	common	geteuid				sys_geteuid
+50	common	getegid				sys_getegid
+51	nospu	acct				sys_acct
+52	nospu	umount2				sys_umount
+53	common	lock				sys_ni_syscall
+54	common	ioctl				sys_ioctl			compat_sys_ioctl
+55	common	fcntl				sys_fcntl			compat_sys_fcntl
+56	common	mpx				sys_ni_syscall
+57	common	setpgid				sys_setpgid
+58	common	ulimit				sys_ni_syscall
+59	32	oldolduname			sys_olduname
+59	64	oldolduname			sys_ni_syscall
+59	spu	oldolduname			sys_ni_syscall
+60	common	umask				sys_umask
+61	common	chroot				sys_chroot
+62	nospu	ustat				sys_ustat			compat_sys_ustat
+63	common	dup2				sys_dup2
+64	common	getppid				sys_getppid
+65	common	getpgrp				sys_getpgrp
+66	common	setsid				sys_setsid
+67	32	sigaction			sys_sigaction			compat_sys_sigaction
+67	64	sigaction			sys_ni_syscall
+67	spu	sigaction			sys_ni_syscall
+68	common	sgetmask			sys_sgetmask
+69	common	ssetmask			sys_ssetmask
+70	common	setreuid			sys_setreuid
+71	common	setregid			sys_setregid
+72	32	sigsuspend			sys_sigsuspend
+72	64	sigsuspend			sys_ni_syscall
+72	spu	sigsuspend			sys_ni_syscall
+73	32	sigpending			sys_sigpending			compat_sys_sigpending
+73	64	sigpending			sys_ni_syscall
+73	spu	sigpending			sys_ni_syscall
+74	common	sethostname			sys_sethostname
+75	common	setrlimit			sys_setrlimit			compat_sys_setrlimit
+76	32	getrlimit			sys_old_getrlimit		compat_sys_old_getrlimit
+76	64	getrlimit			sys_ni_syscall
+76	spu	getrlimit			sys_ni_syscall
+77	common	getrusage			sys_getrusage			compat_sys_getrusage
+78	common	gettimeofday			sys_gettimeofday		compat_sys_gettimeofday
+79	common	settimeofday			sys_settimeofday		compat_sys_settimeofday
+80	common	getgroups			sys_getgroups
+81	common	setgroups			sys_setgroups
+82	32	select				ppc_select			sys_ni_syscall
+82	64	select				sys_ni_syscall
+82	spu	select				sys_ni_syscall
+83	common	symlink				sys_symlink
+84	32	oldlstat			sys_lstat			sys_ni_syscall
+84	64	oldlstat			sys_ni_syscall
+84	spu	oldlstat			sys_ni_syscall
+85	common	readlink			sys_readlink
+86	nospu	uselib				sys_uselib
+87	nospu	swapon				sys_swapon
+88	nospu	reboot				sys_reboot
+89	32	readdir				sys_old_readdir			compat_sys_old_readdir
+89	64	readdir				sys_ni_syscall
+89	spu	readdir				sys_ni_syscall
+90	common	mmap				sys_mmap
+91	common	munmap				sys_munmap
+92	common	truncate			sys_truncate			compat_sys_truncate
+93	common	ftruncate			sys_ftruncate			compat_sys_ftruncate
+94	common	fchmod				sys_fchmod
+95	common	fchown				sys_fchown
+96	common	getpriority			sys_getpriority
+97	common	setpriority			sys_setpriority
+98	common	profil				sys_ni_syscall
+99	nospu	statfs				sys_statfs			compat_sys_statfs
+100	nospu	fstatfs				sys_fstatfs			compat_sys_fstatfs
+101	common	ioperm				sys_ni_syscall
+102	common	socketcall			sys_socketcall			compat_sys_socketcall
+103	common	syslog				sys_syslog
+104	common	setitimer			sys_setitimer			compat_sys_setitimer
+105	common	getitimer			sys_getitimer			compat_sys_getitimer
+106	common	stat				sys_newstat			compat_sys_newstat
+107	common	lstat				sys_newlstat			compat_sys_newlstat
+108	common	fstat				sys_newfstat			compat_sys_newfstat
+109	32	olduname			sys_uname
+109	64	olduname			sys_ni_syscall
+109	spu	olduname			sys_ni_syscall
+110	common	iopl				sys_ni_syscall
+111	common	vhangup				sys_vhangup
+112	common	idle				sys_ni_syscall
+113	common	vm86				sys_ni_syscall
+114	common	wait4				sys_wait4			compat_sys_wait4
+115	nospu	swapoff				sys_swapoff
+116	common	sysinfo				sys_sysinfo			compat_sys_sysinfo
+117	nospu	ipc				sys_ipc				compat_sys_ipc
+118	common	fsync				sys_fsync
+119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
+119	64	sigreturn			sys_ni_syscall
+119	spu	sigreturn			sys_ni_syscall
+120	nospu	clone				ppc_clone
+121	common	setdomainname			sys_setdomainname
+122	common	uname				sys_newuname
+123	common	modify_ldt			sys_ni_syscall
+124	common	adjtimex			sys_adjtimex			compat_sys_adjtimex
+125	common	mprotect			sys_mprotect
+126	32	sigprocmask			sys_sigprocmask			compat_sys_sigprocmask
+126	64	sigprocmask			sys_ni_syscall
+126	spu	sigprocmask			sys_ni_syscall
+127	common	create_module			sys_ni_syscall
+128	nospu	init_module			sys_init_module
+129	nospu	delete_module			sys_delete_module
+130	common	get_kernel_syms			sys_ni_syscall
+131	nospu	quotactl			sys_quotactl
+132	common	getpgid				sys_getpgid
+133	common	fchdir				sys_fchdir
+134	common	bdflush				sys_bdflush
+135	common	sysfs				sys_sysfs
+136	32	personality			sys_personality			ppc64_personality
+136	64	personality			ppc64_personality
+136	spu	personality			ppc64_personality
+137	common	afs_syscall			sys_ni_syscall
+138	common	setfsuid			sys_setfsuid
+139	common	setfsgid			sys_setfsgid
+140	common	_llseek				sys_llseek
+141	common	getdents			sys_getdents			compat_sys_getdents
+142	common	_newselect			sys_select			compat_sys_select
+143	common	flock				sys_flock
+144	common	msync				sys_msync
+145	common	readv				sys_readv			compat_sys_readv
+146	common	writev				sys_writev			compat_sys_writev
+147	common	getsid				sys_getsid
+148	common	fdatasync			sys_fdatasync
+149	nospu	_sysctl				sys_sysctl			compat_sys_sysctl
+150	common	mlock				sys_mlock
+151	common	munlock				sys_munlock
+152	common	mlockall			sys_mlockall
+153	common	munlockall			sys_munlockall
+154	common	sched_setparam			sys_sched_setparam
+155	common	sched_getparam			sys_sched_getparam
+156	common	sched_setscheduler		sys_sched_setscheduler
+157	common	sched_getscheduler		sys_sched_getscheduler
+158	common	sched_yield			sys_sched_yield
+159	common	sched_get_priority_max		sys_sched_get_priority_max
+160	common	sched_get_priority_min		sys_sched_get_priority_min
+161	common	sched_rr_get_interval		sys_sched_rr_get_interval	compat_sys_sched_rr_get_interval
+162	common	nanosleep			sys_nanosleep			compat_sys_nanosleep
+163	common	mremap				sys_mremap
+164	common	setresuid			sys_setresuid
+165	common	getresuid			sys_getresuid
+166	common	query_module			sys_ni_syscall
+167	common	poll				sys_poll
+168	common	nfsservctl			sys_ni_syscall
+169	common	setresgid			sys_setresgid
+170	common	getresgid			sys_getresgid
+171	common	prctl				sys_prctl
+172	nospu	rt_sigreturn			sys_rt_sigreturn		compat_sys_rt_sigreturn
+173	nospu	rt_sigaction			sys_rt_sigaction		compat_sys_rt_sigaction
+174	nospu	rt_sigprocmask			sys_rt_sigprocmask		compat_sys_rt_sigprocmask
+175	nospu	rt_sigpending			sys_rt_sigpending		compat_sys_rt_sigpending
+176	nospu	rt_sigtimedwait			sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
+177	nospu 	rt_sigqueueinfo			sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+178	nospu 	rt_sigsuspend			sys_rt_sigsuspend		compat_sys_rt_sigsuspend
+179	common	pread64				sys_pread64			compat_sys_pread64
+180	common	pwrite64			sys_pwrite64			compat_sys_pwrite64
+181	common	chown				sys_chown
+182	common	getcwd				sys_getcwd
+183	common	capget				sys_capget
+184	common	capset				sys_capset
+185	nospu	sigaltstack			sys_sigaltstack			compat_sys_sigaltstack
+186	32	sendfile			sys_sendfile			compat_sys_sendfile
+186	64	sendfile			sys_sendfile64
+186	spu	sendfile			sys_sendfile64
+187	common	getpmsg				sys_ni_syscall
+188	common 	putpmsg				sys_ni_syscall
+189	nospu	vfork				ppc_vfork
+190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
+191	common	readahead			sys_readahead			compat_sys_readahead
+192	32	mmap2				sys_mmap2			compat_sys_mmap2
+193	32	truncate64			sys_truncate64			compat_sys_truncate64
+194	32	ftruncate64			sys_ftruncate64			compat_sys_ftruncate64
+195	32	stat64				sys_stat64
+196	32	lstat64				sys_lstat64
+197	32	fstat64				sys_fstat64
+198	nospu 	pciconfig_read			sys_pciconfig_read
+199	nospu 	pciconfig_write			sys_pciconfig_write
+200	nospu 	pciconfig_iobase		sys_pciconfig_iobase
+201	common 	multiplexer			sys_ni_syscall
+202	common	getdents64			sys_getdents64
+203	common	pivot_root			sys_pivot_root
+204	32	fcntl64				sys_fcntl64			compat_sys_fcntl64
+205	common	madvise				sys_madvise
+206	common	mincore				sys_mincore
+207	common	gettid				sys_gettid
+208	common	tkill				sys_tkill
+209	common	setxattr			sys_setxattr
+210	common	lsetxattr			sys_lsetxattr
+211	common	fsetxattr			sys_fsetxattr
+212	common	getxattr			sys_getxattr
+213	common	lgetxattr			sys_lgetxattr
+214	common	fgetxattr			sys_fgetxattr
+215	common	listxattr			sys_listxattr
+216	common	llistxattr			sys_llistxattr
+217	common	flistxattr			sys_flistxattr
+218	common	removexattr			sys_removexattr
+219	common	lremovexattr			sys_lremovexattr
+220	common	fremovexattr			sys_fremovexattr
+221	common	futex				sys_futex			compat_sys_futex
+222	common	sched_setaffinity		sys_sched_setaffinity		compat_sys_sched_setaffinity
+223	common	sched_getaffinity		sys_sched_getaffinity		compat_sys_sched_getaffinity
+# 224 unused
+225	common	tuxcall				sys_ni_syscall
+226	32	sendfile64			sys_sendfile64			compat_sys_sendfile64
+227	common	io_setup			sys_io_setup			compat_sys_io_setup
+228	common	io_destroy			sys_io_destroy
+229	common	io_getevents			sys_io_getevents		compat_sys_io_getevents
+230	common	io_submit			sys_io_submit			compat_sys_io_submit
+231	common	io_cancel			sys_io_cancel
+232	nospu	set_tid_address			sys_set_tid_address
+233	common	fadvise64			sys_fadvise64			ppc32_fadvise64
+234	nospu	exit_group			sys_exit_group
+235	nospu	lookup_dcookie			sys_lookup_dcookie		compat_sys_lookup_dcookie
+236	common	epoll_create			sys_epoll_create
+237	common	epoll_ctl			sys_epoll_ctl
+238	common	epoll_wait			sys_epoll_wait
+239	common	remap_file_pages		sys_remap_file_pages
+240	common	timer_create			sys_timer_create		compat_sys_timer_create
+241	common	timer_settime			sys_timer_settime		compat_sys_timer_settime
+242	common	timer_gettime			sys_timer_gettime		compat_sys_timer_gettime
+243	common	timer_getoverrun		sys_timer_getoverrun
+244	common	timer_delete			sys_timer_delete
+245	common	clock_settime			sys_clock_settime		compat_sys_clock_settime
+246	common	clock_gettime			sys_clock_gettime		compat_sys_clock_gettime
+247	common	clock_getres			sys_clock_getres		compat_sys_clock_getres
+248	common	clock_nanosleep			sys_clock_nanosleep		compat_sys_clock_nanosleep
+249	32	swapcontext			ppc_swapcontext			ppc32_swapcontext
+249	64	swapcontext			ppc64_swapcontext
+249	spu	swapcontext			sys_ni_syscall
+250	common	tgkill				sys_tgkill
+251	common	utimes				sys_utimes			compat_sys_utimes
+252	common	statfs64			sys_statfs64			compat_sys_statfs64
+253	common	fstatfs64			sys_fstatfs64			compat_sys_fstatfs64
+254	32	fadvise64_64			ppc_fadvise64_64
+254	spu	fadvise64_64			sys_ni_syscall
+255	common	rtas				sys_rtas
+256	32	sys_debug_setcontext		sys_debug_setcontext		sys_ni_syscall
+256	64	sys_debug_setcontext		sys_ni_syscall
+256	spu	sys_debug_setcontext		sys_ni_syscall
+# 257 reserved for vserver
+258	nospu	migrate_pages			sys_migrate_pages		compat_sys_migrate_pages
+259	nospu	mbind				sys_mbind			compat_sys_mbind
+260	nospu	get_mempolicy			sys_get_mempolicy		compat_sys_get_mempolicy
+261	nospu	set_mempolicy			sys_set_mempolicy		compat_sys_set_mempolicy
+262	nospu	mq_open				sys_mq_open			compat_sys_mq_open
+263	nospu	mq_unlink			sys_mq_unlink
+264	nospu	mq_timedsend			sys_mq_timedsend		compat_sys_mq_timedsend
+265	nospu	mq_timedreceive			sys_mq_timedreceive		compat_sys_mq_timedreceive
+266	nospu	mq_notify			sys_mq_notify			compat_sys_mq_notify
+267	nospu	mq_getsetattr			sys_mq_getsetattr		compat_sys_mq_getsetattr
+268	nospu	kexec_load			sys_kexec_load			compat_sys_kexec_load
+269	nospu	add_key				sys_add_key
+270	nospu	request_key			sys_request_key
+271	nospu	keyctl				sys_keyctl			compat_sys_keyctl
+272	nospu	waitid				sys_waitid			compat_sys_waitid
+273	nospu	ioprio_set			sys_ioprio_set
+274	nospu	ioprio_get			sys_ioprio_get
+275	nospu	inotify_init			sys_inotify_init
+276	nospu	inotify_add_watch		sys_inotify_add_watch
+277	nospu	inotify_rm_watch		sys_inotify_rm_watch
+278	nospu	spu_run				sys_spu_run
+279	nospu	spu_create			sys_spu_create
+280	nospu	pselect6			sys_pselect6			compat_sys_pselect6
+281	nospu	ppoll				sys_ppoll			compat_sys_ppoll
+282	common	unshare				sys_unshare
+283	common	splice				sys_splice
+284	common	tee				sys_tee
+285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+286	common	openat				sys_openat			compat_sys_openat
+287	common	mkdirat				sys_mkdirat
+288	common	mknodat				sys_mknodat
+289	common	fchownat			sys_fchownat
+290	common	futimesat			sys_futimesat			compat_sys_futimesat
+291	32	fstatat64			sys_fstatat64
+291	64	newfstatat			sys_newfstatat
+291	spu	newfstatat			sys_newfstatat
+292	common	unlinkat			sys_unlinkat
+293	common	renameat			sys_renameat
+294	common	linkat				sys_linkat
+295	common	symlinkat			sys_symlinkat
+296	common	readlinkat			sys_readlinkat
+297	common	fchmodat			sys_fchmodat
+298	common	faccessat			sys_faccessat
+299	common	get_robust_list			sys_get_robust_list		compat_sys_get_robust_list
+300	common	set_robust_list			sys_set_robust_list		compat_sys_set_robust_list
+301	common	move_pages			sys_move_pages			compat_sys_move_pages
+302	common	getcpu				sys_getcpu
+303	nospu	epoll_pwait			sys_epoll_pwait			compat_sys_epoll_pwait
+304	common	utimensat			sys_utimensat			compat_sys_utimensat
+305	common	signalfd			sys_signalfd			compat_sys_signalfd
+306	common	timerfd_create			sys_timerfd_create
+307	common	eventfd				sys_eventfd
+308	common	sync_file_range2		sys_sync_file_range2		compat_sys_sync_file_range2
+309	nospu	fallocate			sys_fallocate			compat_sys_fallocate
+310	nospu	subpage_prot			sys_subpage_prot
+311	common	timerfd_settime			sys_timerfd_settime		compat_sys_timerfd_settime
+312	common	timerfd_gettime			sys_timerfd_gettime		compat_sys_timerfd_gettime
+313	common	signalfd4			sys_signalfd4			compat_sys_signalfd4
+314	common	eventfd2			sys_eventfd2
+315	common	epoll_create1			sys_epoll_create1
+316	common	dup3				sys_dup3
+317	common	pipe2				sys_pipe2
+318	nospu	inotify_init1			sys_inotify_init1
+319	common	perf_event_open			sys_perf_event_open
+320	common	preadv				sys_preadv			compat_sys_preadv
+321	common	pwritev				sys_pwritev			compat_sys_pwritev
+322	nospu	rt_tgsigqueueinfo		sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
+323	nospu	fanotify_init			sys_fanotify_init
+324	nospu	fanotify_mark			sys_fanotify_mark		compat_sys_fanotify_mark
+325	common	prlimit64			sys_prlimit64
+326	common	socket				sys_socket
+327	common	bind				sys_bind
+328	common	connect				sys_connect
+329	common	listen				sys_listen
+330	common	accept				sys_accept
+331	common	getsockname			sys_getsockname
+332	common	getpeername			sys_getpeername
+333	common	socketpair			sys_socketpair
+334	common	send				sys_send
+335	common	sendto				sys_sendto
+336	common	recv				sys_recv			compat_sys_recv
+337	common	recvfrom			sys_recvfrom			compat_sys_recvfrom
+338	common	shutdown			sys_shutdown
+339	common	setsockopt			sys_setsockopt			compat_sys_setsockopt
+340	common	getsockopt			sys_getsockopt			compat_sys_getsockopt
+341	common	sendmsg				sys_sendmsg			compat_sys_sendmsg
+342	common	recvmsg				sys_recvmsg			compat_sys_recvmsg
+343	common	recvmmsg			sys_recvmmsg			compat_sys_recvmmsg
+344	common	accept4				sys_accept4
+345	common	name_to_handle_at		sys_name_to_handle_at
+346	common	open_by_handle_at		sys_open_by_handle_at		compat_sys_open_by_handle_at
+347	common	clock_adjtime			sys_clock_adjtime		compat_sys_clock_adjtime
+348	common	syncfs				sys_syncfs
+349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
+350	common	setns				sys_setns
+351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+353	nospu	finit_module			sys_finit_module
+354	nospu	kcmp				sys_kcmp
+355	common	sched_setattr			sys_sched_setattr
+356	common	sched_getattr			sys_sched_getattr
+357	common	renameat2			sys_renameat2
+358	common	seccomp				sys_seccomp
+359	common	getrandom			sys_getrandom
+360	common	memfd_create			sys_memfd_create
+361	common	bpf				sys_bpf
+362	nospu	execveat			sys_execveat			compat_sys_execveat
+363	32	switch_endian			sys_ni_syscall
+363	64	switch_endian			ppc_switch_endian
+363	spu	switch_endian			sys_ni_syscall
+364	common	userfaultfd			sys_userfaultfd
+365	common	membarrier			sys_membarrier
+378	nospu	mlock2				sys_mlock2
+379	nospu	copy_file_range			sys_copy_file_range
+380	common	preadv2				sys_preadv2			compat_sys_preadv2
+381	common	pwritev2			sys_pwritev2			compat_sys_pwritev2
+382	nospu	kexec_file_load			sys_kexec_file_load
+383	nospu	statx				sys_statx
+384	nospu	pkey_alloc			sys_pkey_alloc
+385	nospu	pkey_free			sys_pkey_free
+386	nospu	pkey_mprotect			sys_pkey_mprotect
+387	nospu	rseq				sys_rseq
+388	nospu	io_pgetevents			sys_io_pgetevents		compat_sys_io_pgetevents
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1410d66192f7..63a3afc7f32b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -561,7 +561,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 					break;
 			}
 		}
-		wait4(child_pid, &status, 0, &stat_config.ru_data);
+		if (child_pid != -1)
+			wait4(child_pid, &status, 0, &stat_config.ru_data);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fe3ecfb2e64b..f64e312db787 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1028,12 +1028,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 static int callchain_param__setup_sample_type(struct callchain_param *callchain)
 {
-	if (!perf_hpp_list.sym) {
-		if (callchain->enabled) {
-			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
-			return -EINVAL;
-		}
-	} else if (callchain->mode != CHAIN_NONE) {
+	if (callchain->mode != CHAIN_NONE) {
 		if (callchain_register_param(callchain) < 0) {
 			ui__error("Can't register callchain params.\n");
 			return -EINVAL;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index adbf28183560..ed4583128b9c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1758,6 +1758,7 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 {
 	struct thread_trace *ttrace;
 	size_t printed;
+	int len;
 
 	if (trace->failure_only || trace->current == NULL)
 		return 0;
@@ -1768,9 +1769,14 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 		return 0;
 
 	printed  = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
-	printed += fprintf(trace->output, ")%-*s ...\n", trace->args_alignment, ttrace->entry_str);
-	ttrace->entry_pending = false;
+	printed += len = fprintf(trace->output, "%s)", ttrace->entry_str);
+
+	if (len < trace->args_alignment - 4)
+		printed += fprintf(trace->output, "%-*s", trace->args_alignment - 4 - len, " ");
 
+	printed += fprintf(trace->output, " ...\n");
+
+	ttrace->entry_pending = false;
 	++trace->nr_events_printed;
 
 	return printed;
@@ -2026,9 +2032,10 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (ttrace->entry_pending) {
 		printed = fprintf(trace->output, "%s", ttrace->entry_str);
 	} else {
-		fprintf(trace->output, " ... [");
+		printed += fprintf(trace->output, " ... [");
 		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
-		fprintf(trace->output, "]: %s()", sc->name);
+		printed += 9;
+		printed += fprintf(trace->output, "]: %s()", sc->name);
 	}
 
 	printed++; /* the closing ')' */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 6cb98f8570a2..7b55613924de 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -10,6 +10,7 @@ include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
+include/uapi/linux/mount.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -49,7 +50,6 @@ arch/parisc/include/uapi/asm/errno.h
 arch/powerpc/include/uapi/asm/errno.h
 arch/sparc/include/uapi/asm/errno.h
 arch/x86/include/uapi/asm/errno.h
-arch/powerpc/include/uapi/asm/unistd.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/__fls.h
diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c
index 8c0ca0cc428f..aaa5210ea84a 100644
--- a/tools/perf/perf-read-vdso.c
+++ b/tools/perf/perf-read-vdso.c
@@ -5,17 +5,17 @@
 #define VDSO__MAP_NAME "[vdso]"
 
 /*
- * Include definition of find_vdso_map() also used in util/vdso.c for
+ * Include definition of find_map() also used in util/vdso.c for
  * building perf.
  */
-#include "util/find-vdso-map.c"
+#include "util/find-map.c"
 
 int main(void)
 {
 	void *start, *end;
 	size_t size, written;
 
-	if (find_vdso_map(&start, &end))
+	if (find_map(&start, &end, VDSO__MAP_NAME))
 		return 1;
 
 	size = end - start;
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 1c16e56cd93e..7cb99b433888 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -13,7 +13,8 @@ add_probe_vfs_getname() {
 	local verbose=$1
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string"
+		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
 	fi
 }
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index b82f55fcc294..399f18ca71a3 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -119,4 +119,9 @@ int test__arch_unwind_sample(struct perf_sample *sample,
 			     struct thread *thread);
 #endif
 #endif
+
+#if defined(__arm__)
+int test__vectors_page(struct test *test, int subtest);
+#endif
+
 #endif /* TESTS_H */
diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
index 45547573a1db..847850b2ef6c 100755
--- a/tools/perf/trace/beauty/mount_flags.sh
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -5,11 +5,11 @@
 
 printf "static const char *mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
-egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+egrep $regex ${header_dir}/mount.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
 	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
 	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
-egrep $regex ${header_dir}/fs.h | \
+egrep $regex ${header_dir}/mount.h | \
 	sed -r "s/$regex/\2 \1/g" | \
 	xargs printf "\t[%s + 1] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index d32f8f1124af..3109d7b05e11 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -4,7 +4,7 @@
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
+regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*'
 egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9805e0bc76..70de8f6b3aee 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1723,15 +1723,14 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 opts->show_asm_raw ? "" : "--no-show-raw",
-		 opts->annotate_src ? "-S" : "",
-		 symfs_filename, symfs_filename);
+		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
@@ -1756,7 +1755,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		close(stdout_fd[0]);
 		dup2(stdout_fd[1], 1);
 		close(stdout_fd[1]);
-		execl("/bin/sh", "sh", "-c", command, NULL);
+		execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
+		      NULL);
 		perror(command);
 		exit(-1);
 	}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 32ef7bdca1cf..dc2212e12184 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -766,6 +766,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->iter_cycles += node->iter_cycles;
+			cnode->from_count++;
 		}
 	}
 
@@ -1345,10 +1346,10 @@ static int branch_to_str(char *bf, int bfsize,
 static int branch_from_str(char *bf, int bfsize,
 			   u64 branch_count,
 			   u64 cycles_count, u64 iter_count,
-			   u64 iter_cycles)
+			   u64 iter_cycles, u64 from_count)
 {
 	int printed = 0, i = 0;
-	u64 cycles;
+	u64 cycles, v = 0;
 
 	cycles = cycles_count / branch_count;
 	if (cycles) {
@@ -1357,14 +1358,16 @@ static int branch_from_str(char *bf, int bfsize,
 				bf + printed, bfsize - printed);
 	}
 
-	if (iter_count) {
-		printed += count_pri64_printf(i++, "iter",
-				iter_count,
-				bf + printed, bfsize - printed);
+	if (iter_count && from_count) {
+		v = iter_count / from_count;
+		if (v) {
+			printed += count_pri64_printf(i++, "iter",
+					v, bf + printed, bfsize - printed);
 
-		printed += count_pri64_printf(i++, "avg_cycles",
-				iter_cycles / iter_count,
-				bf + printed, bfsize - printed);
+			printed += count_pri64_printf(i++, "avg_cycles",
+					iter_cycles / iter_count,
+					bf + printed, bfsize - printed);
+		}
 	}
 
 	if (i)
@@ -1377,6 +1380,7 @@ static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 iter_cycles,
+			     u64 from_count,
 			     struct branch_type_stat *brtype_stat)
 {
 	int printed;
@@ -1389,7 +1393,8 @@ static int counts_str_build(char *bf, int bfsize,
 				predicted_count, abort_count, brtype_stat);
 	} else {
 		printed = branch_from_str(bf, bfsize, branch_count,
-				cycles_count, iter_count, iter_cycles);
+				cycles_count, iter_count, iter_cycles,
+				from_count);
 	}
 
 	if (!printed)
@@ -1402,13 +1407,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 				   u64 branch_count, u64 predicted_count,
 				   u64 abort_count, u64 cycles_count,
 				   u64 iter_count, u64 iter_cycles,
+				   u64 from_count,
 				   struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, iter_cycles, brtype_stat);
+			 iter_count, iter_cycles, from_count, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1422,6 +1428,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	u64 branch_count, predicted_count;
 	u64 abort_count, cycles_count;
 	u64 iter_count, iter_cycles;
+	u64 from_count;
 
 	branch_count = clist->branch_count;
 	predicted_count = clist->predicted_count;
@@ -1429,11 +1436,12 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	cycles_count = clist->cycles_count;
 	iter_count = clist->iter_count;
 	iter_cycles = clist->iter_cycles;
+	from_count = clist->from_count;
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
 				       cycles_count, iter_count, iter_cycles,
-				       &clist->brtype_stat);
+				       from_count, &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 154560b1eb65..99d38ac019b8 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -118,6 +118,7 @@ struct callchain_list {
 		bool		has_children;
 	};
 	u64			branch_count;
+	u64			from_count;
 	u64			predicted_count;
 	u64			abort_count;
 	u64			cycles_count;
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-map.c
similarity index 71%
rename from tools/perf/util/find-vdso-map.c
rename to tools/perf/util/find-map.c
index d7823e3508fc..7b2300588ece 100644
--- a/tools/perf/util/find-vdso-map.c
+++ b/tools/perf/util/find-map.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-static int find_vdso_map(void **start, void **end)
+static int find_map(void **start, void **end, const char *name)
 {
 	FILE *maps;
 	char line[128];
@@ -7,7 +7,7 @@ static int find_vdso_map(void **start, void **end)
 
 	maps = fopen("/proc/self/maps", "r");
 	if (!maps) {
-		fprintf(stderr, "vdso: cannot open maps\n");
+		fprintf(stderr, "cannot open maps\n");
 		return -1;
 	}
 
@@ -21,8 +21,7 @@ static int find_vdso_map(void **start, void **end)
 		if (m < 0)
 			continue;
 
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
+		if (!strncmp(&line[m], name, strlen(name)))
 			found = 1;
 	}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6fcb3bce0442..143f7057d581 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2005,7 +2005,7 @@ static void save_iterations(struct iterations *iter,
 {
 	int i;
 
-	iter->nr_loop_iter = nr;
+	iter->nr_loop_iter++;
 	iter->cycles = 0;
 
 	for (i = 0; i < nr; i++)
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 9005fbe0780e..23092fd6451d 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -109,7 +109,6 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 			return ret;
 		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
-		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
 			va_end(ap_saved);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 01f2c7385e38..48efad6d0f90 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -614,6 +614,7 @@ int modules__parse(const char *filename, void *arg,
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
 		"intel_idle",
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 741af209b19d..3702cba11d7d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -18,10 +18,10 @@
 #include "debug.h"
 
 /*
- * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * Include definition of find_map() also used in perf-read-vdso.c for
  * building perf-read-vdso32 and perf-read-vdsox32.
  */
-#include "find-vdso-map.c"
+#include "find-map.c"
 
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
@@ -76,7 +76,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	if (vdso_file->found)
 		return vdso_file->temp_file_name;
 
-	if (vdso_file->error || find_vdso_map(&start, &end))
+	if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME))
 		return NULL;
 
 	size = end - start;
diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 89a2444c1df2..59e417ec3e13 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -6,7 +6,7 @@ VERSION = 1.0
 
 BINDIR=usr/bin
 WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int
-override CFLAGS+= -O1 ${WARNFLAGS}
+override CFLAGS+= $(call cc-option,-O3,-O1) ${WARNFLAGS}
 # Add "-fstack-protector" only if toolchain supports it.
 override CFLAGS+= $(call cc-option,-fstack-protector-strong)
 CC?= $(CROSS_COMPILE)gcc

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2018-11-30  6:25 Ingo Molnar
@ 2018-11-30 21:00 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2018-11-30 21:00 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Fri, 30 Nov 2018 07:25:07 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/a1b3cf6d943800059adc262c4d839524c529db2d

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-11-30  6:25 Ingo Molnar
  2018-11-30 21:00 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2018-11-30  6:25 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 09d3f015d1e1b4fee7e9bbdcf54201d239393391 uprobes: Fix handle_swbp() vs. unregister() + register() race once more

Misc fixes:

 - a counter freezing related regression fix,
 - an uprobes race fix,
 - an Intel PMU unusual event combination fix,
 - and diverse tooling fixes.

 Thanks,

	Ingo

------------------>
Andrea Parri (1):
      uprobes: Fix handle_swbp() vs. unregister() + register() race once more

Arnaldo Carvalho de Melo (5):
      tools build feature: Check if get_current_dir_name() is available
      tools headers uapi: Synchronize i915_drm.h
      tools arch x86: Update tools's copy of cpufeatures.h
      tools uapi asm-generic: Synchronize ioctls.h
      perf tools beauty ioctl: Support new ISO7816 commands

Jiri Olsa (5):
      perf tools: Fix crash on synthesizing the unit
      perf tools: Restore proper cwd on return from mnt namespace
      perf/x86/intel: Move branch tracing setup to the Intel-specific source file
      perf/x86/intel: Add generic branch tracing check to intel_pmu_has_bts()
      perf/x86/intel: Disallow precise_ip on BTS events

Peter Zijlstra (1):
      perf/x86/intel: Fix regression by default disabling perfmon v4 interrupt handling


 Documentation/admin-guide/kernel-parameters.txt |  3 +-
 arch/x86/events/core.c                          | 20 --------
 arch/x86/events/intel/core.c                    | 68 +++++++++++++++++++------
 arch/x86/events/perf_event.h                    | 13 +++--
 kernel/events/uprobes.c                         | 12 ++++-
 tools/arch/x86/include/asm/cpufeatures.h        |  2 +
 tools/build/Makefile.feature                    |  1 +
 tools/build/feature/Makefile                    |  4 ++
 tools/build/feature/test-all.c                  |  5 ++
 tools/build/feature/test-get_current_dir_name.c | 10 ++++
 tools/include/uapi/asm-generic/ioctls.h         |  2 +
 tools/include/uapi/drm/i915_drm.h               | 22 ++++++++
 tools/perf/Makefile.config                      |  5 ++
 tools/perf/tests/attr/base-record               |  2 +-
 tools/perf/trace/beauty/ioctl.c                 |  1 +
 tools/perf/util/Build                           |  1 +
 tools/perf/util/evsel.c                         |  2 +-
 tools/perf/util/get_current_dir_name.c          | 18 +++++++
 tools/perf/util/namespaces.c                    | 17 ++++++-
 tools/perf/util/namespaces.h                    |  1 +
 tools/perf/util/util.h                          |  4 ++
 21 files changed, 166 insertions(+), 47 deletions(-)
 create mode 100644 tools/build/feature/test-get_current_dir_name.c
 create mode 100644 tools/perf/util/get_current_dir_name.c

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 81d1d5a74728..5463d5a4d85c 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -856,7 +856,8 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
-	disable_counter_freezing [HW]
+	perf_v4_pmi=	[X86,INTEL]
+			Format: <bool>
 			Disable Intel PMU counter freezing feature.
 			The feature only exists starting from
 			Arch Perfmon v4 (Skylake and newer).
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 106911b603bd..374a19712e20 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -438,26 +438,6 @@ int x86_setup_perfctr(struct perf_event *event)
 	if (config == -1LL)
 		return -EINVAL;
 
-	/*
-	 * Branch tracing:
-	 */
-	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !attr->freq && hwc->sample_period == 1) {
-		/* BTS is not supported by this architecture. */
-		if (!x86_pmu.bts_active)
-			return -EOPNOTSUPP;
-
-		/* BTS is currently only allowed for user-mode. */
-		if (!attr->exclude_kernel)
-			return -EOPNOTSUPP;
-
-		/* disallow bts if conflicting events are present */
-		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
-			return -EBUSY;
-
-		event->destroy = hw_perf_lbr_event_destroy;
-	}
-
 	hwc->config |= config;
 
 	return 0;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 273c62e81546..ecc3e34ca955 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2306,14 +2306,18 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	return handled;
 }
 
-static bool disable_counter_freezing;
+static bool disable_counter_freezing = true;
 static int __init intel_perf_counter_freezing_setup(char *s)
 {
-	disable_counter_freezing = true;
-	pr_info("Intel PMU Counter freezing feature disabled\n");
+	bool res;
+
+	if (kstrtobool(s, &res))
+		return -EINVAL;
+
+	disable_counter_freezing = !res;
 	return 1;
 }
-__setup("disable_counter_freezing", intel_perf_counter_freezing_setup);
+__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup);
 
 /*
  * Simplified handler for Arch Perfmon v4:
@@ -2470,16 +2474,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 static struct event_constraint *
 intel_bts_constraints(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-	unsigned int hw_event, bts_event;
-
-	if (event->attr.freq)
-		return NULL;
-
-	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
-	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
-
-	if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
+	if (unlikely(intel_pmu_has_bts(event)))
 		return &bts_constraint;
 
 	return NULL;
@@ -3098,10 +3093,51 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 	return flags;
 }
 
+static int intel_pmu_bts_config(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	if (unlikely(intel_pmu_has_bts(event))) {
+		/* BTS is not supported by this architecture. */
+		if (!x86_pmu.bts_active)
+			return -EOPNOTSUPP;
+
+		/* BTS is currently only allowed for user-mode. */
+		if (!attr->exclude_kernel)
+			return -EOPNOTSUPP;
+
+		/* BTS is not allowed for precise events. */
+		if (attr->precise_ip)
+			return -EOPNOTSUPP;
+
+		/* disallow bts if conflicting events are present */
+		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
+			return -EBUSY;
+
+		event->destroy = hw_perf_lbr_event_destroy;
+	}
+
+	return 0;
+}
+
+static int core_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	return intel_pmu_bts_config(event);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
 
+	if (ret)
+		return ret;
+
+	ret = intel_pmu_bts_config(event);
 	if (ret)
 		return ret;
 
@@ -3127,7 +3163,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		/*
 		 * BTS is set up earlier in this path, so don't account twice
 		 */
-		if (!intel_pmu_has_bts(event)) {
+		if (!unlikely(intel_pmu_has_bts(event))) {
 			/* disallow lbr if conflicting events are present */
 			if (x86_add_exclusive(x86_lbr_exclusive_lbr))
 				return -EBUSY;
@@ -3596,7 +3632,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.enable_all		= core_pmu_enable_all,
 	.enable			= core_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
+	.hw_config		= core_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index adae087cecdd..78d7b7031bfc 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -859,11 +859,16 @@ static inline int amd_pmu_init(void)
 
 static inline bool intel_pmu_has_bts(struct perf_event *event)
 {
-	if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !event->attr.freq && event->hw.sample_period == 1)
-		return true;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int hw_event, bts_event;
+
+	if (event->attr.freq)
+		return false;
+
+	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return false;
+	return hw_event == bts_event && hwc->sample_period == 1;
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 96d4bee83489..322e97bbb437 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -829,7 +829,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	BUG_ON((uprobe->offset & ~PAGE_MASK) +
 			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
 
-	smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+	smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
  out:
@@ -2178,10 +2178,18 @@ static void handle_swbp(struct pt_regs *regs)
 	 * After we hit the bp, _unregister + _register can install the
 	 * new and not-yet-analyzed uprobe at the same address, restart.
 	 */
-	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
 	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
 		goto out;
 
+	/*
+	 * Pairs with the smp_wmb() in prepare_uprobe().
+	 *
+	 * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+	 * we must also see the stores to &uprobe->arch performed by the
+	 * prepare_uprobe() call.
+	 */
+	smp_rmb();
+
 	/* Tracing handlers use ->utask to communicate with fetch methods */
 	if (!get_utask())
 		goto out;
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 89a048c2faec..28c4a502b419 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -331,6 +331,8 @@
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
+#define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
+#define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index f216b2f5c3d7..d74bb9414d7c 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC :=                  \
         dwarf_getlocations              \
         fortify-source                  \
         sync-compare-and-swap           \
+        get_current_dir_name            \
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0516259be70f..304b984f11b9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -7,6 +7,7 @@ FILES=                                          \
          test-dwarf_getlocations.bin            \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
+         test-get_current_dir_name.bin          \
          test-glibc.bin                         \
          test-gtk2.bin                          \
          test-gtk2-infobar.bin                  \
@@ -101,6 +102,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-get_current_dir_name.bin:
+	$(BUILD)
+
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 8dc20a61341f..56722bfe6bdd 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -34,6 +34,10 @@
 # include "test-libelf-mmap.c"
 #undef main
 
+#define main main_test_get_current_dir_name
+# include "test-get_current_dir_name.c"
+#undef main
+
 #define main main_test_glibc
 # include "test-glibc.c"
 #undef main
@@ -174,6 +178,7 @@ int main(int argc, char *argv[])
 	main_test_hello();
 	main_test_libelf();
 	main_test_libelf_mmap();
+	main_test_get_current_dir_name();
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
diff --git a/tools/build/feature/test-get_current_dir_name.c b/tools/build/feature/test-get_current_dir_name.c
new file mode 100644
index 000000000000..573000f93212
--- /dev/null
+++ b/tools/build/feature/test-get_current_dir_name.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <stdlib.h>
+
+int main(void)
+{
+	free(get_current_dir_name());
+	return 0;
+}
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
index 040651735662..cdc9f4ca8c27 100644
--- a/tools/include/uapi/asm-generic/ioctls.h
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -79,6 +79,8 @@
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 #define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816	_IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816	_IOWR('T', 0x43, struct serial_iso7816)
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7f5634ce8e88..a4446f452040 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -529,6 +529,28 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
 
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT	52
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index e30d20fb482d..a0e8c23f9125 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -299,6 +299,11 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-get_current_dir_name), 1)
+  CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
+endif
+
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 37940665f736..efd0157b9d22 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -9,7 +9,7 @@ size=112
 config=0
 sample_period=*
 sample_type=263
-read_format=0
+read_format=0|4
 disabled=1
 inherit=1
 pinned=0
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 5d2a7fd8d407..eae59ad15ce3 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -31,6 +31,7 @@ static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 	"TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
 	"TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT",
 	"TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER",
+	"TIOCGISO7816", "TIOCSISO7816",
 	[_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
 	"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
 	"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ecd9f9ceda77..b7bf201fe8a8 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -10,6 +10,7 @@ libperf-y += evlist.o
 libperf-y += evsel.o
 libperf-y += evsel_fprintf.o
 libperf-y += find_bit.o
+libperf-y += get_current_dir_name.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d37bb1566cd9..dbc0466db368 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1092,7 +1092,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
-	if (evsel->own_cpus)
+	if (evsel->own_cpus || evsel->unit)
 		evsel->attr.read_format |= PERF_FORMAT_ID;
 
 	/*
diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c
new file mode 100644
index 000000000000..267aa609a582
--- /dev/null
+++ b/tools/perf/util/get_current_dir_name.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+#include "util.h"
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdlib.h>
+
+/* Android's 'bionic' library, for one, doesn't have this */
+
+char *get_current_dir_name(void)
+{
+	char pwd[PATH_MAX];
+
+	return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd);
+}
+#endif // HAVE_GET_CURRENT_DIR_NAME
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index cf8bd123cf73..aed170bd4384 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
+#include <asm/bug.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
@@ -186,6 +187,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	char curpath[PATH_MAX];
 	int oldns = -1;
 	int newns = -1;
+	char *oldcwd = NULL;
 
 	if (nc == NULL)
 		return;
@@ -199,9 +201,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
 		return;
 
+	oldcwd = get_current_dir_name();
+	if (!oldcwd)
+		return;
+
 	oldns = open(curpath, O_RDONLY);
 	if (oldns < 0)
-		return;
+		goto errout;
 
 	newns = open(nsi->mntns_path, O_RDONLY);
 	if (newns < 0)
@@ -210,11 +216,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (setns(newns, CLONE_NEWNS) < 0)
 		goto errout;
 
+	nc->oldcwd = oldcwd;
 	nc->oldns = oldns;
 	nc->newns = newns;
 	return;
 
 errout:
+	free(oldcwd);
 	if (oldns > -1)
 		close(oldns);
 	if (newns > -1)
@@ -223,11 +231,16 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 
 void nsinfo__mountns_exit(struct nscookie *nc)
 {
-	if (nc == NULL || nc->oldns == -1 || nc->newns == -1)
+	if (nc == NULL || nc->oldns == -1 || nc->newns == -1 || !nc->oldcwd)
 		return;
 
 	setns(nc->oldns, CLONE_NEWNS);
 
+	if (nc->oldcwd) {
+		WARN_ON_ONCE(chdir(nc->oldcwd));
+		zfree(&nc->oldcwd);
+	}
+
 	if (nc->oldns > -1) {
 		close(nc->oldns);
 		nc->oldns = -1;
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index cae1a9a39722..d5f46c09ea31 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -38,6 +38,7 @@ struct nsinfo {
 struct nscookie {
 	int			oldns;
 	int			newns;
+	char			*oldcwd;
 };
 
 int nsinfo__init(struct nsinfo *nsi);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 14508ee7707a..ece040b799f6 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -59,6 +59,10 @@ int fetch_kernel_version(unsigned int *puint,
 
 const char *perf_tip(const char *dirpath);
 
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif
+
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
 #endif

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2018-11-17 10:55 Ingo Molnar
@ 2018-11-18 20:05 ` pr-tracker-bot
  0 siblings, 0 replies; 376+ messages in thread
From: pr-tracker-bot @ 2018-11-18 20:05 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

The pull request you sent on Sat, 17 Nov 2018 11:55:18 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b53e27f618b58d50db72375eb8e1b6ddcef7cdb5

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-11-17 10:55 Ingo Molnar
  2018-11-18 20:05 ` pr-tracker-bot
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2018-11-17 10:55 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4d47d6407ac7b4b442a4e717488a3bb137398b6c perf/x86/intel/uncore: Support CoffeeLake 8th CBOX

Fix uncore PMU enumeration for CofeeLake CPUs.

 Thanks,

	Ingo

------------------>
Kan Liang (2):
      perf/x86/intel/uncore: Add more IMC PCI IDs for KabyLake and CoffeeLake CPUs
      perf/x86/intel/uncore: Support CoffeeLake 8th CBOX


 arch/x86/events/intel/uncore.h     |  33 +++++++---
 arch/x86/events/intel/uncore_snb.c | 121 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 144 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index e17ab885b1e9..cb46d602a6b8 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -129,8 +129,15 @@ struct intel_uncore_box {
 	struct intel_uncore_extra_reg shared_regs[0];
 };
 
-#define UNCORE_BOX_FLAG_INITIATED	0
-#define UNCORE_BOX_FLAG_CTL_OFFS8	1 /* event config registers are 8-byte apart */
+/* CFL uncore 8th cbox MSRs */
+#define CFL_UNC_CBO_7_PERFEVTSEL0		0xf70
+#define CFL_UNC_CBO_7_PER_CTR0			0xf76
+
+#define UNCORE_BOX_FLAG_INITIATED		0
+/* event config registers are 8-byte apart */
+#define UNCORE_BOX_FLAG_CTL_OFFS8		1
+/* CFL 8th CBOX has different MSR space */
+#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS	2
 
 struct uncore_event_desc {
 	struct kobj_attribute attr;
@@ -297,17 +304,27 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
-	return box->pmu->type->event_ctl +
-		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		uncore_msr_box_offset(box);
+	if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+		return CFL_UNC_CBO_7_PERFEVTSEL0 +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+	} else {
+		return box->pmu->type->event_ctl +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+		       uncore_msr_box_offset(box);
+	}
 }
 
 static inline
 unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
-	return box->pmu->type->perf_ctr +
-		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		uncore_msr_box_offset(box);
+	if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+		return CFL_UNC_CBO_7_PER_CTR0 +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+	} else {
+		return box->pmu->type->perf_ctr +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+		       uncore_msr_box_offset(box);
+	}
 }
 
 static inline
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 8527c3e1038b..2593b0d7aeee 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,25 @@
 #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
 #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC	0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC	0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC	0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC	0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC	0x591f
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC	0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC	0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC	0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC	0x3ec4
+#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC	0x3e0f
+#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC	0x3e1f
+#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC	0x3ec2
+#define PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC	0x3e30
+#define PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC	0x3e18
+#define PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC	0x3ec6
+#define PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC	0x3e31
+#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC	0x3e33
+#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC	0x3eca
+#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC	0x3e32
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -202,6 +221,10 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
 			SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
 	}
+
+	/* The 8th CBOX has different MSR space */
+	if (box->pmu->pmu_idx == 7)
+		__set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags);
 }
 
 static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
@@ -228,7 +251,7 @@ static struct intel_uncore_ops skl_uncore_msr_ops = {
 static struct intel_uncore_type skl_uncore_cbox = {
 	.name		= "cbox",
 	.num_counters   = 4,
-	.num_boxes	= 5,
+	.num_boxes	= 8,
 	.perf_ctr_bits	= 44,
 	.fixed_ctr_bits	= 48,
 	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
@@ -569,7 +592,82 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
-
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -618,6 +716,25 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
 	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
 	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
+	IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core Y */
+	IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U */
+	IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U Quad Core */
+	IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core S Dual Core */
+	IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core S Quad Core */
+	IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core U 2 Cores */
+	IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core U 4 Cores */
+	IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core H 4 Cores */
+	IMC_DEV(CFL_6H_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core H 6 Cores */
+	IMC_DEV(CFL_2S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 2 Cores Desktop */
+	IMC_DEV(CFL_4S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Desktop */
+	IMC_DEV(CFL_6S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Desktop */
+	IMC_DEV(CFL_8S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Desktop */
+	IMC_DEV(CFL_4S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Work Station */
+	IMC_DEV(CFL_6S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Work Station */
+	IMC_DEV(CFL_8S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Work Station */
+	IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Server */
+	IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Server */
+	IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Server */
 	{  /* end marker */ }
 };
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2018-10-20  8:10 Ingo Molnar
@ 2018-10-20 13:28 ` Greg Kroah-Hartman
  0 siblings, 0 replies; 376+ messages in thread
From: Greg Kroah-Hartman @ 2018-10-20 13:28 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

On Sat, Oct 20, 2018 at 10:10:39AM +0200, Ingo Molnar wrote:
> Greg,
> 
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

Now merged, thanks.

greg k-h

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-10-20  8:10 Ingo Molnar
  2018-10-20 13:28 ` Greg Kroah-Hartman
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2018-10-20  8:10 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Greg,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 20e8e72d0fa8e26202932c30d592bade73fdc701 Merge tag 'perf-urgent-for-mingo-4.19-20181017' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc perf tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      tools arch uapi: Sync the x86 kvm.h copy
      tools headers uapi: Sync kvm.h copy
      perf tools: Stop fallbacking to kallsyms for vdso symbols lookup

David Miller (1):
      perf cpu_map: Align cpu map synthesized events properly.

Jarod Wilson (1):
      perf tools: Fix use of alternatives to find JDIR

Jiri Olsa (5):
      Revert "perf tools: Fix PMU term format max value calculation"
      perf vendor events intel: Fix wrong filter_band* values for uncore events
      perf evsel: Store ids for events with their own cpus perf_event__synthesize_event_update_cpus
      perf tools: Fix tracing_path_mount proper path
      perf tools: Pass build flags to traceevent build

Milian Wolff (1):
      perf report: Don't crash on invalid inline debug information


 tools/arch/x86/include/uapi/asm/kvm.h              |  1 +
 tools/include/uapi/linux/kvm.h                     |  1 +
 tools/lib/api/fs/tracing_path.c                    |  4 ++--
 tools/perf/Makefile.config                         |  2 +-
 tools/perf/Makefile.perf                           |  2 +-
 tools/perf/builtin-report.c                        |  1 +
 .../pmu-events/arch/x86/ivytown/uncore-power.json  | 16 ++++++++--------
 .../pmu-events/arch/x86/jaketown/uncore-power.json | 16 ++++++++--------
 tools/perf/util/event.c                            | 22 +++-------------------
 tools/perf/util/evsel.c                            |  3 +++
 tools/perf/util/pmu.c                              | 13 +++++++------
 tools/perf/util/srcline.c                          |  3 +++
 12 files changed, 39 insertions(+), 45 deletions(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..fd23d5778ea1 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -377,6 +377,7 @@ struct kvm_sync_regs {
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 07548de5c988..251be353f950 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_HPAGE_1M 156
 #define KVM_CAP_NESTED_STATE 157
 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 120037496f77..5afb11b30fca 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -36,7 +36,7 @@ static const char *tracing_path_tracefs_mount(void)
 
 	__tracing_path_set("", mnt);
 
-	return mnt;
+	return tracing_path;
 }
 
 static const char *tracing_path_debugfs_mount(void)
@@ -49,7 +49,7 @@ static const char *tracing_path_debugfs_mount(void)
 
 	__tracing_path_set("tracing/", mnt);
 
-	return mnt;
+	return tracing_path;
 }
 
 const char *tracing_path_mount(void)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f6d1a03c7523..e30d20fb482d 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -833,7 +833,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
     endif
   endif
   ifndef JDIR
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5224ade3d5af..0be411695379 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -635,7 +635,7 @@ $(LIBPERF_IN): prepare FORCE
 $(LIB_FILE): $(LIBPERF_IN)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS)
 
-LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)'
 
 $(LIBTRACEEVENT): FORCE
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76e12bcd1765..b2188e623e22 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -981,6 +981,7 @@ int cmd_report(int argc, const char **argv)
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_event__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
+			.event_update	 = perf_event__process_event_update,
 			.feature	 = process_feature_event,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
index d40498f2cb1e..635c09fda1d9 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -188,7 +188,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
-        "Filter": "filter_band0=1200",
+        "Filter": "filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -199,7 +199,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
-        "Filter": "filter_band1=2000",
+        "Filter": "filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -210,7 +210,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
-        "Filter": "filter_band2=3000",
+        "Filter": "filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -221,7 +221,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
-        "Filter": "filter_band3=4000",
+        "Filter": "filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
@@ -232,7 +232,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band0=1200",
+        "Filter": "edge=1,filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -243,7 +243,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band1=2000",
+        "Filter": "edge=1,filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -254,7 +254,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band2=4000",
+        "Filter": "edge=1,filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -265,7 +265,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band3=4000",
+        "Filter": "edge=1,filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
index 16034bfd06dd..8755693d86c6 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -187,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
-        "Filter": "filter_band0=1200",
+        "Filter": "filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -198,7 +198,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
-        "Filter": "filter_band1=2000",
+        "Filter": "filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -209,7 +209,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
-        "Filter": "filter_band2=3000",
+        "Filter": "filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -220,7 +220,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
-        "Filter": "filter_band3=4000",
+        "Filter": "filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
@@ -231,7 +231,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band0=1200",
+        "Filter": "edge=1,filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -242,7 +242,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band1=2000",
+        "Filter": "edge=1,filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -253,7 +253,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band2=4000",
+        "Filter": "edge=1,filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -264,7 +264,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band3=4000",
+        "Filter": "edge=1,filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0cd42150f712..bc646185f8d9 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1081,6 +1081,7 @@ void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max
 	}
 
 	*size += sizeof(struct cpu_map_data);
+	*size = PERF_ALIGN(*size, sizeof(u64));
 	return zalloc(*size);
 }
 
@@ -1560,26 +1561,9 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 
 		return NULL;
 	}
-try_again:
+
 	al->map = map_groups__find(mg, al->addr);
-	if (al->map == NULL) {
-		/*
-		 * If this is outside of all known maps, and is a negative
-		 * address, try to look it up in the kernel dso, as it might be
-		 * a vsyscall or vdso (which executes in user-mode).
-		 *
-		 * XXX This is nasty, we should have a symbol list in the
-		 * "[vdso]" dso, but for now lets use the old trick of looking
-		 * in the whole kernel symbol list.
-		 */
-		if (cpumode == PERF_RECORD_MISC_USER && machine &&
-		    mg != &machine->kmaps &&
-		    machine__kernel_ip(machine, al->addr)) {
-			mg = &machine->kmaps;
-			load_map = true;
-			goto try_again;
-		}
-	} else {
+	if (al->map != NULL) {
 		/*
 		 * Kernel maps might be changed when loading symbols so loading
 		 * must be done prior to using kernel maps.
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1a61628a1c12..e596ae358c4d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1089,6 +1089,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
+	if (evsel->own_cpus)
+		evsel->attr.read_format |= PERF_FORMAT_ID;
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index afd68524ffa9..7799788f662f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -930,13 +930,14 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
 
 static __u64 pmu_format_max_value(const unsigned long *format)
 {
-	__u64 w = 0;
-	int fbit;
-
-	for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS)
-		w |= (1ULL << fbit);
+	int w;
 
-	return w;
+	w = bitmap_weight(format, PERF_PMU_FORMAT_BITS);
+	if (!w)
+		return 0;
+	if (w < 64)
+		return (1ULL << w) - 1;
+	return -1;
 }
 
 /*
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 09d6746e6ec8..e767c4a9d4d2 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -85,6 +85,9 @@ static struct symbol *new_inline_sym(struct dso *dso,
 	struct symbol *inline_sym;
 	char *demangled = NULL;
 
+	if (!funcname)
+		funcname = "??";
+
 	if (dso) {
 		demangled = dso__demangle_sym(dso, 0, funcname);
 		if (demangled)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2018-10-11  9:12 Ingo Molnar
@ 2018-10-11 12:32 ` Greg Kroah-Hartman
  0 siblings, 0 replies; 376+ messages in thread
From: Greg Kroah-Hartman @ 2018-10-11 12:32 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Linus Torvalds, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

On Thu, Oct 11, 2018 at 11:12:02AM +0200, Ingo Molnar wrote:
> 
> Greg,
> 
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

Now merged, thanks.

greg k-h


^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-10-11  9:12 Ingo Molnar
  2018-10-11 12:32 ` Greg Kroah-Hartman
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2018-10-11  9:12 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: linux-kernel, Linus Torvalds, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton


Greg,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c1883f10cfe05c707cce46d6999411c50a2413ca Merge tag 'perf-urgent-for-mingo-4.19-20181005' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc perf tooling fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf script python: Fix export-to-postgresql.py occasional failure
      perf script python: Fix export-to-sqlite.py sample columns

Arnaldo Carvalho de Melo (1):
      perf python: Use -Wno-redundant-decls to build with PYTHON=python3

Milian Wolff (2):
      perf report: Don't try to map ip to invalid map
      perf record: Use unmapped IP for inline callchain cursors


 tools/perf/scripts/python/export-to-postgresql.py | 9 +++++++++
 tools/perf/scripts/python/export-to-sqlite.py     | 6 +++++-
 tools/perf/util/machine.c                         | 8 +++++---
 tools/perf/util/setup.py                          | 2 +-
 4 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index efcaf6cac2eb..e46f51b17513 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -204,14 +204,23 @@ from ctypes import *
 libpq = CDLL("libpq.so.5")
 PQconnectdb = libpq.PQconnectdb
 PQconnectdb.restype = c_void_p
+PQconnectdb.argtypes = [ c_char_p ]
 PQfinish = libpq.PQfinish
+PQfinish.argtypes = [ c_void_p ]
 PQstatus = libpq.PQstatus
+PQstatus.restype = c_int
+PQstatus.argtypes = [ c_void_p ]
 PQexec = libpq.PQexec
 PQexec.restype = c_void_p
+PQexec.argtypes = [ c_void_p, c_char_p ]
 PQresultStatus = libpq.PQresultStatus
+PQresultStatus.restype = c_int
+PQresultStatus.argtypes = [ c_void_p ]
 PQputCopyData = libpq.PQputCopyData
+PQputCopyData.restype = c_int
 PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
 PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.restype = c_int
 PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index f827bf77e9d2..e4bb82c8aba9 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -440,7 +440,11 @@ def branch_type_table(*x):
 
 def sample_table(*x):
 	if branches:
-		bind_exec(sample_query, 18, x)
+		for xx in x[0:15]:
+			sample_query.addBindValue(str(xx))
+		for xx in x[19:22]:
+			sample_query.addBindValue(str(xx))
+		do_query_(sample_query)
 	else:
 		bind_exec(sample_query, 22, x)
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c4acd2001db0..111ae858cbcb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2286,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor,
 	if (!symbol_conf.inline_name || !map || !sym)
 		return ret;
 
-	addr = map__rip_2objdump(map, ip);
+	addr = map__map_ip(map, ip);
+	addr = map__rip_2objdump(map, addr);
 
 	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
 	if (!inline_node) {
@@ -2312,7 +2313,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
-	u64 addr;
+	u64 addr = entry->ip;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2324,7 +2325,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	 * Convert entry->ip from a virtual address to an offset in
 	 * its corresponding binary.
 	 */
-	addr = map__map_ip(entry->map, entry->ip);
+	if (entry->map)
+		addr = map__map_ip(entry->map, entry->ip);
 
 	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 

----- End forwarded message -----

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-10-11  8:59 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-10-11  8:59 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner

Greg,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c1883f10cfe05c707cce46d6999411c50a2413ca Merge tag 'perf-urgent-for-mingo-4.19-20181005' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc perf tooling fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf script python: Fix export-to-postgresql.py occasional failure
      perf script python: Fix export-to-sqlite.py sample columns

Arnaldo Carvalho de Melo (1):
      perf python: Use -Wno-redundant-decls to build with PYTHON=python3

Milian Wolff (2):
      perf report: Don't try to map ip to invalid map
      perf record: Use unmapped IP for inline callchain cursors


 tools/perf/scripts/python/export-to-postgresql.py | 9 +++++++++
 tools/perf/scripts/python/export-to-sqlite.py     | 6 +++++-
 tools/perf/util/machine.c                         | 8 +++++---
 tools/perf/util/setup.py                          | 2 +-
 4 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index efcaf6cac2eb..e46f51b17513 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -204,14 +204,23 @@ from ctypes import *
 libpq = CDLL("libpq.so.5")
 PQconnectdb = libpq.PQconnectdb
 PQconnectdb.restype = c_void_p
+PQconnectdb.argtypes = [ c_char_p ]
 PQfinish = libpq.PQfinish
+PQfinish.argtypes = [ c_void_p ]
 PQstatus = libpq.PQstatus
+PQstatus.restype = c_int
+PQstatus.argtypes = [ c_void_p ]
 PQexec = libpq.PQexec
 PQexec.restype = c_void_p
+PQexec.argtypes = [ c_void_p, c_char_p ]
 PQresultStatus = libpq.PQresultStatus
+PQresultStatus.restype = c_int
+PQresultStatus.argtypes = [ c_void_p ]
 PQputCopyData = libpq.PQputCopyData
+PQputCopyData.restype = c_int
 PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
 PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.restype = c_int
 PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index f827bf77e9d2..e4bb82c8aba9 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -440,7 +440,11 @@ def branch_type_table(*x):
 
 def sample_table(*x):
 	if branches:
-		bind_exec(sample_query, 18, x)
+		for xx in x[0:15]:
+			sample_query.addBindValue(str(xx))
+		for xx in x[19:22]:
+			sample_query.addBindValue(str(xx))
+		do_query_(sample_query)
 	else:
 		bind_exec(sample_query, 22, x)
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c4acd2001db0..111ae858cbcb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2286,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor,
 	if (!symbol_conf.inline_name || !map || !sym)
 		return ret;
 
-	addr = map__rip_2objdump(map, ip);
+	addr = map__map_ip(map, ip);
+	addr = map__rip_2objdump(map, addr);
 
 	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
 	if (!inline_node) {
@@ -2312,7 +2313,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
-	u64 addr;
+	u64 addr = entry->ip;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2324,7 +2325,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	 * Convert entry->ip from a virtual address to an offset in
 	 * its corresponding binary.
 	 */
-	addr = map__map_ip(entry->map, entry->ip);
+	if (entry->map)
+		addr = map__map_ip(entry->map, entry->ip);
 
 	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2018-10-05  9:55 ` Ingo Molnar
@ 2018-10-05 23:30   ` Greg Kroah-Hartman
  0 siblings, 0 replies; 376+ messages in thread
From: Greg Kroah-Hartman @ 2018-10-05 23:30 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Linus Torvalds, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

On Fri, Oct 05, 2018 at 11:55:24AM +0200, Ingo Molnar wrote:
> 
> * Ingo Molnar <mingo@kernel.org> wrote:
> 
> > Linus,
> 
> ... and Greg as well!! ;-)

Heh, not a big deal :)

Now merged, thanks.

greg k-h

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2018-10-05  9:42 Ingo Molnar
@ 2018-10-05  9:55 ` Ingo Molnar
  2018-10-05 23:30   ` Greg Kroah-Hartman
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2018-10-05  9:55 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: linux-kernel, Linus Torvalds, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton


* Ingo Molnar <mingo@kernel.org> wrote:

> Linus,

... and Greg as well!! ;-)

Thanks,

	Ingo

ps. script fixed.

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-10-05  9:42 Ingo Molnar
  2018-10-05  9:55 ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2018-10-05  9:42 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: linux-kernel, Linus Torvalds, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d7cbbe49a9304520181fb8c9272d1327deec8453 perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events

Misc fixes:

 - fix a CPU#0 hot unplug bug and a PCI enumeration bug in the x86 Intel uncore PMU driver
 - fix a CPU event enumeration bug in the x86 AMD PMU driver
 - fix a perf ring-buffer corruption bug when using tracepoints
 - fix a PMU unregister locking bug

 Thanks,

	Ingo

------------------>
Jiri Olsa (1):
      perf/ring_buffer: Prevent concurent ring buffer access

Kan Liang (1):
      perf/x86/intel/uncore: Fix PCI BDF address of M3UPI on SKX

Masayoshi Mizuma (1):
      perf/x86/intel/uncore: Use boot_cpu_data.phys_proc_id instead of hardcorded physical package ID 0

Natarajan, Janakarajan (1):
      perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events

Peter Zijlstra (1):
      perf/core: Fix perf_pmu_unregister() locking


 arch/x86/events/amd/uncore.c         | 10 ++++++++++
 arch/x86/events/intel/uncore_snbep.c | 14 +++++++-------
 arch/x86/include/asm/perf_event.h    |  8 ++++++++
 kernel/events/core.c                 | 11 ++++-------
 4 files changed, 29 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e8241b..8671de126eac 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
 
 static int num_counters_llc;
 static int num_counters_nb;
+static bool l3_mask;
 
 static HLIST_HEAD(uncore_unused_list);
 
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events in
+	 * Family 17h. For other events, the two fields do not affect the count.
+	 */
+	if (l3_mask)
+		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l3";
 		format_attr_event_df.show = &event_show_df;
 		format_attr_event_l3.show = &event_show_l3;
+		l3_mask			  = true;
 	} else {
 		num_counters_nb		  = NUM_COUNTERS_NB;
 		num_counters_llc	  = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l2";
 		format_attr_event_df	  = format_attr_event;
 		format_attr_event_l3	  = format_attr_event;
+		l3_mask			  = false;
 	}
 
 	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 51d7c117e3c7..c07bee31abe8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
 
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
 	},
 	{ /* M3UPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
 	},
 	{ /* M3UPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
 	},
 	{ /* M3UPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
 	},
 	{ /* end: all zeroes */ }
 };
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f54082f4c8..78241b736f2a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
 #define INTEL_ARCH_EVENT_MASK	\
 	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
+#define AMD64_L3_SLICE_SHIFT				48
+#define AMD64_L3_SLICE_MASK				\
+	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT				56
+#define AMD64_L3_THREAD_MASK				\
+	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
 	 ARCH_PERFMON_EVENTSEL_UMASK |	\
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dcb093e7b377..5a97f34bc14c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8314,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->cpu != smp_processor_id())
+				continue;
 			if (event->attr.type != PERF_TYPE_TRACEPOINT)
 				continue;
 			if (event->attr.config != entry->type)
@@ -9431,9 +9433,7 @@ static void free_pmu_context(struct pmu *pmu)
 	if (pmu->task_ctx_nr > perf_invalid_context)
 		return;
 
-	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
-	mutex_unlock(&pmus_lock);
 }
 
 /*
@@ -9689,12 +9689,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
-	int remove_device;
-
 	mutex_lock(&pmus_lock);
-	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
-	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -9706,13 +9702,14 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (remove_device) {
+	if (pmu_bus_running) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
 		device_del(pmu->dev);
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
+	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-09-15 13:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-09-15 13:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Jiri Olsa

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: cb48b6a26cace226d8b299a48c73e808eb0c4f61 Merge tag 'perf-urgent-for-mingo-4.19-20180912' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, but also breakpoint and x86 PMU driver fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf tools: Fix maps__find_symbol_by_name()

Arnaldo Carvalho de Melo (7):
      perf tools: Streamline bpf examples and headers installation
      tools headers uapi: Update tools's copy of linux/perf_event.h
      tools headers uapi: Update tools's copy of asm-generic/unistd.h
      tools headers uapi: Update tools's copy of drm/drm.h
      tools headers uapi: Update tools's copies of kvm headers
      tools headers uapi: Update tools's copy of linux/vhost.h
      tools headers uapi: Update tools's copy of linux/if_link.h

Chris Phlipot (2):
      perf util: Fix bad memory access in trace info.
      perf event-parse: Use fixed size string for comms

Hisao Tanabe (1):
      perf evsel: Fix potential null pointer dereference in perf_evsel__new_idx()

Jacek Tomaka (1):
      perf/x86/intel: Add support/quirk for the MISPREDICT bit on Knights Landing CPUs

Jiri Olsa (5):
      perf tests: Add breakpoint modify tests
      perf/hw_breakpoint: Modify breakpoint even if the new attr has disabled set
      perf/hw_breakpoint: Remove superfluous bp->attr.disabled = 0
      perf/hw_breakpoint: Enable breakpoint in modify_user_hw_breakpoint
      perf/hw_breakpoint: Simplify breakpoint enable in perf_event_modify_breakpoint

Kim Phillips (2):
      perf arm64: Fix include path for asm-generic/unistd.h
      perf annotate: Fix parsing aarch64 branch instructions after objdump update

Martin Liška (1):
      perf annotate: Properly interpret indirect call

Peter Zijlstra (1):
      perf/UAPI: Clearly mark __PERF_SAMPLE_CALLCHAIN_EARLY as internal use

Sandipan Das (1):
      perf probe powerpc: Ignore SyS symbols irrespective of endianness

Yabin Cui (1):
      perf/core: Force USER_DS when recording user stack data


 arch/x86/events/intel/lbr.c                       |   4 +
 include/uapi/linux/perf_event.h                   |   2 +-
 kernel/events/core.c                              |  15 +-
 kernel/events/hw_breakpoint.c                     |  13 +-
 tools/arch/arm/include/uapi/asm/kvm.h             |  13 ++
 tools/arch/arm64/include/uapi/asm/kvm.h           |  13 ++
 tools/arch/s390/include/uapi/asm/kvm.h            |   5 +-
 tools/arch/x86/include/uapi/asm/kvm.h             |  37 ++++
 tools/include/uapi/asm-generic/unistd.h           |   4 +-
 tools/include/uapi/drm/drm.h                      |   9 +
 tools/include/uapi/linux/if_link.h                |  17 ++
 tools/include/uapi/linux/kvm.h                    |   6 +
 tools/include/uapi/linux/perf_event.h             |   2 +-
 tools/include/uapi/linux/vhost.h                  |  18 ++
 tools/perf/Makefile.perf                          |  14 +-
 tools/perf/arch/arm64/Makefile                    |   5 +-
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl |   6 +-
 tools/perf/arch/powerpc/util/sym-handling.c       |   4 +-
 tools/perf/arch/x86/include/arch-tests.h          |   1 +
 tools/perf/arch/x86/tests/Build                   |   1 +
 tools/perf/arch/x86/tests/arch-tests.c            |   6 +
 tools/perf/arch/x86/tests/bp-modify.c             | 213 ++++++++++++++++++++++
 tools/perf/util/annotate.c                        |  32 +++-
 tools/perf/util/annotate.h                        |   1 +
 tools/perf/util/evsel.c                           |   5 +-
 tools/perf/util/map.c                             |  11 ++
 tools/perf/util/trace-event-info.c                |   2 +-
 tools/perf/util/trace-event-parse.c               |   7 +-
 28 files changed, 423 insertions(+), 43 deletions(-)
 create mode 100644 tools/perf/arch/x86/tests/bp-modify.c

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f3e006bed9a7..c88ed39582a1 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void)
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	/* Knights Landing does have MISPREDICT bit */
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
+		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index eeb787b1c53c..f35eb72739c0 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -144,7 +144,7 @@ enum perf_event_sample_format {
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 
-	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2a62b96600ad..c80549bf82c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp,
 	_perf_event_disable(bp);
 
 	err = modify_user_hw_breakpoint_check(bp, attr, true);
-	if (err) {
-		if (!bp->attr.disabled)
-			_perf_event_enable(bp);
 
-		return err;
-	}
-
-	if (!attr->disabled)
+	if (!bp->attr.disabled)
 		_perf_event_enable(bp);
-	return 0;
+
+	return err;
 }
 
 static int perf_event_modify_attr(struct perf_event *event,
@@ -5948,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 		unsigned long sp;
 		unsigned int rem;
 		u64 dyn_size;
+		mm_segment_t fs;
 
 		/*
 		 * We dump:
@@ -5965,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
+		fs = get_fs();
+		set_fs(USER_DS);
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
+		set_fs(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b3814fce5ecb..d6b56180827c 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
+	int err;
+
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	else
 		perf_event_disable(bp);
 
-	if (!attr->disabled) {
-		int err = modify_user_hw_breakpoint_check(bp, attr, false);
+	err = modify_user_hw_breakpoint_check(bp, attr, false);
 
-		if (err)
-			return err;
+	if (!bp->attr.disabled)
 		perf_event_enable(bp);
-		bp->attr.disabled = 0;
-	}
-	return 0;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
 
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 16e006f708ca..4602464ebdfb 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -27,6 +27,7 @@
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
@@ -125,6 +126,18 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 serror_pending;
+		__u8 serror_has_esr;
+		/* Align it to 8 bytes */
+		__u8 pad[6];
+		__u64 serror_esr;
+	} exception;
+	__u32 reserved[12];
+};
+
 /* If you need to interpret the index values, here is the key: */
 #define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
 #define KVM_REG_ARM_COPROC_SHIFT	16
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 4e76630dd655..97c3478ee6e7 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -39,6 +39,7 @@
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
@@ -154,6 +155,18 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 serror_pending;
+		__u8 serror_has_esr;
+		/* Align it to 8 bytes */
+		__u8 pad[6];
+		__u64 serror_esr;
+	} exception;
+	__u32 reserved[12];
+};
+
 /* If you need to interpret the index values, here is the key: */
 #define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
 #define KVM_REG_ARM_COPROC_SHIFT	16
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 4cdaa55fabfe..9a50f02b9894 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -4,7 +4,7 @@
 /*
  * KVM s390 specific structures and definitions
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008, 2018
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -225,6 +225,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
+#define KVM_SYNC_ETOKEN (1UL << 11)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -258,6 +259,8 @@ struct kvm_sync_regs {
 		struct {
 			__u64 reserved1[2];
 			__u64 gscb[4];
+			__u64 etoken;
+			__u64 etoken_extension;
 		};
 	};
 };
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index c535c2fdea13..86299efa804a 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -378,4 +378,41 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 
+#define KVM_STATE_NESTED_GUEST_MODE	0x00000001
+#define KVM_STATE_NESTED_RUN_PENDING	0x00000002
+
+#define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
+#define KVM_STATE_NESTED_SMM_VMXON	0x00000002
+
+struct kvm_vmx_nested_state {
+	__u64 vmxon_pa;
+	__u64 vmcs_pa;
+
+	struct {
+		__u16 flags;
+	} smm;
+};
+
+/* for KVM_CAP_NESTED_STATE */
+struct kvm_nested_state {
+	/* KVM_STATE_* flags */
+	__u16 flags;
+
+	/* 0 for VMX, 1 for SVM.  */
+	__u16 format;
+
+	/* 128 for SVM, 128 + VMCS size for VMX.  */
+	__u32 size;
+
+	union {
+		/* VMXON, VMCS */
+		struct kvm_vmx_nested_state vmx;
+
+		/* Pad the header to 128 bytes.  */
+		__u8 pad[120];
+	};
+
+	__u8 data[0];
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 42990676a55e..df4bedb9b01c 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 __SYSCALL(__NR_statx,     sys_statx)
 #define __NR_io_pgetevents 292
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+#define __NR_rseq 293
+__SYSCALL(__NR_rseq, sys_rseq)
 
 #undef __NR_syscalls
-#define __NR_syscalls 293
+#define __NR_syscalls 294
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 9c660e1688ab..300f336633f2 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -687,6 +687,15 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ASPECT_RATIO    4
 
+/**
+ * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
+ *
+ * If set to 1, the DRM core will expose special connectors to be used for
+ * writing back to memory the scene setup in the commit. Depends on client
+ * also supporting DRM_CLIENT_CAP_ATOMIC
+ */
+#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index cf01b6824244..43391e2d1153 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -164,6 +164,8 @@ enum {
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
+	IFLA_MIN_MTU,
+	IFLA_MAX_MTU,
 	__IFLA_MAX
 };
 
@@ -334,6 +336,7 @@ enum {
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
+	IFLA_BRPORT_BACKUP_PORT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -459,6 +462,16 @@ enum {
 
 #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
 
+/* XFRM section */
+enum {
+	IFLA_XFRM_UNSPEC,
+	IFLA_XFRM_LINK,
+	IFLA_XFRM_IF_ID,
+	__IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
 enum macsec_validation_type {
 	MACSEC_VALIDATE_DISABLED = 0,
 	MACSEC_VALIDATE_CHECK = 1,
@@ -920,6 +933,7 @@ enum {
 	XDP_ATTACHED_DRV,
 	XDP_ATTACHED_SKB,
 	XDP_ATTACHED_HW,
+	XDP_ATTACHED_MULTI,
 };
 
 enum {
@@ -928,6 +942,9 @@ enum {
 	IFLA_XDP_ATTACHED,
 	IFLA_XDP_FLAGS,
 	IFLA_XDP_PROG_ID,
+	IFLA_XDP_DRV_PROG_ID,
+	IFLA_XDP_SKB_PROG_ID,
+	IFLA_XDP_HW_PROG_ID,
 	__IFLA_XDP_MAX,
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index b6270a3b38e9..07548de5c988 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -949,6 +949,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
 #define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
+#define KVM_CAP_NESTED_STATE 157
+#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1391,6 +1394,9 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_HYPERV_EVENTFD */
 #define KVM_HYPERV_EVENTFD        _IOW(KVMIO,  0xbd, struct kvm_hyperv_eventfd)
 
+/* Available with KVM_CAP_NESTED_STATE */
+#define KVM_GET_NESTED_STATE         _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
+#define KVM_SET_NESTED_STATE         _IOW(KVMIO,  0xbf, struct kvm_nested_state)
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index eeb787b1c53c..f35eb72739c0 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -144,7 +144,7 @@ enum perf_event_sample_format {
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 
-	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
 
 /*
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index c51f8e5cc608..84c3de89696a 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -65,6 +65,7 @@ struct vhost_iotlb_msg {
 };
 
 #define VHOST_IOTLB_MSG 0x1
+#define VHOST_IOTLB_MSG_V2 0x2
 
 struct vhost_msg {
 	int type;
@@ -74,6 +75,15 @@ struct vhost_msg {
 	};
 };
 
+struct vhost_msg_v2 {
+	__u32 type;
+	__u32 reserved;
+	union {
+		struct vhost_iotlb_msg iotlb;
+		__u8 padding[64];
+	};
+};
+
 struct vhost_memory_region {
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
@@ -160,6 +170,14 @@ struct vhost_memory {
 #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,	\
 					 struct vhost_vring_state)
 
+/* Set or get vhost backend capability */
+
+/* Use message type V2 */
+#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+
+#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
+#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
+
 /* VHOST_NET specific defines */
 
 /* Attach virtio net ring to a raw socket, or tap device.
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index b3d1b12a5081..5224ade3d5af 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -777,14 +777,12 @@ endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBBPF
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, include/bpf) \
-		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, examples/bpf) \
-		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-headers) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-examples) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
+		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
 endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index f013b115dc86..dbef716a1913 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/arm64/include/generated/asm
 header := $(out)/syscalls.c
-sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
 sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
 systbl := $(sysprf)/mksyscalltbl
 
@@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, arm64) $(RM) $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 52e197317d3e..2dbb8cade048 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -11,7 +11,8 @@
 
 gcc=$1
 hostcc=$2
-input=$3
+incpath=$3
+input=$4
 
 if ! test -r $input; then
 	echo "Could not read input file" >&2
@@ -28,7 +29,6 @@ create_table_from_c()
 
 	cat <<-_EoHEADER
 		#include <stdio.h>
-		#define __ARCH_WANT_RENAMEAT
 		#include "$input"
 		int main(int argc, char *argv[])
 		{
@@ -42,7 +42,7 @@ create_table_from_c()
 	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
 	printf "}\n"
 
-	} | $hostcc -o $create_table_exe -x c -
+	} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
 
 	$create_table_exe
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 20e7d74d86cd..10a44e946f77 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 
 #endif
 
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
 int arch__choose_best_symbol(struct symbol *syma,
 			     struct symbol *symb __maybe_unused)
 {
 	char *sym = syma->name;
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 	/* Skip over any initial dot */
 	if (*sym == '.')
 		sym++;
+#endif
 
 	/* Avoid "SyS" kernel syscall aliases */
 	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
@@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma,
 	return SYMBOL_A;
 }
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 /* Allow matching against dot variants */
 int arch__compare_symbol_names(const char *namea, const char *nameb)
 {
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index c1bd979b957b..613709cfbbd0 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -9,6 +9,7 @@ struct test;
 int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__bp_modify(struct test *test, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 8e2c5a38c3b9..586849ff83a0 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -5,3 +5,4 @@ libperf-y += arch-tests.o
 libperf-y += rdpmc.o
 libperf-y += perf-time-to-tsc.o
 libperf-$(CONFIG_AUXTRACE) += insn-x86.o
+libperf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index cc1802ff5410..d47d3f8e3c8e 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -23,6 +23,12 @@ struct test arch_tests[] = {
 		.desc = "x86 instruction decoder - new instructions",
 		.func = test__insn_x86,
 	},
+#endif
+#if defined(__x86_64__)
+	{
+		.desc = "x86 bp modify",
+		.func = test__bp_modify,
+	},
 #endif
 	{
 		.func = NULL,
diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c
new file mode 100644
index 000000000000..f53e4406709f
--- /dev/null
+++ b/tools/perf/arch/x86/tests/bp-modify.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <asm/ptrace.h>
+#include <errno.h>
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+static noinline int bp_1(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static noinline int bp_2(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static int spawn_child(void)
+{
+	int child = fork();
+
+	if (child == 0) {
+		/*
+		 * The child sets itself for as tracee and
+		 * waits in signal for parent to trace it,
+		 * then it calls bp_1 and quits.
+		 */
+		int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL);
+
+		if (err) {
+			pr_debug("failed to PTRACE_TRACEME\n");
+			exit(1);
+		}
+
+		raise(SIGCONT);
+		bp_1();
+		exit(0);
+	}
+
+	return child;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it and checks it was properly changed.
+ */
+static int bp_modify1(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_2 function
+	 *  - changes that breakponit to bp_1 function
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_2)) {
+		pr_debug("failed to set breakpoint, 1st time: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint, 2nd time: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it to bogus value and checks the original
+ * breakpoint is hit.
+ */
+static int bp_modify2(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_1 function
+	 *  - tries to change that breakpoint to (-1) address
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (!ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) {
+		pr_debug("failed, breakpoint set to bogus address\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+int test__bp_modify(struct test *test __maybe_unused,
+		    int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1());
+	TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2());
+
+	return 0;
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 20061cf42288..28cd6a17491b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -246,8 +246,14 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 
 indirect_call:
 	tok = strchr(endptr, '*');
-	if (tok != NULL)
-		ops->target.addr = strtoull(tok + 1, NULL, 16);
+	if (tok != NULL) {
+		endptr++;
+
+		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
+		 * Do not parse such instruction.  */
+		if (strstr(endptr, "(%r") == NULL)
+			ops->target.addr = strtoull(endptr, NULL, 16);
+	}
 	goto find_target;
 }
 
@@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins)
 	return ins->ops == &call_ops || ins->ops == &s390_call_ops;
 }
 
-static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms)
+/*
+ * Prevents from matching commas in the comment section, e.g.:
+ * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
+ */
+static inline const char *validate_comma(const char *c, struct ins_operands *ops)
+{
+	if (ops->raw_comment && c > ops->raw_comment)
+		return NULL;
+
+	return c;
+}
+
+static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
@@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	};
 	const char *c = strchr(ops->raw, ',');
 	u64 start, end;
+
+	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	c = validate_comma(c, ops);
+
 	/*
 	 * Examples of lines to parse for the _cpp_lex_token@@Base
 	 * function:
@@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 		ops->target.addr = strtoull(c, NULL, 16);
 		if (!ops->target.addr) {
 			c = strchr(c, ',');
+			c = validate_comma(c, ops);
 			if (c++ != NULL)
 				ops->target.addr = strtoull(c, NULL, 16);
 		}
@@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
 
 	c = strchr(ops->raw, ',');
+	c = validate_comma(c, ops);
+
 	if (c != NULL) {
 		const char *c2 = strchr(c + 1, ',');
 
+		c2 = validate_comma(c2, ops);
 		/* check for 3-op insn */
 		if (c2 != NULL)
 			c = c2;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 005a5fe8a8c6..5399ba2321bb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -22,6 +22,7 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
+	char	*raw_comment;
 	struct {
 		char	*raw;
 		char	*name;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c980bbff6353..1a61628a1c12 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
 	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
-	if (evsel != NULL)
-		perf_evsel__init(evsel, attr, idx);
+	if (!evsel)
+		return NULL;
+	perf_evsel__init(evsel, attr, idx);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
 		evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 36d0763311ef..6a6929f208b4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -576,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 	return NULL;
 }
 
+static bool map__contains_symbol(struct map *map, struct symbol *sym)
+{
+	u64 ip = map->unmap_ip(map, sym->start);
+
+	return ip >= map->start && ip < map->end;
+}
+
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 					 struct map **mapp)
 {
@@ -591,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
 		if (sym == NULL)
 			continue;
+		if (!map__contains_symbol(pos, sym)) {
+			sym = NULL;
+			continue;
+		}
 		if (mapp != NULL)
 			*mapp = pos;
 		goto out;
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c85d0d1a65ed..7b0ca7cbb7de 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -377,7 +377,7 @@ static int record_ftrace_printk(void)
 
 static int record_saved_cmdline(void)
 {
-	unsigned int size;
+	unsigned long long size;
 	char *path;
 	struct stat st;
 	int ret, err = 0;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 920b1d58a068..e76214f8d596 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent,
 void parse_saved_cmdline(struct tep_handle *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
-	char *comm;
+	char comm[17]; /* Max comm length in the kernel is 16. */
 	char *line;
 	char *next = NULL;
 	int pid;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
-		sscanf(line, "%d %ms", &pid, &comm);
-		tep_register_comm(pevent, comm, pid);
-		free(comm);
+		if (sscanf(line, "%d %16s", &pid, comm) == 2)
+			tep_register_comm(pevent, comm, pid);
 		line = strtok_r(NULL, "\n", &next);
 	}
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-07-30 17:53 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-07-30 17:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7f635ff187ab6be0b350b3ec06791e376af238ab perf/core: Fix crash when using HW tracing kernel filters

Misc fixes:

 - AMD IBS data corruptor fix (uncovered by UBSAN)
 - an Intel PEBS entry unwind error fix
 - a HW-tracing crash fix
 - a MAINTAINERS update

 Thanks,

	Ingo

------------------>
Ananth N Mavinakayanahalli (1):
      MAINTAINERS: Add Naveen N. Rao as kprobes co-maintainer

Mathieu Poirier (1):
      perf/core: Fix crash when using HW tracing kernel filters

Peter Zijlstra (1):
      perf/x86/intel: Fix unwind errors from PEBS entries (mk-II)

Thomas Gleixner (1):
      perf/x86/amd/ibs: Don't access non-started event


 MAINTAINERS                     |  2 +-
 arch/x86/events/amd/ibs.c       |  6 +++++-
 arch/x86/events/intel/core.c    |  3 +++
 arch/x86/events/intel/ds.c      | 25 +++++++++++--------------
 include/linux/perf_event.h      |  1 +
 include/uapi/linux/perf_event.h |  2 ++
 kernel/events/core.c            | 10 ++++++++--
 7 files changed, 31 insertions(+), 18 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0fe4228f78cb..42a884c1b0f7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7984,7 +7984,7 @@ F:	lib/test_kmod.c
 F:	tools/testing/selftests/kmod/
 
 KPROBES
-M:	Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
+M:	Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 4b98101209a1..d50bb4dc0650 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 {
 	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
 	struct perf_event *event = pcpu->event;
-	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event *hwc;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
@@ -602,6 +602,10 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 		return 0;
 	}
 
+	if (WARN_ON_ONCE(!event))
+		goto fail;
+
+	hwc = &event->hw;
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
 	rdmsrl(msr, *buf);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 707b2a96e516..86f0c15dcc2d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
+
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
 	}
 
 	if (needs_branch_stack(event)) {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8cf03f101938..8dbba77e0518 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1185,17 +1185,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		data->data_src.val = val;
 	}
 
+	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happend between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
 	 * contain a full regs set, specifically it seems to lack segment
 	 * descriptors, which get used by things like user_mode().
 	 *
 	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
-	 *
-	 * We must however always use BP,SP from iregs for the unwinder to stay
-	 * sane; the record BP,SP can point into thin air when the record is
-	 * from a previous PMI context or an (I)RET happend between the record
-	 * and PMI.
 	 */
 	*regs = *iregs;
 
@@ -1214,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->si = pebs->si;
 		regs->di = pebs->di;
 
-		/*
-		 * Per the above; only set BP,SP if we don't need callchains.
-		 *
-		 * XXX: does this make sense?
-		 */
-		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
-			regs->bp = pebs->bp;
-			regs->sp = pebs->sp;
-		}
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
 
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1fa12887ec02..87f6db437e4a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
+extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b8e288a1f740..eeb787b1c53c 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -143,6 +143,8 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8f0434a9951a..eec2d5fb676b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt)
 
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
 	bool kernel = !event->attr.exclude_callchain_kernel;
@@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
-		data->callchain = perf_callchain(event, regs);
+		if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+			data->callchain = perf_callchain(event, regs);
+
 		size += data->callchain->nr;
 
 		header->size += size * sizeof(u64);
@@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
+	/* d_inode(NULL) won't be equal to any mapped user-space file */
+	if (!filter->path.dentry)
+		return false;
+
 	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-07-13 19:59 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-07-13 19:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 6e1d33b24a2b4aebcb05782e937ebc9a7a4a3f50 Merge tag 'perf-urgent-for-mingo-4.18-20180711' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc tooling fixes: ptyhon3 related fixes, gcc8 fix, bashism fixes and some other 
smaller fixes.

 Thanks,

	Ingo

------------------>
Janne Huttunen (1):
      perf script python: Fix dict reference counting

Jeremy Cline (7):
      perf tools: Generate a Python script compatible with Python 2 and 3
      perf scripts python: Add Python 3 support to Core.py
      perf scripts python: Add Python 3 support to SchedGui.py
      perf scripts python: Add Python 3 support to Util.py
      perf scripts python: Add Python 3 support to sched-migration.py
      perf scripts python: Add Python 3 support to EventClass.py
      perf tools: Use python-config --includes rather than --cflags

Jiri Olsa (2):
      perf tools: Fix compilation errors on gcc8
      perf stat: Fix --interval_clear option

Kim Phillips (4):
      perf test shell: Replace '|&' with '2>&1 |' to work with more shells
      perf test shell: Make perf's inet_pton test more portable
      perf llvm-utils: Remove bashism from kernel include fetch script
      perf test shell: Prevent temporary editor files from being considered test scripts


 tools/perf/Makefile.config                         |  3 +-
 tools/perf/arch/x86/util/perf_regs.c               |  2 +-
 tools/perf/builtin-stat.c                          |  2 +-
 tools/perf/jvmti/jvmti_agent.c                     |  3 +-
 .../python/Perf-Trace-Util/lib/Perf/Trace/Core.py  | 40 +++++++++-------------
 .../Perf-Trace-Util/lib/Perf/Trace/EventClass.py   |  4 ++-
 .../Perf-Trace-Util/lib/Perf/Trace/SchedGui.py     |  2 +-
 .../python/Perf-Trace-Util/lib/Perf/Trace/Util.py  | 11 +++---
 tools/perf/scripts/python/sched-migration.py       | 14 +++++---
 tools/perf/tests/builtin-test.c                    |  2 +-
 .../tests/shell/record+probe_libc_inet_pton.sh     | 37 +++++++++++---------
 tools/perf/tests/shell/trace+probe_vfs_getname.sh  |  2 +-
 tools/perf/util/llvm-utils.c                       |  6 ++--
 .../util/scripting-engines/trace-event-python.c    | 37 +++++++++-----------
 14 files changed, 84 insertions(+), 81 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b5ac356ba323..f5a3b402589e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -207,8 +207,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 4b2caf6d48e7..fead6b3b4206 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 		else if (rm[2].rm_so != rm[2].rm_eo)
 			prefix[0] = '+';
 		else
-			strncpy(prefix, "+0", 2);
+			scnprintf(prefix, sizeof(prefix), "+0");
 	}
 
 	/* Rename register */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 22547a490e1f..05be023c3f0e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1742,7 +1742,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 		}
 	}
 
-	if ((num_print_interval == 0 && metric_only) || interval_clear)
+	if ((num_print_interval == 0 || interval_clear) && metric_only)
 		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 0c6d1002b524..ac1bcdc17dae 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -35,6 +35,7 @@
 #include <sys/mman.h>
 #include <syscall.h> /* for gettid() */
 #include <err.h>
+#include <linux/kernel.h>
 
 #include "jvmti_agent.h"
 #include "../util/jitdump.h"
@@ -249,7 +250,7 @@ void *jvmti_open(void)
 	/*
 	 * jitdump file name
 	 */
-	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 38dfb720fb6f..54ace2f6bc36 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -31,10 +31,8 @@ symbolic_fields = autodict()
     string = ""
 
     if flag_fields[event_name][field_name]:
-	print_delim = 0
-        keys = flag_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
             if not value and not idx:
                 string += flag_fields[event_name][field_name]['values'][idx]
                 break
@@ -51,14 +49,12 @@ symbolic_fields = autodict()
     string = ""
 
     if symbolic_fields[event_name][field_name]:
-        keys = symbolic_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
             if not value and not idx:
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
-	    if (value == idx):
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
 
     return string
@@ -74,19 +70,17 @@ trace_flags = { 0x00: "NONE", \
     string = ""
     print_delim = 0
 
-    keys = trace_flags.keys()
-
-    for idx in keys:
-	if not value and not idx:
-	    string += "NONE"
-	    break
-
-	if idx and (value & idx) == idx:
-	    if print_delim:
-		string += " | ";
-	    string += trace_flags[idx]
-	    print_delim = 1
-	    value &= ~idx
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
 
     return string
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 81a56cd2b3c1..21a7a1298094 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -8,6 +8,7 @@
 # PerfEvent is the base class for all perf event sample, PebsEvent
 # is a HW base Intel x86 PEBS event, and user could add more SW/HW
 # event classes based on requirements.
+from __future__ import print_function
 
 import struct
 
@@ -44,7 +45,8 @@ EVTYPE_IBS      = 3
                 PerfEvent.event_num += 1
 
         def show(self):
-                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
 
 #
 # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index fdd92f699055..cac7b2542ee8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -11,7 +11,7 @@
 try:
 	import wx
 except ImportError:
-	raise ImportError, "You need to install the wxpython lib for this script"
+	raise ImportError("You need to install the wxpython lib for this script")
 
 
 class RootFrame(wx.Frame):
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index f6c84966e4f8..7384dcb628c4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -5,6 +5,7 @@
 # This software may be distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
+from __future__ import print_function
 
 import errno, os
 
@@ -33,7 +34,7 @@ NSECS_PER_SEC    = 1000000000
     return str
 
 def add_stats(dict, key, value):
-	if not dict.has_key(key):
+	if key not in dict:
 		dict[key] = (value, value, value, 1)
 	else:
 		min, max, avg, count = dict[key]
@@ -72,10 +73,10 @@ audit_package_warned = False
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names.\n" \
-                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
-                    "\n  # yum install audit-libs-python (Fedora)" \
-                    "\n  etc.\n"
+		print("Install the audit-libs-python package to get syscall names.\n"
+                    "For example:\n  # apt-get install python-audit (Ubuntu)"
+                    "\n  # yum install audit-libs-python (Fedora)"
+                    "\n  etc.\n")
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index de66cb3b72c9..3473e7f66081 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -9,13 +9,17 @@
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
-
+from __future__ import print_function
 
 import os
 import sys
 
 from collections import defaultdict
-from UserList import UserList
+try:
+    from UserList import UserList
+except ImportError:
+    # Python 3: UserList moved to the collections package
+    from collections import UserList
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -300,7 +304,7 @@ threads = { 0 : "idle"}
 		if i == -1:
 			return
 
-		for i in xrange(i, len(self.data)):
+		for i in range(i, len(self.data)):
 			timeslice = self.data[i]
 			if timeslice.start > end:
 				return
@@ -336,8 +340,8 @@ threads = { 0 : "idle"}
 		on_cpu_task = self.current_tsk[headers.cpu]
 
 		if on_cpu_task != -1 and on_cpu_task != prev_pid:
-			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
-				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
 
 		threads[prev_pid] = prev_comm
 		threads[next_pid] = next_comm
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2bde505e2e7e..dd850a26d579 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size,
 
 #define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (!is_directory(base, ent))
+		if (!is_directory(base, ent) && ent->d_name[0] != '.')
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 263057039693..94e513e62b34 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -14,35 +14,40 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
-	idx=0
-	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
-		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-	file=`mktemp -u /tmp/perf.data.XXX`
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
 
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $file | while read line ; do
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
 		echo $line
-		echo "$line" | egrep -q "${expected[$idx]}"
+		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
-			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
 			exit 1
 		fi
-		let idx+=1
-		[ -z "${expected[$idx]}" ] && break
 	done
 
 	# If any statements are executed from this point onwards,
@@ -58,6 +63,6 @@ skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
-rm -f ${file}
+rm -f ${perf_data} ${perf_script} ${expected}
 perf probe -q -d probe_libc:inet_pton
 exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 55ad9793d544..4ce276efe6b4 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 976e658e38dc..5e94857dfca2 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -266,16 +266,16 @@ static const char *kinc_fetch_script =
 "#!/usr/bin/env sh\n"
 "if ! test -d \"$KBUILD_DIR\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "TMPDIR=`mktemp -d`\n"
 "if test -z \"$TMPDIR\"\n"
 "then\n"
-"    exit -1\n"
+"    exit 1\n"
 "fi\n"
 "cat << EOF > $TMPDIR/Makefile\n"
 "obj-y := dummy.o\n"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 46e9e19ab1ac..bc32e57d17be 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	if (!dict) {
+	if (!dict)
 		call_object(handler, t, handler_name);
-	} else {
+	else
 		call_object(handler, t, default_handler_name);
-		Py_DECREF(dict);
-	}
 
-	Py_XDECREF(all_entries_dict);
 	Py_DECREF(t);
 }
 
@@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	call_object(handler, t, handler_name);
 
-	Py_DECREF(dict);
 	Py_DECREF(t);
 }
 
@@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
+	fprintf(ofp, "from __future__ import print_function\n\n");
 	fprintf(ofp, "import os\n");
 	fprintf(ofp, "import sys\n\n");
 
@@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "from Core import *\n\n\n");
 
 	fprintf(ofp, "def trace_begin():\n");
-	fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
 
 	fprintf(ofp, "def trace_end():\n");
-	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
@@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			"common_secs, common_nsecs,\n\t\t\t"
 			"common_pid, common_comm)\n\n");
 
-		fprintf(ofp, "\t\tprint \"");
+		fprintf(ofp, "\t\tprint(\"");
 
 		not_first = 0;
 		count = 0;
@@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, ")\n\n");
+		fprintf(ofp, "))\n\n");
 
-		fprintf(ofp, "\t\tprint 'Sample: {'+"
-			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+		fprintf(ofp, "\t\tprint('Sample: {'+"
+			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 		fprintf(ofp, "\t\tfor node in common_callchain:");
 		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
 		fprintf(ofp, "\n\t\t\telse:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
-		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+		fprintf(ofp, "\t\tprint()\n\n");
 
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
 		"event_fields_dict, perf_sample_dict):\n");
 
-	fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
-	fprintf(ofp, "\t\tprint 'Sample: {'+"
-		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+	fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+	fprintf(ofp, "\t\tprint('Sample: {'+"
+		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"
-		"\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-		"(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+		"\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+		"(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
 
 	fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
 		"\treturn delimiter.join"

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-06-30  8:44 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-06-30  8:44 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 9331510135640429711afbd0c810686100824a79 perf/core: Move inline keyword at the beginning of declaration

Tooling fixes mostly, plus a build warning fix.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf intel-pt: Fix packet decoding of CYC packets

Arnaldo Carvalho de Melo (5):
      tools headers uapi: Synchronize drm/drm.h
      perf tools: Update x86's syscall_64.tbl, adding 'io_pgetevents' and 'rseq'
      tools include powerpc: Update arch/powerpc/include/uapi/asm/unistd.h copy to get 'rseq' syscall
      tools include uapi: Update if_link.h to pick IFLA_{BRPORT_ISOLATED,VXLAN_TTL_INHERIT}
      tools include uapi: Synchronize bpf.h with the kernel

Ingo Molnar (1):
      tools/headers: Pick up latest kernel ABIs

Jiri Olsa (3):
      perf tests: Add event parsing error handling to parse events test
      perf tests: Add valid callback for parse-events test
      perf bench: Fix numa report output code

Mathieu Malaterre (1):
      perf/core: Move inline keyword at the beginning of declaration

Ravi Bangoria (3):
      perf script: Add missing output fields in a hint
      perf script: Fix crash because of missing evsel->priv
      perf tools: Fix crash caused by accessing feat_ops[HEADER_LAST_FEATURE]

Sandipan Das (1):
      perf report powerpc: Fix crash if callchain is empty

Thomas Richter (5):
      perf record: Support s390 random socket_id assignment
      perf test session topology: Fix test on s390
      perf alias: Remove trailing newline when reading sysfs files
      perf alias: Rebuild alias expression string to make it comparable
      perf stat: Remove duplicate event counting

Yonghong Song (1):
      perf tools: Fix a clang 7.0 compilation error


 kernel/events/core.c                               |  2 +-
 tools/arch/arm/include/uapi/asm/kvm.h              |  1 +
 tools/arch/arm64/include/uapi/asm/kvm.h            |  1 +
 tools/arch/powerpc/include/uapi/asm/kvm.h          |  1 +
 tools/arch/powerpc/include/uapi/asm/unistd.h       |  1 +
 tools/arch/x86/include/asm/cpufeatures.h           |  2 +
 tools/include/uapi/drm/drm.h                       |  7 ++
 tools/include/uapi/linux/bpf.h                     |  2 +-
 tools/include/uapi/linux/if_link.h                 |  2 +
 tools/include/uapi/linux/kvm.h                     |  1 +
 tools/perf/arch/powerpc/util/skip-callchain-idx.c  |  2 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  2 +
 tools/perf/bench/numa.c                            |  5 +-
 tools/perf/builtin-annotate.c                      | 11 ++-
 tools/perf/builtin-report.c                        |  3 +-
 tools/perf/builtin-script.c                        | 30 ++++++-
 tools/perf/tests/parse-events.c                    | 25 ++++--
 tools/perf/tests/topology.c                        |  1 +
 tools/perf/util/c++/clang.cpp                      | 11 ++-
 tools/perf/util/header.c                           | 12 ++-
 .../util/intel-pt-decoder/intel-pt-pkt-decoder.c   |  2 +-
 tools/perf/util/pmu.c                              | 99 +++++++++++++++++++++-
 22 files changed, 201 insertions(+), 22 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..8f0434a9951a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6482,7 +6482,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
-static void __always_inline
+static __always_inline void
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index caae4843cb70..16e006f708ca 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 04b3256f8e6d..4e76630dd655 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 833ed9a16adf..1b32b56a03d3 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index 389c36fd8299..ac5ba55066dd 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -398,5 +398,6 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index fb00a2fca990..5701f5cecd31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -282,7 +282,9 @@
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0b06784f227..59b19b6a40d7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2630,7 +2630,7 @@ struct bpf_fib_lookup {
 	union {
 		/* inputs to lookup */
 		__u8	tos;		/* AF_INET  */
-		__be32	flowlabel;	/* AF_INET6 */
+		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
 
 		/* output: metric of fib result (IPv4/IPv6 only) */
 		__u32	rt_metric;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 68699f654118..cf01b6824244 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
 	IFLA_BRPORT_BCAST_FLOOD,
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
+	IFLA_BRPORT_ISOLATED,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 39e364c70caf..b6270a3b38e9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..ef5d59a5742e 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -243,7 +243,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
 	ip = chain->ips[2];
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..8180319285af 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ static int process_sample_event(struct perf_tool *tool,
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..c04dc7b53797 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a31d7082188e..568ddfac3213 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3030,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3074,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3125,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7d4077068454..61211918bfba 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static bool test__intel_pt_valid(void)
+{
+	return !!perf_pmu__find("intel_pt");
+}
+
 static int test__intel_pt(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1375,6 +1380,7 @@ struct evlist_test {
 	const char *name;
 	__u32 type;
 	const int id;
+	bool (*valid)(void);
 	int (*check)(struct perf_evlist *evlist);
 };
 
@@ -1648,6 +1654,7 @@ static struct evlist_test test__events[] = {
 	},
 	{
 		.name  = "intel_pt//u",
+		.valid = test__intel_pt_valid,
 		.check = test__intel_pt,
 		.id    = 52,
 	},
@@ -1686,17 +1693,24 @@ static struct terms_test test__terms[] = {
 
 static int test_event(struct evlist_test *e)
 {
+	struct parse_events_error err = { .idx = 0, };
 	struct perf_evlist *evlist;
 	int ret;
 
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP");
+		return 0;
+	}
+
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, NULL);
+	ret = parse_events(evlist, e->name, &err);
 	if (ret) {
-		pr_debug("failed to parse event '%s', err %d\n",
-			 e->name, ret);
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_print_error(&err, e->name);
 	} else {
 		ret = e->check(evlist);
 	}
@@ -1714,10 +1728,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", e->id, e->name);
+		pr_debug("running test %d '%s'", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
+		pr_debug("\n");
 	}
 
 	return ret2;
@@ -1799,7 +1814,7 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-		struct evlist_test e;
+		struct evlist_test e = { .id = 0, };
 		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 40e30a26b23c..9497d02f69e6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -45,6 +45,7 @@ static int session_write_header(char *path)
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
 	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
 
 	session->header.data_size += DATA_SIZE;
 
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index bf31ceab33bd..89512504551b 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
 	raw_svector_ostream ostream(*Buffer);
 
 	legacy::PassManager PM;
-	if (TargetMachine->addPassesToEmitFile(PM, ostream,
-					       TargetMachine::CGFT_ObjectFile)) {
+	bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+						      TargetMachine::CGFT_ObjectFile);
+#else
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+						      TargetMachine::CGFT_ObjectFile);
+#endif
+	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
 		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
 	}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 540cd2dcd3e7..653ff65aa2c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2129,6 +2129,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
 	struct perf_header *ph = ff->ph;
+	bool do_core_id_test = true;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
 	if (!ph->env.cpu)
@@ -2183,6 +2184,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		return 0;
 	}
 
+	/* On s390 the socket_id number is not related to the numbers of cpus.
+	 * The socket_id number might be higher than the numbers of cpus.
+	 * This depends on the configuration.
+	 */
+	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+		do_core_id_test = false;
+
 	for (i = 0; i < (u32)cpu_nr; i++) {
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2192,7 +2200,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
 
-		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+		if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
@@ -3456,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return 0;
 	}
-	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+	if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return -1;
 	}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d2fb597c9a8c..3ba6a1742f91 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+				char **new_str)
+{
+	if (!*old_str)
+		goto set_new;
+
+	if (*new_str) {	/* Have new string, check with old */
+		if (strcasecmp(*old_str, *new_str))
+			pr_debug("alias %s differs in field '%s'\n",
+				 name, field);
+		zfree(old_str);
+	} else		/* Nothing new --> keep old string */
+		return;
+set_new:
+	*old_str = *new_str;
+	*new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+				  struct perf_pmu_alias *newalias)
+{
+	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+			    &newalias->long_desc);
+	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+	perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+			    &newalias->metric_expr);
+	perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+			    &newalias->metric_name);
+	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+	old->scale = newalias->scale;
+	old->per_pkg = newalias->per_pkg;
+	old->snapshot = newalias->snapshot;
+	memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+	zfree(&newalias->name);
+	zfree(&newalias->desc);
+	zfree(&newalias->long_desc);
+	zfree(&newalias->topic);
+	zfree(&newalias->str);
+	zfree(&newalias->metric_expr);
+	zfree(&newalias->metric_name);
+	parse_events_terms__purge(&newalias->terms);
+	free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+				 struct list_head *alist)
+{
+	struct perf_pmu_alias *a;
+
+	list_for_each_entry(a, alist, list) {
+		if (!strcasecmp(newalias->name, a->name)) {
+			perf_pmu_update_alias(a, newalias);
+			perf_pmu_free_alias(newalias);
+			return true;
+		}
+	}
+	return false;
+}
+
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
@@ -241,9 +309,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *metric_expr,
 				 char *metric_name)
 {
+	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
 	int num;
+	char newval[256];
 
 	alias = malloc(sizeof(*alias));
 	if (!alias)
@@ -262,6 +332,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		return ret;
 	}
 
+	/* Scan event and remove leading zeroes, spaces, newlines, some
+	 * platforms have terms specified as
+	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
+	 * and terms specified as event=0x91 (read from JSON files).
+	 *
+	 * Rebuild string to make alias->str member comparable.
+	 */
+	memset(newval, 0, sizeof(newval));
+	ret = 0;
+	list_for_each_entry(term, &alias->terms, list) {
+		if (ret)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 ",");
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%#x", term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%s", term->config, term->val.str);
+	}
+
 	alias->name = strdup(name);
 	if (dir) {
 		/*
@@ -285,9 +376,10 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
-	alias->str = strdup(val);
+	alias->str = strdup(newval);
 
-	list_add_tail(&alias->list, list);
+	if (!perf_pmu_merge_alias(alias, list))
+		list_add_tail(&alias->list, list);
 
 	return 0;
 }
@@ -303,6 +395,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
+	/* Remove trailing newline from sysfs file */
+	rtrim(buf);
+
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
 				     NULL, NULL, NULL);
 }


^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-06-04  9:04 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-06-04  9:04 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Thomas Gleixner, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4e9ae0d3d5bf4e2f1b466ba451bd18f2c5b69845 Merge tag 'perf-urgent-for-mingo-4.17-20180602' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Leftover perf tooling fixes from the v4.17 cycle: they sync up updated ABI headers 
with their tooling versions.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf trace beauty prctl: Default header_dir to cwd to work without parms
      tools headers: Synchronize prctl.h ABI header
      tools headers: Sync x86 cpufeatures.h with the kernel sources
      perf tools intel-pt-decoder: Update insn.h from the kernel sources


 tools/arch/x86/include/asm/cpufeatures.h | 20 ++++++++++++++------
 tools/include/uapi/linux/prctl.h         | 12 ++++++++++++
 tools/perf/trace/beauty/prctl_option.sh  |  2 +-
 tools/perf/util/intel-pt-decoder/insn.h  | 18 ++++++++++++++++++
 4 files changed, 45 insertions(+), 7 deletions(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 578793e97431..fb00a2fca990 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -334,6 +340,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
  * BUG word(s)
@@ -363,5 +370,6 @@
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index af5f8c2df87a..db9f15f5db04 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -207,4 +207,16 @@ struct prctl_mm_map {
 # define PR_SVE_VL_LEN_MASK		0xffff
 # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL		52
+#define PR_SET_SPECULATION_CTRL		53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS		0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED		0
+# define PR_SPEC_PRCTL			(1UL << 0)
+# define PR_SPEC_ENABLE			(1UL << 1)
+# define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 0be4138fbe71..f24722146ebe 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
 regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index e23578c7b1be..2669c9f748e4 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
 #endif /* _ASM_X86_INSN_H */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-03-31 10:40 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-03-31 10:40 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Thomas Gleixner, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: f67b15037a7a50c57f72e69a6d59941ad90a0f0f perf/hwbp: Simplify the perf-hwbp code, fix documentation

Two fixlets.

 Thanks,

	Ingo

------------------>
Linus Torvalds (1):
      perf/hwbp: Simplify the perf-hwbp code, fix documentation

Stephane Eranian (1):
      perf/x86/intel: Fix linear IP of PEBS real_ip on Haswell and later CPUs


 arch/x86/events/intel/ds.c    | 25 +++++++++++++++++--------
 kernel/events/hw_breakpoint.c | 30 +++++++-----------------------
 2 files changed, 24 insertions(+), 31 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index d8015235ba76..5e526c54247e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1153,6 +1153,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	if (pebs == NULL)
 		return;
 
+	regs->flags &= ~PERF_EFLAGS_EXACT;
 	sample_type = event->attr.sample_type;
 	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
 
@@ -1197,7 +1198,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	 */
 	*regs = *iregs;
 	regs->flags = pebs->flags;
-	set_linear_ip(regs, pebs->ip);
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		regs->ax = pebs->ax;
@@ -1233,13 +1233,22 @@ static void setup_pebs_sample_data(struct perf_event *event,
 #endif
 	}
 
-	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
-		regs->ip = pebs->real_ip;
-		regs->flags |= PERF_EFLAGS_EXACT;
-	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
-		regs->flags |= PERF_EFLAGS_EXACT;
-	else
-		regs->flags &= ~PERF_EFLAGS_EXACT;
+	if (event->attr.precise_ip > 1) {
+		/* Haswell and later have the eventing IP, so use it: */
+		if (x86_pmu.intel_cap.pebs_format >= 2) {
+			set_linear_ip(regs, pebs->real_ip);
+			regs->flags |= PERF_EFLAGS_EXACT;
+		} else {
+			/* Otherwise use PEBS off-by-1 IP: */
+			set_linear_ip(regs, pebs->ip);
+
+			/* ... and try to fix it up using the LBR entries: */
+			if (intel_pmu_pebs_fixup_ip(regs))
+				regs->flags |= PERF_EFLAGS_EXACT;
+		}
+	} else
+		set_linear_ip(regs, pebs->ip);
+
 
 	if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 3f8cb1e14588..253ae2da13c3 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -427,16 +427,9 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
  * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
  * @bp: the breakpoint structure to modify
  * @attr: new breakpoint attributes
- * @triggered: callback to trigger when we hit the breakpoint
- * @tsk: pointer to 'task_struct' of the process to which the address belongs
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
-	u64 old_addr = bp->attr.bp_addr;
-	u64 old_len = bp->attr.bp_len;
-	int old_type = bp->attr.bp_type;
-	int err = 0;
-
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -451,27 +444,18 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	bp->attr.bp_addr = attr->bp_addr;
 	bp->attr.bp_type = attr->bp_type;
 	bp->attr.bp_len = attr->bp_len;
+	bp->attr.disabled = 1;
 
-	if (attr->disabled)
-		goto end;
-
-	err = validate_hw_breakpoint(bp);
-	if (!err)
-		perf_event_enable(bp);
+	if (!attr->disabled) {
+		int err = validate_hw_breakpoint(bp);
 
-	if (err) {
-		bp->attr.bp_addr = old_addr;
-		bp->attr.bp_type = old_type;
-		bp->attr.bp_len = old_len;
-		if (!bp->attr.disabled)
-			perf_event_enable(bp);
+		if (err)
+			return err;
 
-		return err;
+		perf_event_enable(bp);
+		bp->attr.disabled = 0;
 	}
 
-end:
-	bp->attr.disabled = attr->disabled;
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-03-25  8:53 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-03-25  8:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Andrew Morton, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c917e0f259908e75bd2a65877e25f9d90c22c848 perf/cgroup: Fix child event counting bug

Misc kernel side fixes:

 - a cgroup events counting fix
 - an x86 Intel PMU truncated-parameter fix
 - an x86 RDPMC fix
 - an x86 API naming fix/rename
 - an x86 uncore driver big-hardware PCI enumeration fix
 - an x86 uncore driver filter constraint fix

 Thanks,

	Ingo

------------------>
Dan Carpenter (1):
      perf/x86/intel: Don't accidentally clear high bits in bdw_limit_period()

Kan Liang (3):
      perf/x86/intel: Disable userspace RDPMC usage for large PEBS
      perf/x86/intel: Rename confusing 'freerunning PEBS' API and implementation to 'large PEBS'
      perf/x86/intel/uncore: Fix multi-domain PCI CHA enumeration bug on Skylake servers

Song Liu (1):
      perf/cgroup: Fix child event counting bug

Stephane Eranian (1):
      perf/x86/intel/uncore: Add missing filter constraint for SKX CHA event


 arch/x86/events/core.c               |  3 ++-
 arch/x86/events/intel/core.c         | 14 +++++++-------
 arch/x86/events/intel/ds.c           |  6 +++---
 arch/x86/events/intel/uncore_snbep.c | 32 ++++++++++++++++++--------------
 arch/x86/events/perf_event.h         |  6 +++---
 kernel/events/core.c                 | 21 ++++++++++++++++-----
 6 files changed, 49 insertions(+), 33 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 140d33288e78..88797c80b3e0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2118,7 +2118,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 			event->destroy(event);
 	}
 
-	if (READ_ONCE(x86_pmu.attr_rdpmc))
+	if (READ_ONCE(x86_pmu.attr_rdpmc) &&
+	    !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
 		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
 
 	return err;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 56457cb73448..1e41d7508d99 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2952,9 +2952,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
 	return intel_pebs_aliases_precdist(event);
 }
 
-static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 {
-	unsigned long flags = x86_pmu.free_running_flags;
+	unsigned long flags = x86_pmu.large_pebs_flags;
 
 	if (event->attr.use_clockid)
 		flags &= ~PERF_SAMPLE_TIME;
@@ -2976,8 +2976,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (!event->attr.freq) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
-			      ~intel_pmu_free_running_flags(event)))
-				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+			      ~intel_pmu_large_pebs_flags(event)))
+				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
@@ -3194,7 +3194,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
 			X86_CONFIG(.event=0xc0, .umask=0x01)) {
 		if (left < 128)
 			left = 128;
-		left &= ~0x3fu;
+		left &= ~0x3fULL;
 	}
 	return left;
 }
@@ -3460,7 +3460,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32-bit width,
@@ -3502,7 +3502,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32 bit width,
 	 * so we install an artificial 1<<31 period regardless of
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 18c25ab28557..d8015235ba76 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs++;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs--;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -1530,7 +1530,7 @@ void __init intel_ds_init(void)
 			x86_pmu.pebs_record_size =
 						sizeof(struct pebs_record_skl);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
-			x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
 		default:
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 22ec65bc033a..c98b943e58b4 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3),
 	EVENT_EXTRA_END
 };
 
@@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
 	NULL,
 };
 
+/*
+ * To determine the number of CHAs, it should read bits 27:0 in the CAPID6
+ * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083.
+ */
+#define SKX_CAPID6		0x9c
+#define SKX_CHA_BIT_MASK	GENMASK(27, 0)
+
 static int skx_count_chabox(void)
 {
-	struct pci_dev *chabox_dev = NULL;
-	int bus, count = 0;
+	struct pci_dev *dev = NULL;
+	u32 val = 0;
 
-	while (1) {
-		chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
-		if (!chabox_dev)
-			break;
-		if (count == 0)
-			bus = chabox_dev->bus->number;
-		if (bus != chabox_dev->bus->number)
-			break;
-		count++;
-	}
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev);
+	if (!dev)
+		goto out;
 
-	pci_dev_put(chabox_dev);
-	return count;
+	pci_read_config_dword(dev, SKX_CAPID6, &val);
+	val &= SKX_CHA_BIT_MASK;
+out:
+	pci_dev_put(dev);
+	return hweight32(val);
 }
 
 void skx_uncore_cpu_init(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78f91ec1056e..39cd0615f04f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -69,7 +69,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
 
 
 struct amd_nb {
@@ -88,7 +88,7 @@ struct amd_nb {
  * REGS_USER can be handled for events limited to ring 3.
  *
  */
-#define PEBS_FREERUNNING_FLAGS \
+#define LARGE_PEBS_FLAGS \
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
@@ -608,7 +608,7 @@ struct x86_pmu {
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	int 		max_pebs_events;
-	unsigned long	free_running_flags;
+	unsigned long	large_pebs_flags;
 
 	/*
 	 * Intel LBR
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4b838470fac4..709a55b9ad97 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -724,9 +724,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
-	if (cgrp_out)
-		__update_cgrp_time(cgrp_out);
+	struct perf_cgroup *cgrp = cpuctx->cgrp;
+	struct cgroup_subsys_state *css;
+
+	if (cgrp) {
+		for (css = &cgrp->css; css; css = css->parent) {
+			cgrp = container_of(css, struct perf_cgroup, css);
+			__update_cgrp_time(cgrp);
+		}
+	}
 }
 
 static inline void update_cgrp_time_from_event(struct perf_event *event)
@@ -754,6 +760,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 	struct perf_cgroup *cgrp;
 	struct perf_cgroup_info *info;
+	struct cgroup_subsys_state *css;
 
 	/*
 	 * ctx->lock held by caller
@@ -764,8 +771,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 		return;
 
 	cgrp = perf_cgroup_from_task(task, ctx);
-	info = this_cpu_ptr(cgrp->info);
-	info->timestamp = ctx->timestamp;
+
+	for (css = &cgrp->css; css; css = css->parent) {
+		cgrp = container_of(css, struct perf_cgroup, css);
+		info = this_cpu_ptr(cgrp->info);
+		info->timestamp = ctx->timestamp;
+	}
 }
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2018-02-06 21:29 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2018-02-06 21:29 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 59410f5ac70a0949a6f06ba43eecb8f99be31291 Merge tag 'perf-urgent-for-mingo-4.16-20180205' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling fixes, plus add missing interval sampling to certain x86 PEBS events.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (5):
      tools headers: Synchronize sound/asound.h
      tooling headers: Synchronize updated s390 kvm UAPI headers
      tools headers: Sync {tools/,}arch/powerpc/include/uapi/asm/kvm.h
      tools headers: Synchronize uapi/linux/sched.h
      tools headers: Synchoronize x86 features UAPI headers

Jiri Olsa (3):
      perf evsel: Fix period/freq terms setup
      perf record: Fix period option handling
      x86/events/intel/ds: Add PERF_SAMPLE_PERIOD into PEBS_FREERUNNING_FLAGS

Ravi Bangoria (2):
      perf trace: Fix call-graph output
      perf tools: Add trace/beauty/generated/ into .gitignore


 arch/x86/events/perf_event.h                   |  3 ++-
 tools/arch/powerpc/include/uapi/asm/kvm.h      | 25 +++++++++++++++++++++++++
 tools/arch/s390/include/uapi/asm/kvm.h         |  5 ++++-
 tools/arch/x86/include/asm/cpufeatures.h       | 24 ++++++++++++++++++++----
 tools/arch/x86/include/asm/disabled-features.h |  3 ++-
 tools/arch/x86/include/asm/required-features.h |  3 ++-
 tools/include/uapi/linux/kvm.h                 |  4 ++++
 tools/include/uapi/linux/sched.h               |  5 +++++
 tools/include/uapi/sound/asound.h              |  9 +++++++++
 tools/perf/.gitignore                          |  1 +
 tools/perf/builtin-record.c                    |  3 ++-
 tools/perf/builtin-trace.c                     |  5 ++++-
 tools/perf/perf.h                              |  1 +
 tools/perf/util/evsel.c                        | 13 ++++++++++---
 14 files changed, 91 insertions(+), 13 deletions(-)

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8e4ea143ed96..78f91ec1056e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -93,7 +93,8 @@ struct amd_nb {
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
-	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
+	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
+	PERF_SAMPLE_PERIOD)
 
 #define PEBS_REGS \
 	(PERF_REG_X86_AX | \
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 61d6049f4c1e..637b7263cb86 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
 	__u32	ap_encodings[8];
 };
 
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 38535a57fef8..4cdaa55fabfe 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -224,6 +224,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -247,7 +248,9 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
+	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
 	union {
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 21ac898df2d8..1d9199e1c2ad 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NCAPINTS			19	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -203,12 +203,15 @@
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
+#define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
+
+#define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -243,6 +246,7 @@
 #define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT		( 9*32+25) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
@@ -268,6 +272,9 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -316,6 +323,13 @@
 #define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
 #define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+
 /*
  * BUG word(s)
  */
@@ -342,5 +356,7 @@
 #define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index b027633e7300..33833d1909af 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -77,6 +77,7 @@
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index d91ba04dd007..fb3a6de7440b 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -106,6 +106,7 @@
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 496e59a2738b..8fb90a0819c3 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -932,6 +932,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
 #define KVM_CAP_S390_AIS_MIGRATION 150
+#define KVM_CAP_PPC_GET_CPU_CHAR 151
+#define KVM_CAP_S390_BPB 152
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1261,6 +1263,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
 /* Available with KVM_CAP_PPC_RADIX_MMU */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
+/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
+#define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 30a9e51bbb1e..22627f80063e 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -49,5 +49,10 @@
  */
 #define SCHED_FLAG_RESET_ON_FORK	0x01
 #define SCHED_FLAG_RECLAIM		0x02
+#define SCHED_FLAG_DL_OVERRUN		0x04
+
+#define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
+			 SCHED_FLAG_RECLAIM		| \
+			 SCHED_FLAG_DL_OVERRUN)
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index c227ccba60ae..07d61583fd02 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -214,6 +214,11 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_IMA_ADPCM	((__force snd_pcm_format_t) 22)
 #define	SNDRV_PCM_FORMAT_MPEG		((__force snd_pcm_format_t) 23)
 #define	SNDRV_PCM_FORMAT_GSM		((__force snd_pcm_format_t) 24)
+#define	SNDRV_PCM_FORMAT_S20_LE	((__force snd_pcm_format_t) 25) /* in four bytes, LSB justified */
+#define	SNDRV_PCM_FORMAT_S20_BE	((__force snd_pcm_format_t) 26) /* in four bytes, LSB justified */
+#define	SNDRV_PCM_FORMAT_U20_LE	((__force snd_pcm_format_t) 27) /* in four bytes, LSB justified */
+#define	SNDRV_PCM_FORMAT_U20_BE	((__force snd_pcm_format_t) 28) /* in four bytes, LSB justified */
+/* gap in the numbering for a future standard linear format */
 #define	SNDRV_PCM_FORMAT_SPECIAL	((__force snd_pcm_format_t) 31)
 #define	SNDRV_PCM_FORMAT_S24_3LE	((__force snd_pcm_format_t) 32)	/* in three bytes */
 #define	SNDRV_PCM_FORMAT_S24_3BE	((__force snd_pcm_format_t) 33)	/* in three bytes */
@@ -248,6 +253,8 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_LE
 #define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_LE
 #define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
+#define	SNDRV_PCM_FORMAT_S20		SNDRV_PCM_FORMAT_S20_LE
+#define	SNDRV_PCM_FORMAT_U20		SNDRV_PCM_FORMAT_U20_LE
 #endif
 #ifdef SNDRV_BIG_ENDIAN
 #define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_BE
@@ -259,6 +266,8 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_BE
 #define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_BE
 #define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
+#define	SNDRV_PCM_FORMAT_S20		SNDRV_PCM_FORMAT_S20_BE
+#define	SNDRV_PCM_FORMAT_U20		SNDRV_PCM_FORMAT_U20_BE
 #endif
 
 typedef int __bitwise snd_pcm_subformat_t;
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 643cc4ba6872..3e5135dded16 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -31,5 +31,6 @@ config.mak.autogen
 .config-detected
 util/intel-pt-decoder/inat-tables.c
 arch/*/include/generated/
+trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 65681a1a292a..bf4ca749d1ac 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1566,7 +1566,8 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
 			&record.opts.sample_time_set,
 			"Record the sample timestamps"),
-	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
+	OPT_BOOLEAN_SET('P', "period", &record.opts.period, &record.opts.period_set,
+			"Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
 	OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 17d11deeb88d..e7f1b182fc15 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1661,9 +1661,12 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 				    struct callchain_cursor *cursor)
 {
 	struct addr_location al;
+	int max_stack = evsel->attr.sample_max_stack ?
+			evsel->attr.sample_max_stack :
+			trace->max_stack;
 
 	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, evsel->attr.sample_max_stack))
+	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
 		return -1;
 
 	return 0;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2357f4ccc9c7..cfe46236a5e5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -50,6 +50,7 @@ struct record_opts {
 	bool	     sample_time_set;
 	bool	     sample_cpu;
 	bool	     period;
+	bool	     period_set;
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 66fa45198a11..ff359c9ece2e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -745,12 +745,14 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
 				attr->sample_period = term->val.period;
 				attr->freq = 0;
+				perf_evsel__reset_sample_bit(evsel, PERIOD);
 			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
 			if (!(term->weak && opts->user_freq != UINT_MAX)) {
 				attr->sample_freq = term->val.freq;
 				attr->freq = 1;
+				perf_evsel__set_sample_bit(evsel, PERIOD);
 			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
@@ -969,9 +971,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	if (target__has_cpu(&opts->target) || opts->sample_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 
-	if (opts->period)
-		perf_evsel__set_sample_bit(evsel, PERIOD);
-
 	/*
 	 * When the user explicitly disabled time don't force it here.
 	 */
@@ -1073,6 +1072,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	apply_config_terms(evsel, opts, track);
 
 	evsel->ignore_missing_thread = opts->ignore_missing_thread;
+
+	/* The --period option takes the precedence. */
+	if (opts->period_set) {
+		if (opts->period)
+			perf_evsel__set_sample_bit(evsel, PERIOD);
+		else
+			perf_evsel__reset_sample_bit(evsel, PERIOD);
+	}
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-12-06 22:17 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-12-06 22:17 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 34c9ca37aaec2e307b837bb099d3b44f0ea04ddc tooling/headers: Synchronize updated s390 and x86 UAPI headers

This tree includes perf namespace support kernel side fixes, plus an accumulated 
set of perf tooling fixes - including UAPI header synchronization that should make 
the perf build less noisy.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf intel-pt: Bring instruction decoder files into line with the kernel

Andi Kleen (1):
      perf record: Fix -c/-F options for cpu event aliases

Andrei Vagin (1):
      perf trace: Fix an exit code of trace__symbols_init

Arnaldo Carvalho de Melo (16):
      perf evlist: Set the correct idx when adding dummy events
      perf record: Generate PERF_RECORD_{MMAP,COMM,EXEC} with --delay
      perf evsel: Fix up leftover perf_evsel_stat usage via evsel->priv
      perf script: Fix --per-event-dump for auxtrace synth evsels
      perf machine: Guard against NULL in machine__exit()
      perf evlist: Add helper to check if attr.exclude_kernel is set in all evsels
      perf report: Ignore kptr_restrict when not sampling the kernel
      perf record: Ignore kptr_restrict when not sampling the kernel
      perf top: Ignore kptr_restrict when not sampling the kernel
      tools headers: Synchronize kernel ABI headers wrt SPDX tags
      tools headers: Synchronize perf_event.h header
      tools headers uapi: Synchronize drm/drm.h
      tools headers: Synchronize drm/i915_drm.h
      tools headers: Synchronize KVM arch ABI headers
      tools headers: Synchronize prctl.h ABI header
      tools headers: Syncronize mman.h ABI header

Ingo Molnar (2):
      tools/headers: Synchronize kernel x86 UAPI headers
      tooling/headers: Synchronize updated s390 and x86 UAPI headers

Jiri Olsa (3):
      perf: Fix header.size for namespace events
      perf top: Fix window dimensions change handling
      perf top: Use signal interface for SIGWINCH handler

Namhyung Kim (1):
      perf help: Fix a bug during strstart() conversion

Ravi Bangoria (1):
      perf annotate: Do not truncate instruction names at 6 chars

Satheesh Rajendran (1):
      perf bench numa: Fixup discontiguous/sparse numa nodes

Thomas Richter (3):
      perf test shell: Fix check open filename arg using 'perf trace' on s390x
      perf test shell: Fix test case probe libc's inet_pton on s390x
      perf test: Fix test 21 for s390x

Vasily Averin (1):
      perf/core: Fix memory leak triggered by perf --namespace


 kernel/events/core.c                               |   5 +-
 tools/arch/arm/include/uapi/asm/kvm.h              |   7 +
 tools/arch/arm64/include/uapi/asm/kvm.h            |   7 +
 tools/arch/s390/include/uapi/asm/kvm.h             |   4 -
 tools/arch/s390/include/uapi/asm/kvm_perf.h        |   4 -
 tools/arch/x86/include/asm/cpufeatures.h           | 537 +++++++++++----------
 tools/arch/x86/include/asm/disabled-features.h     |   8 +-
 tools/include/uapi/asm-generic/mman.h              |   1 +
 tools/include/uapi/drm/drm.h                       |  41 ++
 tools/include/uapi/drm/i915_drm.h                  |  33 +-
 tools/include/uapi/linux/kcmp.h                    |   1 +
 tools/include/uapi/linux/kvm.h                     |   1 +
 tools/include/uapi/linux/perf_event.h              |   1 +
 tools/include/uapi/linux/prctl.h                   |  10 +
 tools/perf/bench/numa.c                            |  56 ++-
 tools/perf/builtin-help.c                          |   4 +-
 tools/perf/builtin-record.c                        |  42 +-
 tools/perf/builtin-report.c                        |   3 +
 tools/perf/builtin-script.c                        |  31 +-
 tools/perf/builtin-top.c                           |  36 +-
 tools/perf/builtin-trace.c                         |   6 +-
 .../perf/tests/shell/trace+probe_libc_inet_pton.sh |   7 +-
 tools/perf/tests/shell/trace+probe_vfs_getname.sh  |   6 +-
 tools/perf/tests/task-exit.c                       |   4 +
 tools/perf/trace/beauty/mmap.c                     |   3 +
 tools/perf/util/annotate.c                         |  18 +-
 tools/perf/util/evlist.c                           |  14 +-
 tools/perf/util/evlist.h                           |   2 +
 tools/perf/util/evsel.c                            |  14 +-
 tools/perf/util/evsel.h                            |   1 +
 tools/perf/util/intel-pt-decoder/inat.h            |  10 +
 .../perf/util/intel-pt-decoder/x86-opcode-map.txt  |   2 +-
 tools/perf/util/machine.c                          |   3 +
 tools/perf/util/parse-events.c                     |   2 +
 tools/perf/util/parse-events.h                     |   3 +
 tools/perf/util/pmu.c                              |   5 +
 36 files changed, 594 insertions(+), 338 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 16beab4767e1..5961ef6dfd64 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6639,6 +6639,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	struct perf_namespaces_event *namespaces_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
+	u16 header_size = namespaces_event->event_id.header.size;
 	int ret;
 
 	if (!perf_event_namespaces_match(event))
@@ -6649,7 +6650,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	ret = perf_output_begin(&handle, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
-		return;
+		goto out;
 
 	namespaces_event->event_id.pid = perf_event_pid(event,
 							namespaces_event->task);
@@ -6661,6 +6662,8 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	perf_event__output_id_sample(event, &handle, &sample);
 
 	perf_output_end(&handle);
+out:
+	namespaces_event->event_id.header.size = header_size;
 }
 
 static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 1f57bbe82b6f..6edd177bb1c7 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -152,6 +152,12 @@ struct kvm_arch_memory_slot {
 	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
+/* PL1 Physical Timer Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM_CP15_REG32(0, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CNT		ARM_CP15_REG64(0, 14)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM_CP15_REG64(2, 14)
+
+/* Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
 #define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
@@ -216,6 +222,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES		1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES	2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 51149ec75fe4..9abbf3044654 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -196,6 +196,12 @@ struct kvm_arch_memory_slot {
 
 #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
 
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
@@ -228,6 +234,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9ad172dcd912..38535a57fef8 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -6,10 +6,6 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
index c36c97ffdc6f..84606b8cc49e 100644
--- a/tools/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -4,10 +4,6 @@
  *
  * Copyright 2014 IBM Corp.
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_KVM_PERF_S390_H
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 793690fbda36..c0b0e9e8aa66 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,173 +13,176 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
+#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
  * in /proc/cpuinfo instead of the macro name.  If the string is "",
  * this feature bit is not displayed in /proc/cpuinfo at all.
+ *
+ * When adding new features here that depend on other features,
+ * please update the table in kernel/cpu/cpuid-deps.c as well.
  */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
+#define X86_FEATURE_FPU			( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME			( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE			( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE			( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC			( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR			( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE			( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE			( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8			( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC		( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP			( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR		( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE			( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA			( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV		( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT			( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36		( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN			( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH		( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS			( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI		( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX			( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR		( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM			( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2		( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP		( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT			( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC			( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64		( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE			( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL		( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP			( 1*32+19) /* MP Capable */
+#define X86_FEATURE_NX			( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT		( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT		( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES		( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP		( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM			( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT		( 1*32+30) /* AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW		( 1*32+31) /* 3DNow */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY		( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN		( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI		( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_CXMMX		( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+/* CPU types for specific tunings: */
+#define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP			( 3*32+ 9) /* SMP kernel running on UP */
+#define X86_FEATURE_ART			( 3*32+10) /* Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON	( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS		( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS			( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
+#define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
+#define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC	( 3*32+17) /* "" MFENCE synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY		( 3*32+22) /* CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE	( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC		( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CPUID		( 3*32+25) /* CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID		( 3*32+26) /* Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM		( 3*32+27) /* AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF		( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
+#define X86_FEATURE_XMM3		( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ		( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64		( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT		( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
+#define X86_FEATURE_DSCPL		( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
+#define X86_FEATURE_VMX			( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX			( 4*32+ 6) /* Safer Mode eXtensions */
+#define X86_FEATURE_EST			( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2			( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3		( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID			( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG		( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA			( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16		( 4*32+13) /* CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR		( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM		( 4*32+15) /* Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID		( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA			( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1		( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2		( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC		( 4*32+21) /* X2APIC */
+#define X86_FEATURE_MOVBE		( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT		( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* TSC deadline timer */
+#define X86_FEATURE_AES			( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE		( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE		( 4*32+27) /* "" XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX			( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C		( 4*32+29) /* 16-bit FP conversions */
+#define X86_FEATURE_RDRAND		( 4*32+30) /* RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR		( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE		( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN		( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT		( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN		( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2		( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN		( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE			( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN		( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM			( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN		( 5*32+13) /* PMM enabled */
 
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
-#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_LLC	( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
+#define X86_FEATURE_LAHF_LM		( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY		( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM			( 6*32+ 2) /* Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC		( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY		( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM			( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A		( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE		( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH	( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW		( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS			( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP			( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT		( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT			( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP			( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4		( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE			( 6*32+17) /* Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR		( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM			( 6*32+21) /* Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT		( 6*32+22) /* Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE	( 6*32+23) /* Core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB		( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT		( 6*32+26) /* Data breakpoint extension */
+#define X86_FEATURE_PTSC		( 6*32+27) /* Performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_LLC		( 6*32+28) /* Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX		( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -187,146 +190,154 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
-#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
-#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_RING3MWAIT		( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT		( 7*32+ 1) /* Intel CPUID faulting */
+#define X86_FEATURE_CPB			( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB			( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 
-#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
 
-#define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
+#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
-#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI		( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY	( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT			( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID		( 8*32+ 4) /* Intel Virtual Processor ID */
 
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+#define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
 
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
+#define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
+#define X86_FEATURE_TSC_ADJUST		( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_BMI1		( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE			( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2		( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP		( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2		( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS		( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
+#define X86_FEATURE_INVPCID		( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM			( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM			( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX			( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A		( 9*32+15) /* Resource Director Technology Allocation */
+#define X86_FEATURE_AVX512F		( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ		( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED		( 9*32+18) /* RDSEED instruction */
+#define X86_FEATURE_ADX			( 9*32+19) /* ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP		( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
+#define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI		( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW		( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL		( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
 
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
+#define X86_FEATURE_XSAVEOPT		(10*32+ 0) /* XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
+#define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
+#define X86_FEATURE_CQM_LLC		(11*32+ 1) /* LLC QoS if 1 */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC	(12*32+ 0) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL	(12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL	(12*32+ 2) /* LLC Local MBM monitoring */
 
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
+/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
+#define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
+#define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA			(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT		(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN			(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS			(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP			(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY		(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW	(14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP		(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ		(14*32+11) /* HWP Package Level Request */
 
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
-#define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
+#define X86_FEATURE_NPT			(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV		(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML		(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS		(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR		(15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN		(15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID		(15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS	(15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER		(15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD		(15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
-#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
-#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
+#define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP		(16*32+ 2) /* User Mode Instruction Protection */
+#define X86_FEATURE_PKU			(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
+#define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
+#define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 
-/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
 
 /*
  * BUG word(s)
  */
-#define X86_BUG(x)		(NCAPINTS*32 + (x))
+#define X86_BUG(x)			(NCAPINTS*32 + (x))
 
-#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_F00F			X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV			X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA			X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH		X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E		X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP			X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK		X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR		X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS		X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
  * to avoid confusion.
  */
-#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX			X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
-#define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
-#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
-#define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_NULL_SEG		X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..14d6d5007314 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_INTEL_UMIP
+# define DISABLE_UMIP	0
+#else
+# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
+#endif
+
 #ifdef CONFIG_X86_64
 # define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
@@ -63,7 +69,7 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 2dffcbf705b3..653687d9771b 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -13,6 +13,7 @@
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
 #define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x40000		/* create a huge page mapping */
+#define MAP_SYNC	0x80000		/* perform synchronous page faults for the mapping */
 
 /* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
 
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 97677cd6964d..6fdff5945c8a 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -737,6 +737,28 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+	__u32 crtc_id;		/* requested crtc_id */
+	__u32 active;		/* return: crtc output is active */
+	__u64 sequence;		/* return: most recent vblank sequence */
+	__s64 sequence_ns;	/* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE		0x00000001	/* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS		0x00000002	/* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+	__u32 crtc_id;
+	__u32 flags;
+	__u64 sequence;		/* on input, target sequence. on output, actual sequence */
+	__u64 user_data;	/* user data passed to event */
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -819,6 +841,9 @@ extern "C" {
 
 #define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)
 
+#define DRM_IOCTL_CRTC_GET_SEQUENCE	DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE	DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
 #define DRM_IOCTL_UPDATE_DRAW		DRM_IOW(0x3f, struct drm_update_draw)
 
 #define DRM_IOCTL_MODE_GETRESOURCES	DRM_IOWR(0xA0, struct drm_mode_card_res)
@@ -863,6 +888,11 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
 #define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
+#define DRM_IOCTL_MODE_CREATE_LEASE	DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES	DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
@@ -893,6 +923,7 @@ struct drm_event {
 
 #define DRM_EVENT_VBLANK 0x01
 #define DRM_EVENT_FLIP_COMPLETE 0x02
+#define DRM_EVENT_CRTC_SEQUENCE	0x03
 
 struct drm_event_vblank {
 	struct drm_event base;
@@ -903,6 +934,16 @@ struct drm_event_vblank {
 	__u32 crtc_id; /* 0 on older kernels that do not support this */
 };
 
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+	struct drm_event	base;
+	__u64			user_data;
+	__s64			time_ns;
+	__u64			sequence;
+};
+
 /* typedef area */
 #ifndef __KERNEL__
 typedef struct drm_clip_rect drm_clip_rect_t;
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 9816590d3ad2..ac3c6503ca27 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -397,10 +397,20 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_MIN_EU_IN_POOL	 39
 #define I915_PARAM_MMAP_GTT_VERSION	 40
 
-/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
  * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
  */
 #define I915_PARAM_HAS_SCHEDULER	 41
+#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+
 #define I915_PARAM_HUC_STATUS		 42
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
@@ -1309,14 +1319,16 @@ struct drm_i915_reg_read {
 	 * be specified
 	 */
 	__u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
 	__u64 val; /* Return value */
 };
 /* Known registers:
  *
  * Render engine timestamp - 0x2358 + 64bit - gen7+
  * - Note this register returns an invalid value if using the default
- *   single instruction 8byte read, in order to workaround that use
- *   offset (0x2538 | 1) instead.
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
  *
  */
 
@@ -1359,6 +1371,10 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 #define I915_CONTEXT_PARAM_BANNABLE	0x5
+#define I915_CONTEXT_PARAM_PRIORITY	0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY		0
+#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
 	__u64 value;
 };
 
@@ -1510,9 +1526,14 @@ struct drm_i915_perf_oa_config {
 	__u32 n_boolean_regs;
 	__u32 n_flex_regs;
 
-	__u64 __user mux_regs_ptr;
-	__u64 __user boolean_regs_ptr;
-	__u64 __user flex_regs_ptr;
+	/*
+	 * These fields are pointers to tuples of u32 values (register
+	 * address, value). For example the expected length of the buffer
+	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 */
+	__u64 mux_regs_ptr;
+	__u64 boolean_regs_ptr;
+	__u64 flex_regs_ptr;
 };
 
 #if defined(__cplusplus)
diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h
index 481e103da78e..ef1305010925 100644
--- a/tools/include/uapi/linux/kcmp.h
+++ b/tools/include/uapi/linux/kcmp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_KCMP_H
 #define _UAPI_LINUX_KCMP_H
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7e99999d6236..282d7613fce8 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -931,6 +931,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 362493a2f950..b9a4953018ed 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -942,6 +942,7 @@ enum perf_callchain_context {
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
 #define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION		0x08	/* sample collided with another */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index a8d0759a9e40..af5f8c2df87a 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
@@ -197,4 +198,13 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL			50	/* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL			51	/* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK		0xffff
+# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
 	NULL
 };
 
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+	int i, nr_nodes = 0;
+
+	for (i = 0; i < g->p.nr_nodes; i++) {
+		if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+			nr_nodes++;
+	}
+
+	return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+	return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+	struct bitmask *cpu = numa_allocate_cpumask();
+	unsigned int i;
+
+	if (cpu && !numa_node_to_cpus(node, cpu)) {
+		for (i = 0; i < cpu->size; i++) {
+			if (numa_bitmask_isbitset(cpu, i))
+				return true;
+		}
+	}
+
+	return false; /* lets fall back to nocpus safely */
+}
+
 static cpu_set_t bind_to_cpu(int target_cpu)
 {
 	cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
 
 static cpu_set_t bind_to_node(int target_node)
 {
-	int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+	int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
 	cpu_set_t orig_mask, mask;
 	int cpu;
 	int ret;
 
-	BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+	BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
 	BUG_ON(!cpus_per_node);
 
 	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
 			int i;
 
 			for (i = 0; i < mul; i++) {
-				if (t >= g->p.nr_tasks) {
+				if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
 					printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
 					goto out;
 				}
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	sum = 0;
 
 	for (node = 0; node < g->p.nr_nodes; node++) {
+		if (!is_node_present(node))
+			continue;
 		nr = nodes[node];
 		nr_min = min(nr, nr_min);
 		nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	process_groups = 0;
 
 	for (node = 0; node < g->p.nr_nodes; node++) {
-		int processes = count_node_processes(node);
+		int processes;
 
+		if (!is_node_present(node))
+			continue;
+		processes = count_node_processes(node);
 		nr = nodes[node];
 		tprintf(" %2d/%-2d", nr, processes);
 
@@ -1291,7 +1337,7 @@ static void print_summary(void)
 
 	printf("\n ###\n");
 	printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
-		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
 	printf(" #      %5dx %5ldMB global  shared mem operations\n",
 			g->p.nr_loops, g->p.bytes_global/1024/1024);
 	printf(" #      %5dx %5ldMB process shared mem operations\n",
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index bd1fedef3d1c..a0f7ed2b869b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 		add_man_viewer(value);
 		return 0;
 	}
-	if (!strstarts(var, "man."))
+	if (strstarts(var, "man."))
 		return add_man_viewer_info(var, value);
 
 	return 0;
@@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
 	if (!perf_cmd)
 		return "perf";
-	else if (!strstarts(perf_cmd, "perf"))
+	else if (strstarts(perf_cmd, "perf"))
 		return perf_cmd;
 
 	return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3d7f33e19df2..003255910c05 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -339,6 +339,22 @@ static int record__open(struct record *rec)
 	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
+	/*
+	 * For initial_delay we need to add a dummy event so that we can track
+	 * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+	 * real events, the ones asked by the user.
+	 */
+	if (opts->initial_delay) {
+		if (perf_evlist__add_dummy(evlist))
+			return -ENOMEM;
+
+		pos = perf_evlist__first(evlist);
+		pos->tracking = 0;
+		pos = perf_evlist__last(evlist);
+		pos->tracking = 1;
+		pos->attr.enable_on_exec = 1;
+	}
+
 	perf_evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
@@ -749,17 +765,19 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 	}
 
-	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/kallsyms permission or run as root.\n");
-
-	err = perf_event__synthesize_modules(tool, process_synthesized_event,
-					     machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/modules permission or run as root.\n");
+	if (!perf_evlist__exclude_kernel(rec->evlist)) {
+		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+							 machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/kallsyms permission or run as root.\n");
+
+		err = perf_event__synthesize_modules(tool, process_synthesized_event,
+						     machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/modules permission or run as root.\n");
+	}
 
 	if (perf_guest) {
 		machines__process_guests(&session->machines,
@@ -1693,7 +1711,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = -ENOMEM;
 
-	if (symbol_conf.kptr_restrict)
+	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1394cd8d96f7..af5dd038195e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -441,6 +441,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
 	struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
 	struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
+	if (perf_evlist__exclude_kernel(rep->session->evlist))
+		return;
+
 	if (kernel_map == NULL ||
 	    (kernel_map->dso->hit &&
 	     (kernel_kmap->ref_reloc_sym == NULL ||
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 68f36dc0344f..9b43bda45a41 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1955,6 +1955,16 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script)
 	struct perf_evsel *evsel;
 
 	evlist__for_each_entry(script->session->evlist, evsel) {
+		/*
+		 * Already setup? I.e. we may be called twice in cases like
+		 * Intel PT, one for the intel_pt// and dummy events, then
+		 * for the evsels syntheized from the auxtrace info.
+		 *
+		 * Ses perf_script__process_auxtrace_info.
+		 */
+		if (evsel->priv != NULL)
+			continue;
+
 		evsel->priv = perf_evsel_script__new(evsel, script->session->data);
 		if (evsel->priv == NULL)
 			goto out_err_fclose;
@@ -2838,6 +2848,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_script__process_auxtrace_info(struct perf_tool *tool,
+					      union perf_event *event,
+					      struct perf_session *session)
+{
+	int ret = perf_event__process_auxtrace_info(tool, event, session);
+
+	if (ret == 0) {
+		struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+		ret = perf_script__setup_per_event_dump(script);
+	}
+
+	return ret;
+}
+#else
+#define perf_script__process_auxtrace_info 0
+#endif
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -2866,7 +2895,7 @@ int cmd_script(int argc, const char **argv)
 			.feature	 = perf_event__process_feature,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
-			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace_info	 = perf_script__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
 			.auxtrace_error	 = perf_event__process_auxtrace_error,
 			.stat		 = perf_event__process_stat_event,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 477a8699f0b5..9e0d2645ae13 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -77,6 +77,7 @@
 #include "sane_ctype.h"
 
 static volatile int done;
+static volatile int resize;
 
 #define HEADER_LINE_NR  5
 
@@ -85,11 +86,13 @@ static void perf_top__update_print_entries(struct perf_top *top)
 	top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void perf_top__sig_winch(int sig __maybe_unused,
-				siginfo_t *info __maybe_unused, void *arg)
+static void winch_sig(int sig __maybe_unused)
 {
-	struct perf_top *top = arg;
+	resize = 1;
+}
 
+static void perf_top__resize(struct perf_top *top)
+{
 	get_term_dimensions(&top->winsize);
 	perf_top__update_print_entries(top);
 }
@@ -473,12 +476,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 		case 'e':
 			prompt_integer(&top->print_entries, "Enter display entries (lines)");
 			if (top->print_entries == 0) {
-				struct sigaction act = {
-					.sa_sigaction = perf_top__sig_winch,
-					.sa_flags     = SA_SIGINFO,
-				};
-				perf_top__sig_winch(SIGWINCH, NULL, top);
-				sigaction(SIGWINCH, &act, NULL);
+				perf_top__resize(top);
+				signal(SIGWINCH, winch_sig);
 			} else {
 				signal(SIGWINCH, SIG_DFL);
 			}
@@ -732,14 +731,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
-		ui__warning(
+		if (!perf_evlist__exclude_kernel(top->session->evlist)) {
+			ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
 			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
 			  " modules" : "");
-		if (use_browser <= 0)
-			sleep(5);
+			if (use_browser <= 0)
+				sleep(5);
+		}
 		machine->kptr_restrict_warned = true;
 	}
 
@@ -1030,6 +1031,11 @@ static int __cmd_top(struct perf_top *top)
 
 		if (hits == top->samples)
 			ret = perf_evlist__poll(top->evlist, 100);
+
+		if (resize) {
+			perf_top__resize(top);
+			resize = 0;
+		}
 	}
 
 	ret = 0;
@@ -1352,12 +1358,8 @@ int cmd_top(int argc, const char **argv)
 
 	get_term_dimensions(&top.winsize);
 	if (top.print_entries == 0) {
-		struct sigaction act = {
-			.sa_sigaction = perf_top__sig_winch,
-			.sa_flags     = SA_SIGINFO,
-		};
 		perf_top__update_print_entries(&top);
-		sigaction(SIGWINCH, &act, NULL);
+		signal(SIGWINCH, winch_sig);
 	}
 
 	status = __cmd_top(&top);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f2757d38c7d7..84debdbad327 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1152,12 +1152,14 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
-		return -errno;
+	err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
+	if (err < 0)
+		goto out;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
 					    trace->opts.proc_map_timeout, 1);
+out:
 	if (err)
 		symbol__exit();
 
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 7a84d73324e3..8b3da21a08f1 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,8 +10,8 @@
 
 . $(dirname $0)/lib/probe.sh
 
-ld=$(realpath /lib64/ld*.so.* | uniq)
-libc=$(echo $ld | sed 's/ld/libc/g')
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
 	idx=0
@@ -37,6 +37,9 @@ trace_libc_inet_pton_backtrace() {
 	done
 }
 
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
 skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2e68c5f120da..2a9ef080efd0 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,8 +17,10 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	perf trace -e open touch $file 2>&1 | \
-	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; }
+
+	perf trace -e ${svc:-open} touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a7344e274..89c8e1604ca7 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 	evsel = perf_evlist__first(evlist);
 	evsel->attr.task = 1;
+#ifdef __s390x__
+	evsel->attr.sample_freq = 1000000;
+#else
 	evsel->attr.sample_freq = 1;
+#endif
 	evsel->attr.inherit = 0;
 	evsel->attr.watermark = 0;
 	evsel->attr.wakeup_events = 1;
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9e1668b2c5d7..417e3ecfe9d7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -62,6 +62,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 	P_MMAP_FLAG(POPULATE);
 	P_MMAP_FLAG(STACK);
 	P_MMAP_FLAG(UNINITIALIZED);
+#ifdef MAP_SYNC
+	P_MMAP_FLAG(SYNC);
+#endif
 #undef P_MMAP_FLAG
 
 	if (flags)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index da1c4c4a0dd8..3369c7830260 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -165,7 +165,7 @@ static void ins__delete(struct ins_operands *ops)
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
 			      struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+	return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
@@ -230,12 +230,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
 	if (ops->target.name)
-		return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
 
 	if (ops->target.addr == 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -299,7 +299,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			c++;
 	}
 
-	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+	return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
 			 ins->name, c ? c - ops->raw : 0, ops->raw,
 			 ops->target.offset);
 }
@@ -372,7 +372,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 	if (ops->locked.ins.ops == NULL)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+	printed = scnprintf(bf, size, "%-6s ", ins->name);
 	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
 					size - printed, ops->locked.ops);
 }
@@ -448,7 +448,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+	return scnprintf(bf, size, "%-6s %s,%s", ins->name,
 			 ops->source.name ?: ops->source.raw,
 			 ops->target.name ?: ops->target.raw);
 }
@@ -488,7 +488,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name,
+	return scnprintf(bf, size, "%-6s %s", ins->name,
 			 ops->target.name ?: ops->target.raw);
 }
 
@@ -500,7 +500,7 @@ static struct ins_ops dec_ops = {
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
 			  struct ins_operands *ops __maybe_unused)
 {
-	return scnprintf(bf, size, "%-6.6s", "nop");
+	return scnprintf(bf, size, "%-6s", "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -924,7 +924,7 @@ void disasm_line__free(struct disasm_line *dl)
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
 {
 	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw);
+		return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
 
 	return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e154a6..b62e523a7035 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -257,7 +257,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist)
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
 	};
-	struct perf_evsel *evsel = perf_evsel__new(&attr);
+	struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
 
 	if (evsel == NULL)
 		return -ENOMEM;
@@ -1786,3 +1786,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 state_err:
 	return;
 }
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel->attr.exclude_kernel)
+			return false;
+	}
+
+	return true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e72ae64c11ac..491f69542920 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -312,4 +312,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
 struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f894893c203d..d5fbcf8c7aa7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -733,12 +733,16 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	list_for_each_entry(term, config_terms, list) {
 		switch (term->type) {
 		case PERF_EVSEL__CONFIG_TERM_PERIOD:
-			attr->sample_period = term->val.period;
-			attr->freq = 0;
+			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
+				attr->sample_period = term->val.period;
+				attr->freq = 0;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
-			attr->sample_freq = term->val.freq;
-			attr->freq = 1;
+			if (!(term->weak && opts->user_freq != UINT_MAX)) {
+				attr->sample_freq = term->val.freq;
+				attr->freq = 1;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
 			if (term->val.time)
@@ -1371,7 +1375,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader,
 static int
 perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
 {
-	struct perf_stat_evsel *ps = leader->priv;
+	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->attr.read_format;
 	int size = perf_evsel__read_size(leader);
 	u64 *data = ps->group_data;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9277df96ffda..157f49e8a772 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -67,6 +67,7 @@ struct perf_evsel_config_term {
 		bool	overwrite;
 		char	*branch;
 	} val;
+	bool weak;
 };
 
 struct perf_stat_evsel;
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 125ecd2a300d..52dc8d911173 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE	0
+#define INAT_SEG_REG_DEFAULT	1
+#define INAT_SEG_REG_CS		2
+#define INAT_SEG_REG_SS		3
+#define INAT_SEG_REG_DS		4
+#define INAT_SEG_REG_ES		5
+#define INAT_SEG_REG_FS		6
+#define INAT_SEG_REG_GS		7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index 12e377184ee4..c4d55919fac1 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6a8d03c3d9b7..270f3223c6df 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -172,6 +172,9 @@ void machine__exit(struct machine *machine)
 {
 	int i;
 
+	if (machine == NULL)
+		return;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a7fcd95961ef..170316795a18 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1116,6 +1116,7 @@ do {								\
 	INIT_LIST_HEAD(&__t->list);				\
 	__t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;	\
 	__t->val.__name = __val;				\
+	__t->weak	= term->weak;				\
 	list_add_tail(&__t->list, head_terms);			\
 } while (0)
 
@@ -2410,6 +2411,7 @@ static int new_term(struct parse_events_term **_term,
 
 	*term = *temp;
 	INIT_LIST_HEAD(&term->list);
+	term->weak = false;
 
 	switch (term->type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index be337c266697..88108cd11b4c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -101,6 +101,9 @@ struct parse_events_term {
 	/* error string indexes for within parsed string */
 	int err_term;
 	int err_val;
+
+	/* Coming from implicit alias */
+	bool weak;
 };
 
 struct parse_events_error {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 07cb2ac041d7..80fb1593913a 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -405,6 +405,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 			parse_events_terms__purge(&list);
 			return ret;
 		}
+		/*
+		 * Weak terms don't override command line options,
+		 * which we don't want for implicit terms in aliases.
+		 */
+		cloned->weak = true;
 		list_add_tail(&cloned->list, &list);
 	}
 	list_splice(&list, terms);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-11-26 12:40 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-11-26 12:40 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4a31b424ac0656d1bb17520ee861144fe7a19664 perf/core: Fix memory leak triggered by perf --namespace

Misc fixes: two PMU driver fixes and a memory leak fix.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86/intel: Hide TSX events when RTM is not supported

Kan Liang (1):
      perf/x86/intel/uncore: Add event constraint for BDX PCU

Vasily Averin (1):
      perf/core: Fix memory leak triggered by perf --namespace


 arch/x86/events/intel/core.c         | 35 +++++++++++++++++++++++------------
 arch/x86/events/intel/uncore_snbep.c |  8 ++++++++
 kernel/events/core.c                 |  1 +
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9fb9a1f1e47b..f94855000d4e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3730,6 +3730,19 @@ EVENT_ATTR_STR(cycles-t,	cycles_t,	"event=0x3c,in_tx=1");
 EVENT_ATTR_STR(cycles-ct,	cycles_ct,	"event=0x3c,in_tx=1,in_tx_cp=1");
 
 static struct attribute *hsw_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
+	NULL
+};
+
+static struct attribute *hsw_tsx_events_attrs[] = {
 	EVENT_PTR(tx_start),
 	EVENT_PTR(tx_commit),
 	EVENT_PTR(tx_abort),
@@ -3742,18 +3755,16 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(el_conflict),
 	EVENT_PTR(cycles_t),
 	EVENT_PTR(cycles_ct),
-	EVENT_PTR(mem_ld_hsw),
-	EVENT_PTR(mem_st_hsw),
-	EVENT_PTR(td_slots_issued),
-	EVENT_PTR(td_slots_retired),
-	EVENT_PTR(td_fetch_bubbles),
-	EVENT_PTR(td_total_slots),
-	EVENT_PTR(td_total_slots_scale),
-	EVENT_PTR(td_recovery_bubbles),
-	EVENT_PTR(td_recovery_bubbles_scale),
 	NULL
 };
 
+static __init struct attribute **get_hsw_events_attrs(void)
+{
+	return boot_cpu_has(X86_FEATURE_RTM) ?
+		merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
+		hsw_events_attrs;
+}
+
 static ssize_t freeze_on_smi_show(struct device *cdev,
 				  struct device_attribute *attr,
 				  char *buf)
@@ -4182,7 +4193,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.cpu_events = get_hsw_events_attrs();
 		x86_pmu.lbr_double_abort = true;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
@@ -4221,7 +4232,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.cpu_events = get_hsw_events_attrs();
 		x86_pmu.limit_period = bdw_limit_period;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
@@ -4279,7 +4290,7 @@ __init int intel_pmu_init(void)
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
 		extra_attr = merge_attr(extra_attr, skl_format_attr);
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.cpu_events = get_hsw_events_attrs();
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
 		pr_cont("Skylake events, ");
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 95cb19f4e06f..f4e4168455a8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3035,11 +3035,19 @@ static struct intel_uncore_type *bdx_msr_uncores[] = {
 	NULL,
 };
 
+/* Bit 7 'Use Occupancy' is not available for counter 0 on BDX */
+static struct event_constraint bdx_uncore_pcu_constraints[] = {
+	EVENT_CONSTRAINT(0x80, 0xe, 0x80),
+	EVENT_CONSTRAINT_END
+};
+
 void bdx_uncore_cpu_init(void)
 {
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
+
+	hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 10cdb9c26b5d..ab5ac84f82e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6756,6 +6756,7 @@ static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
 		ns_inode = ns_path.dentry->d_inode;
 		ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev);
 		ns_link_info->ino = ns_inode->i_ino;
+		path_put(&ns_path);
 	}
 }
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2017-11-05 14:40 Ingo Molnar
@ 2017-11-09  8:13 ` Markus Trippelsdorf
  0 siblings, 0 replies; 376+ messages in thread
From: Markus Trippelsdorf @ 2017-11-09  8:13 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton,
	Jiri Olsa

On 2017.11.05 at 15:40 +0100, Ingo Molnar wrote:
> Linus,
>
> Please pull the latest perf-urgent-for-linus git tree from:
>
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
>
> Jiri Olsa (1):
>       perf tools: Unwind properly location after REJECT

The patch above breaks the build for me:

util/parse-events.l: In function ‘parse_events_lex’:
util/parse-events-flex.c:4722:16: error: ‘reject_used_but_not_detected’ undeclared (first use in this function)
  */
                ^
util/parse-events.l:159:2: note: in expansion of macro ‘REJECT’
  REJECT
  ^~~~~~
util/parse-events.l:343:26: note: in expansion of macro ‘USER_REJECT’
 {bpf_source}  { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
                          ^~~~~~~~~~~
util/parse-events-flex.c:4722:16: note: each undeclared identifier is reported only once for each function it appears in
  */
                ^
util/parse-events.l:159:2: note: in expansion of macro ‘REJECT’
  REJECT
  ^~~~~~
util/parse-events.l:343:26: note: in expansion of macro ‘USER_REJECT’
 {bpf_source}  { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
                          ^~~~~~~~~~~
mv: cannot stat 'util/.parse-events-flex.o.tmp': No such file or directory

--
Markus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-11-05 14:40 Ingo Molnar
  2017-11-09  8:13 ` Markus Trippelsdorf
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2017-11-05 14:40 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: fb7df12d645cfba6a76a45fdcc7e3f7fbbcda661 tools/headers: Synchronize kernel ABI headers

Various fixes:

 - synchronize kernel and tooling headers

 - cgroup support fix

 - two tooling fixes

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      tools/headers: Synchronize kernel ABI headers

Jiri Olsa (1):
      perf tools: Unwind properly location after REJECT

Ravi Bangoria (1):
      perf symbols: Fix memory corruption because of zero length symbols

Tejun Heo (1):
      perf/cgroup: Fix perf cgroup hierarchy support


 include/uapi/sound/asound.h                      |  6 +++---
 kernel/events/core.c                             |  6 ++++--
 tools/arch/x86/include/asm/disabled-features.h   |  1 -
 tools/arch/x86/include/asm/required-features.h   |  1 -
 tools/arch/x86/include/uapi/asm/unistd.h         |  1 +
 tools/arch/x86/lib/memcpy_64.S                   |  5 ++++-
 tools/include/asm-generic/bitops/__fls.h         |  1 +
 tools/include/asm-generic/bitops/arch_hweight.h  |  1 +
 tools/include/asm-generic/bitops/const_hweight.h |  1 +
 tools/include/asm-generic/bitops/fls.h           |  1 +
 tools/include/asm-generic/bitops/fls64.h         |  1 +
 tools/include/asm/export.h                       |  7 +++++++
 tools/include/linux/hash.h                       |  1 -
 tools/include/uapi/asm-generic/ioctls.h          |  1 +
 tools/include/uapi/asm-generic/mman-common.h     |  1 +
 tools/include/uapi/asm-generic/mman.h            |  4 ++--
 tools/include/uapi/linux/bpf.h                   |  4 ++--
 tools/include/uapi/linux/bpf_common.h            |  2 +-
 tools/include/uapi/linux/fcntl.h                 |  2 +-
 tools/include/uapi/linux/hw_breakpoint.h         |  2 +-
 tools/include/uapi/linux/kvm.h                   |  1 +
 tools/include/uapi/linux/mman.h                  |  2 +-
 tools/include/uapi/linux/perf_event.h            |  1 +
 tools/include/uapi/linux/sched.h                 |  1 +
 tools/include/uapi/linux/stat.h                  |  2 +-
 tools/include/uapi/linux/vhost.h                 |  1 +
 tools/include/uapi/sound/asound.h                |  1 +
 tools/perf/util/annotate.c                       | 12 +++++++++++-
 tools/perf/util/parse-events.l                   |  8 ++++++--
 29 files changed, 57 insertions(+), 21 deletions(-)
 create mode 100644 tools/include/asm/export.h

diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 299a822d2c4e..c227ccba60ae 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -94,7 +94,7 @@ enum {
 	SNDRV_HWDEP_IFACE_VX,		/* Digigram VX cards */
 	SNDRV_HWDEP_IFACE_MIXART,	/* Digigram miXart cards */
 	SNDRV_HWDEP_IFACE_USX2Y,	/* Tascam US122, US224 & US428 usb */
-	SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */	
+	SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */
 	SNDRV_HWDEP_IFACE_BLUETOOTH,	/* Bluetooth audio */
 	SNDRV_HWDEP_IFACE_USX2Y_PCM,	/* Tascam US122, US224 & US428 rawusb pcm */
 	SNDRV_HWDEP_IFACE_PCXHR,	/* Digigram PCXHR */
@@ -384,7 +384,7 @@ struct snd_mask {
 
 struct snd_pcm_hw_params {
 	unsigned int flags;
-	struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - 
+	struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK -
 			       SNDRV_PCM_HW_PARAM_FIRST_MASK + 1];
 	struct snd_mask mres[5];	/* reserved masks */
 	struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL -
@@ -857,7 +857,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_INACTIVE		(1<<8)	/* control does actually nothing, but may be updated */
 #define SNDRV_CTL_ELEM_ACCESS_LOCK		(1<<9)	/* write lock */
 #define SNDRV_CTL_ELEM_ACCESS_OWNER		(1<<10)	/* write lock owner */
-#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK	(1<<28)	/* kernel use a TLV callback */ 
+#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK	(1<<28)	/* kernel use a TLV callback */
 #define SNDRV_CTL_ELEM_ACCESS_USER		(1<<29) /* user space element */
 /* bits 30 and 31 are obsoleted (for indirect access) */
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d93db81fa36..10cdb9c26b5d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -901,9 +901,11 @@ list_update_cgroup_event(struct perf_event *event,
 	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
 	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
 	if (add) {
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+
 		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
-		if (perf_cgroup_from_task(current, ctx) == event->cgrp)
-			cpuctx->cgrp = event->cgrp;
+		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+			cpuctx->cgrp = cgrp;
 	} else {
 		list_del(cpuctx_entry);
 		cpuctx->cgrp = NULL;
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c1a6d5d0da0d..c10c9128f54e 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -1,4 +1,3 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_DISABLED_FEATURES_H
 #define _ASM_X86_DISABLED_FEATURES_H
 
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 59ac6baafb6a..d91ba04dd007 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -1,4 +1,3 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_REQUIRED_FEATURES_H
 #define _ASM_X86_REQUIRED_FEATURES_H
 
diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h
index a26df0d75cd0..30d7d04d72d6 100644
--- a/tools/arch/x86/include/uapi/asm/unistd.h
+++ b/tools/arch/x86/include/uapi/asm/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_ASM_X86_UNISTD_H
 #define _UAPI_ASM_X86_UNISTD_H
 
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index ecf2c2067281..9a53a06e5a3e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -1,10 +1,10 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen */
 
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
+#include <asm/export.h>
 
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
@@ -41,6 +41,8 @@ ENTRY(memcpy)
 	ret
 ENDPROC(memcpy)
 ENDPROC(__memcpy)
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(__memcpy)
 
 /*
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
@@ -275,6 +277,7 @@ ENTRY(memcpy_mcsafe_unrolled)
 	xorq %rax, %rax
 	ret
 ENDPROC(memcpy_mcsafe_unrolled)
+EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
 
 	.section .fixup, "ax"
 	/* Return -EFAULT for any failure */
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index a60a7ccb6782..03f721a8a2b1 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS___FLS_H_
 #define _ASM_GENERIC_BITOPS___FLS_H_
 
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
index 6a211f40665c..c2705e1d220d 100644
--- a/tools/include/asm-generic/bitops/arch_hweight.h
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
index 0a7e06623470..149faeeeeaf2 100644
--- a/tools/include/asm-generic/bitops/const_hweight.h
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index 0576d1f42f43..753aecaab641 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_FLS_H_
 #define _ASM_GENERIC_BITOPS_FLS_H_
 
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index b097cf8444e3..866f2b2304ff 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_FLS64_H_
 #define _ASM_GENERIC_BITOPS_FLS64_H_
 
diff --git a/tools/include/asm/export.h b/tools/include/asm/export.h
new file mode 100644
index 000000000000..2cb1a0d83035
--- /dev/null
+++ b/tools/include/asm/export.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_ASM_EXPORT_H
+#define _TOOLS_ASM_EXPORT_H
+
+#define EXPORT_SYMBOL(x)
+#define EXPORT_SYMBOL_GPL(x)
+
+#endif /* _TOOLS_ASM_EXPORT_H */
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
index 2c4183bbc504..ad6fa21d977b 100644
--- a/tools/include/linux/hash.h
+++ b/tools/include/linux/hash.h
@@ -1,4 +1,3 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_HASH_H
 #define _LINUX_HASH_H
 /* Fast hashing routine for ints,  longs and pointers.
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
index 14baf9f23a14..040651735662 100644
--- a/tools/include/uapi/asm-generic/ioctls.h
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_IOCTLS_H
 #define __ASM_GENERIC_IOCTLS_H
 
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 203268f9231e..6d319c46fd90 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_MMAN_COMMON_H
 #define __ASM_GENERIC_MMAN_COMMON_H
 
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index f7c7b4355e56..2dffcbf705b3 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -1,8 +1,8 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <uapi/asm-generic/mman-common.h>
+#include <asm-generic/mman-common.h>
 
 #define MAP_GROWSDOWN	0x0100		/* stack-like segment */
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 01cc7ba39924..30f2ce76b517 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  *
  * This program is free software; you can redistribute it and/or
@@ -569,10 +570,9 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(skb, map, key, flags)
+ * int bpf_sk_redirect_map(map, key, flags)
  *     Redirect skb to a sock in map using key as a lookup key for the
  *     sock in map.
- *     @skb: pointer to skb
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h
index 64ba734aba80..18be90725ab0 100644
--- a/tools/include/uapi/linux/bpf_common.h
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI__LINUX_BPF_COMMON_H__
 #define _UAPI__LINUX_BPF_COMMON_H__
 
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index b6705247afe8..6448cdd9a350 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_FCNTL_H
 #define _UAPI_LINUX_FCNTL_H
 
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
index 6394ea9d5524..965e4d8606d8 100644
--- a/tools/include/uapi/linux/hw_breakpoint.h
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_HW_BREAKPOINT_H
 #define _UAPI_LINUX_HW_BREAKPOINT_H
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 838887587411..7e99999d6236 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __LINUX_KVM_H
 #define __LINUX_KVM_H
 
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 64d2b4e556e5..bfd5938fede6 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_MMAN_H
 #define _UAPI_LINUX_MMAN_H
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 140ae638cfd6..362493a2f950 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Performance events:
  *
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index e2a6c7b3510b..30a9e51bbb1e 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_SCHED_H
 #define _UAPI_LINUX_SCHED_H
 
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 9eac599afd91..7b35e98d3c58 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_STAT_H
 #define _UAPI_LINUX_STAT_H
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 60180c0b5dc6..c51f8e5cc608 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_VHOST_H
 #define _LINUX_VHOST_H
 /* Userspace interface for in-kernel virtio accelerators. */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 87bf30b182df..c227ccba60ae 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
 /*
  *  Advanced Linux Sound Architecture - ALSA - Driver
  *  Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>,
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4397a8b6e6cd..aa66791b1bfc 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -606,9 +606,19 @@ static struct arch *arch__find(const char *name)
 int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	const size_t size = symbol__size(sym);
+	size_t size = symbol__size(sym);
 	size_t sizeof_sym_hist;
 
+	/*
+	 * Add buffer of one element for zero length symbol.
+	 * When sample is taken from first instruction of
+	 * zero length symbol, perf still resolves it and
+	 * shows symbol name in perf report and allows to
+	 * annotate it.
+	 */
+	if (size == 0)
+		size = 1;
+
 	/* Check for overflow when calculating sizeof_sym_hist */
 	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry))
 		return -1;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index dcfdafdc2f1c..6680e4fb7967 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -154,6 +154,10 @@ do {							\
 	yycolumn += yyleng;				\
 } while (0);
 
+#define USER_REJECT		\
+	yycolumn -= yyleng;	\
+	REJECT
+
 %}
 
 %x mem
@@ -335,8 +339,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}		{ if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}		{ if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-10-14 16:04 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-10-14 16:04 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 47a74bdcbfeff543f706dc0e385eebbb5d655ed2 Merge tag 'perf-urgent-for-mingo-4.14-20171010' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Some tooling fixes plus three kernel fixes: a memory leak fix, a statistics fix 
and a crash fix.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools include uapi bpf.h: Sync kernel ABI header with tooling header

Colin Ian King (1):
      perf/x86/intel/uncore: Fix memory leaks on allocation failures

Mark Rutland (1):
      perf pmu: Unbreak perf record for arm/arm64 with events with explicit PMU

Mark Santaniello (1):
      perf script: Add missing separator for "-F ip,brstack" (and brstackoff)

Ravi Bangoria (1):
      perf callchain: Compare dsos (as well) for CCKEY_FUNCTION

Will Deacon (1):
      perf/core: Avoid freeing static PMU contexts when PMU is unregistered

leilei.lin (1):
      perf/core: Fix cgroup time when scheduling descendants


 arch/x86/events/intel/uncore.c | 12 +++++++--
 kernel/events/core.c           | 10 +++++++-
 tools/include/uapi/linux/bpf.h |  2 +-
 tools/perf/builtin-script.c    |  4 +--
 tools/perf/util/callchain.c    |  6 ++++-
 tools/perf/util/parse-events.c |  9 ++++---
 tools/perf/util/pmu.c          | 56 +++++++++++++++++++++++++++++++-----------
 tools/perf/util/pmu.h          |  1 +
 8 files changed, 74 insertions(+), 26 deletions(-)

diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 1c5390f1cf09..d45e06346f14 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
 		if (!pmus[i].boxes)
-			return -ENOMEM;
+			goto err;
 	}
 
 	type->pmus = pmus;
@@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 		attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
 					sizeof(*attr_group), GFP_KERNEL);
 		if (!attr_group)
-			return -ENOMEM;
+			goto err;
 
 		attrs = (struct attribute **)(attr_group + 1);
 		attr_group->name = "events";
@@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
+
 	return 0;
+
+err:
+	for (i = 0; i < type->num_boxes; i++)
+		kfree(pmus[i].boxes);
+	kfree(pmus);
+
+	return -ENOMEM;
 }
 
 static int __init
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6bc21e202ae4..9d93db81fa36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgrp == event->cgrp)
+       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
@@ -8955,6 +8955,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 
 static void free_pmu_context(struct pmu *pmu)
 {
+	/*
+	 * Static contexts such as perf_sw_context have a global lifetime
+	 * and may be shared between different PMUs. Avoid freeing them
+	 * when a single PMU is going away.
+	 */
+	if (pmu->task_ctx_nr > perf_invalid_context)
+		return;
+
 	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
 	mutex_unlock(&pmus_lock);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 43ab5c402f98..f90860d1f897 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -312,7 +312,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3d4c3b5e1868..0c977b6e0f8b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -586,7 +586,7 @@ static void print_sample_brstack(struct perf_sample *sample,
 			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		}
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
@@ -681,7 +681,7 @@ static void print_sample_brstackoff(struct perf_sample *sample,
 		if (alt.map && !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index be09d77cade0..a971caf3759d 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -685,6 +685,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
+	struct dso *left_dso = NULL;
+	struct dso *right_dso = NULL;
 
 	if (callchain_param.key == CCKEY_SRCLINE) {
 		enum match_result match = match_chain_srcline(node, cnode);
@@ -696,12 +698,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
+		left_dso = cnode->ms.map->dso;
+		right_dso = node->map->dso;
 	} else {
 		left = cnode->ip;
 		right = node->ip;
 	}
 
-	if (left == right) {
+	if (left == right && left_dso == right_dso) {
 		if (node->branch) {
 			cnode->branch_count++;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f6257fb4f08c..39b15968eab1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -309,10 +309,11 @@ static char *get_config_name(struct list_head *head_terms)
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
-	    char *name, struct cpu_map *cpus,
+	    char *name, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats)
 {
 	struct perf_evsel *evsel;
+	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
 	event_attr_init(attr);
 
@@ -323,7 +324,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->cpus        = cpu_map__get(cpus);
 	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = !!cpus;
+	evsel->system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
@@ -1233,7 +1234,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1254,7 +1255,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
-			    get_config_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats);
 	if (evsel) {
 		evsel->unit = info.unit;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ac16a9db1fb5..1c4d7b4e4fb5 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -470,17 +470,36 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
+static struct cpu_map *__pmu_cpumask(const char *path)
+{
+	FILE *file;
+	struct cpu_map *cpus;
+
+	file = fopen(path, "r");
+	if (!file)
+		return NULL;
+
+	cpus = cpu_map__read(file);
+	fclose(file);
+	return cpus;
+}
+
+/*
+ * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
+ * may have a "cpus" file.
+ */
+#define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
+#define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
+
 static struct cpu_map *pmu_cpumask(const char *name)
 {
-	struct stat st;
 	char path[PATH_MAX];
-	FILE *file;
 	struct cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
 	const char *templates[] = {
-		 "%s/bus/event_source/devices/%s/cpumask",
-		 "%s/bus/event_source/devices/%s/cpus",
-		 NULL
+		CPUS_TEMPLATE_UNCORE,
+		CPUS_TEMPLATE_CPU,
+		NULL
 	};
 	const char **template;
 
@@ -489,20 +508,25 @@ static struct cpu_map *pmu_cpumask(const char *name)
 
 	for (template = templates; *template; template++) {
 		snprintf(path, PATH_MAX, *template, sysfs, name);
-		if (stat(path, &st) == 0)
-			break;
+		cpus = __pmu_cpumask(path);
+		if (cpus)
+			return cpus;
 	}
 
-	if (!*template)
-		return NULL;
+	return NULL;
+}
 
-	file = fopen(path, "r");
-	if (!file)
-		return NULL;
+static bool pmu_is_uncore(const char *name)
+{
+	char path[PATH_MAX];
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
 
-	cpus = cpu_map__read(file);
-	fclose(file);
-	return cpus;
+	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
+	cpus = __pmu_cpumask(path);
+	cpu_map__put(cpus);
+
+	return !!cpus;
 }
 
 /*
@@ -617,6 +641,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
 
 	pmu->cpus = pmu_cpumask(name);
 
+	pmu->is_uncore = pmu_is_uncore(name);
+
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 389e9729331f..fe0de0502ce2 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,7 @@ struct perf_pmu {
 	char *name;
 	__u32 type;
 	bool selectable;
+	bool is_uncore;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-09-13 18:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-09-13 18:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Andrew Morton, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b130a699c07155a1d6ef7d971a5f3bf0e3818d5a Merge tag 'perf-urgent-for-mingo-4.14-20170912' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

A handful of tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools include linux: Guard against redefinition of some macros

Jiri Olsa (4):
      tools lib api: Fix make DEBUG=1 build
      perf tools: Open perf.data with O_CLOEXEC flag
      perf ui progress: Make sure we always define step value
      perf ui progress: Fix progress update

Milian Wolff (3):
      perf tests: Fix compile when libunwind's unwind.h is available
      perf tools: Support running perf binaries with a dash in their name
      perf stat: Wait for the correct child

Taeung Song (1):
      perf config: Check not only section->from_system_config but also item's


 tools/include/linux/compiler-gcc.h |  9 ++++++---
 tools/lib/api/Makefile             |  8 +++++++-
 tools/perf/builtin-config.c        |  2 +-
 tools/perf/builtin-stat.c          |  2 +-
 tools/perf/perf.c                  | 14 ++++++++++----
 tools/perf/tests/dwarf-unwind.c    |  2 +-
 tools/perf/ui/progress.c           |  9 +++++++--
 tools/perf/util/data.c             | 13 ++++++++++++-
 8 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index bd39b2090ad1..3723b9f8f964 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -21,11 +21,14 @@
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
 #define  noinline	__attribute__((noinline))
-
+#ifndef __packed
 #define __packed	__attribute__((packed))
-
+#endif
+#ifndef __noreturn
 #define __noreturn	__attribute__((noreturn))
-
+#endif
+#ifndef __aligned
 #define __aligned(x)	__attribute__((aligned(x)))
+#endif
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 #define __scanf(a, b)	__attribute__((format(scanf, a, b)))
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 4563ba7ede6f..1e83e3c07448 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -17,13 +17,19 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC
 
+ifeq ($(DEBUG),0)
 ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
 endif
+endif
+
+ifeq ($(DEBUG),0)
+  CFLAGS += -D_FORTIFY_SOURCE
+endif
 
 # Treat warnings as errors unless directed not to
 ifneq ($(WERROR),0)
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 3ddcc6e2abeb..a1d82e33282c 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -59,7 +59,7 @@ static int set_config(struct perf_config_set *set, const char *file_name,
 		fprintf(fp, "[%s]\n", section->name);
 
 		perf_config_items__for_each_entry(&section->items, item) {
-			if (!use_system_config && section->from_system_config)
+			if (!use_system_config && item->from_system_config)
 				continue;
 			if (item->value)
 				fprintf(fp, "\t%s = %s\n",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 85e992d9215b..69523ed55894 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -707,7 +707,7 @@ static int __run_perf_stat(int argc, const char **argv)
 				process_interval();
 			}
 		}
-		wait(&status);
+		waitpid(child_pid, &status, 0);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index e0279babe0c0..2f19e03c5c40 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -467,15 +467,21 @@ int main(int argc, const char **argv)
 	 *  - cannot execute it externally (since it would just do
 	 *    the same thing over again)
 	 *
-	 * So we just directly call the internal command handler, and
-	 * die if that one cannot handle it.
+	 * So we just directly call the internal command handler. If that one
+	 * fails to handle this, then maybe we just run a renamed perf binary
+	 * that contains a dash in its name. To handle this scenario, we just
+	 * fall through and ignore the "xxxx" part of the command string.
 	 */
 	if (strstarts(cmd, "perf-")) {
 		cmd += 5;
 		argv[0] = cmd;
 		handle_internal_command(argc, argv);
-		fprintf(stderr, "cannot handle %s internally", cmd);
-		goto out;
+		/*
+		 * If the command is handled, the above function does not
+		 * return undo changes and fall through in such a case.
+		 */
+		cmd -= 5;
+		argv[0] = cmd;
 	}
 	if (strstarts(cmd, "trace")) {
 #ifdef HAVE_LIBAUDIT_SUPPORT
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2a7b9b47bbcb..9ba1d216a89f 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -6,7 +6,7 @@
 #include "debug.h"
 #include "machine.h"
 #include "event.h"
-#include "unwind.h"
+#include "../util/unwind.h"
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index a0f24c7115c5..ae91c8148edf 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "progress.h"
 
@@ -14,10 +15,14 @@ struct ui_progress_ops *ui_progress__ops = &null_progress__ops;
 
 void ui_progress__update(struct ui_progress *p, u64 adv)
 {
+	u64 last = p->curr;
+
 	p->curr += adv;
 
 	if (p->curr >= p->next) {
-		p->next += p->step;
+		u64 nr = DIV_ROUND_UP(p->curr - last, p->step);
+
+		p->next += nr * p->step;
 		ui_progress__ops->update(p);
 	}
 }
@@ -25,7 +30,7 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
 void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
 {
 	p->curr = 0;
-	p->next = p->step = total / 16;
+	p->next = p->step = total / 16 ?: 1;
 	p->total = total;
 	p->title = title;
 
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e84bbc8ec058..263f5a906ba5 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -10,6 +10,16 @@
 #include "util.h"
 #include "debug.h"
 
+#ifndef O_CLOEXEC
+#ifdef __sparc__
+#define O_CLOEXEC	0x400000
+#elif defined(__alpha__) || defined(__hppa__)
+#define O_CLOEXEC	010000000
+#else
+#define O_CLOEXEC	02000000
+#endif
+#endif
+
 static bool check_pipe(struct perf_data_file *file)
 {
 	struct stat st;
@@ -96,7 +106,8 @@ static int open_file_write(struct perf_data_file *file)
 	if (check_backup(file))
 		return -1;
 
-	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+		  S_IRUSR|S_IWUSR);
 
 	if (fd < 0)
 		pr_err("failed to open %s : %s\n", file->path,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-09-12 15:32 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-09-12 15:32 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 770e96125515daf1c7bc179323f2e0d488dfe6ac Merge tag 'perf-core-for-mingo-4.14-20170901' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Perf tooling updates and fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf syscalltbl: Support glob matching on syscall names
      perf trace: Support syscall name globbing
      perf stat: Only auto-merge events that are PMU aliases
      perf annotate browser: Help for cycling thru hottest instructions with TAB/shift+TAB

Jack Henschel (1):
      perf intel-pt: Fix syntax in documentation of config option

Jin Yao (1):
      perf report: Calculate the average cycles of iterations

Kan Liang (5):
      perf tools: Support new sample type for physical address
      perf sort: Add sort option for physical address
      perf mem: Support physical address
      perf script: Support physical address
      perf test: Add test case for PERF_SAMPLE_PHYS_ADDR

Ravi Bangoria (1):
      perf test powerpc: Fix 'Object code reading' test

Sukadev Bhattiprolu (1):
      perf vendor events powerpc: Remove duplicate events


 tools/include/uapi/linux/perf_event.h              |   4 +-
 tools/perf/Documentation/intel-pt.txt              |   2 +-
 tools/perf/Documentation/perf-mem.txt              |   4 +
 tools/perf/Documentation/perf-record.txt           |   5 +-
 tools/perf/Documentation/perf-report.txt           |   1 +
 tools/perf/Documentation/perf-script.txt           |   2 +-
 tools/perf/Documentation/perf-trace.txt            |   2 +-
 tools/perf/builtin-mem.c                           |  97 ++++++++++++-----
 tools/perf/builtin-record.c                        |   2 +
 tools/perf/builtin-script.c                        |  15 ++-
 tools/perf/builtin-stat.c                          |   2 +-
 tools/perf/builtin-trace.c                         |  39 ++++++-
 tools/perf/perf.h                                  |   1 +
 .../pmu-events/arch/powerpc/power9/frontend.json   |   7 +-
 .../perf/pmu-events/arch/powerpc/power9/other.json | 120 ---------------------
 .../pmu-events/arch/powerpc/power9/pipeline.json   |   7 +-
 tools/perf/pmu-events/arch/powerpc/power9/pmc.json |   7 +-
 tools/perf/tests/code-reading.c                    |   5 +
 tools/perf/tests/sample-parsing.c                  |   6 +-
 tools/perf/ui/browsers/annotate.c                  |   3 +-
 tools/perf/ui/browsers/hists.c                     |   8 +-
 tools/perf/ui/stdio/hist.c                         |  10 +-
 tools/perf/util/callchain.c                        |  49 ++++-----
 tools/perf/util/callchain.h                        |   9 +-
 tools/perf/util/event.h                            |   1 +
 tools/perf/util/evsel.c                            |  19 +++-
 tools/perf/util/evsel.h                            |   1 +
 tools/perf/util/hist.c                             |   4 +
 tools/perf/util/hist.h                             |   1 +
 tools/perf/util/machine.c                          |  96 ++++++++++-------
 tools/perf/util/parse-events.c                     |  24 +++--
 tools/perf/util/session.c                          |   3 +
 tools/perf/util/sort.c                             |  42 ++++++++
 tools/perf/util/sort.h                             |   1 +
 tools/perf/util/symbol.h                           |   1 +
 tools/perf/util/syscalltbl.c                       |  33 ++++++
 tools/perf/util/syscalltbl.h                       |   3 +
 37 files changed, 368 insertions(+), 268 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-07-21 10:15 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-07-21 10:15 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: df6c3db8d30fb1699ccbc403196b86324f4257af perf/x86/intel: Add proper condition to run sched_task callbacks

Two hw-enablement patches, two race fixes, three fixes for regressions of 
semantics, plus a number of tooling fixes.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Fix scheduling regression of pinned groups

Arnaldo Carvalho de Melo (3):
      perf evsel: Fix attr.exclude_kernel setting for default cycles:p
      perf evsel: State in the default event name if attr.exclude_kernel is set
      perf symbols: Accept zero as the kernel base address

Harry Pan (1):
      perf/x86/intel: Enable C-state residency events for Apollo Lake

Ingo Molnar (1):
      Revert "perf/core: Drop kernel samples even though :u is specified"

Jin Yao (1):
      perf annotate: Fix broken arrow at row 0 connecting jmp instruction to its target

Jiri Olsa (3):
      perf/x86/intel: Fix debug_store reset field for freq events
      perf/core: Fix locking for children siblings group read
      perf/x86/intel: Add proper condition to run sched_task callbacks

Kan Liang (1):
      perf/x86/intel: Add Goldmont Plus CPU PMU support


 arch/x86/events/intel/core.c   | 164 ++++++++++++++++++++++++++++++++++++++++-
 arch/x86/events/intel/cstate.c |  26 +++++--
 arch/x86/events/intel/ds.c     |  22 ++++--
 arch/x86/events/intel/lbr.c    |   4 +
 arch/x86/events/perf_event.h   |   2 +
 kernel/events/core.c           |  33 +++------
 tools/perf/ui/browser.c        |   2 +-
 tools/perf/util/evsel.c        |   8 +-
 tools/perf/util/machine.c      |   2 +-
 9 files changed, 221 insertions(+), 42 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index aa62437d1aa1..98b0f0729527 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1708,6 +1708,120 @@ static __initconst const u64 glm_hw_cache_extra_regs
 	},
 };
 
+static __initconst const u64 glp_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x0380,	/* ICACHE.ACCESSES */
+			[C(RESULT_MISS)]	= 0x0280,	/* ICACHE.MISSES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0xe08,	/* DTLB_LOAD_MISSES.WALK_COMPLETED */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0xe49,	/* DTLB_STORE_MISSES.WALK_COMPLETED */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c0,	/* INST_RETIRED.ANY_P */
+			[C(RESULT_MISS)]	= 0x0481,	/* ITLB.MISS */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c4,	/* BR_INST_RETIRED.ALL_BRANCHES */
+			[C(RESULT_MISS)]	= 0x00c5,	/* BR_MISP_RETIRED.ALL_BRANCHES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+};
+
+static __initconst const u64 glp_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -3016,6 +3130,9 @@ static int hsw_hw_config(struct perf_event *event)
 	return 0;
 }
 
+static struct event_constraint counter0_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x1);
+
 static struct event_constraint counter2_constraint =
 			EVENT_CONSTRAINT(0, 0x4, 0);
 
@@ -3037,6 +3154,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return c;
 }
 
+static struct event_constraint *
+glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	/* :ppp means to do reduced skid PEBS which is PMC0 only. */
+	if (event->attr.precise_ip == 3)
+		return &counter0_constraint;
+
+	c = intel_get_event_constraints(cpuc, idx, event);
+
+	return c;
+}
+
 /*
  * Broadwell:
  *
@@ -3265,10 +3397,8 @@ static void intel_pmu_cpu_dying(int cpu)
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
 				 bool sched_in)
 {
-	if (x86_pmu.pebs_active)
-		intel_pmu_pebs_sched_task(ctx, sched_in);
-	if (x86_pmu.lbr_nr)
-		intel_pmu_lbr_sched_task(ctx, sched_in);
+	intel_pmu_pebs_sched_task(ctx, sched_in);
+	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
@@ -3838,6 +3968,32 @@ __init int intel_pmu_init(void)
 		pr_cont("Goldmont events, ");
 		break;
 
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_glm_extra_regs;
+		/*
+		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+		 * for precise cycles.
+		 */
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.get_event_constraints = glp_get_event_constraints;
+		x86_pmu.cpu_events = glm_events_attrs;
+		/* Goldmont Plus has 4-wide pipeline */
+		event_attr_td_total_slots_scale_glm.event_str = "4";
+		pr_cont("Goldmont plus events, ");
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 238ae3248ba5..4cf100ff2a37 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,16 +40,16 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT
+ *			 Available model: SLM,AMT,GLM
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL
+ *						SKL,KNL,GLM
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -57,16 +57,17 @@
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
+ *						GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL
+ *						SKL,KNL,GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -82,7 +83,7 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT only
+ *			       Available model: HSW ULT, GLM
  *			       Scope: Package (physical package)
  *
  */
@@ -504,6 +505,17 @@ static const struct cstate_model knl_cstates __initconst = {
 };
 
 
+static const struct cstate_model glm_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C3_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 
 #define X86_CSTATES_MODEL(model, states)				\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
@@ -546,6 +558,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c6d23ffe422d..a322fed5f8ed 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -606,12 +606,6 @@ static inline void intel_pmu_drain_pebs_buffer(void)
 	x86_pmu.drain_pebs(&regs);
 }
 
-void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
-{
-	if (!sched_in)
-		intel_pmu_drain_pebs_buffer();
-}
-
 /*
  * PEBS
  */
@@ -651,6 +645,12 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_glp_pebs_event_constraints[] = {
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -816,6 +816,14 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
 	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
 }
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!sched_in && pebs_needs_sched_cb(cpuc))
+		intel_pmu_drain_pebs_buffer();
+}
+
 static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
@@ -889,6 +897,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		ds->pebs_event_reset[hwc->idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	} else {
+		ds->pebs_event_reset[hwc->idx] = 0;
 	}
 }
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index eb261656a320..955457a30197 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -380,8 +380,12 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
+	if (!cpuc->lbr_users)
+		return;
+
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 53728eea1bed..476aec3a4cab 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -879,6 +879,8 @@ extern struct event_constraint intel_slm_pebs_event_constraints[];
 
 extern struct event_constraint intel_glm_pebs_event_constraints[];
 
+extern struct event_constraint intel_glp_pebs_event_constraints[];
+
 extern struct event_constraint intel_nehalem_pebs_event_constraints[];
 
 extern struct event_constraint intel_westmere_pebs_event_constraints[];
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4d2c32f98482..c17c0881fd36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1452,6 +1452,13 @@ static enum event_type_t get_event_type(struct perf_event *event)
 
 	lockdep_assert_held(&ctx->lock);
 
+	/*
+	 * It's 'group type', really, because if our group leader is
+	 * pinned, so are we.
+	 */
+	if (event->group_leader != event)
+		event = event->group_leader;
+
 	event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
 	if (!ctx->task)
 		event_type |= EVENT_CPU;
@@ -4365,7 +4372,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
 static int __perf_read_group_add(struct perf_event *leader,
 					u64 read_format, u64 *values)
 {
+	struct perf_event_context *ctx = leader->ctx;
 	struct perf_event *sub;
+	unsigned long flags;
 	int n = 1; /* skip @nr */
 	int ret;
 
@@ -4395,12 +4404,15 @@ static int __perf_read_group_add(struct perf_event *leader,
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
 
+	raw_spin_lock_irqsave(&ctx->lock, flags);
+
 	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
 		values[n++] += perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
 	}
 
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	return 0;
 }
 
@@ -7308,21 +7320,6 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
-static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
-{
-	/*
-	 * Due to interrupt latency (AKA "skid"), we may enter the
-	 * kernel before taking an overflow, even if the PMU is only
-	 * counting user events.
-	 * To avoid leaking information to userspace, we must always
-	 * reject kernel samples when exclude_kernel is set.
-	 */
-	if (event->attr.exclude_kernel && !user_mode(regs))
-		return false;
-
-	return true;
-}
-
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7344,12 +7341,6 @@ static int __perf_event_overflow(struct perf_event *event,
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
-	 * For security, drop the skid kernel samples if necessary.
-	 */
-	if (!sample_is_allowed(event, regs))
-		return ret;
-
-	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index a4d3762cd825..83874b0e266c 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -704,7 +704,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 		ui_browser__gotorc(browser, row, column + 1);
 		SLsmg_draw_hline(2);
 
-		if (row++ == 0)
+		if (++row == 0)
 			goto out;
 	} else
 		row = 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 87b431886670..413f74df08de 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -273,7 +273,7 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
+		.exclude_kernel	= geteuid() != 0,
 	};
 	struct perf_evsel *evsel;
 
@@ -298,8 +298,10 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 		goto out;
 
 	/* use asprintf() because free(evsel) assumes name is allocated */
-	if (asprintf(&evsel->name, "cycles%.*s",
-		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
+	if (asprintf(&evsel->name, "cycles%s%s%.*s",
+		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
+		     attr.exclude_kernel ? "u" : "",
+		     attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0)
 		goto error_free;
 out:
 	return evsel;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5de2b86b9880..2e9eb6aa3ce2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2209,7 +2209,7 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (map->start)
+		if (!err)
 			machine->kernel_start = map->start;
 	}
 	return err;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-06-10  8:39 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-06-10  8:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Jiri Olsa, Namhyung Kim,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 47c1ded7fef108c730b803cd386241beffcdd15c Merge tag 'perf-urgent-for-mingo-4.12-20170608' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

This is mostly tooling fixes, plus an instruction pointer filtering fix. It's more 
fixes than usual - Arnaldo got back from a longer vacation and there was a 
backlog.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf stat: Only print NMI watchdog hint when enabled

Jin Yao (1):
      perf/core: Drop kernel samples even though :u is specified

Jiri Olsa (2):
      perf trace: Add mmap alias for s390
      perf test: Disable breakpoint signal tests for powerpc

Kim Phillips (2):
      perf annotate: Fix branch instruction with multiple operands
      perf annotate: Add missing powerpc triplet

Milian Wolff (2):
      perf report: Include partial stacks unwound with libdw
      perf report: Ensure the perf DSO mapping matches what libdw sees

Namhyung Kim (12):
      perf header: Set proper module name when build-id event found
      perf symbols: Set module info when build-id event found
      perf symbols: Use correct filename for compressed modules in build-id cache
      perf annotate: Fix symbolic link of build-id cache
      perf tools: Fix a memory leak in __open_dso()
      perf tools: Introduce dso__decompress_kmodule_{fd,path}
      perf annotate: Use dso__decompress_kmodule_path()
      perf tools: Decompress kernel module when reading DSO data
      perf tools: Consolidate error path in __open_dso()
      perf tests: Decompress kernel module before objdump
      perf symbols: Keep DSO->symtab_type after decompress
      perf symbols: Kill dso__build_id_is_kmod()

Ravi Bangoria (1):
      perf annotate: Fix failure when filename has special chars

SeongJae Park (6):
      perf probe: Fix examples section of documentation
      perf script: Fix outdated comment for perf-trace-python
      perf script: Fix documentation errors
      perf script python: Fix wrong code snippets in documentation
      perf script python: Updated trace_unhandled() signature
      perf script python: Remove dups in documentation examples


 kernel/events/core.c                               |  21 +++++
 tools/perf/Documentation/perf-probe.txt            |   8 +-
 tools/perf/Documentation/perf-script-perl.txt      |   2 +-
 tools/perf/Documentation/perf-script-python.txt    |  23 ++---
 tools/perf/arch/common.c                           |   1 +
 tools/perf/builtin-stat.c                          |   5 +-
 tools/perf/builtin-trace.c                         |   4 +
 tools/perf/tests/bp_signal.c                       |  14 +++
 tools/perf/tests/builtin-test.c                    |   7 ++
 tools/perf/tests/code-reading.c                    |  20 ++++-
 tools/perf/tests/tests.h                           |   3 +
 tools/perf/util/annotate.c                         |  72 +++++++++------
 tools/perf/util/build-id.c                         |  45 ----------
 tools/perf/util/build-id.h                         |   1 -
 tools/perf/util/dso.c                              | 100 +++++++++++++++++++--
 tools/perf/util/dso.h                              |   9 ++
 tools/perf/util/header.c                           |  12 ++-
 tools/perf/util/machine.c                          |  11 +--
 .../util/scripting-engines/trace-event-python.c    |   2 +-
 tools/perf/util/symbol-elf.c                       |  41 +--------
 tools/perf/util/symbol.c                           |   4 -
 tools/perf/util/unwind-libdw.c                     |  10 ++-
 22 files changed, 259 insertions(+), 156 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c9412d..6c4e523dc1e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7316,6 +7316,21 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7337,6 +7352,12 @@ static int __perf_event_overflow(struct perf_event *event,
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index e6c9902c6d82..165c2b1d4317 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -240,9 +240,13 @@ EXAMPLES
  or
  ./perf probe --add='schedule:12 cpu'
 
- this will add one or more probes which has the name start with "schedule".
+Add one or more probes which has the name start with "schedule".
 
- Add probes on lines in schedule() function which calls update_rq_clock().
+ ./perf probe schedule*
+ or
+ ./perf probe --add='schedule*'
+
+Add probes on lines in schedule() function which calls update_rq_clock().
 
  ./perf probe 'schedule;update_rq_clock*'
  or
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index dfbb506d2c34..142606c0ec9c 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -39,7 +39,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 54acba221558..51ec2d20068a 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -149,10 +149,8 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 		print "id=%d, args=%s\n" % \
 		(id, args),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
-		print_header(event_name, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm)
+def trace_unhandled(event_name, context, event_fields_dict):
+		print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
 
 def print_header(event_name, cpu, secs, nsecs, pid, comm):
 	print "%-20s %5u %05u.%09u %8u %-20s " % \
@@ -321,7 +319,7 @@ So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
 you're interested in - basically find the tracepoint(s) you're
 interested in by looking at the list of available events shown by
-'perf list' and/or look in /sys/kernel/debug/tracing events for
+'perf list' and/or look in /sys/kernel/debug/tracing/events/ for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
 generate a skeleton script using 'perf script -g python' and modify the
@@ -334,7 +332,7 @@ right place, you can have your script listed alongside the other
 scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -383,8 +381,6 @@ to be located in the perf/scripts/python directory in the kernel
 
 ----
 # ls -al kernel-source/tools/perf/scripts/python
-
-root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
 total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
@@ -399,7 +395,7 @@ otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -437,7 +433,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
@@ -532,7 +528,7 @@ Aside from the event handler functions discussed above, every script
 gives scripts a chance to do setup tasks:
 
 ----
-def trace_begin:
+def trace_begin():
     pass
 ----
 
@@ -541,7 +537,7 @@ Aside from the event handler functions discussed above, every script
  as display results:
 
 ----
-def trace_end:
+def trace_end():
     pass
 ----
 
@@ -550,8 +546,7 @@ Aside from the event handler functions discussed above, every script
  of common arguments are passed into it:
 
 ----
-def trace_unhandled(event_name, context, common_cpu, common_secs,
-        common_nsecs, common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     pass
 ----
 
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 837067f48a4c..6b40e9f01740 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -26,6 +26,7 @@ const char *const arm64_triplets[] = {
 
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
+	"powerpc-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
 	"powerpc64-linux-gnu-",
 	"powerpc64le-linux-gnu-",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a935b5023732..ad9324d1daf9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1578,6 +1578,7 @@ static void print_header(int argc, const char **argv)
 static void print_footer(void)
 {
 	FILE *output = stat_config.output;
+	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
@@ -1590,7 +1591,9 @@ static void print_footer(void)
 	}
 	fprintf(output, "\n\n");
 
-	if (print_free_counters_hint)
+	if (print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d014350adc52..4b2a5d298197 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -681,6 +681,10 @@ static struct syscall_fmt {
 	{ .name	    = "mlockall",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mmap",	    .hexret = true,
+/* The standard mmap maps to old_mmap on s390x */
+#if defined(__s390x__)
+	.alias = "old_mmap",
+#endif
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
 			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index e7664fe3bd33..8ba2c4618fe9 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -288,3 +288,17 @@ int test__bp_signal(int subtest __maybe_unused)
 	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
+
+bool test__bp_signal_is_supported(void)
+{
+/*
+ * The powerpc so far does not have support to even create
+ * instruction breakpoint using the perf event interface.
+ * Once it's there we can release this.
+ */
+#ifdef __powerpc__
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 9e08d297f1a9..3ccfd58a8c3c 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -97,10 +97,12 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint overflow signal handler",
 		.func = test__bp_signal,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Breakpoint overflow sampling",
 		.func = test__bp_signal_overflow,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",
@@ -401,6 +403,11 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		if (!perf_test__matches(t, curr, argc, argv))
 			continue;
 
+		if (t->is_supported && !t->is_supported()) {
+			pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
+			continue;
+		}
+
 		pr_info("%2d: %-*s:", i, width, t->desc);
 
 		if (intlist__find(skiplist, i)) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 1f14e7612cbb..94b7c7b02bde 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,6 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	unsigned char buf2[BUFSZ];
 	size_t ret_len;
 	u64 objdump_addr;
+	const char *objdump_name;
+	char decomp_name[KMOD_DECOMP_LEN];
 	int ret;
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -289,9 +291,25 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		state->done[state->done_cnt++] = al.map->start;
 	}
 
+	objdump_name = al.map->dso->long_name;
+	if (dso__needs_decompress(al.map->dso)) {
+		if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
+						 decomp_name,
+						 sizeof(decomp_name)) < 0) {
+			pr_debug("decompression failed\n");
+			return -1;
+		}
+
+		objdump_name = decomp_name;
+	}
+
 	/* Read the object code using objdump */
 	objdump_addr = map__rip_2objdump(al.map, al.addr);
-	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+	ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
+
+	if (dso__needs_decompress(al.map->dso))
+		unlink(objdump_name);
+
 	if (ret > 0) {
 		/*
 		 * The kernel maps are inaccurate - assume objdump is right in
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 631859629403..577363809c9b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -34,6 +34,7 @@ struct test {
 		int (*get_nr)(void);
 		const char *(*get_desc)(int subtest);
 	} subtest;
+	bool (*is_supported)(void);
 };
 
 /* Tests */
@@ -99,6 +100,8 @@ const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(int subtest);
 
+bool test__bp_signal_is_supported(void);
+
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 683f8340460c..ddbd56df9187 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -239,10 +239,20 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	const char *s = strchr(ops->raw, '+');
 	const char *c = strchr(ops->raw, ',');
 
-	if (c++ != NULL)
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
 		ops->target.addr = strtoull(c, NULL, 16);
-	else
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
 		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
 
 	if (s++ != NULL) {
 		ops->target.offset = strtoull(s, NULL, 16);
@@ -257,10 +267,27 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
+	const char *c = strchr(ops->raw, ',');
+
 	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
 }
 
 static struct ins_ops jump_ops = {
@@ -1294,6 +1321,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	char linkname[PATH_MAX];
 	char *build_id_filename;
 	char *build_id_path = NULL;
+	char *pos;
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso))
@@ -1313,7 +1341,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	if (!build_id_path)
 		return -1;
 
-	dirname(build_id_path);
+	/*
+	 * old style build-id cache has name of XX/XXXXXXX.. while
+	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+	 * extract the build-id part of dirname in the new style only.
+	 */
+	pos = strrchr(build_id_path, '/');
+	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+		dirname(build_id_path);
 
 	if (dso__is_kcore(dso) ||
 	    readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
@@ -1396,31 +1431,10 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 				sizeof(symfs_filename));
 		}
 	} else if (dso__needs_decompress(dso)) {
-		char tmp[PATH_MAX];
-		struct kmod_path m;
-		int fd;
-		bool ret;
-
-		if (kmod_path__parse_ext(&m, symfs_filename))
-			goto out;
-
-		snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
-
-		fd = mkstemp(tmp);
-		if (fd < 0) {
-			free(m.ext);
-			goto out;
-		}
-
-		ret = decompress_to_file(m.ext, symfs_filename, fd);
-
-		if (ret)
-			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
-
-		free(m.ext);
-		close(fd);
+		char tmp[KMOD_DECOMP_LEN];
 
-		if (!ret)
+		if (dso__decompress_kmodule_path(dso, symfs_filename,
+						 tmp, sizeof(tmp)) < 0)
 			goto out;
 
 		strcpy(symfs_filename, tmp);
@@ -1429,7 +1443,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
+		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 168cc49654e7..e0148b081bdf 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -278,51 +278,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return bf;
 }
 
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
-{
-	char *id_name = NULL, *ch;
-	struct stat sb;
-	char sbuild_id[SBUILD_ID_SIZE];
-
-	if (!dso->has_build_id)
-		goto err;
-
-	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-	id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
-	if (!id_name)
-		goto err;
-	if (access(id_name, F_OK))
-		goto err;
-	if (lstat(id_name, &sb) == -1)
-		goto err;
-	if ((size_t)sb.st_size > size - 1)
-		goto err;
-	if (readlink(id_name, bf, size - 1) < 0)
-		goto err;
-
-	bf[sb.st_size] = '\0';
-
-	/*
-	 * link should be:
-	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
-	 */
-	ch = strrchr(bf, '/');
-	if (!ch)
-		goto err;
-	if (ch - 3 < bf)
-		goto err;
-
-	free(id_name);
-	return strncmp(".ko", ch - 3, 3) == 0;
-err:
-	pr_err("Invalid build id: %s\n", id_name ? :
-					 dso->long_name ? :
-					 dso->short_name ? :
-					 "[unknown]");
-	free(id_name);
-	return false;
-}
-
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 8a89b195c1fc..96690a55c62c 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -17,7 +17,6 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
 				    size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index a96a99d2369f..4e7ab611377a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -248,6 +248,64 @@ bool dso__needs_decompress(struct dso *dso)
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+{
+	int fd = -1;
+	struct kmod_path m;
+
+	if (!dso__needs_decompress(dso))
+		return -1;
+
+	if (kmod_path__parse_ext(&m, dso->long_name))
+		return -1;
+
+	if (!m.comp)
+		goto out;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0) {
+		dso->load_errno = errno;
+		goto out;
+	}
+
+	if (!decompress_to_file(m.ext, name, fd)) {
+		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+		close(fd);
+		fd = -1;
+	}
+
+out:
+	free(m.ext);
+	return fd;
+}
+
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	unlink(tmpbuf);
+	return fd;
+}
+
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	if (fd < 0) {
+		unlink(tmpbuf);
+		return -1;
+	}
+
+	strncpy(pathname, tmpbuf, len);
+	close(fd);
+	return 0;
+}
+
 /*
  * Parses kernel module specified in @path and updates
  * @m argument like:
@@ -335,6 +393,21 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 	return 0;
 }
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine)
+{
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (m->kmod && m->comp)
+		dso->symtab_type++;
+
+	dso__set_short_name(dso, strdup(m->name), true);
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
@@ -381,7 +454,7 @@ static int do_open(char *name)
 
 static int __open_dso(struct dso *dso, struct machine *machine)
 {
-	int fd;
+	int fd = -EINVAL;
 	char *root_dir = (char *)"";
 	char *name = malloc(PATH_MAX);
 
@@ -392,15 +465,30 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		root_dir = machine->root_dir;
 
 	if (dso__read_binary_type_filename(dso, dso->binary_type,
-					    root_dir, name, PATH_MAX)) {
-		free(name);
-		return -EINVAL;
-	}
+					    root_dir, name, PATH_MAX))
+		goto out;
 
 	if (!is_regular_file(name))
-		return -EINVAL;
+		goto out;
+
+	if (dso__needs_decompress(dso)) {
+		char newpath[KMOD_DECOMP_LEN];
+		size_t len = sizeof(newpath);
+
+		if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
+			fd = -dso->load_errno;
+			goto out;
+		}
+
+		strcpy(name, newpath);
+	}
 
 	fd = do_open(name);
+
+	if (dso__needs_decompress(dso))
+		unlink(name);
+
+out:
 	free(name);
 	return fd;
 }
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 12350b171727..bd061ba7b47c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -244,6 +244,12 @@ bool is_supported_compression(const char *ext);
 bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len);
+
+#define KMOD_DECOMP_NAME  "/tmp/perf-kmod-XXXXXX"
+#define KMOD_DECOMP_LEN   sizeof(KMOD_DECOMP_NAME)
 
 struct kmod_path {
 	char *name;
@@ -259,6 +265,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false)
 #define kmod_path__parse_ext(__m, __p)  __kmod_path__parse(__m, __p, false, true)
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine);
+
 /*
  * The dso__data_* external interface provides following functions:
  *   dso__data_get_fd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 314a07151fb7..5cac8d5e009a 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1469,8 +1469,16 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename, cpumode))
-			dso->kernel = dso_type;
+		if (dso_type != DSO_TYPE_USER) {
+			struct kmod_path m = { .name = NULL, };
+
+			if (!kmod_path__parse_name(&m, filename) && m.kmod)
+				dso__set_module_info(dso, &m, machine);
+			else
+				dso->kernel = dso_type;
+
+			free(m.name);
+		}
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index d97e014c3df3..d7f31cb0a4cb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -572,16 +572,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 		if (dso == NULL)
 			goto out_unlock;
 
-		if (machine__is_host(machine))
-			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
-		else
-			dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-
-		/* _KMODULE_COMP should be next to _KMODULE */
-		if (m->kmod && m->comp)
-			dso->symtab_type++;
-
-		dso__set_short_name(dso, strdup(m->name), true);
+		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9d92af7d0718..40de3cb40d21 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1219,7 +1219,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# be retrieved using Python functions of the form "
 		"common_*(context).\n");
 
-	fprintf(ofp, "# See the perf-trace-python Documentation for the list "
+	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
 	fprintf(ofp, "import os\n");
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index e7ee47f7377a..502505cf236a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -637,43 +637,6 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
 	return 0;
 }
 
-static int decompress_kmodule(struct dso *dso, const char *name,
-			      enum dso_binary_type type)
-{
-	int fd = -1;
-	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
-	struct kmod_path m;
-
-	if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
-	    type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
-	    type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		return -1;
-
-	if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		name = dso->long_name;
-
-	if (kmod_path__parse_ext(&m, name) || !m.comp)
-		return -1;
-
-	fd = mkstemp(tmpbuf);
-	if (fd < 0) {
-		dso->load_errno = errno;
-		goto out;
-	}
-
-	if (!decompress_to_file(m.ext, name, fd)) {
-		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
-		close(fd);
-		fd = -1;
-	}
-
-	unlink(tmpbuf);
-
-out:
-	free(m.ext);
-	return fd;
-}
-
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
 	return ss->dynsym || ss->opdsec;
@@ -705,9 +668,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	int fd;
 
 	if (dso__needs_decompress(dso)) {
-		fd = decompress_kmodule(dso, name, type);
+		fd = dso__decompress_kmodule_fd(dso, name);
 		if (fd < 0)
 			return -1;
+
+		type = dso->symtab_type;
 	} else {
 		fd = open(name, O_RDONLY);
 		if (fd < 0) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8f2b068ff756..e7a98dbd2aed 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1562,10 +1562,6 @@ int dso__load(struct dso *dso, struct map *map)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
-	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
-			kmod = true;
-
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
 	else
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 943a06291587..da45c4be5fb3 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -39,6 +39,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 		return 0;
 
 	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (mod) {
+		Dwarf_Addr s;
+
+		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+		if (s != al->map->start)
+			mod = 0;
+	}
+
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
 				      dso->long_name, -1, al->map->start,
@@ -224,7 +232,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 
 	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui->max_stack)
+	if (err && ui->max_stack != max_stack)
 		err = 0;
 
 	/*

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-05-12  7:31 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-05-12  7:31 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 88b0193d9418c00340e45e0a913a0813bc6c8c96 perf/callchain: Force USER_DS when invoking perf_callchain_user()

Mostly tooling updates, but also two kernel fixes: a call chain handling 
robustness fix and an x86 PMU driver event definition fix.

 Thanks,

	Ingo

------------------>

Arnaldo Carvalho de Melo (9):
      perf buildid: Move prototypes from util.h to build-id.h
      perf tools: Move event prototypes from util.h to event.h
      perf memswap: Split the byteswap memory range wrappers from util.[ch]
      perf tools: Move HAS_BOOL define to where perl headers are used
      perf ui gtk: Move gtk .so name to the only place where it is used
      perf units: Move parse_tag_value() to units.[ch]
      tools lib string: Adopt prefixcmp() from perf and subcmd
      perf symbols: Accept symbols starting at address 0
      tools build: Fixup sched_getcpu feature test

Ingo Molnar (2):
      Merge tag 'perf-core-for-mingo-4.12-20170503' of git://git.kernel.org/.../acme/linux into perf/urgent
      Merge tag 'perf-urgent-for-mingo-4.12-20170504' of git://git.kernel.org/.../acme/linux into perf/urgent

Kim Phillips (3):
      perf tools: Fix spelling mistakes
      perf annotate: Fix AArch64 comment char
      perf tests kmod-path: Don't fail if compressed modules aren't supported

Paul Clarke (1):
      perf symbols: Allow user probes on versioned symbols

Taeung Song (1):
      perf config: Refactor a duplicated code for obtaining config file name

Vince Weaver (1):
      perf/x86: Fix Broadwell-EP DRAM RAPL events

Will Deacon (1):
      perf/callchain: Force USER_DS when invoking perf_callchain_user()


 arch/x86/events/intel/rapl.c                         |  2 +-
 kernel/events/callchain.c                            |  6 ++++++
 tools/build/feature/test-sched_getcpu.c              |  2 ++
 tools/include/linux/string.h                         |  2 ++
 tools/lib/string.c                                   |  9 +++++++++
 tools/lib/subcmd/help.c                              |  1 +
 tools/lib/subcmd/parse-options.c                     |  1 +
 tools/lib/subcmd/subcmd-util.h                       |  9 ---------
 tools/perf/Documentation/perf-c2c.txt                |  4 ++--
 tools/perf/Documentation/perf-record.txt             |  2 +-
 tools/perf/Documentation/perf-report.txt             |  6 +++---
 tools/perf/Documentation/perf.data-file-format.txt   |  4 ++--
 tools/perf/Documentation/tips.txt                    |  2 +-
 tools/perf/arch/arm64/annotate/instructions.c        |  2 +-
 tools/perf/arch/powerpc/util/sym-handling.c          | 12 ++++++++++++
 tools/perf/builtin-buildid-cache.c                   | 13 ++++++++-----
 tools/perf/builtin-c2c.c                             |  1 +
 tools/perf/builtin-config.c                          | 19 ++++++++-----------
 tools/perf/builtin-top.c                             |  2 +-
 tools/perf/builtin-trace.c                           |  1 +
 tools/perf/perf.c                                    |  1 +
 tools/perf/tests/hists_cumulate.c                    |  1 +
 tools/perf/tests/hists_filter.c                      |  1 +
 tools/perf/tests/hists_output.c                      |  1 +
 tools/perf/tests/kmod-path.c                         |  2 ++
 tools/perf/tests/sdt.c                               |  1 -
 tools/perf/ui/setup.c                                |  3 +++
 tools/perf/util/Build                                |  1 +
 tools/perf/util/build-id.h                           |  4 ++++
 tools/perf/util/event.c                              | 10 ++++++----
 tools/perf/util/event.h                              | 14 +++++++++++---
 tools/perf/util/evsel.c                              |  1 +
 tools/perf/util/header.c                             |  1 +
 tools/perf/util/intel-pt.c                           |  1 +
 tools/perf/util/machine.c                            | 28 +++++++++++++++++-----------
 tools/perf/util/map.c                                |  5 -----
 tools/perf/util/map.h                                |  5 +++--
 tools/perf/util/memswap.c                            | 24 ++++++++++++++++++++++++
 tools/perf/util/memswap.h                            |  7 +++++++
 tools/perf/util/scripting-engines/trace-event-perl.c |  4 +++-
 tools/perf/util/session.c                            |  1 +
 tools/perf/util/strbuf.c                             |  9 ---------
 tools/perf/util/symbol.c                             | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++++-------------------
 tools/perf/util/symbol.h                             | 11 +++++++++++
 tools/perf/util/units.c                              | 29 +++++++++++++++++++++++++++++
 tools/perf/util/units.h                              |  7 +++++++
 tools/perf/util/util.c                               | 49 -------------------------------------------------
 tools/perf/util/util.h                               | 26 --------------------------
 48 files changed, 252 insertions(+), 167 deletions(-)
 create mode 100644 tools/perf/util/memswap.c
 create mode 100644 tools/perf/util/memswap.h

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-03-07 20:30 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-03-07 20:30 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 9d020d33fc1b2faa0eb35859df1381ca5dc94ffe Merge branch 'linus' into perf/urgent, to resolve conflict

This includes a fix for a crash if certain special addresses are kprobed, plus 
does a rename of two Kconfig variables that were a minor misnomer.

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      perf/core: Rename CONFIG_[UK]PROBE_EVENT to CONFIG_[UK]PROBE_EVENTS

Masami Hiramatsu (1):
      kprobes/x86: Fix kernel panic when certain exception-handling addresses are probed


 Documentation/trace/kprobetrace.txt     |  2 +-
 Documentation/trace/uprobetracer.txt    |  2 +-
 arch/s390/configs/default_defconfig     |  2 +-
 arch/s390/configs/gcov_defconfig        |  2 +-
 arch/s390/configs/performance_defconfig |  2 +-
 arch/s390/defconfig                     |  2 +-
 arch/x86/kernel/kprobes/common.h        |  2 +-
 arch/x86/kernel/kprobes/core.c          |  6 +++---
 arch/x86/kernel/kprobes/opt.c           |  2 +-
 kernel/trace/Kconfig                    |  6 +++---
 kernel/trace/Makefile                   |  4 ++--
 kernel/trace/trace.c                    | 10 +++++-----
 kernel/trace/trace_probe.h              |  4 ++--
 13 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index e4991fb1eedc..41ef9d8efe95 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -12,7 +12,7 @@ kprobes can probe (this means, all functions body except for __kprobes
 functions). Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
index fa7b680ee8a0..bf526a7c5559 100644
--- a/Documentation/trace/uprobetracer.txt
+++ b/Documentation/trace/uprobetracer.txt
@@ -7,7 +7,7 @@
 Overview
 --------
 Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 143b1e00b818..4b176fe83da4 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -609,7 +609,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index f05d2d6e1087..0de46cc397f6 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -560,7 +560,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 2358bf33c5ef..e167557b434c 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -558,7 +558,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 68bfd09f1b02..97189dbaf34b 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -179,7 +179,7 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_KPROBES_SANITY_TEST=y
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f927ab..d688826e5736 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 520b8dfe1640..88b3c942473d 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -166,12 +166,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
 retry:
@@ -416,7 +416,7 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
+	if (can_boost(p->ainsn.insn, p->addr))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3d1bee9d6a72..3e7c6e5a08ff 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 
 	while (len < RELATIVEJUMP_SIZE) {
 		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		if (!ret || !can_boost(dest + len, src + len))
 			return -EINVAL;
 		len += ret;
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d5038005eb5d..d4a06e714645 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
-config KPROBE_EVENT
+config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API
 	bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@ config KPROBE_EVENT
 	  This option is also required by perf-probe subcommand of perf tools.
 	  If you want to use perf tools, this option is strongly recommended.
 
-config UPROBE_EVENT
+config UPROBE_EVENTS
 	bool "Enable uprobes-based dynamic events"
 	depends on ARCH_SUPPORTS_UPROBES
 	depends on MMU
@@ -466,7 +466,7 @@ config UPROBE_EVENT
 
 config BPF_EVENTS
 	depends on BPF_SYSCALL
-	depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+	depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
 	bool
 	default y
 	help
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e57980845549..90f2701d92a7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445ceb7ef..f35109514a01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4341,22 +4341,22 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
 	"\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
 	"\t           -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"\t    place: <path>:<offset>\n"
 #endif
 	"\t     args: <name>=fetcharg[:type]\n"
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54d44c6..903273c93e61 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define FETCH_TYPE_STRING	0
 #define FETCH_TYPE_STRSIZE	1
 
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
 	struct fetch_param	fetch;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-02-28  8:01 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-02-28  8:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 1572e45a924f254d9570093abde46430c3172e3d perf/core: Fix the perf_cpu_time_max_percent check

Misc fixes on the kernel and tooling side - nothing in particular stands out.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      tools perf scripting python: clang doesn't have -spec, remove it
      perf python: Filter out -specs=/a/b/c from the python binding cc options
      perf session: Fix DEBUG=1 build with clang

Jan Stancek (3):
      perf cpumap: Add cpu__max_present_cpu()
      perf header: Make build_cpu_topology skip offline/absent CPUs
      perf tools: Replace _SC_NPROCESSORS_CONF with max_present_cpu in cpu_topology_map

Jiri Olsa (5):
      perf build: Add special fixdep cleaning rule
      perf tools: Move new_term arguments into struct parse_events_term template
      perf tools: Fail on using multiple bits long terms without value
      perf stat: Add -a as default target
      perf record: Add -a as default target

Namhyung Kim (6):
      perf utils: Add perf_quiet_option()
      perf utils: Check verbose flag properly
      perf report: Add -q/--quiet option
      perf diff: Add -q/--quiet option
      perf annotate: Add -q/--quiet option
      perf record: Honor --quiet option properly

Peter Zijlstra (2):
      perf/core: Remove confusing comment and move put_ctx()
      perf/core: Fix perf_event_enable_on_exec() timekeeping (again)

Steven Rostedt (VMware) (1):
      tools lib traceevent: It's preempt not prempt

Tan Xiaojun (1):
      perf/core: Fix the perf_cpu_time_max_percent check


 kernel/events/core.c                               | 12 ++--
 tools/build/Makefile                               |  4 +-
 tools/build/Makefile.include                       |  3 +
 tools/lib/traceevent/event-parse.c                 |  4 +-
 tools/lib/traceevent/event-parse.h                 |  2 +-
 tools/perf/Documentation/perf-annotate.txt         |  4 ++
 tools/perf/Documentation/perf-diff.txt             |  4 ++
 tools/perf/Documentation/perf-record.txt           |  2 +-
 tools/perf/Documentation/perf-report.txt           |  4 ++
 tools/perf/Documentation/perf-stat.txt             |  2 +-
 tools/perf/Makefile.config                         |  7 +++
 tools/perf/Makefile.perf                           |  4 +-
 tools/perf/builtin-annotate.c                      |  4 ++
 tools/perf/builtin-diff.c                          | 14 +++--
 tools/perf/builtin-mem.c                           |  4 +-
 tools/perf/builtin-record.c                        |  8 ++-
 tools/perf/builtin-report.c                        | 21 +++++--
 tools/perf/builtin-sched.c                         | 12 ++--
 tools/perf/builtin-stat.c                          | 11 ++--
 tools/perf/builtin-top.c                           |  2 +-
 tools/perf/builtin-trace.c                         |  6 +-
 tools/perf/pmu-events/json.c                       |  2 +-
 tools/perf/tests/attr.c                            |  2 +-
 tools/perf/tests/builtin-test.c                    |  2 +-
 tools/perf/tests/code-reading.c                    |  2 +-
 tools/perf/tests/fdarray.c                         |  2 +-
 tools/perf/tests/llvm.c                            |  2 +-
 tools/perf/tests/parse-events.c                    |  2 +-
 tools/perf/tests/perf-record.c                     |  4 +-
 tools/perf/tests/python-use.c                      |  2 +-
 tools/perf/tests/thread-map.c                      |  6 +-
 tools/perf/tests/topology.c                        |  4 +-
 tools/perf/tests/vmlinux-kallsyms.c                |  2 +-
 tools/perf/ui/browsers/map.c                       |  6 +-
 tools/perf/ui/hist.c                               |  2 +-
 tools/perf/util/annotate.c                         |  2 +-
 tools/perf/util/cpumap.c                           | 22 +++++++
 tools/perf/util/cpumap.h                           |  1 +
 tools/perf/util/debug.c                            | 17 ++++++
 tools/perf/util/debug.h                            |  1 +
 tools/perf/util/dso.c                              |  2 +-
 tools/perf/util/env.c                              |  2 +-
 tools/perf/util/header.c                           | 33 ++++++----
 tools/perf/util/hist.c                             |  6 +-
 tools/perf/util/parse-events.c                     | 71 +++++++++++++---------
 tools/perf/util/parse-events.h                     |  2 +
 tools/perf/util/parse-events.y                     | 14 ++---
 tools/perf/util/pmu.c                              | 21 +++++--
 tools/perf/util/probe-event.c                      |  2 +-
 .../util/scripting-engines/trace-event-python.c    |  4 +-
 tools/perf/util/session.c                          |  2 +-
 tools/perf/util/setup.py                           |  9 ++-
 tools/perf/util/sort.c                             |  8 +--
 tools/perf/util/stat.c                             |  2 +-
 tools/perf/util/symbol-elf.c                       |  2 +-
 55 files changed, 260 insertions(+), 137 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 77a932b54a64..c1c1cdf0b811 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -455,7 +455,7 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos)
 {
-	int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (ret || !write)
 		return ret;
@@ -3522,6 +3522,8 @@ static void perf_event_enable_on_exec(int ctxn)
 	if (enabled) {
 		clone_ctx = unclone_ctx(ctx);
 		ctx_resched(cpuctx, ctx, event_type);
+	} else {
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 	}
 	perf_ctx_unlock(cpuctx, ctx);
 
@@ -9955,6 +9957,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * of swizzling perf_event::ctx.
 		 */
 		perf_remove_from_context(group_leader, 0);
+		put_ctx(gctx);
 
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
@@ -9993,13 +9996,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
-
-		/*
-		 * Now that all events are installed in @ctx, nothing
-		 * references @gctx anymore, so drop the last reference we have
-		 * on it.
-		 */
-		put_ctx(gctx);
 	}
 
 	/*
diff --git a/tools/build/Makefile b/tools/build/Makefile
index aaf7ed329a45..477f00eda591 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -35,8 +35,8 @@ all: $(OUTPUT)fixdep
 
 clean:
 	$(call QUIET_CLEAN, fixdep)
-	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-	$(Q)rm -f fixdep
+	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)rm -f $(OUTPUT)fixdep
 
 $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include
index ad22e4e7bc59..d360f39a445b 100644
--- a/tools/build/Makefile.include
+++ b/tools/build/Makefile.include
@@ -3,4 +3,7 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 fixdep:
 	$(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
 
+fixdep-clean:
+	$(Q)$(MAKE) -C $(srctree)/tools/build clean
+
 .PHONY: fixdep
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 14a4f623c1a5..32171310bf82 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5204,13 +5204,13 @@ int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec)
 }
 
 /**
- * pevent_data_prempt_count - parse the preempt count from the record
+ * pevent_data_preempt_count - parse the preempt count from the record
  * @pevent: a handle to the pevent
  * @rec: the record to parse
  *
  * This returns the preempt count from a record.
  */
-int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec)
+int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec)
 {
 	return parse_common_pc(pevent, rec->data);
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 7aae746ec2fe..67daa01260a9 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -709,7 +709,7 @@ void pevent_data_lat_fmt(struct pevent *pevent,
 int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
 struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type);
 int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec);
-int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec);
+int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec);
 int pevent_data_flags(struct pevent *pevent, struct pevent_record *rec);
 const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
 struct cmdline;
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 8ffbd272952d..a89273d8e744 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -39,6 +39,10 @@ OPTIONS
 --verbose::
         Be more verbose. (Show symbol address, etc)
 
+-q::
+--quiet::
+	Do not show any message.  (Suppress -v)
+
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 66dbe3dee74b..a79c84ae61aa 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -73,6 +73,10 @@ OPTIONS
 	Be verbose, for instance, show the raw counts in addition to the
 	diff.
 
+-q::
+--quiet::
+	Do not show any message.  (Suppress -v)
+
 -f::
 --force::
         Don't do ownership validation.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 27256bc68eda..b16003ec14a7 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -157,7 +157,7 @@ OPTIONS
 
 -a::
 --all-cpus::
-        System-wide collection from all CPUs.
+        System-wide collection from all CPUs (default if no target is specified).
 
 -p::
 --pid=::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index f2914f03ae7b..c04cc0647c16 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -25,6 +25,10 @@ OPTIONS
 --verbose::
         Be more verbose. (show symbol address, etc)
 
+-q::
+--quiet::
+	Do not show any message.  (Suppress -v)
+
 -n::
 --show-nr-samples::
 	Show the number of samples for each symbol
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index d96ccd4844df..aecf2a87e7d6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -63,7 +63,7 @@ OPTIONS
 
 -a::
 --all-cpus::
-        system-wide collection from all CPUs
+        system-wide collection from all CPUs (default if no target is specified)
 
 -c::
 --scale::
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 2b941efadb04..27c9fbca7bd9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -175,6 +175,10 @@ PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
 PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 
+ifeq ($(CC), clang)
+  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+endif
+
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
 FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
@@ -601,6 +605,9 @@ else
       PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
       PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
       PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      ifeq ($(CC), clang)
+        PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+      endif
       FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
       ifneq ($(feature-libpython), 1)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 4da19b6ba94a..79fe31f20a17 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -726,13 +726,13 @@ install: install-bin try-install-man
 	$(call QUIET_CLEAN, config)
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
-		$(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
+		$(OUTPUT)util/intel-pt-decoder/inat-tables.c \
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ebb628332a6e..4f52d85f5ebc 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -410,6 +410,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
 	OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
@@ -463,6 +464,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		annotate.sym_hist_filter = argv[0];
 	}
 
+	if (quiet)
+		perf_quiet_option();
+
 	file.path  = input_name;
 
 	annotate.session = perf_session__new(&file, false, &annotate.tool);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 70a289347591..1b96a3122228 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -691,7 +691,7 @@ static void hists__process(struct hists *hists)
 	hists__precompute(hists);
 	hists__output_resort(hists, NULL);
 
-	hists__fprintf(hists, true, 0, 0, 0, stdout,
+	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
 		       symbol_conf.use_callchain);
 }
 
@@ -739,12 +739,14 @@ static void data_process(void)
 				hists__link(hists_base, hists);
 		}
 
-		fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
-			perf_evsel__name(evsel_base));
+		if (!quiet) {
+			fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
+				perf_evsel__name(evsel_base));
+		}
 
 		first = false;
 
-		if (verbose || data__files_cnt > 2)
+		if (verbose > 0 || ((data__files_cnt > 2) && !quiet))
 			data__fprintf();
 
 		/* Don't sort callchain for perf diff */
@@ -807,6 +809,7 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
 	OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
 		    "Show only items with match in baseline"),
 	OPT_CALLBACK('c', "compute", &compute,
@@ -1328,6 +1331,9 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
+	if (quiet)
+		perf_quiet_option();
+
 	if (symbol__init(NULL) < 0)
 		return -1;
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index cd7bc4d104e2..6114e07ca613 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -42,8 +42,8 @@ static int parse_record_events(const struct option *opt,
 
 		fprintf(stderr, "%-13s%-*s%s\n",
 			e->tag,
-			verbose ? 25 : 0,
-			verbose ? perf_mem_events__name(j) : "",
+			verbose > 0 ? 25 : 0,
+			verbose > 0 ? perf_mem_events__name(j) : "",
 			e->supported ? ": available" : "");
 	}
 	exit(0);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6cd6776052e7..bc84a375295d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -432,7 +432,7 @@ static int record__open(struct record *rec)
 try_again:
 		if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
 			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
-				if (verbose)
+				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
@@ -1677,8 +1677,12 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
+	if (quiet)
+		perf_quiet_option();
+
+	/* Make system wide (-a) the default target. */
 	if (!argc && target__none(&rec->opts.target))
-		usage_with_options(record_usage, record_options);
+		rec->opts.target.system_wide = true;
 
 	if (nr_cgroups && !rec->opts.target.system_wide) {
 		usage_with_options_msg(record_usage, record_options,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dbd7fa028861..0a88670e56f3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -320,6 +320,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	size_t size = sizeof(buf);
 	int socked_id = hists->socket_filter;
 
+	if (quiet)
+		return 0;
+
 	if (symbol_conf.filter_relative) {
 		nr_samples = hists->stats.nr_non_filtered_samples;
 		nr_events = hists->stats.total_non_filtered_period;
@@ -372,7 +375,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
-	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
+	if (!quiet) {
+		fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n",
+			evlist->stats.total_lost_samples);
+	}
+
 	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
@@ -382,7 +389,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 			continue;
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
-		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout,
+		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
 			       symbol_conf.use_callchain);
 		fprintf(stdout, "\n\n");
 	}
@@ -716,6 +723,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "input file name"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
@@ -863,6 +871,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		report.symbol_filter_str = argv[0];
 	}
 
+	if (quiet)
+		perf_quiet_option();
+
 	if (symbol_conf.vmlinux_name &&
 	    access(symbol_conf.vmlinux_name, R_OK)) {
 		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
@@ -983,14 +994,14 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto error;
 	}
 
-	if (report.header || report.header_only) {
+	if ((report.header || report.header_only) && !quiet) {
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
 		if (report.header_only) {
 			ret = 0;
 			goto error;
 		}
-	} else if (use_browser == 0) {
+	} else if (use_browser == 0 && !quiet) {
 		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
 		      stdout);
 	}
@@ -1009,7 +1020,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
  		 * providing it only in verbose mode not to bloat too
  		 * much struct symbol.
  		 */
-		if (verbose) {
+		if (verbose > 0) {
 			/*
 			 * XXX: Need to provide a less kludgy way to ask for
 			 * more space per symbol, the u32 is for the index on
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 270eb2d8ca6b..b94cf0de715a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -460,7 +460,7 @@ static struct task_desc *register_pid(struct perf_sched *sched,
 	BUG_ON(!sched->tasks);
 	sched->tasks[task->nr] = task;
 
-	if (verbose)
+	if (verbose > 0)
 		printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
 
 	return task;
@@ -794,7 +794,7 @@ replay_wakeup_event(struct perf_sched *sched,
 	const u32 pid	 = perf_evsel__intval(evsel, sample, "pid");
 	struct task_desc *waker, *wakee;
 
-	if (verbose) {
+	if (verbose > 0) {
 		printf("sched_wakeup event %p\n", evsel);
 
 		printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
@@ -822,7 +822,7 @@ static int replay_switch_event(struct perf_sched *sched,
 	int cpu = sample->cpu;
 	s64 delta;
 
-	if (verbose)
+	if (verbose > 0)
 		printf("sched_switch event %p\n", evsel);
 
 	if (cpu >= MAX_CPUS || cpu < 0)
@@ -870,7 +870,7 @@ static int replay_fork_event(struct perf_sched *sched,
 		goto out_put;
 	}
 
-	if (verbose) {
+	if (verbose > 0) {
 		printf("fork event\n");
 		printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
 		printf("...  child: %s/%d\n", thread__comm_str(child), child->tid);
@@ -1573,7 +1573,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 	timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
 	color_fprintf(stdout, color, "  %12s secs ", stimestamp);
-	if (new_shortname || (verbose && sched_in->tid)) {
+	if (new_shortname || (verbose > 0 && sched_in->tid)) {
 		const char *pid_color = color;
 
 		if (thread__has_color(sched_in))
@@ -2050,7 +2050,7 @@ static void save_task_callchain(struct perf_sched *sched,
 
 	if (thread__resolve_callchain(thread, cursor, evsel, sample,
 				      NULL, NULL, sched->max_stack + 2) != 0) {
-		if (verbose)
+		if (verbose > 0)
 			error("Failed to resolve callchain. Skipping\n");
 
 		return;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f28719178b51..13b54999ad79 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -573,7 +573,7 @@ static int __run_perf_stat(int argc, const char **argv)
 			if (errno == EINVAL || errno == ENOSYS ||
 			    errno == ENOENT || errno == EOPNOTSUPP ||
 			    errno == ENXIO) {
-				if (verbose)
+				if (verbose > 0)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    perf_evsel__name(counter));
 				counter->supported = false;
@@ -582,7 +582,7 @@ static int __run_perf_stat(int argc, const char **argv)
 				    !(counter->leader->nr_members > 1))
 					continue;
 			} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                         ui__warning("%s\n", msg);
                                 goto try_again;
                         }
@@ -1765,7 +1765,7 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, i
 
 	cpu = map->map[idx];
 
-	if (cpu >= env->nr_cpus_online)
+	if (cpu >= env->nr_cpus_avail)
 		return -1;
 
 	return cpu;
@@ -2445,8 +2445,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		big_num = false;
 
+	/* Make system wide (-a) the default target. */
 	if (!argc && target__none(&target))
-		usage_with_options(stat_usage, stat_options);
+		target.system_wide = true;
 
 	if (run_count < 0) {
 		pr_err("Run count must be a positive number\n");
@@ -2538,7 +2539,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	status = 0;
 	for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
-		if (run_count != 1 && verbose)
+		if (run_count != 1 && verbose > 0)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5a7fd7af3a6d..ab9077915763 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -871,7 +871,7 @@ static int perf_top__start_counters(struct perf_top *top)
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads) < 0) {
 			if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-				if (verbose)
+				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 40ef9b293d1b..256f1fac6f7e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1399,7 +1399,7 @@ static struct syscall *trace__syscall_info(struct trace *trace,
 	return &trace->syscalls.table[id];
 
 out_cant_read:
-	if (verbose) {
+	if (verbose > 0) {
 		fprintf(trace->output, "Problems reading syscall %d", id);
 		if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
 			fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
@@ -1801,10 +1801,10 @@ static void print_location(FILE *f, struct perf_sample *sample,
 			   bool print_dso, bool print_sym)
 {
 
-	if ((verbose || print_dso) && al->map)
+	if ((verbose > 0 || print_dso) && al->map)
 		fprintf(f, "%s@", al->map->dso->long_name);
 
-	if ((verbose || print_sym) && al->sym)
+	if ((verbose > 0 || print_sym) && al->sym)
 		fprintf(f, "%s+0x%" PRIx64, al->sym->name,
 			al->addr - al->sym->start);
 	else if (al->map)
diff --git a/tools/perf/pmu-events/json.c b/tools/perf/pmu-events/json.c
index f67bbb0aa36e..0544398d6e2d 100644
--- a/tools/perf/pmu-events/json.c
+++ b/tools/perf/pmu-events/json.c
@@ -49,7 +49,7 @@ static char *mapfile(const char *fn, size_t *size)
 	int err;
 	int fd = open(fn, O_RDONLY);
 
-	if (fd < 0 && verbose && fn) {
+	if (fd < 0 && verbose > 0 && fn) {
 		pr_err("Error opening events file '%s': %s\n", fn,
 				strerror(errno));
 	}
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 28d1605b0338..88dc51f4c27b 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -144,7 +144,7 @@ static int run_dir(const char *d, const char *perf)
 	int vcnt = min(verbose, (int) sizeof(v) - 1);
 	char cmd[3*PATH_MAX];
 
-	if (verbose)
+	if (verbose > 0)
 		vcnt++;
 
 	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 37e326bfd2dc..83c4669cbc5b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -299,7 +299,7 @@ static int run_test(struct test *test, int subtest)
 		if (!dont_fork) {
 			pr_debug("test child forked, pid %d\n", getpid());
 
-			if (!verbose) {
+			if (verbose <= 0) {
 				int nullfd = open("/dev/null", O_WRONLY);
 
 				if (nullfd >= 0) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index ff5bc6363a79..d1f693041324 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -599,7 +599,7 @@ static int do_test_code_reading(bool try_kcore)
 				continue;
 			}
 
-			if (verbose) {
+			if (verbose > 0) {
 				char errbuf[512];
 				perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
 				pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index a2b5ff9bf83d..bc5982f42dc3 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -19,7 +19,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 {
 	int printed = 0;
 
-	if (!verbose)
+	if (verbose <= 0)
 		return 0;
 
 	printed += fprintf(fp, "\n%s: ", prefix);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index d357dab72e68..482b5365e68d 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -76,7 +76,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 	 * Skip this test if user's .perfconfig doesn't set [llvm] section
 	 * and clang is not found in $PATH, and this is not perf test -v
 	 */
-	if (!force && (verbose == 0 &&
+	if (!force && (verbose <= 0 &&
 		       !llvm_param.user_set_param &&
 		       llvm__search_clang())) {
 		pr_debug("No clang and no verbosive, skip this test\n");
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index aa9276bfe3e9..1dc838014422 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1808,7 +1808,7 @@ static void debug_warn(const char *warn, va_list params)
 {
 	char msg[1024];
 
-	if (!verbose)
+	if (verbose <= 0)
 		return;
 
 	vsnprintf(msg, sizeof(msg), warn, params);
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 541da7a68f91..87893f3ba5f1 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -172,13 +172,13 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 
 				err = perf_evlist__parse_sample(evlist, event, &sample);
 				if (err < 0) {
-					if (verbose)
+					if (verbose > 0)
 						perf_event__fprintf(event, stderr);
 					pr_debug("Couldn't parse sample\n");
 					goto out_delete_evlist;
 				}
 
-				if (verbose) {
+				if (verbose > 0) {
 					pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
 					perf_event__fprintf(event, stderr);
 				}
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 7a52834ee0d0..fa79509da535 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -15,7 +15,7 @@ int test__python_use(int subtest __maybe_unused)
 	int ret;
 
 	if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s",
-		     PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0)
+		     PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0)
 		return -1;
 
 	ret = system(cmd) ? -1 : 0;
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index a4a4b4625ac3..f2d2e542d0ee 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -109,7 +109,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
 	TEST_ASSERT_VAL("failed to allocate thread_map",
 			threads);
 
-	if (verbose)
+	if (verbose > 0)
 		thread_map__fprintf(threads, stderr);
 
 	TEST_ASSERT_VAL("failed to remove thread",
@@ -117,7 +117,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
 
 	TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1);
 
-	if (verbose)
+	if (verbose > 0)
 		thread_map__fprintf(threads, stderr);
 
 	TEST_ASSERT_VAL("failed to remove thread",
@@ -125,7 +125,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
 
 	TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0);
 
-	if (verbose)
+	if (verbose > 0)
 		thread_map__fprintf(threads, stderr);
 
 	TEST_ASSERT_VAL("failed to not remove thread",
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 98fe69ac553c..803f893550d6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -65,7 +65,9 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
 	session = perf_session__new(&file, false, NULL);
 	TEST_ASSERT_VAL("can't get session", session);
 
-	for (i = 0; i < session->header.env.nr_cpus_online; i++) {
+	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
+		if (!cpu_map__has(map, i))
+			continue;
 		pr_debug("CPU %d, core %d, socket %d\n", i,
 			 session->header.env.cpu[i].core_id,
 			 session->header.env.cpu[i].socket_id);
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index a5082331f246..862b043e5924 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -168,7 +168,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 		err = -1;
 	}
 
-	if (!verbose)
+	if (verbose <= 0)
 		goto out;
 
 	header_printed = false;
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 98a34664bb7e..9ce142de536d 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -73,7 +73,7 @@ static int map_browser__run(struct map_browser *browser)
 
 	if (ui_browser__show(&browser->b, browser->map->dso->long_name,
 			     "Press ESC to exit, %s / to search",
-			     verbose ? "" : "restart with -v to use") < 0)
+			     verbose > 0 ? "" : "restart with -v to use") < 0)
 		return -1;
 
 	while (1) {
@@ -81,7 +81,7 @@ static int map_browser__run(struct map_browser *browser)
 
 		switch (key) {
 		case '/':
-			if (verbose)
+			if (verbose > 0)
 				map_browser__search(browser);
 		default:
 			break;
@@ -117,7 +117,7 @@ int map__browse(struct map *map)
 
 		if (maxaddr < pos->end)
 			maxaddr = pos->end;
-		if (verbose) {
+		if (verbose > 0) {
 			u32 *idx = symbol__browser_index(pos);
 			*idx = mb.b.nr_entries;
 		}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 18cfcdc90356..5d632dca672a 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -648,7 +648,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 		ret += fmt->width(fmt, &dummy_hpp, hists);
 	}
 
-	if (verbose && hists__has(hists, sym)) /* Addr + origin */
+	if (verbose > 0 && hists__has(hists, sym)) /* Addr + origin */
 		ret += 3 + BITS_PER_LONG / 4;
 
 	return ret;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 06cc04e5806a..273f21fa32b5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1768,7 +1768,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	printf("%-*.*s----\n",
 	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
-	if (verbose)
+	if (verbose > 0)
 		symbol__annotate_hits(sym, evsel);
 
 	list_for_each_entry(pos, &notes->src->source, node) {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 2c0b52264a46..8c7504939113 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -9,6 +9,7 @@
 #include "asm/bug.h"
 
 static int max_cpu_num;
+static int max_present_cpu_num;
 static int max_node_num;
 static int *cpunode_map;
 
@@ -442,6 +443,7 @@ static void set_max_cpu_num(void)
 
 	/* set up default */
 	max_cpu_num = 4096;
+	max_present_cpu_num = 4096;
 
 	mnt = sysfs__mountpoint();
 	if (!mnt)
@@ -455,6 +457,17 @@ static void set_max_cpu_num(void)
 	}
 
 	ret = get_max_num(path, &max_cpu_num);
+	if (ret)
+		goto out;
+
+	/* get the highest present cpu number for a sparse allocation */
+	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
+	if (ret == PATH_MAX) {
+		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+		goto out;
+	}
+
+	ret = get_max_num(path, &max_present_cpu_num);
 
 out:
 	if (ret)
@@ -505,6 +518,15 @@ int cpu__max_cpu(void)
 	return max_cpu_num;
 }
 
+int cpu__max_present_cpu(void)
+{
+	if (unlikely(!max_present_cpu_num))
+		set_max_cpu_num();
+
+	return max_present_cpu_num;
+}
+
+
 int cpu__get_node(int cpu)
 {
 	if (unlikely(cpunode_map == NULL)) {
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 06bd689f5989..1a0549af8f5c 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -62,6 +62,7 @@ int cpu__setup_cpunode_map(void);
 
 int cpu__max_node(void);
 int cpu__max_cpu(void);
+int cpu__max_present_cpu(void);
 int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c1838b643108..03eb81f30d0d 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -203,11 +203,28 @@ int perf_debug_option(const char *str)
 		v = (v < 0) || (v > 10) ? 0 : v;
 	}
 
+	if (quiet)
+		v = -1;
+
 	*var->ptr = v;
 	free(s);
 	return 0;
 }
 
+int perf_quiet_option(void)
+{
+	struct debug_variable *var = &debug_variables[0];
+
+	/* disable all debug messages */
+	while (var->name) {
+		*var->ptr = -1;
+		var++;
+	}
+
+	quiet = true;
+	return 0;
+}
+
 #define DEBUG_WRAPPER(__n, __l)				\
 static int pr_ ## __n ## _wrapper(const char *fmt, ...)	\
 {							\
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index d242adc3d5a2..98832f5531d3 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -54,5 +54,6 @@ int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
 void perf_debug_setup(void);
+int perf_quiet_option(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 28d41e709128..1a03e9e310a4 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1058,7 +1058,7 @@ int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
 		return strlen("[unknown]");
-	if (verbose)
+	if (verbose > 0)
 		return dso->long_name_len;
 
 	return dso->short_name_len;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index bb964e86b09d..075fc77286bf 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -66,7 +66,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 		return 0;
 
 	if (env->nr_cpus_avail == 0)
-		env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+		env->nr_cpus_avail = cpu__max_present_cpu();
 
 	nr_cpus = env->nr_cpus_avail;
 	if (nr_cpus == -1)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3d12c16e5103..05714d548584 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -295,11 +295,7 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
 	u32 nrc, nra;
 	int ret;
 
-	nr = sysconf(_SC_NPROCESSORS_CONF);
-	if (nr < 0)
-		return -1;
-
-	nrc = (u32)(nr & UINT_MAX);
+	nrc = cpu__max_present_cpu();
 
 	nr = sysconf(_SC_NPROCESSORS_ONLN);
 	if (nr < 0)
@@ -505,24 +501,29 @@ static void free_cpu_topo(struct cpu_topo *tp)
 
 static struct cpu_topo *build_cpu_topology(void)
 {
-	struct cpu_topo *tp;
+	struct cpu_topo *tp = NULL;
 	void *addr;
 	u32 nr, i;
 	size_t sz;
 	long ncpus;
 	int ret = -1;
+	struct cpu_map *map;
 
-	ncpus = sysconf(_SC_NPROCESSORS_CONF);
-	if (ncpus < 0)
+	ncpus = cpu__max_present_cpu();
+
+	/* build online CPU map */
+	map = cpu_map__new(NULL);
+	if (map == NULL) {
+		pr_debug("failed to get system cpumap\n");
 		return NULL;
+	}
 
 	nr = (u32)(ncpus & UINT_MAX);
 
 	sz = nr * sizeof(char *);
-
 	addr = calloc(1, sizeof(*tp) + 2 * sz);
 	if (!addr)
-		return NULL;
+		goto out_free;
 
 	tp = addr;
 	tp->cpu_nr = nr;
@@ -532,10 +533,16 @@ static struct cpu_topo *build_cpu_topology(void)
 	tp->thread_siblings = addr;
 
 	for (i = 0; i < nr; i++) {
+		if (!cpu_map__has(map, i))
+			continue;
+
 		ret = build_cpu_topo(tp, i);
 		if (ret < 0)
 			break;
 	}
+
+out_free:
+	cpu_map__put(map);
 	if (ret) {
 		free_cpu_topo(tp);
 		tp = NULL;
@@ -1126,7 +1133,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 {
 	int nr, i;
 	char *str;
-	int cpu_nr = ph->env.nr_cpus_online;
+	int cpu_nr = ph->env.nr_cpus_avail;
 
 	nr = ph->env.nr_sibling_cores;
 	str = ph->env.sibling_cores;
@@ -1781,7 +1788,7 @@ static int process_cpu_topology(struct perf_file_section *section,
 	u32 nr, i;
 	char *str;
 	struct strbuf sb;
-	int cpu_nr = ph->env.nr_cpus_online;
+	int cpu_nr = ph->env.nr_cpus_avail;
 	u64 size = 0;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
@@ -1862,7 +1869,7 @@ static int process_cpu_topology(struct perf_file_section *section,
 		if (ph->needs_swap)
 			nr = bswap_32(nr);
 
-		if (nr > (u32)cpu_nr) {
+		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 32c6a939e4cc..eaf72a938fb4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -69,7 +69,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	 */
 	if (h->ms.sym) {
 		symlen = h->ms.sym->namelen + 4;
-		if (verbose)
+		if (verbose > 0)
 			symlen += BITS_PER_LONG / 4 + 2 + 3;
 		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
 	} else {
@@ -93,7 +93,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	if (h->branch_info) {
 		if (h->branch_info->from.sym) {
 			symlen = (int)h->branch_info->from.sym->namelen + 4;
-			if (verbose)
+			if (verbose > 0)
 				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
 
@@ -107,7 +107,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 		if (h->branch_info->to.sym) {
 			symlen = (int)h->branch_info->to.sym->namelen + 4;
-			if (verbose)
+			if (verbose > 0)
 				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 281e44af31e2..67a8aebc67ab 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2318,24 +2318,20 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term)
 	return term->type_term != PARSE_EVENTS__TERM_TYPE_USER;
 }
 
-static int new_term(struct parse_events_term **_term, int type_val,
-		    int type_term, char *config,
-		    char *str, u64 num, int err_term, int err_val)
+static int new_term(struct parse_events_term **_term,
+		    struct parse_events_term *temp,
+		    char *str, u64 num)
 {
 	struct parse_events_term *term;
 
-	term = zalloc(sizeof(*term));
+	term = malloc(sizeof(*term));
 	if (!term)
 		return -ENOMEM;
 
+	*term = *temp;
 	INIT_LIST_HEAD(&term->list);
-	term->type_val  = type_val;
-	term->type_term = type_term;
-	term->config = config;
-	term->err_term = err_term;
-	term->err_val  = err_val;
 
-	switch (type_val) {
+	switch (term->type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
 		term->val.num = num;
 		break;
@@ -2353,15 +2349,22 @@ static int new_term(struct parse_events_term **_term, int type_val,
 
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
+			   bool no_value,
 			   void *loc_term_, void *loc_val_)
 {
 	YYLTYPE *loc_term = loc_term_;
 	YYLTYPE *loc_val = loc_val_;
 
-	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
-			config, NULL, num,
-			loc_term ? loc_term->first_column : 0,
-			loc_val ? loc_val->first_column : 0);
+	struct parse_events_term temp = {
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = type_term,
+		.config    = config,
+		.no_value  = no_value,
+		.err_term  = loc_term ? loc_term->first_column : 0,
+		.err_val   = loc_val  ? loc_val->first_column  : 0,
+	};
+
+	return new_term(term, &temp, NULL, num);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
@@ -2371,37 +2374,45 @@ int parse_events_term__str(struct parse_events_term **term,
 	YYLTYPE *loc_term = loc_term_;
 	YYLTYPE *loc_val = loc_val_;
 
-	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
-			config, str, 0,
-			loc_term ? loc_term->first_column : 0,
-			loc_val ? loc_val->first_column : 0);
+	struct parse_events_term temp = {
+		.type_val  = PARSE_EVENTS__TERM_TYPE_STR,
+		.type_term = type_term,
+		.config    = config,
+		.err_term  = loc_term ? loc_term->first_column : 0,
+		.err_val   = loc_val  ? loc_val->first_column  : 0,
+	};
+
+	return new_term(term, &temp, str, 0);
 }
 
 int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx)
 {
 	struct event_symbol *sym;
+	struct parse_events_term temp = {
+		.type_val  = PARSE_EVENTS__TERM_TYPE_STR,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+		.config    = config ?: (char *) "event",
+	};
 
 	BUG_ON(idx >= PERF_COUNT_HW_MAX);
 	sym = &event_symbols_hw[idx];
 
-	if (config)
-		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
-				PARSE_EVENTS__TERM_TYPE_USER, config,
-				(char *) sym->symbol, 0, 0, 0);
-	else
-		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
-				PARSE_EVENTS__TERM_TYPE_USER,
-				(char *) "event", (char *) sym->symbol,
-				0, 0, 0);
+	return new_term(term, &temp, (char *) sym->symbol, 0);
 }
 
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term)
 {
-	return new_term(new, term->type_val, term->type_term, term->config,
-			term->val.str, term->val.num,
-			term->err_term, term->err_val);
+	struct parse_events_term temp = {
+		.type_val  = term->type_val,
+		.type_term = term->type_term,
+		.config    = term->config,
+		.err_term  = term->err_term,
+		.err_val   = term->err_val,
+	};
+
+	return new_term(new, &temp, term->val.str, term->val.num);
 }
 
 void parse_events_terms__purge(struct list_head *terms)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index da246a3ddb69..1af6a267c21b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -94,6 +94,7 @@ struct parse_events_term {
 	int type_term;
 	struct list_head list;
 	bool used;
+	bool no_value;
 
 	/* error string indexes for within parsed string */
 	int err_term;
@@ -122,6 +123,7 @@ void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
+			   bool novalue,
 			   void *loc_term, void *loc_val);
 int parse_events_term__str(struct parse_events_term **term,
 			   int type_term, char *config, char *str,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index a14b47ab3879..30f018ea1370 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -252,7 +252,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 			if (!strcasecmp(alias->name, $1)) {
 				ALLOC_LIST(head);
 				ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, &@1, NULL));
+					$1, 1, false, &@1, NULL));
 				list_add_tail(&term->list, head);
 
 				if (!parse_events_add_pmu(data, list,
@@ -282,7 +282,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					&pmu_name, 1, &@1, NULL));
+					&pmu_name, 1, false, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
@@ -548,7 +548,7 @@ PE_NAME '=' PE_VALUE
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3, &@1, &@3));
+					$1, $3, false, &@1, &@3));
 	$$ = term;
 }
 |
@@ -566,7 +566,7 @@ PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, &@1, NULL));
+					$1, 1, true, &@1, NULL));
 	$$ = term;
 }
 |
@@ -591,7 +591,7 @@ PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3));
 	$$ = term;
 }
 |
@@ -599,7 +599,7 @@ PE_TERM
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL));
 	$$ = term;
 }
 |
@@ -620,7 +620,7 @@ PE_NAME array '=' PE_VALUE
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $4, &@1, &@4));
+					$1, $4, false, &@1, &@4));
 	term->array = $2;
 	$$ = term;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 49bfee0e3d9e..12f84dd2ac5d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -745,7 +745,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 		}
 	}
 
-	if (verbose)
+	if (verbose > 0)
 		printf("Required parameter '%s' not specified\n", term->config);
 
 	return -1;
@@ -803,7 +803,7 @@ static int pmu_config_term(struct list_head *formats,
 
 	format = pmu_find_format(formats, term->config);
 	if (!format) {
-		if (verbose)
+		if (verbose > 0)
 			printf("Invalid event/parameter '%s'\n", term->config);
 		if (err) {
 			char *pmu_term = pmu_formats_string(formats);
@@ -834,11 +834,20 @@ static int pmu_config_term(struct list_head *formats,
 	 * Either directly use a numeric term, or try to translate string terms
 	 * using event parameters.
 	 */
-	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+		if (term->no_value &&
+		    bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) {
+			if (err) {
+				err->idx = term->err_val;
+				err->str = strdup("no value assigned for term");
+			}
+			return -EINVAL;
+		}
+
 		val = term->val.num;
-	else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+	} else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 		if (strcmp(term->val.str, "?")) {
-			if (verbose) {
+			if (verbose > 0) {
 				pr_info("Invalid sysfs entry %s=%s\n",
 						term->config, term->val.str);
 			}
@@ -1223,7 +1232,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			printf("%*s", 8, "[");
 			wordwrap(aliases[j].desc, 8, columns, 0);
 			printf("]\n");
-			if (verbose)
+			if (verbose > 0)
 				printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
 		} else
 			printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 35f5b7b7715c..28fb62c32678 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -594,7 +594,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
 		 tp->module ? : "kernel");
 
-	dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+	dinfo = debuginfo_cache__open(tp->module, verbose <= 0);
 	if (dinfo)
 		ret = debuginfo__find_probe_point(dinfo,
 						 (unsigned long)addr, pp);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 089438da1f7f..89b532c47cc4 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -368,10 +368,10 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 		if (node->map) {
 			struct map *map = node->map;
 			const char *dsoname = "[unknown]";
-			if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+			if (map && map->dso) {
 				if (symbol_conf.show_kernel_path && map->dso->long_name)
 					dsoname = map->dso->long_name;
-				else if (map->dso->name)
+				else
 					dsoname = map->dso->name;
 			}
 			pydict_set_item_string_decref(pyelem, "dso",
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4cdbc8f5f14d..1dd617d116b5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -932,7 +932,7 @@ static void branch_stack__printf(struct perf_sample *sample)
 
 		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
 			i, e->from, e->to,
-			e->flags.cycles,
+			(unsigned short)e->flags.cycles,
 			e->flags.mispred ? "M" : " ",
 			e->flags.predicted ? "P" : " ",
 			e->flags.abort ? "A" : " ",
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index c8680984d2d6..af415febbc46 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,8 +1,15 @@
 #!/usr/bin/python2
 
-from distutils.core import setup, Extension
 from os import getenv
 
+cc = getenv("CC")
+if cc == "clang":
+    from _sysconfigdata import build_time_vars
+    from re import sub
+    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
+
+from distutils.core import setup, Extension
+
 from distutils.command.build_ext   import build_ext   as _build_ext
 from distutils.command.install_lib import install_lib as _install_lib
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index df622f4e301e..0ff622288d24 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -151,7 +151,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
 	if (!dso_l || !dso_r)
 		return cmp_null(dso_r, dso_l);
 
-	if (verbose) {
+	if (verbose > 0) {
 		dso_name_l = dso_l->long_name;
 		dso_name_r = dso_r->long_name;
 	} else {
@@ -172,8 +172,8 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
 				     size_t size, unsigned int width)
 {
 	if (map && map->dso) {
-		const char *dso_name = !verbose ? map->dso->short_name :
-			map->dso->long_name;
+		const char *dso_name = verbose > 0 ? map->dso->long_name :
+			map->dso->short_name;
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
 	}
 
@@ -261,7 +261,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 {
 	size_t ret = 0;
 
-	if (verbose) {
+	if (verbose > 0) {
 		char o = map ? dso__symtab_origin(map->dso) : '!';
 		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
 				       BITS_PER_LONG / 4 + 2, ip, o);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 39345c2ddfc2..0d51334a9b46 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -344,7 +344,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	for (i = 0; i < 3; i++)
 		update_stats(&ps->res_stats[i], count[i]);
 
-	if (verbose) {
+	if (verbose > 0) {
 		fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
 			perf_evsel__name(counter), count[0], count[1], count[2]);
 	}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index adbc6c02c3aa..4e59ddeb4eda 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -213,7 +213,7 @@ static bool want_demangle(bool is_kernel_sym)
 
 static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 {
-	int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
+	int demangle_flags = verbose > 0 ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
 	char *demangled = NULL;
 
 	/*

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-02-11 18:12 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-02-11 18:12 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 451d24d1e5f40bad000fa9abe36ddb16fc9928cb perf/core: Fix crash in perf_event_read()

A kernel crash fix plus three tooling fixes.

 Thanks,

	Ingo

------------------>
Krister Johansen (1):
      perf callchain: Reference count maps

Namhyung Kim (2):
      perf diff: Fix segfault on 'perf diff -o N' option
      perf diff: Fix -o/--order option behavior (again)

Peter Zijlstra (1):
      perf/core: Fix crash in perf_event_read()


 kernel/events/core.c        | 25 +++++++++++++++----------
 tools/perf/builtin-diff.c   |  2 +-
 tools/perf/ui/hist.c        | 10 ++++++++++
 tools/perf/util/callchain.c | 11 +++++++++--
 tools/perf/util/callchain.h |  6 ++++++
 tools/perf/util/hist.c      |  7 +++++++
 tools/perf/util/hist.h      |  7 +++++++
 7 files changed, 55 insertions(+), 13 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5aaa806702d..e235bb991bdd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3487,14 +3487,15 @@ struct perf_read_data {
 	int ret;
 };
 
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
-	int event_cpu = event->oncpu;
 	u16 local_pkg, event_pkg;
 
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		event_pkg =  topology_physical_package_id(event_cpu);
-		local_pkg =  topology_physical_package_id(local_cpu);
+		int local_cpu = smp_processor_id();
+
+		event_pkg = topology_physical_package_id(event_cpu);
+		local_pkg = topology_physical_package_id(local_cpu);
 
 		if (event_pkg == local_pkg)
 			return local_cpu;
@@ -3624,7 +3625,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0, cpu_to_read, local_cpu;
+	int event_cpu, ret = 0;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3637,21 +3638,25 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.ret = 0,
 		};
 
-		local_cpu = get_cpu();
-		cpu_to_read = find_cpu_to_read(event, local_cpu);
-		put_cpu();
+		event_cpu = READ_ONCE(event->oncpu);
+		if ((unsigned)event_cpu >= nr_cpu_ids)
+			return 0;
+
+		preempt_disable();
+		event_cpu = __perf_event_read_cpu(event, event_cpu);
 
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
 		 *
-		 * If event->oncpu isn't a valid CPU it means the event got
+		 * If event_cpu isn't a valid CPU it means the event got
 		 * scheduled out and that will have updated the event count.
 		 *
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+		preempt_enable();
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4e2d0c..933aeec46f4a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1199,7 +1199,7 @@ static int ui_init(void)
 		BUG_ON(1);
 	}
 
-	perf_hpp__register_sort_field(fmt);
+	perf_hpp__prepend_sort_field(fmt);
 	return 0;
 }
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 37388397b5bc..18cfcdc90356 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 	list_add_tail(&format->sort_list, &list->sorts);
 }
 
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format)
+{
+	list_add(&format->sort_list, &list->sorts);
+}
+
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del(&format->list);
@@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 	perf_hpp_list__for_each_sort_list(list, fmt) {
 		struct perf_hpp_fmt *pos;
 
+		/* skip sort-only fields ("sort_compute" in perf diff) */
+		if (!fmt->entry && !fmt->color)
+			continue;
+
 		perf_hpp_list__for_each_format(list, pos) {
 			if (fmt_equal(fmt, pos))
 				goto next;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42922512c1c6..8b610dd9e2f6 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -437,7 +437,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
-		call->ms.map = cursor_node->map;
+		call->ms.map = map__get(cursor_node->map);
 
 		if (cursor_node->branch) {
 			call->branch_count = 1;
@@ -477,6 +477,7 @@ add_child(struct callchain_node *parent,
 
 		list_for_each_entry_safe(call, tmp, &new->val, list) {
 			list_del(&call->list);
+			map__zput(call->ms.map);
 			free(call);
 		}
 		free(new);
@@ -761,6 +762,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 					list->ms.map, list->ms.sym,
 					false, NULL, 0, 0);
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -811,7 +813,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	}
 
 	node->ip = ip;
-	node->map = map;
+	map__zput(node->map);
+	node->map = map__get(map);
 	node->sym = sym;
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
@@ -1142,11 +1145,13 @@ static void free_callchain_node(struct callchain_node *node)
 
 	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -1210,6 +1215,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 				goto out;
 			*new = *chain;
 			new->has_children = false;
+			map__get(new->ms.map);
 			list_add_tail(&new->list, &head);
 		}
 		parent = parent->parent;
@@ -1230,6 +1236,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 out:
 	list_for_each_entry_safe(chain, new, &head, list) {
 		list_del(&chain->list);
+		map__zput(chain->ms.map);
 		free(chain);
 	}
 	return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 35c8e379530f..4f4b60f1558a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"
+#include "map.h"
 #include "symbol.h"
 
 #define HELP_PAD "\t\t\t\t"
@@ -184,8 +185,13 @@ int callchain_merge(struct callchain_cursor *cursor,
  */
 static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 {
+	struct callchain_cursor_node *node;
+
 	cursor->nr = 0;
 	cursor->last = &cursor->first;
+
+	for (node = cursor->first; node != NULL; node = node->next)
+		map__zput(node->map);
 }
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6770a9645609..7d1b7d33e644 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
+#include "map.h"
 #include "session.h"
 #include "sort.h"
 #include "evlist.h"
@@ -1019,6 +1020,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
+	struct map *alm = NULL;
+
+	if (al && al->map)
+		alm = map__get(al->map);
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
@@ -1058,6 +1063,8 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (!err)
 		err = err2;
 
+	map__put(alm);
+
 	return err;
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4b6514eeef5..28c216e3d5b7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -283,6 +283,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list,
 				    struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 					struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format);
 
 static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
 {
@@ -294,6 +296,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
 }
 
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
 #define perf_hpp_list__for_each_format(_list, format) \
 	list_for_each_entry(format, &(_list)->fields, list)
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-02-02 21:01 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-02-02 21:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton, Jiri Olsa, Alexander Shishkin

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: fff4b87e594ad3d2e4f51e8d3d86a6f9d3d8b654 perf/x86/intel/uncore: Make package handling more robust

Five kernel fixes:

 - an mmap tracing ABI fix for certain mappings
 - a use-after-free fix, found via KASAN
 - three CPU hotplug related x86 PMU driver fixes

 Thanks,

	Ingo

------------------>
Peter Zijlstra (2):
      perf/core: Fix use-after-free bug
      perf/core: Fix PERF_RECORD_MMAP2 prot/flags for anonymous memory

Thomas Gleixner (3):
      perf/x86/intel/rapl: Make package handling more robust
      perf/x86/intel/uncore: Clean up hotplug conversion fallout
      perf/x86/intel/uncore: Make package handling more robust


 arch/x86/events/intel/rapl.c   |  60 +++++------
 arch/x86/events/intel/uncore.c | 232 ++++++++++++++++-------------------------
 include/linux/cpuhotplug.h     |   3 -
 kernel/events/core.c           |  69 ++++++++----
 4 files changed, 163 insertions(+), 201 deletions(-)

diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 17c3564d087a..22ef4f72cf32 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
 
 	/* must be done before validate_group */
 	pmu = cpu_to_rapl_pmu(event->cpu);
+	if (!pmu)
+		return -EINVAL;
 	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = msr;
@@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu)
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
+	if (!pmu) {
+		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+		if (!pmu)
+			return -ENOMEM;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	}
+
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.
@@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_cpu_prepare(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
-	if (pmu)
-		return 0;
-
-	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-	if (!pmu)
-		return -ENOMEM;
-
-	raw_spin_lock_init(&pmu->lock);
-	INIT_LIST_HEAD(&pmu->active_list);
-	pmu->pmu = &rapl_pmus->pmu;
-	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-	pmu->cpu = -1;
-	rapl_hrtimer_init(pmu);
-	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
-	return 0;
-}
-
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -803,29 +804,21 @@ static int __init rapl_pmu_init(void)
 	/*
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
-
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
-				rapl_cpu_prepare, NULL);
-	if (ret)
-		goto out;
-
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
 				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
-		goto out1;
+		goto out;
 
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out2;
+		goto out1;
 
 	rapl_advertise();
 	return 0;
 
-out2:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out1:
-	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
@@ -836,7 +829,6 @@ module_init(rapl_pmu_init);
 static void __exit intel_rapl_exit(void)
 {
 	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 8c4ccdc3a3f3..1ab45976474d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
 
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
-	return pmu->boxes[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -764,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
 	pmu->registered = false;
 }
 
-static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
-{
-	struct intel_uncore_pmu *pmu = type->pmus;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	if (pmu) {
-		pkg = topology_physical_package_id(cpu);
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (box)
-				uncore_box_exit(box);
-		}
-	}
-}
-
-static void uncore_exit_boxes(void *dummy)
-{
-	struct intel_uncore_type **types;
-
-	for (types = uncore_msr_uncores; *types; types++)
-		__uncore_exit_boxes(*types++, smp_processor_id());
-}
-
 static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 {
 	int pkg;
@@ -1058,86 +1040,6 @@ static void uncore_pci_exit(void)
 	}
 }
 
-static int uncore_cpu_dying(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (box && atomic_dec_return(&box->refcnt) == 0)
-				uncore_box_exit(box);
-		}
-	}
-	return 0;
-}
-
-static int first_init;
-
-static int uncore_cpu_starting(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg, ncpus = 1;
-
-	if (first_init) {
-		/*
-		 * On init we get the number of online cpus in the package
-		 * and set refcount for all of them.
-		 */
-		ncpus = cpumask_weight(topology_core_cpumask(cpu));
-	}
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (!box)
-				continue;
-			/* The first cpu on a package activates the box */
-			if (atomic_add_return(ncpus, &box->refcnt) == ncpus)
-				uncore_box_init(box);
-		}
-	}
-
-	return 0;
-}
-
-static int uncore_cpu_prepare(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			if (pmu->boxes[pkg])
-				continue;
-			/* First cpu of a package allocates the box */
-			box = uncore_alloc_box(type, cpu_to_node(cpu));
-			if (!box)
-				return -ENOMEM;
-			box->pmu = pmu;
-			box->pkgid = pkg;
-			pmu->boxes[pkg] = box;
-		}
-	}
-	return 0;
-}
-
 static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 				   int new_cpu)
 {
@@ -1177,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
 
 static int uncore_event_cpu_offline(unsigned int cpu)
 {
-	int target;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	int i, pkg, target;
 
 	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
-		return 0;
-
+		goto unref;
 	/* Find a new cpu to collect uncore events */
 	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
@@ -1194,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu)
 
 	uncore_change_context(uncore_msr_uncores, cpu, target);
 	uncore_change_context(uncore_pci_uncores, cpu, target);
+
+unref:
+	/* Clear the references */
+	pkg = topology_logical_package_id(cpu);
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (box && atomic_dec_return(&box->refcnt) == 0)
+				uncore_box_exit(box);
+		}
+	}
 	return 0;
 }
 
+static int allocate_boxes(struct intel_uncore_type **types,
+			 unsigned int pkg, unsigned int cpu)
+{
+	struct intel_uncore_box *box, *tmp;
+	struct intel_uncore_type *type;
+	struct intel_uncore_pmu *pmu;
+	LIST_HEAD(allocated);
+	int i;
+
+	/* Try to allocate all required boxes */
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			if (pmu->boxes[pkg])
+				continue;
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
+			if (!box)
+				goto cleanup;
+			box->pmu = pmu;
+			box->pkgid = pkg;
+			list_add(&box->active_list, &allocated);
+		}
+	}
+	/* Install them in the pmus */
+	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+		list_del_init(&box->active_list);
+		box->pmu->boxes[pkg] = box;
+	}
+	return 0;
+
+cleanup:
+	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+		list_del_init(&box->active_list);
+		kfree(box);
+	}
+	return -ENOMEM;
+}
+
 static int uncore_event_cpu_online(unsigned int cpu)
 {
-	int target;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	int i, ret, pkg, target;
+
+	pkg = topology_logical_package_id(cpu);
+	ret = allocate_boxes(types, pkg, cpu);
+	if (ret)
+		return ret;
+
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (!box && atomic_inc_return(&box->refcnt) == 1)
+				uncore_box_init(box);
+		}
+	}
 
 	/*
 	 * Check if there is an online cpu in the package
@@ -1389,38 +1363,16 @@ static int __init intel_uncore_init(void)
 	if (cret && pret)
 		return -ENODEV;
 
-	/*
-	 * Install callbacks. Core will call them for each online cpu.
-	 *
-	 * The first online cpu of each package allocates and takes
-	 * the refcounts for all other online cpus in that package.
-	 * If msrs are not enabled no allocation is required and
-	 * uncore_cpu_prepare() is not called for each online cpu.
-	 */
-	if (!cret) {
-	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-				       "perf/x86/intel/uncore:prepare",
-				       uncore_cpu_prepare, NULL);
-		if (ret)
-			goto err;
-	} else {
-		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "perf/x86/intel/uncore:prepare",
-					  uncore_cpu_prepare, NULL);
-	}
-	first_init = 1;
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "perf/x86/uncore:starting",
-			  uncore_cpu_starting, uncore_cpu_dying);
-	first_init = 0;
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "perf/x86/uncore:online",
-			  uncore_event_cpu_online, uncore_event_cpu_offline);
+	/* Install hotplug callbacks to setup the targets for each package */
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+				"perf/x86/intel/uncore:online",
+				uncore_event_cpu_online,
+				uncore_event_cpu_offline);
+	if (ret)
+		goto err;
 	return 0;
 
 err:
-	/* Undo box->init_box() */
-	on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
 	return ret;
@@ -1429,9 +1381,7 @@ module_init(intel_uncore_init);
 
 static void __exit intel_uncore_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
 }
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d936a0021839..921acaaa1601 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -8,9 +8,7 @@ enum cpuhp_state {
 	CPUHP_CREATE_THREADS,
 	CPUHP_PERF_PREPARE,
 	CPUHP_PERF_X86_PREPARE,
-	CPUHP_PERF_X86_UNCORE_PREP,
 	CPUHP_PERF_X86_AMD_UNCORE_PREP,
-	CPUHP_PERF_X86_RAPL_PREP,
 	CPUHP_PERF_BFIN,
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,
@@ -86,7 +84,6 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
-	CPUHP_AP_PERF_X86_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 110b38a58493..e5aaa806702d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1469,7 +1469,6 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-
 	lockdep_assert_held(&ctx->lock);
 
 	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1624,6 +1623,8 @@ static void perf_group_attach(struct perf_event *event)
 {
 	struct perf_event *group_leader = event->group_leader, *pos;
 
+	lockdep_assert_held(&event->ctx->lock);
+
 	/*
 	 * We can have double attach due to group movement in perf_event_open.
 	 */
@@ -1697,6 +1698,8 @@ static void perf_group_detach(struct perf_event *event)
 	struct perf_event *sibling, *tmp;
 	struct list_head *list = NULL;
 
+	lockdep_assert_held(&event->ctx->lock);
+
 	/*
 	 * We can have double detach due to exit/hot-unplug + close.
 	 */
@@ -1895,9 +1898,29 @@ __perf_remove_from_context(struct perf_event *event,
  */
 static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
 {
-	lockdep_assert_held(&event->ctx->mutex);
+	struct perf_event_context *ctx = event->ctx;
+
+	lockdep_assert_held(&ctx->mutex);
 
 	event_function_call(event, __perf_remove_from_context, (void *)flags);
+
+	/*
+	 * The above event_function_call() can NO-OP when it hits
+	 * TASK_TOMBSTONE. In that case we must already have been detached
+	 * from the context (by perf_event_exit_event()) but the grouping
+	 * might still be in-tact.
+	 */
+	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+	if ((flags & DETACH_GROUP) &&
+	    (event->attach_state & PERF_ATTACH_GROUP)) {
+		/*
+		 * Since in that case we cannot possibly be scheduled, simply
+		 * detach now.
+		 */
+		raw_spin_lock_irq(&ctx->lock);
+		perf_group_detach(event);
+		raw_spin_unlock_irq(&ctx->lock);
+	}
 }
 
 /*
@@ -6609,6 +6632,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	char *buf = NULL;
 	char *name;
 
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	if (vma->vm_flags & VM_MAYSHARE)
+		flags = MAP_SHARED;
+	else
+		flags = MAP_PRIVATE;
+
+	if (vma->vm_flags & VM_DENYWRITE)
+		flags |= MAP_DENYWRITE;
+	if (vma->vm_flags & VM_MAYEXEC)
+		flags |= MAP_EXECUTABLE;
+	if (vma->vm_flags & VM_LOCKED)
+		flags |= MAP_LOCKED;
+	if (vma->vm_flags & VM_HUGETLB)
+		flags |= MAP_HUGETLB;
+
 	if (file) {
 		struct inode *inode;
 		dev_t dev;
@@ -6635,27 +6679,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		maj = MAJOR(dev);
 		min = MINOR(dev);
 
-		if (vma->vm_flags & VM_READ)
-			prot |= PROT_READ;
-		if (vma->vm_flags & VM_WRITE)
-			prot |= PROT_WRITE;
-		if (vma->vm_flags & VM_EXEC)
-			prot |= PROT_EXEC;
-
-		if (vma->vm_flags & VM_MAYSHARE)
-			flags = MAP_SHARED;
-		else
-			flags = MAP_PRIVATE;
-
-		if (vma->vm_flags & VM_DENYWRITE)
-			flags |= MAP_DENYWRITE;
-		if (vma->vm_flags & VM_MAYEXEC)
-			flags |= MAP_EXECUTABLE;
-		if (vma->vm_flags & VM_LOCKED)
-			flags |= MAP_LOCKED;
-		if (vma->vm_flags & VM_HUGETLB)
-			flags |= MAP_HUGETLB;
-
 		goto got_name;
 	} else {
 		if (vma->vm_ops && vma->vm_ops->name) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-01-18  9:27 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-01-18  9:27 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 31f5260a7653e6042ac28578db1c61e84f2d7898 Merge tag 'perf-urgent-for-mingo-4.10-20170117' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

An Intel PMU driver hotplug fix and three 'perf probe' tooling fixes.

 Thanks,

	Ingo

------------------>
Masami Hiramatsu (3):
      perf probe: Fix to show correct locations for events on modules
      perf probe: Add error checks to offline probe post-processing
      perf probe: Fix to probe on gcc generated functions in modules

Zhou Chengming (1):
      perf/x86/intel: Handle exclusive threadid correctly on CPU hotplug


 arch/x86/events/intel/core.c   |  7 +++-
 tools/perf/util/probe-event.c  | 95 +++++++++++++++++++++++++++---------------
 tools/perf/util/probe-finder.c | 15 ++++---
 tools/perf/util/probe-finder.h |  3 ++
 4 files changed, 77 insertions(+), 43 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d611cab214a6..eb1484c86bb4 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3176,13 +3176,16 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
 		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
+			struct cpu_hw_events *sibling;
 			struct intel_excl_cntrs *c;
 
-			c = per_cpu(cpu_hw_events, i).excl_cntrs;
+			sibling = &per_cpu(cpu_hw_events, i);
+			c = sibling->excl_cntrs;
 			if (c && c->core_id == core_id) {
 				cpuc->kfree_on_online[1] = cpuc->excl_cntrs;
 				cpuc->excl_cntrs = c;
-				cpuc->excl_thread_id = 1;
+				if (!sibling->excl_thread_id)
+					cpuc->excl_thread_id = 1;
 				break;
 			}
 		}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 4a57c8a60bd9..6a6f44dd594b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -610,6 +610,33 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	return ret ? : -ENOENT;
 }
 
+/* Adjust symbol name and address */
+static int post_process_probe_trace_point(struct probe_trace_point *tp,
+					   struct map *map, unsigned long offs)
+{
+	struct symbol *sym;
+	u64 addr = tp->address + tp->offset - offs;
+
+	sym = map__find_symbol(map, addr);
+	if (!sym)
+		return -ENOENT;
+
+	if (strcmp(sym->name, tp->symbol)) {
+		/* If we have no realname, use symbol for it */
+		if (!tp->realname)
+			tp->realname = tp->symbol;
+		else
+			free(tp->symbol);
+		tp->symbol = strdup(sym->name);
+		if (!tp->symbol)
+			return -ENOMEM;
+	}
+	tp->offset = addr - sym->start;
+	tp->address -= offs;
+
+	return 0;
+}
+
 /*
  * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
  * and generate new symbols with suffixes such as .constprop.N or .isra.N
@@ -622,11 +649,9 @@ static int
 post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 					int ntevs, const char *pathname)
 {
-	struct symbol *sym;
 	struct map *map;
 	unsigned long stext = 0;
-	u64 addr;
-	int i;
+	int i, ret = 0;
 
 	/* Prepare a map for offline binary */
 	map = dso__new_map(pathname);
@@ -636,23 +661,14 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		addr = tevs[i].point.address + tevs[i].point.offset - stext;
-		sym = map__find_symbol(map, addr);
-		if (!sym)
-			continue;
-		if (!strcmp(sym->name, tevs[i].point.symbol))
-			continue;
-		/* If we have no realname, use symbol for it */
-		if (!tevs[i].point.realname)
-			tevs[i].point.realname = tevs[i].point.symbol;
-		else
-			free(tevs[i].point.symbol);
-		tevs[i].point.symbol = strdup(sym->name);
-		tevs[i].point.offset = addr - sym->start;
+		ret = post_process_probe_trace_point(&tevs[i].point,
+						     map, stext);
+		if (ret < 0)
+			break;
 	}
 	map__put(map);
 
-	return 0;
+	return ret;
 }
 
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
@@ -682,18 +698,31 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 	return ret;
 }
 
-static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
-					    int ntevs, const char *module)
+static int
+post_process_module_probe_trace_events(struct probe_trace_event *tevs,
+				       int ntevs, const char *module,
+				       struct debuginfo *dinfo)
 {
+	Dwarf_Addr text_offs = 0;
 	int i, ret = 0;
 	char *mod_name = NULL;
+	struct map *map;
 
 	if (!module)
 		return 0;
 
-	mod_name = find_module_name(module);
+	map = get_target_map(module, false);
+	if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
+		pr_warning("Failed to get ELF symbols for %s\n", module);
+		return -EINVAL;
+	}
 
+	mod_name = find_module_name(module);
 	for (i = 0; i < ntevs; i++) {
+		ret = post_process_probe_trace_point(&tevs[i].point,
+						map, (unsigned long)text_offs);
+		if (ret < 0)
+			break;
 		tevs[i].point.module =
 			strdup(mod_name ? mod_name : module);
 		if (!tevs[i].point.module) {
@@ -703,6 +732,8 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	free(mod_name);
+	map__put(map);
+
 	return ret;
 }
 
@@ -760,7 +791,7 @@ arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unuse
 static int post_process_probe_trace_events(struct perf_probe_event *pev,
 					   struct probe_trace_event *tevs,
 					   int ntevs, const char *module,
-					   bool uprobe)
+					   bool uprobe, struct debuginfo *dinfo)
 {
 	int ret;
 
@@ -768,7 +799,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
 		ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
 	else if (module)
 		/* Currently ref_reloc_sym based probe is not for drivers */
-		ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+		ret = post_process_module_probe_trace_events(tevs, ntevs,
+							     module, dinfo);
 	else
 		ret = post_process_kernel_probe_trace_events(tevs, ntevs);
 
@@ -812,30 +844,27 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 		}
 	}
 
-	debuginfo__delete(dinfo);
-
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
 		ret = post_process_probe_trace_events(pev, *tevs, ntevs,
-						pev->target, pev->uprobes);
+					pev->target, pev->uprobes, dinfo);
 		if (ret < 0 || ret == ntevs) {
+			pr_debug("Post processing failed or all events are skipped. (%d)\n", ret);
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
+			ntevs = 0;
 		}
-		if (ret != ntevs)
-			return ret < 0 ? ret : ntevs;
-		ntevs = 0;
-		/* Fall through */
 	}
 
+	debuginfo__delete(dinfo);
+
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
 		pr_warning("Probe point '%s' not found.\n",
 			   synthesize_perf_probe_point(&pev->point));
 		return -ENOENT;
-	}
-	/* Error path : ntevs < 0 */
-	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
-	if (ntevs < 0) {
+	} else if (ntevs < 0) {
+		/* Error path : ntevs < 0 */
+		pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
 		if (ntevs == -EBADF)
 			pr_warning("Warning: No dwarf info found in the vmlinux - "
 				"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df4debe564da..0d9d6e0803b8 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1501,7 +1501,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 }
 
 /* For the kernel module, we need a special code to get a DIE */
-static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
 {
 	int n, i;
 	Elf32_Word shndx;
@@ -1530,6 +1531,8 @@ static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
 			if (!shdr)
 				return -ENOENT;
 			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
 		}
 	}
 	return 0;
@@ -1543,16 +1546,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 	Dwarf_Addr _addr = 0, baseaddr = 0;
 	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
-	bool reloc = false;
 
-retry:
+	/* We always need to relocate the address for aranges */
+	if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
+		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-		if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-			addr += baseaddr;
-			reloc = true;
-			goto retry;
-		}
 		pr_warning("Failed to find debug information for address %lx\n",
 			   addr);
 		ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index f1d8558f498e..2956c5198652 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,6 +46,9 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 				struct perf_probe_point *ppt);
 
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+			       bool adjust_offset);
+
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2017-01-15  9:59 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2017-01-15  9:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Alexander Shishkin, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 18e7a45af91acdde99d3aa1372cc40e1f8142f7b perf/x86: Reject non sampling events with precise_ip

Misc race fixes uncovered by fuzzing efforts, a Sparse fix, two PMU driver fixes, 
plus miscellanous tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      samples/bpf sock_example: Avoid getting ethhdr from two includes
      samples/bpf trace_output_user: Remove duplicate sys/ioctl.h include
      perf tools: Install tools/lib/traceevent plugins with install-bin
      perf symbols: Robustify reading of build-id from sysfs

Colin King (1):
      perf/x86/intel: Use ULL constant to prevent undefined shift behaviour

Daniel Bristot de Oliveira (1):
      tools lib traceevent: Fix prev/next_prio for deadline tasks

David Carrillo-Cisneros (1):
      perf/x86: Set pmu->module in Intel PMU modules

Jiri Olsa (5):
      tools lib subcmd: Add OPT_STRING_OPTARG_SET option
      perf record: Make __record_options static
      perf record: Fix --switch-output documentation and comment
      perf/x86/intel: Account interrupts for PEBS errors
      perf/x86: Reject non sampling events with precise_ip

Masami Hiramatsu (3):
      perf probe: Fix to get correct modname from elf header
      perf probe: Fix --funcs to show correct symbols for offline module
      perf probe: Fix to probe on gcc generated symbols for offline kernel

Namhyung Kim (1):
      perf sched timehist: Show total scheduling time

Peter Zijlstra (2):
      perf/core: Fix sys_perf_event_open() vs. hotplug
      perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race

Prarit Bhargava (1):
      perf/x86/intel/uncore: Fix hardcoded socket 0 assumption in the Haswell init code


 arch/x86/events/core.c                     |   4 +
 arch/x86/events/intel/core.c               |   2 +-
 arch/x86/events/intel/cstate.c             |   2 +
 arch/x86/events/intel/ds.c                 |   6 +-
 arch/x86/events/intel/rapl.c               |   1 +
 arch/x86/events/intel/uncore.c             |   1 +
 arch/x86/events/intel/uncore_snbep.c       |   2 +-
 include/linux/perf_event.h                 |   1 +
 kernel/events/core.c                       | 175 ++++++++++++++++++++++-------
 samples/bpf/sock_example.h                 |   2 +-
 samples/bpf/trace_output_user.c            |   1 -
 tools/lib/subcmd/parse-options.c           |   3 +
 tools/lib/subcmd/parse-options.h           |   5 +
 tools/lib/traceevent/plugin_sched_switch.c |   4 +-
 tools/perf/Documentation/perf-record.txt   |   4 +
 tools/perf/Makefile.perf                   |   4 +-
 tools/perf/builtin-record.c                |   4 +-
 tools/perf/builtin-sched.c                 |  17 ++-
 tools/perf/util/probe-event.c              | 105 +++++++++++------
 tools/perf/util/symbol-elf.c               |   6 +
 20 files changed, 257 insertions(+), 92 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 019c5887b698..1635c0c8df23 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+
+		/* There's no sense in having PEBS for non sampling events: */
+		if (!is_sampling_event(event))
+			return -EINVAL;
 	}
 	/*
 	 * check that PEBS LBR correction does not conflict with
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 86138267b68a..d611cab214a6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3987,7 +3987,7 @@ __init int intel_pmu_init(void)
 		     x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
 		x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
 	}
-	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1;
 
 	if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index fec8a461bdef..1076c9a77292 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -434,6 +434,7 @@ static struct pmu cstate_core_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.module		= THIS_MODULE,
 };
 
 static struct pmu cstate_pkg_pmu = {
@@ -447,6 +448,7 @@ static struct pmu cstate_pkg_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.module		= THIS_MODULE,
 };
 
 static const struct cstate_model nhm_cstates __initconst = {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index be202390bbd3..9dfeeeca0ea8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		/* log dropped samples number */
-		if (error[bit])
+		if (error[bit]) {
 			perf_log_lost_samples(event, error[bit]);
 
+			if (perf_event_account_interrupt(event))
+				x86_pmu_stop(event, 0);
+		}
+
 		if (counts[bit]) {
 			__intel_pmu_pebs_event(event, iregs, base,
 					       top, bit, counts[bit]);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index bd34124449b0..17c3564d087a 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -697,6 +697,7 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.start		= rapl_pmu_event_start;
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
+	rapl_pmus->pmu.module		= THIS_MODULE;
 	return 0;
 }
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 97c246f84dea..8c4ccdc3a3f3 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -733,6 +733,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 			.start		= uncore_pmu_event_start,
 			.stop		= uncore_pmu_event_stop,
 			.read		= uncore_pmu_event_read,
+			.module		= THIS_MODULE,
 		};
 	} else {
 		pmu->pmu = *pmu->type->pmu;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index e6832be714bc..dae2fedc1601 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = {
 
 void hswep_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = boot_cpu_data.logical_proc_id;
 
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4741ecdb9817..78ed8105e64d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1259,6 +1259,7 @@ extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_disable_local(struct perf_event *event);
 extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
+extern int perf_event_account_interrupt(struct perf_event *event);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
 perf_aux_output_begin(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ab15509fab8c..110b38a58493 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2249,7 +2249,7 @@ static int  __perf_install_in_context(void *info)
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
-	bool activate = true;
+	bool reprogram = true;
 	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
@@ -2257,27 +2257,26 @@ static int  __perf_install_in_context(void *info)
 		raw_spin_lock(&ctx->lock);
 		task_ctx = ctx;
 
-		/* If we're on the wrong CPU, try again */
-		if (task_cpu(ctx->task) != smp_processor_id()) {
-			ret = -ESRCH;
-			goto unlock;
-		}
+		reprogram = (ctx->task == current);
 
 		/*
-		 * If we're on the right CPU, see if the task we target is
-		 * current, if not we don't have to activate the ctx, a future
-		 * context switch will do that for us.
+		 * If the task is running, it must be running on this CPU,
+		 * otherwise we cannot reprogram things.
+		 *
+		 * If its not running, we don't care, ctx->lock will
+		 * serialize against it becoming runnable.
 		 */
-		if (ctx->task != current)
-			activate = false;
-		else
-			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+		if (task_curr(ctx->task) && !reprogram) {
+			ret = -ESRCH;
+			goto unlock;
+		}
 
+		WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx);
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	if (activate) {
+	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);
 		ctx_resched(cpuctx, task_ctx);
@@ -2328,13 +2327,36 @@ perf_install_in_context(struct perf_event_context *ctx,
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
+	 *
+	 * Instead we use task_curr(), which tells us if the task is running.
+	 * However, since we use task_curr() outside of rq::lock, we can race
+	 * against the actual state. This means the result can be wrong.
+	 *
+	 * If we get a false positive, we retry, this is harmless.
+	 *
+	 * If we get a false negative, things are complicated. If we are after
+	 * perf_event_context_sched_in() ctx::lock will serialize us, and the
+	 * value must be correct. If we're before, it doesn't matter since
+	 * perf_event_context_sched_in() will program the counter.
+	 *
+	 * However, this hinges on the remote context switch having observed
+	 * our task->perf_event_ctxp[] store, such that it will in fact take
+	 * ctx::lock in perf_event_context_sched_in().
+	 *
+	 * We do this by task_function_call(), if the IPI fails to hit the task
+	 * we know any future context switch of task must see the
+	 * perf_event_ctpx[] store.
 	 */
-again:
+
 	/*
-	 * Cannot use task_function_call() because we need to run on the task's
-	 * CPU regardless of whether its current or not.
+	 * This smp_mb() orders the task->perf_event_ctxp[] store with the
+	 * task_cpu() load, such that if the IPI then does not find the task
+	 * running, a future context switch of that task must observe the
+	 * store.
 	 */
-	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+	smp_mb();
+again:
+	if (!task_function_call(task, __perf_install_in_context, event))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -2348,12 +2370,16 @@ perf_install_in_context(struct perf_event_context *ctx,
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Since !ctx->is_active doesn't mean anything, we must IPI
-	 * unconditionally.
+	 * If the task is not running, ctx->lock will avoid it becoming so,
+	 * thus we can safely install the event.
 	 */
-	goto again;
+	if (task_curr(task)) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	add_event_to_ctx(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
@@ -7034,25 +7060,12 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
-/*
- * Generic event overflow handling, sampling.
- */
-
-static int __perf_event_overflow(struct perf_event *event,
-				   int throttle, struct perf_sample_data *data,
-				   struct pt_regs *regs)
+static int
+__perf_event_account_interrupt(struct perf_event *event, int throttle)
 {
-	int events = atomic_read(&event->event_limit);
 	struct hw_perf_event *hwc = &event->hw;
-	u64 seq;
 	int ret = 0;
-
-	/*
-	 * Non-sampling counters might still use the PMI to fold short
-	 * hardware counters, ignore those.
-	 */
-	if (unlikely(!is_sampling_event(event)))
-		return 0;
+	u64 seq;
 
 	seq = __this_cpu_read(perf_throttled_seq);
 	if (seq != hwc->interrupts_seq) {
@@ -7080,6 +7093,34 @@ static int __perf_event_overflow(struct perf_event *event,
 			perf_adjust_period(event, delta, hwc->last_period, true);
 	}
 
+	return ret;
+}
+
+int perf_event_account_interrupt(struct perf_event *event)
+{
+	return __perf_event_account_interrupt(event, 1);
+}
+
+/*
+ * Generic event overflow handling, sampling.
+ */
+
+static int __perf_event_overflow(struct perf_event *event,
+				   int throttle, struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
+	int events = atomic_read(&event->event_limit);
+	int ret = 0;
+
+	/*
+	 * Non-sampling counters might still use the PMI to fold short
+	 * hardware counters, ignore those.
+	 */
+	if (unlikely(!is_sampling_event(event)))
+		return 0;
+
+	ret = __perf_event_account_interrupt(event, throttle);
+
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
@@ -9503,6 +9544,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 	return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+			     struct perf_event_context *ctx)
+{
+	struct perf_event_context *gctx;
+
+again:
+	rcu_read_lock();
+	gctx = READ_ONCE(group_leader->ctx);
+	if (!atomic_inc_not_zero(&gctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+	if (group_leader->ctx != gctx) {
+		mutex_unlock(&ctx->mutex);
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+		goto again;
+	}
+
+	return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -9746,12 +9818,31 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		gctx = group_leader->ctx;
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
 		if (gctx->task == TASK_TOMBSTONE) {
 			err = -ESRCH;
 			goto err_locked;
 		}
+
+		/*
+		 * Check if we raced against another sys_perf_event_open() call
+		 * moving the software group underneath us.
+		 */
+		if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
+			/*
+			 * If someone moved the group out from under us, check
+			 * if this new event wound up on the same ctx, if so
+			 * its the regular !move_group case, otherwise fail.
+			 */
+			if (gctx != ctx) {
+				err = -EINVAL;
+				goto err_locked;
+			} else {
+				perf_event_ctx_unlock(group_leader, gctx);
+				move_group = 0;
+			}
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -9853,7 +9944,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_unpin_context(ctx);
 
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
@@ -9879,7 +9970,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 /* err_file: */
 	fput(event_file);
diff --git a/samples/bpf/sock_example.h b/samples/bpf/sock_example.h
index 09f7fe7e5fd7..d8014065d479 100644
--- a/samples/bpf/sock_example.h
+++ b/samples/bpf/sock_example.h
@@ -4,7 +4,7 @@
 #include <unistd.h>
 #include <string.h>
 #include <errno.h>
-#include <net/ethernet.h>
+#include <linux/if_ether.h>
 #include <net/if.h>
 #include <linux/if_packet.h>
 #include <arpa/inet.h>
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index f4fa6af22def..ccca1e348017 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -9,7 +9,6 @@
 #include <string.h>
 #include <fcntl.h>
 #include <poll.h>
-#include <sys/ioctl.h>
 #include <linux/perf_event.h>
 #include <linux/bpf.h>
 #include <errno.h>
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 3284bb14ae78..8aad81151d50 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p,
 		else
 			err = get_arg(p, opt, flags, (const char **)opt->value);
 
+		if (opt->set)
+			*(bool *)opt->set = true;
+
 		/* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
 		if (opt->flags & PARSE_OPT_NOEMPTY) {
 			const char *val = *(const char **)opt->value;
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 8866ac438b34..11c3be3bcce7 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -137,6 +137,11 @@ struct option {
 	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
 	  .value = check_vtype(v, const char **), (a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
+#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
+	{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
+	  .set = check_vtype(os, bool *)}
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index f1ce60065258..ec30c2fcbac0 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld ", val);
 
 	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, "[%lld] ", val);
+		trace_seq_printf(s, "[%d] ", (int) val);
 
 	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
 		write_state(s, val);
@@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld", val);
 
 	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, " [%lld]", val);
+		trace_seq_printf(s, " [%d]", (int) val);
 
 	return 0;
 }
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 27fc3617c6a4..5054d9147f0f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that
 particular perf.data snapshot should be kept or not.
 
 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+The reason for the latter two is to reduce the data file switching
+overhead. You can still switch them on with:
+
+  --switch-output --no-no-buildid  --no-no-buildid-cache
 
 --dry-run::
 Parse options then exit. --dry-run can be used to detect errors in cmdline
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8fc24824705e..8bb16aa9d661 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -704,9 +704,9 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
 
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
 
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 74d6a035133a..4ec10e9427d9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1405,7 +1405,7 @@ static bool dry_run;
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-struct option __record_options[] = {
+static struct option __record_options[] = {
 	OPT_CALLBACK('e', "event", &record.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events_option),
@@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		 * overhead. Still generate buildid if they are required
 		 * explicitly using
 		 *
-		 *  perf record --signal-trigger --no-no-buildid \
+		 *  perf record --switch-output --no-no-buildid \
 		 *              --no-no-buildid-cache
 		 *
 		 * Following code equals to:
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d53e706a6f17..5b134b0d1ff3 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -209,6 +209,7 @@ struct perf_sched {
 	u64		skipped_samples;
 	const char	*time_str;
 	struct perf_time_interval ptime;
+	struct perf_time_interval hist_time;
 };
 
 /* per thread run time data */
@@ -2460,6 +2461,11 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		timehist_print_sample(sched, sample, &al, thread, t);
 
 out:
+	if (sched->hist_time.start == 0 && t >= ptime->start)
+		sched->hist_time.start = t;
+	if (ptime->end == 0 || t <= ptime->end)
+		sched->hist_time.end = t;
+
 	if (tr) {
 		/* time of this sched_switch event becomes last time task seen */
 		tr->last_time = sample->time;
@@ -2624,6 +2630,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 	struct thread *t;
 	struct thread_runtime *r;
 	int i;
+	u64 hist_time = sched->hist_time.end - sched->hist_time.start;
 
 	memset(&totals, 0, sizeof(totals));
 
@@ -2665,7 +2672,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 			totals.sched_count += r->run_stats.n;
 			printf("    CPU %2d idle for ", i);
 			print_sched_time(r->total_run_time, 6);
-			printf(" msec\n");
+			printf(" msec  (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time);
 		} else
 			printf("    CPU %2d idle entire time window\n", i);
 	}
@@ -2701,12 +2708,16 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	printf("\n"
 	       "    Total number of unique tasks: %" PRIu64 "\n"
-	       "Total number of context switches: %" PRIu64 "\n"
-	       "           Total run time (msec): ",
+	       "Total number of context switches: %" PRIu64 "\n",
 	       totals.task_count, totals.sched_count);
 
+	printf("           Total run time (msec): ");
 	print_sched_time(totals.total_run_time, 2);
 	printf("\n");
+
+	printf("    Total scheduling time (msec): ");
+	print_sched_time(hist_time, 2);
+	printf(" (x %d)\n", sched->max_cpu);
 }
 
 typedef int (*sched_handler)(struct perf_tool *tool,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d281ae2b54e8..4a57c8a60bd9 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module)
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__findnew_module_map(host_machine, 0, module);
+		return dso__new_map(module);
 
 	if (!module)
 		module = "kernel";
@@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module)
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0 &&
 		    module[pos->dso->short_name_len - 2] == '\0') {
+			map__get(pos);
 			return pos;
 		}
 	}
@@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user)
 		return kernel_get_module_map(target);
 }
 
-static void put_target_map(struct map *map, bool user)
-{
-	if (map && user) {
-		/* Only the user map needs to be released */
-		map__put(map);
-	}
-}
-
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -268,21 +260,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 }
 
 /*
- * NOTE:
- * '.gnu.linkonce.this_module' section of kernel module elf directly
- * maps to 'struct module' from linux/module.h. This section contains
- * actual module name which will be used by kernel after loading it.
- * But, we cannot use 'struct module' here since linux/module.h is not
- * exposed to user-space. Offset of 'name' has remained same from long
- * time, so hardcoding it here.
- */
-#ifdef __LP64__
-#define MOD_NAME_OFFSET 24
-#else
-#define MOD_NAME_OFFSET 12
-#endif
-
-/*
  * @module can be module name of module file path. In case of path,
  * inspect elf and find out what is actual module name.
  * Caller has to free mod_name after using it.
@@ -296,6 +273,7 @@ static char *find_module_name(const char *module)
 	Elf_Data *data;
 	Elf_Scn *sec;
 	char *mod_name = NULL;
+	int name_offset;
 
 	fd = open(module, O_RDONLY);
 	if (fd < 0)
@@ -317,7 +295,21 @@ static char *find_module_name(const char *module)
 	if (!data || !data->d_buf)
 		goto ret_err;
 
-	mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+	/*
+	 * NOTE:
+	 * '.gnu.linkonce.this_module' section of kernel module elf directly
+	 * maps to 'struct module' from linux/module.h. This section contains
+	 * actual module name which will be used by kernel after loading it.
+	 * But, we cannot use 'struct module' here since linux/module.h is not
+	 * exposed to user-space. Offset of 'name' has remained same from long
+	 * time, so hardcoding it here.
+	 */
+	if (ehdr.e_ident[EI_CLASS] == ELFCLASS32)
+		name_offset = 12;
+	else	/* expect ELFCLASS64 by default */
+		name_offset = 24;
+
+	mod_name = strdup((char *)data->d_buf + name_offset);
 
 ret_err:
 	elf_end(elf);
@@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
 	}
 
 out:
-	put_target_map(map, uprobes);
+	map__put(map);
 	return ret;
 
 }
@@ -618,6 +610,51 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	return ret ? : -ENOENT;
 }
 
+/*
+ * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
+ * and generate new symbols with suffixes such as .constprop.N or .isra.N
+ * etc. Since those symbols are not recorded in DWARF, we have to find
+ * correct generated symbols from offline ELF binary.
+ * For online kernel or uprobes we don't need this because those are
+ * rebased on _text, or already a section relative address.
+ */
+static int
+post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
+					int ntevs, const char *pathname)
+{
+	struct symbol *sym;
+	struct map *map;
+	unsigned long stext = 0;
+	u64 addr;
+	int i;
+
+	/* Prepare a map for offline binary */
+	map = dso__new_map(pathname);
+	if (!map || get_text_start_address(pathname, &stext) < 0) {
+		pr_warning("Failed to get ELF symbols for %s\n", pathname);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ntevs; i++) {
+		addr = tevs[i].point.address + tevs[i].point.offset - stext;
+		sym = map__find_symbol(map, addr);
+		if (!sym)
+			continue;
+		if (!strcmp(sym->name, tevs[i].point.symbol))
+			continue;
+		/* If we have no realname, use symbol for it */
+		if (!tevs[i].point.realname)
+			tevs[i].point.realname = tevs[i].point.symbol;
+		else
+			free(tevs[i].point.symbol);
+		tevs[i].point.symbol = strdup(sym->name);
+		tevs[i].point.offset = addr - sym->start;
+	}
+	map__put(map);
+
+	return 0;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 					  int ntevs, const char *exec)
 {
@@ -679,7 +716,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 
 	/* Skip post process if the target is an offline kernel */
 	if (symbol_conf.ignore_vmlinux_buildid)
-		return 0;
+		return post_process_offline_probe_trace_events(tevs, ntevs,
+						symbol_conf.vmlinux_name);
 
 	reloc_sym = kernel_get_ref_reloc_sym();
 	if (!reloc_sym) {
@@ -2869,7 +2907,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 out:
-	put_target_map(map, pev->uprobes);
+	map__put(map);
 	free(syms);
 	return ret;
 
@@ -3362,10 +3400,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 		return ret;
 
 	/* Get a symbol map */
-	if (user)
-		map = dso__new_map(target);
-	else
-		map = kernel_get_module_map(target);
+	map = get_target_map(target, user);
 	if (!map) {
 		pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
 		return -EINVAL;
@@ -3397,9 +3432,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
         }
 
 end:
-	if (user) {
-		map__put(map);
-	}
+	map__put(map);
 	exit_probe_symbol_maps();
 
 	return ret;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 99400b0e8f2a..adbc6c02c3aa 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -537,6 +537,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 				break;
 		} else {
 			int n = namesz + descsz;
+
+			if (n > (int)sizeof(bf)) {
+				n = sizeof(bf);
+				pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n",
+					 __func__, filename, nhdr.n_namesz, nhdr.n_descsz);
+			}
 			if (read(fd, bf, n) != n)
 				break;
 		}

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-12-23 22:50 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-12-23 22:50 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Alexander Shishkin, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 3705b97505bcbf6440f38119c0e7d6058f585b54 Merge tag 'perf-urgent-for-mingo-20161222' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

On the kernel side there's two x86 PMU driver fixes and a uprobes fix, plus on the 
tooling side there's a number of fixes and some late updates.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf tools: Remove some needless __maybe_unused
      samples/bpf: Make perf_event_read() static
      samples/bpf: Be consistent with bpf_load_program bpf_insn parameter

Davidlohr Bueso (1):
      perf bench futex: Fix lock-pi help string

Jiri Olsa (7):
      perf tools: Move headers check into bash script
      perf mem: Fix --all-user/--all-kernel options
      perf evsel: Use variable instead of repeating lengthy FD macro
      perf thread_map: Add thread_map__remove function
      perf evsel: Allow to ignore missing pid
      perf record: Force ignore_missing_thread for uid option
      perf trace: Check if MAP_32BIT is defined (again)

Joe Stringer (8):
      tools lib bpf: Sync {tools,}/include/uapi/linux/bpf.h
      tools lib bpf: use __u32 from linux/types.h
      tools lib bpf: Add flags to bpf_create_map()
      samples/bpf: Make samples more libbpf-centric
      samples/bpf: Switch over to libbpf
      tools lib bpf: Add bpf_prog_{attach,detach}
      samples/bpf: Remove perf_event_open() declaration
      samples/bpf: Move open_raw_sock to separate header

Kan Liang (1):
      perf diff: Do not overwrite valid build id

Marcin Nowakowski (1):
      uprobes: Fix uprobes on MIPS, allow for a cache flush after ixol breakpoint creation

Namhyung Kim (10):
      perf sched timehist: Split is_idle_sample()
      perf sched timehist: Introduce struct idle_time_data
      perf sched timehist: Save callchain when entering idle
      perf sched timehist: Skip non-idle events when necessary
      perf sched timehist: Add -I/--idle-hist option
      perf sched timehist: Show callchains for idle stat
      perf sched timehist: Honour 'comm_width' when aligning the headers
      perf sched timehist: Enlarge default 'comm_width'
      perf sched timehist: Remove hardcoded 'comm_width' check at print_summary
      perf sched timehist: Fix invalid period calculation

Peter Zijlstra (1):
      perf/x86: Fix overlap counter scheduling bug

Ravi Bangoria (3):
      perf annotate: Support jump instruction with target as second operand
      perf annotate: Fix jump target outside of function address range
      perf annotate: Don't throw error for zero length symbols

Stephane Eranian (1):
      perf/x86/pebs: Fix handling of PEBS buffer overflows


 arch/x86/events/intel/core.c                      |  30 +-
 arch/x86/events/intel/uncore_snbep.c              |   2 +-
 kernel/events/uprobes.c                           |   2 +-
 samples/bpf/Makefile                              |  70 +--
 samples/bpf/README.rst                            |   4 +-
 samples/bpf/bpf_load.c                            |  21 +-
 samples/bpf/bpf_load.h                            |   3 +
 samples/bpf/fds_example.c                         |  13 +-
 samples/bpf/lathist_user.c                        |   2 +-
 samples/bpf/libbpf.c                              | 176 -------
 samples/bpf/libbpf.h                              |  28 +-
 samples/bpf/lwt_len_hist_user.c                   |   6 +-
 samples/bpf/offwaketime_user.c                    |   8 +-
 samples/bpf/sampleip_user.c                       |   7 +-
 samples/bpf/sock_example.c                        |  14 +-
 samples/bpf/sock_example.h                        |  35 ++
 samples/bpf/sockex1_user.c                        |   7 +-
 samples/bpf/sockex2_user.c                        |   5 +-
 samples/bpf/sockex3_user.c                        |   5 +-
 samples/bpf/spintest_user.c                       |   8 +-
 samples/bpf/tc_l2_redirect_user.c                 |   4 +-
 samples/bpf/test_cgrp2_array_pin.c                |   4 +-
 samples/bpf/test_cgrp2_attach.c                   |  12 +-
 samples/bpf/test_cgrp2_attach2.c                  |   8 +-
 samples/bpf/test_cgrp2_sock.c                     |   7 +-
 samples/bpf/test_current_task_under_cgroup_user.c |   8 +-
 samples/bpf/test_lru_dist.c                       |  32 +-
 samples/bpf/test_probe_write_user_user.c          |   2 +-
 samples/bpf/trace_event_user.c                    |  23 +-
 samples/bpf/trace_output_user.c                   |   7 +-
 samples/bpf/tracex2_user.c                        |  10 +-
 samples/bpf/tracex3_user.c                        |   4 +-
 samples/bpf/tracex4_user.c                        |   4 +-
 samples/bpf/tracex6_user.c                        |   5 +-
 samples/bpf/xdp1_user.c                           |   2 +-
 samples/bpf/xdp_tx_iptunnel_user.c                |   6 +-
 tools/include/uapi/linux/bpf.h                    | 593 +++++++++++++---------
 tools/lib/bpf/bpf.c                               |  30 +-
 tools/lib/bpf/bpf.h                               |   9 +-
 tools/lib/bpf/libbpf.c                            |   3 +-
 tools/perf/Documentation/perf-sched.txt           |   4 +
 tools/perf/Makefile.perf                          |  94 +---
 tools/perf/bench/futex-lock-pi.c                  |   2 +-
 tools/perf/builtin-c2c.c                          |  13 +-
 tools/perf/builtin-mem.c                          |   4 +-
 tools/perf/builtin-record.c                       |   3 +
 tools/perf/builtin-report.c                       |   2 +-
 tools/perf/builtin-sched.c                        | 275 ++++++++--
 tools/perf/builtin-stat.c                         |   6 +-
 tools/perf/check-headers.sh                       |  59 +++
 tools/perf/perf.h                                 |   1 +
 tools/perf/tests/builtin-test.c                   |   4 +
 tools/perf/tests/tests.h                          |   1 +
 tools/perf/tests/thread-map.c                     |  44 ++
 tools/perf/trace/beauty/mmap.c                    |   2 +
 tools/perf/ui/browsers/annotate.c                 |   5 +-
 tools/perf/util/annotate.c                        |  23 +-
 tools/perf/util/annotate.h                        |   5 +-
 tools/perf/util/evsel.c                           |  61 ++-
 tools/perf/util/evsel.h                           |   1 +
 tools/perf/util/symbol.c                          |   3 +-
 tools/perf/util/thread_map.c                      |  22 +
 tools/perf/util/thread_map.h                      |   1 +
 63 files changed, 1104 insertions(+), 750 deletions(-)
 delete mode 100644 samples/bpf/libbpf.c
 create mode 100644 samples/bpf/sock_example.h
 create mode 100755 tools/perf/check-headers.sh

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-12-07 18:45 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-12-07 18:45 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Alexander Shishkin,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 8fc31ce8896fc3cea1d79688c8ff950ad4e73afe perf/core: Remove invalid warning from list_update_cgroup_even()t

A bogus warning fix, a counter width handling fix affecting certain machines, plus 
a oneliner hw-enablement patch for Knights Mill CPUs.

 Thanks,

	Ingo

------------------>
David Carrillo-Cisneros (1):
      perf/core: Remove invalid warning from list_update_cgroup_even()t

Peter Zijlstra (Intel) (1):
      perf/x86: Fix full width counter, counter overflow

Piotr Luc (1):
      perf/x86/intel: Enable C-state residency events for Knights Mill


 arch/x86/events/core.c         |  2 +-
 arch/x86/events/intel/core.c   |  2 +-
 arch/x86/events/intel/cstate.c |  1 +
 kernel/events/core.c           | 19 ++++++++-----------
 4 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9d4bf3ab049e..6e395c996900 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -69,7 +69,7 @@ u64 x86_perf_event_update(struct perf_event *event)
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
 	int idx = hwc->idx;
-	s64 delta;
+	u64 delta;
 
 	if (idx == INTEL_PMC_IDX_FIXED_BTS)
 		return 0;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a74a2dbc0180..cb8522290e6a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4034,7 +4034,7 @@ __init int intel_pmu_init(void)
 
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
-		x86_pmu.max_period = x86_pmu.cntval_mask;
+		x86_pmu.max_period = x86_pmu.cntval_mask >> 1;
 		x86_pmu.perfctr = MSR_IA32_PMC0;
 		pr_cont("full-width counters, ");
 	}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4f5ac726335f..da51e5a3e2ff 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -540,6 +540,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6ee1febdf6ff..02c8421f8c01 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -903,17 +903,14 @@ list_update_cgroup_event(struct perf_event *event,
 	 */
 	cpuctx = __get_cpu_context(ctx);
 
-	/* Only set/clear cpuctx->cgrp if current task uses event->cgrp. */
-	if (perf_cgroup_from_task(current, ctx) != event->cgrp) {
-		/*
-		 * We are removing the last cpu event in this context.
-		 * If that event is not active in this cpu, cpuctx->cgrp
-		 * should've been cleared by perf_cgroup_switch.
-		 */
-		WARN_ON_ONCE(!add && cpuctx->cgrp);
-		return;
-	}
-	cpuctx->cgrp = add ? event->cgrp : NULL;
+	/*
+	 * cpuctx->cgrp is NULL until a cgroup event is sched in or
+	 * ctx->nr_cgroup == 0 .
+	 */
+	if (add && perf_cgroup_from_task(current, ctx) == event->cgrp)
+		cpuctx->cgrp = event->cgrp;
+	else if (!add)
+		cpuctx->cgrp = NULL;
 }
 
 #else /* !CONFIG_CGROUP_PERF */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-11-23  9:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-11-23  9:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 033ac60c7f21f9996a0fab2fd04f334afbf77b33 perf/x86/intel/uncore: Allow only a single PMU/box within an events group

Six fixes for bugs that were found via fuzzing, and a trivial hw-enablement patch 
for AMD Family-17h CPU PMUs.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Fix address filter parser

David Carrillo-Cisneros (1):
      perf/core: Do not set cpuctx->cgrp for unscheduled cgroups

Janakarajan Natarajan (1):
      perf/x86: Add perf support for AMD family-17h processors

Johannes Weiner (1):
      perf/x86: Restore TASK_SIZE check on frame pointer

Kan Liang (1):
      perf/x86/uncore: Fix crash by removing bogus event_list[] handling for SNB client uncore IMC

Peter Zijlstra (2):
      perf/x86/intel: Cure bogus unwind from PEBS entries
      perf/x86/intel/uncore: Allow only a single PMU/box within an events group


 arch/x86/events/amd/core.c         |  8 +++++++-
 arch/x86/events/core.c             | 10 ++--------
 arch/x86/events/intel/ds.c         | 35 +++++++++++++++++++++++------------
 arch/x86/events/intel/uncore.c     |  8 ++++----
 arch/x86/events/intel/uncore_snb.c | 12 ------------
 arch/x86/events/perf_event.h       |  2 +-
 kernel/events/core.c               | 13 +++++++++++++
 7 files changed, 50 insertions(+), 38 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index f5f4b3fbbbc2..afb222b63cae 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -662,7 +662,13 @@ static int __init amd_core_pmu_init(void)
 		pr_cont("Fam15h ");
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
 		break;
-
+	case 0x17:
+		pr_cont("Fam17h ");
+		/*
+		 * In family 17h, there are no event constraints in the PMC hardware.
+		 * We fallback to using default amd_get_event_constraints.
+		 */
+		break;
 	default:
 		pr_err("core perfctr but no constraints; unknown hardware!\n");
 		return -ENODEV;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d31735f37ed7..9d4bf3ab049e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2352,7 +2352,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 		frame.next_frame     = 0;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 8))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
@@ -2362,9 +2362,6 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 		if (bytes != 0)
 			break;
 
-		if (!valid_user_frame(fp, sizeof(frame)))
-			break;
-
 		perf_callchain_store(entry, cs_base + frame.return_address);
 		fp = compat_ptr(ss_base + frame.next_frame);
 	}
@@ -2413,7 +2410,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
@@ -2423,9 +2420,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		if (bytes != 0)
 			break;
 
-		if (!valid_user_frame(fp, sizeof(frame)))
-			break;
-
 		perf_callchain_store(entry, frame.return_address);
 		fp = (void __user *)frame.next_frame;
 	}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 0319311dbdbb..be202390bbd3 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1108,20 +1108,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	/*
-	 * We use the interrupt regs as a base because the PEBS record
-	 * does not contain a full regs set, specifically it seems to
-	 * lack segment descriptors, which get used by things like
-	 * user_mode().
+	 * We use the interrupt regs as a base because the PEBS record does not
+	 * contain a full regs set, specifically it seems to lack segment
+	 * descriptors, which get used by things like user_mode().
 	 *
-	 * In the simple case fix up only the IP and BP,SP regs, for
-	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
-	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
+	 *
+	 * We must however always use BP,SP from iregs for the unwinder to stay
+	 * sane; the record BP,SP can point into thin air when the record is
+	 * from a previous PMI context or an (I)RET happend between the record
+	 * and PMI.
 	 */
 	*regs = *iregs;
 	regs->flags = pebs->flags;
 	set_linear_ip(regs, pebs->ip);
-	regs->bp = pebs->bp;
-	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		regs->ax = pebs->ax;
@@ -1130,10 +1130,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->dx = pebs->dx;
 		regs->si = pebs->si;
 		regs->di = pebs->di;
-		regs->bp = pebs->bp;
-		regs->sp = pebs->sp;
 
-		regs->flags = pebs->flags;
+		/*
+		 * Per the above; only set BP,SP if we don't need callchains.
+		 *
+		 * XXX: does this make sense?
+		 */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			regs->bp = pebs->bp;
+			regs->sp = pebs->sp;
+		}
+
+		/*
+		 * Preserve PERF_EFLAGS_VM from set_linear_ip().
+		 */
+		regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
 		regs->r9 = pebs->r9;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index efca2685d876..dbaaf7dc8373 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -319,9 +319,9 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
  */
 static int uncore_pmu_event_init(struct perf_event *event);
 
-static bool is_uncore_event(struct perf_event *event)
+static bool is_box_event(struct intel_uncore_box *box, struct perf_event *event)
 {
-	return event->pmu->event_init == uncore_pmu_event_init;
+	return &box->pmu->pmu == event->pmu;
 }
 
 static int
@@ -340,7 +340,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
 
 	n = box->n_events;
 
-	if (is_uncore_event(leader)) {
+	if (is_box_event(box, leader)) {
 		box->event_list[n] = leader;
 		n++;
 	}
@@ -349,7 +349,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (!is_uncore_event(event) ||
+		if (!is_box_event(box, event) ||
 		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 81195cca7eae..a3dcc12bef4a 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -490,24 +490,12 @@ static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
 
 	snb_uncore_imc_event_start(event, 0);
 
-	box->n_events++;
-
 	return 0;
 }
 
 static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
 {
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	int i;
-
 	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
-	for (i = 0; i < box->n_events; i++) {
-		if (event == box->event_list[i]) {
-			--box->n_events;
-			break;
-		}
-	}
 }
 
 int snb_pci2phy_map_init(int devid)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 5874d8de1f8d..a77ee026643d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -113,7 +113,7 @@ struct debug_store {
  * Per register state.
  */
 struct er_account {
-	raw_spinlock_t		lock;	/* per-core: protect structure */
+	raw_spinlock_t      lock;	/* per-core: protect structure */
 	u64                 config;	/* extra MSR config */
 	u64                 reg;	/* extra MSR number */
 	atomic_t            ref;	/* reference count */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0e292132efac..6ee1febdf6ff 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -902,6 +902,17 @@ list_update_cgroup_event(struct perf_event *event,
 	 * this will always be called from the right CPU.
 	 */
 	cpuctx = __get_cpu_context(ctx);
+
+	/* Only set/clear cpuctx->cgrp if current task uses event->cgrp. */
+	if (perf_cgroup_from_task(current, ctx) != event->cgrp) {
+		/*
+		 * We are removing the last cpu event in this context.
+		 * If that event is not active in this cpu, cpuctx->cgrp
+		 * should've been cleared by perf_cgroup_switch.
+		 */
+		WARN_ON_ONCE(!add && cpuctx->cgrp);
+		return;
+	}
 	cpuctx->cgrp = add ? event->cgrp : NULL;
 }
 
@@ -8018,6 +8029,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
  * if <size> is not specified, the range is treated as a single address.
  */
 enum {
+	IF_ACT_NONE = -1,
 	IF_ACT_FILTER,
 	IF_ACT_START,
 	IF_ACT_STOP,
@@ -8041,6 +8053,7 @@ static const match_table_t if_tokens = {
 	{ IF_SRC_KERNEL,	"%u/%u" },
 	{ IF_SRC_FILEADDR,	"%u@%s" },
 	{ IF_SRC_KERNELADDR,	"%u" },
+	{ IF_ACT_NONE,		NULL },
 };
 
 /*

----- End forwarded message -----

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-11-14  7:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-11-14  7:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: ce75632cc4012f1832bd56efd97c2ba75ca964bb Merge tag 'perf-hists-hierarchy-fixes-for-mingo-20161111' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

An uncore PMU driver hardware enablement change for Intel SkyLake uncore PMUs 
(Skylake Y, U, H and S platforms), plus a number of tooling fixes for the 
histogram handling/displaying code.

 Thanks,

	Ingo

------------------>
Kan Liang (1):
      perf/x86/intel/uncore: Add more Intel uncore IMC PCI IDs for SkyLake

Namhyung Kim (5):
      perf hist browser: Fix hierarchy column counts
      perf hists browser: Fix indentation of folded sign on --hierarchy
      perf hists browser: Show folded sign properly on --hierarchy
      perf hists browser: Fix column indentation on --hierarchy
      perf hists: Fix column length on --hierarchy


 arch/x86/events/intel/uncore_snb.c | 32 +++++++++++++++++++++----
 tools/perf/ui/browsers/hists.c     | 48 +++++++++++++++++++++++++++++---------
 tools/perf/util/hist.c             | 12 +++++-----
 3 files changed, 71 insertions(+), 21 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 5f845eef9a4d..81195cca7eae 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -8,8 +8,12 @@
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC	0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC	0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -616,13 +620,29 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
 
 static const struct pci_device_id skl_uncore_pci_ids[] = {
 	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
 	{ /* IMC */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 
 	{ /* end: all zeroes */ },
 };
@@ -666,8 +686,12 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
-	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
+	IMC_DEV(SKL_Y_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core Y */
 	IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core U */
+	IMC_DEV(SKL_HD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Dual Core */
+	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
+	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
+	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
 	{  /* end marker */ }
 };
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 4ffff7be9299..a53fef0c673b 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1337,8 +1337,8 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		}
 
 		if (first) {
-			ui_browser__printf(&browser->b, "%c", folded_sign);
-			width--;
+			ui_browser__printf(&browser->b, "%c ", folded_sign);
+			width -= 2;
 			first = false;
 		} else {
 			ui_browser__printf(&browser->b, "  ");
@@ -1361,8 +1361,10 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		width -= hpp.buf - s;
 	}
 
-	ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
-	width -= hierarchy_indent;
+	if (!first) {
+		ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+		width -= hierarchy_indent;
+	}
 
 	if (column >= browser->b.horiz_scroll) {
 		char s[2048];
@@ -1381,7 +1383,13 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		}
 
 		perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
-			ui_browser__write_nstring(&browser->b, "", 2);
+			if (first) {
+				ui_browser__printf(&browser->b, "%c ", folded_sign);
+				first = false;
+			} else {
+				ui_browser__write_nstring(&browser->b, "", 2);
+			}
+
 			width -= 2;
 
 			/*
@@ -1555,10 +1563,11 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 	int indent = hists->nr_hpp_node - 2;
 	bool first_node, first_col;
 
-	ret = scnprintf(buf, size, " ");
+	ret = scnprintf(buf, size, "  ");
 	if (advance_hpp_check(&dummy_hpp, ret))
 		return ret;
 
+	first_node = true;
 	/* the first hpp_list_node is for overhead columns */
 	fmt_node = list_first_entry(&hists->hpp_formats,
 				    struct perf_hpp_list_node, list);
@@ -1573,12 +1582,16 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
+
+		first_node = false;
 	}
 
-	ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
-			indent * HIERARCHY_INDENT, "");
-	if (advance_hpp_check(&dummy_hpp, ret))
-		return ret;
+	if (!first_node) {
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
+				indent * HIERARCHY_INDENT, "");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			return ret;
+	}
 
 	first_node = true;
 	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
@@ -2076,8 +2089,21 @@ void hist_browser__init(struct hist_browser *browser,
 	browser->b.use_navkeypressed	= true;
 	browser->show_headers		= symbol_conf.show_hist_headers;
 
-	hists__for_each_format(hists, fmt)
+	if (symbol_conf.report_hierarchy) {
+		struct perf_hpp_list_node *fmt_node;
+
+		/* count overhead columns (in the first node) */
+		fmt_node = list_first_entry(&hists->hpp_formats,
+					    struct perf_hpp_list_node, list);
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+			++browser->b.columns;
+
+		/* add a single column for whole hierarchy sort keys*/
 		++browser->b.columns;
+	} else {
+		hists__for_each_format(hists, fmt)
+			++browser->b.columns;
+	}
 
 	hists__reset_column_width(hists);
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b02992efb513..a69f027368ef 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1600,18 +1600,18 @@ static void hists__hierarchy_output_resort(struct hists *hists,
 		if (prog)
 			ui_progress__update(prog, 1);
 
+		hists->nr_entries++;
+		if (!he->filtered) {
+			hists->nr_non_filtered_entries++;
+			hists__calc_col_len(hists, he);
+		}
+
 		if (!he->leaf) {
 			hists__hierarchy_output_resort(hists, prog,
 						       &he->hroot_in,
 						       &he->hroot_out,
 						       min_callchain_hits,
 						       use_callchain);
-			hists->nr_entries++;
-			if (!he->filtered) {
-				hists->nr_non_filtered_entries++;
-				hists__calc_col_len(hists, he);
-			}
-
 			continue;
 		}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-10-28 19:41 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-10-28 19:41 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: f92b7604149a55cb601fc0b52911b1e11f0f2514 perf/x86/intel: Honour the CPUID for number of fixed counters in hypervisors

Misc kerenl fixes: a virtualization environment related fix, an uncore PMU driver 
removal handling fix, a PowerPC fix and new events for Knights Landing.

 Thanks,

	Ingo

------------------>
Imre Palik (1):
      perf/x86/intel: Honour the CPUID for number of fixed counters in hypervisors

Jiri Olsa (2):
      perf/core: Protect PMU device removal with a 'pmu_bus_running' check, to fix CONFIG_DEBUG_TEST_DRIVER_REMOVE=y kernel panic
      perf/powerpc: Don't call perf_event_disable() from atomic context

Lukasz Odzioba (1):
      perf/x86/intel/cstate: Add C-state residency events for Knights Landing


 arch/powerpc/kernel/hw_breakpoint.c |  2 +-
 arch/x86/events/intel/core.c        | 10 +++++++---
 arch/x86/events/intel/cstate.c      | 30 ++++++++++++++++++++++++++----
 include/linux/perf_event.h          |  1 +
 kernel/events/core.c                | 23 +++++++++++++++++------
 5 files changed, 52 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 9781c69eae57..03d089b3ed72 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -275,7 +275,7 @@ int hw_breakpoint_handler(struct die_args *args)
 	if (!stepped) {
 		WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
 			"0x%lx will be disabled.", info->address);
-		perf_event_disable(bp);
+		perf_event_disable_inatomic(bp);
 		goto out;
 	}
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index eab0915f5995..a74a2dbc0180 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3607,10 +3607,14 @@ __init int intel_pmu_init(void)
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
-	 * assume at least 3 events:
+	 * assume at least 3 events, when not running in a hypervisor:
 	 */
-	if (version > 1)
-		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+	if (version > 1) {
+		int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
+
+		x86_pmu.num_counters_fixed =
+			max((int)edx.split.num_counters_fixed, assume);
+	}
 
 	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 3ca87b5a8677..4f5ac726335f 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -48,7 +48,8 @@
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ *						SKL,KNL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -56,15 +57,16 @@
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ *						SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -118,6 +120,7 @@ struct cstate_model {
 
 /* Quirk flags */
 #define SLM_PKG_C6_USE_C7_MSR	(1UL << 0)
+#define KNL_CORE_C6_MSR		(1UL << 1)
 
 struct perf_cstate_msr {
 	u64	msr;
@@ -488,6 +491,18 @@ static const struct cstate_model slm_cstates __initconst = {
 	.quirks			= SLM_PKG_C6_USE_C7_MSR,
 };
 
+
+static const struct cstate_model knl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
+	.quirks			= KNL_CORE_C6_MSR,
+};
+
+
+
 #define X86_CSTATES_MODEL(model, states)				\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
 
@@ -523,6 +538,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
@@ -558,6 +575,11 @@ static int __init cstate_probe(const struct cstate_model *cm)
 	if (cm->quirks & SLM_PKG_C6_USE_C7_MSR)
 		pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
 
+	/* KNL has different MSR for CORE C6 */
+	if (cm->quirks & KNL_CORE_C6_MSR)
+		pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
+
+
 	has_cstate_core = cstate_probe_msr(cm->core_events,
 					   PERF_CSTATE_CORE_EVENT_MAX,
 					   core_msr, core_events_attrs);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 060d0ede88df..4741ecdb9817 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1257,6 +1257,7 @@ extern u64 perf_swevent_set_period(struct perf_event *event);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_disable_local(struct perf_event *event);
+extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c6e47e97b33f..0e292132efac 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1960,6 +1960,12 @@ void perf_event_disable(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_disable);
 
+void perf_event_disable_inatomic(struct perf_event *event)
+{
+	event->pending_disable = 1;
+	irq_work_queue(&event->pending);
+}
+
 static void perf_set_shadow_time(struct perf_event *event,
 				 struct perf_event_context *ctx,
 				 u64 tstamp)
@@ -7075,8 +7081,8 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (events && atomic_dec_and_test(&event->event_limit)) {
 		ret = 1;
 		event->pending_kill = POLL_HUP;
-		event->pending_disable = 1;
-		irq_work_queue(&event->pending);
+
+		perf_event_disable_inatomic(event);
 	}
 
 	READ_ONCE(event->overflow_handler)(event, data, regs);
@@ -8855,7 +8861,10 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
+	int remove_device;
+
 	mutex_lock(&pmus_lock);
+	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
 	mutex_unlock(&pmus_lock);
 
@@ -8869,10 +8878,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (pmu->nr_addr_filters)
-		device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
-	device_del(pmu->dev);
-	put_device(pmu->dev);
+	if (remove_device) {
+		if (pmu->nr_addr_filters)
+			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
+		device_del(pmu->dev);
+		put_device(pmu->dev);
+	}
 	free_pmu_context(pmu);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-10-18 11:07 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-10-18 11:07 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 0130669966bf337b616d559d5405614c0a4ae313 Merge tag 'perf-urgent-for-mingo-20161017' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Four tooling fixes, two kprobes KASAN related fixes and an x86 PMU driver 
fix/cleanup.

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      perf jit: Fix build issue on Ubuntu

Dan Carpenter (1):
      perf/x86/intel: Remove an inconsistent NULL check

Dmitry Vyukov (2):
      kprobes: Avoid false KASAN reports during stack copy
      kprobes: Unpoison stack in jprobe_return() for KASAN

Jiri Olsa (1):
      perf header: Set nr_numa_nodes only when we parsed all the data

Namhyung Kim (1):
      perf top: Fix refreshing hierarchy entries on TUI

Wang Nan (1):
      perf jevents: Handle events including .c and .o


 arch/arm64/kernel/sleep.S      |  2 +-
 arch/x86/events/intel/lbr.c    |  4 ++--
 arch/x86/kernel/kprobes/core.c | 11 ++++++++---
 include/linux/kasan.h          |  2 ++
 mm/kasan/kasan.c               | 22 +++++++++++++++++++---
 tools/perf/jvmti/Makefile      |  2 +-
 tools/perf/ui/browsers/hists.c |  3 ++-
 tools/perf/util/header.c       |  2 +-
 tools/perf/util/parse-events.l |  4 ++--
 9 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index b8799e7c79de..1bec41b5fda3 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -135,7 +135,7 @@ ENTRY(_cpu_resume)
 
 #ifdef CONFIG_KASAN
 	mov	x0, sp
-	bl	kasan_unpoison_remaining_stack
+	bl	kasan_unpoison_task_stack_below
 #endif
 
 	ldp	x19, x20, [x29, #16]
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index fc6cf21c535e..81b321ace8e0 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -458,8 +458,8 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
-					event->ctx->task_ctx_data) {
+	if (branch_user_callstack(cpuc->br_sel) &&
+	    event->ctx->task_ctx_data) {
 		task_ctx = event->ctx->task_ctx_data;
 		task_ctx->lbr_callstack_users--;
 	}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 28cee019209c..d9d8d16b69db 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -50,6 +50,7 @@
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
 #include <linux/frame.h>
+#include <linux/kasan.h>
 
 #include <asm/text-patching.h>
 #include <asm/cacheflush.h>
@@ -1057,9 +1058,10 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	 * tailcall optimization. So, to be absolutely safe
 	 * we also save and restore enough stack bytes to cover
 	 * the argument area.
+	 * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
+	 * raw stack chunk with redzones:
 	 */
-	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr,
-	       MIN_STACK_SIZE(addr));
+	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
 	regs->flags &= ~X86_EFLAGS_IF;
 	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
@@ -1080,6 +1082,9 @@ void jprobe_return(void)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
+	/* Unpoison stack redzones in the frames we are going to jump over. */
+	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
+
 	asm volatile (
 #ifdef CONFIG_X86_64
 			"       xchg   %%rbx,%%rsp	\n"
@@ -1118,7 +1123,7 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 		/* It's OK to start function graph tracing again */
 		unpause_graph_tracing();
 		*regs = kcb->jprobe_saved_regs;
-		memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
+		__memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
 		preempt_enable_no_resched();
 		return 1;
 	}
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d600303306eb..820c0ad54a01 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -44,6 +44,7 @@ static inline void kasan_disable_current(void)
 void kasan_unpoison_shadow(const void *address, size_t size);
 
 void kasan_unpoison_task_stack(struct task_struct *task);
+void kasan_unpoison_stack_above_sp_to(const void *watermark);
 
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
@@ -85,6 +86,7 @@ size_t kasan_metadata_size(struct kmem_cache *cache);
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
 
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+static inline void kasan_unpoison_stack_above_sp_to(const void *watermark) {}
 
 static inline void kasan_enable_current(void) {}
 static inline void kasan_disable_current(void) {}
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 88af13c00d3c..70c009741aab 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -34,6 +34,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
+#include <linux/bug.h>
 
 #include "kasan.h"
 #include "../slab.h"
@@ -62,7 +63,7 @@ void kasan_unpoison_shadow(const void *address, size_t size)
 	}
 }
 
-static void __kasan_unpoison_stack(struct task_struct *task, void *sp)
+static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
 {
 	void *base = task_stack_page(task);
 	size_t size = sp - base;
@@ -77,9 +78,24 @@ void kasan_unpoison_task_stack(struct task_struct *task)
 }
 
 /* Unpoison the stack for the current task beyond a watermark sp value. */
-asmlinkage void kasan_unpoison_remaining_stack(void *sp)
+asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 {
-	__kasan_unpoison_stack(current, sp);
+	__kasan_unpoison_stack(current, watermark);
+}
+
+/*
+ * Clear all poison for the region between the current SP and a provided
+ * watermark value, as is sometimes required prior to hand-crafted asm function
+ * returns in the middle of functions.
+ */
+void kasan_unpoison_stack_above_sp_to(const void *watermark)
+{
+	const void *sp = __builtin_frame_address(0);
+	size_t size = watermark - sp;
+
+	if (WARN_ON(sp > watermark))
+		return;
+	kasan_unpoison_shadow(sp, size);
 }
 
 /*
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
index 5ce61a1bda9c..df14e6b67b63 100644
--- a/tools/perf/jvmti/Makefile
+++ b/tools/perf/jvmti/Makefile
@@ -36,7 +36,7 @@ SOLIBEXT=so
 # The following works at least on fedora 23, you may need the next
 # line for other distros.
 ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
-JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
 else
   ifneq (,$(wildcard /usr/sbin/alternatives))
     JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fb8e42c7507a..4ffff7be9299 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -601,7 +601,8 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
 			u64 nr_entries;
 			hbt->timer(hbt->arg);
 
-			if (hist_browser__has_filter(browser))
+			if (hist_browser__has_filter(browser) ||
+			    symbol_conf.report_hierarchy)
 				hist_browser__update_nr_entries(browser);
 
 			nr_entries = hist_browser__nr_entries(browser);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 85dd0db0a127..2f3eded54b0c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1895,7 +1895,6 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_numa_nodes = nr;
 	nodes = zalloc(sizeof(*nodes) * nr);
 	if (!nodes)
 		return -ENOMEM;
@@ -1932,6 +1931,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 
 		free(str);
 	}
+	ph->env.nr_numa_nodes = nr;
 	ph->env.numa_nodes = nodes;
 	return 0;
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 9f43fda2570f..660fca05bc93 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -136,8 +136,8 @@ do {							\
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
 event		[^,{}/]+
-bpf_object	.*\.(o|bpf)
-bpf_source	.*\.c
+bpf_object	[^,{}]+\.(o|bpf)
+bpf_source	[^,{}]+\.c
 
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-09-13 18:14 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-09-13 18:14 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Alexander Shishkin, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 8ef9b8455a2a3049efa9e46e8a6402b972a3eb41 perf/x86/intel: Fix PEBSv3 record drain

This contains:

- A set of fixes found by directed-random perf fuzzing efforts by Vince Weaver, 
  Alexander Shishkin and Peter Zijlstra,

- a cqm driver crash fix,

- an AMD uncore driver use after free fix.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (5):
      perf/core: Fix a race between mmap_close() and set_output() of AUX events
      perf/core: Fix aux_mmap_count vs aux_refcount order
      perf/x86/intel/bts: Fix confused ordering of PMU callbacks
      perf/x86/intel/bts: Fix BTS PMI detection
      perf/x86/intel/bts: Kill a silly warning

Jiri Olsa (1):
      perf/x86/intel/cqm: Check cqm/mbm enabled state in event init

Peter Zijlstra (2):
      perf/core: Remove WARN from perf_event_read()
      perf/x86/intel: Fix PEBSv3 record drain

Sebastian Andrzej Siewior (1):
      perf/x86/amd/uncore: Prevent use after free


 arch/x86/events/amd/uncore.c |  22 ++++++--
 arch/x86/events/intel/bts.c  | 123 +++++++++++++++++++++++++++++++++----------
 arch/x86/events/intel/cqm.c  |   9 ++++
 arch/x86/events/intel/ds.c   |  19 ++++---
 kernel/events/core.c         |  47 +++++++++++++----
 kernel/events/ring_buffer.c  |  15 ++++--
 6 files changed, 180 insertions(+), 55 deletions(-)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index e6131d4454e6..65577f081d07 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -29,6 +29,8 @@
 
 #define COUNTER_SHIFT		16
 
+static HLIST_HEAD(uncore_unused_list);
+
 struct amd_uncore {
 	int id;
 	int refcnt;
@@ -39,7 +41,7 @@ struct amd_uncore {
 	cpumask_t *active_mask;
 	struct pmu *pmu;
 	struct perf_event *events[MAX_COUNTERS];
-	struct amd_uncore *free_when_cpu_online;
+	struct hlist_node node;
 };
 
 static struct amd_uncore * __percpu *amd_uncore_nb;
@@ -306,6 +308,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
 		uncore_nb->active_mask = &amd_nb_active_mask;
 		uncore_nb->pmu = &amd_nb_pmu;
+		uncore_nb->id = -1;
 		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
@@ -319,6 +322,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
 		uncore_l2->active_mask = &amd_l2_active_mask;
 		uncore_l2->pmu = &amd_l2_pmu;
+		uncore_l2->id = -1;
 		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
 	}
 
@@ -348,7 +352,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
 			continue;
 
 		if (this->id == that->id) {
-			that->free_when_cpu_online = this;
+			hlist_add_head(&this->node, &uncore_unused_list);
 			this = that;
 			break;
 		}
@@ -388,13 +392,23 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
 	return 0;
 }
 
+static void uncore_clean_online(void)
+{
+	struct amd_uncore *uncore;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+		hlist_del(&uncore->node);
+		kfree(uncore);
+	}
+}
+
 static void uncore_online(unsigned int cpu,
 			  struct amd_uncore * __percpu *uncores)
 {
 	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
 
-	kfree(uncore->free_when_cpu_online);
-	uncore->free_when_cpu_online = NULL;
+	uncore_clean_online();
 
 	if (cpu == uncore->cpu)
 		cpumask_set_cpu(cpu, uncore->active_mask);
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 0a6e393a2e62..bdcd6510992c 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -31,7 +31,17 @@
 struct bts_ctx {
 	struct perf_output_handle	handle;
 	struct debug_store		ds_back;
-	int				started;
+	int				state;
+};
+
+/* BTS context states: */
+enum {
+	/* no ongoing AUX transactions */
+	BTS_STATE_STOPPED = 0,
+	/* AUX transaction is on, BTS tracing is disabled */
+	BTS_STATE_INACTIVE,
+	/* AUX transaction is on, BTS tracing is running */
+	BTS_STATE_ACTIVE,
 };
 
 static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
@@ -204,6 +214,15 @@ static void bts_update(struct bts_ctx *bts)
 static int
 bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ *  - is set when bts::handle::event is valid, that is, between
+ *    perf_aux_output_begin() and perf_aux_output_end();
+ *  - is zero otherwise;
+ *  - is ordered against bts::handle::event with a compiler barrier.
+ */
+
 static void __bts_event_start(struct perf_event *event)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
@@ -221,10 +240,13 @@ static void __bts_event_start(struct perf_event *event)
 
 	/*
 	 * local barrier to make sure that ds configuration made it
-	 * before we enable BTS
+	 * before we enable BTS and bts::state goes ACTIVE
 	 */
 	wmb();
 
+	/* INACTIVE/STOPPED -> ACTIVE */
+	WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
 	intel_pmu_enable_bts(config);
 
 }
@@ -251,9 +273,6 @@ static void bts_event_start(struct perf_event *event, int flags)
 
 	__bts_event_start(event);
 
-	/* PMI handler: this counter is running and likely generating PMIs */
-	ACCESS_ONCE(bts->started) = 1;
-
 	return;
 
 fail_end_stop:
@@ -263,30 +282,34 @@ static void bts_event_start(struct perf_event *event, int flags)
 	event->hw.state = PERF_HES_STOPPED;
 }
 
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
 {
+	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+	/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+	WRITE_ONCE(bts->state, state);
+
 	/*
 	 * No extra synchronization is mandated by the documentation to have
 	 * BTS data stores globally visible.
 	 */
 	intel_pmu_disable_bts();
-
-	if (event->hw.state & PERF_HES_STOPPED)
-		return;
-
-	ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
 }
 
 static void bts_event_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_buffer *buf = NULL;
+	int state = READ_ONCE(bts->state);
 
-	/* PMI handler: don't restart this counter */
-	ACCESS_ONCE(bts->started) = 0;
+	if (state == BTS_STATE_ACTIVE)
+		__bts_event_stop(event, BTS_STATE_STOPPED);
 
-	__bts_event_stop(event);
+	if (state != BTS_STATE_STOPPED)
+		buf = perf_get_aux(&bts->handle);
+
+	event->hw.state |= PERF_HES_STOPPED;
 
 	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
@@ -296,6 +319,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
 				bts->handle.head =
 					local_xchg(&buf->data_size,
 						   buf->nr_pages << PAGE_SHIFT);
+
 			perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
 					    !!local_xchg(&buf->lost, 0));
 		}
@@ -310,8 +334,20 @@ static void bts_event_stop(struct perf_event *event, int flags)
 void intel_bts_enable_local(void)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	int state = READ_ONCE(bts->state);
+
+	/*
+	 * Here we transition from INACTIVE to ACTIVE;
+	 * if we instead are STOPPED from the interrupt handler,
+	 * stay that way. Can't be ACTIVE here though.
+	 */
+	if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+		return;
+
+	if (state == BTS_STATE_STOPPED)
+		return;
 
-	if (bts->handle.event && bts->started)
+	if (bts->handle.event)
 		__bts_event_start(bts->handle.event);
 }
 
@@ -319,8 +355,15 @@ void intel_bts_disable_local(void)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 
+	/*
+	 * Here we transition from ACTIVE to INACTIVE;
+	 * do nothing for STOPPED or INACTIVE.
+	 */
+	if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+		return;
+
 	if (bts->handle.event)
-		__bts_event_stop(bts->handle.event);
+		__bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
 }
 
 static int
@@ -335,8 +378,6 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 		return 0;
 
 	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
-	if (WARN_ON_ONCE(head != local_read(&buf->head)))
-		return -EINVAL;
 
 	phys = &buf->buf[buf->cur_buf];
 	space = phys->offset + phys->displacement + phys->size - head;
@@ -403,22 +444,37 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 
 int intel_bts_interrupt(void)
 {
+	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct perf_event *event = bts->handle.event;
 	struct bts_buffer *buf;
 	s64 old_head;
-	int err;
+	int err = -ENOSPC, handled = 0;
 
-	if (!event || !bts->started)
-		return 0;
+	/*
+	 * The only surefire way of knowing if this NMI is ours is by checking
+	 * the write ptr against the PMI threshold.
+	 */
+	if (ds->bts_index >= ds->bts_interrupt_threshold)
+		handled = 1;
+
+	/*
+	 * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+	 * so we can only be INACTIVE or STOPPED
+	 */
+	if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+		return handled;
 
 	buf = perf_get_aux(&bts->handle);
+	if (!buf)
+		return handled;
+
 	/*
 	 * Skip snapshot counters: they don't use the interrupt, but
 	 * there's no other way of telling, because the pointer will
 	 * keep moving
 	 */
-	if (!buf || buf->snapshot)
+	if (buf->snapshot)
 		return 0;
 
 	old_head = local_read(&buf->head);
@@ -426,18 +482,27 @@ int intel_bts_interrupt(void)
 
 	/* no new data */
 	if (old_head == local_read(&buf->head))
-		return 0;
+		return handled;
 
 	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
 			    !!local_xchg(&buf->lost, 0));
 
 	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
-		return 1;
+	if (buf)
+		err = bts_buffer_reset(buf, &bts->handle);
+
+	if (err) {
+		WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
 
-	err = bts_buffer_reset(buf, &bts->handle);
-	if (err)
-		perf_aux_output_end(&bts->handle, 0, false);
+		if (buf) {
+			/*
+			 * BTS_STATE_STOPPED should be visible before
+			 * cleared handle::event
+			 */
+			barrier();
+			perf_aux_output_end(&bts->handle, 0, false);
+		}
+	}
 
 	return 1;
 }
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 783c49ddef29..8f82b02934fa 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -458,6 +458,11 @@ static void __intel_cqm_event_count(void *info);
 static void init_mbm_sample(u32 rmid, u32 evt_type);
 static void __intel_mbm_event_count(void *info);
 
+static bool is_cqm_event(int e)
+{
+	return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
 static bool is_mbm_event(int e)
 {
 	return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
@@ -1366,6 +1371,10 @@ static int intel_cqm_event_init(struct perf_event *event)
 	     (event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
 		return -EINVAL;
 
+	if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+	    (is_mbm_event(event->attr.config) && !mbm_enabled))
+		return -EINVAL;
+
 	/* unsupported modes and filters */
 	if (event->attr.exclude_user   ||
 	    event->attr.exclude_kernel ||
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f669e6..9b983a474253 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1274,18 +1274,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		struct pebs_record_nhm *p = at;
 		u64 pebs_status;
 
-		/* PEBS v3 has accurate status bits */
+		pebs_status = p->status & cpuc->pebs_enabled;
+		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
-			for_each_set_bit(bit, (unsigned long *)&p->status,
-					 MAX_PEBS_EVENTS)
+			for_each_set_bit(bit, (unsigned long *)&pebs_status,
+					 x86_pmu.max_pebs_events)
 				counts[bit]++;
 
 			continue;
 		}
 
-		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
 		/*
 		 * On some CPUs the PEBS status can be zero when PEBS is
 		 * racing with clearing of GLOBAL_STATUS.
@@ -1333,8 +1333,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		event = cpuc->events[bit];
-		WARN_ON_ONCE(!event);
-		WARN_ON_ONCE(!event->attr.precise_ip);
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		if (WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
 
 		/* log dropped samples number */
 		if (error[bit])
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3cfabdf7b942..a54f2c2cdb20 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2496,11 +2496,11 @@ static int __perf_event_stop(void *info)
 	return 0;
 }
 
-static int perf_event_restart(struct perf_event *event)
+static int perf_event_stop(struct perf_event *event, int restart)
 {
 	struct stop_event_data sd = {
 		.event		= event,
-		.restart	= 1,
+		.restart	= restart,
 	};
 	int ret = 0;
 
@@ -3549,10 +3549,18 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
-		/* The event must have been read from an online CPU: */
-		WARN_ON_ONCE(ret);
-		ret = ret ? : data.ret;
+		/*
+		 * Purposely ignore the smp_call_function_single() return
+		 * value.
+		 *
+		 * If event->oncpu isn't a valid CPU it means the event got
+		 * scheduled out and that will have updated the event count.
+		 *
+		 * Therefore, either way, we'll have an up-to-date event count
+		 * after this.
+		 */
+		(void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;
@@ -4837,6 +4845,19 @@ static void ring_buffer_attach(struct perf_event *event,
 		spin_unlock_irqrestore(&rb->event_lock, flags);
 	}
 
+	/*
+	 * Avoid racing with perf_mmap_close(AUX): stop the event
+	 * before swizzling the event::rb pointer; if it's getting
+	 * unmapped, its aux_mmap_count will be 0 and it won't
+	 * restart. See the comment in __perf_pmu_output_stop().
+	 *
+	 * Data will inevitably be lost when set_output is done in
+	 * mid-air, but then again, whoever does it like this is
+	 * not in for the data anyway.
+	 */
+	if (has_aux(event))
+		perf_event_stop(event, 0);
+
 	rcu_assign_pointer(event->rb, rb);
 
 	if (old_rb) {
@@ -6112,7 +6133,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (restart)
-		perf_event_restart(event);
+		perf_event_stop(event, 1);
 }
 
 void perf_event_exec(void)
@@ -6156,7 +6177,13 @@ static void __perf_event_output_stop(struct perf_event *event, void *data)
 
 	/*
 	 * In case of inheritance, it will be the parent that links to the
-	 * ring-buffer, but it will be the child that's actually using it:
+	 * ring-buffer, but it will be the child that's actually using it.
+	 *
+	 * We are using event::rb to determine if the event should be stopped,
+	 * however this may race with ring_buffer_attach() (through set_output),
+	 * which will make us skip the event that actually needs to be stopped.
+	 * So ring_buffer_attach() has to stop an aux event before re-assigning
+	 * its rb pointer.
 	 */
 	if (rcu_dereference(parent->rb) == rb)
 		ro->err = __perf_event_stop(&sd);
@@ -6670,7 +6697,7 @@ static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (restart)
-		perf_event_restart(event);
+		perf_event_stop(event, 1);
 }
 
 /*
@@ -7859,7 +7886,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	mmput(mm);
 
 restart:
-	perf_event_restart(event);
+	perf_event_stop(event, 1);
 }
 
 /*
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index ae9b90dc9a5a..257fa460b846 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -330,15 +330,22 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	if (!rb)
 		return NULL;
 
-	if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+	if (!rb_has_aux(rb))
 		goto err;
 
 	/*
-	 * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
-	 * the aux buffer is in perf_mmap_close(), about to get freed.
+	 * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
+	 * about to get freed, so we leave immediately.
+	 *
+	 * Checking rb::aux_mmap_count and rb::refcount has to be done in
+	 * the same order, see perf_mmap_close. Otherwise we end up freeing
+	 * aux pages in this path, which is a bug, because in_atomic().
 	 */
 	if (!atomic_read(&rb->aux_mmap_count))
-		goto err_put;
+		goto err;
+
+	if (!atomic_inc_not_zero(&rb->aux_refcount))
+		goto err;
 
 	/*
 	 * Nesting is not supported for AUX area, make sure nested

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-08-18 20:38 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-08-18 20:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 71e7bc2bab77e64882c031c2af943c3256c1adb0 perf/core: Check return value of the perf_event_read() IPI

Mostly tooling fixes, but also start/stop filter related fixes, a perf event 
read() fix, a fix uncovered by fuzzing, and an uprobes leak fix.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf intel-pt: Fix ip compression
      perf intel-pt: Fix occasional decoding errors when tracing system-wide

Anton Blanchard (1):
      perf symbols: Fix annotation of objects with debuginfo files

Arnaldo Carvalho de Melo (3):
      perf jitdump: Add the right header to get the major()/minor() definitions
      perf probe: Release resources on error when handling exit paths
      tools: Sync kvm related header files for arm64 and s390

Colin Ian King (1):
      perf probe: Check for dup and fdopen failures

David Carrillo-Cisneros (1):
      perf/core: Check return value of the perf_event_read() IPI

He Kuang (2):
      perf script: Show proper message when failed list scripts
      perf script: Don't disable use_callchain if input is pipe

Jiri Olsa (1):
      perf tools mem: Fix -t store option for record command

Mathieu Poirier (3):
      perf/core: Fix file name handling for start/stop filters
      perf/core: Update filters only on executable mmap
      perf/core: Enable mapping of the stop filters

Oleg Nesterov (1):
      uprobes: Fix the memcg accounting

Peter Zijlstra (1):
      perf/core: Fix event_function_local()

Ravi Bangoria (1):
      perf ppc64le: Fix build failure when libelf is not present


 kernel/events/core.c                               | 95 ++++++++++++++++------
 kernel/events/uprobes.c                            |  5 +-
 tools/arch/arm64/include/uapi/asm/kvm.h            |  2 +
 tools/arch/s390/include/uapi/asm/kvm.h             | 41 ++++++++++
 tools/arch/s390/include/uapi/asm/sie.h             |  1 +
 tools/perf/arch/powerpc/util/sym-handling.c        |  2 +
 tools/perf/arch/x86/util/intel-pt.c                |  6 +-
 tools/perf/builtin-mem.c                           |  3 +
 tools/perf/builtin-script.c                        | 13 ++-
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  | 44 +++++-----
 .../util/intel-pt-decoder/intel-pt-pkt-decoder.c   | 24 ++++--
 tools/perf/util/jitdump.c                          |  1 +
 tools/perf/util/probe-file.c                       | 36 ++++++--
 tools/perf/util/symbol-elf.c                       |  3 +-
 14 files changed, 207 insertions(+), 69 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1903b8f3a705..5650f5317e0c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -242,18 +242,6 @@ static int event_function(void *info)
 	return ret;
 }
 
-static void event_function_local(struct perf_event *event, event_f func, void *data)
-{
-	struct event_function_struct efs = {
-		.event = event,
-		.func = func,
-		.data = data,
-	};
-
-	int ret = event_function(&efs);
-	WARN_ON_ONCE(ret);
-}
-
 static void event_function_call(struct perf_event *event, event_f func, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -303,6 +291,54 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+/*
+ * Similar to event_function_call() + event_function(), but hard assumes IRQs
+ * are already disabled and we're on the right CPU.
+ */
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct task_struct *task = READ_ONCE(ctx->task);
+	struct perf_event_context *task_ctx = NULL;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (task) {
+		if (task == TASK_TOMBSTONE)
+			return;
+
+		task_ctx = ctx;
+	}
+
+	perf_ctx_lock(cpuctx, task_ctx);
+
+	task = ctx->task;
+	if (task == TASK_TOMBSTONE)
+		goto unlock;
+
+	if (task) {
+		/*
+		 * We must be either inactive or active and the right task,
+		 * otherwise we're screwed, since we cannot IPI to somewhere
+		 * else.
+		 */
+		if (ctx->is_active) {
+			if (WARN_ON_ONCE(task != current))
+				goto unlock;
+
+			if (WARN_ON_ONCE(cpuctx->task_ctx != ctx))
+				goto unlock;
+		}
+	} else {
+		WARN_ON_ONCE(&cpuctx->ctx != ctx);
+	}
+
+	func(event, cpuctx, ctx, data);
+unlock:
+	perf_ctx_unlock(cpuctx, task_ctx);
+}
+
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP |\
@@ -3513,9 +3549,10 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		smp_call_function_single(event->oncpu,
-					 __perf_event_read, &data, 1);
-		ret = data.ret;
+		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		/* The event must have been read from an online CPU: */
+		WARN_ON_ONCE(ret);
+		ret = ret ? : data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;
@@ -6584,15 +6621,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 }
 
 /*
- * Whether this @filter depends on a dynamic object which is not loaded
- * yet or its load addresses are not known.
- */
-static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
-{
-	return filter->filter && filter->inode;
-}
-
-/*
  * Check whether inode and address range match filter criteria.
  */
 static bool perf_addr_filter_match(struct perf_addr_filter *filter,
@@ -6653,6 +6681,13 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma)
 	struct perf_event_context *ctx;
 	int ctxn;
 
+	/*
+	 * Data tracing isn't supported yet and as such there is no need
+	 * to keep track of anything that isn't related to executable code:
+	 */
+	if (!(vma->vm_flags & VM_EXEC))
+		return;
+
 	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
 		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
@@ -7805,7 +7840,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	list_for_each_entry(filter, &ifh->list, entry) {
 		event->addr_filters_offs[count] = 0;
 
-		if (perf_addr_filter_needs_mmap(filter))
+		/*
+		 * Adjust base offset if the filter is associated to a binary
+		 * that needs to be mapped:
+		 */
+		if (filter->inode)
 			event->addr_filters_offs[count] =
 				perf_addr_filter_apply(filter, mm);
 
@@ -7936,8 +7975,10 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 					goto fail;
 			}
 
-			if (token == IF_SRC_FILE) {
-				filename = match_strdup(&args[2]);
+			if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
+				int fpos = filter->range ? 2 : 1;
+
+				filename = match_strdup(&args[fpos]);
 				if (!filename) {
 					ret = -ENOMEM;
 					goto fail;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index b7a525ab2083..8c50276b60d1 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!ptep) {
+		mem_cgroup_cancel_charge(kpage, memcg, false);
 		goto unlock;
+	}
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr, false);
@@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
-	mem_cgroup_cancel_charge(kpage, memcg, false);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index f209ea151dca..3051f86a9b5f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -87,9 +87,11 @@ struct kvm_regs {
 /* Supported VGICv3 address types  */
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+#define KVM_VGIC_ITS_ADDR_TYPE		4
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE		(2 * SZ_64K)
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 3b8e99ef9d58..a2ffec4139ad 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine {
 	__u64 fac_list[256];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_FEAT	2
+#define KVM_S390_VM_CPU_MACHINE_FEAT	3
+
+#define KVM_S390_VM_CPU_FEAT_NR_BITS	1024
+#define KVM_S390_VM_CPU_FEAT_ESOP	0
+#define KVM_S390_VM_CPU_FEAT_SIEF2	1
+#define KVM_S390_VM_CPU_FEAT_64BSCAO	2
+#define KVM_S390_VM_CPU_FEAT_SIIF	3
+#define KVM_S390_VM_CPU_FEAT_GPERE	4
+#define KVM_S390_VM_CPU_FEAT_GSLS	5
+#define KVM_S390_VM_CPU_FEAT_IB		6
+#define KVM_S390_VM_CPU_FEAT_CEI	7
+#define KVM_S390_VM_CPU_FEAT_IBS	8
+#define KVM_S390_VM_CPU_FEAT_SKEY	9
+#define KVM_S390_VM_CPU_FEAT_CMMA	10
+#define KVM_S390_VM_CPU_FEAT_PFMFI	11
+#define KVM_S390_VM_CPU_FEAT_SIGPIF	12
+struct kvm_s390_vm_cpu_feat {
+	__u64 feat[16];
+};
+
+#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC	4
+#define KVM_S390_VM_CPU_MACHINE_SUBFUNC		5
+/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */
+struct kvm_s390_vm_cpu_subfunc {
+	__u8 plo[32];		/* always */
+	__u8 ptff[16];		/* with TOD-clock steering */
+	__u8 kmac[16];		/* with MSA */
+	__u8 kmc[16];		/* with MSA */
+	__u8 km[16];		/* with MSA */
+	__u8 kimd[16];		/* with MSA */
+	__u8 klmd[16];		/* with MSA */
+	__u8 pckmo[16];		/* with MSA3 */
+	__u8 kmctr[16];		/* with MSA4 */
+	__u8 kmf[16];		/* with MSA4 */
+	__u8 kmo[16];		/* with MSA4 */
+	__u8 pcc[16];		/* with MSA4 */
+	__u8 ppno[16];		/* with MSA5 */
+	__u8 reserved[1824];
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
index 8fb5d4a6dd25..3ac634368939 100644
--- a/tools/arch/s390/include/uapi/asm/sie.h
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -140,6 +140,7 @@
 	exit_code_ipa0(0xB2, 0x4c, "TAR"),	\
 	exit_code_ipa0(0xB2, 0x50, "CSP"),	\
 	exit_code_ipa0(0xB2, 0x54, "MVPG"),	\
+	exit_code_ipa0(0xB2, 0x56, "STHYI"),	\
 	exit_code_ipa0(0xB2, 0x58, "BSG"),	\
 	exit_code_ipa0(0xB2, 0x5a, "BSA"),	\
 	exit_code_ipa0(0xB2, 0x5f, "CHSC"),	\
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 8d4dc97d80ba..35745a733100 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -97,6 +97,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 	}
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
 void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 					   int ntevs)
 {
@@ -118,5 +119,6 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 		}
 	}
 }
+#endif /* HAVE_LIBELF_SUPPORT */
 
 #endif
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index fb51457ba338..a2412e9d883b 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	struct intel_pt_recording *ptr =
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
-	bool have_timing_info;
+	bool have_timing_info, need_immediate = false;
 	struct perf_evsel *evsel, *intel_pt_evsel = NULL;
 	const struct cpu_map *cpus = evlist->cpus;
 	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
@@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 				ptr->have_sched_switch = 3;
 			} else {
 				opts->record_switch_events = true;
+				need_immediate = true;
 				if (cpu_wide)
 					ptr->have_sched_switch = 3;
 				else
@@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		tracking_evsel->attr.freq = 0;
 		tracking_evsel->attr.sample_period = 1;
 
+		if (need_immediate)
+			tracking_evsel->immediate = true;
+
 		/* In per-cpu case, always need the time of mmap events etc */
 		if (!cpu_map__empty(cpus)) {
 			perf_evsel__set_sample_bit(tracking_evsel, TIME);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d608a2c9e48c..d1ce29be560e 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (mem->operation & MEM_OPERATION_LOAD)
 		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
 
+	if (mem->operation & MEM_OPERATION_STORE)
+		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+
 	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9c640a8081c7..c859e59dfe3e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
 	if (!no_callchain) {
 		bool use_callchain = false;
+		bool not_pipe = false;
 
 		evlist__for_each_entry(session->evlist, evsel) {
+			not_pipe = true;
 			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 				use_callchain = true;
 				break;
 			}
 		}
-		if (!use_callchain)
+		if (not_pipe && !use_callchain)
 			symbol_conf.use_callchain = false;
 	}
 
@@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
 	scripts_dir = opendir(scripts_path);
-	if (!scripts_dir)
-		return -1;
+	if (!scripts_dir) {
+		fprintf(stdout,
+			"open(%s) failed.\n"
+			"Check \"PERF_EXEC_PATH\" env to set scripts dir.\n",
+			scripts_path);
+		exit(-1);
+	}
 
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 9c8f15da86ce..8ff6c6a61291 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -123,8 +123,6 @@ struct intel_pt_decoder {
 	bool have_calc_cyc_to_tsc;
 	int exec_mode;
 	unsigned int insn_bytes;
-	uint64_t sign_bit;
-	uint64_t sign_bits;
 	uint64_t period;
 	enum intel_pt_period_type period_type;
 	uint64_t tot_insn_cnt;
@@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
 
-	decoder->sign_bit           = (uint64_t)1 << 47;
-	decoder->sign_bits          = ~(((uint64_t)1 << 48) - 1);
-
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;
 
@@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen)
 	return 0;
 }
 
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
-				 const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 				 uint64_t last_ip)
 {
 	uint64_t ip;
 
 	switch (packet->count) {
-	case 2:
+	case 1:
 		ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
 		     packet->payload;
 		break;
-	case 4:
+	case 2:
 		ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
 		     packet->payload;
 		break;
+	case 3:
+		ip = packet->payload;
+		/* Sign-extend 6-byte ip */
+		if (ip & (uint64_t)0x800000000000ULL)
+			ip |= (uint64_t)0xffff000000000000ULL;
+		break;
+	case 4:
+		ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+		     packet->payload;
+		break;
 	case 6:
 		ip = packet->payload;
 		break;
@@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
 		return 0;
 	}
 
-	if (ip & decoder->sign_bit)
-		return ip | decoder->sign_bits;
-
 	return ip;
 }
 
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
-	decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
-					    decoder->last_ip);
+	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -1657,6 +1657,12 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 	}
 }
 
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+	return decoder->last_ip || decoder->packet.count == 0 ||
+	       decoder->packet.count == 3 || decoder->packet.count == 6;
+}
+
 /* Walk PSB+ packets to get in sync. */
 static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 {
@@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0) {
+			if (intel_pt_have_ip(decoder)) {
 				uint64_t current_ip = decoder->ip;
 
 				intel_pt_set_ip(decoder);
@@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0)
+			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
 			if (decoder->ip)
 				return 0;
@@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			if (decoder->overflow) {
-				if (decoder->last_ip ||
-				    decoder->packet.count == 6 ||
-				    decoder->packet.count == 0)
+				if (intel_pt_have_ip(decoder))
 					intel_pt_set_ip(decoder);
 				if (decoder->ip)
 					return 0;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index b1257c816310..4f7b32020487 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
 			   const unsigned char *buf, size_t len,
 			   struct intel_pt_pkt *packet)
 {
-	switch (byte >> 5) {
+	int ip_len;
+
+	packet->count = byte >> 5;
+
+	switch (packet->count) {
 	case 0:
-		packet->count = 0;
+		ip_len = 0;
 		break;
 	case 1:
 		if (len < 3)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 2;
+		ip_len = 2;
 		packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
 		break;
 	case 2:
 		if (len < 5)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 4;
+		ip_len = 4;
 		packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
 		break;
 	case 3:
-	case 6:
+	case 4:
 		if (len < 7)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 6;
+		ip_len = 6;
 		memcpy_le64(&packet->payload, buf + 1, 6);
 		break;
+	case 6:
+		if (len < 9)
+			return INTEL_PT_NEED_MORE_BYTES;
+		ip_len = 8;
+		packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+		break;
 	default:
 		return INTEL_PT_BAD_PACKET;
 	}
 
 	packet->type = type;
 
-	return packet->count + 1;
+	return ip_len + 1;
 }
 
 static int intel_pt_get_mode(const unsigned char *buf, size_t len,
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 9f3305f6b6d5..95f0884aae02 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -1,3 +1,4 @@
+#include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 9aed9c332da6..9c3b9ed5b3c3 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag)
 /* Get raw string list of current kprobe_events  or uprobe_events */
 struct strlist *probe_file__get_rawlist(int fd)
 {
-	int ret, idx;
+	int ret, idx, fddup;
 	FILE *fp;
 	char buf[MAX_CMDLEN];
 	char *p;
@@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd)
 		return NULL;
 
 	sl = strlist__new(NULL, NULL);
+	if (sl == NULL)
+		return NULL;
+
+	fddup = dup(fd);
+	if (fddup < 0)
+		goto out_free_sl;
+
+	fp = fdopen(fddup, "r");
+	if (!fp)
+		goto out_close_fddup;
 
-	fp = fdopen(dup(fd), "r");
 	while (!feof(fp)) {
 		p = fgets(buf, MAX_CMDLEN, fp);
 		if (!p)
@@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd)
 		ret = strlist__add(sl, buf);
 		if (ret < 0) {
 			pr_debug("strlist__add failed (%d)\n", ret);
-			strlist__delete(sl);
-			return NULL;
+			goto out_close_fp;
 		}
 	}
 	fclose(fp);
 
 	return sl;
+
+out_close_fp:
+	fclose(fp);
+	goto out_free_sl;
+out_close_fddup:
+	close(fddup);
+out_free_sl:
+	strlist__delete(sl);
+	return NULL;
 }
 
 static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
@@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache)
 {
 	struct probe_cache_entry *entry = NULL;
 	char buf[MAX_CMDLEN], *p;
-	int ret = 0;
+	int ret = 0, fddup;
 	FILE *fp;
 
-	fp = fdopen(dup(pcache->fd), "r");
-	if (!fp)
+	fddup = dup(pcache->fd);
+	if (fddup < 0)
+		return -errno;
+	fp = fdopen(fddup, "r");
+	if (!fp) {
+		close(fddup);
 		return -EINVAL;
+	}
 
 	while (!feof(fp)) {
 		if (!fgets(buf, MAX_CMDLEN, fp))
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a34321e9b44d..a811c13a74d6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	sec = syms_ss->symtab;
 	shdr = syms_ss->symshdr;
 
-	if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+	if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
+				".text", NULL))
 		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
 
 	if (runtime_ss->opdsec)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-08-12 19:35 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-08-12 19:35 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 95f3be798472f63b495ca4712af005ea5ac7aa47 perf/x86/intel/uncore: Add enable_box for client MSR uncore

Mostly tooling fixes, plus two uncore-PMU fixes, an uprobes fix, a perf-cgroups 
fix and an AUX events fix.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf hists: Trim libtraceevent trace_seq buffers
      tools: Sync cpufeatures.h and vmx.h with the kernel
      toops: Sync tools/include/uapi/linux/bpf.h with the kernel
      tools: Sync cpufeatures headers with the kernel

Brendan Gregg (1):
      perf script: Add 'bpf-output' field to usage message

David Carrillo-Cisneros (1):
      perf/core: Set cgroup in CPU contexts for new cgroup events

Denys Vlasenko (1):
      uprobes/x86: Fix RIP-relative handling of EVEX-encoded instructions

Kan Liang (2):
      perf/x86/intel/uncore: Fix uncore num_counters
      perf/x86/intel/uncore: Add enable_box for client MSR uncore

Konstantin Khlebnikov (1):
      perf probe: Fix module name matching

Mark Rutland (1):
      perf stat: Avoid skew when reading events

Masami Hiramatsu (1):
      perf probe: Adjust map->reloc offset when finding kernel symbol from map

Naohiro Aota (1):
      perf probe: Support signedness casting

Peter Zijlstra (1):
      perf/core: Fix sideband list-iteration vs. event ordering NULL pointer deference crash

Ravi Bangoria (2):
      perf probe: Add function to post process kernel trace events
      perf probe ppc64le: Fix probe location when using DWARF


 arch/x86/events/intel/uncore_snb.c             | 14 +++++
 arch/x86/events/intel/uncore_snbep.c           | 10 +--
 arch/x86/kernel/uprobes.c                      | 22 +++----
 include/linux/perf_event.h                     |  4 ++
 kernel/events/core.c                           | 77 ++++++++++++++++-------
 tools/arch/x86/include/asm/cpufeatures.h       |  9 +--
 tools/arch/x86/include/asm/disabled-features.h |  2 +
 tools/arch/x86/include/asm/required-features.h |  2 +
 tools/arch/x86/include/uapi/asm/vmx.h          |  4 +-
 tools/include/uapi/linux/bpf.h                 | 86 +++++++++++++++++++++++++-
 tools/perf/Documentation/perf-probe.txt        | 10 ++-
 tools/perf/Documentation/perf-script.txt       |  4 +-
 tools/perf/arch/powerpc/util/sym-handling.c    | 27 ++++++--
 tools/perf/builtin-script.c                    |  2 +-
 tools/perf/builtin-stat.c                      | 31 +++++++---
 tools/perf/util/probe-event.c                  | 60 +++++++++++-------
 tools/perf/util/probe-event.h                  |  6 +-
 tools/perf/util/probe-finder.c                 | 15 ++++-
 tools/perf/util/sort.c                         |  6 +-
 19 files changed, 298 insertions(+), 93 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 97a69dbba649..9d35ec0cb8fc 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+		SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
 static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
@@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = {
 
 static struct intel_uncore_ops snb_uncore_msr_ops = {
 	.init_box	= snb_uncore_msr_init_box,
+	.enable_box	= snb_uncore_msr_enable_box,
 	.exit_box	= snb_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
@@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+		SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
 static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
@@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 
 static struct intel_uncore_ops skl_uncore_msr_ops = {
 	.init_box	= skl_uncore_msr_init_box,
+	.enable_box	= skl_uncore_msr_enable_box,
 	.exit_box	= skl_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 824e54086e07..8aee83bcf71f 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2626,7 +2626,7 @@ void hswep_uncore_cpu_init(void)
 
 static struct intel_uncore_type hswep_uncore_ha = {
 	.name		= "ha",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 2,
 	.perf_ctr_bits	= 48,
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
@@ -2645,7 +2645,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = {
 
 static struct intel_uncore_type hswep_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
@@ -2691,7 +2691,7 @@ static struct intel_uncore_type hswep_uncore_irp = {
 
 static struct intel_uncore_type hswep_uncore_qpi = {
 	.name			= "qpi",
-	.num_counters		= 5,
+	.num_counters		= 4,
 	.num_boxes		= 3,
 	.perf_ctr_bits		= 48,
 	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
@@ -2773,7 +2773,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = {
 
 static struct intel_uncore_type hswep_uncore_r3qpi = {
 	.name		= "r3qpi",
-	.num_counters   = 4,
+	.num_counters   = 3,
 	.num_boxes	= 3,
 	.perf_ctr_bits	= 44,
 	.constraints	= hswep_uncore_r3qpi_constraints,
@@ -2972,7 +2972,7 @@ static struct intel_uncore_type bdx_uncore_ha = {
 
 static struct intel_uncore_type bdx_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c1ff31d99ff..495c776de4b4 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 		*cursor &= 0xfe;
 	}
 	/*
-	 * Similar treatment for VEX3 prefix.
-	 * TODO: add XOP/EVEX treatment when insn decoder supports them
+	 * Similar treatment for VEX3/EVEX prefix.
+	 * TODO: add XOP treatment when insn decoder supports them
 	 */
-	if (insn->vex_prefix.nbytes == 3) {
+	if (insn->vex_prefix.nbytes >= 3) {
 		/*
 		 * vex2:     c5    rvvvvLpp   (has no b bit)
 		 * vex3/xop: c4/8f rxbmmmmm wvvvvLpp
 		 * evex:     62    rxbR00mm wvvvv1pp zllBVaaa
-		 *   (evex will need setting of both b and x since
-		 *   in non-sib encoding evex.x is 4th bit of MODRM.rm)
-		 * Setting VEX3.b (setting because it has inverted meaning):
+		 * Setting VEX3.b (setting because it has inverted meaning).
+		 * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+		 * is the 4th bit of MODRM.rm, and needs the same treatment.
+		 * For VEX3-encoded insns, VEX3.x value has no effect in
+		 * non-SIB encoding, the change is superfluous but harmless.
 		 */
 		cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
-		*cursor |= 0x20;
+		*cursor |= 0x60;
 	}
 
 	/*
@@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 
 	reg = MODRM_REG(insn);	/* Fetch modrm.reg */
 	reg2 = 0xff;		/* Fetch vex.vvvv */
-	if (insn->vex_prefix.nbytes == 2)
-		reg2 = insn->vex_prefix.bytes[1];
-	else if (insn->vex_prefix.nbytes == 3)
+	if (insn->vex_prefix.nbytes)
 		reg2 = insn->vex_prefix.bytes[2];
 	/*
-	 * TODO: add XOP, EXEV vvvv reading.
+	 * TODO: add XOP vvvv reading.
 	 *
 	 * vex.vvvv field is in bits 6-3, bits are inverted.
 	 * But in 32-bit mode, high-order bit may be ignored.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8ed4326164cc..2b6b43cc0dd5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -743,7 +743,9 @@ struct perf_event_context {
 	u64				parent_gen;
 	u64				generation;
 	int				pin_count;
+#ifdef CONFIG_CGROUP_PERF
 	int				nr_cgroups;	 /* cgroup evts */
+#endif
 	void				*task_ctx_data; /* pmu specific data */
 	struct rcu_head			rcu_head;
 };
@@ -769,7 +771,9 @@ struct perf_cpu_context {
 	unsigned int			hrtimer_active;
 
 	struct pmu			*unique_pmu;
+#ifdef CONFIG_CGROUP_PERF
 	struct perf_cgroup		*cgrp;
+#endif
 };
 
 struct perf_output_handle {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a19550d80ab1..1903b8f3a705 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -843,6 +843,32 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 		}
 	}
 }
+
+/*
+ * Update cpuctx->cgrp so that it is set when first cgroup event is added and
+ * cleared when last cgroup event is removed.
+ */
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+			 struct perf_event_context *ctx, bool add)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (!is_cgroup_event(event))
+		return;
+
+	if (add && ctx->nr_cgroups++)
+		return;
+	else if (!add && --ctx->nr_cgroups)
+		return;
+	/*
+	 * Because cgroup events are always per-cpu events,
+	 * this will always be called from the right CPU.
+	 */
+	cpuctx = __get_cpu_context(ctx);
+	cpuctx->cgrp = add ? event->cgrp : NULL;
+}
+
 #else /* !CONFIG_CGROUP_PERF */
 
 static inline bool
@@ -920,6 +946,13 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 			 struct perf_event_context *ctx)
 {
 }
+
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+			 struct perf_event_context *ctx, bool add)
+{
+}
+
 #endif
 
 /*
@@ -1392,6 +1425,7 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
+
 	lockdep_assert_held(&ctx->lock);
 
 	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1412,8 +1446,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		list_add_tail(&event->group_entry, list);
 	}
 
-	if (is_cgroup_event(event))
-		ctx->nr_cgroups++;
+	list_update_cgroup_event(event, ctx, true);
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	ctx->nr_events++;
@@ -1581,8 +1614,6 @@ static void perf_group_attach(struct perf_event *event)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-	struct perf_cpu_context *cpuctx;
-
 	WARN_ON_ONCE(event->ctx != ctx);
 	lockdep_assert_held(&ctx->lock);
 
@@ -1594,20 +1625,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
-	if (is_cgroup_event(event)) {
-		ctx->nr_cgroups--;
-		/*
-		 * Because cgroup events are always per-cpu events, this will
-		 * always be called from the right CPU.
-		 */
-		cpuctx = __get_cpu_context(ctx);
-		/*
-		 * If there are no more cgroup events then clear cgrp to avoid
-		 * stale pointer in update_cgrp_time_from_cpuctx().
-		 */
-		if (!ctx->nr_cgroups)
-			cpuctx->cgrp = NULL;
-	}
+	list_update_cgroup_event(event, ctx, false);
 
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
@@ -1716,8 +1734,8 @@ static inline int pmu_filter_match(struct perf_event *event)
 static inline int
 event_filter_match(struct perf_event *event)
 {
-	return (event->cpu == -1 || event->cpu == smp_processor_id())
-	    && perf_cgroup_match(event) && pmu_filter_match(event);
+	return (event->cpu == -1 || event->cpu == smp_processor_id()) &&
+	       perf_cgroup_match(event) && pmu_filter_match(event);
 }
 
 static void
@@ -1737,8 +1755,8 @@ event_sched_out(struct perf_event *event,
 	 * maintained, otherwise bogus information is return
 	 * via read() for time_enabled, time_running:
 	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE
-	    && !event_filter_match(event)) {
+	if (event->state == PERF_EVENT_STATE_INACTIVE &&
+	    !event_filter_match(event)) {
 		delta = tstamp - event->tstamp_stopped;
 		event->tstamp_running += delta;
 		event->tstamp_stopped = tstamp;
@@ -2236,10 +2254,15 @@ perf_install_in_context(struct perf_event_context *ctx,
 
 	lockdep_assert_held(&ctx->mutex);
 
-	event->ctx = ctx;
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
+	/*
+	 * Ensures that if we can observe event->ctx, both the event and ctx
+	 * will be 'complete'. See perf_iterate_sb_cpu().
+	 */
+	smp_store_release(&event->ctx, ctx);
+
 	if (!task) {
 		cpu_function_call(cpu, __perf_install_in_context, event);
 		return;
@@ -5969,6 +5992,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data)
 	struct perf_event *event;
 
 	list_for_each_entry_rcu(event, &pel->list, sb_list) {
+		/*
+		 * Skip events that are not fully formed yet; ensure that
+		 * if we observe event->ctx, both event and ctx will be
+		 * complete enough. See perf_install_in_context().
+		 */
+		if (!smp_load_acquire(&event->ctx))
+			continue;
+
 		if (event->state < PERF_EVENT_STATE_INACTIVE)
 			continue;
 		if (!event_filter_match(event))
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 4a413485f9eb..92a8308b96f6 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -225,7 +225,6 @@
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
 #define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
@@ -301,10 +300,6 @@
 #define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
-
-
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
@@ -312,5 +307,7 @@
  */
 #define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
-
+#define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 911e9358ceb1..85599ad4d024 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,5 +56,7 @@
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 4916144e3c42..fac9a5c0abe9 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -99,5 +99,7 @@
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
+#define REQUIRED_MASK17	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 5b15d94a33f8..37fee272618f 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -78,7 +78,6 @@
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
-#define EXIT_REASON_PCOMMIT             65
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -127,8 +126,7 @@
 	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
-	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
-	{ EXIT_REASON_PCOMMIT,               "PCOMMIT" }
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 406459b935a2..da218fec6056 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -84,6 +84,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_PERCPU_HASH,
 	BPF_MAP_TYPE_PERCPU_ARRAY,
 	BPF_MAP_TYPE_STACK_TRACE,
+	BPF_MAP_TYPE_CGROUP_ARRAY,
 };
 
 enum bpf_prog_type {
@@ -93,6 +94,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SCHED_CLS,
 	BPF_PROG_TYPE_SCHED_ACT,
 	BPF_PROG_TYPE_TRACEPOINT,
+	BPF_PROG_TYPE_XDP,
 };
 
 #define BPF_PSEUDO_MAP_FD	1
@@ -313,6 +315,66 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_skb_get_tunnel_opt,
 	BPF_FUNC_skb_set_tunnel_opt,
+
+	/**
+	 * bpf_skb_change_proto(skb, proto, flags)
+	 * Change protocol of the skb. Currently supported is
+	 * v4 -> v6, v6 -> v4 transitions. The helper will also
+	 * resize the skb. eBPF program is expected to fill the
+	 * new headers via skb_store_bytes and lX_csum_replace.
+	 * @skb: pointer to skb
+	 * @proto: new skb->protocol type
+	 * @flags: reserved
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_skb_change_proto,
+
+	/**
+	 * bpf_skb_change_type(skb, type)
+	 * Change packet type of skb.
+	 * @skb: pointer to skb
+	 * @type: new skb->pkt_type type
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_skb_change_type,
+
+	/**
+	 * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+	 * @skb: pointer to skb
+	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+	 * @index: index of the cgroup in the bpf_map
+	 * Return:
+	 *   == 0 skb failed the cgroup2 descendant test
+	 *   == 1 skb succeeded the cgroup2 descendant test
+	 *    < 0 error
+	 */
+	BPF_FUNC_skb_in_cgroup,
+
+	/**
+	 * bpf_get_hash_recalc(skb)
+	 * Retrieve and possibly recalculate skb->hash.
+	 * @skb: pointer to skb
+	 * Return: hash
+	 */
+	BPF_FUNC_get_hash_recalc,
+
+	/**
+	 * u64 bpf_get_current_task(void)
+	 * Returns current task_struct
+	 * Return: current
+	 */
+	BPF_FUNC_get_current_task,
+
+	/**
+	 * bpf_probe_write_user(void *dst, void *src, int len)
+	 * safely attempt to write to a location
+	 * @dst: destination address in userspace
+	 * @src: source address on stack
+	 * @len: number of bytes to copy
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_probe_write_user,
+
 	__BPF_FUNC_MAX_ID,
 };
 
@@ -347,9 +409,11 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
-/* BPF_FUNC_perf_event_output flags. */
+/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
 #define BPF_F_INDEX_MASK		0xffffffffULL
 #define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+#define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
@@ -386,4 +450,24 @@ struct bpf_tunnel_key {
 	__u32 tunnel_label;
 };
 
+/* User return codes for XDP prog type.
+ * A valid XDP program must return one of these defined values. All other
+ * return codes are reserved for future use. Unknown return codes will result
+ * in packet drop.
+ */
+enum xdp_action {
+	XDP_ABORTED = 0,
+	XDP_DROP,
+	XDP_PASS,
+	XDP_TX,
+};
+
+/* user accessible metadata for XDP packet hook
+ * new fields must be added to the end of this structure
+ */
+struct xdp_md {
+	__u32 data;
+	__u32 data_end;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 736da44596e4..b303bcdd8ed1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -176,10 +176,18 @@ Each probe argument follows below syntax.
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
 '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
-'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
 
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
 
+TYPES
+-----
+Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe.
+String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
 LINE SYNTAX
 -----------
 Line range is described by following syntax.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 1f6c70594f0f..053bbbd84ece 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,8 +116,8 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-	srcline, period, iregs, brstack, brstacksym, flags.
-        Field list can be prepended with the type, trace, sw or hw,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        callindent. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index c6d0f91731a1..8d4dc97d80ba 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -54,10 +54,6 @@ int arch__compare_symbol_names(const char *namea, const char *nameb)
 #endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
-bool arch__prefers_symtab(void)
-{
-	return true;
-}
 
 #ifdef HAVE_LIBELF_SUPPORT
 void arch__sym_update(struct symbol *s, GElf_Sym *sym)
@@ -100,4 +96,27 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 			tev->point.offset += lep_offset;
 	}
 }
+
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+					   int ntevs)
+{
+	struct probe_trace_event *tev;
+	struct map *map;
+	struct symbol *sym = NULL;
+	struct rb_node *tmp;
+	int i = 0;
+
+	map = get_target_map(pev->target, pev->uprobes);
+	if (!map || map__load(map, NULL) < 0)
+		return;
+
+	for (i = 0; i < ntevs; i++) {
+		tev = &pev->tevs[i];
+		map__for_each_symbol(map, sym, tmp) {
+			if (map->unmap_ip(map, sym->start) == tev->point.address)
+				arch__fix_tev_from_maps(pev, tev, map, sym);
+		}
+	}
+}
+
 #endif
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 971ff91b16cb..9c640a8081c7 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2116,7 +2116,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "callindent", parse_output_fields),
+		     "bpf-output,callindent", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0c16d20d7e32..3c7452b39f57 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -331,7 +331,7 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void read_counters(bool close_counters)
+static void read_counters(void)
 {
 	struct perf_evsel *counter;
 
@@ -341,11 +341,6 @@ static void read_counters(bool close_counters)
 
 		if (perf_stat_process_counter(&stat_config, counter))
 			pr_warning("failed to process counter %s\n", counter->name);
-
-		if (close_counters) {
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-					     thread_map__nr(evsel_list->threads));
-		}
 	}
 }
 
@@ -353,7 +348,7 @@ static void process_interval(void)
 {
 	struct timespec ts, rs;
 
-	read_counters(false);
+	read_counters();
 
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
@@ -380,6 +375,17 @@ static void enable_counters(void)
 		perf_evlist__enable(evsel_list);
 }
 
+static void disable_counters(void)
+{
+	/*
+	 * If we don't have tracee (attaching to task or cpu), counters may
+	 * still be running. To get accurate group ratios, we must stop groups
+	 * from counting before reading their constituent counters.
+	 */
+	if (!target__none(&target))
+		perf_evlist__disable(evsel_list);
+}
+
 static volatile int workload_exec_errno;
 
 /*
@@ -657,11 +663,20 @@ static int __run_perf_stat(int argc, const char **argv)
 		}
 	}
 
+	disable_counters();
+
 	t1 = rdclock();
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	read_counters(true);
+	/*
+	 * Closing a group leader splits the group, and as we only disable
+	 * group leaders, results in remaining events becoming enabled. To
+	 * avoid arbitrary skew, we must read all counters before closing any
+	 * group leaders.
+	 */
+	read_counters();
+	perf_evlist__close(evsel_list);
 
 	return WEXITSTATUS(status);
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 953dc1ab2ed7..28733962cd80 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -170,15 +170,17 @@ static struct map *kernel_get_module_map(const char *module)
 		module = "kernel";
 
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+		/* short_name is "[module]" */
 		if (strncmp(pos->dso->short_name + 1, module,
-			    pos->dso->short_name_len - 2) == 0) {
+			    pos->dso->short_name_len - 2) == 0 &&
+		    module[pos->dso->short_name_len - 2] == '\0') {
 			return pos;
 		}
 	}
 	return NULL;
 }
 
-static struct map *get_target_map(const char *target, bool user)
+struct map *get_target_map(const char *target, bool user)
 {
 	/* Init maps of given executable or kernel */
 	if (user)
@@ -385,7 +387,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
 		if (uprobes)
 			address = sym->start;
 		else
-			address = map->unmap_ip(map, sym->start);
+			address = map->unmap_ip(map, sym->start) - map->reloc;
 		break;
 	}
 	if (!address) {
@@ -664,22 +666,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 	return ret;
 }
 
-/* Post processing the probe events */
-static int post_process_probe_trace_events(struct probe_trace_event *tevs,
-					   int ntevs, const char *module,
-					   bool uprobe)
+static int
+post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
+				       int ntevs)
 {
 	struct ref_reloc_sym *reloc_sym;
 	char *tmp;
 	int i, skipped = 0;
 
-	if (uprobe)
-		return add_exec_to_probe_trace_events(tevs, ntevs, module);
-
-	/* Note that currently ref_reloc_sym based probe is not for drivers */
-	if (module)
-		return add_module_to_probe_trace_events(tevs, ntevs, module);
-
 	reloc_sym = kernel_get_ref_reloc_sym();
 	if (!reloc_sym) {
 		pr_warning("Relocated base symbol is not found!\n");
@@ -711,6 +705,34 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 	return skipped;
 }
 
+void __weak
+arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused,
+				      int ntevs __maybe_unused)
+{
+}
+
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct perf_probe_event *pev,
+					   struct probe_trace_event *tevs,
+					   int ntevs, const char *module,
+					   bool uprobe)
+{
+	int ret;
+
+	if (uprobe)
+		ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
+	else if (module)
+		/* Currently ref_reloc_sym based probe is not for drivers */
+		ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+	else
+		ret = post_process_kernel_probe_trace_events(tevs, ntevs);
+
+	if (ret >= 0)
+		arch__post_process_probe_trace_events(pev, ntevs);
+
+	return ret;
+}
+
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 					  struct probe_trace_event **tevs)
@@ -749,7 +771,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
-		ret = post_process_probe_trace_events(*tevs, ntevs,
+		ret = post_process_probe_trace_events(pev, *tevs, ntevs,
 						pev->target, pev->uprobes);
 		if (ret < 0 || ret == ntevs) {
 			clear_probe_trace_events(*tevs, ntevs);
@@ -2936,8 +2958,6 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
 	return err;
 }
 
-bool __weak arch__prefers_symtab(void) { return false; }
-
 /* Concatinate two arrays */
 static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
 {
@@ -3158,12 +3178,6 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 	if (ret > 0 || pev->sdt)	/* SDT can be found only in the cache */
 		return ret == 0 ? -ENOENT : ret; /* Found in probe cache */
 
-	if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
-		ret = find_probe_trace_events_from_map(pev, tevs);
-		if (ret > 0)
-			return ret; /* Found in symbol table */
-	}
-
 	/* Convert perf_probe_event with debuginfo */
 	ret = try_to_find_probe_trace_events(pev, tevs);
 	if (ret != 0)
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index e18ea9fe6385..f4f45db77c1c 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -158,7 +158,6 @@ int show_line_range(struct line_range *lr, const char *module, bool user);
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
 			struct strfilter *filter);
 int show_available_funcs(const char *module, struct strfilter *filter, bool user);
-bool arch__prefers_symtab(void);
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 			     struct probe_trace_event *tev, struct map *map,
 			     struct symbol *sym);
@@ -173,4 +172,9 @@ int e_snprintf(char *str, size_t size, const char *format, ...)
 int copy_to_probe_trace_arg(struct probe_trace_arg *tvar,
 			    struct perf_probe_arg *pvar);
 
+struct map *get_target_map(const char *target, bool user);
+
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+					   int ntevs);
+
 #endif /*_PROBE_EVENT_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index f2d9ff064e2d..5c290c682afe 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -297,10 +297,13 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	char sbuf[STRERR_BUFSIZE];
 	int bsize, boffs, total;
 	int ret;
+	char sign;
 
 	/* TODO: check all types */
-	if (cast && strcmp(cast, "string") != 0) {
+	if (cast && strcmp(cast, "string") != 0 &&
+	    strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) {
 		/* Non string type is OK */
+		/* and respect signedness cast */
 		tvar->type = strdup(cast);
 		return (tvar->type == NULL) ? -ENOMEM : 0;
 	}
@@ -361,6 +364,13 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		return (tvar->type == NULL) ? -ENOMEM : 0;
 	}
 
+	if (cast && (strcmp(cast, "u") == 0))
+		sign = 'u';
+	else if (cast && (strcmp(cast, "s") == 0))
+		sign = 's';
+	else
+		sign = die_is_signed_type(&type) ? 's' : 'u';
+
 	ret = dwarf_bytesize(&type);
 	if (ret <= 0)
 		/* No size ... try to use default type */
@@ -373,8 +383,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 			dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
 		ret = MAX_BASIC_TYPE_BITS;
 	}
-	ret = snprintf(buf, 16, "%c%d",
-		       die_is_signed_type(&type) ? 's' : 'u', ret);
+	ret = snprintf(buf, 16, "%c%d", sign, ret);
 
 formatted:
 	if (ret < 0 || ret >= 16) {
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 947d21f38398..3d3cb8392c86 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -588,7 +588,11 @@ static char *get_trace_output(struct hist_entry *he)
 	} else {
 		pevent_event_info(&seq, evsel->tp_format, &rec);
 	}
-	return seq.buffer;
+	/*
+	 * Trim the buffer, it starts at 4KB and we're not going to
+	 * add anything more to this buffer.
+	 */
+	return realloc(seq.buffer, seq.len + 1);
 }
 
 static int64_t

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-07-26 14:13 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-07-26 14:13 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Stephen Rothwell, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 674d2d69b14f677a771ceec4b48bfade94a0c5f1 Merge tag 'perf-core-for-mingo-20160725' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

This tree contains tooling fixes plus some additions:

 - fixes to the vdso2c build environment that Stephen Rothwell is using for the 
   linux-next build (Arnaldo Carvalho de Melo)

 - AVX-512 instruction mappings (Adrian Hunter)

 - misc fixes 

 Thanks,

	Ingo

------------------>
Adrian Hunter (4):
      x86/insn: perf tools: Fix vcvtph2ps instruction decoding
      x86/insn: Add AVX-512 support to the instruction decoder
      perf tools: Add AVX-512 support to the instruction decoder used by Intel PT
      perf tools: Add AVX-512 instructions to the new instructions test

Arnaldo Carvalho de Melo (5):
      perf tests kmod-path: Fix build on ubuntu:16.04-x-armhf
      tools build: Add HOSTARCH Makefile variable
      objtool: Use tools/scripts/Makefile.arch to get ARCH and HOSTARCH
      objtool: Always use host headers
      Revert "perf tools: event.h needs asm/perf_regs.h"

Josh Poimboeuf (1):
      tools build: Fix objtool build with ARCH=x86_64

Stephen Rothwell (1):
      x86: Make the vdso2c compiler use the host architecture headers


 arch/x86/entry/vdso/Makefile                       |    2 +-
 arch/x86/include/asm/inat.h                        |   17 +-
 arch/x86/include/asm/insn.h                        |   12 +-
 arch/x86/lib/insn.c                                |   18 +-
 arch/x86/lib/x86-opcode-map.txt                    |  263 ++-
 arch/x86/tools/gen-insn-attr-x86.awk               |   11 +-
 tools/objtool/Build                                |    2 +-
 tools/objtool/Makefile                             |    8 +-
 tools/perf/arch/x86/tests/insn-x86-dat-32.c        | 1018 ++++++++++-
 tools/perf/arch/x86/tests/insn-x86-dat-64.c        |  940 +++++++++-
 tools/perf/arch/x86/tests/insn-x86-dat-src.c       | 1789 ++++++++++++++++++++
 tools/perf/tests/kmod-path.c                       |    1 +
 tools/perf/util/event.h                            |    1 -
 .../util/intel-pt-decoder/gen-insn-attr-x86.awk    |   11 +-
 tools/perf/util/intel-pt-decoder/inat.h            |   17 +-
 tools/perf/util/intel-pt-decoder/insn.c            |   18 +-
 tools/perf/util/intel-pt-decoder/insn.h            |   12 +-
 .../perf/util/intel-pt-decoder/x86-opcode-map.txt  |  263 ++-
 tools/scripts/Makefile.arch                        |   41 +-
 19 files changed, 4221 insertions(+), 223 deletions(-)

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 253b72eaade6..25e88c030c47 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -55,7 +55,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 74a2e312e8a2..02aff0867211 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index e7814b74caf8..b3e32b010ab1 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 1a416935bac9..1088eb8f3a5f 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -155,14 +155,24 @@ void insn_get_prefixes(struct insn *insn)
 			/*
 			 * In 32-bits mode, if the [7:6] bits (mod bits of
 			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES.
+			 * LDS or LES or BOUND.
 			 */
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
 		insn->vex_prefix.bytes[0] = b;
 		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_vex3_prefix(attr)) {
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
 			insn->vex_prefix.bytes[2] = b2;
 			insn->vex_prefix.nbytes = 3;
@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
-		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+		    (!inat_accept_vex(insn->attr) &&
+		     !inat_is_group(insn->attr)))
 			insn->attr = 0;	/* This instruction is bad */
 		goto end;	/* VEX has only 1 byte for opcode */
 	}
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index d388de72eaca..ec378cd7b71e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -13,12 +13,17 @@
 # opcode: escape # escaped-name
 # EndTable
 #
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
 #<group maps>
 # GrpTable: GrpXXX
 # reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
 # EndTable
 #
 # AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
 #
@@ -137,7 +142,7 @@ Table: one byte opcode
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -399,17 +404,17 @@ AVXcode: 1
 3f:
 # 0x0f 0x40-0x4f
 40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev
-42: CMOVB/C/NAE Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
 43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev
-45: CMOVNE/NZ Gv,Ev
-46: CMOVBE/NA Gv,Ev
-47: CMOVA/NBE Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
 48: CMOVS Gv,Ev
 49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev
-4b: CMOVNP/PO Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
 4c: CMOVL/NGE Gv,Ev
 4d: CMOVNL/GE Gv,Ev
 4e: CMOVLE/NG Gv,Ev
@@ -426,7 +431,7 @@ AVXcode: 1
 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
@@ -447,7 +452,7 @@ AVXcode: 1
 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
 # 0x0f 0x70-0x7f
 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
@@ -458,14 +463,14 @@ AVXcode: 1
 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
 # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
 77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy
-79: VMWRITE Gy,Ey
-7a:
-7b:
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
 80: JO Jz (f64)
@@ -485,16 +490,16 @@ AVXcode: 1
 8e: JLE/JNG Jz (f64)
 8f: JNLE/JG Jz (f64)
 # 0x0f 0x90-0x9f
-90: SETO Eb
-91: SETNO Eb
-92: SETB/C/NAE Eb
-93: SETAE/NB/NC Eb
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
 94: SETE/Z Eb
 95: SETNE/NZ Eb
 96: SETBE/NA Eb
 97: SETA/NBE Eb
-98: SETS Eb
-99: SETNS Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
 9a: SETP/PE Eb
 9b: SETNP/PO Eb
 9c: SETL/NGE Eb
@@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
 d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
 d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
 da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
 dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
 dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
 de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xe0-0xef
 e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
 e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
@@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
 e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
 e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
 e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
 e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
 e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
 e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
 ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
 ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
 ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
 ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xf0-0xff
 f0: vlddqu Vx,Mx (F2)
 f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
@@ -626,81 +631,105 @@ AVXcode: 2
 0e: vtestps Vx,Wx (66),(v)
 0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66)
-11:
-12:
-13: vcvtph2ps Vx,Wx,Ib (66),(v)
-14: blendvps Vdq,Wdq (66)
-15: blendvpd Vdq,Wdq (66)
-16: vpermps Vqq,Hqq,Wqq (66),(v)
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
 17: vptest Vx,Wx (66)
 18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 Vqq,Mdq (66),(v)
-1b:
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f:
+1f: vpabsq Vx,Wx (66),(ev)
 # 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1)
-26:
-27:
-28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: vmovntdqa Vx,Mx (66),(v1)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
 2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
 2e: vmaskmovps Mx,Hx,Vx (66),(v)
 2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36: vpermd Vqq,Hqq,Wqq (66),(v)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
 37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1)
-39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: vpminud Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
 3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
 3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1)
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
 41: vphminposuw Vdq,Wdq (66),(v1)
-42:
-43:
-44:
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
 45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
 47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x57
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
 58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v)
-5a: vbroadcasti128 Vqq,Mdq (66),(v)
-# Skip 0x5b-0x77
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
 78: vpbroadcastb Vx,Wx (66),(v)
 79: vpbroadcastw Vx,Wx (66),(v)
-# Skip 0x7a-0x7f
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
 81: INVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v)
-91: vgatherqd/q Vx,Hx,Wx (66),(v)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
 92: vgatherdps/d Vx,Hx,Wx (66),(v)
 93: vgatherqps/d Vx,Hx,Wx (66),(v)
 94:
@@ -715,6 +744,10 @@ AVXcode: 2
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
 a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
@@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-c8: sha1nexte Vdq,Wdq
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq
-cb: sha256rnds2 Vdq,Wdq
-cc: sha256msg1 Vdq,Wdq
-cd: sha256msg2 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -763,15 +801,15 @@ AVXcode: 3
 00: vpermq Vqq,Wqq,Ib (66),(v)
 01: vpermpd Vqq,Wqq,Ib (66),(v)
 02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03:
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
 04: vpermilps Vx,Wx,Ib (66),(v)
 05: vpermilpd Vx,Wx,Ib (66),(v)
 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
 07:
-08: vroundps Vx,Wx,Ib (66)
-09: vroundpd Vx,Wx,Ib (66)
-0a: vroundss Vss,Wss,Ib (66),(v1)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
 0c: vblendps Vx,Hx,Wx,Ib (66)
 0d: vblendpd Vx,Hx,Wx,Ib (66)
 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
@@ -780,26 +818,51 @@ AVXcode: 3
 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
 16: vpextrd/q Ey,Vdq,Ib (66),(v1)
 17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-19: vextractf128 Wdq,Vqq,Ib (66),(v)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
 1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-39: vextracti128 Wdq,Vqq,Ib (66),(v)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
 40: vdpps Vx,Hx,Wx,Ib (66)
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
@@ -927,8 +990,10 @@ GrpTable: Grp12
 EndTable
 
 GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
@@ -963,6 +1028,20 @@ GrpTable: Grp17
 3: BLSI By,Ey (v)
 EndTable
 
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 093a892026f9..a3d2c62fd805 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 2457916a3943..d6cdece5e58b 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -1,4 +1,4 @@
-objtool-y += arch/$(ARCH)/
+objtool-y += arch/$(SRCARCH)/
 objtool-y += builtin-check.o
 objtool-y += elf.o
 objtool-y += special.o
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 1f75b0a046cc..0b437700f688 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -1,11 +1,9 @@
 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
-ifndef ($(ARCH))
-ARCH ?= $(shell uname -m)
 ifeq ($(ARCH),x86_64)
 ARCH := x86
 endif
-endif
 
 # always use the host compiler
 CC = gcc
@@ -26,7 +24,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi
 CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
 
@@ -35,7 +33,7 @@ elfshdr := $(shell echo '\#include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | gre
 CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
 
 AWK = awk
-export srctree OUTPUT CFLAGS ARCH AWK
+export srctree OUTPUT CFLAGS SRCARCH AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(OBJTOOL_IN): fixdep FORCE
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
index 3b491cfe204e..3918dd52e903 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -6,6 +6,1016 @@
 
 {{0x0f, 0x31, }, 2, 0, "", "",
 "0f 31                \trdtsc  ",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 81 78 56 34 12    \tbound  %eax,0x12345678(%ecx)",},
+{{0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 88 78 56 34 12    \tbound  %ecx,0x12345678(%eax)",},
+{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 90 78 56 34 12    \tbound  %edx,0x12345678(%eax)",},
+{{0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 98 78 56 34 12    \tbound  %ebx,0x12345678(%eax)",},
+{{0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 a0 78 56 34 12    \tbound  %esp,0x12345678(%eax)",},
+{{0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 a8 78 56 34 12    \tbound  %ebp,0x12345678(%eax)",},
+{{0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 b0 78 56 34 12    \tbound  %esi,0x12345678(%eax)",},
+{{0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 b8 78 56 34 12    \tbound  %edi,0x12345678(%eax)",},
+{{0x62, 0x08, }, 2, 0, "", "",
+"62 08                \tbound  %ecx,(%eax)",},
+{{0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 05 78 56 34 12    \tbound  %eax,0x12345678",},
+{{0x62, 0x14, 0x01, }, 3, 0, "", "",
+"62 14 01             \tbound  %edx,(%ecx,%eax,1)",},
+{{0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 14 05 78 56 34 12 \tbound  %edx,0x12345678(,%eax,1)",},
+{{0x62, 0x14, 0x08, }, 3, 0, "", "",
+"62 14 08             \tbound  %edx,(%eax,%ecx,1)",},
+{{0x62, 0x14, 0xc8, }, 3, 0, "", "",
+"62 14 c8             \tbound  %edx,(%eax,%ecx,8)",},
+{{0x62, 0x50, 0x12, }, 3, 0, "", "",
+"62 50 12             \tbound  %edx,0x12(%eax)",},
+{{0x62, 0x55, 0x12, }, 3, 0, "", "",
+"62 55 12             \tbound  %edx,0x12(%ebp)",},
+{{0x62, 0x54, 0x01, 0x12, }, 4, 0, "", "",
+"62 54 01 12          \tbound  %edx,0x12(%ecx,%eax,1)",},
+{{0x62, 0x54, 0x05, 0x12, }, 4, 0, "", "",
+"62 54 05 12          \tbound  %edx,0x12(%ebp,%eax,1)",},
+{{0x62, 0x54, 0x08, 0x12, }, 4, 0, "", "",
+"62 54 08 12          \tbound  %edx,0x12(%eax,%ecx,1)",},
+{{0x62, 0x54, 0xc8, 0x12, }, 4, 0, "", "",
+"62 54 c8 12          \tbound  %edx,0x12(%eax,%ecx,8)",},
+{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 90 78 56 34 12    \tbound  %edx,0x12345678(%eax)",},
+{{0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 95 78 56 34 12    \tbound  %edx,0x12345678(%ebp)",},
+{{0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 01 78 56 34 12 \tbound  %edx,0x12345678(%ecx,%eax,1)",},
+{{0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 05 78 56 34 12 \tbound  %edx,0x12345678(%ebp,%eax,1)",},
+{{0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 08 78 56 34 12 \tbound  %edx,0x12345678(%eax,%ecx,1)",},
+{{0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 c8 78 56 34 12 \tbound  %edx,0x12345678(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 81 78 56 34 12 \tbound  %ax,0x12345678(%ecx)",},
+{{0x66, 0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 88 78 56 34 12 \tbound  %cx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 90 78 56 34 12 \tbound  %dx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 98 78 56 34 12 \tbound  %bx,0x12345678(%eax)",},
+{{0x66, 0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 a0 78 56 34 12 \tbound  %sp,0x12345678(%eax)",},
+{{0x66, 0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 a8 78 56 34 12 \tbound  %bp,0x12345678(%eax)",},
+{{0x66, 0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 b0 78 56 34 12 \tbound  %si,0x12345678(%eax)",},
+{{0x66, 0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 b8 78 56 34 12 \tbound  %di,0x12345678(%eax)",},
+{{0x66, 0x62, 0x08, }, 3, 0, "", "",
+"66 62 08             \tbound  %cx,(%eax)",},
+{{0x66, 0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 05 78 56 34 12 \tbound  %ax,0x12345678",},
+{{0x66, 0x62, 0x14, 0x01, }, 4, 0, "", "",
+"66 62 14 01          \tbound  %dx,(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 14 05 78 56 34 12 \tbound  %dx,0x12345678(,%eax,1)",},
+{{0x66, 0x62, 0x14, 0x08, }, 4, 0, "", "",
+"66 62 14 08          \tbound  %dx,(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x14, 0xc8, }, 4, 0, "", "",
+"66 62 14 c8          \tbound  %dx,(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x50, 0x12, }, 4, 0, "", "",
+"66 62 50 12          \tbound  %dx,0x12(%eax)",},
+{{0x66, 0x62, 0x55, 0x12, }, 4, 0, "", "",
+"66 62 55 12          \tbound  %dx,0x12(%ebp)",},
+{{0x66, 0x62, 0x54, 0x01, 0x12, }, 5, 0, "", "",
+"66 62 54 01 12       \tbound  %dx,0x12(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x54, 0x05, 0x12, }, 5, 0, "", "",
+"66 62 54 05 12       \tbound  %dx,0x12(%ebp,%eax,1)",},
+{{0x66, 0x62, 0x54, 0x08, 0x12, }, 5, 0, "", "",
+"66 62 54 08 12       \tbound  %dx,0x12(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x54, 0xc8, 0x12, }, 5, 0, "", "",
+"66 62 54 c8 12       \tbound  %dx,0x12(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 90 78 56 34 12 \tbound  %dx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 95 78 56 34 12 \tbound  %dx,0x12345678(%ebp)",},
+{{0x66, 0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 01 78 56 34 12 \tbound  %dx,0x12345678(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 05 78 56 34 12 \tbound  %dx,0x12345678(%ebp,%eax,1)",},
+{{0x66, 0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 08 78 56 34 12 \tbound  %dx,0x12345678(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 c8 78 56 34 12 \tbound  %dx,0x12345678(%eax,%ecx,8)",},
+{{0x0f, 0x41, 0xd8, }, 3, 0, "", "",
+"0f 41 d8             \tcmovno %eax,%ebx",},
+{{0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%ecx",},
+{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%cx",},
+{{0x0f, 0x44, 0xd8, }, 3, 0, "", "",
+"0f 44 d8             \tcmove  %eax,%ebx",},
+{{0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 44 88 78 56 34 12 \tcmove  0x12345678(%eax),%ecx",},
+{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 44 88 78 56 34 12 \tcmove  0x12345678(%eax),%cx",},
+{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 90 80 78 56 34 12 \tseto   0x12345678(%eax)",},
+{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 91 80 78 56 34 12 \tsetno  0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 98 80 78 56 34 12 \tsets   0x12345678(%eax)",},
+{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 99 80 78 56 34 12 \tsetns  0x12345678(%eax)",},
+{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cc 41 ef          \tkandw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 41 ef       \tkandq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cd 41 ef          \tkandb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 41 ef       \tkandd  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cc 42 ef          \tkandnw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 42 ef       \tkandnq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cd 42 ef          \tkandnb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 42 ef       \tkandnd %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f8 44 f7          \tknotw  %k7,%k6",},
+{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f8 44 f7       \tknotq  %k7,%k6",},
+{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f9 44 f7          \tknotb  %k7,%k6",},
+{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f9 44 f7       \tknotd  %k7,%k6",},
+{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cc 45 ef          \tkorw   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 45 ef       \tkorq   %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cd 45 ef          \tkorb   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 45 ef       \tkord   %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cc 46 ef          \tkxnorw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 46 ef       \tkxnorq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cd 46 ef          \tkxnorb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 46 ef       \tkxnord %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cc 47 ef          \tkxorw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 47 ef       \tkxorq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cd 47 ef          \tkxorb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 47 ef       \tkxord  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cc 4a ef          \tkaddw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4a ef       \tkaddq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cd 4a ef          \tkaddb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 4a ef       \tkaddd  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cd 4b ef          \tkunpckbw %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cc 4b ef          \tkunpckwd %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4b ef       \tkunpckdq %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f8 90 ee          \tkmovw  %k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f8 90 29          \tkmovw  (%ecx),%k5",},
+{{0xc5, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f8 90 ac c8 23 01 00 00 \tkmovw  0x123(%eax,%ecx,8),%k5",},
+{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f8 91 29          \tkmovw  %k5,(%ecx)",},
+{{0xc5, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f8 91 ac c8 23 01 00 00 \tkmovw  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f8 92 e8          \tkmovw  %eax,%k5",},
+{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f8 92 ed          \tkmovw  %ebp,%k5",},
+{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f8 93 c5          \tkmovw  %k5,%eax",},
+{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f8 93 ed          \tkmovw  %k5,%ebp",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 90 ee       \tkmovq  %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 90 29       \tkmovq  (%ecx),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f8 90 ac c8 23 01 00 00 \tkmovq  0x123(%eax,%ecx,8),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 91 29       \tkmovq  %k5,(%ecx)",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f8 91 ac c8 23 01 00 00 \tkmovq  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f9 90 ee          \tkmovb  %k6,%k5",},
+{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f9 90 29          \tkmovb  (%ecx),%k5",},
+{{0xc5, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f9 90 ac c8 23 01 00 00 \tkmovb  0x123(%eax,%ecx,8),%k5",},
+{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f9 91 29          \tkmovb  %k5,(%ecx)",},
+{{0xc5, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f9 91 ac c8 23 01 00 00 \tkmovb  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f9 92 e8          \tkmovb  %eax,%k5",},
+{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f9 92 ed          \tkmovb  %ebp,%k5",},
+{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f9 93 c5          \tkmovb  %k5,%eax",},
+{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f9 93 ed          \tkmovb  %k5,%ebp",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 90 ee       \tkmovd  %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 90 29       \tkmovd  (%ecx),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f9 90 ac c8 23 01 00 00 \tkmovd  0x123(%eax,%ecx,8),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 91 29       \tkmovd  %k5,(%ecx)",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f9 91 ac c8 23 01 00 00 \tkmovd  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 fb 92 e8          \tkmovd  %eax,%k5",},
+{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "",
+"c5 fb 92 ed          \tkmovd  %ebp,%k5",},
+{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 fb 93 c5          \tkmovd  %k5,%eax",},
+{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "",
+"c5 fb 93 ed          \tkmovd  %k5,%ebp",},
+{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f8 98 ee          \tkortestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 98 ee       \tkortestq %k6,%k5",},
+{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f9 98 ee          \tkortestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 98 ee       \tkortestd %k6,%k5",},
+{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f8 99 ee          \tktestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 99 ee       \tktestq %k6,%k5",},
+{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f9 99 ee          \tktestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 99 ee       \tktestd %k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 30 ee 12    \tkshiftrw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 31 ee 5b    \tkshiftrq $0x5b,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 32 ee 12    \tkshiftlw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 33 ee 5b    \tkshiftlq $0x5b,%k6,%k5",},
+{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f8 5b f5          \tvcvtdq2ps %xmm5,%xmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 5b f5    \tvcvtqq2ps %zmm5,%ymm6{%k7}",},
+{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f9 5b f5          \tvcvtps2dq %xmm5,%xmm6",},
+{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 fa 5b f5          \tvcvttps2dq %xmm5,%xmm6",},
+{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "",
+"0f 6f e0             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fd 6f f4          \tvmovdqa %ymm4,%ymm6",},
+{{0x62, 0xf1, 0x7d, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 48 6f f5    \tvmovdqa32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 6f f5    \tvmovdqa64 %zmm5,%zmm6",},
+{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fe 6f f4          \tvmovdqu %ymm4,%ymm6",},
+{{0x62, 0xf1, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 48 6f f5    \tvmovdqu32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 6f f5    \tvmovdqu64 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7f 48 6f f5    \tvmovdqu8 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 ff 48 6f f5    \tvmovdqu16 %zmm5,%zmm6",},
+{{0x0f, 0x78, 0xc3, }, 3, 0, "", "",
+"0f 78 c3             \tvmread %eax,%ebx",},
+{{0x62, 0xf1, 0x7c, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 7c 48 78 f5    \tvcvttps2udq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 78 f5    \tvcvttpd2udq %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7f, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 7f 08 78 c6    \tvcvttsd2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7e, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 7e 08 78 c6    \tvcvttss2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 78 f5    \tvcvttps2uqq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 78 f5    \tvcvttpd2uqq %zmm5,%zmm6",},
+{{0x0f, 0x79, 0xd8, }, 3, 0, "", "",
+"0f 79 d8             \tvmwrite %eax,%ebx",},
+{{0x62, 0xf1, 0x7c, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 7c 48 79 f5    \tvcvtps2udq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 79 f5    \tvcvtpd2udq %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7f, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 7f 08 79 c6    \tvcvtsd2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7e, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 7e 08 79 c6    \tvcvtss2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 79 f5    \tvcvtps2uqq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 79 f5    \tvcvtpd2uqq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7e, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 4f 7a f5    \tvcvtudq2pd %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 7a f5    \tvcvtuqq2pd %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7f 48 7a f5    \tvcvtudq2ps %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 ff 4f 7a f5    \tvcvtuqq2ps %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 7a f5    \tvcvttps2qq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 7a f5    \tvcvttpd2qq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 57 08 7b f0    \tvcvtusi2sd %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 56 08 7b f0    \tvcvtusi2ss %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 7b f5    \tvcvtps2qq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 7b f5    \tvcvtpd2qq %zmm5,%zmm6",},
+{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "",
+"0f 7f c4             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x7f, 0xee, }, 4, 0, "", "",
+"c5 fd 7f ee          \tvmovdqa %ymm5,%ymm6",},
+{{0x62, 0xf1, 0x7d, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7d 48 7f ee    \tvmovdqa32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 fd 48 7f ee    \tvmovdqa64 %zmm5,%zmm6",},
+{{0xc5, 0xfe, 0x7f, 0xee, }, 4, 0, "", "",
+"c5 fe 7f ee          \tvmovdqu %ymm5,%ymm6",},
+{{0x62, 0xf1, 0x7e, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7e 48 7f ee    \tvmovdqu32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 fe 48 7f ee    \tvmovdqu64 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7f 48 7f ee    \tvmovdqu8 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 ff 48 7f ee    \tvmovdqu16 %zmm5,%zmm6",},
+{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "",
+"0f db d1             \tpand   %mm1,%mm2",},
+{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "",
+"66 0f db d1          \tpand   %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "",
+"c5 cd db d4          \tvpand  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xdb, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 db f4    \tvpandd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xdb, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 db f4    \tvpandq %zmm4,%zmm5,%zmm6",},
+{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "",
+"0f df d1             \tpandn  %mm1,%mm2",},
+{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "",
+"66 0f df d1          \tpandn  %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "",
+"c5 cd df d4          \tvpandn %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xdf, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 df f4    \tvpandnd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xdf, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 df f4    \tvpandnq %zmm4,%zmm5,%zmm6",},
+{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 f9 e6 d1          \tvcvttpd2dq %xmm1,%xmm2",},
+{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "",
+"c5 fa e6 f5          \tvcvtdq2pd %xmm5,%xmm6",},
+{{0x62, 0xf1, 0x7e, 0x4f, 0xe6, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 4f e6 f5    \tvcvtdq2pd %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfe, 0x48, 0xe6, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 e6 f5    \tvcvtqq2pd %zmm5,%zmm6",},
+{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 fb e6 d1          \tvcvtpd2dq %xmm1,%xmm2",},
+{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "",
+"0f eb f4             \tpor    %mm4,%mm6",},
+{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "",
+"c5 cd eb d4          \tvpor   %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xeb, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 eb f4    \tvpord  %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xeb, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 eb f4    \tvporq  %zmm4,%zmm5,%zmm6",},
+{{0x0f, 0xef, 0xf4, }, 3, 0, "", "",
+"0f ef f4             \tpxor   %mm4,%mm6",},
+{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "",
+"c5 cd ef d4          \tvpxor  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xef, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 ef f4    \tvpxord %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xef, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 ef f4    \tvpxorq %zmm4,%zmm5,%zmm6",},
+{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "",
+"66 0f 38 10 c1       \tpblendvb %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x10, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 10 f4    \tvpsrlvw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x10, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 10 ee    \tvpmovuswb %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x11, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 11 ee    \tvpmovusdb %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x11, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 11 f4    \tvpsravw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x12, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 12 ee    \tvpmovusqb %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x12, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 12 f4    \tvpsllvw %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0xf2, 0x7d, 0x4f, 0x13, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 4f 13 f5    \tvcvtph2ps %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x13, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 13 ee    \tvpmovusdw %zmm5,%ymm6{%k7}",},
+{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "",
+"66 0f 38 14 c1       \tblendvps %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x14, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 14 ee    \tvpmovusqw %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0x55, 0x48, 0x14, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 14 f4    \tvprorvd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x14, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 14 f4    \tvprorvq %zmm4,%zmm5,%zmm6",},
+{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "",
+"66 0f 38 15 c1       \tblendvpd %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x15, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 15 ee    \tvpmovusqd %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x55, 0x48, 0x15, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 15 f4    \tvprolvd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x15, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 15 f4    \tvprolvq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 16 d4       \tvpermps %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x4d, 0x2f, 0x16, 0xd4, }, 6, 0, "", "",
+"62 f2 4d 2f 16 d4    \tvpermps %ymm4,%ymm6,%ymm2{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x2f, 0x16, 0xd4, }, 6, 0, "", "",
+"62 f2 cd 2f 16 d4    \tvpermpd %ymm4,%ymm6,%ymm2{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 19 f4       \tvbroadcastsd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x19, 0xf7, }, 6, 0, "", "",
+"62 f2 7d 48 19 f7    \tvbroadcastf32x2 %xmm7,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 1a 21       \tvbroadcastf128 (%ecx),%ymm4",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x1a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 1a 31    \tvbroadcastf32x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 1a 31    \tvbroadcastf64x2 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x1b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 1b 31    \tvbroadcastf32x8 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 1b 31    \tvbroadcastf64x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1f, 0xf4, }, 6, 0, "", "",
+"62 f2 fd 48 1f f4    \tvpabsq %zmm4,%zmm6",},
+{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "",
+"c4 e2 79 20 ec       \tvpmovsxbw %xmm4,%xmm5",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x20, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 20 ee    \tvpmovswb %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 21 f4       \tvpmovsxbd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x21, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 21 ee    \tvpmovsdb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 22 e4       \tvpmovsxbq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x22, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 22 ee    \tvpmovsqb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 23 e4       \tvpmovsxwd %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x23, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 23 ee    \tvpmovsdw %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 24 f4       \tvpmovsxwq %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x24, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 24 ee    \tvpmovsqw %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 25 e4       \tvpmovsxdq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x25, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 25 ee    \tvpmovsqd %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x4d, 0x48, 0x26, 0xed, }, 6, 0, "", "",
+"62 f2 4d 48 26 ed    \tvptestmb %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0xcd, 0x48, 0x26, 0xed, }, 6, 0, "", "",
+"62 f2 cd 48 26 ed    \tvptestmw %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0x56, 0x48, 0x26, 0xec, }, 6, 0, "", "",
+"62 f2 56 48 26 ec    \tvptestnmb %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0xd6, 0x48, 0x26, 0xec, }, 6, 0, "", "",
+"62 f2 d6 48 26 ec    \tvptestnmw %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0x4d, 0x48, 0x27, 0xed, }, 6, 0, "", "",
+"62 f2 4d 48 27 ed    \tvptestmd %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0xcd, 0x48, 0x27, 0xed, }, 6, 0, "", "",
+"62 f2 cd 48 27 ed    \tvptestmq %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0x56, 0x48, 0x27, 0xec, }, 6, 0, "", "",
+"62 f2 56 48 27 ec    \tvptestnmd %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0xd6, 0x48, 0x27, 0xec, }, 6, 0, "", "",
+"62 f2 d6 48 27 ec    \tvptestnmq %zmm4,%zmm5,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 28 d4       \tvpmuldq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x28, 0xf5, }, 6, 0, "", "",
+"62 f2 7e 48 28 f5    \tvpmovm2b %k5,%zmm6",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x28, 0xf5, }, 6, 0, "", "",
+"62 f2 fe 48 28 f5    \tvpmovm2w %k5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 29 d4       \tvpcmpeqq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x29, 0xee, }, 6, 0, "", "",
+"62 f2 7e 48 29 ee    \tvpmovb2m %zmm6,%k5",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x29, 0xee, }, 6, 0, "", "",
+"62 f2 fe 48 29 ee    \tvpmovw2m %zmm6,%k5",},
+{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 2a 21       \tvmovntdqa (%ecx),%ymm4",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x2a, 0xce, }, 6, 0, "", "",
+"62 f2 fe 48 2a ce    \tvpbroadcastmb2q %k6,%zmm1",},
+{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2c 31       \tvmaskmovps (%ecx),%ymm4,%ymm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x2c, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 2c f4    \tvscalefps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x2c, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 2c f4    \tvscalefpd %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2d 31       \tvmaskmovpd (%ecx),%ymm4,%ymm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 2d f4    \tvscalefss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 2d f4    \tvscalefsd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 30 e4       \tvpmovzxbw %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x30, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 30 ee    \tvpmovwb %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 31 f4       \tvpmovzxbd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x31, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 31 ee    \tvpmovdb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 32 e4       \tvpmovzxbq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x32, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 32 ee    \tvpmovqb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 33 e4       \tvpmovzxwd %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x33, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 33 ee    \tvpmovdw %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 34 f4       \tvpmovzxwq %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x34, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 34 ee    \tvpmovqw %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 35 e4       \tvpmovzxdq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x35, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 35 ee    \tvpmovqd %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 36 d4       \tvpermd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x4d, 0x2f, 0x36, 0xd4, }, 6, 0, "", "",
+"62 f2 4d 2f 36 d4    \tvpermd %ymm4,%ymm6,%ymm2{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x2f, 0x36, 0xd4, }, 6, 0, "", "",
+"62 f2 cd 2f 36 d4    \tvpermq %ymm4,%ymm6,%ymm2{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 38 d4       \tvpminsb %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x38, 0xf5, }, 6, 0, "", "",
+"62 f2 7e 48 38 f5    \tvpmovm2d %k5,%zmm6",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x38, 0xf5, }, 6, 0, "", "",
+"62 f2 fe 48 38 f5    \tvpmovm2q %k5,%zmm6",},
+{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "",
+"c4 e2 69 39 d9       \tvpminsd %xmm1,%xmm2,%xmm3",},
+{{0x62, 0xf2, 0x55, 0x48, 0x39, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 39 f4    \tvpminsd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x39, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 39 f4    \tvpminsq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x39, 0xee, }, 6, 0, "", "",
+"62 f2 7e 48 39 ee    \tvpmovd2m %zmm6,%k5",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x39, 0xee, }, 6, 0, "", "",
+"62 f2 fe 48 39 ee    \tvpmovq2m %zmm6,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3a d4       \tvpminuw %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x3a, 0xf6, }, 6, 0, "", "",
+"62 f2 7e 48 3a f6    \tvpbroadcastmw2d %k6,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3b d4       \tvpminud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3b, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3b f4    \tvpminud %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3b, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3b f4    \tvpminuq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3d d4       \tvpmaxsd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3d f4    \tvpmaxsd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3d f4    \tvpmaxsq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3f d4       \tvpmaxud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3f f4    \tvpmaxud %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3f f4    \tvpmaxuq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 40 d4       \tvpmulld %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x40, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 40 f4    \tvpmulld %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x40, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 40 f4    \tvpmullq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x42, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 42 f5    \tvgetexpps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x42, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 42 f5    \tvgetexppd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x43, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 43 f4    \tvgetexpss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xe5, 0x0f, 0x43, 0xe2, }, 6, 0, "", "",
+"62 f2 e5 0f 43 e2    \tvgetexpsd %xmm2,%xmm3,%xmm4{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x44, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 44 f5    \tvplzcntd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x44, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 44 f5    \tvplzcntq %zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 46 d4       \tvpsravd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x46, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 46 f4    \tvpsravd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x46, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 46 f4    \tvpsravq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x4c, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 4c f5    \tvrcp14ps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x4c, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 4c f5    \tvrcp14pd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 4d f4    \tvrcp14ss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 4d f4    \tvrcp14sd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x4e, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 4e f5    \tvrsqrt14ps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x4e, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 4e f5    \tvrsqrt14pd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 4f f4    \tvrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 4f f4    \tvrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "",
+"c4 e2 79 59 f4       \tvpbroadcastq %xmm4,%xmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x59, 0xf7, }, 6, 0, "", "",
+"62 f2 7d 48 59 f7    \tvbroadcasti32x2 %xmm7,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 5a 21       \tvbroadcasti128 (%ecx),%ymm4",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x5a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 5a 31    \tvbroadcasti32x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x5a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 5a 31    \tvbroadcasti64x2 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x5b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 5b 31    \tvbroadcasti32x8 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x5b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 5b 31    \tvbroadcasti64x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x64, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 64 f4    \tvpblendmd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x64, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 64 f4    \tvpblendmq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x65, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 65 f4    \tvblendmps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x65, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 65 f4    \tvblendmpd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x66, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 66 f4    \tvpblendmb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x66, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 66 f4    \tvpblendmw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x75, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 75 f4    \tvpermi2b %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x75, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 75 f4    \tvpermi2w %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x76, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 76 f4    \tvpermi2d %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x76, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 76 f4    \tvpermi2q %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x77, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 77 f4    \tvpermi2ps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x77, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 77 f4    \tvpermi2pd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7a, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7a d8    \tvpbroadcastb %eax,%xmm3",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7b, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7b d8    \tvpbroadcastw %eax,%xmm3",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7c, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7c d8    \tvpbroadcastd %eax,%xmm3",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7d f4    \tvpermt2b %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7d f4    \tvpermt2w %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7e, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7e f4    \tvpermt2d %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7e, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7e f4    \tvpermt2q %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7f f4    \tvpermt2ps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7f f4    \tvpermt2pd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x83, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 83 f4    \tvpmultishiftqb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x88, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 88 31    \tvexpandps (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x88, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 88 31    \tvexpandpd (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x89, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 89 31    \tvpexpandd (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x89, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 89 31    \tvpexpandq (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x8a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 8a 31    \tvcompressps %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x8a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 8a 31    \tvcompresspd %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x8b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 8b 31    \tvpcompressd %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x8b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 8b 31    \tvpcompressq %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0x55, 0x48, 0x8d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 8d f4    \tvpermb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x8d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 8d f4    \tvpermw %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "",
+"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%ebp,%xmm7,2),%xmm1",},
+{{0x62, 0xf2, 0x7d, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 90 b4 fd 7b 00 00 00 \tvpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 90 b4 fd 7b 00 00 00 \tvpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}",},
+{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0x62, 0xf2, 0x7d, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 91 b4 fd 7b 00 00 00 \tvpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 91 b4 fd 7b 00 00 00 \tvpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a0 b4 fd 7b 00 00 00 \tvpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a0 b4 fd 7b 00 00 00 \tvpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a1 b4 fd 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x29, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 29 a1 b4 fd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a2 b4 fd 7b 00 00 00 \tvscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a2 b4 fd 7b 00 00 00 \tvscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a3 b4 fd 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a3 b4 fd 7b 00 00 00 \tvscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0xb4, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 b4 f4    \tvpmadd52luq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0xb5, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 b5 f4    \tvpmadd52huq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xc4, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 c4 f5    \tvpconflictd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xc4, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 c4 f5    \tvpconflictq %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xc8, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 c8 fe    \tvexp2ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xc8, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 c8 fe    \tvexp2pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xca, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 ca fe    \tvrcp28ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xca, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 ca fe    \tvrcp28pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x4d, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "",
+"62 f2 4d 0f cb fd    \tvrcp28ss %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "",
+"62 f2 cd 0f cb fd    \tvrcp28sd %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xcc, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 cc fe    \tvrsqrt28ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xcc, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 cc fe    \tvrsqrt28pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x4d, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "",
+"62 f2 4d 0f cd fd    \tvrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "",
+"62 f2 cd 0f cd fd    \tvrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 03 fd 12 \tvalignd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 03 fd 12 \tvalignq $0x12,%zmm5,%zmm6,%zmm7",},
+{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 08 d6 05    \tvroundps $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x08, 0xf5, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 08 f5 12 \tvrndscaleps $0x12,%zmm5,%zmm6",},
+{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 09 d6 05    \tvroundpd $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x09, 0xf5, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 09 f5 12 \tvrndscalepd $0x12,%zmm5,%zmm6",},
+{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0a d4 05    \tvroundss $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0xf3, 0x55, 0x0f, 0x0a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 0f 0a f4 12 \tvrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0b d4 05    \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0xf3, 0xd5, 0x0f, 0x0b, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 0f 0b f4 12 \tvrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 18 f4 05    \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0xf3, 0x55, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 4f 18 f4 12 \tvinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf3, 0xd5, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 4f 18 f4 12 \tvinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 19 e4 05    \tvextractf128 $0x5,%ymm4,%xmm4",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 19 ee 12 \tvextractf32x4 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 19 ee 12 \tvextractf64x2 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 4f 1a fd 12 \tvinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 4f 1a fd 12 \tvinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 1b f7 12 \tvextractf32x8 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 1b f7 12 \tvextractf64x4 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0x45, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 1e ee 12 \tvpcmpud $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 1e ee 12 \tvpcmpuq $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x45, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 1f ee 12 \tvpcmpd $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 1f ee 12 \tvpcmpq $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 23 fd 12 \tvshuff32x4 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 23 fd 12 \tvshuff64x2 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 25 fd 12 \tvpternlogd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 25 fd 12 \tvpternlogq $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 26 fe 12 \tvgetmantps $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 26 fe 12 \tvgetmantpd $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 0f 27 fd 12 \tvgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 0f 27 fd 12 \tvgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 38 f4 05    \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0xf3, 0x55, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 4f 38 f4 12 \tvinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf3, 0xd5, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 4f 38 f4 12 \tvinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 39 e6 05    \tvextracti128 $0x5,%ymm4,%xmm6",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 39 ee 12 \tvextracti32x4 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 39 ee 12 \tvextracti64x2 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 4f 3a fd 12 \tvinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 4f 3a fd 12 \tvinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 3b f7 12 \tvextracti32x8 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 3b f7 12 \tvextracti64x4 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0x45, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 3e ee 12 \tvpcmpub $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 3e ee 12 \tvpcmpuw $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x45, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 3f ee 12 \tvpcmpb $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 3f ee 12 \tvpcmpw $0x12,%zmm6,%zmm7,%k5",},
+{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 4d 42 d4 05    \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 43 fd 12 \tvshufi32x4 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 43 fd 12 \tvshufi64x2 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 50 fd 12 \tvrangeps $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 50 fd 12 \tvrangepd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 08 51 fd 12 \tvrangess $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0xcd, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 08 51 fd 12 \tvrangesd $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 54 fd 12 \tvfixupimmps $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 54 fd 12 \tvfixupimmpd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 0f 55 fd 12 \tvfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 0f 55 fd 12 \tvfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 56 fe 12 \tvreduceps $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 56 fe 12 \tvreducepd $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 08 57 fd 12 \tvreducess $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0xcd, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 08 57 fd 12 \tvreducesd $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 66 ef 12 \tvfpclassps $0x12,%zmm7,%k5",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 66 ef 12 \tvfpclasspd $0x12,%zmm7,%k5",},
+{{0x62, 0xf3, 0x7d, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 7d 08 67 ef 12 \tvfpclassss $0x12,%xmm7,%k5",},
+{{0x62, 0xf3, 0xfd, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 fd 08 67 ef 12 \tvfpclasssd $0x12,%xmm7,%k5",},
+{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "",
+"62 f1 4d 48 72 c5 12 \tvprord $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "",
+"62 f1 cd 48 72 c5 12 \tvprorq $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 f1 4d 48 72 cd 12 \tvprold $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 f1 cd 48 72 cd 12 \tvprolq $0x12,%zmm5,%zmm6",},
+{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "",
+"0f 72 e6 02          \tpsrad  $0x2,%mm6",},
+{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "",
+"c5 ed 72 e6 05       \tvpsrad $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x6d, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "",
+"62 f1 6d 48 72 e6 05 \tvpsrad $0x5,%zmm6,%zmm2",},
+{{0x62, 0xf1, 0xed, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "",
+"62 f1 ed 48 72 e6 05 \tvpsraq $0x5,%zmm6,%zmm2",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x4f, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 4f 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xd5, 0xcf, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 cf 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6{%k7}{z}",},
+{{0x62, 0xf1, 0xd5, 0x18, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 18 58 f4    \tvaddpd {rn-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 58 58 f4    \tvaddpd {ru-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x38, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 38 58 f4    \tvaddpd {rd-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x78, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 78 58 f4    \tvaddpd {rz-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x31, }, 6, 0, "", "",
+"62 f1 d5 48 58 31    \tvaddpd (%ecx),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xb4, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "",
+"62 f1 d5 48 58 b4 c8 23 01 00 00 \tvaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x31, }, 6, 0, "", "",
+"62 f1 d5 58 58 31    \tvaddpd (%ecx){1to8},%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 f1 d5 48 58 72 7f \tvaddpd 0x1fc0(%edx),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 f1 d5 58 58 72 7f \tvaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6",},
+{{0x62, 0xf1, 0x4c, 0x58, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "",
+"62 f1 4c 58 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5",},
+{{0x62, 0xf1, 0xe7, 0x0f, 0xc2, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "",
+"62 f1 e7 0f c2 ac c8 23 01 00 00 01 \tvcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}",},
+{{0x62, 0xf1, 0xd7, 0x1f, 0xc2, 0xec, 0x02, }, 7, 0, "", "",
+"62 f1 d7 1f c2 ec 02 \tvcmplesd {sae},%xmm4,%xmm5,%k5{%k7}",},
+{{0x62, 0xf3, 0x5d, 0x0f, 0x27, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "",
+"62 f3 5d 0f 27 ac c8 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}",},
 {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "",
 "f3 0f 1b 00          \tbndmk  (%eax),%bnd0",},
 {{0xf3, 0x0f, 0x1b, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
@@ -309,19 +1319,19 @@
 {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%eax,%ecx,1)",},
 {{0xf2, 0xe8, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "call", "unconditional",
-"f2 e8 fc ff ff ff    \tbnd call 3c3 <main+0x3c3>",},
+"f2 e8 fc ff ff ff    \tbnd call fce <main+0xfce>",},
 {{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect",
 "f2 ff 10             \tbnd call *(%eax)",},
 {{0xf2, 0xc3, }, 2, 0, "ret", "indirect",
 "f2 c3                \tbnd ret ",},
 {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional",
-"f2 e9 fc ff ff ff    \tbnd jmp 3ce <main+0x3ce>",},
+"f2 e9 fc ff ff ff    \tbnd jmp fd9 <main+0xfd9>",},
 {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional",
-"f2 e9 fc ff ff ff    \tbnd jmp 3d4 <main+0x3d4>",},
+"f2 e9 fc ff ff ff    \tbnd jmp fdf <main+0xfdf>",},
 {{0xf2, 0xff, 0x21, }, 3, 0, "jmp", "indirect",
 "f2 ff 21             \tbnd jmp *(%ecx)",},
 {{0xf2, 0x0f, 0x85, 0xfc, 0xff, 0xff, 0xff, }, 7, 0xfffffffc, "jcc", "conditional",
-"f2 0f 85 fc ff ff ff \tbnd jne 3de <main+0x3de>",},
+"f2 0f 85 fc ff ff ff \tbnd jne fe9 <main+0xfe9>",},
 {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
 "0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
 {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
index 4fe7cce179c4..9c8c61e06d5a 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -6,6 +6,938 @@
 
 {{0x0f, 0x31, }, 2, 0, "", "",
 "0f 31                \trdtsc  ",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x48, 0x0f, 0x41, 0xd8, }, 4, 0, "", "",
+"48 0f 41 d8          \tcmovno %rax,%rbx",},
+{{0x48, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"48 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%rcx",},
+{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%cx",},
+{{0x48, 0x0f, 0x44, 0xd8, }, 4, 0, "", "",
+"48 0f 44 d8          \tcmove  %rax,%rbx",},
+{{0x48, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"48 0f 44 88 78 56 34 12 \tcmove  0x12345678(%rax),%rcx",},
+{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 44 88 78 56 34 12 \tcmove  0x12345678(%rax),%cx",},
+{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 90 80 78 56 34 12 \tseto   0x12345678(%rax)",},
+{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 91 80 78 56 34 12 \tsetno  0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 98 80 78 56 34 12 \tsets   0x12345678(%rax)",},
+{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 99 80 78 56 34 12 \tsetns  0x12345678(%rax)",},
+{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cc 41 ef          \tkandw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 41 ef       \tkandq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cd 41 ef          \tkandb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 41 ef       \tkandd  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cc 42 ef          \tkandnw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 42 ef       \tkandnq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cd 42 ef          \tkandnb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 42 ef       \tkandnd %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f8 44 f7          \tknotw  %k7,%k6",},
+{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f8 44 f7       \tknotq  %k7,%k6",},
+{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f9 44 f7          \tknotb  %k7,%k6",},
+{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f9 44 f7       \tknotd  %k7,%k6",},
+{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cc 45 ef          \tkorw   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 45 ef       \tkorq   %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cd 45 ef          \tkorb   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 45 ef       \tkord   %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cc 46 ef          \tkxnorw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 46 ef       \tkxnorq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cd 46 ef          \tkxnorb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 46 ef       \tkxnord %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cc 47 ef          \tkxorw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 47 ef       \tkxorq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cd 47 ef          \tkxorb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 47 ef       \tkxord  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cc 4a ef          \tkaddw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4a ef       \tkaddq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cd 4a ef          \tkaddb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 4a ef       \tkaddd  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cd 4b ef          \tkunpckbw %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cc 4b ef          \tkunpckwd %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4b ef       \tkunpckdq %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f8 90 ee          \tkmovw  %k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f8 90 29          \tkmovw  (%rcx),%k5",},
+{{0xc4, 0xa1, 0x78, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 78 90 ac f0 23 01 00 00 \tkmovw  0x123(%rax,%r14,8),%k5",},
+{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f8 91 29          \tkmovw  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0x78, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 78 91 ac f0 23 01 00 00 \tkmovw  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f8 92 e8          \tkmovw  %eax,%k5",},
+{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f8 92 ed          \tkmovw  %ebp,%k5",},
+{{0xc4, 0xc1, 0x78, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 78 92 ed       \tkmovw  %r13d,%k5",},
+{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f8 93 c5          \tkmovw  %k5,%eax",},
+{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f8 93 ed          \tkmovw  %k5,%ebp",},
+{{0xc5, 0x78, 0x93, 0xed, }, 4, 0, "", "",
+"c5 78 93 ed          \tkmovw  %k5,%r13d",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 90 ee       \tkmovq  %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 90 29       \tkmovq  (%rcx),%k5",},
+{{0xc4, 0xa1, 0xf8, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f8 90 ac f0 23 01 00 00 \tkmovq  0x123(%rax,%r14,8),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 91 29       \tkmovq  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0xf8, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f8 91 ac f0 23 01 00 00 \tkmovq  %k5,0x123(%rax,%r14,8)",},
+{{0xc4, 0xe1, 0xfb, 0x92, 0xe8, }, 5, 0, "", "",
+"c4 e1 fb 92 e8       \tkmovq  %rax,%k5",},
+{{0xc4, 0xe1, 0xfb, 0x92, 0xed, }, 5, 0, "", "",
+"c4 e1 fb 92 ed       \tkmovq  %rbp,%k5",},
+{{0xc4, 0xc1, 0xfb, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 fb 92 ed       \tkmovq  %r13,%k5",},
+{{0xc4, 0xe1, 0xfb, 0x93, 0xc5, }, 5, 0, "", "",
+"c4 e1 fb 93 c5       \tkmovq  %k5,%rax",},
+{{0xc4, 0xe1, 0xfb, 0x93, 0xed, }, 5, 0, "", "",
+"c4 e1 fb 93 ed       \tkmovq  %k5,%rbp",},
+{{0xc4, 0x61, 0xfb, 0x93, 0xed, }, 5, 0, "", "",
+"c4 61 fb 93 ed       \tkmovq  %k5,%r13",},
+{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f9 90 ee          \tkmovb  %k6,%k5",},
+{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f9 90 29          \tkmovb  (%rcx),%k5",},
+{{0xc4, 0xa1, 0x79, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 79 90 ac f0 23 01 00 00 \tkmovb  0x123(%rax,%r14,8),%k5",},
+{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f9 91 29          \tkmovb  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0x79, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 79 91 ac f0 23 01 00 00 \tkmovb  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f9 92 e8          \tkmovb  %eax,%k5",},
+{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f9 92 ed          \tkmovb  %ebp,%k5",},
+{{0xc4, 0xc1, 0x79, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 79 92 ed       \tkmovb  %r13d,%k5",},
+{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f9 93 c5          \tkmovb  %k5,%eax",},
+{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f9 93 ed          \tkmovb  %k5,%ebp",},
+{{0xc5, 0x79, 0x93, 0xed, }, 4, 0, "", "",
+"c5 79 93 ed          \tkmovb  %k5,%r13d",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 90 ee       \tkmovd  %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 90 29       \tkmovd  (%rcx),%k5",},
+{{0xc4, 0xa1, 0xf9, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f9 90 ac f0 23 01 00 00 \tkmovd  0x123(%rax,%r14,8),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 91 29       \tkmovd  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0xf9, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f9 91 ac f0 23 01 00 00 \tkmovd  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 fb 92 e8          \tkmovd  %eax,%k5",},
+{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "",
+"c5 fb 92 ed          \tkmovd  %ebp,%k5",},
+{{0xc4, 0xc1, 0x7b, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 7b 92 ed       \tkmovd  %r13d,%k5",},
+{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 fb 93 c5          \tkmovd  %k5,%eax",},
+{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "",
+"c5 fb 93 ed          \tkmovd  %k5,%ebp",},
+{{0xc5, 0x7b, 0x93, 0xed, }, 4, 0, "", "",
+"c5 7b 93 ed          \tkmovd  %k5,%r13d",},
+{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f8 98 ee          \tkortestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 98 ee       \tkortestq %k6,%k5",},
+{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f9 98 ee          \tkortestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 98 ee       \tkortestd %k6,%k5",},
+{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f8 99 ee          \tktestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 99 ee       \tktestq %k6,%k5",},
+{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f9 99 ee          \tktestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 99 ee       \tktestd %k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 30 ee 12    \tkshiftrw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 31 ee 5b    \tkshiftrq $0x5b,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 32 ee 12    \tkshiftlw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 33 ee 5b    \tkshiftlq $0x5b,%k6,%k5",},
+{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f8 5b f5          \tvcvtdq2ps %xmm5,%xmm6",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 5b f5    \tvcvtqq2ps %zmm29,%ymm6{%k7}",},
+{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f9 5b f5          \tvcvtps2dq %xmm5,%xmm6",},
+{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 fa 5b f5          \tvcvttps2dq %xmm5,%xmm6",},
+{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "",
+"0f 6f e0             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fd 6f f4          \tvmovdqa %ymm4,%ymm6",},
+{{0x62, 0x01, 0x7d, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 7d 48 6f d1    \tvmovdqa32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfd, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 fd 48 6f d1    \tvmovdqa64 %zmm25,%zmm26",},
+{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fe 6f f4          \tvmovdqu %ymm4,%ymm6",},
+{{0x62, 0x01, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 01 7e 48 6f f5    \tvmovdqu32 %zmm29,%zmm30",},
+{{0x62, 0x01, 0xfe, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 6f d1    \tvmovdqu64 %zmm25,%zmm26",},
+{{0x62, 0x01, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 01 7f 48 6f f5    \tvmovdqu8 %zmm29,%zmm30",},
+{{0x62, 0x01, 0xff, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 ff 48 6f d1    \tvmovdqu16 %zmm25,%zmm26",},
+{{0x0f, 0x78, 0xc3, }, 3, 0, "", "",
+"0f 78 c3             \tvmread %rax,%rbx",},
+{{0x62, 0x01, 0x7c, 0x48, 0x78, 0xd1, }, 6, 0, "", "",
+"62 01 7c 48 78 d1    \tvcvttps2udq %zmm25,%zmm26",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 78 f5    \tvcvttpd2udq %zmm29,%ymm6{%k7}",},
+{{0x62, 0xf1, 0xff, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 ff 08 78 c6    \tvcvttsd2usi %xmm6,%rax",},
+{{0x62, 0xf1, 0xfe, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 fe 08 78 c6    \tvcvttss2usi %xmm6,%rax",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x78, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 78 d5    \tvcvttps2uqq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 78 f5    \tvcvttpd2uqq %zmm29,%zmm30",},
+{{0x0f, 0x79, 0xd8, }, 3, 0, "", "",
+"0f 79 d8             \tvmwrite %rax,%rbx",},
+{{0x62, 0x01, 0x7c, 0x48, 0x79, 0xd1, }, 6, 0, "", "",
+"62 01 7c 48 79 d1    \tvcvtps2udq %zmm25,%zmm26",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 79 f5    \tvcvtpd2udq %zmm29,%ymm6{%k7}",},
+{{0x62, 0xf1, 0xff, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 ff 08 79 c6    \tvcvtsd2usi %xmm6,%rax",},
+{{0x62, 0xf1, 0xfe, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 fe 08 79 c6    \tvcvtss2usi %xmm6,%rax",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x79, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 79 d5    \tvcvtps2uqq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 79 f5    \tvcvtpd2uqq %zmm29,%zmm30",},
+{{0x62, 0x61, 0x7e, 0x4f, 0x7a, 0xed, }, 6, 0, "", "",
+"62 61 7e 4f 7a ed    \tvcvtudq2pd %ymm5,%zmm29{%k7}",},
+{{0x62, 0x01, 0xfe, 0x48, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 7a d1    \tvcvtuqq2pd %zmm25,%zmm26",},
+{{0x62, 0x01, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 01 7f 48 7a f5    \tvcvtudq2ps %zmm29,%zmm30",},
+{{0x62, 0x01, 0xff, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 ff 4f 7a d1    \tvcvtuqq2ps %zmm25,%ymm26{%k7}",},
+{{0x62, 0x01, 0x7d, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 7d 4f 7a d1    \tvcvttps2qq %ymm25,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 7a f5    \tvcvttpd2qq %zmm29,%zmm30",},
+{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 57 08 7b f0    \tvcvtusi2sd %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 56 08 7b f0    \tvcvtusi2ss %eax,%xmm5,%xmm6",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x7b, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 7b d5    \tvcvtps2qq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 7b f5    \tvcvtpd2qq %zmm29,%zmm30",},
+{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "",
+"0f 7f c4             \tmovq   %mm0,%mm4",},
+{{0xc5, 0x7d, 0x7f, 0xc6, }, 4, 0, "", "",
+"c5 7d 7f c6          \tvmovdqa %ymm8,%ymm6",},
+{{0x62, 0x01, 0x7d, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 7d 48 7f ca    \tvmovdqa32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 fd 48 7f ca    \tvmovdqa64 %zmm25,%zmm26",},
+{{0xc5, 0x7e, 0x7f, 0xc6, }, 4, 0, "", "",
+"c5 7e 7f c6          \tvmovdqu %ymm8,%ymm6",},
+{{0x62, 0x01, 0x7e, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 7e 48 7f ca    \tvmovdqu32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfe, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 fe 48 7f ca    \tvmovdqu64 %zmm25,%zmm26",},
+{{0x62, 0x61, 0x7f, 0x48, 0x7f, 0x31, }, 6, 0, "", "",
+"62 61 7f 48 7f 31    \tvmovdqu8 %zmm30,(%rcx)",},
+{{0x62, 0x01, 0xff, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 ff 48 7f ca    \tvmovdqu16 %zmm25,%zmm26",},
+{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "",
+"0f db d1             \tpand   %mm1,%mm2",},
+{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "",
+"66 0f db d1          \tpand   %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "",
+"c5 cd db d4          \tvpand  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xdb, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 db d0    \tvpandd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xdb, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 db d0    \tvpandq %zmm24,%zmm25,%zmm26",},
+{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "",
+"0f df d1             \tpandn  %mm1,%mm2",},
+{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "",
+"66 0f df d1          \tpandn  %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "",
+"c5 cd df d4          \tvpandn %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xdf, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 df d0    \tvpandnd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xdf, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 df d0    \tvpandnq %zmm24,%zmm25,%zmm26",},
+{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 f9 e6 d1          \tvcvttpd2dq %xmm1,%xmm2",},
+{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "",
+"c5 fa e6 f5          \tvcvtdq2pd %xmm5,%xmm6",},
+{{0x62, 0x61, 0x7e, 0x4f, 0xe6, 0xd5, }, 6, 0, "", "",
+"62 61 7e 4f e6 d5    \tvcvtdq2pd %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfe, 0x48, 0xe6, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 e6 d1    \tvcvtqq2pd %zmm25,%zmm26",},
+{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 fb e6 d1          \tvcvtpd2dq %xmm1,%xmm2",},
+{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "",
+"0f eb f4             \tpor    %mm4,%mm6",},
+{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "",
+"c5 cd eb d4          \tvpor   %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xeb, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 eb d0    \tvpord  %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xeb, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 eb d0    \tvporq  %zmm24,%zmm25,%zmm26",},
+{{0x0f, 0xef, 0xf4, }, 3, 0, "", "",
+"0f ef f4             \tpxor   %mm4,%mm6",},
+{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "",
+"c5 cd ef d4          \tvpxor  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xef, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 ef d0    \tvpxord %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xef, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 ef d0    \tvpxorq %zmm24,%zmm25,%zmm26",},
+{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "",
+"66 0f 38 10 c1       \tpblendvb %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x02, 0x9d, 0x40, 0x10, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 10 eb    \tvpsrlvw %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x10, 0xe6, }, 6, 0, "", "",
+"62 62 7e 4f 10 e6    \tvpmovuswb %zmm28,%ymm6{%k7}",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x11, 0xe6, }, 6, 0, "", "",
+"62 62 7e 4f 11 e6    \tvpmovusdb %zmm28,%xmm6{%k7}",},
+{{0x62, 0x02, 0x9d, 0x40, 0x11, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 11 eb    \tvpsravw %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x12, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 12 de    \tvpmovusqb %zmm27,%xmm6{%k7}",},
+{{0x62, 0x02, 0x9d, 0x40, 0x12, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 12 eb    \tvpsllvw %zmm27,%zmm28,%zmm29",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0x62, 0x7d, 0x4f, 0x13, 0xdd, }, 6, 0, "", "",
+"62 62 7d 4f 13 dd    \tvcvtph2ps %ymm5,%zmm27{%k7}",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x13, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 13 de    \tvpmovusdw %zmm27,%ymm6{%k7}",},
+{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "",
+"66 0f 38 14 c1       \tblendvps %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x14, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 14 de    \tvpmovusqw %zmm27,%xmm6{%k7}",},
+{{0x62, 0x02, 0x1d, 0x40, 0x14, 0xeb, }, 6, 0, "", "",
+"62 02 1d 40 14 eb    \tvprorvd %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x02, 0x9d, 0x40, 0x14, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 14 eb    \tvprorvq %zmm27,%zmm28,%zmm29",},
+{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "",
+"66 0f 38 15 c1       \tblendvpd %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x15, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 15 de    \tvpmovusqd %zmm27,%ymm6{%k7}",},
+{{0x62, 0x02, 0x1d, 0x40, 0x15, 0xeb, }, 6, 0, "", "",
+"62 02 1d 40 15 eb    \tvprolvd %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x02, 0x9d, 0x40, 0x15, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 15 eb    \tvprolvq %zmm27,%zmm28,%zmm29",},
+{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 16 d4       \tvpermps %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x82, 0x2d, 0x27, 0x16, 0xf0, }, 6, 0, "", "",
+"62 82 2d 27 16 f0    \tvpermps %ymm24,%ymm26,%ymm22{%k7}",},
+{{0x62, 0x82, 0xad, 0x27, 0x16, 0xf0, }, 6, 0, "", "",
+"62 82 ad 27 16 f0    \tvpermpd %ymm24,%ymm26,%ymm22{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 19 f4       \tvbroadcastsd %xmm4,%ymm6",},
+{{0x62, 0x02, 0x7d, 0x48, 0x19, 0xd3, }, 6, 0, "", "",
+"62 02 7d 48 19 d3    \tvbroadcastf32x2 %xmm27,%zmm26",},
+{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 1a 21       \tvbroadcastf128 (%rcx),%ymm4",},
+{{0x62, 0x62, 0x7d, 0x48, 0x1a, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 1a 11    \tvbroadcastf32x4 (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x1a, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 1a 11    \tvbroadcastf64x2 (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x1b, 0x19, }, 6, 0, "", "",
+"62 62 7d 48 1b 19    \tvbroadcastf32x8 (%rcx),%zmm27",},
+{{0x62, 0x62, 0xfd, 0x48, 0x1b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 1b 11    \tvbroadcastf64x4 (%rcx),%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x1f, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 1f e3    \tvpabsq %zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "",
+"c4 e2 79 20 ec       \tvpmovsxbw %xmm4,%xmm5",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x20, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 20 de    \tvpmovswb %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 21 f4       \tvpmovsxbd %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x21, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 21 de    \tvpmovsdb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 22 e4       \tvpmovsxbq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x22, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 22 de    \tvpmovsqb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 23 e4       \tvpmovsxwd %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x23, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 23 de    \tvpmovsdw %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 24 f4       \tvpmovsxwq %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x24, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 24 de    \tvpmovsqw %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 25 e4       \tvpmovsxdq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x25, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 25 de    \tvpmovsqd %zmm27,%ymm6{%k7}",},
+{{0x62, 0x92, 0x1d, 0x40, 0x26, 0xeb, }, 6, 0, "", "",
+"62 92 1d 40 26 eb    \tvptestmb %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x9d, 0x40, 0x26, 0xeb, }, 6, 0, "", "",
+"62 92 9d 40 26 eb    \tvptestmw %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x26, 0x40, 0x26, 0xea, }, 6, 0, "", "",
+"62 92 26 40 26 ea    \tvptestnmb %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0xa6, 0x40, 0x26, 0xea, }, 6, 0, "", "",
+"62 92 a6 40 26 ea    \tvptestnmw %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0x1d, 0x40, 0x27, 0xeb, }, 6, 0, "", "",
+"62 92 1d 40 27 eb    \tvptestmd %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x9d, 0x40, 0x27, 0xeb, }, 6, 0, "", "",
+"62 92 9d 40 27 eb    \tvptestmq %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x26, 0x40, 0x27, 0xea, }, 6, 0, "", "",
+"62 92 26 40 27 ea    \tvptestnmd %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0xa6, 0x40, 0x27, 0xea, }, 6, 0, "", "",
+"62 92 a6 40 27 ea    \tvptestnmq %zmm26,%zmm27,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 28 d4       \tvpmuldq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x28, 0xe5, }, 6, 0, "", "",
+"62 62 7e 48 28 e5    \tvpmovm2b %k5,%zmm28",},
+{{0x62, 0x62, 0xfe, 0x48, 0x28, 0xe5, }, 6, 0, "", "",
+"62 62 fe 48 28 e5    \tvpmovm2w %k5,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 29 d4       \tvpcmpeqq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x92, 0x7e, 0x48, 0x29, 0xec, }, 6, 0, "", "",
+"62 92 7e 48 29 ec    \tvpmovb2m %zmm28,%k5",},
+{{0x62, 0x92, 0xfe, 0x48, 0x29, 0xec, }, 6, 0, "", "",
+"62 92 fe 48 29 ec    \tvpmovw2m %zmm28,%k5",},
+{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 2a 21       \tvmovntdqa (%rcx),%ymm4",},
+{{0x62, 0x62, 0xfe, 0x48, 0x2a, 0xf6, }, 6, 0, "", "",
+"62 62 fe 48 2a f6    \tvpbroadcastmb2q %k6,%zmm30",},
+{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2c 31       \tvmaskmovps (%rcx),%ymm4,%ymm6",},
+{{0x62, 0x02, 0x35, 0x40, 0x2c, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 2c d0    \tvscalefps %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x2c, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 2c d0    \tvscalefpd %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2d 31       \tvmaskmovpd (%rcx),%ymm4,%ymm6",},
+{{0x62, 0x02, 0x35, 0x07, 0x2d, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 2d d0    \tvscalefss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x2d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 2d d0    \tvscalefsd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 30 e4       \tvpmovzxbw %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x30, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 30 de    \tvpmovwb %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 31 f4       \tvpmovzxbd %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x31, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 31 de    \tvpmovdb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 32 e4       \tvpmovzxbq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x32, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 32 de    \tvpmovqb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 33 e4       \tvpmovzxwd %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x33, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 33 de    \tvpmovdw %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 34 f4       \tvpmovzxwq %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x34, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 34 de    \tvpmovqw %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 35 e4       \tvpmovzxdq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x35, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 35 de    \tvpmovqd %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 36 d4       \tvpermd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x82, 0x2d, 0x27, 0x36, 0xf0, }, 6, 0, "", "",
+"62 82 2d 27 36 f0    \tvpermd %ymm24,%ymm26,%ymm22{%k7}",},
+{{0x62, 0x82, 0xad, 0x27, 0x36, 0xf0, }, 6, 0, "", "",
+"62 82 ad 27 36 f0    \tvpermq %ymm24,%ymm26,%ymm22{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 38 d4       \tvpminsb %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x38, 0xe5, }, 6, 0, "", "",
+"62 62 7e 48 38 e5    \tvpmovm2d %k5,%zmm28",},
+{{0x62, 0x62, 0xfe, 0x48, 0x38, 0xe5, }, 6, 0, "", "",
+"62 62 fe 48 38 e5    \tvpmovm2q %k5,%zmm28",},
+{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "",
+"c4 e2 69 39 d9       \tvpminsd %xmm1,%xmm2,%xmm3",},
+{{0x62, 0x02, 0x35, 0x40, 0x39, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 39 d0    \tvpminsd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x39, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 39 d0    \tvpminsq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x92, 0x7e, 0x48, 0x39, 0xec, }, 6, 0, "", "",
+"62 92 7e 48 39 ec    \tvpmovd2m %zmm28,%k5",},
+{{0x62, 0x92, 0xfe, 0x48, 0x39, 0xec, }, 6, 0, "", "",
+"62 92 fe 48 39 ec    \tvpmovq2m %zmm28,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3a d4       \tvpminuw %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x3a, 0xe6, }, 6, 0, "", "",
+"62 62 7e 48 3a e6    \tvpbroadcastmw2d %k6,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3b d4       \tvpminud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3b, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3b d0    \tvpminud %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3b, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3b d0    \tvpminuq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3d d4       \tvpmaxsd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3d, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3d d0    \tvpmaxsd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3d d0    \tvpmaxsq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3f d4       \tvpmaxud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3f, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3f d0    \tvpmaxud %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3f, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3f d0    \tvpmaxuq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 40 d4       \tvpmulld %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x40, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 40 d0    \tvpmulld %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x40, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 40 d0    \tvpmullq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0x7d, 0x48, 0x42, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 42 d1    \tvgetexpps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x42, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 42 e3    \tvgetexppd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x43, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 43 d0    \tvgetexpss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0x95, 0x07, 0x43, 0xf4, }, 6, 0, "", "",
+"62 02 95 07 43 f4    \tvgetexpsd %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0x44, 0xe3, }, 6, 0, "", "",
+"62 02 7d 48 44 e3    \tvplzcntd %zmm27,%zmm28",},
+{{0x62, 0x02, 0xfd, 0x48, 0x44, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 44 e3    \tvplzcntq %zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 46 d4       \tvpsravd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x46, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 46 d0    \tvpsravd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x46, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 46 d0    \tvpsravq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0x7d, 0x48, 0x4c, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 4c d1    \tvrcp14ps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x4c, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 4c e3    \tvrcp14pd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x4d, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 4d d0    \tvrcp14ss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x4d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 4d d0    \tvrcp14sd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0x4e, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 4e d1    \tvrsqrt14ps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x4e, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 4e e3    \tvrsqrt14pd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x4f, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 4f d0    \tvrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x4f, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 4f d0    \tvrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "",
+"c4 e2 79 59 f4       \tvpbroadcastq %xmm4,%xmm6",},
+{{0x62, 0x02, 0x7d, 0x48, 0x59, 0xd3, }, 6, 0, "", "",
+"62 02 7d 48 59 d3    \tvbroadcasti32x2 %xmm27,%zmm26",},
+{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 5a 21       \tvbroadcasti128 (%rcx),%ymm4",},
+{{0x62, 0x62, 0x7d, 0x48, 0x5a, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 5a 11    \tvbroadcasti32x4 (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x5a, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 5a 11    \tvbroadcasti64x2 (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x5b, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 5b 21    \tvbroadcasti32x8 (%rcx),%zmm28",},
+{{0x62, 0x62, 0xfd, 0x48, 0x5b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 5b 11    \tvbroadcasti64x4 (%rcx),%zmm26",},
+{{0x62, 0x02, 0x25, 0x40, 0x64, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 64 e2    \tvpblendmd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x64, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 64 e2    \tvpblendmq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x40, 0x65, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 65 d0    \tvblendmps %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xa5, 0x40, 0x65, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 65 e2    \tvblendmpd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x66, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 66 e2    \tvpblendmb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x66, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 66 e2    \tvpblendmw %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x40, 0x75, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 75 d0    \tvpermi2b %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xa5, 0x40, 0x75, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 75 e2    \tvpermi2w %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x76, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 76 e2    \tvpermi2d %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x76, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 76 e2    \tvpermi2q %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x77, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 77 e2    \tvpermi2ps %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x77, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 77 e2    \tvpermi2pd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7a, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7a f0    \tvpbroadcastb %eax,%xmm30",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7b f0    \tvpbroadcastw %eax,%xmm30",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7c, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7c f0    \tvpbroadcastd %eax,%xmm30",},
+{{0x62, 0x62, 0xfd, 0x48, 0x7c, 0xf0, }, 6, 0, "", "",
+"62 62 fd 48 7c f0    \tvpbroadcastq %rax,%zmm30",},
+{{0x62, 0x02, 0x25, 0x40, 0x7d, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7d e2    \tvpermt2b %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7d, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7d e2    \tvpermt2w %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x7e, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7e e2    \tvpermt2d %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7e, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7e e2    \tvpermt2q %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x7f, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7f e2    \tvpermt2ps %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7f, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7f e2    \tvpermt2pd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x83, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 83 e2    \tvpmultishiftqb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x62, 0x7d, 0x48, 0x88, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 88 11    \tvexpandps (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x88, 0x21, }, 6, 0, "", "",
+"62 62 fd 48 88 21    \tvexpandpd (%rcx),%zmm28",},
+{{0x62, 0x62, 0x7d, 0x48, 0x89, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 89 21    \tvpexpandd (%rcx),%zmm28",},
+{{0x62, 0x62, 0xfd, 0x48, 0x89, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 89 11    \tvpexpandq (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x8a, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 8a 21    \tvcompressps %zmm28,(%rcx)",},
+{{0x62, 0x62, 0xfd, 0x48, 0x8a, 0x21, }, 6, 0, "", "",
+"62 62 fd 48 8a 21    \tvcompresspd %zmm28,(%rcx)",},
+{{0x62, 0x62, 0x7d, 0x48, 0x8b, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 8b 21    \tvpcompressd %zmm28,(%rcx)",},
+{{0x62, 0x62, 0xfd, 0x48, 0x8b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 8b 11    \tvpcompressq %zmm26,(%rcx)",},
+{{0x62, 0x02, 0x25, 0x40, 0x8d, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 8d e2    \tvpermb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x8d, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 8d e2    \tvpermw %zmm26,%zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "",
+"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%rbp,%xmm7,2),%xmm1",},
+{{0x62, 0x22, 0x7d, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 90 94 dd 7b 00 00 00 \tvpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 90 94 dd 7b 00 00 00 \tvpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}",},
+{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0x62, 0x22, 0x7d, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 91 94 dd 7b 00 00 00 \tvpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 91 94 dd 7b 00 00 00 \tvpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",},
+{{0x62, 0x22, 0x7d, 0x41, 0xa0, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 a0 a4 ed 7b 00 00 00 \tvpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa0, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a0 94 dd 7b 00 00 00 \tvpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0xb2, 0x7d, 0x41, 0xa1, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 7d 41 a1 b4 ed 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0xb2, 0xfd, 0x21, 0xa1, 0xb4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 fd 21 a1 b4 dd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0x22, 0x7d, 0x41, 0xa2, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 a2 a4 ed 7b 00 00 00 \tvscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa2, 0xa4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a2 a4 dd 7b 00 00 00 \tvscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0xb2, 0x7d, 0x41, 0xa3, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 7d 41 a3 b4 ed 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa3, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a3 a4 ed 7b 00 00 00 \tvscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x02, 0xa5, 0x40, 0xb4, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 b4 e2    \tvpmadd52luq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0xb5, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 b5 e2    \tvpmadd52huq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x7d, 0x48, 0xc4, 0xda, }, 6, 0, "", "",
+"62 02 7d 48 c4 da    \tvpconflictd %zmm26,%zmm27",},
+{{0x62, 0x02, 0xfd, 0x48, 0xc4, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 c4 da    \tvpconflictq %zmm26,%zmm27",},
+{{0x62, 0x02, 0x7d, 0x48, 0xc8, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 c8 f5    \tvexp2ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xc8, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 c8 da    \tvexp2pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x7d, 0x48, 0xca, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 ca f5    \tvrcp28ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xca, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 ca da    \tvrcp28pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x15, 0x07, 0xcb, 0xf4, }, 6, 0, "", "",
+"62 02 15 07 cb f4    \tvrcp28ss %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0xad, 0x07, 0xcb, 0xd9, }, 6, 0, "", "",
+"62 02 ad 07 cb d9    \tvrcp28sd %xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0xcc, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 cc f5    \tvrsqrt28ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xcc, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 cc da    \tvrsqrt28pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x15, 0x07, 0xcd, 0xf4, }, 6, 0, "", "",
+"62 02 15 07 cd f4    \tvrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0xad, 0x07, 0xcd, 0xd9, }, 6, 0, "", "",
+"62 02 ad 07 cd d9    \tvrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x15, 0x40, 0x03, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 03 f4 12 \tvalignd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x03, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 03 d9 12 \tvalignq $0x12,%zmm25,%zmm26,%zmm27",},
+{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 08 d6 05    \tvroundps $0x5,%ymm6,%ymm2",},
+{{0x62, 0x03, 0x7d, 0x48, 0x08, 0xd1, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 08 d1 12 \tvrndscaleps $0x12,%zmm25,%zmm26",},
+{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 09 d6 05    \tvroundpd $0x5,%ymm6,%ymm2",},
+{{0x62, 0x03, 0xfd, 0x48, 0x09, 0xd1, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 09 d1 12 \tvrndscalepd $0x12,%zmm25,%zmm26",},
+{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0a d4 05    \tvroundss $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0x03, 0x35, 0x07, 0x0a, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 07 0a d0 12 \tvrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0b d4 05    \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0x03, 0xb5, 0x07, 0x0b, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 07 0b d0 12 \tvrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 18 f4 05    \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0x03, 0x35, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 47 18 d0 12 \tvinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0x62, 0x03, 0xb5, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 47 18 d0 12 \tvinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 19 e4 05    \tvextractf128 $0x5,%ymm4,%xmm4",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 19 ca 12 \tvextractf32x4 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 19 ca 12 \tvextractf64x2 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0x2d, 0x47, 0x1a, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 47 1a d9 12 \tvinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}",},
+{{0x62, 0x03, 0x95, 0x47, 0x1a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 47 1a f4 12 \tvinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x1b, 0xee, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 1b ee 12 \tvextractf32x8 $0x12,%zmm29,%ymm30{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x1b, 0xd3, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 1b d3 12 \tvextractf64x4 $0x12,%zmm26,%ymm27{%k7}",},
+{{0x62, 0x93, 0x0d, 0x40, 0x1e, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 1e ed 12 \tvpcmpud $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x1e, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 1e ea 12 \tvpcmpuq $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x93, 0x0d, 0x40, 0x1f, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 1f ed 12 \tvpcmpd $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x1f, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 1f ea 12 \tvpcmpq $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x03, 0x15, 0x40, 0x23, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 23 f4 12 \tvshuff32x4 $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x23, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 23 d9 12 \tvshuff64x2 $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x15, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 25 f4 12 \tvpternlogd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x95, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 25 f4 12 \tvpternlogq $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x7d, 0x48, 0x26, 0xda, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 26 da 12 \tvgetmantps $0x12,%zmm26,%zmm27",},
+{{0x62, 0x03, 0xfd, 0x48, 0x26, 0xf5, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 26 f5 12 \tvgetmantpd $0x12,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x07, 0x27, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 07 27 d9 12 \tvgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x95, 0x07, 0x27, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 07 27 f4 12 \tvgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 38 f4 05    \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0x03, 0x35, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 47 38 d0 12 \tvinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0x62, 0x03, 0xb5, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 47 38 d0 12 \tvinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 39 e6 05    \tvextracti128 $0x5,%ymm4,%xmm6",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 39 ca 12 \tvextracti32x4 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 39 ca 12 \tvextracti64x2 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0x15, 0x47, 0x3a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 47 3a f4 12 \tvinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x03, 0xad, 0x47, 0x3a, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 47 3a d9 12 \tvinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x3b, 0xee, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 3b ee 12 \tvextracti32x8 $0x12,%zmm29,%ymm30{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x3b, 0xd3, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 3b d3 12 \tvextracti64x4 $0x12,%zmm26,%ymm27{%k7}",},
+{{0x62, 0x93, 0x0d, 0x40, 0x3e, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 3e ed 12 \tvpcmpub $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x3e, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 3e ea 12 \tvpcmpuw $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x93, 0x0d, 0x40, 0x3f, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 3f ed 12 \tvpcmpb $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x3f, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 3f ea 12 \tvpcmpw $0x12,%zmm26,%zmm27,%k5",},
+{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 4d 42 d4 05    \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",},
+{{0x62, 0x03, 0x2d, 0x40, 0x43, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 40 43 d9 12 \tvshufi32x4 $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x95, 0x40, 0x43, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 43 f4 12 \tvshufi64x2 $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x40, 0x50, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 40 50 d9 12 \tvrangeps $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x95, 0x40, 0x50, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 50 f4 12 \tvrangepd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x00, 0x51, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 00 51 d9 12 \tvrangess $0x12,%xmm25,%xmm26,%xmm27",},
+{{0x62, 0x03, 0x95, 0x00, 0x51, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 00 51 f4 12 \tvrangesd $0x12,%xmm28,%xmm29,%xmm30",},
+{{0x62, 0x03, 0x15, 0x40, 0x54, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 54 f4 12 \tvfixupimmps $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x54, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 54 d9 12 \tvfixupimmpd $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x15, 0x07, 0x55, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 07 55 f4 12 \tvfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x03, 0xad, 0x07, 0x55, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 07 55 d9 12 \tvfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x7d, 0x48, 0x56, 0xda, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 56 da 12 \tvreduceps $0x12,%zmm26,%zmm27",},
+{{0x62, 0x03, 0xfd, 0x48, 0x56, 0xf5, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 56 f5 12 \tvreducepd $0x12,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x00, 0x57, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 00 57 d9 12 \tvreducess $0x12,%xmm25,%xmm26,%xmm27",},
+{{0x62, 0x03, 0x95, 0x00, 0x57, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 00 57 f4 12 \tvreducesd $0x12,%xmm28,%xmm29,%xmm30",},
+{{0x62, 0x93, 0x7d, 0x48, 0x66, 0xeb, 0x12, }, 7, 0, "", "",
+"62 93 7d 48 66 eb 12 \tvfpclassps $0x12,%zmm27,%k5",},
+{{0x62, 0x93, 0xfd, 0x48, 0x66, 0xee, 0x12, }, 7, 0, "", "",
+"62 93 fd 48 66 ee 12 \tvfpclasspd $0x12,%zmm30,%k5",},
+{{0x62, 0x93, 0x7d, 0x08, 0x67, 0xeb, 0x12, }, 7, 0, "", "",
+"62 93 7d 08 67 eb 12 \tvfpclassss $0x12,%xmm27,%k5",},
+{{0x62, 0x93, 0xfd, 0x08, 0x67, 0xee, 0x12, }, 7, 0, "", "",
+"62 93 fd 08 67 ee 12 \tvfpclasssd $0x12,%xmm30,%k5",},
+{{0x62, 0x91, 0x2d, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "",
+"62 91 2d 40 72 c1 12 \tvprord $0x12,%zmm25,%zmm26",},
+{{0x62, 0x91, 0xad, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "",
+"62 91 ad 40 72 c1 12 \tvprorq $0x12,%zmm25,%zmm26",},
+{{0x62, 0x91, 0x0d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 91 0d 40 72 cd 12 \tvprold $0x12,%zmm29,%zmm30",},
+{{0x62, 0x91, 0x8d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 91 8d 40 72 cd 12 \tvprolq $0x12,%zmm29,%zmm30",},
+{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "",
+"0f 72 e6 02          \tpsrad  $0x2,%mm6",},
+{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "",
+"c5 ed 72 e6 05       \tvpsrad $0x5,%ymm6,%ymm2",},
+{{0x62, 0x91, 0x4d, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "",
+"62 91 4d 40 72 e2 05 \tvpsrad $0x5,%zmm26,%zmm22",},
+{{0x62, 0x91, 0xcd, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "",
+"62 91 cd 40 72 e2 05 \tvpsraq $0x5,%zmm26,%zmm22",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x01, 0x95, 0x40, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 40 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x47, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 47 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x01, 0x95, 0xc7, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 c7 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30{%k7}{z}",},
+{{0x62, 0x01, 0x95, 0x10, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 10 58 f4    \tvaddpd {rn-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x50, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 50 58 f4    \tvaddpd {ru-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x30, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 30 58 f4    \tvaddpd {rd-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x70, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 70 58 f4    \tvaddpd {rz-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x40, 0x58, 0x31, }, 6, 0, "", "",
+"62 61 95 40 58 31    \tvaddpd (%rcx),%zmm29,%zmm30",},
+{{0x62, 0x21, 0x95, 0x40, 0x58, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "",
+"62 21 95 40 58 b4 f0 23 01 00 00 \tvaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x50, 0x58, 0x31, }, 6, 0, "", "",
+"62 61 95 50 58 31    \tvaddpd (%rcx){1to8},%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x40, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 61 95 40 58 72 7f \tvaddpd 0x1fc0(%rdx),%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x50, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 61 95 50 58 72 7f \tvaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30",},
+{{0x62, 0xf1, 0x0c, 0x50, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "",
+"62 f1 0c 50 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5",},
+{{0x62, 0xb1, 0x97, 0x07, 0xc2, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "",
+"62 b1 97 07 c2 ac f0 23 01 00 00 01 \tvcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}",},
+{{0x62, 0x91, 0x97, 0x17, 0xc2, 0xec, 0x02, }, 7, 0, "", "",
+"62 91 97 17 c2 ec 02 \tvcmplesd {sae},%xmm28,%xmm29,%k5{%k7}",},
+{{0x62, 0x23, 0x15, 0x07, 0x27, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "",
+"62 23 15 07 27 b4 f0 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}",},
 {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "",
 "f3 0f 1b 00          \tbndmk  (%rax),%bnd0",},
 {{0xf3, 0x41, 0x0f, 0x1b, 0x00, }, 5, 0, "", "",
@@ -325,19 +1257,19 @@
 {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%rax,%rcx,1)",},
 {{0xf2, 0xe8, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "call", "unconditional",
-"f2 e8 00 00 00 00    \tbnd callq 3f6 <main+0x3f6>",},
+"f2 e8 00 00 00 00    \tbnd callq f22 <main+0xf22>",},
 {{0x67, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect",
 "67 f2 ff 10          \tbnd callq *(%eax)",},
 {{0xf2, 0xc3, }, 2, 0, "ret", "indirect",
 "f2 c3                \tbnd retq ",},
 {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional",
-"f2 e9 00 00 00 00    \tbnd jmpq 402 <main+0x402>",},
+"f2 e9 00 00 00 00    \tbnd jmpq f2e <main+0xf2e>",},
 {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional",
-"f2 e9 00 00 00 00    \tbnd jmpq 408 <main+0x408>",},
+"f2 e9 00 00 00 00    \tbnd jmpq f34 <main+0xf34>",},
 {{0x67, 0xf2, 0xff, 0x21, }, 4, 0, "jmp", "indirect",
 "67 f2 ff 21          \tbnd jmpq *(%ecx)",},
 {{0xf2, 0x0f, 0x85, 0x00, 0x00, 0x00, 0x00, }, 7, 0, "jcc", "conditional",
-"f2 0f 85 00 00 00 00 \tbnd jne 413 <main+0x413>",},
+"f2 0f 85 00 00 00 00 \tbnd jne f3f <main+0xf3f>",},
 {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
 "0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
 {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
index 41b1b1c62660..76e0ec379c8b 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -19,8 +19,882 @@ int main(void)
 	/* Following line is a marker for the awk script - do not change */
 	asm volatile("rdtsc"); /* Start here */
 
+	/* Test fix for vcvtph2ps in x86-opcode-map.txt */
+
+	asm volatile("vcvtph2ps %xmm3,%ymm5");
+
 #ifdef __x86_64__
 
+	/* AVX-512: Instructions with the same op codes as Mask Instructions  */
+
+	asm volatile("cmovno %rax,%rbx");
+	asm volatile("cmovno 0x12345678(%rax),%rcx");
+	asm volatile("cmovno 0x12345678(%rax),%cx");
+
+	asm volatile("cmove  %rax,%rbx");
+	asm volatile("cmove 0x12345678(%rax),%rcx");
+	asm volatile("cmove 0x12345678(%rax),%cx");
+
+	asm volatile("seto    0x12345678(%rax)");
+	asm volatile("setno   0x12345678(%rax)");
+	asm volatile("setb    0x12345678(%rax)");
+	asm volatile("setc    0x12345678(%rax)");
+	asm volatile("setnae  0x12345678(%rax)");
+	asm volatile("setae   0x12345678(%rax)");
+	asm volatile("setnb   0x12345678(%rax)");
+	asm volatile("setnc   0x12345678(%rax)");
+	asm volatile("sets    0x12345678(%rax)");
+	asm volatile("setns   0x12345678(%rax)");
+
+	/* AVX-512: Mask Instructions */
+
+	asm volatile("kandw  %k7,%k6,%k5");
+	asm volatile("kandq  %k7,%k6,%k5");
+	asm volatile("kandb  %k7,%k6,%k5");
+	asm volatile("kandd  %k7,%k6,%k5");
+
+	asm volatile("kandnw  %k7,%k6,%k5");
+	asm volatile("kandnq  %k7,%k6,%k5");
+	asm volatile("kandnb  %k7,%k6,%k5");
+	asm volatile("kandnd  %k7,%k6,%k5");
+
+	asm volatile("knotw  %k7,%k6");
+	asm volatile("knotq  %k7,%k6");
+	asm volatile("knotb  %k7,%k6");
+	asm volatile("knotd  %k7,%k6");
+
+	asm volatile("korw  %k7,%k6,%k5");
+	asm volatile("korq  %k7,%k6,%k5");
+	asm volatile("korb  %k7,%k6,%k5");
+	asm volatile("kord  %k7,%k6,%k5");
+
+	asm volatile("kxnorw  %k7,%k6,%k5");
+	asm volatile("kxnorq  %k7,%k6,%k5");
+	asm volatile("kxnorb  %k7,%k6,%k5");
+	asm volatile("kxnord  %k7,%k6,%k5");
+
+	asm volatile("kxorw  %k7,%k6,%k5");
+	asm volatile("kxorq  %k7,%k6,%k5");
+	asm volatile("kxorb  %k7,%k6,%k5");
+	asm volatile("kxord  %k7,%k6,%k5");
+
+	asm volatile("kaddw  %k7,%k6,%k5");
+	asm volatile("kaddq  %k7,%k6,%k5");
+	asm volatile("kaddb  %k7,%k6,%k5");
+	asm volatile("kaddd  %k7,%k6,%k5");
+
+	asm volatile("kunpckbw %k7,%k6,%k5");
+	asm volatile("kunpckwd %k7,%k6,%k5");
+	asm volatile("kunpckdq %k7,%k6,%k5");
+
+	asm volatile("kmovw  %k6,%k5");
+	asm volatile("kmovw  (%rcx),%k5");
+	asm volatile("kmovw  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovw  %k5,(%rcx)");
+	asm volatile("kmovw  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovw  %eax,%k5");
+	asm volatile("kmovw  %ebp,%k5");
+	asm volatile("kmovw  %r13d,%k5");
+	asm volatile("kmovw  %k5,%eax");
+	asm volatile("kmovw  %k5,%ebp");
+	asm volatile("kmovw  %k5,%r13d");
+
+	asm volatile("kmovq  %k6,%k5");
+	asm volatile("kmovq  (%rcx),%k5");
+	asm volatile("kmovq  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovq  %k5,(%rcx)");
+	asm volatile("kmovq  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovq  %rax,%k5");
+	asm volatile("kmovq  %rbp,%k5");
+	asm volatile("kmovq  %r13,%k5");
+	asm volatile("kmovq  %k5,%rax");
+	asm volatile("kmovq  %k5,%rbp");
+	asm volatile("kmovq  %k5,%r13");
+
+	asm volatile("kmovb  %k6,%k5");
+	asm volatile("kmovb  (%rcx),%k5");
+	asm volatile("kmovb  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovb  %k5,(%rcx)");
+	asm volatile("kmovb  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovb  %eax,%k5");
+	asm volatile("kmovb  %ebp,%k5");
+	asm volatile("kmovb  %r13d,%k5");
+	asm volatile("kmovb  %k5,%eax");
+	asm volatile("kmovb  %k5,%ebp");
+	asm volatile("kmovb  %k5,%r13d");
+
+	asm volatile("kmovd  %k6,%k5");
+	asm volatile("kmovd  (%rcx),%k5");
+	asm volatile("kmovd  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovd  %k5,(%rcx)");
+	asm volatile("kmovd  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovd  %eax,%k5");
+	asm volatile("kmovd  %ebp,%k5");
+	asm volatile("kmovd  %r13d,%k5");
+	asm volatile("kmovd  %k5,%eax");
+	asm volatile("kmovd  %k5,%ebp");
+	asm volatile("kmovd %k5,%r13d");
+
+	asm volatile("kortestw %k6,%k5");
+	asm volatile("kortestq %k6,%k5");
+	asm volatile("kortestb %k6,%k5");
+	asm volatile("kortestd %k6,%k5");
+
+	asm volatile("ktestw %k6,%k5");
+	asm volatile("ktestq %k6,%k5");
+	asm volatile("ktestb %k6,%k5");
+	asm volatile("ktestd %k6,%k5");
+
+	asm volatile("kshiftrw $0x12,%k6,%k5");
+	asm volatile("kshiftrq $0x5b,%k6,%k5");
+	asm volatile("kshiftlw $0x12,%k6,%k5");
+	asm volatile("kshiftlq $0x5b,%k6,%k5");
+
+	/* AVX-512: Op code 0f 5b */
+	asm volatile("vcvtdq2ps %xmm5,%xmm6");
+	asm volatile("vcvtqq2ps %zmm29,%ymm6{%k7}");
+	asm volatile("vcvtps2dq %xmm5,%xmm6");
+	asm volatile("vcvttps2dq %xmm5,%xmm6");
+
+	/* AVX-512: Op code 0f 6f */
+
+	asm volatile("movq   %mm0,%mm4");
+	asm volatile("vmovdqa %ymm4,%ymm6");
+	asm volatile("vmovdqa32 %zmm25,%zmm26");
+	asm volatile("vmovdqa64 %zmm25,%zmm26");
+	asm volatile("vmovdqu %ymm4,%ymm6");
+	asm volatile("vmovdqu32 %zmm29,%zmm30");
+	asm volatile("vmovdqu64 %zmm25,%zmm26");
+	asm volatile("vmovdqu8 %zmm29,%zmm30");
+	asm volatile("vmovdqu16 %zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 78 */
+
+	asm volatile("vmread %rax,%rbx");
+	asm volatile("vcvttps2udq %zmm25,%zmm26");
+	asm volatile("vcvttpd2udq %zmm29,%ymm6{%k7}");
+	asm volatile("vcvttsd2usi %xmm6,%rax");
+	asm volatile("vcvttss2usi %xmm6,%rax");
+	asm volatile("vcvttps2uqq %ymm5,%zmm26{%k7}");
+	asm volatile("vcvttpd2uqq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 79 */
+
+	asm volatile("vmwrite %rax,%rbx");
+	asm volatile("vcvtps2udq %zmm25,%zmm26");
+	asm volatile("vcvtpd2udq %zmm29,%ymm6{%k7}");
+	asm volatile("vcvtsd2usi %xmm6,%rax");
+	asm volatile("vcvtss2usi %xmm6,%rax");
+	asm volatile("vcvtps2uqq %ymm5,%zmm26{%k7}");
+	asm volatile("vcvtpd2uqq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 7a */
+
+	asm volatile("vcvtudq2pd %ymm5,%zmm29{%k7}");
+	asm volatile("vcvtuqq2pd %zmm25,%zmm26");
+	asm volatile("vcvtudq2ps %zmm29,%zmm30");
+	asm volatile("vcvtuqq2ps %zmm25,%ymm26{%k7}");
+	asm volatile("vcvttps2qq %ymm25,%zmm26{%k7}");
+	asm volatile("vcvttpd2qq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 7b */
+
+	asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6");
+	asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6");
+	asm volatile("vcvtps2qq %ymm5,%zmm26{%k7}");
+	asm volatile("vcvtpd2qq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 7f */
+
+	asm volatile("movq.s  %mm0,%mm4");
+	asm volatile("vmovdqa %ymm8,%ymm6");
+	asm volatile("vmovdqa32.s %zmm25,%zmm26");
+	asm volatile("vmovdqa64.s %zmm25,%zmm26");
+	asm volatile("vmovdqu %ymm8,%ymm6");
+	asm volatile("vmovdqu32.s %zmm25,%zmm26");
+	asm volatile("vmovdqu64.s %zmm25,%zmm26");
+	asm volatile("vmovdqu8.s %zmm30,(%rcx)");
+	asm volatile("vmovdqu16.s %zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f db */
+
+	asm volatile("pand  %mm1,%mm2");
+	asm volatile("pand  %xmm1,%xmm2");
+	asm volatile("vpand  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpandq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f df */
+
+	asm volatile("pandn  %mm1,%mm2");
+	asm volatile("pandn  %xmm1,%xmm2");
+	asm volatile("vpandn %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandnd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpandnq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f e6 */
+
+	asm volatile("vcvttpd2dq %xmm1,%xmm2");
+	asm volatile("vcvtdq2pd %xmm5,%xmm6");
+	asm volatile("vcvtdq2pd %ymm5,%zmm26{%k7}");
+	asm volatile("vcvtqq2pd %zmm25,%zmm26");
+	asm volatile("vcvtpd2dq %xmm1,%xmm2");
+
+	/* AVX-512: Op code 0f eb */
+
+	asm volatile("por   %mm4,%mm6");
+	asm volatile("vpor   %ymm4,%ymm6,%ymm2");
+	asm volatile("vpord  %zmm24,%zmm25,%zmm26");
+	asm volatile("vporq  %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f ef */
+
+	asm volatile("pxor   %mm4,%mm6");
+	asm volatile("vpxor  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpxord %zmm24,%zmm25,%zmm26");
+	asm volatile("vpxorq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 10 */
+
+	asm volatile("pblendvb %xmm1,%xmm0");
+	asm volatile("vpsrlvw %zmm27,%zmm28,%zmm29");
+	asm volatile("vpmovuswb %zmm28,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 11 */
+
+	asm volatile("vpmovusdb %zmm28,%xmm6{%k7}");
+	asm volatile("vpsravw %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 12 */
+
+	asm volatile("vpmovusqb %zmm27,%xmm6{%k7}");
+	asm volatile("vpsllvw %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 13 */
+
+	asm volatile("vcvtph2ps %xmm3,%ymm5");
+	asm volatile("vcvtph2ps %ymm5,%zmm27{%k7}");
+	asm volatile("vpmovusdw %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 14 */
+
+	asm volatile("blendvps %xmm1,%xmm0");
+	asm volatile("vpmovusqw %zmm27,%xmm6{%k7}");
+	asm volatile("vprorvd %zmm27,%zmm28,%zmm29");
+	asm volatile("vprorvq %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 15 */
+
+	asm volatile("blendvpd %xmm1,%xmm0");
+	asm volatile("vpmovusqd %zmm27,%ymm6{%k7}");
+	asm volatile("vprolvd %zmm27,%zmm28,%zmm29");
+	asm volatile("vprolvq %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 16 */
+
+	asm volatile("vpermps %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermps %ymm24,%ymm26,%ymm22{%k7}");
+	asm volatile("vpermpd %ymm24,%ymm26,%ymm22{%k7}");
+
+	/* AVX-512: Op code 0f 38 19 */
+
+	asm volatile("vbroadcastsd %xmm4,%ymm6");
+	asm volatile("vbroadcastf32x2 %xmm27,%zmm26");
+
+	/* AVX-512: Op code 0f 38 1a */
+
+	asm volatile("vbroadcastf128 (%rcx),%ymm4");
+	asm volatile("vbroadcastf32x4 (%rcx),%zmm26");
+	asm volatile("vbroadcastf64x2 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 1b */
+
+	asm volatile("vbroadcastf32x8 (%rcx),%zmm27");
+	asm volatile("vbroadcastf64x4 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 1f */
+
+	asm volatile("vpabsq %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 20 */
+
+	asm volatile("vpmovsxbw %xmm4,%xmm5");
+	asm volatile("vpmovswb %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 21 */
+
+	asm volatile("vpmovsxbd %xmm4,%ymm6");
+	asm volatile("vpmovsdb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 22 */
+
+	asm volatile("vpmovsxbq %xmm4,%ymm4");
+	asm volatile("vpmovsqb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 23 */
+
+	asm volatile("vpmovsxwd %xmm4,%ymm4");
+	asm volatile("vpmovsdw %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 24 */
+
+	asm volatile("vpmovsxwq %xmm4,%ymm6");
+	asm volatile("vpmovsqw %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 25 */
+
+	asm volatile("vpmovsxdq %xmm4,%ymm4");
+	asm volatile("vpmovsqd %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 26 */
+
+	asm volatile("vptestmb %zmm27,%zmm28,%k5");
+	asm volatile("vptestmw %zmm27,%zmm28,%k5");
+	asm volatile("vptestnmb %zmm26,%zmm27,%k5");
+	asm volatile("vptestnmw %zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 38 27 */
+
+	asm volatile("vptestmd %zmm27,%zmm28,%k5");
+	asm volatile("vptestmq %zmm27,%zmm28,%k5");
+	asm volatile("vptestnmd %zmm26,%zmm27,%k5");
+	asm volatile("vptestnmq %zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 38 28 */
+
+	asm volatile("vpmuldq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2b %k5,%zmm28");
+	asm volatile("vpmovm2w %k5,%zmm28");
+
+	/* AVX-512: Op code 0f 38 29 */
+
+	asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovb2m %zmm28,%k5");
+	asm volatile("vpmovw2m %zmm28,%k5");
+
+	/* AVX-512: Op code 0f 38 2a */
+
+	asm volatile("vmovntdqa (%rcx),%ymm4");
+	asm volatile("vpbroadcastmb2q %k6,%zmm30");
+
+	/* AVX-512: Op code 0f 38 2c */
+
+	asm volatile("vmaskmovps (%rcx),%ymm4,%ymm6");
+	asm volatile("vscalefps %zmm24,%zmm25,%zmm26");
+	asm volatile("vscalefpd %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 2d */
+
+	asm volatile("vmaskmovpd (%rcx),%ymm4,%ymm6");
+	asm volatile("vscalefss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vscalefsd %xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 38 30 */
+
+	asm volatile("vpmovzxbw %xmm4,%ymm4");
+	asm volatile("vpmovwb %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 31 */
+
+	asm volatile("vpmovzxbd %xmm4,%ymm6");
+	asm volatile("vpmovdb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 32 */
+
+	asm volatile("vpmovzxbq %xmm4,%ymm4");
+	asm volatile("vpmovqb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 33 */
+
+	asm volatile("vpmovzxwd %xmm4,%ymm4");
+	asm volatile("vpmovdw %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 34 */
+
+	asm volatile("vpmovzxwq %xmm4,%ymm6");
+	asm volatile("vpmovqw %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 35 */
+
+	asm volatile("vpmovzxdq %xmm4,%ymm4");
+	asm volatile("vpmovqd %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 38 */
+
+	asm volatile("vpermd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermd %ymm24,%ymm26,%ymm22{%k7}");
+	asm volatile("vpermq %ymm24,%ymm26,%ymm22{%k7}");
+
+	/* AVX-512: Op code 0f 38 38 */
+
+	asm volatile("vpminsb %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2d %k5,%zmm28");
+	asm volatile("vpmovm2q %k5,%zmm28");
+
+	/* AVX-512: Op code 0f 38 39 */
+
+	asm volatile("vpminsd %xmm1,%xmm2,%xmm3");
+	asm volatile("vpminsd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpminsq %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmovd2m %zmm28,%k5");
+	asm volatile("vpmovq2m %zmm28,%k5");
+
+	/* AVX-512: Op code 0f 38 3a */
+
+	asm volatile("vpminuw %ymm4,%ymm6,%ymm2");
+	asm volatile("vpbroadcastmw2d %k6,%zmm28");
+
+	/* AVX-512: Op code 0f 38 3b */
+
+	asm volatile("vpminud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpminud %zmm24,%zmm25,%zmm26");
+	asm volatile("vpminuq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 3d */
+
+	asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxsd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmaxsq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 3f */
+
+	asm volatile("vpmaxud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxud %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmaxuq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 42 */
+
+	asm volatile("vpmulld %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmulld %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmullq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 42 */
+
+	asm volatile("vgetexpps %zmm25,%zmm26");
+	asm volatile("vgetexppd %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 43 */
+
+	asm volatile("vgetexpss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vgetexpsd %xmm28,%xmm29,%xmm30{%k7}");
+
+	/* AVX-512: Op code 0f 38 44 */
+
+	asm volatile("vplzcntd %zmm27,%zmm28");
+	asm volatile("vplzcntq %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 46 */
+
+	asm volatile("vpsravd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpsravd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpsravq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 4c */
+
+	asm volatile("vrcp14ps %zmm25,%zmm26");
+	asm volatile("vrcp14pd %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 4d */
+
+	asm volatile("vrcp14ss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vrcp14sd %xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 38 4e */
+
+	asm volatile("vrsqrt14ps %zmm25,%zmm26");
+	asm volatile("vrsqrt14pd %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 4f */
+
+	asm volatile("vrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 38 59 */
+
+	asm volatile("vpbroadcastq %xmm4,%xmm6");
+	asm volatile("vbroadcasti32x2 %xmm27,%zmm26");
+
+	/* AVX-512: Op code 0f 38 5a */
+
+	asm volatile("vbroadcasti128 (%rcx),%ymm4");
+	asm volatile("vbroadcasti32x4 (%rcx),%zmm26");
+	asm volatile("vbroadcasti64x2 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 5b */
+
+	asm volatile("vbroadcasti32x8 (%rcx),%zmm28");
+	asm volatile("vbroadcasti64x4 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 64 */
+
+	asm volatile("vpblendmd %zmm26,%zmm27,%zmm28");
+	asm volatile("vpblendmq %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 65 */
+
+	asm volatile("vblendmps %zmm24,%zmm25,%zmm26");
+	asm volatile("vblendmpd %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 66 */
+
+	asm volatile("vpblendmb %zmm26,%zmm27,%zmm28");
+	asm volatile("vpblendmw %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 75 */
+
+	asm volatile("vpermi2b %zmm24,%zmm25,%zmm26");
+	asm volatile("vpermi2w %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 76 */
+
+	asm volatile("vpermi2d %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermi2q %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 77 */
+
+	asm volatile("vpermi2ps %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermi2pd %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 7a */
+
+	asm volatile("vpbroadcastb %eax,%xmm30");
+
+	/* AVX-512: Op code 0f 38 7b */
+
+	asm volatile("vpbroadcastw %eax,%xmm30");
+
+	/* AVX-512: Op code 0f 38 7c */
+
+	asm volatile("vpbroadcastd %eax,%xmm30");
+	asm volatile("vpbroadcastq %rax,%zmm30");
+
+	/* AVX-512: Op code 0f 38 7d */
+
+	asm volatile("vpermt2b %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermt2w %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 7e */
+
+	asm volatile("vpermt2d %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermt2q %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 7f */
+
+	asm volatile("vpermt2ps %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermt2pd %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 83 */
+
+	asm volatile("vpmultishiftqb %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 88 */
+
+	asm volatile("vexpandps (%rcx),%zmm26");
+	asm volatile("vexpandpd (%rcx),%zmm28");
+
+	/* AVX-512: Op code 0f 38 89 */
+
+	asm volatile("vpexpandd (%rcx),%zmm28");
+	asm volatile("vpexpandq (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 8a */
+
+	asm volatile("vcompressps %zmm28,(%rcx)");
+	asm volatile("vcompresspd %zmm28,(%rcx)");
+
+	/* AVX-512: Op code 0f 38 8b */
+
+	asm volatile("vpcompressd %zmm28,(%rcx)");
+	asm volatile("vpcompressq %zmm26,(%rcx)");
+
+	/* AVX-512: Op code 0f 38 8d */
+
+	asm volatile("vpermb %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermw %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 90 */
+
+	asm volatile("vpgatherdd %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdq %xmm2,0x04(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}");
+	asm volatile("vpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}");
+
+	/* AVX-512: Op code 0f 38 91 */
+
+	asm volatile("vpgatherqd %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqq %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}");
+	asm volatile("vpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}");
+
+	/* AVX-512: Op code 0f 38 a0 */
+
+	asm volatile("vpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a1 */
+
+	asm volatile("vpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a2 */
+
+	asm volatile("vscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a3 */
+
+	asm volatile("vscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 b4 */
+
+	asm volatile("vpmadd52luq %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 b5 */
+
+	asm volatile("vpmadd52huq %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 c4 */
+
+	asm volatile("vpconflictd %zmm26,%zmm27");
+	asm volatile("vpconflictq %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 c8 */
+
+	asm volatile("vexp2ps %zmm29,%zmm30");
+	asm volatile("vexp2pd %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 ca */
+
+	asm volatile("vrcp28ps %zmm29,%zmm30");
+	asm volatile("vrcp28pd %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 cb */
+
+	asm volatile("vrcp28ss %xmm28,%xmm29,%xmm30{%k7}");
+	asm volatile("vrcp28sd %xmm25,%xmm26,%xmm27{%k7}");
+
+	/* AVX-512: Op code 0f 38 cc */
+
+	asm volatile("vrsqrt28ps %zmm29,%zmm30");
+	asm volatile("vrsqrt28pd %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 cd */
+
+	asm volatile("vrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}");
+	asm volatile("vrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 03 */
+
+	asm volatile("valignd $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("valignq $0x12,%zmm25,%zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 3a 08 */
+
+	asm volatile("vroundps $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscaleps $0x12,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 3a 09 */
+
+	asm volatile("vroundpd $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscalepd $0x12,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 3a 1a */
+
+	asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 0b */
+
+	asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 18 */
+
+	asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+	asm volatile("vinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 19 */
+
+	asm volatile("vextractf128 $0x5,%ymm4,%xmm4");
+	asm volatile("vextractf32x4 $0x12,%zmm25,%xmm26{%k7}");
+	asm volatile("vextractf64x2 $0x12,%zmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1a */
+
+	asm volatile("vinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}");
+	asm volatile("vinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1b */
+
+	asm volatile("vextractf32x8 $0x12,%zmm29,%ymm30{%k7}");
+	asm volatile("vextractf64x4 $0x12,%zmm26,%ymm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1e */
+
+	asm volatile("vpcmpud $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpuq $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 1f */
+
+	asm volatile("vpcmpd $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpq $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 23 */
+
+	asm volatile("vshuff32x4 $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("vshuff64x2 $0x12,%zmm25,%zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 3a 25 */
+
+	asm volatile("vpternlogd $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("vpternlogq $0x12,%zmm28,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 26 */
+
+	asm volatile("vgetmantps $0x12,%zmm26,%zmm27");
+	asm volatile("vgetmantpd $0x12,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 27 */
+
+	asm volatile("vgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}");
+	asm volatile("vgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}");
+
+	/* AVX-512: Op code 0f 3a 38 */
+
+	asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+	asm volatile("vinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 39 */
+
+	asm volatile("vextracti128 $0x5,%ymm4,%xmm6");
+	asm volatile("vextracti32x4 $0x12,%zmm25,%xmm26{%k7}");
+	asm volatile("vextracti64x2 $0x12,%zmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3a */
+
+	asm volatile("vinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}");
+	asm volatile("vinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3b */
+
+	asm volatile("vextracti32x8 $0x12,%zmm29,%ymm30{%k7}");
+	asm volatile("vextracti64x4 $0x12,%zmm26,%ymm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3e */
+
+	asm volatile("vpcmpub $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpuw $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 3f */
+
+	asm volatile("vpcmpb $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpw $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 43 */
+
+	asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2");
+	asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 43 */
+
+	asm volatile("vshufi32x4 $0x12,%zmm25,%zmm26,%zmm27");
+	asm volatile("vshufi64x2 $0x12,%zmm28,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 50 */
+
+	asm volatile("vrangeps $0x12,%zmm25,%zmm26,%zmm27");
+	asm volatile("vrangepd $0x12,%zmm28,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 51 */
+
+	asm volatile("vrangess $0x12,%xmm25,%xmm26,%xmm27");
+	asm volatile("vrangesd $0x12,%xmm28,%xmm29,%xmm30");
+
+	/* AVX-512: Op code 0f 3a 54 */
+
+	asm volatile("vfixupimmps $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("vfixupimmpd $0x12,%zmm25,%zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 3a 55 */
+
+	asm volatile("vfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}");
+	asm volatile("vfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 56 */
+
+	asm volatile("vreduceps $0x12,%zmm26,%zmm27");
+	asm volatile("vreducepd $0x12,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 57 */
+
+	asm volatile("vreducess $0x12,%xmm25,%xmm26,%xmm27");
+	asm volatile("vreducesd $0x12,%xmm28,%xmm29,%xmm30");
+
+	/* AVX-512: Op code 0f 3a 66 */
+
+	asm volatile("vfpclassps $0x12,%zmm27,%k5");
+	asm volatile("vfpclasspd $0x12,%zmm30,%k5");
+
+	/* AVX-512: Op code 0f 3a 67 */
+
+	asm volatile("vfpclassss $0x12,%xmm27,%k5");
+	asm volatile("vfpclasssd $0x12,%xmm30,%k5");
+
+	/* AVX-512: Op code 0f 72 (Grp13) */
+
+	asm volatile("vprord $0x12,%zmm25,%zmm26");
+	asm volatile("vprorq $0x12,%zmm25,%zmm26");
+	asm volatile("vprold $0x12,%zmm29,%zmm30");
+	asm volatile("vprolq $0x12,%zmm29,%zmm30");
+	asm volatile("psrad  $0x2,%mm6");
+	asm volatile("vpsrad $0x5,%ymm6,%ymm2");
+	asm volatile("vpsrad $0x5,%zmm26,%zmm22");
+	asm volatile("vpsraq $0x5,%zmm26,%zmm22");
+
+	/* AVX-512: Op code 0f 38 c6 (Grp18) */
+
+	asm volatile("vgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}");
+	asm volatile("vgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}");
+	asm volatile("vscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}");
+	asm volatile("vscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 c7 (Grp19) */
+
+	asm volatile("vgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}");
+
+	/* AVX-512: Examples */
+
+	asm volatile("vaddpd %zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}");
+	asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}{z}");
+	asm volatile("vaddpd {rn-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd {ru-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd {rd-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd {rz-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd (%rcx),%zmm29,%zmm30");
+	asm volatile("vaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30");
+	asm volatile("vaddpd (%rcx){1to8},%zmm29,%zmm30");
+	asm volatile("vaddpd 0x1fc0(%rdx),%zmm29,%zmm30");
+	asm volatile("vaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30");
+	asm volatile("vcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5");
+	asm volatile("vcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}");
+	asm volatile("vcmplesd {sae},%xmm28,%xmm29,%k5{%k7}");
+	asm volatile("vgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}");
+
 	/* bndmk m64, bnd */
 
 	asm volatile("bndmk (%rax), %bnd0");
@@ -471,6 +1345,921 @@ int main(void)
 
 #else  /* #ifdef __x86_64__ */
 
+	/* bound r32, mem (same op code as EVEX prefix) */
+
+	asm volatile("bound %eax, 0x12345678(%ecx)");
+	asm volatile("bound %ecx, 0x12345678(%eax)");
+	asm volatile("bound %edx, 0x12345678(%eax)");
+	asm volatile("bound %ebx, 0x12345678(%eax)");
+	asm volatile("bound %esp, 0x12345678(%eax)");
+	asm volatile("bound %ebp, 0x12345678(%eax)");
+	asm volatile("bound %esi, 0x12345678(%eax)");
+	asm volatile("bound %edi, 0x12345678(%eax)");
+	asm volatile("bound %ecx, (%eax)");
+	asm volatile("bound %eax, (0x12345678)");
+	asm volatile("bound %edx, (%ecx,%eax,1)");
+	asm volatile("bound %edx, 0x12345678(,%eax,1)");
+	asm volatile("bound %edx, (%eax,%ecx,1)");
+	asm volatile("bound %edx, (%eax,%ecx,8)");
+	asm volatile("bound %edx, 0x12(%eax)");
+	asm volatile("bound %edx, 0x12(%ebp)");
+	asm volatile("bound %edx, 0x12(%ecx,%eax,1)");
+	asm volatile("bound %edx, 0x12(%ebp,%eax,1)");
+	asm volatile("bound %edx, 0x12(%eax,%ecx,1)");
+	asm volatile("bound %edx, 0x12(%eax,%ecx,8)");
+	asm volatile("bound %edx, 0x12345678(%eax)");
+	asm volatile("bound %edx, 0x12345678(%ebp)");
+	asm volatile("bound %edx, 0x12345678(%ecx,%eax,1)");
+	asm volatile("bound %edx, 0x12345678(%ebp,%eax,1)");
+	asm volatile("bound %edx, 0x12345678(%eax,%ecx,1)");
+	asm volatile("bound %edx, 0x12345678(%eax,%ecx,8)");
+
+	/* bound r16, mem (same op code as EVEX prefix) */
+
+	asm volatile("bound %ax, 0x12345678(%ecx)");
+	asm volatile("bound %cx, 0x12345678(%eax)");
+	asm volatile("bound %dx, 0x12345678(%eax)");
+	asm volatile("bound %bx, 0x12345678(%eax)");
+	asm volatile("bound %sp, 0x12345678(%eax)");
+	asm volatile("bound %bp, 0x12345678(%eax)");
+	asm volatile("bound %si, 0x12345678(%eax)");
+	asm volatile("bound %di, 0x12345678(%eax)");
+	asm volatile("bound %cx, (%eax)");
+	asm volatile("bound %ax, (0x12345678)");
+	asm volatile("bound %dx, (%ecx,%eax,1)");
+	asm volatile("bound %dx, 0x12345678(,%eax,1)");
+	asm volatile("bound %dx, (%eax,%ecx,1)");
+	asm volatile("bound %dx, (%eax,%ecx,8)");
+	asm volatile("bound %dx, 0x12(%eax)");
+	asm volatile("bound %dx, 0x12(%ebp)");
+	asm volatile("bound %dx, 0x12(%ecx,%eax,1)");
+	asm volatile("bound %dx, 0x12(%ebp,%eax,1)");
+	asm volatile("bound %dx, 0x12(%eax,%ecx,1)");
+	asm volatile("bound %dx, 0x12(%eax,%ecx,8)");
+	asm volatile("bound %dx, 0x12345678(%eax)");
+	asm volatile("bound %dx, 0x12345678(%ebp)");
+	asm volatile("bound %dx, 0x12345678(%ecx,%eax,1)");
+	asm volatile("bound %dx, 0x12345678(%ebp,%eax,1)");
+	asm volatile("bound %dx, 0x12345678(%eax,%ecx,1)");
+	asm volatile("bound %dx, 0x12345678(%eax,%ecx,8)");
+
+	/* AVX-512: Instructions with the same op codes as Mask Instructions  */
+
+	asm volatile("cmovno %eax,%ebx");
+	asm volatile("cmovno 0x12345678(%eax),%ecx");
+	asm volatile("cmovno 0x12345678(%eax),%cx");
+
+	asm volatile("cmove  %eax,%ebx");
+	asm volatile("cmove 0x12345678(%eax),%ecx");
+	asm volatile("cmove 0x12345678(%eax),%cx");
+
+	asm volatile("seto    0x12345678(%eax)");
+	asm volatile("setno   0x12345678(%eax)");
+	asm volatile("setb    0x12345678(%eax)");
+	asm volatile("setc    0x12345678(%eax)");
+	asm volatile("setnae  0x12345678(%eax)");
+	asm volatile("setae   0x12345678(%eax)");
+	asm volatile("setnb   0x12345678(%eax)");
+	asm volatile("setnc   0x12345678(%eax)");
+	asm volatile("sets    0x12345678(%eax)");
+	asm volatile("setns   0x12345678(%eax)");
+
+	/* AVX-512: Mask Instructions */
+
+	asm volatile("kandw  %k7,%k6,%k5");
+	asm volatile("kandq  %k7,%k6,%k5");
+	asm volatile("kandb  %k7,%k6,%k5");
+	asm volatile("kandd  %k7,%k6,%k5");
+
+	asm volatile("kandnw  %k7,%k6,%k5");
+	asm volatile("kandnq  %k7,%k6,%k5");
+	asm volatile("kandnb  %k7,%k6,%k5");
+	asm volatile("kandnd  %k7,%k6,%k5");
+
+	asm volatile("knotw  %k7,%k6");
+	asm volatile("knotq  %k7,%k6");
+	asm volatile("knotb  %k7,%k6");
+	asm volatile("knotd  %k7,%k6");
+
+	asm volatile("korw  %k7,%k6,%k5");
+	asm volatile("korq  %k7,%k6,%k5");
+	asm volatile("korb  %k7,%k6,%k5");
+	asm volatile("kord  %k7,%k6,%k5");
+
+	asm volatile("kxnorw  %k7,%k6,%k5");
+	asm volatile("kxnorq  %k7,%k6,%k5");
+	asm volatile("kxnorb  %k7,%k6,%k5");
+	asm volatile("kxnord  %k7,%k6,%k5");
+
+	asm volatile("kxorw  %k7,%k6,%k5");
+	asm volatile("kxorq  %k7,%k6,%k5");
+	asm volatile("kxorb  %k7,%k6,%k5");
+	asm volatile("kxord  %k7,%k6,%k5");
+
+	asm volatile("kaddw  %k7,%k6,%k5");
+	asm volatile("kaddq  %k7,%k6,%k5");
+	asm volatile("kaddb  %k7,%k6,%k5");
+	asm volatile("kaddd  %k7,%k6,%k5");
+
+	asm volatile("kunpckbw %k7,%k6,%k5");
+	asm volatile("kunpckwd %k7,%k6,%k5");
+	asm volatile("kunpckdq %k7,%k6,%k5");
+
+	asm volatile("kmovw  %k6,%k5");
+	asm volatile("kmovw  (%ecx),%k5");
+	asm volatile("kmovw  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovw  %k5,(%ecx)");
+	asm volatile("kmovw  %k5,0x123(%eax,%ecx,8)");
+	asm volatile("kmovw  %eax,%k5");
+	asm volatile("kmovw  %ebp,%k5");
+	asm volatile("kmovw  %k5,%eax");
+	asm volatile("kmovw  %k5,%ebp");
+
+	asm volatile("kmovq  %k6,%k5");
+	asm volatile("kmovq  (%ecx),%k5");
+	asm volatile("kmovq  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovq  %k5,(%ecx)");
+	asm volatile("kmovq  %k5,0x123(%eax,%ecx,8)");
+
+	asm volatile("kmovb  %k6,%k5");
+	asm volatile("kmovb  (%ecx),%k5");
+	asm volatile("kmovb  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovb  %k5,(%ecx)");
+	asm volatile("kmovb  %k5,0x123(%eax,%ecx,8)");
+	asm volatile("kmovb  %eax,%k5");
+	asm volatile("kmovb  %ebp,%k5");
+	asm volatile("kmovb  %k5,%eax");
+	asm volatile("kmovb  %k5,%ebp");
+
+	asm volatile("kmovd  %k6,%k5");
+	asm volatile("kmovd  (%ecx),%k5");
+	asm volatile("kmovd  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovd  %k5,(%ecx)");
+	asm volatile("kmovd  %k5,0x123(%eax,%ecx,8)");
+	asm volatile("kmovd  %eax,%k5");
+	asm volatile("kmovd  %ebp,%k5");
+	asm volatile("kmovd  %k5,%eax");
+	asm volatile("kmovd  %k5,%ebp");
+
+	asm volatile("kortestw %k6,%k5");
+	asm volatile("kortestq %k6,%k5");
+	asm volatile("kortestb %k6,%k5");
+	asm volatile("kortestd %k6,%k5");
+
+	asm volatile("ktestw %k6,%k5");
+	asm volatile("ktestq %k6,%k5");
+	asm volatile("ktestb %k6,%k5");
+	asm volatile("ktestd %k6,%k5");
+
+	asm volatile("kshiftrw $0x12,%k6,%k5");
+	asm volatile("kshiftrq $0x5b,%k6,%k5");
+	asm volatile("kshiftlw $0x12,%k6,%k5");
+	asm volatile("kshiftlq $0x5b,%k6,%k5");
+
+	/* AVX-512: Op code 0f 5b */
+	asm volatile("vcvtdq2ps %xmm5,%xmm6");
+	asm volatile("vcvtqq2ps %zmm5,%ymm6{%k7}");
+	asm volatile("vcvtps2dq %xmm5,%xmm6");
+	asm volatile("vcvttps2dq %xmm5,%xmm6");
+
+	/* AVX-512: Op code 0f 6f */
+
+	asm volatile("movq   %mm0,%mm4");
+	asm volatile("vmovdqa %ymm4,%ymm6");
+	asm volatile("vmovdqa32 %zmm5,%zmm6");
+	asm volatile("vmovdqa64 %zmm5,%zmm6");
+	asm volatile("vmovdqu %ymm4,%ymm6");
+	asm volatile("vmovdqu32 %zmm5,%zmm6");
+	asm volatile("vmovdqu64 %zmm5,%zmm6");
+	asm volatile("vmovdqu8 %zmm5,%zmm6");
+	asm volatile("vmovdqu16 %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 78 */
+
+	asm volatile("vmread %eax,%ebx");
+	asm volatile("vcvttps2udq %zmm5,%zmm6");
+	asm volatile("vcvttpd2udq %zmm5,%ymm6{%k7}");
+	asm volatile("vcvttsd2usi %xmm6,%eax");
+	asm volatile("vcvttss2usi %xmm6,%eax");
+	asm volatile("vcvttps2uqq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvttpd2uqq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 79 */
+
+	asm volatile("vmwrite %eax,%ebx");
+	asm volatile("vcvtps2udq %zmm5,%zmm6");
+	asm volatile("vcvtpd2udq %zmm5,%ymm6{%k7}");
+	asm volatile("vcvtsd2usi %xmm6,%eax");
+	asm volatile("vcvtss2usi %xmm6,%eax");
+	asm volatile("vcvtps2uqq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtpd2uqq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 7a */
+
+	asm volatile("vcvtudq2pd %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtuqq2pd %zmm5,%zmm6");
+	asm volatile("vcvtudq2ps %zmm5,%zmm6");
+	asm volatile("vcvtuqq2ps %zmm5,%ymm6{%k7}");
+	asm volatile("vcvttps2qq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvttpd2qq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 7b */
+
+	asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6");
+	asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6");
+	asm volatile("vcvtps2qq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtpd2qq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 7f */
+
+	asm volatile("movq.s  %mm0,%mm4");
+	asm volatile("vmovdqa.s %ymm5,%ymm6");
+	asm volatile("vmovdqa32.s %zmm5,%zmm6");
+	asm volatile("vmovdqa64.s %zmm5,%zmm6");
+	asm volatile("vmovdqu.s %ymm5,%ymm6");
+	asm volatile("vmovdqu32.s %zmm5,%zmm6");
+	asm volatile("vmovdqu64.s %zmm5,%zmm6");
+	asm volatile("vmovdqu8.s %zmm5,%zmm6");
+	asm volatile("vmovdqu16.s %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f db */
+
+	asm volatile("pand  %mm1,%mm2");
+	asm volatile("pand  %xmm1,%xmm2");
+	asm volatile("vpand  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpandq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f df */
+
+	asm volatile("pandn  %mm1,%mm2");
+	asm volatile("pandn  %xmm1,%xmm2");
+	asm volatile("vpandn %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandnd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpandnq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f e6 */
+
+	asm volatile("vcvttpd2dq %xmm1,%xmm2");
+	asm volatile("vcvtdq2pd %xmm5,%xmm6");
+	asm volatile("vcvtdq2pd %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtqq2pd %zmm5,%zmm6");
+	asm volatile("vcvtpd2dq %xmm1,%xmm2");
+
+	/* AVX-512: Op code 0f eb */
+
+	asm volatile("por   %mm4,%mm6");
+	asm volatile("vpor   %ymm4,%ymm6,%ymm2");
+	asm volatile("vpord  %zmm4,%zmm5,%zmm6");
+	asm volatile("vporq  %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f ef */
+
+	asm volatile("pxor   %mm4,%mm6");
+	asm volatile("vpxor  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpxord %zmm4,%zmm5,%zmm6");
+	asm volatile("vpxorq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 10 */
+
+	asm volatile("pblendvb %xmm1,%xmm0");
+	asm volatile("vpsrlvw %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmovuswb %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 11 */
+
+	asm volatile("vpmovusdb %zmm5,%xmm6{%k7}");
+	asm volatile("vpsravw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 12 */
+
+	asm volatile("vpmovusqb %zmm5,%xmm6{%k7}");
+	asm volatile("vpsllvw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 13 */
+
+	asm volatile("vcvtph2ps %xmm3,%ymm5");
+	asm volatile("vcvtph2ps %ymm5,%zmm6{%k7}");
+	asm volatile("vpmovusdw %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 14 */
+
+	asm volatile("blendvps %xmm1,%xmm0");
+	asm volatile("vpmovusqw %zmm5,%xmm6{%k7}");
+	asm volatile("vprorvd %zmm4,%zmm5,%zmm6");
+	asm volatile("vprorvq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 15 */
+
+	asm volatile("blendvpd %xmm1,%xmm0");
+	asm volatile("vpmovusqd %zmm5,%ymm6{%k7}");
+	asm volatile("vprolvd %zmm4,%zmm5,%zmm6");
+	asm volatile("vprolvq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 16 */
+
+	asm volatile("vpermps %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermps %ymm4,%ymm6,%ymm2{%k7}");
+	asm volatile("vpermpd %ymm4,%ymm6,%ymm2{%k7}");
+
+	/* AVX-512: Op code 0f 38 19 */
+
+	asm volatile("vbroadcastsd %xmm4,%ymm6");
+	asm volatile("vbroadcastf32x2 %xmm7,%zmm6");
+
+	/* AVX-512: Op code 0f 38 1a */
+
+	asm volatile("vbroadcastf128 (%ecx),%ymm4");
+	asm volatile("vbroadcastf32x4 (%ecx),%zmm6");
+	asm volatile("vbroadcastf64x2 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 1b */
+
+	asm volatile("vbroadcastf32x8 (%ecx),%zmm6");
+	asm volatile("vbroadcastf64x4 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 1f */
+
+	asm volatile("vpabsq %zmm4,%zmm6");
+
+	/* AVX-512: Op code 0f 38 20 */
+
+	asm volatile("vpmovsxbw %xmm4,%xmm5");
+	asm volatile("vpmovswb %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 21 */
+
+	asm volatile("vpmovsxbd %xmm4,%ymm6");
+	asm volatile("vpmovsdb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 22 */
+
+	asm volatile("vpmovsxbq %xmm4,%ymm4");
+	asm volatile("vpmovsqb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 23 */
+
+	asm volatile("vpmovsxwd %xmm4,%ymm4");
+	asm volatile("vpmovsdw %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 24 */
+
+	asm volatile("vpmovsxwq %xmm4,%ymm6");
+	asm volatile("vpmovsqw %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 25 */
+
+	asm volatile("vpmovsxdq %xmm4,%ymm4");
+	asm volatile("vpmovsqd %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 26 */
+
+	asm volatile("vptestmb %zmm5,%zmm6,%k5");
+	asm volatile("vptestmw %zmm5,%zmm6,%k5");
+	asm volatile("vptestnmb %zmm4,%zmm5,%k5");
+	asm volatile("vptestnmw %zmm4,%zmm5,%k5");
+
+	/* AVX-512: Op code 0f 38 27 */
+
+	asm volatile("vptestmd %zmm5,%zmm6,%k5");
+	asm volatile("vptestmq %zmm5,%zmm6,%k5");
+	asm volatile("vptestnmd %zmm4,%zmm5,%k5");
+	asm volatile("vptestnmq %zmm4,%zmm5,%k5");
+
+	/* AVX-512: Op code 0f 38 28 */
+
+	asm volatile("vpmuldq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2b %k5,%zmm6");
+	asm volatile("vpmovm2w %k5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 29 */
+
+	asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovb2m %zmm6,%k5");
+	asm volatile("vpmovw2m %zmm6,%k5");
+
+	/* AVX-512: Op code 0f 38 2a */
+
+	asm volatile("vmovntdqa (%ecx),%ymm4");
+	asm volatile("vpbroadcastmb2q %k6,%zmm1");
+
+	/* AVX-512: Op code 0f 38 2c */
+
+	asm volatile("vmaskmovps (%ecx),%ymm4,%ymm6");
+	asm volatile("vscalefps %zmm4,%zmm5,%zmm6");
+	asm volatile("vscalefpd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 2d */
+
+	asm volatile("vmaskmovpd (%ecx),%ymm4,%ymm6");
+	asm volatile("vscalefss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vscalefsd %xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 30 */
+
+	asm volatile("vpmovzxbw %xmm4,%ymm4");
+	asm volatile("vpmovwb %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 31 */
+
+	asm volatile("vpmovzxbd %xmm4,%ymm6");
+	asm volatile("vpmovdb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 32 */
+
+	asm volatile("vpmovzxbq %xmm4,%ymm4");
+	asm volatile("vpmovqb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 33 */
+
+	asm volatile("vpmovzxwd %xmm4,%ymm4");
+	asm volatile("vpmovdw %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 34 */
+
+	asm volatile("vpmovzxwq %xmm4,%ymm6");
+	asm volatile("vpmovqw %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 35 */
+
+	asm volatile("vpmovzxdq %xmm4,%ymm4");
+	asm volatile("vpmovqd %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 36 */
+
+	asm volatile("vpermd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermd %ymm4,%ymm6,%ymm2{%k7}");
+	asm volatile("vpermq %ymm4,%ymm6,%ymm2{%k7}");
+
+	/* AVX-512: Op code 0f 38 38 */
+
+	asm volatile("vpminsb %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2d %k5,%zmm6");
+	asm volatile("vpmovm2q %k5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 39 */
+
+	asm volatile("vpminsd %xmm1,%xmm2,%xmm3");
+	asm volatile("vpminsd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpminsq %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmovd2m %zmm6,%k5");
+	asm volatile("vpmovq2m %zmm6,%k5");
+
+	/* AVX-512: Op code 0f 38 3a */
+
+	asm volatile("vpminuw %ymm4,%ymm6,%ymm2");
+	asm volatile("vpbroadcastmw2d %k6,%zmm6");
+
+	/* AVX-512: Op code 0f 38 3b */
+
+	asm volatile("vpminud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpminud %zmm4,%zmm5,%zmm6");
+	asm volatile("vpminuq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 3d */
+
+	asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxsd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmaxsq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 3f */
+
+	asm volatile("vpmaxud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxud %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmaxuq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 40 */
+
+	asm volatile("vpmulld %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmulld %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmullq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 42 */
+
+	asm volatile("vgetexpps %zmm5,%zmm6");
+	asm volatile("vgetexppd %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 43 */
+
+	asm volatile("vgetexpss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vgetexpsd %xmm2,%xmm3,%xmm4{%k7}");
+
+	/* AVX-512: Op code 0f 38 44 */
+
+	asm volatile("vplzcntd %zmm5,%zmm6");
+	asm volatile("vplzcntq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 46 */
+
+	asm volatile("vpsravd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpsravd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpsravq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 4c */
+
+	asm volatile("vrcp14ps %zmm5,%zmm6");
+	asm volatile("vrcp14pd %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 4d */
+
+	asm volatile("vrcp14ss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vrcp14sd %xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 4e */
+
+	asm volatile("vrsqrt14ps %zmm5,%zmm6");
+	asm volatile("vrsqrt14pd %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 4f */
+
+	asm volatile("vrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 59 */
+
+	asm volatile("vpbroadcastq %xmm4,%xmm6");
+	asm volatile("vbroadcasti32x2 %xmm7,%zmm6");
+
+	/* AVX-512: Op code 0f 38 5a */
+
+	asm volatile("vbroadcasti128 (%ecx),%ymm4");
+	asm volatile("vbroadcasti32x4 (%ecx),%zmm6");
+	asm volatile("vbroadcasti64x2 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 5b */
+
+	asm volatile("vbroadcasti32x8 (%ecx),%zmm6");
+	asm volatile("vbroadcasti64x4 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 64 */
+
+	asm volatile("vpblendmd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpblendmq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 65 */
+
+	asm volatile("vblendmps %zmm4,%zmm5,%zmm6");
+	asm volatile("vblendmpd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 66 */
+
+	asm volatile("vpblendmb %zmm4,%zmm5,%zmm6");
+	asm volatile("vpblendmw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 75 */
+
+	asm volatile("vpermi2b %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermi2w %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 76 */
+
+	asm volatile("vpermi2d %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermi2q %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 77 */
+
+	asm volatile("vpermi2ps %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermi2pd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 7a */
+
+	asm volatile("vpbroadcastb %eax,%xmm3");
+
+	/* AVX-512: Op code 0f 38 7b */
+
+	asm volatile("vpbroadcastw %eax,%xmm3");
+
+	/* AVX-512: Op code 0f 38 7c */
+
+	asm volatile("vpbroadcastd %eax,%xmm3");
+
+	/* AVX-512: Op code 0f 38 7d */
+
+	asm volatile("vpermt2b %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermt2w %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 7e */
+
+	asm volatile("vpermt2d %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermt2q %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 7f */
+
+	asm volatile("vpermt2ps %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermt2pd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 83 */
+
+	asm volatile("vpmultishiftqb %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 88 */
+
+	asm volatile("vexpandps (%ecx),%zmm6");
+	asm volatile("vexpandpd (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 89 */
+
+	asm volatile("vpexpandd (%ecx),%zmm6");
+	asm volatile("vpexpandq (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 8a */
+
+	asm volatile("vcompressps %zmm6,(%ecx)");
+	asm volatile("vcompresspd %zmm6,(%ecx)");
+
+	/* AVX-512: Op code 0f 38 8b */
+
+	asm volatile("vpcompressd %zmm6,(%ecx)");
+	asm volatile("vpcompressq %zmm6,(%ecx)");
+
+	/* AVX-512: Op code 0f 38 8d */
+
+	asm volatile("vpermb %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 90 */
+
+	asm volatile("vpgatherdd %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdq %xmm2,0x04(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}");
+	asm volatile("vpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}");
+
+	/* AVX-512: Op code 0f 38 91 */
+
+	asm volatile("vpgatherqd %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqq %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}");
+	asm volatile("vpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}");
+
+	/* AVX-512: Op code 0f 38 a0 */
+
+	asm volatile("vpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a1 */
+
+	asm volatile("vpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a2 */
+
+	asm volatile("vscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a3 */
+
+	asm volatile("vscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 b4 */
+
+	asm volatile("vpmadd52luq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 b5 */
+
+	asm volatile("vpmadd52huq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 c4 */
+
+	asm volatile("vpconflictd %zmm5,%zmm6");
+	asm volatile("vpconflictq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 c8 */
+
+	asm volatile("vexp2ps %zmm6,%zmm7");
+	asm volatile("vexp2pd %zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 38 ca */
+
+	asm volatile("vrcp28ps %zmm6,%zmm7");
+	asm volatile("vrcp28pd %zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 38 cb */
+
+	asm volatile("vrcp28ss %xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vrcp28sd %xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 38 cc */
+
+	asm volatile("vrsqrt28ps %zmm6,%zmm7");
+	asm volatile("vrsqrt28pd %zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 38 cd */
+
+	asm volatile("vrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 03 */
+
+	asm volatile("valignd $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("valignq $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 08 */
+
+	asm volatile("vroundps $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscaleps $0x12,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 09 */
+
+	asm volatile("vroundpd $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscalepd $0x12,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 0a */
+
+	asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 0b */
+
+	asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 18 */
+
+	asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+	asm volatile("vinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 19 */
+
+	asm volatile("vextractf128 $0x5,%ymm4,%xmm4");
+	asm volatile("vextractf32x4 $0x12,%zmm5,%xmm6{%k7}");
+	asm volatile("vextractf64x2 $0x12,%zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1a */
+
+	asm volatile("vinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+	asm volatile("vinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1b */
+
+	asm volatile("vextractf32x8 $0x12,%zmm6,%ymm7{%k7}");
+	asm volatile("vextractf64x4 $0x12,%zmm6,%ymm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1e */
+
+	asm volatile("vpcmpud $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpuq $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 1f */
+
+	asm volatile("vpcmpd $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpq $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 23 */
+
+	asm volatile("vshuff32x4 $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vshuff64x2 $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 25 */
+
+	asm volatile("vpternlogd $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vpternlogq $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 26 */
+
+	asm volatile("vgetmantps $0x12,%zmm6,%zmm7");
+	asm volatile("vgetmantpd $0x12,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 27 */
+
+	asm volatile("vgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 38 */
+
+	asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+	asm volatile("vinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 39 */
+
+	asm volatile("vextracti128 $0x5,%ymm4,%xmm6");
+	asm volatile("vextracti32x4 $0x12,%zmm5,%xmm6{%k7}");
+	asm volatile("vextracti64x2 $0x12,%zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3a */
+
+	asm volatile("vinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+	asm volatile("vinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3b */
+
+	asm volatile("vextracti32x8 $0x12,%zmm6,%ymm7{%k7}");
+	asm volatile("vextracti64x4 $0x12,%zmm6,%ymm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3e */
+
+	asm volatile("vpcmpub $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpuw $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 3f */
+
+	asm volatile("vpcmpb $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpw $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 42 */
+
+	asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2");
+	asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 43 */
+
+	asm volatile("vshufi32x4 $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vshufi64x2 $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 50 */
+
+	asm volatile("vrangeps $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vrangepd $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 51 */
+
+	asm volatile("vrangess $0x12,%xmm5,%xmm6,%xmm7");
+	asm volatile("vrangesd $0x12,%xmm5,%xmm6,%xmm7");
+
+	/* AVX-512: Op code 0f 3a 54 */
+
+	asm volatile("vfixupimmps $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vfixupimmpd $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 55 */
+
+	asm volatile("vfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 56 */
+
+	asm volatile("vreduceps $0x12,%zmm6,%zmm7");
+	asm volatile("vreducepd $0x12,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 57 */
+
+	asm volatile("vreducess $0x12,%xmm5,%xmm6,%xmm7");
+	asm volatile("vreducesd $0x12,%xmm5,%xmm6,%xmm7");
+
+	/* AVX-512: Op code 0f 3a 66 */
+
+	asm volatile("vfpclassps $0x12,%zmm7,%k5");
+	asm volatile("vfpclasspd $0x12,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 67 */
+
+	asm volatile("vfpclassss $0x12,%xmm7,%k5");
+	asm volatile("vfpclasssd $0x12,%xmm7,%k5");
+
+	/* AVX-512: Op code 0f 72 (Grp13) */
+
+	asm volatile("vprord $0x12,%zmm5,%zmm6");
+	asm volatile("vprorq $0x12,%zmm5,%zmm6");
+	asm volatile("vprold $0x12,%zmm5,%zmm6");
+	asm volatile("vprolq $0x12,%zmm5,%zmm6");
+	asm volatile("psrad  $0x2,%mm6");
+	asm volatile("vpsrad $0x5,%ymm6,%ymm2");
+	asm volatile("vpsrad $0x5,%zmm6,%zmm2");
+	asm volatile("vpsraq $0x5,%zmm6,%zmm2");
+
+	/* AVX-512: Op code 0f 38 c6 (Grp18) */
+
+	asm volatile("vgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}");
+	asm volatile("vgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}");
+	asm volatile("vscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}");
+	asm volatile("vscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 c7 (Grp19) */
+
+	asm volatile("vgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}");
+
+	/* AVX-512: Examples */
+
+	asm volatile("vaddpd %zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}");
+	asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}{z}");
+	asm volatile("vaddpd {rn-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd {ru-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd {rd-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd {rz-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd (%ecx),%zmm5,%zmm6");
+	asm volatile("vaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6");
+	asm volatile("vaddpd (%ecx){1to8},%zmm5,%zmm6");
+	asm volatile("vaddpd 0x1fc0(%edx),%zmm5,%zmm6");
+	asm volatile("vaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6");
+	asm volatile("vcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5");
+	asm volatile("vcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}");
+	asm volatile("vcmplesd {sae},%xmm4,%xmm5,%k5{%k7}");
+	asm volatile("vgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}");
+
 	/* bndmk m32, bnd */
 
 	asm volatile("bndmk (%eax), %bnd0");
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index d2af78193153..76f41f249944 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -1,4 +1,5 @@
 #include <stdbool.h>
+#include <stdlib.h>
 #include "tests.h"
 #include "dso.h"
 #include "debug.h"
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b32464b353aa..8d363d5e65a2 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,7 +8,6 @@
 #include "map.h"
 #include "build-id.h"
 #include "perf_regs.h"
-#include <asm/perf_regs.h>
 
 struct mmap_event {
 	struct perf_event_header header;
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
index 517567347aac..54e961659514 100644
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 611645e903a8..125ecd2a300d 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c
index 9f26eae6c9f0..ca983e2bea8b 100644
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ b/tools/perf/util/intel-pt-decoder/insn.c
@@ -155,14 +155,24 @@ void insn_get_prefixes(struct insn *insn)
 			/*
 			 * In 32-bits mode, if the [7:6] bits (mod bits of
 			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES.
+			 * LDS or LES or BOUND.
 			 */
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
 		insn->vex_prefix.bytes[0] = b;
 		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_vex3_prefix(attr)) {
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
 			insn->vex_prefix.bytes[2] = b2;
 			insn->vex_prefix.nbytes = 3;
@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
-		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+		    (!inat_accept_vex(insn->attr) &&
+		     !inat_is_group(insn->attr)))
 			insn->attr = 0;	/* This instruction is bad */
 		goto end;	/* VEX has only 1 byte for opcode */
 	}
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index dd12da0f4593..e23578c7b1be 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index d388de72eaca..ec378cd7b71e 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -13,12 +13,17 @@
 # opcode: escape # escaped-name
 # EndTable
 #
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
 #<group maps>
 # GrpTable: GrpXXX
 # reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
 # EndTable
 #
 # AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
 #
@@ -137,7 +142,7 @@ Table: one byte opcode
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -399,17 +404,17 @@ AVXcode: 1
 3f:
 # 0x0f 0x40-0x4f
 40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev
-42: CMOVB/C/NAE Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
 43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev
-45: CMOVNE/NZ Gv,Ev
-46: CMOVBE/NA Gv,Ev
-47: CMOVA/NBE Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
 48: CMOVS Gv,Ev
 49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev
-4b: CMOVNP/PO Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
 4c: CMOVL/NGE Gv,Ev
 4d: CMOVNL/GE Gv,Ev
 4e: CMOVLE/NG Gv,Ev
@@ -426,7 +431,7 @@ AVXcode: 1
 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
@@ -447,7 +452,7 @@ AVXcode: 1
 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
 # 0x0f 0x70-0x7f
 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
@@ -458,14 +463,14 @@ AVXcode: 1
 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
 # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
 77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy
-79: VMWRITE Gy,Ey
-7a:
-7b:
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
 80: JO Jz (f64)
@@ -485,16 +490,16 @@ AVXcode: 1
 8e: JLE/JNG Jz (f64)
 8f: JNLE/JG Jz (f64)
 # 0x0f 0x90-0x9f
-90: SETO Eb
-91: SETNO Eb
-92: SETB/C/NAE Eb
-93: SETAE/NB/NC Eb
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
 94: SETE/Z Eb
 95: SETNE/NZ Eb
 96: SETBE/NA Eb
 97: SETA/NBE Eb
-98: SETS Eb
-99: SETNS Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
 9a: SETP/PE Eb
 9b: SETNP/PO Eb
 9c: SETL/NGE Eb
@@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
 d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
 d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
 da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
 dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
 dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
 de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xe0-0xef
 e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
 e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
@@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
 e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
 e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
 e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
 e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
 e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
 e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
 ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
 ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
 ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
 ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xf0-0xff
 f0: vlddqu Vx,Mx (F2)
 f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
@@ -626,81 +631,105 @@ AVXcode: 2
 0e: vtestps Vx,Wx (66),(v)
 0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66)
-11:
-12:
-13: vcvtph2ps Vx,Wx,Ib (66),(v)
-14: blendvps Vdq,Wdq (66)
-15: blendvpd Vdq,Wdq (66)
-16: vpermps Vqq,Hqq,Wqq (66),(v)
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
 17: vptest Vx,Wx (66)
 18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 Vqq,Mdq (66),(v)
-1b:
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f:
+1f: vpabsq Vx,Wx (66),(ev)
 # 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1)
-26:
-27:
-28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: vmovntdqa Vx,Mx (66),(v1)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
 2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
 2e: vmaskmovps Mx,Hx,Vx (66),(v)
 2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36: vpermd Vqq,Hqq,Wqq (66),(v)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
 37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1)
-39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: vpminud Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
 3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
 3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1)
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
 41: vphminposuw Vdq,Wdq (66),(v1)
-42:
-43:
-44:
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
 45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
 47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x57
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
 58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v)
-5a: vbroadcasti128 Vqq,Mdq (66),(v)
-# Skip 0x5b-0x77
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
 78: vpbroadcastb Vx,Wx (66),(v)
 79: vpbroadcastw Vx,Wx (66),(v)
-# Skip 0x7a-0x7f
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
 81: INVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v)
-91: vgatherqd/q Vx,Hx,Wx (66),(v)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
 92: vgatherdps/d Vx,Hx,Wx (66),(v)
 93: vgatherqps/d Vx,Hx,Wx (66),(v)
 94:
@@ -715,6 +744,10 @@ AVXcode: 2
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
 a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
@@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-c8: sha1nexte Vdq,Wdq
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq
-cb: sha256rnds2 Vdq,Wdq
-cc: sha256msg1 Vdq,Wdq
-cd: sha256msg2 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -763,15 +801,15 @@ AVXcode: 3
 00: vpermq Vqq,Wqq,Ib (66),(v)
 01: vpermpd Vqq,Wqq,Ib (66),(v)
 02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03:
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
 04: vpermilps Vx,Wx,Ib (66),(v)
 05: vpermilpd Vx,Wx,Ib (66),(v)
 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
 07:
-08: vroundps Vx,Wx,Ib (66)
-09: vroundpd Vx,Wx,Ib (66)
-0a: vroundss Vss,Wss,Ib (66),(v1)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
 0c: vblendps Vx,Hx,Wx,Ib (66)
 0d: vblendpd Vx,Hx,Wx,Ib (66)
 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
@@ -780,26 +818,51 @@ AVXcode: 3
 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
 16: vpextrd/q Ey,Vdq,Ib (66),(v1)
 17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-19: vextractf128 Wdq,Vqq,Ib (66),(v)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
 1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-39: vextracti128 Wdq,Vqq,Ib (66),(v)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
 40: vdpps Vx,Hx,Wx,Ib (66)
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
@@ -927,8 +990,10 @@ GrpTable: Grp12
 EndTable
 
 GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
@@ -963,6 +1028,20 @@ GrpTable: Grp17
 3: BLSI By,Ey (v)
 EndTable
 
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch
index e11fbd6fae78..ad85b921a607 100644
--- a/tools/scripts/Makefile.arch
+++ b/tools/scripts/Makefile.arch
@@ -1,8 +1,4 @@
-ifndef ARCH
-ARCH := $(shell uname -m 2>/dev/null || echo not)
-endif
-
-ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
+HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sun4u/sparc/ -e s/sparc64/sparc/ \
                                   -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
@@ -10,6 +6,41 @@ ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
                                   -e s/tile.*/tile/ )
 
+ifndef ARCH
+ARCH := $(HOSTARCH)
+endif
+
+SRCARCH := $(ARCH)
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+        SRCARCH := x86
+endif
+ifeq ($(ARCH),x86_64)
+        SRCARCH := x86
+endif
+
+# Additional ARCH settings for sparc
+ifeq ($(ARCH),sparc32)
+       SRCARCH := sparc
+endif
+ifeq ($(ARCH),sparc64)
+       SRCARCH := sparc
+endif
+
+# Additional ARCH settings for sh
+ifeq ($(ARCH),sh64)
+       SRCARCH := sh
+endif
+
+# Additional ARCH settings for tile
+ifeq ($(ARCH),tilepro)
+       SRCARCH := tile
+endif
+ifeq ($(ARCH),tilegx)
+       SRCARCH := tile
+endif
+
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
   IS_64_BIT := 1

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-07-08 13:42 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-07-08 13:42 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Andrew Morton, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 2c81a6477081966fe80b8c6daa68459bca896774 perf/core: Fix pmu::filter_match for SW-led groups

Various fixes:

 - 32-bit callgraph bug fix
 - suboptimal event group scheduling bug fix
 - event constraint fixes for Broadwell/Skylake
 - RAPL module name collision fix

 Thanks,

	Ingo

------------------>
Josh Poimboeuf (1):
      perf/x86: Fix 32-bit perf user callgraph collection

Mark Rutland (1):
      perf/core: Fix pmu::filter_match for SW-led groups

Stephane Eranian (1):
      perf/x86/intel: Update event constraints when HT is off

Ville Syrjälä (1):
      x86/perf/intel/rapl: Fix module name collision with powercap intel-rapl


 arch/x86/events/core.c         | 11 ++++++-----
 arch/x86/events/intel/Makefile |  4 ++--
 arch/x86/events/intel/core.c   | 29 +++++++++++++++++++++++++++++
 kernel/events/core.c           | 23 ++++++++++++++++++++++-
 4 files changed, 59 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 33787ee817f0..26ced536005a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2319,7 +2319,7 @@ void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
-	const void __user *fp;
+	const unsigned long __user *fp;
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
 		return;
 
-	fp = (void __user *)regs->bp;
+	fp = (unsigned long __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
 
@@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	pagefault_disable();
 	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
+
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 16))
+		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
 			break;
 
-		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
 		if (bytes != 0)
 			break;
-		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
+		bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
 		if (bytes != 0)
 			break;
 
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3660b2cf245a..06c2baa51814 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -1,8 +1,8 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
-intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
+intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7c666958a625..9b4f9d3ce465 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
 	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc6, 0xf),	/* FRONTEND_RETIRED.* */
+
 	EVENT_CONSTRAINT_END
 };
 
@@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 85cd41878a74..43d43a2d5811 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1678,12 +1678,33 @@ static bool is_orphaned_event(struct perf_event *event)
 	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
-static inline int pmu_filter_match(struct perf_event *event)
+static inline int __pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 	return pmu->filter_match ? pmu->filter_match(event) : 1;
 }
 
+/*
+ * Check whether we should attempt to schedule an event group based on
+ * PMU-specific filtering. An event group can consist of HW and SW events,
+ * potentially with a SW leader, so we must check all the filters, to
+ * determine whether a group is schedulable:
+ */
+static inline int pmu_filter_match(struct perf_event *event)
+{
+	struct perf_event *child;
+
+	if (!__pmu_filter_match(event))
+		return 0;
+
+	list_for_each_entry(child, &event->sibling_list, group_entry) {
+		if (!__pmu_filter_match(child))
+			return 0;
+	}
+
+	return 1;
+}
+
 static inline int
 event_filter_match(struct perf_event *event)
 {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-06-10 12:50 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-06-10 12:50 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 62a92c8f553e49270a0ee391b8733da71ab0aebc perf/core: Remove a redundant check

A handful of tooling fixes, two PMU driver fixes and a cleanup of redundant code 
that addresses a security analyzer false positive.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Remove a redundant check

Kan Liang (1):
      perf/x86/intel/uncore: Remove SBOX support for Broadwell server

Vincent Stehlé (1):
      perf/x86/intel/rapl: Fix pmus free during cleanup

Wang Nan (3):
      perf symbols: Check kptr_restrict for root
      perf record: Fix crash when kptr is restricted
      perf ctf: Convert invalid chars in a string before set value


 arch/x86/events/intel/rapl.c         |  2 +-
 arch/x86/events/intel/uncore_snbep.c | 21 ------------------
 kernel/events/core.c                 |  6 ++----
 tools/perf/util/data-convert-bt.c    | 41 ++++++++++++++++++++++++++++++++++--
 tools/perf/util/event.c              |  2 ++
 tools/perf/util/symbol.c             | 16 +++++++-------
 6 files changed, 52 insertions(+), 36 deletions(-)

diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 99c4bab123cd..e30eef4f29a6 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -714,7 +714,7 @@ static void cleanup_rapl_pmus(void)
 	int i;
 
 	for (i = 0; i < rapl_pmus->maxpkg; i++)
-		kfree(rapl_pmus->pmus + i);
+		kfree(rapl_pmus->pmus[i]);
 	kfree(rapl_pmus);
 }
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b2625867ebd1..874e8bd64d1d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2868,27 +2868,10 @@ static struct intel_uncore_type bdx_uncore_cbox = {
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
-static struct intel_uncore_type bdx_uncore_sbox = {
-	.name			= "sbox",
-	.num_counters		= 4,
-	.num_boxes		= 4,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= HSWEP_S0_MSR_PMON_CTL0,
-	.perf_ctr		= HSWEP_S0_MSR_PMON_CTR0,
-	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
-	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
-	.ops			= &hswep_uncore_sbox_msr_ops,
-	.format_group		= &hswep_uncore_sbox_format_group,
-};
-
-#define BDX_MSR_UNCORE_SBOX	3
-
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
 	&hswep_uncore_pcu,
-	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -2897,10 +2880,6 @@ void bdx_uncore_cpu_init(void)
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
-
-	/* BDX-DE doesn't have SBOX */
-	if (boot_cpu_data.x86_model == 86)
-		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 050a290c72c7..87e945d6ebb8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3862,10 +3862,8 @@ static void _free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
-	if (event->pmu) {
-		exclusive_event_destroy(event);
-		module_put(event->pmu->module);
-	}
+	exclusive_event_destroy(event);
+	module_put(event->pmu->module);
 
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index bbf69d248ec5..9f53020c3269 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -204,6 +204,44 @@ static unsigned long long adjust_signedness(unsigned long long value_int, int si
 	return (value_int & value_mask) | ~value_mask;
 }
 
+static int string_set_value(struct bt_ctf_field *field, const char *string)
+{
+	char *buffer = NULL;
+	size_t len = strlen(string), i, p;
+	int err;
+
+	for (i = p = 0; i < len; i++, p++) {
+		if (isprint(string[i])) {
+			if (!buffer)
+				continue;
+			buffer[p] = string[i];
+		} else {
+			char numstr[5];
+
+			snprintf(numstr, sizeof(numstr), "\\x%02x",
+				 (unsigned int)(string[i]) & 0xff);
+
+			if (!buffer) {
+				buffer = zalloc(i + (len - i) * 4 + 2);
+				if (!buffer) {
+					pr_err("failed to set unprintable string '%s'\n", string);
+					return bt_ctf_field_string_set_value(field, "UNPRINTABLE-STRING");
+				}
+				if (i > 0)
+					strncpy(buffer, string, i);
+			}
+			strncat(buffer + p, numstr, 4);
+			p += 3;
+		}
+	}
+
+	if (!buffer)
+		return bt_ctf_field_string_set_value(field, string);
+	err = bt_ctf_field_string_set_value(field, buffer);
+	free(buffer);
+	return err;
+}
+
 static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
@@ -270,8 +308,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 
 		if (flags & FIELD_IS_STRING)
-			ret = bt_ctf_field_string_set_value(field,
-					data + offset + i * len);
+			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f6fcc6832949..9b141f12329e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -673,6 +673,8 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	int err;
 	union perf_event *event;
 
+	if (symbol_conf.kptr_restrict)
+		return -1;
 	if (map == NULL)
 		return -1;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 20f9cb32b703..54c4ff2b1cee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1933,17 +1933,17 @@ int setup_intlist(struct intlist **list, const char *list_str,
 static bool symbol__read_kptr_restrict(void)
 {
 	bool value = false;
+	FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
 
-	if (geteuid() != 0) {
-		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
-		if (fp != NULL) {
-			char line[8];
+	if (fp != NULL) {
+		char line[8];
 
-			if (fgets(line, sizeof(line), fp) != NULL)
-				value = atoi(line) != 0;
+		if (fgets(line, sizeof(line), fp) != NULL)
+			value = (geteuid() != 0) ?
+					(atoi(line) != 0) :
+					(atoi(line) == 2);
 
-			fclose(fp);
-		}
+		fclose(fp);
 	}
 
 	return value;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-05-13 18:51 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-05-13 18:51 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 636fa4a7b0d2987b7395cd2e259962cdca16e887 Merge tag 'perf-urgent-for-mingo-20160512' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

An uncharacteristically large number of bugs popped up in the last week:

 - various tooling fixes, two crashes and build problems
 - two Intel PT fixes
 - an KNL uncore driver fix
 - an Intel PMU driver fix

 Thanks,

	Ingo

------------------>
Alexander Shishkin (2):
      perf/x86/intel/pt: Generate PMI in the STOP region as well
      perf/core: Disable the event on a truncated AUX record

Andrey Ryabinin (1):
      perf/x86: Fix undefined shift on 32-bit kernels

Arnaldo Carvalho de Melo (9):
      perf tools: Use readdir() instead of deprecated readdir_r()
      perf script: Use readdir() instead of deprecated readdir_r()
      perf thread_map: Use readdir() instead of deprecated readdir_r()
      perf tools: Use readdir() instead of deprecated readdir_r()
      perf dwarf: Guard !x86_64 definitions under #ifdef else clause
      perf probe: Check if dwarf_getlocations() is available
      perf evsel: Improve EPERM error handling in open_strerror()
      perf evsel: Handle EACCESS + perf_event_paranoid=2 in fallback()
      perf stat: Fallback to user only counters when perf_event_paranoid > 1

Namhyung Kim (1):
      perf diff: Fix duplicated output column

Peter Zijlstra (1):
      perf/x86/msr: Fix SMI overflow

Steven Rostedt (1):
      tools lib traceevent: Do not reassign parg after collapse_tree()

hchrzani (1):
      perf/x86/intel/uncore: Fix CHA registers configuration procedure for Knights Landing platform


 arch/x86/events/intel/core.c                  |  2 +-
 arch/x86/events/intel/pt.c                    |  2 +
 arch/x86/events/intel/uncore_snbep.c          |  7 +++
 arch/x86/events/msr.c                         |  2 +-
 kernel/events/ring_buffer.c                   | 10 +++-
 tools/build/Makefile.feature                  |  2 +
 tools/build/feature/Makefile                  |  4 ++
 tools/build/feature/test-all.c                |  5 ++
 tools/build/feature/test-dwarf_getlocations.c | 12 +++++
 tools/lib/traceevent/parse-filter.c           |  4 +-
 tools/perf/arch/x86/util/dwarf-regs.c         |  8 +--
 tools/perf/builtin-script.c                   | 70 +++++++++++++--------------
 tools/perf/builtin-stat.c                     |  7 ++-
 tools/perf/config/Makefile                    |  6 +++
 tools/perf/util/dwarf-aux.c                   |  9 ++++
 tools/perf/util/event.c                       | 12 ++---
 tools/perf/util/evsel.c                       | 23 ++++++++-
 tools/perf/util/parse-events.c                | 60 +++++++++++------------
 tools/perf/util/sort.c                        |  3 ++
 tools/perf/util/thread_map.c                  |  8 +--
 20 files changed, 168 insertions(+), 88 deletions(-)
 create mode 100644 tools/build/feature/test-dwarf_getlocations.c

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6fd4dbcf820..5210eaa4aa62 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3708,7 +3708,7 @@ __init int intel_pmu_init(void)
 				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
 			c->idxmsk64 &=
-				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
 			c->weight = hweight64(c->idxmsk64);
 		}
 	}
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 09a77dbc73c9..7377814de30b 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -709,6 +709,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 
 	/* clear STOP and INT from current entry */
 	buf->topa_index[buf->stop_pos]->stop = 0;
+	buf->topa_index[buf->stop_pos]->intr = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
 	/* how many pages till the STOP marker */
@@ -733,6 +734,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
+	buf->topa_index[buf->stop_pos]->intr = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
 
 	return 0;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index ab2bcaaebe38..b2625867ebd1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -219,6 +219,9 @@
 #define KNL_CHA_MSR_PMON_BOX_FILTER_TID		0x1ff
 #define KNL_CHA_MSR_PMON_BOX_FILTER_STATE	(7 << 18)
 #define KNL_CHA_MSR_PMON_BOX_FILTER_OP		(0xfffffe2aULL << 32)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE	(0x1ULL << 32)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE	(0x1ULL << 33)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_NNC		(0x1ULL << 37)
 
 /* KNL EDC/MC UCLK */
 #define KNL_UCLK_MSR_PMON_CTR0_LOW		0x400
@@ -1902,6 +1905,10 @@ static int knl_cha_hw_config(struct intel_uncore_box *box,
 		reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
 			    KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx;
 		reg1->config = event->attr.config1 & knl_cha_filter_mask(idx);
+
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE;
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE;
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_NNC;
 		reg1->idx = idx;
 	}
 	return 0;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index ec863b9a9f78..8bef19f098d4 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -166,7 +166,7 @@ static void msr_event_update(struct perf_event *event)
 	if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
 		delta = sign_extend64(delta, 31);
 
-	local64_add(now - prev, &event->count);
+	local64_add(delta, &event->count);
 }
 
 static void msr_event_start(struct perf_event *event, int flags)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index c61f0cbd308b..7611d0f66cf8 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -347,6 +347,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 			 bool truncated)
 {
 	struct ring_buffer *rb = handle->rb;
+	bool wakeup = truncated;
 	unsigned long aux_head;
 	u64 flags = 0;
 
@@ -375,9 +376,16 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
 
 	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
-		perf_output_wakeup(handle);
+		wakeup = true;
 		local_add(rb->aux_watermark, &rb->aux_wakeup);
 	}
+
+	if (wakeup) {
+		if (truncated)
+			handle->event->pending_disable = 1;
+		perf_output_wakeup(handle);
+	}
+
 	handle->event = NULL;
 
 	local_set(&rb->aux_nest, 0);
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 6b7707270aa3..9f878619077a 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -30,6 +30,7 @@ endef
 FEATURE_TESTS_BASIC :=			\
 	backtrace			\
 	dwarf				\
+	dwarf_getlocations		\
 	fortify-source			\
 	sync-compare-and-swap		\
 	glibc				\
@@ -78,6 +79,7 @@ endif
 
 FEATURE_DISPLAY ?=			\
 	dwarf				\
+	dwarf_getlocations		\
 	glibc				\
 	gtk2				\
 	libaudit			\
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index c5f4c417428d..4ae94dbfdab9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -3,6 +3,7 @@ FILES=					\
 	test-backtrace.bin		\
 	test-bionic.bin			\
 	test-dwarf.bin			\
+	test-dwarf_getlocations.bin	\
 	test-fortify-source.bin		\
 	test-sync-compare-and-swap.bin	\
 	test-glibc.bin			\
@@ -82,6 +83,9 @@ endif
 $(OUTPUT)test-dwarf.bin:
 	$(BUILD) $(DWARFLIBS)
 
+$(OUTPUT)test-dwarf_getlocations.bin:
+	$(BUILD) $(DWARFLIBS)
+
 $(OUTPUT)test-libelf-mmap.bin:
 	$(BUILD) -lelf
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index e499a36c1e4a..a282e8cb84f3 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -41,6 +41,10 @@
 # include "test-dwarf.c"
 #undef main
 
+#define main main_test_dwarf_getlocations
+# include "test-dwarf_getlocations.c"
+#undef main
+
 #define main main_test_libelf_getphdrnum
 # include "test-libelf-getphdrnum.c"
 #undef main
@@ -143,6 +147,7 @@ int main(int argc, char *argv[])
 	main_test_libelf_mmap();
 	main_test_glibc();
 	main_test_dwarf();
+	main_test_dwarf_getlocations();
 	main_test_libelf_getphdrnum();
 	main_test_libunwind();
 	main_test_libaudit();
diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c
new file mode 100644
index 000000000000..70162699dd43
--- /dev/null
+++ b/tools/build/feature/test-dwarf_getlocations.c
@@ -0,0 +1,12 @@
+#include <stdlib.h>
+#include <elfutils/libdw.h>
+
+int main(void)
+{
+	Dwarf_Addr base, start, end;
+	Dwarf_Attribute attr;
+	Dwarf_Op *op;
+        size_t nops;
+	ptrdiff_t offset = 0;
+        return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
+}
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 0144b3d1bb77..88cccea3ca99 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1164,11 +1164,11 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		current_op = current_exp;
 
 	ret = collapse_tree(current_op, parg, error_str);
+	/* collapse_tree() may free current_op, and updates parg accordingly */
+	current_op = NULL;
 	if (ret < 0)
 		goto fail;
 
-	*parg = current_op;
-
 	free(token);
 	return 0;
 
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index 9223c164e545..1f86ee8fb831 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -63,6 +63,8 @@ struct pt_regs_offset {
 # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
 #endif
 
+/* TODO: switching by dwarf address size */
+#ifndef __x86_64__
 static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_NAME_32("%ax",	eax),
 	REG_OFFSET_NAME_32("%cx",	ecx),
@@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
+#define regoffset_table x86_32_regoffset_table
+#else
 static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_NAME_64("%ax",	rax),
 	REG_OFFSET_NAME_64("%dx",	rdx),
@@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
-/* TODO: switching by dwarf address size */
-#ifdef __x86_64__
 #define regoffset_table x86_64_regoffset_table
-#else
-#define regoffset_table x86_32_regoffset_table
 #endif
 
 /* Minus 1 for the ending REG_OFFSET_END */
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3770c3dffe5e..52826696c852 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1415,21 +1415,19 @@ static int is_directory(const char *base_path, const struct dirent *dent)
 	return S_ISDIR(st.st_mode);
 }
 
-#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
-	while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&	\
-	       lang_next)						\
-		if ((lang_dirent.d_type == DT_DIR ||			\
-		     (lang_dirent.d_type == DT_UNKNOWN &&		\
-		      is_directory(scripts_path, &lang_dirent))) &&	\
-		    (strcmp(lang_dirent.d_name, ".")) &&		\
-		    (strcmp(lang_dirent.d_name, "..")))
-
-#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
-	while (!readdir_r(lang_dir, &script_dirent, &script_next) &&	\
-	       script_next)						\
-		if (script_dirent.d_type != DT_DIR &&			\
-		    (script_dirent.d_type != DT_UNKNOWN ||		\
-		     !is_directory(lang_path, &script_dirent)))
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent)		\
+	while ((lang_dirent = readdir(scripts_dir)) != NULL)		\
+		if ((lang_dirent->d_type == DT_DIR ||			\
+		     (lang_dirent->d_type == DT_UNKNOWN &&		\
+		      is_directory(scripts_path, lang_dirent))) &&	\
+		    (strcmp(lang_dirent->d_name, ".")) &&		\
+		    (strcmp(lang_dirent->d_name, "..")))
+
+#define for_each_script(lang_path, lang_dir, script_dirent)		\
+	while ((script_dirent = readdir(lang_dir)) != NULL)		\
+		if (script_dirent->d_type != DT_DIR &&			\
+		    (script_dirent->d_type != DT_UNKNOWN ||		\
+		     !is_directory(lang_path, script_dirent)))
 
 
 #define RECORD_SUFFIX			"-record"
@@ -1575,7 +1573,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 				  const char *s __maybe_unused,
 				  int unset __maybe_unused)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	char script_path[MAXPATHLEN];
@@ -1590,19 +1588,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	if (!scripts_dir)
 		return -1;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			script_root = get_script_root(&script_dirent, REPORT_SUFFIX);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			script_root = get_script_root(script_dirent, REPORT_SUFFIX);
 			if (script_root) {
 				desc = script_desc__findnew(script_root);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				read_script_info(desc, script_path);
 				free(script_root);
 			}
@@ -1690,7 +1688,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
  */
 int find_scripts(char **scripts_array, char **scripts_path_array)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	struct perf_session *session;
@@ -1713,9 +1711,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		return -1;
 	}
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 #ifdef NO_LIBPERL
 		if (strstr(lang_path, "perl"))
 			continue;
@@ -1729,16 +1727,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+		for_each_script(lang_path, lang_dir, script_dirent) {
 			/* Skip those real time scripts: xxxtop.p[yl] */
-			if (strstr(script_dirent.d_name, "top."))
+			if (strstr(script_dirent->d_name, "top."))
 				continue;
 			sprintf(scripts_path_array[i], "%s/%s", lang_path,
-				script_dirent.d_name);
-			temp = strchr(script_dirent.d_name, '.');
+				script_dirent->d_name);
+			temp = strchr(script_dirent->d_name, '.');
 			snprintf(scripts_array[i],
-				(temp - script_dirent.d_name) + 1,
-				"%s", script_dirent.d_name);
+				(temp - script_dirent->d_name) + 1,
+				"%s", script_dirent->d_name);
 
 			if (check_ev_match(lang_path,
 					scripts_array[i], session))
@@ -1756,7 +1754,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 
 static char *get_script_path(const char *script_root, const char *suffix)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	char script_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
@@ -1769,21 +1767,21 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	if (!scripts_dir)
 		return NULL;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			__script_root = get_script_root(&script_dirent, suffix);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			__script_root = get_script_root(script_dirent, suffix);
 			if (__script_root && !strcmp(script_root, __script_root)) {
 				free(__script_root);
 				closedir(lang_dir);
 				closedir(scripts_dir);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				return strdup(script_path);
 			}
 			free(__script_root);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1f19f2f999c8..307e8a1a003c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -528,6 +528,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		perf_evlist__set_leader(evsel_list);
 
 	evlist__for_each(evsel_list, counter) {
+try_again:
 		if (create_perf_stat_counter(counter) < 0) {
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37
@@ -544,7 +545,11 @@ static int __run_perf_stat(int argc, const char **argv)
 				if ((counter->leader != counter) ||
 				    !(counter->leader->nr_members > 1))
 					continue;
-			}
+			} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+                                if (verbose)
+                                        ui__warning("%s\n", msg);
+                                goto try_again;
+                        }
 
 			perf_evsel__open_strerror(counter, &target,
 						  errno, msg, sizeof(msg));
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f7d7f5a1cad5..6f8f6430f2bf 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -268,6 +268,12 @@ else
     ifneq ($(feature-dwarf), 1)
       msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
       NO_DWARF := 1
+    else
+      ifneq ($(feature-dwarf_getlocations), 1)
+        msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
+      else
+        CFLAGS += -DHAVE_DWARF_GETLOCATIONS
+      endif # dwarf_getlocations
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 577e600c8eb1..aea189b41cc8 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -959,6 +959,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return 0;
 }
 
+#ifdef HAVE_DWARF_GETLOCATIONS
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE
@@ -1080,3 +1081,11 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 
 	return ret;
 }
+#else
+int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+		      Dwarf_Die *vr_die __maybe_unused,
+		      struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dad55d04ffdd..edcf4ed4e99c 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -433,7 +433,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	pid_t tgid, ppid;
 	int rc = 0;
 
@@ -462,11 +462,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		return 0;
 	}
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
+	while ((dirent = readdir(tasks)) != NULL) {
 		char *end;
 		pid_t _pid;
 
-		_pid = strtol(dirent.d_name, &end, 10);
+		_pid = strtol(dirent->d_name, &end, 10);
 		if (*end)
 			continue;
 
@@ -575,7 +575,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
@@ -600,9 +600,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (proc == NULL)
 		goto out_free_fork;
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 738ce226002b..645dc1828836 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2345,6 +2345,8 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
+	int paranoid;
+
 	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
 	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
@@ -2364,6 +2366,22 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 
 		zfree(&evsel->name);
 		return true;
+	} else if (err == EACCES && !evsel->attr.exclude_kernel &&
+		   (paranoid = perf_event_paranoid()) > 1) {
+		const char *name = perf_evsel__name(evsel);
+		char *new_name;
+
+		if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+			return false;
+
+		if (evsel->name)
+			free(evsel->name);
+		evsel->name = new_name;
+		scnprintf(msg, msgsize,
+"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid);
+		evsel->attr.exclude_kernel = 1;
+
+		return true;
 	}
 
 	return false;
@@ -2382,12 +2400,13 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
 		 "which controls use of the performance events system by\n"
 		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
-		 "The default value is 1:\n\n"
+		 "The current value is %d:\n\n"
 		 "  -1: Allow use of (almost) all events by all users\n"
 		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
 		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
 		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
-				 target->system_wide ? "system-wide " : "");
+				 target->system_wide ? "system-wide " : "",
+				 perf_event_paranoid());
 	case ENOENT:
 		return scnprintf(msg, size, "The %s event is not supported.",
 				 perf_evsel__name(evsel));
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4c19d5e79d8c..bcbc983d4b12 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-#define for_each_subsystem(sys_dir, sys_dirent, sys_next)	       \
-	while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next)	       \
-	if (sys_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(sys_dirent.d_name, ".")) &&				       \
-	   (strcmp(sys_dirent.d_name, "..")))
+#define for_each_subsystem(sys_dir, sys_dirent)			\
+	while ((sys_dirent = readdir(sys_dir)) != NULL)		\
+		if (sys_dirent->d_type == DT_DIR &&		\
+		    (strcmp(sys_dirent->d_name, ".")) &&	\
+		    (strcmp(sys_dirent->d_name, "..")))
 
 static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 {
@@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next)	       \
-	while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next)        \
-	if (evt_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(evt_dirent.d_name, ".")) &&				       \
-	   (strcmp(evt_dirent.d_name, "..")) &&				       \
-	   (!tp_event_has_id(&sys_dirent, &evt_dirent)))
+#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
+		if (evt_dirent->d_type == DT_DIR &&		\
+		    (strcmp(evt_dirent->d_name, ".")) &&	\
+		    (strcmp(evt_dirent->d_name, "..")) &&	\
+		    (!tp_event_has_id(sys_dirent, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 {
 	struct tracepoint_path *path = NULL;
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char id_buf[24];
 	int fd;
 	u64 id;
@@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	if (!sys_dir)
 		return NULL;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 
 			snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
-				 evt_dirent.d_name);
+				 evt_dirent->d_name);
 			fd = open(evt_path, O_RDONLY);
 			if (fd < 0)
 				continue;
@@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 					free(path);
 					return NULL;
 				}
-				strncpy(path->system, sys_dirent.d_name,
+				strncpy(path->system, sys_dirent->d_name,
 					MAX_EVENT_LENGTH);
-				strncpy(path->name, evt_dirent.d_name,
+				strncpy(path->name, evt_dirent->d_name,
 					MAX_EVENT_LENGTH);
 				return path;
 			}
@@ -1812,7 +1812,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 	char **evt_list = NULL;
@@ -1830,20 +1830,20 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			goto out_close_sys_dir;
 	}
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 		if (subsys_glob != NULL &&
-		    !strglobmatch(sys_dirent.d_name, subsys_glob))
+		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
-			    !strglobmatch(evt_dirent.d_name, event_glob))
+			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
 
 			if (!evt_num_known) {
@@ -1852,7 +1852,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			}
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
 			if (evt_list[evt_i] == NULL)
@@ -1905,7 +1905,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 int is_valid_tracepoint(const char *event_string)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 
@@ -1913,17 +1913,17 @@ int is_valid_tracepoint(const char *event_string)
 	if (!sys_dir)
 		return 0;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
 				closedir(evt_dir);
 				closedir(sys_dir);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 47966a1618c7..f5ba111cd9fb 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2445,6 +2445,9 @@ static char *prefix_if_not_in(const char *pre, char *str)
 
 static char *setup_overhead(char *keys)
 {
+	if (sort__mode == SORT_MODE__DIFF)
+		return keys;
+
 	keys = prefix_if_not_in("overhead", keys);
 
 	if (symbol_conf.cumulate_callchain)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 08afc6909953..267112b4e3db 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -94,7 +94,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	DIR *proc;
 	int max_threads = 32, items, i;
 	char path[256];
-	struct dirent dirent, *next, **namelist = NULL;
+	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);
 
 	if (threads == NULL)
@@ -107,16 +107,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	threads->nr = 0;
 	atomic_set(&threads->refcnt, 1);
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
 		struct stat st;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
 		if (stat(path, &st) != 0)
 			continue;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-05-06 11:26 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-05-06 11:26 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 8482716b9d865db34c55d4bf2fed19498e7195b9 perf/x86/amd/iommu: Do not register a task ctx for uncore like PMUs

This tree contains two fixes: new Intel CPU model numbers and an AMD/iommu uncore 
PMU driver fix.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86: Add model numbers for Kabylake CPUs

Peter Zijlstra (1):
      perf/x86/amd/iommu: Do not register a task ctx for uncore like PMUs


 arch/x86/events/amd/iommu.c  | 1 +
 arch/x86/events/intel/core.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 40625ca7a190..6011a573dd64 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -474,6 +474,7 @@ static __init int _init_perf_amd_iommu(
 
 static struct perf_amd_iommu __perf_iommu = {
 	.pmu = {
+		.task_ctx_nr    = perf_invalid_context,
 		.event_init	= perf_iommu_event_init,
 		.add		= perf_iommu_add,
 		.del		= perf_iommu_del,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index aff79884e17d..a6fd4dbcf820 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3637,6 +3637,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Knights Landing events, ");
 		break;
 
+	case 142: /* 14nm Kabylake Mobile */
+	case 158: /* 14nm Kabylake Desktop */
 	case 78: /* 14nm Skylake Mobile */
 	case 94: /* 14nm Skylake Desktop */
 	case 85: /* 14nm Skylake Server */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-04-28 17:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-04-28 17:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: cf3beb7c90a8efa16a06b26634cddddc92bb819c perf/x86/intel: Fix incorrect lbr_sel_mask value

x86 PMU driver fixes plus a core code race fix.

 Thanks,

	Ingo

------------------>
Adam Borowski (1):
      perf/x86/amd: Set the size of event map array to PERF_COUNT_HW_MAX

Alexander Shishkin (1):
      perf/x86/intel/pt: Don't die on VMXON

Andi Kleen (1):
      perf/x86/intel: Add model number for Skylake Server to perf

Kan Liang (1):
      perf/x86/intel: Fix incorrect lbr_sel_mask value

Peter Zijlstra (2):
      perf/core: Make sysctl_perf_cpu_time_max_percent conform to documentation
      perf/core: Fix perf_event_open() vs. execve() race

Srinivas Pandruvada (1):
      perf/x86/intel/rapl: Add missing Haswell model


 arch/x86/events/amd/core.c        |  2 +-
 arch/x86/events/intel/core.c      |  1 +
 arch/x86/events/intel/lbr.c       |  6 ++--
 arch/x86/events/intel/pt.c        | 75 +++++++++++++++++++++++++++++++++------
 arch/x86/events/intel/pt.h        |  3 ++
 arch/x86/events/intel/rapl.c      |  1 +
 arch/x86/include/asm/perf_event.h |  4 +++
 arch/x86/kvm/vmx.c                |  4 +++
 kernel/events/core.c              | 55 +++++++++++++++++++---------
 9 files changed, 120 insertions(+), 31 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 86a9bec18dab..bd3e8421b57c 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -115,7 +115,7 @@ static __initconst const u64 amd_hw_cache_event_ids
 /*
  * AMD Performance Monitor K7 and later.
  */
-static const u64 amd_perfmon_event_map[] =
+static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
   [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
   [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 68fa55b4d42e..aff79884e17d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3639,6 +3639,7 @@ __init int intel_pmu_init(void)
 
 	case 78: /* 14nm Skylake Mobile */
 	case 94: /* 14nm Skylake Desktop */
+	case 85: /* 14nm Skylake Server */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 6c3b7c1780c9..1ca5d1e7d4f2 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -63,7 +63,7 @@ static enum {
 
 #define LBR_PLM (LBR_KERNEL | LBR_USER)
 
-#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */
+#define LBR_SEL_MASK	0x3ff	/* valid bits in LBR_SELECT */
 #define LBR_NOT_SUPP	-1	/* LBR filter not supported */
 #define LBR_IGN		0	/* ignored */
 
@@ -610,8 +610,10 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
 	 * in suppress mode. So LBR_SELECT should be set to
 	 * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK)
+	 * But the 10th bit LBR_CALL_STACK does not operate
+	 * in suppress mode.
 	 */
-	reg->config = mask ^ x86_pmu.lbr_sel_mask;
+	reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK);
 
 	if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
 	    (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 6af7cf71d6b2..09a77dbc73c9 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -136,9 +136,21 @@ static int __init pt_pmu_hw_init(void)
 	struct dev_ext_attribute *de_attrs;
 	struct attribute **attrs;
 	size_t size;
+	u64 reg;
 	int ret;
 	long i;
 
+	if (boot_cpu_has(X86_FEATURE_VMX)) {
+		/*
+		 * Intel SDM, 36.5 "Tracing post-VMXON" says that
+		 * "IA32_VMX_MISC[bit 14]" being 1 means PT can trace
+		 * post-VMXON.
+		 */
+		rdmsrl(MSR_IA32_VMX_MISC, reg);
+		if (reg & BIT(14))
+			pt_pmu.vmx = true;
+	}
+
 	attrs = NULL;
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
@@ -269,20 +281,23 @@ static void pt_config(struct perf_event *event)
 
 	reg |= (event->attr.config & PT_CONFIG_MASK);
 
+	event->hw.config = reg;
 	wrmsrl(MSR_IA32_RTIT_CTL, reg);
 }
 
-static void pt_config_start(bool start)
+static void pt_config_stop(struct perf_event *event)
 {
-	u64 ctl;
+	u64 ctl = READ_ONCE(event->hw.config);
+
+	/* may be already stopped by a PMI */
+	if (!(ctl & RTIT_CTL_TRACEEN))
+		return;
 
-	rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-	if (start)
-		ctl |= RTIT_CTL_TRACEEN;
-	else
-		ctl &= ~RTIT_CTL_TRACEEN;
+	ctl &= ~RTIT_CTL_TRACEEN;
 	wrmsrl(MSR_IA32_RTIT_CTL, ctl);
 
+	WRITE_ONCE(event->hw.config, ctl);
+
 	/*
 	 * A wrmsr that disables trace generation serializes other PT
 	 * registers and causes all data packets to be written to memory,
@@ -291,8 +306,7 @@ static void pt_config_start(bool start)
 	 * The below WMB, separating data store and aux_head store matches
 	 * the consumer's RMB that separates aux_head load and data load.
 	 */
-	if (!start)
-		wmb();
+	wmb();
 }
 
 static void pt_config_buffer(void *buf, unsigned int topa_idx,
@@ -942,11 +956,17 @@ void intel_pt_interrupt(void)
 	if (!ACCESS_ONCE(pt->handle_nmi))
 		return;
 
-	pt_config_start(false);
+	/*
+	 * If VMX is on and PT does not support it, don't touch anything.
+	 */
+	if (READ_ONCE(pt->vmx_on))
+		return;
 
 	if (!event)
 		return;
 
+	pt_config_stop(event);
+
 	buf = perf_get_aux(&pt->handle);
 	if (!buf)
 		return;
@@ -983,6 +1003,35 @@ void intel_pt_interrupt(void)
 	}
 }
 
+void intel_pt_handle_vmx(int on)
+{
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	struct perf_event *event;
+	unsigned long flags;
+
+	/* PT plays nice with VMX, do nothing */
+	if (pt_pmu.vmx)
+		return;
+
+	/*
+	 * VMXON will clear RTIT_CTL.TraceEn; we need to make
+	 * sure to not try to set it while VMX is on. Disable
+	 * interrupts to avoid racing with pmu callbacks;
+	 * concurrent PMI should be handled fine.
+	 */
+	local_irq_save(flags);
+	WRITE_ONCE(pt->vmx_on, on);
+
+	if (on) {
+		/* prevent pt_config_stop() from writing RTIT_CTL */
+		event = pt->handle.event;
+		if (event)
+			event->hw.config = 0;
+	}
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);
+
 /*
  * PMU callbacks
  */
@@ -992,6 +1041,9 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
+	if (READ_ONCE(pt->vmx_on))
+		return;
+
 	if (!buf || pt_buffer_is_full(buf, pt)) {
 		event->hw.state = PERF_HES_STOPPED;
 		return;
@@ -1014,7 +1066,8 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	 * see comment in intel_pt_interrupt().
 	 */
 	ACCESS_ONCE(pt->handle_nmi) = 0;
-	pt_config_start(false);
+
+	pt_config_stop(event);
 
 	if (event->hw.state == PERF_HES_STOPPED)
 		return;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 336878a5d205..3abb5f5cccc8 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -65,6 +65,7 @@ enum pt_capabilities {
 struct pt_pmu {
 	struct pmu		pmu;
 	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
+	bool			vmx;
 };
 
 /**
@@ -107,10 +108,12 @@ struct pt_buffer {
  * struct pt - per-cpu pt context
  * @handle:	perf output handle
  * @handle_nmi:	do handle PT PMI on this cpu, there's an active event
+ * @vmx_on:	1 if VMX is ON on this cpu
  */
 struct pt {
 	struct perf_output_handle handle;
 	int			handle_nmi;
+	int			vmx_on;
 };
 
 #endif /* __INTEL_PT_H__ */
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 70c93f9b03ac..1705c9d75e44 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -718,6 +718,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 70: /* Haswell GT3e */
 	case 61: /* Broadwell */
 	case 71: /* Broadwell-H */
 		rapl_cntr_mask = RAPL_IDX_HSW;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 5a2ed3ed2f26..f353061bba1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -285,6 +285,10 @@ static inline void perf_events_lapic_init(void)	{ }
 static inline void perf_check_microcode(void) { }
 #endif
 
+#ifdef CONFIG_CPU_SUP_INTEL
+ extern void intel_pt_handle_vmx(int on);
+#endif
+
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
  extern void amd_pmu_enable_virt(void);
  extern void amd_pmu_disable_virt(void);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ee1c8a93871c..133679d520af 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3103,6 +3103,8 @@ static __init int vmx_disabled_by_bios(void)
 
 static void kvm_cpu_vmxon(u64 addr)
 {
+	intel_pt_handle_vmx(1);
+
 	asm volatile (ASM_VMX_VMXON_RAX
 			: : "a"(&addr), "m"(addr)
 			: "memory", "cc");
@@ -3172,6 +3174,8 @@ static void vmclear_local_loaded_vmcss(void)
 static void kvm_cpu_vmxoff(void)
 {
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
+
+	intel_pt_handle_vmx(0);
 }
 
 static void hardware_disable(void)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 52bedc5a5aaa..4e2ebf6f2f1f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -412,7 +412,8 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 	if (ret || !write)
 		return ret;
 
-	if (sysctl_perf_cpu_time_max_percent == 100) {
+	if (sysctl_perf_cpu_time_max_percent == 100 ||
+	    sysctl_perf_cpu_time_max_percent == 0) {
 		printk(KERN_WARNING
 		       "perf: Dynamic interrupt throttling disabled, can hang your system!\n");
 		WRITE_ONCE(perf_sample_allowed_ns, 0);
@@ -1105,6 +1106,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
+ *    cred_guard_mutex
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event::child_mutex;
@@ -3420,7 +3422,6 @@ static struct task_struct *
 find_lively_task_by_vpid(pid_t vpid)
 {
 	struct task_struct *task;
-	int err;
 
 	rcu_read_lock();
 	if (!vpid)
@@ -3434,16 +3435,7 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/* Reuse ptrace permission checks for now. */
-	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
-		goto errout;
-
 	return task;
-errout:
-	put_task_struct(task);
-	return ERR_PTR(err);
-
 }
 
 /*
@@ -8413,6 +8405,24 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	get_online_cpus();
 
+	if (task) {
+		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+		if (err)
+			goto err_cpus;
+
+		/*
+		 * Reuse ptrace permission checks for now.
+		 *
+		 * We must hold cred_guard_mutex across this and any potential
+		 * perf_install_in_context() call for this new event to
+		 * serialize against exec() altering our credentials (and the
+		 * perf_event_exit_task() that could imply).
+		 */
+		err = -EACCES;
+		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+			goto err_cred;
+	}
+
 	if (flags & PERF_FLAG_PID_CGROUP)
 		cgroup_fd = pid;
 
@@ -8420,7 +8430,7 @@ SYSCALL_DEFINE5(perf_event_open,
 				 NULL, NULL, cgroup_fd);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_cpus;
+		goto err_cred;
 	}
 
 	if (is_sampling_event(event)) {
@@ -8479,11 +8489,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
-	if (task) {
-		put_task_struct(task);
-		task = NULL;
-	}
-
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -8581,6 +8586,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 
+	/*
+	 * This is the point on no return; we cannot fail hereafter. This is
+	 * where we start modifying current state.
+	 */
+
 	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
@@ -8652,6 +8662,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		mutex_unlock(&gctx->mutex);
 	mutex_unlock(&ctx->mutex);
 
+	if (task) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		put_task_struct(task);
+	}
+
 	put_online_cpus();
 
 	mutex_lock(&current->perf_event_mutex);
@@ -8684,6 +8699,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	 */
 	if (!event_file)
 		free_event(event);
+err_cred:
+	if (task)
+		mutex_unlock(&task->signal->cred_guard_mutex);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8968,6 +8986,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 
 /*
  * When a child task exits, feed back event values to parent events.
+ *
+ * Can be called with cred_guard_mutex held when called from
+ * install_exec_creds().
  */
 void perf_event_exit_task(struct task_struct *child)
 {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-04-03 11:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-04-03 11:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 85dc600263c2291cea33bffa90038808ee64198b perf/x86/amd/ibs: Fix pmu::stop() nesting

Misc kernel side fixes: 

 - fix event leak
 - fix AMD PMU driver bug
 - fix core event handling bug
 - fix build bug on certain randconfigs

Plus misc tooling fixes.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Don't leak event in the syscall error path

Andres Freund (1):
      perf hists: Fix determination of a callchain node's childlessness

Anton Blanchard (1):
      perf jit: genelf makes assumptions about endian

Arnaldo Carvalho de Melo (3):
      perf tests: Fix tarpkg build test error output redirection
      perf bench: Fix detached tarball building due to missing 'perf bench memcpy' headers
      perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples

Huang Rui (1):
      perf/x86: Move events_sysfs_show() outside CPU_SUP_INTEL

Peter Zijlstra (2):
      perf/core: Fix time tracking bug with multiplexing
      perf/x86/amd/ibs: Fix pmu::stop() nesting

Sukadev Bhattiprolu (1):
      perf tools: Fix build break on powerpc


 arch/x86/events/amd/ibs.c             | 52 ++++++++++++++++++++++++++++++-----
 arch/x86/events/perf_event.h          |  6 ++--
 kernel/events/core.c                  | 15 ++++++++--
 tools/perf/MANIFEST                   |  1 +
 tools/perf/arch/powerpc/util/header.c |  2 ++
 tools/perf/tests/perf-targz-src-pkg   |  2 +-
 tools/perf/ui/browsers/hists.c        |  2 +-
 tools/perf/util/event.c               | 23 +++++++++++-----
 tools/perf/util/genelf.h              | 24 +++++++---------
 tools/perf/util/intel-bts.c           |  1 +
 tools/perf/util/intel-pt.c            |  3 ++
 tools/perf/util/jitdump.c             |  2 ++
 12 files changed, 98 insertions(+), 35 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 3ea25c3917c0..feb90f6730e8 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -28,10 +28,46 @@ static u32 ibs_caps;
 #define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
 #define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
 
+
+/*
+ * IBS states:
+ *
+ * ENABLED; tracks the pmu::add(), pmu::del() state, when set the counter is taken
+ * and any further add()s must fail.
+ *
+ * STARTED/STOPPING/STOPPED; deal with pmu::start(), pmu::stop() state but are
+ * complicated by the fact that the IBS hardware can send late NMIs (ie. after
+ * we've cleared the EN bit).
+ *
+ * In order to consume these late NMIs we have the STOPPED state, any NMI that
+ * happens after we've cleared the EN state will clear this bit and report the
+ * NMI handled (this is fundamentally racy in the face or multiple NMI sources,
+ * someone else can consume our BIT and our NMI will go unhandled).
+ *
+ * And since we cannot set/clear this separate bit together with the EN bit,
+ * there are races; if we cleared STARTED early, an NMI could land in
+ * between clearing STARTED and clearing the EN bit (in fact multiple NMIs
+ * could happen if the period is small enough), and consume our STOPPED bit
+ * and trigger streams of unhandled NMIs.
+ *
+ * If, however, we clear STARTED late, an NMI can hit between clearing the
+ * EN bit and clearing STARTED, still see STARTED set and process the event.
+ * If this event will have the VALID bit clear, we bail properly, but this
+ * is not a given. With VALID set we can end up calling pmu::stop() again
+ * (the throttle logic) and trigger the WARNs in there.
+ *
+ * So what we do is set STOPPING before clearing EN to avoid the pmu::stop()
+ * nesting, and clear STARTED late, so that we have a well defined state over
+ * the clearing of the EN bit.
+ *
+ * XXX: we could probably be using !atomic bitops for all this.
+ */
+
 enum ibs_states {
 	IBS_ENABLED	= 0,
 	IBS_STARTED	= 1,
 	IBS_STOPPING	= 2,
+	IBS_STOPPED	= 3,
 
 	IBS_MAX_STATES,
 };
@@ -377,11 +413,10 @@ static void perf_ibs_start(struct perf_event *event, int flags)
 
 	perf_ibs_set_period(perf_ibs, hwc, &period);
 	/*
-	 * Set STARTED before enabling the hardware, such that
-	 * a subsequent NMI must observe it. Then clear STOPPING
-	 * such that we don't consume NMIs by accident.
+	 * Set STARTED before enabling the hardware, such that a subsequent NMI
+	 * must observe it.
 	 */
-	set_bit(IBS_STARTED, pcpu->state);
+	set_bit(IBS_STARTED,    pcpu->state);
 	clear_bit(IBS_STOPPING, pcpu->state);
 	perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
 
@@ -396,6 +431,9 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
 	u64 config;
 	int stopping;
 
+	if (test_and_set_bit(IBS_STOPPING, pcpu->state))
+		return;
+
 	stopping = test_bit(IBS_STARTED, pcpu->state);
 
 	if (!stopping && (hwc->state & PERF_HES_UPTODATE))
@@ -405,12 +443,12 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
 
 	if (stopping) {
 		/*
-		 * Set STOPPING before disabling the hardware, such that it
+		 * Set STOPPED before disabling the hardware, such that it
 		 * must be visible to NMIs the moment we clear the EN bit,
 		 * at which point we can generate an !VALID sample which
 		 * we need to consume.
 		 */
-		set_bit(IBS_STOPPING, pcpu->state);
+		set_bit(IBS_STOPPED, pcpu->state);
 		perf_ibs_disable_event(perf_ibs, hwc, config);
 		/*
 		 * Clear STARTED after disabling the hardware; if it were
@@ -556,7 +594,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 		 * with samples that even have the valid bit cleared.
 		 * Mark all this NMIs as handled.
 		 */
-		if (test_and_clear_bit(IBS_STOPPING, pcpu->state))
+		if (test_and_clear_bit(IBS_STOPPED, pcpu->state))
 			return 1;
 
 		return 0;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba6ef18528c9..a6771e2303d2 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -795,6 +795,9 @@ ssize_t intel_event_sysfs_show(char *page, u64 config);
 
 struct attribute **merge_attr(struct attribute **a, struct attribute **b);
 
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
@@ -925,9 +928,6 @@ int p6_pmu_init(void);
 
 int knc_pmu_init(void);
 
-ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
-			  char *page);
-
 static inline int is_ht_workaround_enabled(void)
 {
 	return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index de24fbce5277..52bedc5a5aaa 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2417,14 +2417,24 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 			cpuctx->task_ctx = NULL;
 	}
 
-	is_active ^= ctx->is_active; /* changed bits */
-
+	/*
+	 * Always update time if it was set; not only when it changes.
+	 * Otherwise we can 'forget' to update time for any but the last
+	 * context we sched out. For example:
+	 *
+	 *   ctx_sched_out(.event_type = EVENT_FLEXIBLE)
+	 *   ctx_sched_out(.event_type = EVENT_PINNED)
+	 *
+	 * would only update time for the pinned events.
+	 */
 	if (is_active & EVENT_TIME) {
 		/* update (and stop) ctx time */
 		update_context_time(ctx);
 		update_cgrp_time_from_cpuctx(cpuctx);
 	}
 
+	is_active ^= ctx->is_active; /* changed bits */
+
 	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
@@ -8532,6 +8542,7 @@ SYSCALL_DEFINE5(perf_event_open,
 					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
+		event_file = NULL;
 		goto err_context;
 	}
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 2e1fa2357528..8c8c6b9ce915 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -74,6 +74,7 @@ arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
 arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
+arch/*/include/asm/*features.h
 include/linux/poison.h
 include/linux/hw_breakpoint.h
 include/uapi/linux/perf_event.h
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 6138bdef6e63..f8ccee132867 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -4,6 +4,8 @@
 #include <stdlib.h>
 #include <string.h>
 #include <linux/stringify.h>
+#include "header.h"
+#include "util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
index 238aa3927c71..f2d9c5fe58e0 100755
--- a/tools/perf/tests/perf-targz-src-pkg
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -15,7 +15,7 @@ TMP_DEST=$(mktemp -d)
 tar xf ${TARBALL} -C $TMP_DEST
 rm -f ${TARBALL}
 cd - > /dev/null
-make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+make -C $TMP_DEST/perf*/tools/perf > /dev/null
 RC=$?
 rm -rf ${TMP_DEST}
 exit $RC
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 4b9816555946..2a83414159a6 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -337,7 +337,7 @@ static void callchain_node__init_have_children(struct callchain_node *node,
 	chain = list_entry(node->val.next, struct callchain_list, list);
 	chain->has_children = has_sibling;
 
-	if (node->val.next != node->val.prev) {
+	if (!list_empty(&node->val)) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
 	}
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 52cf479bc593..dad55d04ffdd 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -56,13 +56,22 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-static struct perf_sample synth_sample = {
+static int perf_tool__process_synth_event(struct perf_tool *tool,
+					  union perf_event *event,
+					  struct machine *machine,
+					  perf_event__handler_t process)
+{
+	struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
 	.time	   = -1,
 	.stream_id = -1,
 	.cpu	   = -1,
 	.period	   = 1,
+	.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
+	};
+
+	return process(tool, event, &synth_sample, machine);
 };
 
 /*
@@ -186,7 +195,7 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
 		return -1;
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return tgid;
@@ -218,7 +227,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return 0;
@@ -344,7 +353,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;
 
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -402,7 +411,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 
 		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -472,7 +481,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		/*
 		 * Send the prepared comm event
 		 */
-		if (process(tool, comm_event, &synth_sample, machine) != 0)
+		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
 			break;
 
 		rc = 0;
@@ -701,7 +710,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
 
-	err = process(tool, event, &synth_sample, machine);
+	err = perf_tool__process_synth_event(tool, event, machine, process);
 	free(event);
 
 	return err;
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index cd67e64a0494..2fbeb59c4bdd 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -9,36 +9,32 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 
 #if   defined(__arm__)
 #define GEN_ELF_ARCH	EM_ARM
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS32
 #elif defined(__aarch64__)
 #define GEN_ELF_ARCH	EM_AARCH64
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS64
 #elif defined(__x86_64__)
 #define GEN_ELF_ARCH	EM_X86_64
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS64
 #elif defined(__i386__)
 #define GEN_ELF_ARCH	EM_386
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS32
-#elif defined(__ppcle__)
-#define GEN_ELF_ARCH	EM_PPC
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
-#define GEN_ELF_CLASS	ELFCLASS64
-#elif defined(__powerpc__)
-#define GEN_ELF_ARCH	EM_PPC64
-#define GEN_ELF_ENDIAN	ELFDATA2MSB
-#define GEN_ELF_CLASS	ELFCLASS64
-#elif defined(__powerpcle__)
+#elif defined(__powerpc64__)
 #define GEN_ELF_ARCH	EM_PPC64
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__powerpc__)
+#define GEN_ELF_ARCH	EM_PPC
+#define GEN_ELF_CLASS	ELFCLASS32
 #else
 #error "unsupported architecture"
 #endif
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define GEN_ELF_ENDIAN	ELFDATA2MSB
+#else
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#endif
+
 #if GEN_ELF_CLASS == ELFCLASS64
 #define elf_newehdr	elf64_newehdr
 #define elf_getshdr	elf64_getshdr
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 6bc3ecd2e7ca..abf1366e2a24 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -279,6 +279,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	event.sample.header.misc = PERF_RECORD_MISC_USER;
 	event.sample.header.size = sizeof(struct perf_event_header);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 05d815851be1..407f11b97c8d 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -979,6 +979,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1035,6 +1036,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1092,6 +1094,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index cd272cc21e05..ad0c0bb1fbc7 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -417,6 +417,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	 * use first address as sample address
 	 */
 	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.pid  = pid;
 	sample.tid  = tid;
 	sample.time = id->time;
@@ -505,6 +506,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 	 * use first address as sample address
 	 */
 	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.pid  = pid;
 	sample.tid  = tid;
 	sample.time = id->time;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-02-20 11:14 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-02-20 11:14 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 059fcd8cd16622da6513804a7a3e826d152c6c96 perf/core: Plug potential memory leak in CPU_UP_PREPARE

A handful of CPU hotplug related fixes.

 Thanks,

	Ingo

------------------>
Thomas Gleixner (4):
      perf/x86/amd/uncore: Plug reference leak
      perf/core: Remove bogus UP_CANCELED hotplug state
      perf/core: Remove the bogus and dangerous CPU_DOWN_FAILED hotplug state
      perf/core: Plug potential memory leak in CPU_UP_PREPARE


 arch/x86/kernel/cpu/perf_event_amd_uncore.c | 2 ++
 kernel/events/core.c                        | 4 +---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 49742746a6c9..8836fc9fa84b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -323,6 +323,8 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 	return 0;
 
 fail:
+	if (amd_uncore_nb)
+		*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
 	kfree(uncore_nb);
 	return -ENOMEM;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5946460b2425..0d58522103cd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9206,7 +9206,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0) {
+	if (swhash->hlist_refcount > 0 && !swevent_hlist_deref(swhash)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -9282,11 +9282,9 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
-	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
 		perf_event_exit_cpu(cpu);
 		break;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-01-14 10:03 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-01-14 10:03 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton,
	Arnaldo Carvalho de Melo, Jiri Olsa

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c36608843adf4674c462e49f63b64b2987d0ba0b Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling fixes, the biggest patch is one that decouples the kernel's list.h from 
tooling list.h.

 Thanks,

	Ingo

------------------>
Jiri Olsa (5):
      tools: Add clean targets for tools directory
      tools bpf: Add *.cmd files clean up
      tools lockdep: Add *.cmd files clean up
      perf tools: Add missing sources to perf's MANIFEST
      perf stat: Fix recort_usage typo

Josh Poimboeuf (3):
      tools: Make list.h self-sufficient
      tools: Fix formatting of the "make -C tools" help message
      tools subcmd: Add missing NORETURN define for parse-options.h

Namhyung Kim (6):
      perf record: Add --buildid-all option
      perf tools: Add more usage tips
      perf tools: Add file_only config option to strlist
      perf tools: Set and pass DOCDIR to builtin-report.c
      perf ui/tui: Print helpline message as is
      perf tools: Fallback to srcdir/Documentation/tips.txt

Naveen N. Rao (1):
      perf bpf: Fix build breakage due to libbpf

Wang Nan (8):
      perf tools: Add -lutil in python lib list for broken python-config
      perf tools: Fix phony build target for build-test
      perf tools: Fix PowerPC native building
      tools: Move Makefile.arch from perf/config to tools/scripts
      tools build: Add BPF feature check to test-all
      perf test: Fix false TEST_OK result for 'perf test hist'
      perf test: Reset err after using it hold errcode in hist testcases
      perf tools: Fix mmap2 event allocation in synthesize code


 tools/Makefile                               |  43 +-
 tools/build/feature/test-all.c               |   5 +
 tools/build/feature/test-bpf.c               |  20 +-
 tools/include/linux/list.h                   | 753 ++++++++++++++++++++++++++-
 tools/lib/bpf/Makefile                       |  18 +-
 tools/lib/bpf/bpf.c                          |   4 +-
 tools/lib/lockdep/Makefile                   |   2 +-
 tools/lib/subcmd/parse-options.h             |   4 +
 tools/perf/Build                             |   1 +
 tools/perf/Documentation/perf-record.txt     |   3 +
 tools/perf/Documentation/tips.txt            |  15 +
 tools/perf/MANIFEST                          |   2 +
 tools/perf/builtin-record.c                  |  26 +-
 tools/perf/builtin-report.c                  |  10 +-
 tools/perf/builtin-stat.c                    |   8 +-
 tools/perf/config/Makefile                   |   7 +-
 tools/perf/tests/hists_common.c              |   5 -
 tools/perf/tests/hists_cumulate.c            |   1 +
 tools/perf/tests/hists_filter.c              |   1 +
 tools/perf/tests/hists_link.c                |   1 +
 tools/perf/tests/hists_output.c              |   1 +
 tools/perf/tests/make                        |  18 +-
 tools/perf/ui/browsers/hists.c               |   2 +-
 tools/perf/util/event.c                      |   4 +-
 tools/perf/util/strlist.c                    |   8 +
 tools/perf/util/strlist.h                    |   9 +-
 tools/perf/util/util.c                       |  11 +-
 tools/{perf/config => scripts}/Makefile.arch |   0
 28 files changed, 917 insertions(+), 65 deletions(-)
 rename tools/{perf/config => scripts}/Makefile.arch (100%)

diff --git a/tools/Makefile b/tools/Makefile
index 0ba0df3b516f..09ec69db4bc8 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -8,23 +8,23 @@ include scripts/Makefile.include
 help:
 	@echo 'Possible targets:'
 	@echo ''
-	@echo '  acpi       - ACPI tools'
-	@echo '  cgroup     - cgroup tools'
-	@echo '  cpupower   - a tool for all things x86 CPU power'
-	@echo '  firewire   - the userspace part of nosy, an IEEE-1394 traffic sniffer'
-	@echo '  hv         - tools used when in Hyper-V clients'
-	@echo '  iio        - IIO tools'
-	@echo '  lguest     - a minimal 32-bit x86 hypervisor'
-	@echo '  perf       - Linux performance measurement and analysis tool'
-	@echo '  selftests  - various kernel selftests'
-	@echo '  turbostat  - Intel CPU idle stats and freq reporting tool'
-	@echo '  usb        - USB testing tools'
-	@echo '  virtio     - vhost test module'
-	@echo '  net        - misc networking tools'
-	@echo '  vm         - misc vm tools'
+	@echo '  acpi                   - ACPI tools'
+	@echo '  cgroup                 - cgroup tools'
+	@echo '  cpupower               - a tool for all things x86 CPU power'
+	@echo '  firewire               - the userspace part of nosy, an IEEE-1394 traffic sniffer'
+	@echo '  freefall               - laptop accelerometer program for disk protection'
+	@echo '  hv                     - tools used when in Hyper-V clients'
+	@echo '  iio                    - IIO tools'
+	@echo '  lguest                 - a minimal 32-bit x86 hypervisor'
+	@echo '  net                    - misc networking tools'
+	@echo '  perf                   - Linux performance measurement and analysis tool'
+	@echo '  selftests              - various kernel selftests'
+	@echo '  tmon                   - thermal monitoring and tuning tool'
+	@echo '  turbostat              - Intel CPU idle stats and freq reporting tool'
+	@echo '  usb                    - USB testing tools'
+	@echo '  virtio                 - vhost test module'
+	@echo '  vm                     - misc vm tools'
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
-	@echo '  tmon       - thermal monitoring and tuning tool'
-	@echo '  freefall   - laptop accelerometer program for disk protection'
 	@echo ''
 	@echo 'You can do:'
 	@echo ' $$ make -C tools/ <tool>_install'
@@ -127,6 +127,12 @@ install: acpi_install cgroup_install cpupower_install hv_install firewire_instal
 libapi_clean:
 	$(call descend,lib/api,clean)
 
+libbpf_clean:
+	$(call descend,lib/bpf,clean)
+
+libsubcmd_clean:
+	$(call descend,lib/subcmd,clean)
+
 perf_clean:
 	$(call descend,$(@:_clean=),clean)
 
@@ -142,9 +148,12 @@ install: acpi_install cgroup_install cpupower_install hv_install firewire_instal
 freefall_clean:
 	$(call descend,laptop/freefall,clean)
 
+build_clean:
+	$(call descend,build,clean)
+
 clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \
 		perf_clean selftests_clean turbostat_clean usb_clean virtio_clean \
 		vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
-		freefall_clean
+		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean
 
 .PHONY: FORCE
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 33cf6f20bd4e..81025cade45f 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -125,6 +125,10 @@
 # include "test-get_cpuid.c"
 #undef main
 
+#define main main_test_bpf
+# include "test-bpf.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -153,6 +157,7 @@ int main(int argc, char *argv[])
 	main_test_pthread_attr_setaffinity_np();
 	main_test_lzma();
 	main_test_get_cpuid();
+	main_test_bpf();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c
index 062bac811af9..b389026839b9 100644
--- a/tools/build/feature/test-bpf.c
+++ b/tools/build/feature/test-bpf.c
@@ -1,9 +1,23 @@
+#include <asm/unistd.h>
 #include <linux/bpf.h>
+#include <unistd.h>
+
+#ifndef __NR_bpf
+# if defined(__i386__)
+#  define __NR_bpf 357
+# elif defined(__x86_64__)
+#  define __NR_bpf 321
+# elif defined(__aarch64__)
+#  define __NR_bpf 280
+#  error __NR_bpf not defined. libbpf does not support your arch.
+# endif
+#endif
 
 int main(void)
 {
 	union bpf_attr attr;
 
+	/* Check fields in attr */
 	attr.prog_type = BPF_PROG_TYPE_KPROBE;
 	attr.insn_cnt = 0;
 	attr.insns = 0;
@@ -14,5 +28,9 @@ int main(void)
 	attr.kern_version = 0;
 
 	attr = attr;
-	return 0;
+	/*
+	 * Test existence of __NR_bpf and BPF_PROG_LOAD.
+	 * This call should fail if we run the testcase.
+	 */
+	return syscall(__NR_bpf, BPF_PROG_LOAD, attr, sizeof(attr));
 }
diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h
index a017f1595676..1da423820ad4 100644
--- a/tools/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,11 +1,751 @@
-#include <linux/compiler.h>
-#include <linux/kernel.h>
+#ifndef __TOOLS_LINUX_LIST_H
+#define __TOOLS_LINUX_LIST_H
+
 #include <linux/types.h>
+#include <linux/poison.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+
+/*
+ * Simple doubly linked list implementation.
+ *
+ * Some of the internal functions ("__xxx") are useful when
+ * manipulating whole lists rather than single entries, as
+ * sometimes we already know the next/prev entries and we can
+ * generate better code by using them directly rather than
+ * using the generic single-entry routines.
+ */
+
+#define LIST_HEAD_INIT(name) { &(name), &(name) }
+
+#define LIST_HEAD(name) \
+	struct list_head name = LIST_HEAD_INIT(name)
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+	list->next = list;
+	list->prev = list;
+}
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next)
+{
+	next->prev = new;
+	new->next = next;
+	new->prev = prev;
+	prev->next = new;
+}
+#else
+extern void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next);
+#endif
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head, head->next);
+}
+
+
+/**
+ * list_add_tail - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ */
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head->prev, head);
+}
+
+/*
+ * Delete a list entry by making the prev/next entries
+ * point to each other.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_del(struct list_head * prev, struct list_head * next)
+{
+	next->prev = prev;
+	WRITE_ONCE(prev->next, next);
+}
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty() on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_del_entry(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+}
+
+static inline void list_del(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+	entry->next = LIST_POISON1;
+	entry->prev = LIST_POISON2;
+}
+#else
+extern void __list_del_entry(struct list_head *entry);
+extern void list_del(struct list_head *entry);
+#endif
+
+/**
+ * list_replace - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * If @old was empty, it will be overwritten.
+ */
+static inline void list_replace(struct list_head *old,
+				struct list_head *new)
+{
+	new->next = old->next;
+	new->next->prev = new;
+	new->prev = old->prev;
+	new->prev->next = new;
+}
+
+static inline void list_replace_init(struct list_head *old,
+					struct list_head *new)
+{
+	list_replace(old, new);
+	INIT_LIST_HEAD(old);
+}
+
+/**
+ * list_del_init - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ */
+static inline void list_del_init(struct list_head *entry)
+{
+	__list_del_entry(entry);
+	INIT_LIST_HEAD(entry);
+}
+
+/**
+ * list_move - delete from one list and add as another's head
+ * @list: the entry to move
+ * @head: the head that will precede our entry
+ */
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+	__list_del_entry(list);
+	list_add(list, head);
+}
+
+/**
+ * list_move_tail - delete from one list and add as another's tail
+ * @list: the entry to move
+ * @head: the head that will follow our entry
+ */
+static inline void list_move_tail(struct list_head *list,
+				  struct list_head *head)
+{
+	__list_del_entry(list);
+	list_add_tail(list, head);
+}
+
+/**
+ * list_is_last - tests whether @list is the last entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_last(const struct list_head *list,
+				const struct list_head *head)
+{
+	return list->next == head;
+}
+
+/**
+ * list_empty - tests whether a list is empty
+ * @head: the list to test.
+ */
+static inline int list_empty(const struct list_head *head)
+{
+	return head->next == head;
+}
+
+/**
+ * list_empty_careful - tests whether a list is empty and not being modified
+ * @head: the list to test
+ *
+ * Description:
+ * tests whether a list is empty _and_ checks that no other CPU might be
+ * in the process of modifying either member (next or prev)
+ *
+ * NOTE: using list_empty_careful() without synchronization
+ * can only be safe if the only activity that can happen
+ * to the list entry is list_del_init(). Eg. it cannot be used
+ * if another CPU could re-list_add() it.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+	struct list_head *next = head->next;
+	return (next == head) && (next == head->prev);
+}
+
+/**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+	struct list_head *first;
+
+	if (!list_empty(head)) {
+		first = head->next;
+		list_move_tail(first, head);
+	}
+}
+
+/**
+ * list_is_singular - tests whether a list has just one entry.
+ * @head: the list to test.
+ */
+static inline int list_is_singular(const struct list_head *head)
+{
+	return !list_empty(head) && (head->next == head->prev);
+}
+
+static inline void __list_cut_position(struct list_head *list,
+		struct list_head *head, struct list_head *entry)
+{
+	struct list_head *new_first = entry->next;
+	list->next = head->next;
+	list->next->prev = list;
+	list->prev = entry;
+	entry->next = list;
+	head->next = new_first;
+	new_first->prev = head;
+}
+
+/**
+ * list_cut_position - cut a list into two
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ *	and if so we won't cut the list
+ *
+ * This helper moves the initial part of @head, up to and
+ * including @entry, from @head to @list. You should
+ * pass on @entry an element you know is on @head. @list
+ * should be an empty list or a list you do not care about
+ * losing its data.
+ *
+ */
+static inline void list_cut_position(struct list_head *list,
+		struct list_head *head, struct list_head *entry)
+{
+	if (list_empty(head))
+		return;
+	if (list_is_singular(head) &&
+		(head->next != entry && head != entry))
+		return;
+	if (entry == head)
+		INIT_LIST_HEAD(list);
+	else
+		__list_cut_position(list, head, entry);
+}
+
+static inline void __list_splice(const struct list_head *list,
+				 struct list_head *prev,
+				 struct list_head *next)
+{
+	struct list_head *first = list->next;
+	struct list_head *last = list->prev;
+
+	first->prev = prev;
+	prev->next = first;
+
+	last->next = next;
+	next->prev = last;
+}
+
+/**
+ * list_splice - join two lists, this is designed for stacks
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice(const struct list_head *list,
+				struct list_head *head)
+{
+	if (!list_empty(list))
+		__list_splice(list, head, head->next);
+}
+
+/**
+ * list_splice_tail - join two lists, each list being a queue
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice_tail(struct list_head *list,
+				struct list_head *head)
+{
+	if (!list_empty(list))
+		__list_splice(list, head->prev, head);
+}
+
+/**
+ * list_splice_init - join two lists and reinitialise the emptied list.
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_init(struct list_head *list,
+				    struct list_head *head)
+{
+	if (!list_empty(list)) {
+		__list_splice(list, head, head->next);
+		INIT_LIST_HEAD(list);
+	}
+}
+
+/**
+ * list_splice_tail_init - join two lists and reinitialise the emptied list
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * Each of the lists is a queue.
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_tail_init(struct list_head *list,
+					 struct list_head *head)
+{
+	if (!list_empty(list)) {
+		__list_splice(list, head->prev, head);
+		INIT_LIST_HEAD(list);
+	}
+}
+
+/**
+ * list_entry - get the struct for this entry
+ * @ptr:	the &struct list_head pointer.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_entry(ptr, type, member) \
+	container_of(ptr, type, member)
+
+/**
+ * list_first_entry - get the first element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_first_entry(ptr, type, member) \
+	list_entry((ptr)->next, type, member)
+
+/**
+ * list_last_entry - get the last element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+	list_entry((ptr)->prev, type, member)
+
+/**
+ * list_first_entry_or_null - get the first element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_first_entry_or_null(ptr, type, member) \
+	(!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
+
+/**
+ * list_next_entry - get the next element in list
+ * @pos:	the type * to cursor
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_next_entry(pos, member) \
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos:	the type * to cursor
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_prev_entry(pos, member) \
+	list_entry((pos)->member.prev, typeof(*(pos)), member)
+
+/**
+ * list_for_each	-	iterate over a list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each(pos, head) \
+	for (pos = (head)->next; pos != (head); pos = pos->next)
+
+/**
+ * list_for_each_prev	-	iterate over a list backwards
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each_prev(pos, head) \
+	for (pos = (head)->prev; pos != (head); pos = pos->prev)
+
+/**
+ * list_for_each_safe - iterate over a list safe against removal of list entry
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @n:		another &struct list_head to use as temporary storage
+ * @head:	the head for your list.
+ */
+#define list_for_each_safe(pos, n, head) \
+	for (pos = (head)->next, n = pos->next; pos != (head); \
+		pos = n, n = pos->next)
+
+/**
+ * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @n:		another &struct list_head to use as temporary storage
+ * @head:	the head for your list.
+ */
+#define list_for_each_prev_safe(pos, n, head) \
+	for (pos = (head)->prev, n = pos->prev; \
+	     pos != (head); \
+	     pos = n, n = pos->prev)
+
+/**
+ * list_for_each_entry	-	iterate over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_first_entry(head, typeof(*pos), member);	\
+	     &pos->member != (head);					\
+	     pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_reverse - iterate backwards over list of given type.
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_for_each_entry_reverse(pos, head, member)			\
+	for (pos = list_last_entry(head, typeof(*pos), member);		\
+	     &pos->member != (head); 					\
+	     pos = list_prev_entry(pos, member))
+
+/**
+ * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
+ * @pos:	the type * to use as a start point
+ * @head:	the head of the list
+ * @member:	the name of the list_head within the struct.
+ *
+ * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
+ */
+#define list_prepare_entry(pos, head, member) \
+	((pos) ? : list_entry(head, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue - continue iteration over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue(pos, head, member) 		\
+	for (pos = list_next_entry(pos, member);			\
+	     &pos->member != (head);					\
+	     pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_continue_reverse - iterate backwards from the given point
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Start to iterate over list of given type backwards, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue_reverse(pos, head, member)		\
+	for (pos = list_prev_entry(pos, member);			\
+	     &pos->member != (head);					\
+	     pos = list_prev_entry(pos, member))
+
+/**
+ * list_for_each_entry_from - iterate over list of given type from the current point
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing from current position.
+ */
+#define list_for_each_entry_from(pos, head, member) 			\
+	for (; &pos->member != (head);					\
+	     pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_for_each_entry_safe(pos, n, head, member)			\
+	for (pos = list_first_entry(head, typeof(*pos), member),	\
+		n = list_next_entry(pos, member);			\
+	     &pos->member != (head); 					\
+	     pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_continue - continue list iteration safe against removal
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing after current point,
+ * safe against removal of list entry.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member) 		\
+	for (pos = list_next_entry(pos, member), 				\
+		n = list_next_entry(pos, member);				\
+	     &pos->member != (head);						\
+	     pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_from - iterate over list from current point safe against removal
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Iterate over list of given type from current point, safe against
+ * removal of list entry.
+ */
+#define list_for_each_entry_safe_from(pos, n, head, member) 			\
+	for (n = list_next_entry(pos, member);					\
+	     &pos->member != (head);						\
+	     pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Iterate backwards over list of given type, safe against removal
+ * of list entry.
+ */
+#define list_for_each_entry_safe_reverse(pos, n, head, member)		\
+	for (pos = list_last_entry(head, typeof(*pos), member),		\
+		n = list_prev_entry(pos, member);			\
+	     &pos->member != (head); 					\
+	     pos = n, n = list_prev_entry(n, member))
 
-#include "../../../include/linux/list.h"
+/**
+ * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
+ * @pos:	the loop cursor used in the list_for_each_entry_safe loop
+ * @n:		temporary storage used in list_for_each_entry_safe
+ * @member:	the name of the list_head within the struct.
+ *
+ * list_safe_reset_next is not safe to use in general if the list may be
+ * modified concurrently (eg. the lock is dropped in the loop body). An
+ * exception to this is if the cursor element (pos) is pinned in the list,
+ * and list_safe_reset_next is called after re-taking the lock and before
+ * completing the current iteration of the loop body.
+ */
+#define list_safe_reset_next(pos, n, member)				\
+	n = list_next_entry(pos, member)
+
+/*
+ * Double linked lists with a single pointer list head.
+ * Mostly useful for hash tables where the two pointer list head is
+ * too wasteful.
+ * You lose the ability to access the tail in O(1).
+ */
+
+#define HLIST_HEAD_INIT { .first = NULL }
+#define HLIST_HEAD(name) struct hlist_head name = {  .first = NULL }
+#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
+static inline void INIT_HLIST_NODE(struct hlist_node *h)
+{
+	h->next = NULL;
+	h->pprev = NULL;
+}
+
+static inline int hlist_unhashed(const struct hlist_node *h)
+{
+	return !h->pprev;
+}
+
+static inline int hlist_empty(const struct hlist_head *h)
+{
+	return !h->first;
+}
+
+static inline void __hlist_del(struct hlist_node *n)
+{
+	struct hlist_node *next = n->next;
+	struct hlist_node **pprev = n->pprev;
+
+	WRITE_ONCE(*pprev, next);
+	if (next)
+		next->pprev = pprev;
+}
+
+static inline void hlist_del(struct hlist_node *n)
+{
+	__hlist_del(n);
+	n->next = LIST_POISON1;
+	n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_del_init(struct hlist_node *n)
+{
+	if (!hlist_unhashed(n)) {
+		__hlist_del(n);
+		INIT_HLIST_NODE(n);
+	}
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+	struct hlist_node *first = h->first;
+	n->next = first;
+	if (first)
+		first->pprev = &n->next;
+	h->first = n;
+	n->pprev = &h->first;
+}
+
+/* next must be != NULL */
+static inline void hlist_add_before(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	n->pprev = next->pprev;
+	n->next = next;
+	next->pprev = &n->next;
+	*(n->pprev) = n;
+}
+
+static inline void hlist_add_behind(struct hlist_node *n,
+				    struct hlist_node *prev)
+{
+	n->next = prev->next;
+	prev->next = n;
+	n->pprev = &prev->next;
+
+	if (n->next)
+		n->next->pprev  = &n->next;
+}
+
+/* after that we'll appear to be on some hlist and hlist_del will work */
+static inline void hlist_add_fake(struct hlist_node *n)
+{
+	n->pprev = &n->next;
+}
+
+static inline bool hlist_fake(struct hlist_node *h)
+{
+	return h->pprev == &h->next;
+}
+
+/*
+ * Move a list from one list head to another. Fixup the pprev
+ * reference of the first entry if it exists.
+ */
+static inline void hlist_move_list(struct hlist_head *old,
+				   struct hlist_head *new)
+{
+	new->first = old->first;
+	if (new->first)
+		new->first->pprev = &new->first;
+	old->first = NULL;
+}
+
+#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_for_each(pos, head) \
+	for (pos = (head)->first; pos ; pos = pos->next)
+
+#define hlist_for_each_safe(pos, n, head) \
+	for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+	     pos = n)
+
+#define hlist_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+	})
+
+/**
+ * hlist_for_each_entry	- iterate over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(pos, head, member)				\
+	for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
+	     pos;							\
+	     pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_continue - iterate over a hlist continuing after current point
+ * @pos:	the type * to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_continue(pos, member)			\
+	for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\
+	     pos;							\
+	     pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_from - iterate over a hlist continuing from current point
+ * @pos:	the type * to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from(pos, member)				\
+	for (; pos;							\
+	     pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another &struct hlist_node to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(pos, n, head, member) 		\
+	for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\
+	     pos && ({ n = pos->member.next; 1; });			\
+	     pos = hlist_entry_safe(n, typeof(*pos), member))
 
-#ifndef TOOLS_LIST_H
-#define TOOLS_LIST_H
 /**
  * list_del_range - deletes range of entries from list.
  * @begin: first element in the range to delete from the list.
@@ -27,4 +767,5 @@ static inline void list_del_range(struct list_head *begin,
  */
 #define list_for_each_from(pos, head) \
 	for (; pos != (head); pos = pos->next)
-#endif
+
+#endif /* __TOOLS_LINUX_LIST_H */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 919b71780710..fc1bc75ae56d 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -6,6 +6,12 @@ BPF_EXTRAVERSION = 1
 
 MAKEFLAGS += --no-print-directory
 
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
 
 # Makefiles suck: This macro sets a default value of $(2) for the
 # variable named by $(1), unless the variable has been set by
@@ -31,7 +37,8 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
-LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+include $(srctree)/tools/scripts/Makefile.arch
+
 ifeq ($(LP64), 1)
   libdir_relative = lib64
 else
@@ -57,13 +64,6 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-#$(info Determined 'srctree' to be $(srctree))
-endif
-
 FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
 FEATURE_DISPLAY = libelf bpf
@@ -192,7 +192,7 @@ install: install_lib
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
 		$(RM) LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5bdc6eab6852..1f91cc941b7c 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -14,8 +14,8 @@
 #include "bpf.h"
 
 /*
- * When building perf, unistd.h is override. Define __NR_bpf is
- * required to be defined.
+ * When building perf, unistd.h is overrided. __NR_bpf is
+ * required to be defined explicitly.
  */
 #ifndef __NR_bpf
 # if defined(__i386__)
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 7e319afac78a..90d2baeb621a 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -149,7 +149,7 @@ install_lib: all_cmd
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d
+	$(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d .*.cmd
 	$(RM) tags TAGS
 
 PHONY += force
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 13a2cc1d6140..d60cab2726da 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -4,6 +4,10 @@
 #include <stdbool.h>
 #include <stdint.h>
 
+#ifndef NORETURN
+#define NORETURN __attribute__((__noreturn__))
+#endif
+
 enum parse_opt_type {
 	/* special types */
 	OPTION_END,
diff --git a/tools/perf/Build b/tools/perf/Build
index 6b67e6f4179f..a43fae7f439a 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -42,6 +42,7 @@ CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"	\
 			      -include $(OUTPUT)PERF-VERSION-FILE
 CFLAGS_builtin-trace.o	   += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
 CFLAGS_builtin-report.o	   += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
+CFLAGS_builtin-report.o	   += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
 
 libperf-y += util/
 libperf-y += arch/
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3a1a32f5479f..fbceb631387c 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -338,6 +338,9 @@ Options passed to clang when compiling BPF scriptlets.
 Specify vmlinux path which has debuginfo.
 (enabled when BPF prologue is on)
 
+--buildid-all::
+Record build-id of all DSOs regardless whether it's actually hit or not.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index a1c10e360db5..e0ce9573b79b 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -12,3 +12,18 @@ List events using substring match: perf list <keyword>
 To see list of saved events and attributes: perf evlist -v
 Use --symfs <dir> if your symbol files are in non-standard locations
 To see callchains in a more compact form: perf report -g folded
+Show individual samples with: perf script
+Limit to show entries above 5% only: perf report --percent-limit 5
+Profiling branch (mis)predictions with: perf record -b / perf report
+Treat branches as callchains: perf report --branch-history
+To count events in every 1000 msec: perf stat -I 1000
+Print event counts in CSV format with: perf stat -x,
+If you have debuginfo enabled, try: perf report -s sym,srcline
+For memory address profiling, try: perf mem record / perf mem report
+For tracepoint events, try: perf report -s trace_fields
+To record callchains for each sample: perf record -g
+To record every process run by an user: perf record -u <user>
+Skip collecing build-id when recording: perf record -B
+To change sampling frequency to 100 Hz: perf record -F 100
+See assembly instructions with percentage: perf annotate <symbol>
+If you prefer Intel style assembly, try: perf annotate -M intel
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index ddf922f93aa1..2e1fa2357528 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -28,6 +28,7 @@ tools/lib/string.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
+tools/lib/bitmap.c
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
@@ -57,6 +58,7 @@ tools/include/linux/rbtree_augmented.h
 tools/include/linux/string.h
 tools/include/linux/types.h
 tools/include/linux/err.h
+tools/include/linux/bitmap.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc4e0adf5c5b..319712a4e02b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -50,6 +50,7 @@ struct record {
 	int			realtime_prio;
 	bool			no_buildid;
 	bool			no_buildid_cache;
+	bool			buildid_all;
 	unsigned long long	samples;
 };
 
@@ -362,6 +363,13 @@ static int process_buildids(struct record *rec)
 	 */
 	symbol_conf.ignore_vmlinux_buildid = true;
 
+	/*
+	 * If --buildid-all is given, it marks all DSO regardless of hits,
+	 * so no need to process samples.
+	 */
+	if (rec->buildid_all)
+		rec->tool.sample = NULL;
+
 	return perf_session__process_events(session);
 }
 
@@ -756,12 +764,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 		if (!rec->no_buildid) {
 			process_buildids(rec);
-			/*
-			 * We take all buildids when the file contains
-			 * AUX area tracing data because we do not decode the
-			 * trace because it would take too long.
-			 */
-			if (rec->opts.full_auxtrace)
+
+			if (rec->buildid_all)
 				dsos__hit_all(rec->session);
 		}
 		perf_session__write_header(rec->session, rec->evlist, fd, true);
@@ -1138,6 +1142,8 @@ struct option __record_options[] = {
 		   "options passed to clang when compiling BPF scriptlets"),
 	OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
+	OPT_BOOLEAN(0, "buildid-all", &record.buildid_all,
+		    "Record build-id of all DSOs regardless of hits"),
 	OPT_END()
 };
 
@@ -1255,6 +1261,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (err)
 		goto out_symbol_exit;
 
+	/*
+	 * We take all buildids when the file contains
+	 * AUX area tracing data because we do not decode the
+	 * trace because it would take too long.
+	 */
+	if (rec->opts.full_auxtrace)
+		rec->buildid_all = true;
+
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
 		goto out_symbol_exit;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d5a42ee12529..2bf537f190a0 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -28,6 +28,7 @@
 #include "util/tool.h"
 
 #include <subcmd/parse-options.h>
+#include <subcmd/exec-cmd.h>
 #include "util/parse-events.h"
 
 #include "util/thread.h"
@@ -433,7 +434,14 @@ static int report__browse_hists(struct report *rep)
 	int ret;
 	struct perf_session *session = rep->session;
 	struct perf_evlist *evlist = session->evlist;
-	const char *help = perf_tip(TIPDIR);
+	const char *help = perf_tip(system_path(TIPDIR));
+
+	if (help == NULL) {
+		/* fallback for people who don't install perf ;-) */
+		help = perf_tip(DOCDIR);
+		if (help == NULL)
+			help = "Cannot load tips.txt file, please install perf!";
+	}
 
 	switch (use_browser) {
 	case 1:
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7f568244662b..038e877081b6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1588,7 +1588,7 @@ static int add_default_attributes(void)
 	return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
-static const char * const recort_usage[] = {
+static const char * const stat_record_usage[] = {
 	"perf stat record [<options>]",
 	NULL,
 };
@@ -1611,7 +1611,7 @@ static int __cmd_record(int argc, const char **argv)
 	struct perf_session *session;
 	struct perf_data_file *file = &perf_stat.file;
 
-	argc = parse_options(argc, argv, stat_options, record_usage,
+	argc = parse_options(argc, argv, stat_options, stat_record_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	if (output_name)
@@ -1745,7 +1745,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(st);
 }
 
-static const char * const report_usage[] = {
+static const char * const stat_report_usage[] = {
 	"perf stat report [<options>]",
 	NULL,
 };
@@ -1779,7 +1779,7 @@ static int __cmd_report(int argc, const char **argv)
 	struct stat st;
 	int ret;
 
-	argc = parse_options(argc, argv, options, report_usage, 0);
+	argc = parse_options(argc, argv, options, stat_report_usage, 0);
 
 	if (!input_name || !strlen(input_name)) {
 		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 254d06e39bea..e5959c136a19 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -17,7 +17,7 @@ detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 
-include $(src-perf)/config/Makefile.arch
+include $(srctree)/tools/scripts/Makefile.arch
 
 $(call detected_var,ARCH)
 
@@ -493,7 +493,7 @@ else
 
       PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
       PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
       PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
       FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
@@ -692,6 +692,7 @@ template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
 htmldir = share/doc/perf-doc
 tipdir = share/doc/perf-tip
+srcdir = $(srctree)/tools/perf
 ifeq ($(prefix),/usr)
 sysconfdir = /etc
 ETC_PERFCONFIG = $(sysconfdir)/perfconfig
@@ -722,6 +723,7 @@ tipdir_SQ = $(subst ','\'',$(tipdir))
 prefix_SQ = $(subst ','\'',$(prefix))
 sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
 libdir_SQ = $(subst ','\'',$(libdir))
+srcdir_SQ = $(subst ','\'',$(srcdir))
 
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
@@ -776,6 +778,7 @@ $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
 $(call detected_var,tipdir_SQ)
+$(call detected_var,srcdir_SQ)
 $(call detected_var,LIBDIR)
 $(call detected_var,GTK_CFLAGS)
 $(call detected_var,PERL_EMBED_CCOPTS)
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index bcfd081ee1d2..071a8b5f5232 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -87,11 +87,6 @@ struct machine *setup_fake_machine(struct machines *machines)
 		return NULL;
 	}
 
-	if (machine__create_kernel_maps(machine)) {
-		pr_debug("Cannot create kernel maps\n");
-		return NULL;
-	}
-
 	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
 		struct thread *thread;
 
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index e36089212061..5e6a86e50fb9 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -706,6 +706,7 @@ int test__hists_cumulate(int subtest __maybe_unused)
 	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
+	err = TEST_FAIL;
 
 	machines__init(&machines);
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 2a784befd9ce..351a42463444 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -120,6 +120,7 @@ int test__hists_filter(int subtest __maybe_unused)
 	err = parse_events(evlist, "task-clock", NULL);
 	if (err)
 		goto out;
+	err = TEST_FAIL;
 
 	/* default sort order (comm,dso,sym) will be used */
 	if (setup_sorting(NULL) < 0)
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index c764d69ac6ef..64b257d8d557 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -293,6 +293,7 @@ int test__hists_link(int subtest __maybe_unused)
 	if (err)
 		goto out;
 
+	err = TEST_FAIL;
 	/* default sort order (comm,dso,sym) will be used */
 	if (setup_sorting(NULL) < 0)
 		goto out;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index ebe6cd485b5d..b231265148d8 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -597,6 +597,7 @@ int test__hists_output(int subtest __maybe_unused)
 	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
+	err = TEST_FAIL;
 
 	machines__init(&machines);
 
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index c1fbb8e884c0..df38decc48c3 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,3 +1,5 @@
+include ../scripts/Makefile.include
+
 ifndef MK
 ifeq ($(MAKECMDGOALS),)
 # no target specified, trigger the whole suite
@@ -12,7 +14,19 @@ endif
 else
 PERF := .
 
-include config/Makefile.arch
+# As per kernel Makefile, avoid funny character set dependencies
+unexport LC_ALL
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_COLLATE LC_NUMERIC
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+include $(srctree)/tools/scripts/Makefile.arch
 
 # FIXME looks like x86 is the only arch running tests ;-)
 # we need some IS_(32/64) flag to make this generic
@@ -280,5 +294,5 @@ all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 out: $(run_O)
 	@echo OK
 
-.PHONY: all $(run) $(run_O) tarpkg clean
+.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
 endif # ifndef MK
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 901d481e6cea..08c09ad755d2 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -480,7 +480,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 
 	hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
-	if (ui_browser__show(&browser->b, title, help) < 0)
+	if (ui_browser__show(&browser->b, title, "%s", help) < 0)
 		return -1;
 
 	while (1) {
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index cd61bb1f3917..85155e91b61b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -503,7 +503,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	if (comm_event == NULL)
 		goto out;
 
-	mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
+	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
@@ -577,7 +577,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (comm_event == NULL)
 		goto out;
 
-	mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
+	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index bdf98f6f27bb..0d3dfcb919b4 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -126,6 +126,11 @@ static int strlist__parse_list_entry(struct strlist *slist, const char *s,
 			err = strlist__load(slist, subst);
 			goto out;
 		}
+
+		if (slist->file_only) {
+			err = -ENOENT;
+			goto out;
+		}
 	}
 
 	err = strlist__add(slist, s);
@@ -157,11 +162,13 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf
 
 	if (slist != NULL) {
 		bool dupstr = true;
+		bool file_only = false;
 		const char *dirname = NULL;
 
 		if (config) {
 			dupstr = !config->dont_dupstr;
 			dirname = config->dirname;
+			file_only = config->file_only;
 		}
 
 		rblist__init(&slist->rblist);
@@ -170,6 +177,7 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf
 		slist->rblist.node_delete = strlist__node_delete;
 
 		slist->dupstr	 = dupstr;
+		slist->file_only = file_only;
 
 		if (list && strlist__parse_list(slist, list, dirname) != 0)
 			goto out_error;
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index 297565aa7535..ca990029e243 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -13,11 +13,18 @@ struct str_node {
 
 struct strlist {
 	struct rblist rblist;
-	bool	       dupstr;
+	bool	      dupstr;
+	bool	      file_only;
 };
 
+/*
+ * @file_only: When dirname is present, only consider entries as filenames,
+ *             that should not be added to the list if dirname/entry is not
+ *             found
+ */
 struct strlist_config {
 	bool dont_dupstr;
+	bool file_only;
 	const char *dirname;
 };
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 88b8f8d21f58..ead9509835d2 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,7 +17,6 @@
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
-#include <subcmd/exec-cmd.h>
 
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_ABS,
@@ -672,14 +671,16 @@ const char *perf_tip(const char *dirpath)
 	struct str_node *node;
 	char *tip = NULL;
 	struct strlist_config conf = {
-		.dirname = system_path(dirpath) ,
+		.dirname = dirpath,
+		.file_only = true,
 	};
 
 	tips = strlist__new("tips.txt", &conf);
-	if (tips == NULL || strlist__nr_entries(tips) == 1) {
-		tip = (char *)"Cannot find tips.txt file";
+	if (tips == NULL)
+		return errno == ENOENT ? NULL : "Tip: get more memory! ;-p";
+
+	if (strlist__nr_entries(tips) == 0)
 		goto out;
-	}
 
 	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
 	if (asprintf(&tip, "Tip: %s", node->s) < 0)
diff --git a/tools/perf/config/Makefile.arch b/tools/scripts/Makefile.arch
similarity index 100%
rename from tools/perf/config/Makefile.arch
rename to tools/scripts/Makefile.arch

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2016-01-08 12:46 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2016-01-08 12:46 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 12ca6ad2e3a896256f086497a7c7406a547ee373 perf: Fix race in swevent hash

Two core subsystem fixes, plus a handful of tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf list: Add support for PERF_COUNT_SW_BPF_OUT
      perf list: Robustify event printing routine

Michael Petlan (2):
      perf buildid-list: Show running kernel build id fix
      perf buildid-list: Fix return value of perf buildid-list -k

Peter Zijlstra (2):
      perf: Fix race in perf_event_exec()
      perf: Fix race in swevent hash

Wang Nan (3):
      perf hists browser: Add NULL pointer check to prevent crash
      perf hists browser: Reset selection when refresh
      perf hists browser: Fix segfault if use symbol filter in cmdline


 kernel/events/core.c              | 35 ++++++-----------------------------
 tools/perf/builtin-buildid-list.c |  2 +-
 tools/perf/ui/browsers/hists.c    |  8 ++++++++
 tools/perf/util/build-id.c        |  2 +-
 tools/perf/util/parse-events.c    |  6 +++++-
 5 files changed, 21 insertions(+), 32 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 39cf4a40aa4c..0a791a2203dc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3154,15 +3154,16 @@ static int event_enable_on_exec(struct perf_event *event,
  * Enable all of a task's events that have been marked enable-on-exec.
  * This expects task == current.
  */
-static void perf_event_enable_on_exec(struct perf_event_context *ctx)
+static void perf_event_enable_on_exec(int ctxn)
 {
-	struct perf_event_context *clone_ctx = NULL;
+	struct perf_event_context *ctx, *clone_ctx = NULL;
 	struct perf_event *event;
 	unsigned long flags;
 	int enabled = 0;
 	int ret;
 
 	local_irq_save(flags);
+	ctx = current->perf_event_ctxp[ctxn];
 	if (!ctx || !ctx->nr_events)
 		goto out;
 
@@ -3205,17 +3206,11 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
 void perf_event_exec(void)
 {
-	struct perf_event_context *ctx;
 	int ctxn;
 
 	rcu_read_lock();
-	for_each_task_context_nr(ctxn) {
-		ctx = current->perf_event_ctxp[ctxn];
-		if (!ctx)
-			continue;
-
-		perf_event_enable_on_exec(ctx);
-	}
+	for_each_task_context_nr(ctxn)
+		perf_event_enable_on_exec(ctxn);
 	rcu_read_unlock();
 }
 
@@ -6493,9 +6488,6 @@ struct swevent_htable {
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
-
-	/* Keeps track of cpu being initialized/exited */
-	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -6753,14 +6745,8 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (!head) {
-		/*
-		 * We can race with cpu hotplug code. Do not
-		 * WARN if the cpu just got unplugged.
-		 */
-		WARN_ON_ONCE(swhash->online);
+	if (WARN_ON_ONCE(!head))
 		return -EINVAL;
-	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 	perf_event_update_userpage(event);
@@ -6828,7 +6814,6 @@ static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
 	int err = 0;
 
 	mutex_lock(&swhash->hlist_mutex);
-
 	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
 		struct swevent_hlist *hlist;
 
@@ -9291,7 +9276,6 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -9333,14 +9317,7 @@ static void perf_event_exit_cpu_context(int cpu)
 
 static void perf_event_exit_cpu(int cpu)
 {
-	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
-
 	perf_event_exit_cpu_context(cpu);
-
-	mutex_lock(&swhash->hlist_mutex);
-	swhash->online = false;
-	swevent_hlist_release(swhash);
-	mutex_unlock(&swhash->hlist_mutex);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 918b4de29de4..6419f57b0850 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -110,7 +110,7 @@ int cmd_buildid_list(int argc, const char **argv,
 	setup_pager();
 
 	if (show_kernel)
-		return sysfs__fprintf_build_id(stdout);
+		return !(sysfs__fprintf_build_id(stdout) > 0);
 
 	return perf_session__list_build_ids(force, with_hits);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fa9eb92c9e24..81def6c3f24b 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -298,6 +298,9 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 	struct callchain_list *cl = container_of(ms, struct callchain_list, ms);
 	bool has_children;
 
+	if (!he || !ms)
+		return false;
+
 	if (ms == &he->ms)
 		has_children = hist_entry__toggle_fold(he);
 	else
@@ -928,6 +931,8 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	}
 
 	ui_browser__hists_init_top(browser);
+	hb->he_selection = NULL;
+	hb->selection = NULL;
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
@@ -1033,6 +1038,9 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 	 * and stop when we printed enough lines to fill the screen.
 	 */
 do_offset:
+	if (!nd)
+		return;
+
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 217b5a60e2ab..6a7e273a514a 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -91,7 +91,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf)
 		bid += 2;
 	}
 
-	return raw - build_id;
+	return (bid - bf) + 1;
 }
 
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e48d9da75707..6fc8cd753e1a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -124,6 +124,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		.symbol = "dummy",
 		.alias  = "",
 	},
+	[PERF_COUNT_SW_BPF_OUTPUT] = {
+		.symbol = "bpf-output",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -1879,7 +1883,7 @@ void print_symbol_events(const char *event_glob, unsigned type,
 
 	for (i = 0; i < max; i++, syms++) {
 
-		if (event_glob != NULL &&
+		if (event_glob != NULL && syms->symbol != NULL &&
 		    !(strglobmatch(syms->symbol, event_glob) ||
 		      (syms->alias && strglobmatch(syms->alias, event_glob))))
 			continue;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-12-08  4:22 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-12-08  4:22 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4e93ad601a4308d4a67673c81556580817d56940 perf: Do not send exit event twice

This tree includes 4 core perf fixes for misc bugs, 3 fixes to x86 PMU drivers, 
and 2 updates to old email addresses.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86: Fix LBR call stack save/restore

Jiri Olsa (2):
      perf/x86/intel: Fix INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA macro
      perf: Do not send exit event twice

Peter Zijlstra (3):
      perf: Update email address in MAINTAINERS
      treewide: Remove old email address
      perf: Fix PERF_EVENT_IOC_PERIOD deadlock

Stephane Eranian (2):
      perf/core: Fix RCU problem with cgroup context switching code
      perf/core: Robustify the perf_cgroup_from_task() RCU checks

Yuanfang Chen (1):
      perf/x86/intel: Make L1D_PEND_MISS.FB_FULL not constrained on Haswell


 MAINTAINERS                                |  2 +-
 arch/blackfin/kernel/perf_event.c          |  2 +-
 arch/sh/kernel/perf_event.c                |  2 +-
 arch/sparc/kernel/perf_event.c             |  2 +-
 arch/tile/kernel/perf_event.c              |  2 +-
 arch/x86/kernel/cpu/perf_event.c           |  2 +-
 arch/x86/kernel/cpu/perf_event.h           |  5 +-
 arch/x86/kernel/cpu/perf_event_intel.c     |  2 +-
 arch/x86/kernel/cpu/perf_event_intel_cqm.c |  2 +-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |  4 +-
 arch/x86/kernel/irq_work.c                 |  2 +-
 include/asm-generic/tlb.h                  |  2 +-
 include/linux/jump_label.h                 |  2 +-
 include/linux/lockdep.h                    |  2 +-
 include/linux/perf_event.h                 |  6 ++-
 include/linux/proportions.h                |  2 +-
 include/linux/uprobes.h                    |  2 +-
 kernel/events/callchain.c                  |  2 +-
 kernel/events/core.c                       | 84 ++++++++++++++++++++++--------
 kernel/events/ring_buffer.c                |  2 +-
 kernel/events/uprobes.c                    |  2 +-
 kernel/irq_work.c                          |  2 +-
 kernel/jump_label.c                        |  2 +-
 kernel/locking/lockdep.c                   |  2 +-
 kernel/locking/lockdep_proc.c              |  2 +-
 kernel/sched/clock.c                       |  2 +-
 kernel/sched/fair.c                        |  2 +-
 kernel/trace/trace_event_perf.c            |  2 +-
 lib/btree.c                                |  2 +-
 lib/proportions.c                          |  2 +-
 mm/page-writeback.c                        |  2 +-
 31 files changed, 98 insertions(+), 55 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 050d0e77a2cf..a45fe3538d2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8284,7 +8284,7 @@ F:	include/linux/delayacct.h
 F:	kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
-M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
+M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 1e9c8b0bf486..170d786807c4 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -14,7 +14,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7cfd7f153966..4dca18347ee9 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -10,7 +10,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b0da5aedb336..3091267c5cc3 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -9,7 +9,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/perf_event.h>
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index bb509cee3b59..8767060d70fb 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -21,7 +21,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4562cf070c27..2bf79d7c97df 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 499f533dd3cc..d0e35ebb2adb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
@@ -387,7 +387,7 @@ struct cpu_hw_events {
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
 	__EVENT_CONSTRAINT(code, n, 			\
-			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
@@ -627,6 +627,7 @@ struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	int tos;
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f63360be2238..e2a430021e46 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 377e8f8ed391..a316ca96f1b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
 	if (event->attach_state & PERF_ATTACH_TASK)
-		return perf_cgroup_from_task(event->hw.target);
+		return perf_cgroup_from_task(event->hw.target, event->ctx);
 
 	return event->cgrp;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index bfd0b717e944..659f01e165d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 	}
 
 	mask = x86_pmu.lbr_nr - 1;
-	tos = intel_pmu_lbr_tos();
+	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
 
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index dc5fa6a1e8d6..3512ba607361 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index db284bff29dc..9dbb739cafa0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -5,7 +5,7 @@
  * Copyright 2001 Red Hat, Inc.
  * Based on code from mm/memory.c Copyright Linus Torvalds and others.
  *
- * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8dde55974f18..0536524bb9eb 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -5,7 +5,7 @@
  * Jump label support
  *
  * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  *
  * DEPRECATED API:
  *
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 70400dc7660f..c57e424d914b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -2,7 +2,7 @@
  * Runtime locking correctness validator
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * see Documentation/locking/lockdep-design.txt for more details.
  */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d841d33bcdc9..f9828a48f16a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -697,9 +697,11 @@ struct perf_cgroup {
  * if there is no cgroup event for the current CPU context.
  */
 static inline struct perf_cgroup *
-perf_cgroup_from_task(struct task_struct *task)
+perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
 {
-	return container_of(task_css(task, perf_event_cgrp_id),
+	return container_of(task_css_check(task, perf_event_cgrp_id,
+					   ctx ? lockdep_is_held(&ctx->lock)
+					       : true),
 			    struct perf_cgroup, css);
 }
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 5440f64d2942..21221338ad18 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -1,7 +1,7 @@
 /*
  * FLoating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * This file contains the public data structure and API definitions.
  */
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 0bdc72f36905..4a29c75b146e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -21,7 +21,7 @@
  * Authors:
  *	Srikar Dronamraju
  *	Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/errno.h>
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index d659487254d5..9c418002b8c1 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  �  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 36babfd20648..39cf4a40aa4c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
@@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	if (!is_cgroup_event(event))
 		return;
 
-	cgrp = perf_cgroup_from_task(current);
+	cgrp = perf_cgroup_from_task(current, event->ctx);
 	/*
 	 * Do not update time when cgroup is not active
 	 */
@@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 	if (!task || !ctx->nr_cgroups)
 		return;
 
-	cgrp = perf_cgroup_from_task(task);
+	cgrp = perf_cgroup_from_task(task, ctx);
 	info = this_cpu_ptr(cgrp->info);
 	info->timestamp = ctx->timestamp;
 }
@@ -489,7 +489,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 	 * we reschedule only in the presence of cgroup
 	 * constrained events.
 	 */
-	rcu_read_lock();
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
@@ -522,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 				 * set cgrp before ctxsw in to allow
 				 * event_filter_match() to not have to pass
 				 * task around
+				 * we pass the cpuctx->ctx to perf_cgroup_from_task()
+				 * because cgorup events are only per-cpu
 				 */
-				cpuctx->cgrp = perf_cgroup_from_task(task);
+				cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
 				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
 			}
 			perf_pmu_enable(cpuctx->ctx.pmu);
@@ -531,8 +532,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 		}
 	}
 
-	rcu_read_unlock();
-
 	local_irq_restore(flags);
 }
 
@@ -542,17 +541,20 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
 	struct perf_cgroup *cgrp1;
 	struct perf_cgroup *cgrp2 = NULL;
 
+	rcu_read_lock();
 	/*
 	 * we come here when we know perf_cgroup_events > 0
+	 * we do not need to pass the ctx here because we know
+	 * we are holding the rcu lock
 	 */
-	cgrp1 = perf_cgroup_from_task(task);
+	cgrp1 = perf_cgroup_from_task(task, NULL);
 
 	/*
 	 * next is NULL when called from perf_event_enable_on_exec()
 	 * that will systematically cause a cgroup_switch()
 	 */
 	if (next)
-		cgrp2 = perf_cgroup_from_task(next);
+		cgrp2 = perf_cgroup_from_task(next, NULL);
 
 	/*
 	 * only schedule out current cgroup events if we know
@@ -561,6 +563,8 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
 	 */
 	if (cgrp1 != cgrp2)
 		perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+
+	rcu_read_unlock();
 }
 
 static inline void perf_cgroup_sched_in(struct task_struct *prev,
@@ -569,13 +573,16 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
 	struct perf_cgroup *cgrp1;
 	struct perf_cgroup *cgrp2 = NULL;
 
+	rcu_read_lock();
 	/*
 	 * we come here when we know perf_cgroup_events > 0
+	 * we do not need to pass the ctx here because we know
+	 * we are holding the rcu lock
 	 */
-	cgrp1 = perf_cgroup_from_task(task);
+	cgrp1 = perf_cgroup_from_task(task, NULL);
 
 	/* prev can never be NULL */
-	cgrp2 = perf_cgroup_from_task(prev);
+	cgrp2 = perf_cgroup_from_task(prev, NULL);
 
 	/*
 	 * only need to schedule in cgroup events if we are changing
@@ -584,6 +591,8 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
 	 */
 	if (cgrp1 != cgrp2)
 		perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+
+	rcu_read_unlock();
 }
 
 static inline int perf_cgroup_connect(int fd, struct perf_event *event,
@@ -4216,7 +4225,14 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		goto retry;
 	}
 
-	__perf_event_period(&pe);
+	if (event->attr.freq) {
+		event->attr.sample_freq = value;
+	} else {
+		event->attr.sample_period = value;
+		event->hw.sample_period = value;
+	}
+
+	local64_set(&event->hw.period_left, 0);
 	raw_spin_unlock_irq(&ctx->lock);
 
 	return 0;
@@ -5667,6 +5683,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx,
 }
 
 static void
+perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
+			struct perf_event_context *task_ctx)
+{
+	rcu_read_lock();
+	preempt_disable();
+	perf_event_aux_ctx(task_ctx, output, data);
+	preempt_enable();
+	rcu_read_unlock();
+}
+
+static void
 perf_event_aux(perf_event_aux_output_cb output, void *data,
 	       struct perf_event_context *task_ctx)
 {
@@ -5675,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
 	struct pmu *pmu;
 	int ctxn;
 
+	/*
+	 * If we have task_ctx != NULL we only notify
+	 * the task context itself. The task_ctx is set
+	 * only for EXIT events before releasing task
+	 * context.
+	 */
+	if (task_ctx) {
+		perf_event_aux_task_ctx(output, data, task_ctx);
+		return;
+	}
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
 		if (cpuctx->unique_pmu != pmu)
 			goto next;
 		perf_event_aux_ctx(&cpuctx->ctx, output, data);
-		if (task_ctx)
-			goto next;
 		ctxn = pmu->task_ctx_nr;
 		if (ctxn < 0)
 			goto next;
@@ -5692,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
 next:
 		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
-
-	if (task_ctx) {
-		preempt_disable();
-		perf_event_aux_ctx(task_ctx, output, data);
-		preempt_enable();
-	}
 	rcu_read_unlock();
 }
 
@@ -8787,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	struct perf_event_context *child_ctx, *clone_ctx = NULL;
 	unsigned long flags;
 
-	if (likely(!child->perf_event_ctxp[ctxn])) {
-		perf_event_task(child, NULL, 0);
+	if (likely(!child->perf_event_ctxp[ctxn]))
 		return;
-	}
 
 	local_irq_save(flags);
 	/*
@@ -8874,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn)
 		perf_event_exit_task_context(child, ctxn);
+
+	/*
+	 * The perf_event_exit_task_context calls perf_event_task
+	 * with child's task_ctx, which generates EXIT events for
+	 * child contexts and sets child->perf_event_ctxp[] to NULL.
+	 * At this point we need to send EXIT events to cpu contexts.
+	 */
+	perf_event_task(child, NULL, 0);
 }
 
 static void perf_free_event(struct perf_event *event,
@@ -9452,7 +9488,9 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
 static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
+	rcu_read_lock();
 	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index b5d1ea79c595..adfdc0536117 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 4e5e9798aa0c..7dad84913abf 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -19,7 +19,7 @@
  * Authors:
  *	Srikar Dronamraju
  *	Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index cbf9fb899d92..bcf107ce0854 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  *
  * Provides a framework for enqueueing and running callbacks from hardirq
  * context. The enqueueing is NMI-safe.
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index f7dd15d537f9..05254eeb4b4e 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -2,7 +2,7 @@
  * jump label support
  *
  * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011 Peter Zijlstra
  *
  */
 #include <linux/memory.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index deae3907ac1e..60ace56618f6 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6,7 +6,7 @@
  * Started by Ingo Molnar:
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * this code maps all the lock dependencies as they occur in a live kernel
  * and will warn about the following classes of locking bugs:
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index d83d798bef95..dbb61a302548 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -6,7 +6,7 @@
  * Started by Ingo Molnar:
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Code for /proc/lockdep and /proc/lockdep_stats:
  *
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c0a205101c23..caf4041f5b0a 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -1,7 +1,7 @@
 /*
  * sched_clock for unstable cpu clocks
  *
- *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra
  *
  *  Updates and enhancements:
  *    Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f04fda8f669c..90e26b11deaa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -17,7 +17,7 @@
  *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
  *
  *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/latencytop.h>
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index abfc903e741e..cc9f7a9319be 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,7 +1,7 @@
 /*
  * trace event based perf event profiling/tracing
  *
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra
  * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
diff --git a/lib/btree.c b/lib/btree.c
index 4264871ea1a0..f93a945274af 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -5,7 +5,7 @@
  *
  * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org>
  * Bits and pieces stolen from Peter Zijlstra's code, which is
- * Copyright 2007, Red Hat Inc. Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2007, Red Hat Inc. Peter Zijlstra
  * GPLv2
  *
  * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch
diff --git a/lib/proportions.c b/lib/proportions.c
index 6f724298f67a..efa54f259ea9 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -1,7 +1,7 @@
 /*
  * Floating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Description:
  *
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e4d65445fa7..d15d88c8efa1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2,7 +2,7 @@
  * mm/page-writeback.c
  *
  * Copyright (C) 2002, Linus Torvalds.
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Contains functions related to writing back dirty pages at the
  * address_space level.

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-09-17  8:02 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-09-17  8:02 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: f6cf87f748ff9480f97ff9c5caf6d6faacf52aa1 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, but also two x86 PMU driver fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (15):
      perf tools: Fix use of wrong event when processing exit events
      perf evlist: Simplify propagate_maps() logic
      perf evlist: Simplify set_maps() logic
      perf evlist: Remove redundant validation from propagate_maps()
      perf evlist: Add has_user_cpus member
      perf evlist: Fix splice_list_tail() not setting evlist
      perf evlist: Fix missing thread_map__put in propagate_maps()
      perf evsel: Add own_cpus member
      perf evlist: Make set_maps() more resilient
      perf evlist: Make create_maps() use set_maps()
      perf evlist: Factor out a function to propagate maps for a single evsel
      perf evlist: Fix add() not propagating maps
      perf evlist: Fix create_syswide_maps() not propagating maps
      perf tests: Fix task exit test setting maps
      perf tests: Fix software clock events test setting maps

Alexander Shishkin (1):
      perf/x86/intel/bts: Set event->hw.itrace_started in pmu::start to match the new logic

Arnaldo Carvalho de Melo (1):
      perf header: Fixup reading of HEADER_NRCPUS feature

Jiri Olsa (1):
      perf tools: Fix parse_events_add_pmu caller

Peter Zijlstra (1):
      perf/x86/intel: Fix constraint access

Wang Nan (1):
      perf top: Fix segfault pressing -> with no hist entries


 arch/x86/kernel/cpu/perf_event_intel.c     |   5 +-
 arch/x86/kernel/cpu/perf_event_intel_bts.c |   1 +
 tools/perf/builtin-script.c                |   4 +-
 tools/perf/tests/sw-clock.c                |  18 +++-
 tools/perf/tests/task-exit.c               |  18 +++-
 tools/perf/ui/browsers/hists.c             |  12 ++-
 tools/perf/util/evlist.c                   | 138 ++++++++++++++++-------------
 tools/perf/util/evlist.h                   |   9 +-
 tools/perf/util/evsel.c                    |   1 +
 tools/perf/util/evsel.h                    |   1 +
 tools/perf/util/header.c                   |   4 +-
 tools/perf/util/intel-bts.c                |   2 +-
 tools/perf/util/intel-pt.c                 |   2 +-
 tools/perf/util/parse-events.c             |   7 +-
 tools/perf/util/parse-events.y             |   2 +-
 15 files changed, 136 insertions(+), 88 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3f124d553c5a..f41e4dc78119 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2316,9 +2316,12 @@ static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = cpuc->event_constraint[idx];
+	struct event_constraint *c1 = NULL;
 	struct event_constraint *c2;
 
+	if (idx >= 0) /* fake does < 0 */
+		c1 = cpuc->event_constraint[idx];
+
 	/*
 	 * first time only
 	 * - static constraint: no change across incremental scheduling calls
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index 54690e885759..d1c0f254afbe 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -222,6 +222,7 @@ static void __bts_event_start(struct perf_event *event)
 	if (!buf || bts_buffer_is_full(buf, bts))
 		return;
 
+	event->hw.itrace_started = 1;
 	event->hw.state = 0;
 
 	if (!buf->snapshot)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index eb51325e8ad9..284a76e04628 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -768,8 +768,8 @@ static int process_exit_event(struct perf_tool *tool,
 	if (!evsel->attr.sample_id_all) {
 		sample->cpu = 0;
 		sample->time = 0;
-		sample->tid = event->comm.tid;
-		sample->pid = event->comm.pid;
+		sample->tid = event->fork.tid;
+		sample->pid = event->fork.pid;
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 1aa21c90731b..5b83f56a3b6f 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -34,6 +34,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		.disabled = 1,
 		.freq = 1,
 	};
+	struct cpu_map *cpus;
+	struct thread_map *threads;
 
 	attr.sample_freq = 500;
 
@@ -50,14 +52,19 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	}
 	perf_evlist__add(evlist, evsel);
 
-	evlist->cpus = cpu_map__dummy_new();
-	evlist->threads = thread_map__new_by_tid(getpid());
-	if (!evlist->cpus || !evlist->threads) {
+	cpus = cpu_map__dummy_new();
+	threads = thread_map__new_by_tid(getpid());
+	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_evlist;
+		goto out_free_maps;
 	}
 
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	cpus	= NULL;
+	threads = NULL;
+
 	if (perf_evlist__open(evlist)) {
 		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
 
@@ -107,6 +114,9 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		err = -1;
 	}
 
+out_free_maps:
+	cpu_map__put(cpus);
+	thread_map__put(threads);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 3a8fedef83bc..add16385f13e 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -43,6 +43,8 @@ int test__task_exit(void)
 	};
 	const char *argv[] = { "true", NULL };
 	char sbuf[STRERR_BUFSIZE];
+	struct cpu_map *cpus;
+	struct thread_map *threads;
 
 	signal(SIGCHLD, sig_handler);
 
@@ -58,14 +60,19 @@ int test__task_exit(void)
 	 * perf_evlist__prepare_workload we'll fill in the only thread
 	 * we're monitoring, the one forked there.
 	 */
-	evlist->cpus = cpu_map__dummy_new();
-	evlist->threads = thread_map__new_by_tid(-1);
-	if (!evlist->cpus || !evlist->threads) {
+	cpus = cpu_map__dummy_new();
+	threads = thread_map__new_by_tid(-1);
+	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_evlist;
+		goto out_free_maps;
 	}
 
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	cpus	= NULL;
+	threads = NULL;
+
 	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
 					    workload_exec_failed_signal);
 	if (err < 0) {
@@ -114,6 +121,9 @@ int test__task_exit(void)
 		err = -1;
 	}
 
+out_free_maps:
+	cpu_map__put(cpus);
+	thread_map__put(threads);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index cf86f2d3a5e7..c04c60d4863c 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1968,7 +1968,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					  &options[nr_options], dso);
 		nr_options += add_map_opt(browser, &actions[nr_options],
 					  &options[nr_options],
-					  browser->selection->map);
+					  browser->selection ?
+						browser->selection->map : NULL);
 
 		/* perf script support */
 		if (browser->he_selection) {
@@ -1976,6 +1977,15 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 						     &actions[nr_options],
 						     &options[nr_options],
 						     thread, NULL);
+			/*
+			 * Note that browser->selection != NULL
+			 * when browser->he_selection is not NULL,
+			 * so we don't need to check browser->selection
+			 * before fetching browser->selection->sym like what
+			 * we do before fetching browser->selection->map.
+			 *
+			 * See hist_browser__show_entry.
+			 */
 			nr_options += add_script_opt(browser,
 						     &actions[nr_options],
 						     &options[nr_options],
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d51a5200c8af..c8fc8a258f42 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -124,6 +124,33 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 	free(evlist);
 }
 
+static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
+					  struct perf_evsel *evsel)
+{
+	/*
+	 * We already have cpus for evsel (via PMU sysfs) so
+	 * keep it, if there's no target cpu list defined.
+	 */
+	if (!evsel->own_cpus || evlist->has_user_cpus) {
+		cpu_map__put(evsel->cpus);
+		evsel->cpus = cpu_map__get(evlist->cpus);
+	} else if (evsel->cpus != evsel->own_cpus) {
+		cpu_map__put(evsel->cpus);
+		evsel->cpus = cpu_map__get(evsel->own_cpus);
+	}
+
+	thread_map__put(evsel->threads);
+	evsel->threads = thread_map__get(evlist->threads);
+}
+
+static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel)
+		__perf_evlist__propagate_maps(evlist, evsel);
+}
+
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	entry->evlist = evlist;
@@ -133,18 +160,19 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
+
+	__perf_evlist__propagate_maps(evlist, entry);
 }
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-				   struct list_head *list,
-				   int nr_entries)
+				   struct list_head *list)
 {
-	bool set_id_pos = !evlist->nr_entries;
+	struct perf_evsel *evsel, *temp;
 
-	list_splice_tail(list, &evlist->entries);
-	evlist->nr_entries += nr_entries;
-	if (set_id_pos)
-		perf_evlist__set_id_pos(evlist);
+	__evlist__for_each_safe(list, temp, evsel) {
+		list_del_init(&evsel->node);
+		perf_evlist__add(evlist, evsel);
+	}
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
@@ -210,7 +238,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 		list_add_tail(&evsel->node, &head);
 	}
 
-	perf_evlist__splice_list_tail(evlist, &head, nr_attrs);
+	perf_evlist__splice_list_tail(evlist, &head);
 
 	return 0;
 
@@ -1103,71 +1131,56 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
-static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
-				       bool has_user_cpus)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		/*
-		 * We already have cpus for evsel (via PMU sysfs) so
-		 * keep it, if there's no target cpu list defined.
-		 */
-		if (evsel->cpus && has_user_cpus)
-			cpu_map__put(evsel->cpus);
-
-		if (!evsel->cpus || has_user_cpus)
-			evsel->cpus = cpu_map__get(evlist->cpus);
-
-		evsel->threads = thread_map__get(evlist->threads);
-
-		if ((evlist->cpus && !evsel->cpus) ||
-		    (evlist->threads && !evsel->threads))
-			return -ENOMEM;
-	}
-
-	return 0;
-}
-
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
-	evlist->threads = thread_map__new_str(target->pid, target->tid,
-					      target->uid);
+	struct cpu_map *cpus;
+	struct thread_map *threads;
+
+	threads = thread_map__new_str(target->pid, target->tid, target->uid);
 
-	if (evlist->threads == NULL)
+	if (!threads)
 		return -1;
 
 	if (target__uses_dummy_map(target))
-		evlist->cpus = cpu_map__dummy_new();
+		cpus = cpu_map__dummy_new();
 	else
-		evlist->cpus = cpu_map__new(target->cpu_list);
+		cpus = cpu_map__new(target->cpu_list);
 
-	if (evlist->cpus == NULL)
+	if (!cpus)
 		goto out_delete_threads;
 
-	return perf_evlist__propagate_maps(evlist, !!target->cpu_list);
+	evlist->has_user_cpus = !!target->cpu_list;
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	return 0;
 
 out_delete_threads:
-	thread_map__put(evlist->threads);
-	evlist->threads = NULL;
+	thread_map__put(threads);
 	return -1;
 }
 
-int perf_evlist__set_maps(struct perf_evlist *evlist,
-			  struct cpu_map *cpus,
-			  struct thread_map *threads)
+void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
+			   struct thread_map *threads)
 {
-	if (evlist->cpus)
+	/*
+	 * Allow for the possibility that one or another of the maps isn't being
+	 * changed i.e. don't put it.  Note we are assuming the maps that are
+	 * being applied are brand new and evlist is taking ownership of the
+	 * original reference count of 1.  If that is not the case it is up to
+	 * the caller to increase the reference count.
+	 */
+	if (cpus != evlist->cpus) {
 		cpu_map__put(evlist->cpus);
+		evlist->cpus = cpus;
+	}
 
-	evlist->cpus = cpus;
-
-	if (evlist->threads)
+	if (threads != evlist->threads) {
 		thread_map__put(evlist->threads);
+		evlist->threads = threads;
+	}
 
-	evlist->threads = threads;
-
-	return perf_evlist__propagate_maps(evlist, false);
+	perf_evlist__propagate_maps(evlist);
 }
 
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
@@ -1387,6 +1400,8 @@ void perf_evlist__close(struct perf_evlist *evlist)
 
 static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 {
+	struct cpu_map	  *cpus;
+	struct thread_map *threads;
 	int err = -ENOMEM;
 
 	/*
@@ -1398,20 +1413,19 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 	 * error, and we may not want to do that fallback to a
 	 * default cpu identity map :-\
 	 */
-	evlist->cpus = cpu_map__new(NULL);
-	if (evlist->cpus == NULL)
+	cpus = cpu_map__new(NULL);
+	if (!cpus)
 		goto out;
 
-	evlist->threads = thread_map__new_dummy();
-	if (evlist->threads == NULL)
-		goto out_free_cpus;
+	threads = thread_map__new_dummy();
+	if (!threads)
+		goto out_put;
 
-	err = 0;
+	perf_evlist__set_maps(evlist, cpus, threads);
 out:
 	return err;
-out_free_cpus:
-	cpu_map__put(evlist->cpus);
-	evlist->cpus = NULL;
+out_put:
+	cpu_map__put(cpus);
 	goto out;
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b39a6198f4ac..115d8b53c601 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -42,6 +42,7 @@ struct perf_evlist {
 	int		 nr_mmaps;
 	bool		 overwrite;
 	bool		 enabled;
+	bool		 has_user_cpus;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -155,9 +156,8 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 
-int perf_evlist__set_maps(struct perf_evlist *evlist,
-			  struct cpu_map *cpus,
-			  struct thread_map *threads);
+void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
+			   struct thread_map *threads);
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel);
 
@@ -179,8 +179,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-				   struct list_head *list,
-				   int nr_entries);
+				   struct list_head *list);
 
 static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
 {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c53f79123b37..5410483d5219 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1033,6 +1033,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_config_terms(evsel);
 	close_cgroup(evsel->cgrp);
 	cpu_map__put(evsel->cpus);
+	cpu_map__put(evsel->own_cpus);
 	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 298e6bbca200..ef8925f7211a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -98,6 +98,7 @@ struct perf_evsel {
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct cpu_map		*own_cpus;
 	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 41814547da15..fce6634aebe2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1438,7 +1438,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_cpus_online = nr;
+	ph->env.nr_cpus_avail = nr;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
@@ -1447,7 +1447,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_cpus_avail = nr;
+	ph->env.nr_cpus_online = nr;
 	return 0;
 }
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index ea768625ab5b..eb0e7f8bf515 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -623,7 +623,7 @@ static int intel_bts_process_event(struct perf_session *session,
 	if (err)
 		return err;
 	if (event->header.type == PERF_RECORD_EXIT) {
-		err = intel_bts_process_tid_exit(bts, event->comm.tid);
+		err = intel_bts_process_tid_exit(bts, event->fork.tid);
 		if (err)
 			return err;
 	}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index bb41c20e6005..535d86f8e4d1 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1494,7 +1494,7 @@ static int intel_pt_process_event(struct perf_session *session,
 	if (pt->timeless_decoding) {
 		if (event->header.type == PERF_RECORD_EXIT) {
 			err = intel_pt_process_timeless_queues(pt,
-							       event->comm.tid,
+							       event->fork.tid,
 							       sample->time);
 		}
 	} else if (timestamp) {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d826e6f515db..21ed6ee63da9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -287,8 +287,8 @@ __add_event(struct list_head *list, int *idx,
 	if (!evsel)
 		return NULL;
 
-	if (cpus)
-		evsel->cpus = cpu_map__get(cpus);
+	evsel->cpus     = cpu_map__get(cpus);
+	evsel->own_cpus = cpu_map__get(cpus);
 
 	if (name)
 		evsel->name = strdup(name);
@@ -1140,10 +1140,9 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
 	perf_pmu__parse_cleanup();
 	if (!ret) {
-		int entries = data.idx - evlist->nr_entries;
 		struct perf_evsel *last;
 
-		perf_evlist__splice_list_tail(evlist, &data.list, entries);
+		perf_evlist__splice_list_tail(evlist, &data.list);
 		evlist->nr_groups += data.nr_groups;
 		last = perf_evlist__last(evlist);
 		last->cmdline_group_boundary = true;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 591905a02b92..9cd70819c795 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -255,7 +255,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
 	parse_events__free_terms(head);
 	$$ = list;
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-09-02 18:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-09-02 18:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 5b923564ccf43f92969c9e0fd199c8c5db657039 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling fixes plus a handful of late arriving tooling changes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf tools: Fix build on powerpc broken by pt/bts

Kan Liang (1):
      perf evlist: Open event on evsel cpus and threads

Stephane Eranian (4):
      perf script: Enable printing of interrupted machine state
      perf/x86: Add list of register names
      perf record: Add ability to name registers to record
      perf tools: Fix link time error with sample_reg_masks on non x86

Wang Nan (3):
      bpf tools: New API to get name from a BPF object
      perf dwarf: Fix potential array out of bounds access
      perf build: Fix Intel PT instruction decoder dependency problem


 tools/lib/bpf/libbpf.c                             | 25 +++++++-
 tools/lib/bpf/libbpf.h                             |  4 +-
 tools/perf/Documentation/perf-record.txt           |  6 +-
 tools/perf/Documentation/perf-script.txt           |  2 +-
 tools/perf/arch/sh/util/dwarf-regs.c               |  2 +-
 tools/perf/arch/sparc/util/dwarf-regs.c            |  2 +-
 tools/perf/arch/x86/util/Build                     |  1 +
 tools/perf/arch/x86/util/dwarf-regs.c              |  2 +-
 tools/perf/arch/x86/util/perf_regs.c               | 28 +++++++++
 tools/perf/builtin-record.c                        |  9 ++-
 tools/perf/builtin-script.c                        | 31 +++++++++-
 tools/perf/perf.h                                  |  2 +-
 tools/perf/tests/llvm.c                            |  2 +-
 tools/perf/util/Build                              |  2 +
 tools/perf/util/evlist.c                           |  4 ++
 tools/perf/util/evsel.c                            |  2 +-
 tools/perf/util/intel-pt-decoder/Build             |  1 +
 .../util/intel-pt-decoder/intel-pt-insn-decoder.c  |  3 +
 tools/perf/util/parse-regs-options.c               | 71 ++++++++++++++++++++++
 tools/perf/util/parse-regs-options.h               |  5 ++
 tools/perf/util/perf_regs.c                        |  4 ++
 tools/perf/util/perf_regs.h                        |  9 +++
 22 files changed, 201 insertions(+), 16 deletions(-)
 create mode 100644 tools/perf/arch/x86/util/perf_regs.c
 create mode 100644 tools/perf/util/parse-regs-options.c
 create mode 100644 tools/perf/util/parse-regs-options.h

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4fa4bc4505f5..4252fc22f78f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -880,15 +880,26 @@ struct bpf_object *bpf_object__open(const char *path)
 }
 
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz)
+					   size_t obj_buf_sz,
+					   const char *name)
 {
+	char tmp_name[64];
+
 	/* param validation */
 	if (!obj_buf || obj_buf_sz <= 0)
 		return NULL;
 
-	pr_debug("loading object from buffer\n");
+	if (!name) {
+		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
+			 (unsigned long)obj_buf,
+			 (unsigned long)obj_buf_sz);
+		tmp_name[sizeof(tmp_name) - 1] = '\0';
+		name = tmp_name;
+	}
+	pr_debug("loading object '%s' from buffer\n",
+		 name);
 
-	return __bpf_object__open("[buffer]", obj_buf, obj_buf_sz);
+	return __bpf_object__open(name, obj_buf, obj_buf_sz);
 }
 
 int bpf_object__unload(struct bpf_object *obj)
@@ -975,6 +986,14 @@ bpf_object__next(struct bpf_object *prev)
 	return next;
 }
 
+const char *
+bpf_object__get_name(struct bpf_object *obj)
+{
+	if (!obj)
+		return NULL;
+	return obj->path;
+}
+
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index ea8adc206b62..f16170c95ffd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -28,12 +28,14 @@ struct bpf_object;
 
 struct bpf_object *bpf_object__open(const char *path);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz);
+					   size_t obj_buf_sz,
+					   const char *name);
 void bpf_object__close(struct bpf_object *object);
 
 /* Load/unload object into/from kernel */
 int bpf_object__load(struct bpf_object *obj);
 int bpf_object__unload(struct bpf_object *obj);
+const char *bpf_object__get_name(struct bpf_object *obj);
 
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 347a27322ed8..2e9ce77b5e14 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -276,7 +276,11 @@ filter out the startup phase of the program, which is often very different.
 --intr-regs::
 Capture machine state (registers) at interrupt, i.e., on counter overflows for
 each sample. List of captured registers depends on the architecture. This option
-is off by default.
+is off by default. It is possible to select the registers to sample using their
+symbolic names, e.g. on x86, ax, si. To list the available registers use
+--intr-regs=\?. To name registers, pass a comma separated list such as
+--intr-regs=ax,bx. The list of register is architecture dependent.
+
 
 --running-time::
 Record running and enabled time for read events (:S)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 614b2c7b0293..dc3ec783b7bd 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-	srcline, period, flags.
+	srcline, period, iregs, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c
index 0d0897f57a10..f8dfa89696f4 100644
--- a/tools/perf/arch/sh/util/dwarf-regs.c
+++ b/tools/perf/arch/sh/util/dwarf-regs.c
@@ -51,5 +51,5 @@ const char *sh_regs_table[SH_MAX_REGS] = {
 /* Return architecture dependent register string (for kprobe-tracer) */
 const char *get_arch_regstr(unsigned int n)
 {
-	return (n <= SH_MAX_REGS) ? sh_regs_table[n] : NULL;
+	return (n < SH_MAX_REGS) ? sh_regs_table[n] : NULL;
 }
diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c
index 92eda412fed3..b704fdb9237a 100644
--- a/tools/perf/arch/sparc/util/dwarf-regs.c
+++ b/tools/perf/arch/sparc/util/dwarf-regs.c
@@ -39,5 +39,5 @@ const char *sparc_regs_table[SPARC_MAX_REGS] = {
  */
 const char *get_arch_regstr(unsigned int n)
 {
-	return (n <= SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
+	return (n < SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
 }
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 2c55e1b336c5..ff63649fa9ac 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += tsc.o
 libperf-y += pmu.o
 libperf-y += kvm-stat.o
+libperf-y += perf_regs.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index be22dd463232..a08de0a35b83 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -71,5 +71,5 @@ const char *x86_64_regs_table[X86_64_MAX_REGS] = {
 /* Return architecture dependent register string (for kprobe-tracer) */
 const char *get_arch_regstr(unsigned int n)
 {
-	return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
+	return (n < ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
 }
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
new file mode 100644
index 000000000000..c5db14f36cc7
--- /dev/null
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -0,0 +1,28 @@
+#include "../../perf.h"
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG(AX, PERF_REG_X86_AX),
+	SMPL_REG(BX, PERF_REG_X86_BX),
+	SMPL_REG(CX, PERF_REG_X86_CX),
+	SMPL_REG(DX, PERF_REG_X86_DX),
+	SMPL_REG(SI, PERF_REG_X86_SI),
+	SMPL_REG(DI, PERF_REG_X86_DI),
+	SMPL_REG(BP, PERF_REG_X86_BP),
+	SMPL_REG(SP, PERF_REG_X86_SP),
+	SMPL_REG(IP, PERF_REG_X86_IP),
+	SMPL_REG(FLAGS, PERF_REG_X86_FLAGS),
+	SMPL_REG(CS, PERF_REG_X86_CS),
+	SMPL_REG(SS, PERF_REG_X86_SS),
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+	SMPL_REG(R8, PERF_REG_X86_R8),
+	SMPL_REG(R9, PERF_REG_X86_R9),
+	SMPL_REG(R10, PERF_REG_X86_R10),
+	SMPL_REG(R11, PERF_REG_X86_R11),
+	SMPL_REG(R12, PERF_REG_X86_R12),
+	SMPL_REG(R13, PERF_REG_X86_R13),
+	SMPL_REG(R14, PERF_REG_X86_R14),
+	SMPL_REG(R15, PERF_REG_X86_R15),
+#endif
+	SMPL_REG_END
+};
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a660022f2c92..142eeb341b29 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,8 +27,10 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/data.h"
+#include "util/perf_regs.h"
 #include "util/auxtrace.h"
 #include "util/parse-branch-options.h"
+#include "util/parse-regs-options.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -279,7 +281,7 @@ static int record__open(struct record *rec)
 
 	evlist__for_each(evlist, pos) {
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
+		if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
 			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
 				if (verbose)
 					ui__warning("%s\n", msg);
@@ -1080,8 +1082,9 @@ struct option __record_options[] = {
 		    "sample transaction flags (special events only)"),
 	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
 		    "use per-thread mmaps"),
-	OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
-		    "Sample machine registers on interrupt"),
+	OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
+		    "sample selected machine registers on interrupt,"
+		    " use -I ? to list register names", parse_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
 	OPT_CALLBACK('k', "clockid", &record.opts,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4430340292c0..eb51325e8ad9 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -6,6 +6,7 @@
 #include "util/exec_cmd.h"
 #include "util/header.h"
 #include "util/parse-options.h"
+#include "util/perf_regs.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/symbol.h"
@@ -46,6 +47,7 @@ enum perf_output_field {
 	PERF_OUTPUT_SYMOFFSET       = 1U << 11,
 	PERF_OUTPUT_SRCLINE         = 1U << 12,
 	PERF_OUTPUT_PERIOD          = 1U << 13,
+	PERF_OUTPUT_IREGS	    = 1U << 14,
 };
 
 struct output_option {
@@ -66,6 +68,7 @@ struct output_option {
 	{.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
 	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 	{.str = "period", .field = PERF_OUTPUT_PERIOD},
+	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 };
 
 /* default set to maintain compatibility with current format */
@@ -255,6 +258,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_PERIOD))
 		return -EINVAL;
 
+	if (PRINT_FIELD(IREGS) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS",
+					PERF_OUTPUT_IREGS))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -352,6 +360,24 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	return 0;
 }
 
+static void print_sample_iregs(union perf_event *event __maybe_unused,
+			  struct perf_sample *sample,
+			  struct thread *thread __maybe_unused,
+			  struct perf_event_attr *attr)
+{
+	struct regs_dump *regs = &sample->intr_regs;
+	uint64_t mask = attr->sample_regs_intr;
+	unsigned i = 0, r;
+
+	if (!regs)
+		return;
+
+	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs->regs[i++];
+		printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+	}
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)
@@ -525,6 +551,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 				     PERF_MAX_STACK_DEPTH);
 	}
 
+	if (PRINT_FIELD(IREGS))
+		print_sample_iregs(event, sample, thread, attr);
+
 	printf("\n");
 }
 
@@ -1643,7 +1672,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,flags", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cccb4cf575d3..90129accffbe 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,7 +54,6 @@ struct record_opts {
 	bool	     sample_time_set;
 	bool	     callgraph_set;
 	bool	     period;
-	bool	     sample_intr_regs;
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
@@ -64,6 +63,7 @@ struct record_opts {
 	unsigned int auxtrace_mmap_pages;
 	unsigned int user_freq;
 	u64          branch_stack;
+	u64	     sample_intr_regs;
 	u64	     default_interval;
 	u64	     user_interval;
 	size_t	     auxtrace_snapshot_size;
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index a337356fd979..52d55971f66f 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -26,7 +26,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
 
-	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz);
+	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
 	if (!obj)
 		return -1;
 	bpf_object__close(obj);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index e912856cc4e5..349bc96ca1fe 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -75,6 +75,7 @@ libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
 libperf-$(CONFIG_X86) += tsc.o
+libperf-$(CONFIG_AUXTRACE) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
@@ -82,6 +83,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
+libperf-y += parse-regs-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8d00039d6a20..d51a5200c8af 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1181,6 +1181,10 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 		if (evsel->filter == NULL)
 			continue;
 
+		/*
+		 * filters only work for tracepoint event, which doesn't have cpu limit.
+		 * So evlist and evsel should always be same.
+		 */
 		err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter);
 		if (err) {
 			*err_evsel = evsel;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index bac25f41a751..c53f79123b37 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -787,7 +787,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		perf_evsel__config_callgraph(evsel, opts, &callchain_param);
 
 	if (opts->sample_intr_regs) {
-		attr->sample_regs_intr = PERF_REGS_MASK;
+		attr->sample_regs_intr = opts->sample_intr_regs;
 		perf_evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 240730d682c1..2386322ece4f 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -4,6 +4,7 @@ inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
 inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
 
 $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	$(call rule_mkdir)
 	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 9e4eb8fcd559..d23138c06665 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -146,6 +146,9 @@ static void intel_pt_insn_decoder(struct insn *insn,
 		case 4:
 			intel_pt_insn->rel = bswap_32(insn->immediate.value);
 			break;
+		default:
+			intel_pt_insn->rel = 0;
+			break;
 		}
 #else
 		intel_pt_insn->rel = insn->immediate.value;
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
new file mode 100644
index 000000000000..4f2c1c255d81
--- /dev/null
+++ b/tools/perf/util/parse-regs-options.c
@@ -0,0 +1,71 @@
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/parse-regs-options.h"
+
+int
+parse_regs(const struct option *opt, const char *str, int unset)
+{
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct sample_reg *r;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -I */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			if (!strcmp(s, "?")) {
+				fprintf(stderr, "available registers: ");
+				for (r = sample_reg_masks; r->name; r++) {
+					fprintf(stderr, "%s ", r->name);
+				}
+				fputc('\n', stderr);
+				/* just printing available regs */
+				return -1;
+			}
+			for (r = sample_reg_masks; r->name; r++) {
+				if (!strcasecmp(s, r->name))
+					break;
+			}
+			if (!r->name) {
+				ui__warning("unknown register %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= r->mask;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to all possible regs */
+	if (*mode == 0)
+		*mode = PERF_REGS_MASK;
+error:
+	free(os);
+	return ret;
+}
diff --git a/tools/perf/util/parse-regs-options.h b/tools/perf/util/parse-regs-options.h
new file mode 100644
index 000000000000..7d762b188007
--- /dev/null
+++ b/tools/perf/util/parse-regs-options.h
@@ -0,0 +1,5 @@
+#ifndef _PERF_PARSE_REGS_OPTIONS_H
+#define _PERF_PARSE_REGS_OPTIONS_H 1
+struct option;
+int parse_regs(const struct option *opt, const char *str, int unset);
+#endif /* _PERF_PARSE_REGS_OPTIONS_H */
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 43168fb0d9a2..885e8ac83997 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -2,6 +2,10 @@
 #include "perf_regs.h"
 #include "event.h"
 
+const struct sample_reg __weak sample_reg_masks[] = {
+	SMPL_REG_END
+};
+
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
 	int i, idx = 0;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 980dbf76bc98..2984dcc54d67 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -5,6 +5,15 @@
 
 struct regs_dump;
 
+struct sample_reg {
+	const char *name;
+	uint64_t mask;
+};
+#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) }
+#define SMPL_REG_END { .name = NULL }
+
+extern const struct sample_reg sample_reg_masks[];
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-08-22 12:19 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-08-22 12:19 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 196676497f2507966f99abef63bede6a8550f8b3 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling fixes: a 'perf record' deadlock fix plus debuggability fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (3):
      perf tools: Avoid deadlock when map_groups are broken
      perf tools: Make fork event processing more resilient
      perf tools: Fix buildid processing

Arnaldo Carvalho de Melo (1):
      perf top: Show backtrace when handling a SIGSEGV on --stdio mode


 tools/perf/builtin-record.c | 11 +++++++++++
 tools/perf/builtin-top.c    |  4 ++--
 tools/perf/util/machine.c   | 20 ++++++++++++++++++--
 tools/perf/util/thread.c    |  6 ++++++
 4 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index de165a1b9240..20b56eb987f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -521,6 +521,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	/*
+	 * Normally perf_session__new would do this, but it doesn't have the
+	 * evlist.
+	 */
+	if (rec->tool.ordered_events && !perf_evlist__sample_id_all(rec->evlist)) {
+		pr_warning("WARNING: No sample_id_all support, falling back to unordered processing\n");
+		rec->tool.ordered_events = false;
+	}
+
 	if (!rec->evlist->nr_groups)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
@@ -965,9 +974,11 @@ static struct record record = {
 	.tool = {
 		.sample		= process_sample_event,
 		.fork		= perf_event__process_fork,
+		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
 		.mmap		= perf_event__process_mmap,
 		.mmap2		= perf_event__process_mmap2,
+		.ordered_events	= true,
 	},
 };
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ecf319728f25..6135cc07213c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -601,8 +601,8 @@ static void display_sig(int sig __maybe_unused)
 
 static void display_setup_sig(void)
 {
-	signal(SIGSEGV, display_sig);
-	signal(SIGFPE,  display_sig);
+	signal(SIGSEGV, sighandler_dump_stack);
+	signal(SIGFPE, sighandler_dump_stack);
 	signal(SIGINT,  display_sig);
 	signal(SIGQUIT, display_sig);
 	signal(SIGTERM, display_sig);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7ff682770fdb..f1a4c833121e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1387,6 +1387,24 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 							event->fork.ptid);
 	int err = 0;
 
+	if (dump_trace)
+		perf_event__fprintf_task(event, stdout);
+
+	/*
+	 * There may be an existing thread that is not actually the parent,
+	 * either because we are processing events out of order, or because the
+	 * (fork) event that would have removed the thread was lost. Assume the
+	 * latter case and continue on as best we can.
+	 */
+	if (parent->pid_ != (pid_t)event->fork.ppid) {
+		dump_printf("removing erroneous parent thread %d/%d\n",
+			    parent->pid_, parent->tid);
+		machine__remove_thread(machine, parent);
+		thread__put(parent);
+		parent = machine__findnew_thread(machine, event->fork.ppid,
+						 event->fork.ptid);
+	}
+
 	/* if a thread currently exists for the thread id remove it */
 	if (thread != NULL) {
 		machine__remove_thread(machine, thread);
@@ -1395,8 +1413,6 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
-	if (dump_trace)
-		perf_event__fprintf_task(event, stdout);
 
 	if (thread == NULL || parent == NULL ||
 	    thread__fork(thread, parent, sample->time) < 0) {
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 28c4b746baa1..0a9ae8014729 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -191,6 +191,12 @@ static int thread__clone_map_groups(struct thread *thread,
 	if (thread->pid_ == parent->pid_)
 		return 0;
 
+	if (thread->mg == parent->mg) {
+		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
+			 thread->pid_, thread->tid, parent->pid_, parent->tid);
+		return 0;
+	}
+
 	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		if (map_groups__clone(thread->mg, parent->mg, i) < 0)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-08-14  7:12 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-08-14  7:12 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d7a702f0b1033cf402fef65bd6395072738f0844 perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler

Misc fixes: PMU driver corner cases, tooling fixes, and an 'AUX' (Intel PT) race 
related core fix.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf stat: Fix transaction lenght metrics

Ben Hutchings (1):
      perf: Fix double-free of the AUX buffer

Matt Fleming (1):
      perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler

Pawel Moll (1):
      perf tools: Fix test build error when bindir contains double slash

Peter Zijlstra (4):
      perf: Fix running time accounting
      perf: Fix fasync handling on inherited events
      perf: Fix PERF_EVENT_IOC_PERIOD migration race
      perf/x86/intel: Fix memory leak on hot-plug allocation fail


 arch/x86/kernel/cpu/perf_event_intel.c     | 23 +++++---
 arch/x86/kernel/cpu/perf_event_intel_cqm.c |  8 +--
 kernel/events/core.c                       | 91 ++++++++++++++++++++++--------
 kernel/events/ring_buffer.c                | 10 ++--
 tools/perf/config/Makefile                 |  2 +-
 tools/perf/util/stat-shadow.c              |  8 +--
 6 files changed, 96 insertions(+), 46 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b9826a981fb2..6326ae24e4d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2534,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
-			return NOTIFY_BAD;
+			goto err;
 	}
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
@@ -2542,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu)
 
 		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
 		if (!cpuc->constraint_list)
-			return NOTIFY_BAD;
+			goto err_shared_regs;
 
 		cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
-		if (!cpuc->excl_cntrs) {
-			kfree(cpuc->constraint_list);
-			kfree(cpuc->shared_regs);
-			return NOTIFY_BAD;
-		}
+		if (!cpuc->excl_cntrs)
+			goto err_constraint_list;
+
 		cpuc->excl_thread_id = 0;
 	}
 
 	return NOTIFY_OK;
+
+err_constraint_list:
+	kfree(cpuc->constraint_list);
+	cpuc->constraint_list = NULL;
+
+err_shared_regs:
+	kfree(cpuc->shared_regs);
+	cpuc->shared_regs = NULL;
+
+err:
+	return NOTIFY_BAD;
 }
 
 static void intel_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 63eb68b73589..377e8f8ed391 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -1255,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu)
 	cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
-static void intel_cqm_cpu_prepare(unsigned int cpu)
+static void intel_cqm_cpu_starting(unsigned int cpu)
 {
 	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1296,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb,
 	unsigned int cpu  = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		intel_cqm_cpu_prepare(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
 		intel_cqm_cpu_exit(cpu);
 		break;
 	case CPU_STARTING:
+		intel_cqm_cpu_starting(cpu);
 		cqm_pick_event_reader(cpu);
 		break;
 	}
@@ -1373,7 +1371,7 @@ static int __init intel_cqm_init(void)
 		goto out;
 
 	for_each_online_cpu(i) {
-		intel_cqm_cpu_prepare(i);
+		intel_cqm_cpu_starting(i);
 		cqm_pick_event_reader(i);
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3dae3419b99..e6feb5114134 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1868,8 +1868,6 @@ event_sched_in(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
-	event->tstamp_running += tstamp - event->tstamp_stopped;
-
 	perf_set_shadow_time(event, ctx, tstamp);
 
 	perf_log_itrace_start(event);
@@ -1881,6 +1879,8 @@ event_sched_in(struct perf_event *event,
 		goto out;
 	}
 
+	event->tstamp_running += tstamp - event->tstamp_stopped;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	if (!ctx->nr_active++)
@@ -3958,28 +3958,21 @@ static void perf_event_for_each(struct perf_event *event,
 		perf_event_for_each_child(sibling, func);
 }
 
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
-{
-	struct perf_event_context *ctx = event->ctx;
-	int ret = 0, active;
+struct period_event {
+	struct perf_event *event;
 	u64 value;
+};
 
-	if (!is_sampling_event(event))
-		return -EINVAL;
-
-	if (copy_from_user(&value, arg, sizeof(value)))
-		return -EFAULT;
-
-	if (!value)
-		return -EINVAL;
+static int __perf_event_period(void *info)
+{
+	struct period_event *pe = info;
+	struct perf_event *event = pe->event;
+	struct perf_event_context *ctx = event->ctx;
+	u64 value = pe->value;
+	bool active;
 
-	raw_spin_lock_irq(&ctx->lock);
+	raw_spin_lock(&ctx->lock);
 	if (event->attr.freq) {
-		if (value > sysctl_perf_event_sample_rate) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-
 		event->attr.sample_freq = value;
 	} else {
 		event->attr.sample_period = value;
@@ -3998,11 +3991,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->pmu->start(event, PERF_EF_RELOAD);
 		perf_pmu_enable(ctx->pmu);
 	}
+	raw_spin_unlock(&ctx->lock);
 
-unlock:
+	return 0;
+}
+
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
+{
+	struct period_event pe = { .event = event, };
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task;
+	u64 value;
+
+	if (!is_sampling_event(event))
+		return -EINVAL;
+
+	if (copy_from_user(&value, arg, sizeof(value)))
+		return -EFAULT;
+
+	if (!value)
+		return -EINVAL;
+
+	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
+		return -EINVAL;
+
+	task = ctx->task;
+	pe.value = value;
+
+	if (!task) {
+		cpu_function_call(event->cpu, __perf_event_period, &pe);
+		return 0;
+	}
+
+retry:
+	if (!task_function_call(task, __perf_event_period, &pe))
+		return 0;
+
+	raw_spin_lock_irq(&ctx->lock);
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		task = ctx->task;
+		goto retry;
+	}
+
+	__perf_event_period(&pe);
 	raw_spin_unlock_irq(&ctx->lock);
 
-	return ret;
+	return 0;
 }
 
 static const struct file_operations perf_fops;
@@ -4740,12 +4775,20 @@ static const struct file_operations perf_fops = {
  * to user-space before waking everybody up.
  */
 
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+	/* only the parent has fasync state */
+	if (event->parent)
+		event = event->parent;
+	return &event->fasync;
+}
+
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
-		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
 		event->pending_kill = 0;
 	}
 }
@@ -6124,7 +6167,7 @@ static int __perf_event_overflow(struct perf_event *event,
 	else
 		perf_event_output(event, data, regs);
 
-	if (event->fasync && event->pending_kill) {
+	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending);
 	}
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index b2be01b1aa9d..c8aa3f75bc4d 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -559,11 +559,13 @@ static void __rb_free_aux(struct ring_buffer *rb)
 		rb->aux_priv = NULL;
 	}
 
-	for (pg = 0; pg < rb->aux_nr_pages; pg++)
-		rb_free_aux_page(rb, pg);
+	if (rb->aux_nr_pages) {
+		for (pg = 0; pg < rb->aux_nr_pages; pg++)
+			rb_free_aux_page(rb, pg);
 
-	kfree(rb->aux_pages);
-	rb->aux_nr_pages = 0;
+		kfree(rb->aux_pages);
+		rb->aux_nr_pages = 0;
+	}
 }
 
 void rb_free_aux(struct ring_buffer *rb)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 094ddaee104c..d31fac19c30b 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -638,7 +638,7 @@ ifndef DESTDIR
 prefix ?= $(HOME)
 endif
 bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 53e8bb7bc852..2a5d8d7698ae 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -85,7 +85,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
 		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
@@ -398,20 +398,18 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				" #   %5.2f%% aborted cycles         ",
 				100.0 * ((total2-avg) / total));
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   avg > 0 &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-		if (total)
+		if (avg)
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   avg > 0 &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-		if (total)
+		if (avg)
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-07-18  2:53 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-07-18  2:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: a6acd6a41168dc304738e84c8360cda9a6b86887 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, plus a static key fix fixing /sys/devices/cpu/rdpmc.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf tools: Fix lockup using 32-bit compat vdso
      perf auxtrace: Fix misplaced check for HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT

Alexey Brodkin (1):
      perf tools: Really allow to specify custom CC, AR or LD

Arnaldo Carvalho de Melo (5):
      perf thread_map: Fix the sizeof() calculation for map entries
      perf tools: Fix the detached tarball wrt rbtree copy
      tools: Copy lib/hweight.c from the kernel sources
      perf symbols: Store if there is a filter in place
      perf hists browser: Take the --comm, --dsos, etc filters into account

Jiri Olsa (1):
      perf stat: Fix shadow declaration of close

Peter Zijlstra (1):
      x86, perf: Fix static_key bug in load_mm_cr4()

Riku Voipio (1):
      tools lib: Improve clean target


 arch/x86/include/asm/mmu_context.h |  2 +-
 tools/lib/api/Makefile             |  2 +-
 tools/lib/hweight.c                | 62 ++++++++++++++++++++++++++++++++++++++
 tools/lib/traceevent/Makefile      |  2 +-
 tools/perf/MANIFEST                |  2 +-
 tools/perf/Makefile.perf           | 19 ++++++++++--
 tools/perf/builtin-stat.c          |  4 +--
 tools/perf/ui/browsers/hists.c     |  2 +-
 tools/perf/util/Build              |  2 +-
 tools/perf/util/auxtrace.c         | 10 +++---
 tools/perf/util/python-ext-sources |  4 +--
 tools/perf/util/symbol.c           |  2 ++
 tools/perf/util/symbol.h           |  3 +-
 tools/perf/util/thread_map.c       |  3 +-
 tools/perf/util/vdso.c             |  8 ++---
 15 files changed, 101 insertions(+), 26 deletions(-)
 create mode 100644 tools/lib/hweight.c

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5e8daee7c5c9..804a3a6030ca 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -23,7 +23,7 @@ extern struct static_key rdpmc_always_available;
 
 static inline void load_mm_cr4(struct mm_struct *mm)
 {
-	if (static_key_true(&rdpmc_always_available) ||
+	if (static_key_false(&rdpmc_always_available) ||
 	    atomic_read(&mm->context.perf_rdpmc_allowed))
 		cr4_set_bits(X86_CR4_PCE);
 	else
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 8bd960658463..fe1b02c2c95b 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -36,7 +36,7 @@ $(LIBFILE): $(API_IN)
 
 clean:
 	$(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \
-	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o | xargs $(RM)
+	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
 
 FORCE:
 
diff --git a/tools/lib/hweight.c b/tools/lib/hweight.c
new file mode 100644
index 000000000000..0b859b884339
--- /dev/null
+++ b/tools/lib/hweight.c
@@ -0,0 +1,62 @@
+#include <linux/bitops.h>
+#include <asm/types.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int __sw_hweight32(unsigned int w)
+{
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x55555555;
+	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f;
+	return (w * 0x01010101) >> 24;
+#else
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+#endif
+}
+
+unsigned int __sw_hweight16(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x5555);
+	res = (res & 0x3333) + ((res >> 2) & 0x3333);
+	res = (res + (res >> 4)) & 0x0F0F;
+	return (res + (res >> 8)) & 0x00FF;
+}
+
+unsigned int __sw_hweight8(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55);
+	res = (res & 0x33) + ((res >> 2) & 0x33);
+	return (res + (res >> 4)) & 0x0F;
+}
+
+unsigned long __sw_hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return __sw_hweight32((unsigned int)(w >> 32)) +
+	       __sw_hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x5555555555555555ul;
+	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
+	return (w * 0x0101010101010101ul) >> 56;
+#else
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+#endif
+}
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 6daaff652aff..7851df1490e0 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -268,7 +268,7 @@ install: install_lib
 
 clean:
 	$(call QUIET_CLEAN, libtraceevent) \
-		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
 		$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 PHONY += force plugins
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 09dc0aabb515..d01a0aad5a01 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@ tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/hweight.c
 tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
@@ -57,7 +58,6 @@ include/linux/perf_event.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/hweight.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7a4b549214e3..bba34636b733 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -109,9 +109,22 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
 	$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
-CC = $(CROSS_COMPILE)gcc
-LD ?= $(CROSS_COMPILE)ld
-AR = $(CROSS_COMPILE)ar
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 37e301a32f43..d99d850e1444 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -343,7 +343,7 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void read_counters(bool close)
+static void read_counters(bool close_counters)
 {
 	struct perf_evsel *counter;
 
@@ -354,7 +354,7 @@ static void read_counters(bool close)
 		if (process_counter(counter))
 			pr_warning("failed to process counter %s\n", counter->name);
 
-		if (close) {
+		if (close_counters) {
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
 					     thread_map__nr(evsel_list->threads));
 		}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7629bef2fd79..fa67613976a8 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -48,7 +48,7 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
 {
-	return hists__has_filter(hb->hists) || hb->min_pcnt;
+	return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter;
 }
 
 static int hist_browser__get_folding(struct hist_browser *browser)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 601d11440596..d2d318c59b37 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -143,6 +143,6 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE
+$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7e7405c9b936..83d9dd96fe08 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -53,11 +53,6 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 {
 	struct perf_event_mmap_page *pc = userpg;
 
-#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
-	pr_err("Cannot use AUX area tracing mmaps\n");
-	return -1;
-#endif
-
 	WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
 
 	mm->userpg = userpg;
@@ -73,6 +68,11 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 		return 0;
 	}
 
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pr_err("Cannot use AUX area tracing mmaps\n");
+	return -1;
+#endif
+
 	pc->aux_offset = mp->offset;
 	pc->aux_size = mp->len;
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e23ded40c79e..0766d98c5da5 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-../../lib/hweight.c
+../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
@@ -19,5 +19,5 @@ util/rblist.c
 util/stat.c
 util/strlist.c
 util/trace-event.c
-../../lib/rbtree.c
+../lib/rbtree.c
 util/string.c
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 48b588c6951a..60f11414bb5c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1911,6 +1911,8 @@ int setup_list(struct strlist **list, const char *list_str,
 		pr_err("problems parsing %s list\n", list_name);
 		return -1;
 	}
+
+	symbol_conf.has_filter = true;
 	return 0;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bef47ead1d9b..b98ce51af142 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -105,7 +105,8 @@ struct symbol_conf {
 			demangle_kernel,
 			filter_relative,
 			show_hist_headers,
-			branch_callstack;
+			branch_callstack,
+			has_filter;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index da7646d767fe..292ae2c90e06 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -136,8 +136,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		if (grow) {
 			struct thread_map *tmp;
 
-			tmp = realloc(threads, (sizeof(*threads) +
-						max_threads * sizeof(pid_t)));
+			tmp = thread_map__realloc(threads, max_threads);
 			if (tmp == NULL)
 				goto out_free_namelist;
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 4b89118f158d..44d440da15dc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -236,18 +236,16 @@ static struct dso *__machine__findnew_compat(struct machine *machine,
 	const char *file_name;
 	struct dso *dso;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
 	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		goto out_unlock;
+		goto out;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		goto out_unlock;
+		goto out;
 
 	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out_unlock:
-	pthread_rwlock_unlock(&machine->dsos.lock);
+out:
 	return dso;
 }
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-07-06 15:29 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-07-06 15:29 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: ebf2d2689de551d90965090bb991fc640a0c0d41 perf/x86: Fix copy_from_user_nmi() return if range is not ok

This:

  - Fixes the perf build, by fixing the rbtree.c sharing bug between kernel and 
    tools/perf by creating a local copy of rbtree.c (more will be done for v4.3)

  - Fixes an AUX buffer (Intel-PT support) refcounting bug

  - Fixes copy_from_user_nmi() return value.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (5):
      tools: Adopt {READ,WRITE_ONCE} from the kernel
      perf tools: Copy rbtree.h from the kernel
      tools: Copy lib/rbtree.c to tools/lib/
      tools: Move rbtree.h from tools/perf/
      tools: Copy rbtree_augmented.h from the kernel

Peter Zijlstra (1):
      perf: Fix AUX buffer refcounting

Yann Droneaud (1):
      perf/x86: Fix copy_from_user_nmi() return if range is not ok


 arch/x86/lib/usercopy.c                          |   2 +-
 kernel/events/core.c                             |   8 -
 kernel/events/internal.h                         |  10 +
 kernel/events/ring_buffer.c                      |  27 +-
 tools/include/linux/compiler.h                   |  58 +++
 tools/include/linux/export.h                     |  10 -
 tools/include/linux/rbtree.h                     | 104 +++++
 tools/include/linux/rbtree_augmented.h           | 245 ++++++++++
 tools/lib/rbtree.c                               | 548 +++++++++++++++++++++++
 tools/perf/MANIFEST                              |   6 +-
 tools/perf/util/Build                            |   2 +-
 tools/perf/util/include/linux/rbtree.h           |  16 -
 tools/perf/util/include/linux/rbtree_augmented.h |   2 -
 13 files changed, 995 insertions(+), 43 deletions(-)
 delete mode 100644 tools/include/linux/export.h
 create mode 100644 tools/include/linux/rbtree.h
 create mode 100644 tools/include/linux/rbtree_augmented.h
 create mode 100644 tools/lib/rbtree.c
 delete mode 100644 tools/perf/util/include/linux/rbtree.h
 delete mode 100644 tools/perf/util/include/linux/rbtree_augmented.h

diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ddf9ecb53cc3..e342586db6e4 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -20,7 +20,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	unsigned long ret;
 
 	if (__range_not_ok(from, n, TASK_SIZE))
-		return 0;
+		return n;
 
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e965cfae4207..d3dae3419b99 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4358,14 +4358,6 @@ static void ring_buffer_wakeup(struct perf_event *event)
 	rcu_read_unlock();
 }
 
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
-	struct ring_buffer *rb;
-
-	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
-	rb_free(rb);
-}
-
 struct ring_buffer *ring_buffer_get(struct perf_event *event)
 {
 	struct ring_buffer *rb;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2deb24c7a40d..2bbad9c1274c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
 struct ring_buffer {
 	atomic_t			refcount;
 	struct rcu_head			rcu_head;
+	struct irq_work			irq_work;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
 	int				page_order;	/* allocation order  */
@@ -55,6 +56,15 @@ struct ring_buffer {
 };
 
 extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct ring_buffer *rb;
+
+	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+	rb_free(rb);
+}
+
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 96472824a752..b2be01b1aa9d 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -221,6 +221,8 @@ void perf_output_end(struct perf_output_handle *handle)
 	rcu_read_unlock();
 }
 
+static void rb_irq_work(struct irq_work *work);
+
 static void
 ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 {
@@ -241,6 +243,16 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
+	init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+	if (!atomic_dec_and_test(&rb->refcount))
+		return;
+
+	rb->rcu_head.next = (void *)rb;
+	irq_work_queue(&rb->irq_work);
 }
 
 /*
@@ -319,7 +331,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	rb_free_aux(rb);
 
 err:
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 	handle->event = NULL;
 
 	return NULL;
@@ -370,7 +382,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 
 	local_set(&rb->aux_nest, 0);
 	rb_free_aux(rb);
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 }
 
 /*
@@ -557,7 +569,18 @@ static void __rb_free_aux(struct ring_buffer *rb)
 void rb_free_aux(struct ring_buffer *rb)
 {
 	if (atomic_dec_and_test(&rb->aux_refcount))
+		irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+	struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+	if (!atomic_read(&rb->aux_refcount))
 		__rb_free_aux(rb);
+
+	if (rb->rcu_head.next == (void *)rb)
+		call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index f0e72674c52d..9098083869c8 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -41,4 +41,62 @@
 
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
+#include <linux/types.h>
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+	case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+	case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+	case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+	case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+	case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		barrier();
+	}
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering.  One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#define WRITE_ONCE(x, val) \
+	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h
deleted file mode 100644
index d07e586b9ba0..000000000000
--- a/tools/include/linux/export.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _TOOLS_LINUX_EXPORT_H_
-#define _TOOLS_LINUX_EXPORT_H_
-
-#define EXPORT_SYMBOL(sym)
-#define EXPORT_SYMBOL_GPL(sym)
-#define EXPORT_SYMBOL_GPL_FUTURE(sym)
-#define EXPORT_UNUSED_SYMBOL(sym)
-#define EXPORT_UNUSED_SYMBOL_GPL(sym)
-
-#endif
diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h
new file mode 100644
index 000000000000..112582253dd0
--- /dev/null
+++ b/tools/include/linux/rbtree.h
@@ -0,0 +1,104 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree.h
+
+  To use rbtrees you'll have to implement your own insert and search cores.
+  This will avoid us to use callbacks and to drop drammatically performances.
+  I know it's not the cleaner way,  but in C (not in C++) to get
+  performances and genericity...
+
+  See Documentation/rbtree.txt for documentation and samples.
+*/
+
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+	unsigned long  __rb_parent_color;
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+    /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+	struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT	(struct rb_root) { NULL, }
+#define	rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node)  \
+	((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node)  \
+	((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+			    struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+				struct rb_node **rb_link)
+{
+	node->__rb_parent_color = (unsigned long)parent;
+	node->rb_left = node->rb_right = NULL;
+
+	*rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+	})
+
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h
new file mode 100644
index 000000000000..43be941db695
--- /dev/null
+++ b/tools/include/linux/rbtree_augmented.h
@@ -0,0 +1,245 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  tools/linux/include/linux/rbtree_augmented.h
+
+  Copied from:
+  linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _TOOLS_LINUX_RBTREE_AUGMENTED_H
+#define _TOOLS_LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+	void (*propagate)(struct rb_node *node, struct rb_node *stop);
+	void (*copy)(struct rb_node *old, struct rb_node *new);
+	void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+		    const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
+			     rbtype, rbaugmented, rbcompute)		\
+static inline void							\
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop)		\
+{									\
+	while (rb != stop) {						\
+		rbstruct *node = rb_entry(rb, rbstruct, rbfield);	\
+		rbtype augmented = rbcompute(node);			\
+		if (node->rbaugmented == augmented)			\
+			break;						\
+		node->rbaugmented = augmented;				\
+		rb = rb_parent(&node->rbfield);				\
+	}								\
+}									\
+static inline void							\
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new)		\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+}									\
+static void								\
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+	old->rbaugmented = rbcompute(old);				\
+}									\
+rbstatic const struct rb_augment_callbacks rbname = {			\
+	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+};
+
+
+#define	RB_RED		0
+#define	RB_BLACK	1
+
+#define __rb_parent(pc)    ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc)     ((pc) & 1)
+#define __rb_is_black(pc)  __rb_color(pc)
+#define __rb_is_red(pc)    (!__rb_color(pc))
+#define rb_color(rb)       __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb)      __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb)    __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+				       struct rb_node *p, int color)
+{
+	rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+		  struct rb_node *parent, struct rb_root *root)
+{
+	if (parent) {
+		if (parent->rb_left == old)
+			parent->rb_left = new;
+		else
+			parent->rb_right = new;
+	} else
+		root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *parent, *rebalance;
+	unsigned long pc;
+
+	if (!tmp) {
+		/*
+		 * Case 1: node to erase has no more than 1 child (easy!)
+		 *
+		 * Note that if there is one child it must be red due to 5)
+		 * and node must be black due to 4). We adjust colors locally
+		 * so as to bypass __rb_erase_color() later on.
+		 */
+		pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, child, parent, root);
+		if (child) {
+			child->__rb_parent_color = pc;
+			rebalance = NULL;
+		} else
+			rebalance = __rb_is_black(pc) ? parent : NULL;
+		tmp = parent;
+	} else if (!child) {
+		/* Still case 1, but this time the child is node->rb_left */
+		tmp->__rb_parent_color = pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, tmp, parent, root);
+		rebalance = NULL;
+		tmp = parent;
+	} else {
+		struct rb_node *successor = child, *child2;
+		tmp = child->rb_left;
+		if (!tmp) {
+			/*
+			 * Case 2: node's successor is its right child
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (s)  ->  (x) (c)
+			 *        \
+			 *        (c)
+			 */
+			parent = successor;
+			child2 = successor->rb_right;
+			augment->copy(node, successor);
+		} else {
+			/*
+			 * Case 3: node's successor is leftmost under
+			 * node's right child subtree
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (y)  ->  (x) (y)
+			 *      /            /
+			 *    (p)          (p)
+			 *    /            /
+			 *  (s)          (c)
+			 *    \
+			 *    (c)
+			 */
+			do {
+				parent = successor;
+				successor = tmp;
+				tmp = tmp->rb_left;
+			} while (tmp);
+			parent->rb_left = child2 = successor->rb_right;
+			successor->rb_right = child;
+			rb_set_parent(child, successor);
+			augment->copy(node, successor);
+			augment->propagate(parent, successor);
+		}
+
+		successor->rb_left = tmp = node->rb_left;
+		rb_set_parent(tmp, successor);
+
+		pc = node->__rb_parent_color;
+		tmp = __rb_parent(pc);
+		__rb_change_child(node, successor, tmp, root);
+		if (child2) {
+			successor->__rb_parent_color = pc;
+			rb_set_parent_color(child2, parent, RB_BLACK);
+			rebalance = NULL;
+		} else {
+			unsigned long pc2 = successor->__rb_parent_color;
+			successor->__rb_parent_color = pc;
+			rebalance = __rb_is_black(pc2) ? parent : NULL;
+		}
+		tmp = successor;
+	}
+
+	augment->propagate(tmp, NULL);
+	return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif	/* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
new file mode 100644
index 000000000000..17c2b596f043
--- /dev/null
+++ b/tools/lib/rbtree.c
@@ -0,0 +1,548 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/lib/rbtree.c
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ *
+ *  1) A node is either red or black
+ *  2) The root is black
+ *  3) All leaves (NULL) are black
+ *  4) Both children of every red node are black
+ *  5) Every simple path from root to leaves contains the same number
+ *     of black nodes.
+ *
+ *  4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ *  consecutive red nodes in a path and every red node is therefore followed by
+ *  a black. So if B is the number of black nodes on every simple path (as per
+ *  5), then the longest possible path due to 4 is 2B.
+ *
+ *  We shall indicate color with case, where black nodes are uppercase and red
+ *  nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ *  parentheses and have some accompanying text comment.
+ */
+
+static inline void rb_set_black(struct rb_node *rb)
+{
+	rb->__rb_parent_color |= RB_BLACK;
+}
+
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
+{
+	return (struct rb_node *)red->__rb_parent_color;
+}
+
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+			struct rb_root *root, int color)
+{
+	struct rb_node *parent = rb_parent(old);
+	new->__rb_parent_color = old->__rb_parent_color;
+	rb_set_parent_color(old, new, color);
+	__rb_change_child(old, new, parent, root);
+}
+
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+	    void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+	while (true) {
+		/*
+		 * Loop invariant: node is red
+		 *
+		 * If there is a black parent, we are done.
+		 * Otherwise, take some corrective action as we don't
+		 * want a red root or two consecutive red nodes.
+		 */
+		if (!parent) {
+			rb_set_parent_color(node, NULL, RB_BLACK);
+			break;
+		} else if (rb_is_black(parent))
+			break;
+
+		gparent = rb_red_parent(parent);
+
+		tmp = gparent->rb_right;
+		if (parent != tmp) {	/* parent == gparent->rb_left */
+			if (tmp && rb_is_red(tmp)) {
+				/*
+				 * Case 1 - color flips
+				 *
+				 *       G            g
+				 *      / \          / \
+				 *     p   u  -->   P   U
+				 *    /            /
+				 *   n            n
+				 *
+				 * However, since g's parent might be red, and
+				 * 4) does not allow this, we need to recurse
+				 * at g.
+				 */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_right;
+			if (node == tmp) {
+				/*
+				 * Case 2 - left rotate at parent
+				 *
+				 *      G             G
+				 *     / \           / \
+				 *    p   U  -->    n   U
+				 *     \           /
+				 *      n         p
+				 *
+				 * This still leaves us in violation of 4), the
+				 * continuation into Case 3 will fix that.
+				 */
+				parent->rb_right = tmp = node->rb_left;
+				node->rb_left = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_right;
+			}
+
+			/*
+			 * Case 3 - right rotate at gparent
+			 *
+			 *        G           P
+			 *       / \         / \
+			 *      p   U  -->  n   g
+			 *     /                 \
+			 *    n                   U
+			 */
+			gparent->rb_left = tmp;  /* == parent->rb_right */
+			parent->rb_right = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		} else {
+			tmp = gparent->rb_left;
+			if (tmp && rb_is_red(tmp)) {
+				/* Case 1 - color flips */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_left;
+			if (node == tmp) {
+				/* Case 2 - right rotate at parent */
+				parent->rb_left = tmp = node->rb_right;
+				node->rb_right = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_left;
+			}
+
+			/* Case 3 - left rotate at gparent */
+			gparent->rb_right = tmp;  /* == parent->rb_left */
+			parent->rb_left = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		}
+	}
+}
+
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+	while (true) {
+		/*
+		 * Loop invariants:
+		 * - node is black (or NULL on first iteration)
+		 * - node is not the root (parent is not NULL)
+		 * - All leaf paths going through parent and node have a
+		 *   black node count that is 1 lower than other leaf paths.
+		 */
+		sibling = parent->rb_right;
+		if (node != sibling) {	/* node == parent->rb_left */
+			if (rb_is_red(sibling)) {
+				/*
+				 * Case 1 - left rotate at parent
+				 *
+				 *     P               S
+				 *    / \             / \
+				 *   N   s    -->    p   Sr
+				 *      / \         / \
+				 *     Sl  Sr      N   Sl
+				 */
+				parent->rb_right = tmp1 = sibling->rb_left;
+				sibling->rb_left = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_right;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_left;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/*
+					 * Case 2 - sibling color flip
+					 * (p could be either color here)
+					 *
+					 *    (p)           (p)
+					 *    / \           / \
+					 *   N   S    -->  N   s
+					 *      / \           / \
+					 *     Sl  Sr        Sl  Sr
+					 *
+					 * This leaves us violating 5) which
+					 * can be fixed by flipping p to black
+					 * if it was red, or by recursing at p.
+					 * p is red when coming from Case 1.
+					 */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/*
+				 * Case 3 - right rotate at sibling
+				 * (p could be either color here)
+				 *
+				 *   (p)           (p)
+				 *   / \           / \
+				 *  N   S    -->  N   Sl
+				 *     / \             \
+				 *    sl  Sr            s
+				 *                       \
+				 *                        Sr
+				 */
+				sibling->rb_left = tmp1 = tmp2->rb_right;
+				tmp2->rb_right = sibling;
+				parent->rb_right = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/*
+			 * Case 4 - left rotate at parent + color flips
+			 * (p and sl could be either color here.
+			 *  After rotation, p becomes black, s acquires
+			 *  p's color, and sl keeps its color)
+			 *
+			 *      (p)             (s)
+			 *      / \             / \
+			 *     N   S     -->   P   Sr
+			 *        / \         / \
+			 *      (sl) sr      N  (sl)
+			 */
+			parent->rb_right = tmp2 = sibling->rb_left;
+			sibling->rb_left = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		} else {
+			sibling = parent->rb_left;
+			if (rb_is_red(sibling)) {
+				/* Case 1 - right rotate at parent */
+				parent->rb_left = tmp1 = sibling->rb_right;
+				sibling->rb_right = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_left;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_right;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/* Case 2 - sibling color flip */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/* Case 3 - right rotate at sibling */
+				sibling->rb_right = tmp1 = tmp2->rb_left;
+				tmp2->rb_left = sibling;
+				parent->rb_left = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/* Case 4 - left rotate at parent + color flips */
+			parent->rb_left = tmp2 = sibling->rb_right;
+			sibling->rb_right = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		}
+	}
+}
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	____rb_erase_color(parent, root, augment_rotate);
+}
+
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
+
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
+
+static const struct rb_augment_callbacks dummy_callbacks = {
+	dummy_propagate, dummy_copy, dummy_rotate
+};
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+	__rb_insert(node, root, dummy_rotate);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+/*
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
+ */
+
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	__rb_insert(node, root, augment_rotate);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_left)
+		n = n->rb_left;
+	return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_right)
+		n = n->rb_right;
+	return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a right-hand child, go down and then left as far
+	 * as we can.
+	 */
+	if (node->rb_right) {
+		node = node->rb_right;
+		while (node->rb_left)
+			node=node->rb_left;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No right-hand children. Everything down and left is smaller than us,
+	 * so any 'next' node must be in the general direction of our parent.
+	 * Go up the tree; any time the ancestor is a right-hand child of its
+	 * parent, keep going up. First time it's a left-hand child of its
+	 * parent, said parent is our 'next' node.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_right)
+		node = parent;
+
+	return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a left-hand child, go down and then right as far
+	 * as we can.
+	 */
+	if (node->rb_left) {
+		node = node->rb_left;
+		while (node->rb_right)
+			node=node->rb_right;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No left-hand children. Go up till we find an ancestor which
+	 * is a right-hand child of its parent.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_left)
+		node = parent;
+
+	return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+		     struct rb_root *root)
+{
+	struct rb_node *parent = rb_parent(victim);
+
+	/* Set the surrounding nodes to point to the replacement */
+	__rb_change_child(victim, new, parent, root);
+	if (victim->rb_left)
+		rb_set_parent(victim->rb_left, new);
+	if (victim->rb_right)
+		rb_set_parent(victim->rb_right, new);
+
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+}
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+	for (;;) {
+		if (node->rb_left)
+			node = node->rb_left;
+		else if (node->rb_right)
+			node = node->rb_right;
+		else
+			return (struct rb_node *)node;
+	}
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+	const struct rb_node *parent;
+	if (!node)
+		return NULL;
+	parent = rb_parent(node);
+
+	/* If we're sitting on node, we've already seen our children */
+	if (parent && node == parent->rb_left && parent->rb_right) {
+		/* If we are the parent's left node, go to the parent's right
+		 * node then all the way down to the left */
+		return rb_left_deepest_node(parent->rb_right);
+	} else
+		/* Otherwise we are the parent's right node, and the parent
+		 * should be next */
+		return (struct rb_node *)parent;
+}
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+	if (!root->rb_node)
+		return NULL;
+
+	return rb_left_deepest_node(root->rb_node);
+}
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index fe50a1b34aa0..09dc0aabb515 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@ tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
@@ -44,6 +45,8 @@ tools/include/linux/kernel.h
 tools/include/linux/list.h
 tools/include/linux/log2.h
 tools/include/linux/poison.h
+tools/include/linux/rbtree.h
+tools/include/linux/rbtree_augmented.h
 tools/include/linux/types.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
@@ -51,12 +54,10 @@ include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/linux/perf_event.h
-include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
 lib/hweight.c
-lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
@@ -65,7 +66,6 @@ arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/hw_breakpoint.h
-include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 586a59d46022..601d11440596 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -139,7 +139,7 @@ $(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE
+$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
deleted file mode 100644
index f06d89f0b867..000000000000
--- a/tools/perf/util/include/linux/rbtree.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __TOOLS_LINUX_PERF_RBTREE_H
-#define __TOOLS_LINUX_PERF_RBTREE_H
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree.h"
-
-/*
- * Handy for checking that we are not deleting an entry that is
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
- * probably should be moved to lib/rbtree.c...
- */
-static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
-{
-	rb_erase(n, root);
-	RB_CLEAR_NODE(n);
-}
-#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
deleted file mode 100644
index 9d6fcdf1788b..000000000000
--- a/tools/perf/util/include/linux/rbtree_augmented.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree_augmented.h"

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-06-13 14:29 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-06-13 14:29 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 15c1247953e8a45232ed5a5540f291d2d0a77665 Revert "perf/x86/intel/uncore: Move uncore_box_init() out of driver initialization"

A regression fix for a crash, and a Intel HSW uncore PMU driver fix.

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      Revert "perf/x86/intel/uncore: Move uncore_box_init() out of driver initialization"

Kan Liang (1):
      perf/x86/intel/uncore: Fix CBOX bit wide and UBOX reg on Haswell-EP


 arch/x86/kernel/cpu/perf_event_intel_uncore.c       |  9 +++++++--
 arch/x86/kernel/cpu/perf_event_intel_uncore.h       | 18 ++++++++----------
 arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c |  6 +++---
 3 files changed, 18 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index dd319e59246b..90b7c501c95b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -839,6 +839,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
+	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -1002,8 +1003,10 @@ static int uncore_cpu_starting(int cpu)
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0)
+			if (box && box->phys_id >= 0) {
+				uncore_box_init(box);
 				continue;
+			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1019,8 +1022,10 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			if (box)
+			if (box) {
 				box->phys_id = phys_id;
+				uncore_box_init(box);
+			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index f789ec9a0133..ceac8f5dc018 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -258,14 +258,6 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	return box->pmu->type->num_counters;
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -274,8 +266,6 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
-	uncore_box_init(box);
-
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -298,6 +288,14 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 12d9548457e7..6d6e85dd5849 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -164,8 +164,8 @@
 				((1ULL << (n)) - 1)))
 
 /* Haswell-EP Ubox */
-#define HSWEP_U_MSR_PMON_CTR0			0x705
-#define HSWEP_U_MSR_PMON_CTL0			0x709
+#define HSWEP_U_MSR_PMON_CTR0			0x709
+#define HSWEP_U_MSR_PMON_CTL0			0x705
 #define HSWEP_U_MSR_PMON_FILTER			0x707
 
 #define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL		0x703
@@ -1914,7 +1914,7 @@ static struct intel_uncore_type hswep_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 4,
 	.num_boxes		= 18,
-	.perf_ctr_bits		= 44,
+	.perf_ctr_bits		= 48,
 	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
 	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
 	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-06-05  8:37 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-06-05  8:37 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Peter Zijlstra, Arnaldo Carvalho de Melo, Thomas Gleixner,
	Andrew Morton, linux-kernel

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b44a2b53becf2485f484bd6bb6c1d963ebc339f8 perf/x86/intel/pt: Fix a refactoring bug

The biggest chunk of the changes are two regression fixes: a HT workaround fix and 
an event-group scheduling fix. It's been verified with 5 days of fuzzer testing.

Other fixes:

   - eBPF fix,
   - a BIOS breakage detection fix
   - PMU driver fixes.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (3):
      perf: Disallow sparse AUX allocations for non-SG PMUs in overwrite mode
      perf/x86/intel/pt: Untangle pt_buffer_reset_markers()
      perf/x86/intel/pt: Fix a refactoring bug

Alexei Starovoitov (1):
      perf: Fix race in BPF program unregister

Don Zickus (1):
      perf/x86: Tweak broken BIOS rules during check_hw_exists()

Peter Zijlstra (2):
      perf/x86: Fix event/group validation
      perf/x86: Improve HT workaround GP counter constraint


 arch/x86/kernel/cpu/perf_event.c              | 83 ++++++++++++++++++++-------
 arch/x86/kernel/cpu/perf_event.h              | 24 +++++---
 arch/x86/kernel/cpu/perf_event_intel.c        | 45 +++++----------
 arch/x86/kernel/cpu/perf_event_intel_ds.c     |  4 +-
 arch/x86/kernel/cpu/perf_event_intel_pt.c     | 36 +++++++-----
 arch/x86/kernel/cpu/perf_event_intel_uncore.c |  9 ++-
 arch/x86/kernel/cpu/perf_event_intel_uncore.h |  1 +
 include/linux/perf_event.h                    |  4 --
 kernel/events/core.c                          |  3 +-
 kernel/events/ring_buffer.c                   | 14 +++++
 10 files changed, 139 insertions(+), 84 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87848ebe2bb7..4f7001f28936 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -190,6 +190,7 @@ static bool check_hw_exists(void)
 	u64 val, val_fail, val_new= ~0;
 	int i, reg, reg_fail, ret = 0;
 	int bios_fail = 0;
+	int reg_safe = -1;
 
 	/*
 	 * Check to see if the BIOS enabled any of the counters, if so
@@ -204,6 +205,8 @@ static bool check_hw_exists(void)
 			bios_fail = 1;
 			val_fail = val;
 			reg_fail = reg;
+		} else {
+			reg_safe = i;
 		}
 	}
 
@@ -222,11 +225,22 @@ static bool check_hw_exists(void)
 	}
 
 	/*
+	 * If all the counters are enabled, the below test will always
+	 * fail.  The tools will also become useless in this scenario.
+	 * Just fail and disable the hardware counters.
+	 */
+
+	if (reg_safe == -1) {
+		reg = reg_safe;
+		goto msr_fail;
+	}
+
+	/*
 	 * Read the current value, change it and read it back to see if it
 	 * matches, this is needed to detect certain hardware emulators
 	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
-	reg = x86_pmu_event_addr(0);
+	reg = x86_pmu_event_addr(reg_safe);
 	if (rdmsrl_safe(reg, &val))
 		goto msr_fail;
 	val ^= 0xffffUL;
@@ -611,6 +625,7 @@ struct sched_state {
 	int	event;		/* event index */
 	int	counter;	/* counter index */
 	int	unassigned;	/* number of events to be assigned left */
+	int	nr_gp;		/* number of GP counters used */
 	unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 };
 
@@ -620,27 +635,29 @@ struct sched_state {
 struct perf_sched {
 	int			max_weight;
 	int			max_events;
-	struct perf_event	**events;
-	struct sched_state	state;
+	int			max_gp;
 	int			saved_states;
+	struct event_constraint	**constraints;
+	struct sched_state	state;
 	struct sched_state	saved[SCHED_STATES_MAX];
 };
 
 /*
  * Initialize interator that runs through all events and counters.
  */
-static void perf_sched_init(struct perf_sched *sched, struct perf_event **events,
-			    int num, int wmin, int wmax)
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints,
+			    int num, int wmin, int wmax, int gpmax)
 {
 	int idx;
 
 	memset(sched, 0, sizeof(*sched));
 	sched->max_events	= num;
 	sched->max_weight	= wmax;
-	sched->events		= events;
+	sched->max_gp		= gpmax;
+	sched->constraints	= constraints;
 
 	for (idx = 0; idx < num; idx++) {
-		if (events[idx]->hw.constraint->weight == wmin)
+		if (constraints[idx]->weight == wmin)
 			break;
 	}
 
@@ -687,7 +704,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 	if (sched->state.event >= sched->max_events)
 		return false;
 
-	c = sched->events[sched->state.event]->hw.constraint;
+	c = sched->constraints[sched->state.event];
 	/* Prefer fixed purpose counters */
 	if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
 		idx = INTEL_PMC_IDX_FIXED;
@@ -696,11 +713,16 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 				goto done;
 		}
 	}
+
 	/* Grab the first unused counter starting with idx */
 	idx = sched->state.counter;
 	for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
-		if (!__test_and_set_bit(idx, sched->state.used))
+		if (!__test_and_set_bit(idx, sched->state.used)) {
+			if (sched->state.nr_gp++ >= sched->max_gp)
+				return false;
+
 			goto done;
+		}
 	}
 
 	return false;
@@ -745,7 +767,7 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 			if (sched->state.weight > sched->max_weight)
 				return false;
 		}
-		c = sched->events[sched->state.event]->hw.constraint;
+		c = sched->constraints[sched->state.event];
 	} while (c->weight != sched->state.weight);
 
 	sched->state.counter = 0;	/* start with first counter */
@@ -756,12 +778,12 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 /*
  * Assign a counter for each event.
  */
-int perf_assign_events(struct perf_event **events, int n,
-			int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+			int wmin, int wmax, int gpmax, int *assign)
 {
 	struct perf_sched sched;
 
-	perf_sched_init(&sched, events, n, wmin, wmax);
+	perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax);
 
 	do {
 		if (!perf_sched_find_counter(&sched))
@@ -788,9 +810,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		x86_pmu.start_scheduling(cpuc);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		hwc = &cpuc->event_list[i]->hw;
+		cpuc->event_constraint[i] = NULL;
 		c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
-		hwc->constraint = c;
+		cpuc->event_constraint[i] = c;
 
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
@@ -801,7 +823,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	 */
 	for (i = 0; i < n; i++) {
 		hwc = &cpuc->event_list[i]->hw;
-		c = hwc->constraint;
+		c = cpuc->event_constraint[i];
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -821,9 +843,26 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	}
 
 	/* slow path */
-	if (i != n)
-		unsched = perf_assign_events(cpuc->event_list, n, wmin,
-					     wmax, assign);
+	if (i != n) {
+		int gpmax = x86_pmu.num_counters;
+
+		/*
+		 * Do not allow scheduling of more than half the available
+		 * generic counters.
+		 *
+		 * This helps avoid counter starvation of sibling thread by
+		 * ensuring at most half the counters cannot be in exclusive
+		 * mode. There is no designated counters for the limits. Any
+		 * N/2 counters can be used. This helps with events with
+		 * specific counter constraints.
+		 */
+		if (is_ht_workaround_enabled() && !cpuc->is_fake &&
+		    READ_ONCE(cpuc->excl_cntrs->exclusive_present))
+			gpmax /= 2;
+
+		unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
+					     wmax, gpmax, assign);
+	}
 
 	/*
 	 * In case of success (unsched = 0), mark events as committed,
@@ -840,7 +879,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			e = cpuc->event_list[i];
 			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
 			if (x86_pmu.commit_scheduling)
-				x86_pmu.commit_scheduling(cpuc, e, assign[i]);
+				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
 	}
 
@@ -1292,8 +1331,10 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 		x86_pmu.put_event_constraints(cpuc, event);
 
 	/* Delete the array entry. */
-	while (++i < cpuc->n_events)
+	while (++i < cpuc->n_events) {
 		cpuc->event_list[i-1] = cpuc->event_list[i];
+		cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+	}
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6ac5cb7a9e14..ef78516850fb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -74,6 +74,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_EXCL		0x0040 /* HT exclusivity on counter */
 #define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
 
 
 struct amd_nb {
@@ -134,8 +135,6 @@ enum intel_excl_state_type {
 struct intel_excl_states {
 	enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
 	enum intel_excl_state_type state[X86_PMC_IDX_MAX];
-	int  num_alloc_cntrs;/* #counters allocated */
-	int  max_alloc_cntrs;/* max #counters allowed */
 	bool sched_started; /* true if scheduling has started */
 };
 
@@ -144,6 +143,11 @@ struct intel_excl_cntrs {
 
 	struct intel_excl_states states[2];
 
+	union {
+		u16	has_exclusive[2];
+		u32	exclusive_present;
+	};
+
 	int		refcnt;		/* per-core: #HT threads */
 	unsigned	core_id;	/* per-core: core id */
 };
@@ -172,7 +176,11 @@ struct cpu_hw_events {
 					     added in the current transaction */
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
+
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
+
+	int			n_excl; /* the number of exclusive events */
 
 	unsigned int		group_flag;
 	int			is_fake;
@@ -519,9 +527,7 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 
-	void		(*commit_scheduling)(struct cpu_hw_events *cpuc,
-					     struct perf_event *event,
-					     int cntr);
+	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
 
 	void		(*start_scheduling)(struct cpu_hw_events *cpuc);
 
@@ -717,8 +723,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 
 void x86_pmu_enable_all(int added);
 
-int perf_assign_events(struct perf_event **events, int n,
-			int wmin, int wmax, int *assign);
+int perf_assign_events(struct event_constraint **constraints, int n,
+			int wmin, int wmax, int gpmax, int *assign);
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
 
 void x86_pmu_stop(struct perf_event *event, int flags);
@@ -929,4 +935,8 @@ static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
 	return NULL;
 }
 
+static inline int is_ht_workaround_enabled(void)
+{
+	return 0;
+}
 #endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3998131d1a68..a1e35c9f06b9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1923,7 +1923,6 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	xl = &excl_cntrs->states[tid];
 
 	xl->sched_started = true;
-	xl->num_alloc_cntrs = 0;
 	/*
 	 * lock shared state until we are done scheduling
 	 * in stop_event_scheduling()
@@ -2000,6 +1999,11 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * across HT threads
 	 */
 	is_excl = c->flags & PERF_X86_EVENT_EXCL;
+	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+		if (!cpuc->n_excl++)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+	}
 
 	/*
 	 * xl = state of current HT
@@ -2008,18 +2012,6 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	xl = &excl_cntrs->states[tid];
 	xlo = &excl_cntrs->states[o_tid];
 
-	/*
-	 * do not allow scheduling of more than max_alloc_cntrs
-	 * which is set to half the available generic counters.
-	 * this helps avoid counter starvation of sibling thread
-	 * by ensuring at most half the counters cannot be in
-	 * exclusive mode. There is not designated counters for the
-	 * limits. Any N/2 counters can be used. This helps with
-	 * events with specifix counter constraints
-	 */
-	if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs)
-		return &emptyconstraint;
-
 	cx = c;
 
 	/*
@@ -2106,7 +2098,7 @@ static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = event->hw.constraint;
+	struct event_constraint *c1 = cpuc->event_constraint[idx];
 	struct event_constraint *c2;
 
 	/*
@@ -2150,6 +2142,11 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 
 	xl = &excl_cntrs->states[tid];
 	xlo = &excl_cntrs->states[o_tid];
+	if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
+		hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
+		if (!--cpuc->n_excl)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0);
+	}
 
 	/*
 	 * put_constraint may be called from x86_schedule_events()
@@ -2188,8 +2185,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 					struct perf_event *event)
 {
-	struct event_constraint *c = event->hw.constraint;
-
 	intel_put_shared_regs_event_constraints(cpuc, event);
 
 	/*
@@ -2197,19 +2192,14 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	 * all events are subject to and must call the
 	 * put_excl_constraints() routine
 	 */
-	if (c && cpuc->excl_cntrs)
+	if (cpuc->excl_cntrs)
 		intel_put_excl_constraints(cpuc, event);
-
-	/* cleanup dynamic constraint */
-	if (c && (c->flags & PERF_X86_EVENT_DYNAMIC))
-		event->hw.constraint = NULL;
 }
 
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc,
-				    struct perf_event *event, int cntr)
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct event_constraint *c = event->hw.constraint;
+	struct event_constraint *c = cpuc->event_constraint[idx];
 	struct intel_excl_states *xlo, *xl;
 	int tid = cpuc->excl_thread_id;
 	int o_tid = 1 - tid;
@@ -2639,8 +2629,6 @@ static void intel_pmu_cpu_starting(int cpu)
 		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
-		int h = x86_pmu.num_counters >> 1;
-
 		for_each_cpu(i, topology_thread_cpumask(cpu)) {
 			struct intel_excl_cntrs *c;
 
@@ -2654,11 +2642,6 @@ static void intel_pmu_cpu_starting(int cpu)
 		}
 		cpuc->excl_cntrs->core_id = core_id;
 		cpuc->excl_cntrs->refcnt++;
-		/*
-		 * set hard limit to half the number of generic counters
-		 */
-		cpuc->excl_cntrs->states[0].max_alloc_cntrs = h;
-		cpuc->excl_cntrs->states[1].max_alloc_cntrs = h;
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 813f75d71175..7f73b3553e2e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -706,9 +706,9 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
-	if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
-	else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST)
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
 	if (cpuc->enabled)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index ffe666c2c6b5..123ff1bb2f60 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -151,7 +151,7 @@ static int __init pt_pmu_hw_init(void)
 
 		de_attr->attr.attr.name = pt_caps[i].name;
 
-		sysfs_attr_init(&de_attrs->attr.attr);
+		sysfs_attr_init(&de_attr->attr.attr);
 
 		de_attr->attr.attr.mode		= S_IRUGO;
 		de_attr->attr.show		= pt_cap_show;
@@ -615,7 +615,8 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 				   struct perf_output_handle *handle)
 
 {
-	unsigned long idx, npages, end;
+	unsigned long head = local64_read(&buf->head);
+	unsigned long idx, npages, wakeup;
 
 	if (buf->snapshot)
 		return 0;
@@ -634,17 +635,26 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->topa_index[buf->stop_pos]->stop = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
-	if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
-		npages = (handle->size + 1) >> PAGE_SHIFT;
-		end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages;
-		/*if (end > handle->wakeup >> PAGE_SHIFT)
-		  end = handle->wakeup >> PAGE_SHIFT;*/
-		idx = end & (buf->nr_pages - 1);
-		buf->stop_pos = idx;
-		idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1;
-		idx &= buf->nr_pages - 1;
-		buf->intr_pos = idx;
-	}
+	/* how many pages till the STOP marker */
+	npages = handle->size >> PAGE_SHIFT;
+
+	/* if it's on a page boundary, fill up one more page */
+	if (!offset_in_page(head + handle->size + 1))
+		npages++;
+
+	idx = (head >> PAGE_SHIFT) + npages;
+	idx &= buf->nr_pages - 1;
+	buf->stop_pos = idx;
+
+	wakeup = handle->wakeup >> PAGE_SHIFT;
+
+	/* in the worst case, wake up the consumer one page before hard stop */
+	idx = (head >> PAGE_SHIFT) + npages - 1;
+	if (idx > wakeup)
+		idx = wakeup;
+
+	idx &= buf->nr_pages - 1;
+	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c635b8b49e93..dd319e59246b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -365,9 +365,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
 
 	for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		hwc = &box->event_list[i]->hw;
 		c = uncore_get_event_constraint(box, box->event_list[i]);
-		hwc->constraint = c;
+		box->event_constraint[i] = c;
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
 	}
@@ -375,7 +374,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	/* fastpath, try to reuse previous register */
 	for (i = 0; i < n; i++) {
 		hwc = &box->event_list[i]->hw;
-		c = hwc->constraint;
+		c = box->event_constraint[i];
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -395,8 +394,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	}
 	/* slow path */
 	if (i != n)
-		ret = perf_assign_events(box->event_list, n,
-					 wmin, wmax, assign);
+		ret = perf_assign_events(box->event_constraint, n,
+					 wmin, wmax, n, assign);
 
 	if (!assign || ret) {
 		for (i = 0; i < n; i++)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 6c8c1e7e69d8..f789ec9a0133 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -97,6 +97,7 @@ struct intel_uncore_box {
 	atomic_t refcnt;
 	struct perf_event *events[UNCORE_PMC_IDX_MAX];
 	struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+	struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX];
 	unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
 	u64 tags[UNCORE_PMC_IDX_MAX];
 	struct pci_dev *pci_dev;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 61992cf2e977..d8a82a89f35a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -92,8 +92,6 @@ struct hw_perf_event_extra {
 	int		idx;	/* index in shared_regs->regs[] */
 };
 
-struct event_constraint;
-
 /**
  * struct hw_perf_event - performance event hardware details:
  */
@@ -112,8 +110,6 @@ struct hw_perf_event {
 
 			struct hw_perf_event_extra extra_reg;
 			struct hw_perf_event_extra branch_reg;
-
-			struct event_constraint *constraint;
 		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1a3bf48743ce..eddf1ed4155e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3442,7 +3442,6 @@ static void free_event_rcu(struct rcu_head *head)
 	if (event->ns)
 		put_pid_ns(event->ns);
 	perf_event_free_filter(event);
-	perf_event_free_bpf_prog(event);
 	kfree(event);
 }
 
@@ -3573,6 +3572,8 @@ static void __free_event(struct perf_event *event)
 			put_callchain_buffers();
 	}
 
+	perf_event_free_bpf_prog(event);
+
 	if (event->destroy)
 		event->destroy(event);
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 232f00f273cb..725c416085e3 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -493,6 +493,20 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 			rb->aux_pages[rb->aux_nr_pages] = page_address(page++);
 	}
 
+	/*
+	 * In overwrite mode, PMUs that don't support SG may not handle more
+	 * than one contiguous allocation, since they rely on PMI to do double
+	 * buffering. In this case, the entire buffer has to be one contiguous
+	 * chunk.
+	 */
+	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) &&
+	    overwrite) {
+		struct page *page = virt_to_page(rb->aux_pages[0]);
+
+		if (page_private(page) != max_order)
+			goto out;
+	}
+
 	rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
 					     overwrite);
 	if (!rb->aux_priv)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-05-15  7:17 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-05-15  7:17 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 60d5ddeabdda2d6453280efcf172d2429da10eac Merge branch 'liblockdep-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/sashal/linux into perf/urgent

Mostly tooling fixes, but also a lockdep annotation fix, a PMU event 
list fix and a new model addition.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      tools: Fix tools/vm build

Eunbong Song (2):
      tools/liblockdep: Fix linker error in case of cross compile
      tools/liblockdep: Fix compilation error

Kan Liang (1):
      perf/x86/intel: Fix SLM cache event list

Peter Zijlstra (1):
      perf: Annotate inherited event ctx->mutex recursion

Stephane Eranian (1):
      perf/x86/rapl: Enable Broadwell-U RAPL support

Will Deacon (1):
      perf tools: Use getconf to determine number of online CPUs


 arch/x86/kernel/cpu/perf_event_intel.c      |  7 +++--
 arch/x86/kernel/cpu/perf_event_intel_rapl.c |  1 +
 kernel/events/core.c                        | 41 +++++++++++++++++++++++------
 tools/lib/lockdep/Makefile                  |  3 ++-
 tools/lib/lockdep/uinclude/linux/kernel.h   |  3 +++
 tools/perf/Makefile                         |  2 +-
 tools/vm/Makefile                           |  2 +-
 7 files changed, 44 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 960e85de13fb..3998131d1a68 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
-		[ C(RESULT_MISS)   ] = SLM_DMND_READ|SLM_LLC_MISS,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
@@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids
 	[ C(OP_READ) ] = {
 		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
@@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
-		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES */
+		[ C(RESULT_MISS)   ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 999289b94025..358c54ad20d4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -722,6 +722,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 61: /* Broadwell */
 		rapl_cntr_mask = RAPL_IDX_HSW;
 		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
 		break;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 81aa3a4ece9f..1a3bf48743ce 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -913,10 +913,30 @@ static void put_ctx(struct perf_event_context *ctx)
  * Those places that change perf_event::ctx will hold both
  * perf_event_ctx::mutex of the 'old' and 'new' ctx value.
  *
- * Lock ordering is by mutex address. There is one other site where
- * perf_event_context::mutex nests and that is put_event(). But remember that
- * that is a parent<->child context relation, and migration does not affect
- * children, therefore these two orderings should not interact.
+ * Lock ordering is by mutex address. There are two other sites where
+ * perf_event_context::mutex nests and those are:
+ *
+ *  - perf_event_exit_task_context()	[ child , 0 ]
+ *      __perf_event_exit_task()
+ *        sync_child_event()
+ *          put_event()			[ parent, 1 ]
+ *
+ *  - perf_event_init_context()		[ parent, 0 ]
+ *      inherit_task_group()
+ *        inherit_group()
+ *          inherit_event()
+ *            perf_event_alloc()
+ *              perf_init_event()
+ *                perf_try_init_event()	[ child , 1 ]
+ *
+ * While it appears there is an obvious deadlock here -- the parent and child
+ * nesting levels are inverted between the two. This is in fact safe because
+ * life-time rules separate them. That is an exiting task cannot fork, and a
+ * spawning task cannot (yet) exit.
+ *
+ * But remember that that these are parent<->child context relations, and
+ * migration does not affect children, therefore these two orderings should not
+ * interact.
  *
  * The change in perf_event::ctx does not affect children (as claimed above)
  * because the sys_perf_event_open() case will install a new event and break
@@ -3657,9 +3677,6 @@ static void perf_remove_from_owner(struct perf_event *event)
 	}
 }
 
-/*
- * Called when the last reference to the file is gone.
- */
 static void put_event(struct perf_event *event)
 {
 	struct perf_event_context *ctx;
@@ -3697,6 +3714,9 @@ int perf_event_release_kernel(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
+/*
+ * Called when the last reference to the file is gone.
+ */
 static int perf_release(struct inode *inode, struct file *file)
 {
 	put_event(file->private_data);
@@ -7364,7 +7384,12 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 		return -ENODEV;
 
 	if (event->group_leader != event) {
-		ctx = perf_event_ctx_lock(event->group_leader);
+		/*
+		 * This ctx->mutex can nest when we're called through
+		 * inheritance. See the perf_event_ctx_lock_nested() comment.
+		 */
+		ctx = perf_event_ctx_lock_nested(event->group_leader,
+						 SINGLE_DEPTH_NESTING);
 		BUG_ON(!ctx);
 	}
 
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 0c356fb65022..18ffccf00426 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -14,9 +14,10 @@ define allow-override
     $(eval $(1) = $(2)))
 endef
 
-# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
 $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
 
 INSTALL = install
 
diff --git a/tools/lib/lockdep/uinclude/linux/kernel.h b/tools/lib/lockdep/uinclude/linux/kernel.h
index a11e3c357be7..cd2cc59a5da7 100644
--- a/tools/lib/lockdep/uinclude/linux/kernel.h
+++ b/tools/lib/lockdep/uinclude/linux/kernel.h
@@ -28,6 +28,9 @@
 #define __init
 #define noinline
 #define list_add_tail_rcu list_add_tail
+#define list_for_each_entry_rcu list_for_each_entry
+#define barrier() 
+#define synchronize_sched()
 
 #ifndef CALLER_ADDR0
 #define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index c699dc35eef9..d31a7bbd7cee 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -24,7 +24,7 @@ unexport MAKEFLAGS
 # (To override it, run 'make JOBS=1' and similar.)
 #
 ifeq ($(JOBS),)
-  JOBS := $(shell egrep -c '^processor|^CPU' /proc/cpuinfo 2>/dev/null)
+  JOBS := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
   ifeq ($(JOBS),0)
     JOBS := 1
   endif
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index ac884b65a072..93aadaf7ff63 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -3,7 +3,7 @@
 TARGETS=page-types slabinfo page_owner_sort
 
 LIB_DIR = ../lib/api
-LIBS = $(LIB_DIR)/libapikfs.a
+LIBS = $(LIB_DIR)/libapi.a
 
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-05-06 12:52 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-05-06 12:52 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 74f40c1f437674f5ab4a3977f1894ea6db535dee Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, but also an uncore PMU driver fix and an uncore 
PMU driver hardware-enablement addition.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf trace: Enable events when doing system wide tracing and starting a workload
      perf trace: Disable events and drain events when forked workload ends

Bobby Powers (1):
      tools lib api: Undefine _FORTIFY_SOURCE before setting it

David Ahern (1):
      perf kmem: Fix compiles on RHEL6/OL6

Davidlohr Bueso (1):
      perf bench futex: Fix hung wakeup tasks after requeueing

He Kuang (1):
      perf probe: Fix bug with global variables handling

Jiri Olsa (1):
      perf/x86/intel: Add cpu_(prepare|starting|dying) for core_pmu

Namhyung Kim (2):
      tools lib traceevent: Fix build failure on 32-bit arch
      perf report: Fix -T/--threads option to work again

Petr Holasek (2):
      perf bench numa: Fixes of --quiet argument
      perf bench numa: Fix immediate meeting of convergence condition

Sonny Rao (2):
      perf/x86/intel/uncore: Add support for Intel Haswell ULT (lower power Mobile Processor) IMC uncore PMUs
      perf/x86/intel/uncore: Move PCI IDs for IMC to uncore driver

Wang Nan (2):
      perf top: Fix a segfault when kernel map is restricted.
      perf probe: Fix segfault if passed with ''.

Will Deacon (1):
      perf kmem: Consistently use PRIu64 for printing u64 values


 arch/x86/kernel/cpu/perf_event_intel.c            | 66 +++++++++++++----------
 arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c | 12 +++++
 include/linux/pci_ids.h                           |  4 --
 tools/lib/api/Makefile                            |  2 +-
 tools/lib/traceevent/event-parse.c                |  2 +-
 tools/perf/bench/futex-requeue.c                  | 15 +++---
 tools/perf/bench/numa.c                           | 12 ++++-
 tools/perf/builtin-kmem.c                         | 58 ++++++++++----------
 tools/perf/builtin-report.c                       |  2 +-
 tools/perf/builtin-top.c                          |  2 +-
 tools/perf/builtin-trace.c                        | 10 +++-
 tools/perf/util/probe-event.c                     |  2 +
 tools/perf/util/probe-finder.c                    |  4 +-
 13 files changed, 114 insertions(+), 77 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 219d3fb423a1..960e85de13fb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2533,34 +2533,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-static __initconst const struct x86_pmu core_pmu = {
-	.name			= "core",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= core_pmu_enable_all,
-	.enable			= core_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
-	.schedule_events	= x86_schedule_events,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.get_event_constraints	= intel_get_event_constraints,
-	.put_event_constraints	= intel_put_event_constraints,
-	.event_constraints	= intel_core_event_constraints,
-	.guest_get_msrs		= core_guest_get_msrs,
-	.format_attrs		= intel_arch_formats_attr,
-	.events_sysfs_show	= intel_event_sysfs_show,
-};
-
 struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
@@ -2743,6 +2715,44 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static __initconst const struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32-bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL<<31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
+	/*
+	 * Virtual (or funny metal) CPU can define x86_pmu.extra_regs
+	 * together with PMU version 1 and thus be using core_pmu with
+	 * shared_regs. We need following callbacks here to allocate
+	 * it properly.
+	 */
+	.cpu_prepare		= intel_pmu_cpu_prepare,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 3001015b755c..4562e9e22c60 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -1,6 +1,13 @@
 /* Nehalem/SandBridge/Haswell uncore support */
 #include "perf_event_intel_uncore.h"
 
+/* Uncore IMC PCI IDs */
+#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
 #define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
@@ -472,6 +479,10 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -502,6 +513,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	{  /* end marker */ }
 };
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index e63c02a93f6b..a59385852233 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2539,10 +2539,6 @@
 
 #define PCI_VENDOR_ID_INTEL		0x8086
 #define PCI_DEVICE_ID_INTEL_EESSC	0x0008
-#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
-#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
-#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
-#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_PXHD_0	0x0320
 #define PCI_DEVICE_ID_INTEL_PXHD_1	0x0321
 #define PCI_DEVICE_ID_INTEL_PXH_0	0x0329
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index d8fe29fc19a4..8bd960658463 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -16,7 +16,7 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
 RM = rm -f
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 12a7e2a40c89..aa21bd55bd8a 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3865,7 +3865,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			} else if (el_size == 4) {
 				trace_seq_printf(s, "%u", *(uint32_t *)num);
 			} else if (el_size == 8) {
-				trace_seq_printf(s, "%lu", *(uint64_t *)num);
+				trace_seq_printf(s, "%"PRIu64, *(uint64_t *)num);
 			} else {
 				trace_seq_printf(s, "BAD SIZE:%d 0x%x",
 						 el_size, *(uint8_t *)num);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index bedff6b5b3cf..ad0d9b5342fb 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -132,6 +132,9 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
+	if (nrequeue > nthreads)
+		nrequeue = nthreads;
+
 	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
 	       "%d at a time.\n\n",  getpid(), nthreads,
 	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);
@@ -161,20 +164,18 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
+		while (nrequeued < nthreads) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0,
-					  nrequeue, futex_flag);
+			nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
+						       nrequeue, futex_flag);
 		}
+
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
-		if (nrequeued > nthreads)
-			nrequeued = nthreads;
-
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -184,7 +185,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
+		nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index ebfa163b80b5..ba5efa4710b5 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -180,7 +180,7 @@ static const struct option options[] = {
 	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
 	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
 	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
-	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"bzero the initial allocations"),
+	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"quiet mode"),
 	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
 
 	/* Special option string parsing callbacks: */
@@ -828,6 +828,9 @@ static int count_process_nodes(int process_nr)
 		td = g->threads + task_nr;
 
 		node = numa_node_of_cpu(td->curr_cpu);
+		if (node < 0) /* curr_cpu was likely still -1 */
+			return 0;
+
 		node_present[node] = 1;
 	}
 
@@ -882,6 +885,11 @@ static void calc_convergence_compression(int *strong)
 	for (p = 0; p < g->p.nr_proc; p++) {
 		unsigned int nodes = count_process_nodes(p);
 
+		if (!nodes) {
+			*strong = 0;
+			return;
+		}
+
 		nodes_min = min(nodes, nodes_min);
 		nodes_max = max(nodes, nodes_max);
 	}
@@ -1395,7 +1403,7 @@ static void print_res(const char *name, double val,
 	if (!name)
 		name = "main,";
 
-	if (g->p.show_quiet)
+	if (!g->p.show_quiet)
 		printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short);
 	else
 		printf(" %14.3f %s\n", val, txt_long);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 63ea01349b6e..1634186d537c 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -319,7 +319,7 @@ static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
 	return 0;
 }
 
-static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool create)
+static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
 {
 	struct rb_node **node = &page_alloc_tree.rb_node;
 	struct rb_node *parent = NULL;
@@ -331,7 +331,7 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = page_stat_cmp(data, stat);
+		cmp = page_stat_cmp(data, pstat);
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -345,10 +345,10 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 
 	data = zalloc(sizeof(*data));
 	if (data != NULL) {
-		data->page = stat->page;
-		data->order = stat->order;
-		data->gfp_flags = stat->gfp_flags;
-		data->migrate_type = stat->migrate_type;
+		data->page = pstat->page;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
 
 		rb_link_node(&data->node, parent, node);
 		rb_insert_color(&data->node, &page_alloc_tree);
@@ -375,7 +375,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
-	struct page_stat *stat;
+	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
 		.gfp_flags = gfp_flags,
@@ -401,21 +401,21 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.
 	 */
-	stat = search_page(page, true);
-	if (stat == NULL)
+	pstat = search_page(page, true);
+	if (pstat == NULL)
 		return -ENOMEM;
 
-	stat->order = order;
-	stat->gfp_flags = gfp_flags;
-	stat->migrate_type = migrate_type;
+	pstat->order = order;
+	pstat->gfp_flags = gfp_flags;
+	pstat->migrate_type = migrate_type;
 
 	this.page = page;
-	stat = search_page_alloc_stat(&this, true);
-	if (stat == NULL)
+	pstat = search_page_alloc_stat(&this, true);
+	if (pstat == NULL)
 		return -ENOMEM;
 
-	stat->nr_alloc++;
-	stat->alloc_bytes += bytes;
+	pstat->nr_alloc++;
+	pstat->alloc_bytes += bytes;
 
 	order_stats[order][migrate_type]++;
 
@@ -428,7 +428,7 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	u64 page;
 	unsigned int order = perf_evsel__intval(evsel, sample, "order");
 	u64 bytes = kmem_page_size << order;
-	struct page_stat *stat;
+	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
 	};
@@ -441,8 +441,8 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
 
-	stat = search_page(page, false);
-	if (stat == NULL) {
+	pstat = search_page(page, false);
+	if (pstat == NULL) {
 		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
 			  page, order);
 
@@ -453,18 +453,18 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	}
 
 	this.page = page;
-	this.gfp_flags = stat->gfp_flags;
-	this.migrate_type = stat->migrate_type;
+	this.gfp_flags = pstat->gfp_flags;
+	this.migrate_type = pstat->migrate_type;
 
-	rb_erase(&stat->node, &page_tree);
-	free(stat);
+	rb_erase(&pstat->node, &page_tree);
+	free(pstat);
 
-	stat = search_page_alloc_stat(&this, false);
-	if (stat == NULL)
+	pstat = search_page_alloc_stat(&this, false);
+	if (pstat == NULL)
 		return -ENOENT;
 
-	stat->nr_free++;
-	stat->free_bytes += bytes;
+	pstat->nr_free++;
+	pstat->free_bytes += bytes;
 
 	return 0;
 }
@@ -640,9 +640,9 @@ static void print_page_summary(void)
 	       nr_page_frees, total_page_free_bytes / 1024);
 	printf("\n");
 
-	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
+	printf("%-30s: %'16"PRIu64"   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
 	       nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
-	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
+	printf("%-30s: %'16"PRIu64"   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
 	       nr_page_allocs - nr_alloc_freed,
 	       (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
 	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total free-only requests",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 476cdf7afcca..b63aeda719be 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -329,7 +329,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		fprintf(stdout, "\n\n");
 	}
 
-	if (sort_order == default_sort_order &&
+	if (sort_order == NULL &&
 	    parent_pattern == default_parent_pattern) {
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1cb3436276d1..6a4d5d41c671 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -733,7 +733,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
-			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
 			  " modules" : "");
 		if (use_browser <= 0)
 			sleep(5);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e124741be187..e122970361f2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2241,10 +2241,11 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_mmap;
 
+	if (!target__none(&trace->opts.target))
+		perf_evlist__enable(evlist);
+
 	if (forks)
 		perf_evlist__start_workload(evlist);
-	else
-		perf_evlist__enable(evlist);
 
 	trace->multiple_threads = evlist->threads->map[0] == -1 ||
 				  evlist->threads->nr > 1 ||
@@ -2272,6 +2273,11 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 			if (interrupted)
 				goto out_disable;
+
+			if (done && !draining) {
+				perf_evlist__disable(evlist);
+				draining = true;
+			}
 		}
 	}
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d8bb616ff57c..d05b77cf35f7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1084,6 +1084,8 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	 *
 	 * TODO:Group name support
 	 */
+	if (!arg)
+		return -EINVAL;
 
 	ptr = strpbrk(arg, ";=@+%");
 	if (ptr && *ptr == '=') {	/* Event name */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 44554c3c2220..1c3cc07937d5 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -578,10 +578,12 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* Search child die for local variables and parameters. */
 	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
 		/* Search again in global variables */
-		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var,
+						0, &vr_die)) {
 			pr_warning("Failed to find '%s' in this function.\n",
 				   pf->pvar->var);
 			ret = -ENOENT;
+		}
 	}
 	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-04-03 13:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-04-03 13:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c420f19b9cdc59662dbb56677417487efc1729ec perf/x86/intel: Fix Haswell CYCLE_ACTIVITY.* counter constraints

Two x86 Intel PMU constraint handling fixes.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86/intel: Fix Haswell CYCLE_ACTIVITY.* counter constraints

Kan Liang (1):
      perf/x86/intel: Filter branches for PEBS event


 arch/x86/kernel/cpu/perf_event_intel.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d967138..258990688a5e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -212,11 +212,11 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
-	INTEL_EVENT_CONSTRAINT(0x08a3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	/* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
-	INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
-	INTEL_EVENT_CONSTRAINT(0x04a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
@@ -1649,11 +1649,11 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
 	if (c)
 		return c;
 
-	c = intel_pebs_constraints(event);
+	c = intel_shared_regs_constraints(cpuc, event);
 	if (c)
 		return c;
 
-	c = intel_shared_regs_constraints(cpuc, event);
+	c = intel_pebs_constraints(event);
 	if (c)
 		return c;
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-03-17 16:48 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-03-17 16:48 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d415a7f1c1a8406b22d95b943c66a5b73a37bc19 perf: Fix context leak in put_event()

Two small fixes: a kernel side context leak fix, and a tooling crash fix.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf annotate: Fix fallback to unparsed disassembler line

Leon Yu (1):
      perf: Fix context leak in put_event()


 kernel/events/core.c       | 2 +-
 tools/perf/util/annotate.c | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f04daabfd1cf..453ef61311d4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3591,7 +3591,7 @@ static void put_event(struct perf_event *event)
 	ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
 	WARN_ON_ONCE(ctx->parent_ctx);
 	perf_remove_from_context(event, true);
-	mutex_unlock(&ctx->mutex);
+	perf_event_ctx_unlock(event, ctx);
 
 	_free_event(event);
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 61bf9128e1f2..9d9db3b296dd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -30,6 +30,8 @@ static int disasm_line__parse(char *line, char **namep, char **rawp);
 
 static void ins__delete(struct ins_operands *ops)
 {
+	if (ops == NULL)
+		return;
 	zfree(&ops->source.raw);
 	zfree(&ops->source.name);
 	zfree(&ops->target.raw);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-03-01 17:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-03-01 17:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 021f5f12f2ab44874193c68fb19eea154493f83a Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Two kprobes fixes and a handful of tooling fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf tools: Fix pthread_attr_setaffinity_np build error
      perf tools: Fix probing for PERF_FLAG_FD_CLOEXEC flag

Bruce Merry (1):
      perf bench: Fix order of arguments to memcpy_alloc_mem

David Ahern (3):
      perf top: Fix SIGBUS on sparc64
      perf symbols: Define EM_AARCH64 for older OSes
      perf tools: Make sparc64 arch point to sparc

Josh Boyer (1):
      perf tools: Define _GNU_SOURCE on pthread_attr_setaffinity_np feature check

Petr Mladek (2):
      kprobes/x86: Use 5-byte NOP when the code might be modified by ftrace
      kprobes/x86: Check for invalid ftrace location in __recover_probed_insn()


 arch/x86/kernel/kprobes/core.c                     | 54 ++++++++++++++++------
 arch/x86/kernel/kprobes/opt.c                      |  2 +
 tools/perf/bench/mem-memcpy.c                      |  4 +-
 tools/perf/config/Makefile.arch                    |  4 ++
 tools/perf/config/feature-checks/Makefile          |  2 +-
 .../test-pthread-attr-setaffinity-np.c             |  3 +-
 tools/perf/util/cloexec.c                          | 18 ++++++--
 tools/perf/util/evlist.h                           |  2 +-
 tools/perf/util/symbol-elf.c                       |  5 ++
 9 files changed, 72 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6a1146ea4d4d..4e3d5a9621fe 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -223,27 +223,48 @@ static unsigned long
 __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+	unsigned long faddr;
 
 	kp = get_kprobe((void *)addr);
-	/* There is no probe, return original address */
-	if (!kp)
+	faddr = ftrace_location(addr);
+	/*
+	 * Addresses inside the ftrace location are refused by
+	 * arch_check_ftrace_location(). Something went terribly wrong
+	 * if such an address is checked here.
+	 */
+	if (WARN_ON(faddr && faddr != addr))
+		return 0UL;
+	/*
+	 * Use the current code if it is not modified by Kprobe
+	 * and it cannot be modified by ftrace.
+	 */
+	if (!kp && !faddr)
 		return addr;
 
 	/*
-	 *  Basically, kp->ainsn.insn has an original instruction.
-	 *  However, RIP-relative instruction can not do single-stepping
-	 *  at different place, __copy_instruction() tweaks the displacement of
-	 *  that instruction. In that case, we can't recover the instruction
-	 *  from the kp->ainsn.insn.
+	 * Basically, kp->ainsn.insn has an original instruction.
+	 * However, RIP-relative instruction can not do single-stepping
+	 * at different place, __copy_instruction() tweaks the displacement of
+	 * that instruction. In that case, we can't recover the instruction
+	 * from the kp->ainsn.insn.
 	 *
-	 *  On the other hand, kp->opcode has a copy of the first byte of
-	 *  the probed instruction, which is overwritten by int3. And
-	 *  the instruction at kp->addr is not modified by kprobes except
-	 *  for the first byte, we can recover the original instruction
-	 *  from it and kp->opcode.
+	 * On the other hand, in case on normal Kprobe, kp->opcode has a copy
+	 * of the first byte of the probed instruction, which is overwritten
+	 * by int3. And the instruction at kp->addr is not modified by kprobes
+	 * except for the first byte, we can recover the original instruction
+	 * from it and kp->opcode.
+	 *
+	 * In case of Kprobes using ftrace, we do not have a copy of
+	 * the original instruction. In fact, the ftrace location might
+	 * be modified at anytime and even could be in an inconsistent state.
+	 * Fortunately, we know that the original code is the ideal 5-byte
+	 * long NOP.
 	 */
-	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-	buf[0] = kp->opcode;
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (faddr)
+		memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+	else
+		buf[0] = kp->opcode;
 	return (unsigned long)buf;
 }
 
@@ -251,6 +272,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
  * Recover the probed instruction at addr for further analysis.
  * Caller must lock kprobes by kprobe_mutex, or disable preemption
  * for preventing to release referencing kprobes.
+ * Returns zero if the instruction can not get recovered.
  */
 unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 {
@@ -285,6 +307,8 @@ static int can_probe(unsigned long paddr)
 		 * normally used, we just go through if there is no kprobe.
 		 */
 		__addr = recover_probed_instruction(buf, addr);
+		if (!__addr)
+			return 0;
 		kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 
@@ -333,6 +357,8 @@ int __copy_instruction(u8 *dest, u8 *src)
 	unsigned long recovered_insn =
 		recover_probed_instruction(buf, (unsigned long)src);
 
+	if (!recovered_insn)
+		return 0;
 	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 	insn_get_length(&insn);
 	/* Another subsystem puts a breakpoint, failed to recover */
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7c523bbf3dc8..3aef248ec1ee 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -259,6 +259,8 @@ static int can_optimize(unsigned long paddr)
 			 */
 			return 0;
 		recovered_insn = recover_probed_instruction(buf, addr);
+		if (!recovered_insn)
+			return 0;
 		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 		/* Another subsystem puts a breakpoint */
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 6c14afe8c1b1..db1d3a29d97f 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -289,7 +289,7 @@ static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	memcpy_alloc_mem(&src, &dst, len);
+	memcpy_alloc_mem(&dst, &src, len);
 
 	if (prefault)
 		fn(dst, src, len);
@@ -312,7 +312,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
 	void *src = NULL, *dst = NULL;
 	int i;
 
-	memcpy_alloc_mem(&src, &dst, len);
+	memcpy_alloc_mem(&dst, &src, len);
 
 	if (prefault)
 		fn(dst, src, len);
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index ff95a68741d1..ac8721ffa6c8 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -21,6 +21,10 @@ ifeq ($(RAW_ARCH),x86_64)
   endif
 endif
 
+ifeq ($(RAW_ARCH),sparc64)
+  ARCH ?= sparc
+endif
+
 ARCH ?= $(RAW_ARCH)
 
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 42ac05aaf8ac..b32ff3372514 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -49,7 +49,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 	$(BUILD)
 
 test-pthread-attr-setaffinity-np.bin:
-	$(BUILD) -Werror -lpthread
+	$(BUILD) -D_GNU_SOURCE -Werror -lpthread
 
 test-stackprotector-all.bin:
 	$(BUILD) -Werror -fstack-protector-all
diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
index 0a0d3ecb4e8a..2b81b72eca23 100644
--- a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
+++ b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
@@ -5,10 +5,11 @@ int main(void)
 {
 	int ret = 0;
 	pthread_attr_t thread_attr;
+	cpu_set_t cs;
 
 	pthread_attr_init(&thread_attr);
 	/* don't care abt exact args, just the API itself in libpthread */
-	ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL);
+	ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cs), &cs);
 
 	return ret;
 }
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 47b78b3f0325..6da965bdbc2c 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -25,6 +25,10 @@ static int perf_flag_probe(void)
 	if (cpu < 0)
 		cpu = 0;
 
+	/*
+	 * Using -1 for the pid is a workaround to avoid gratuitous jump label
+	 * changes.
+	 */
 	while (1) {
 		/* check cloexec flag */
 		fd = sys_perf_event_open(&attr, pid, cpu, -1,
@@ -47,16 +51,24 @@ static int perf_flag_probe(void)
 		  err, strerror_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+	while (1) {
+		fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+		if (fd < 0 && pid == -1 && errno == EACCES) {
+			pid = 0;
+			continue;
+		}
+		break;
+	}
 	err = errno;
 
+	if (fd >= 0)
+		close(fd);
+
 	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
 		      err, strerror_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
-	close(fd);
-
 	return 0;
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c94a9e03ecf1..e99a67632831 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -28,7 +28,7 @@ struct perf_mmap {
 	int		 mask;
 	int		 refcnt;
 	unsigned int	 prev;
-	char		 event_copy[PERF_SAMPLE_MAX_SIZE];
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
 struct perf_evlist {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index b24f9d8727a8..33b7a2aef713 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -11,6 +11,11 @@
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
+#ifndef EM_AARCH64
+#define EM_AARCH64	183  /* ARM 64 bit */
+#endif
+
+
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-02-20 13:40 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-02-20 13:40 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b7e37567d080301d38a302bb93ba79d1ca446dca kprobes/x86: Mark 2 bytes NOP as boostable

This tree contains two uprobes fixes, an uprobes comment 
update and a kprobes fix.

 Thanks,

	Ingo

------------------>
Denys Vlasenko (3):
      uprobes/x86: Add comment with insn opcodes, mnemonics and why we dont support them
      uprobes/x86: Fix 1-byte opcode tables
      uprobes/x86: Fix 2-byte opcode table

Wang Nan (1):
      kprobes/x86: Mark 2 bytes NOP as boostable


 arch/x86/kernel/kprobes/core.c |   2 +-
 arch/x86/kernel/uprobes.c      | 153 +++++++++++++++++++++++++++++------------
 2 files changed, 111 insertions(+), 44 deletions(-)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 98f654d466e5..6a1146ea4d4d 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -84,7 +84,7 @@ static volatile u32 twobyte_is_boostable[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
 	/*      ----------------------------------------------          */
 	W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
-	W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */
+	W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1) , /* 10 */
 	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */
 	W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
 	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 8b96a947021f..81f8adb0679e 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -66,27 +66,54 @@
  * Good-instruction tables for 32-bit apps.  This is non-const and volatile
  * to keep gcc from statically optimizing it out, as variable_test_bit makes
  * some versions of gcc to think only *(unsigned long*) is used.
+ *
+ * Opcodes we'll probably never support:
+ * 6c-6f - ins,outs. SEGVs if used in userspace
+ * e4-e7 - in,out imm. SEGVs if used in userspace
+ * ec-ef - in,out acc. SEGVs if used in userspace
+ * cc - int3. SIGTRAP if used in userspace
+ * ce - into. Not used in userspace - no kernel support to make it useful. SEGVs
+ *	(why we support bound (62) then? it's similar, and similarly unused...)
+ * f1 - int1. SIGTRAP if used in userspace
+ * f4 - hlt. SEGVs if used in userspace
+ * fa - cli. SEGVs if used in userspace
+ * fb - sti. SEGVs if used in userspace
+ *
+ * Opcodes which need some work to be supported:
+ * 07,17,1f - pop es/ss/ds
+ *	Normally not used in userspace, but would execute if used.
+ *	Can cause GP or stack exception if tries to load wrong segment descriptor.
+ *	We hesitate to run them under single step since kernel's handling
+ *	of userspace single-stepping (TF flag) is fragile.
+ *	We can easily refuse to support push es/cs/ss/ds (06/0e/16/1e)
+ *	on the same grounds that they are never used.
+ * cd - int N.
+ *	Used by userspace for "int 80" syscall entry. (Other "int N"
+ *	cause GP -> SEGV since their IDT gates don't allow calls from CPL 3).
+ *	Not supported since kernel's handling of userspace single-stepping
+ *	(TF flag) is fragile.
+ * cf - iret. Normally not used in userspace. Doesn't SEGV unless arguments are bad
  */
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static volatile u32 good_insns_32[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 	/*      ----------------------------------------------         */
-	W(0x00, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) | /* 00 */
+	W(0x00, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 00 */
 	W(0x10, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) , /* 10 */
-	W(0x20, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1) | /* 20 */
-	W(0x30, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1) , /* 30 */
+	W(0x20, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
+	W(0x30, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 30 */
 	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
 	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
-	W(0x60, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
+	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
 	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */
 	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
 	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
 	W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */
 	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
 	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
-	W(0xd0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+	W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
 	W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */
-	W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1)   /* f0 */
+	W(0xf0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1)   /* f0 */
 	/*      ----------------------------------------------         */
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 };
@@ -94,27 +121,61 @@ static volatile u32 good_insns_32[256 / 32] = {
 #define good_insns_32	NULL
 #endif
 
-/* Good-instruction tables for 64-bit apps */
+/* Good-instruction tables for 64-bit apps.
+ *
+ * Genuinely invalid opcodes:
+ * 06,07 - formerly push/pop es
+ * 0e - formerly push cs
+ * 16,17 - formerly push/pop ss
+ * 1e,1f - formerly push/pop ds
+ * 27,2f,37,3f - formerly daa/das/aaa/aas
+ * 60,61 - formerly pusha/popa
+ * 62 - formerly bound. EVEX prefix for AVX512 (not yet supported)
+ * 82 - formerly redundant encoding of Group1
+ * 9a - formerly call seg:ofs
+ * ce - formerly into
+ * d4,d5 - formerly aam/aad
+ * d6 - formerly undocumented salc
+ * ea - formerly jmp seg:ofs
+ *
+ * Opcodes we'll probably never support:
+ * 6c-6f - ins,outs. SEGVs if used in userspace
+ * e4-e7 - in,out imm. SEGVs if used in userspace
+ * ec-ef - in,out acc. SEGVs if used in userspace
+ * cc - int3. SIGTRAP if used in userspace
+ * f1 - int1. SIGTRAP if used in userspace
+ * f4 - hlt. SEGVs if used in userspace
+ * fa - cli. SEGVs if used in userspace
+ * fb - sti. SEGVs if used in userspace
+ *
+ * Opcodes which need some work to be supported:
+ * cd - int N.
+ *	Used by userspace for "int 80" syscall entry. (Other "int N"
+ *	cause GP -> SEGV since their IDT gates don't allow calls from CPL 3).
+ *	Not supported since kernel's handling of userspace single-stepping
+ *	(TF flag) is fragile.
+ * cf - iret. Normally not used in userspace. Doesn't SEGV unless arguments are bad
+ */
 #if defined(CONFIG_X86_64)
 static volatile u32 good_insns_64[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 	/*      ----------------------------------------------         */
-	W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 00 */
+	W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* 00 */
 	W(0x10, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 10 */
-	W(0x20, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 20 */
-	W(0x30, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 30 */
-	W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */
+	W(0x20, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) | /* 20 */
+	W(0x30, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) , /* 30 */
+	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
 	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
-	W(0x60, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
+	W(0x60, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
 	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */
 	W(0x80, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
-	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1) , /* 90 */
 	W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */
 	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
-	W(0xc0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
+	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
 	W(0xd0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
-	W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */
-	W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1)   /* f0 */
+	W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0) | /* e0 */
+	W(0xf0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1)   /* f0 */
 	/*      ----------------------------------------------         */
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 };
@@ -122,49 +183,55 @@ static volatile u32 good_insns_64[256 / 32] = {
 #define good_insns_64	NULL
 #endif
 
-/* Using this for both 64-bit and 32-bit apps */
+/* Using this for both 64-bit and 32-bit apps.
+ * Opcodes we don't support:
+ * 0f 00 - SLDT/STR/LLDT/LTR/VERR/VERW/-/- group. System insns
+ * 0f 01 - SGDT/SIDT/LGDT/LIDT/SMSW/-/LMSW/INVLPG group.
+ *	Also encodes tons of other system insns if mod=11.
+ *	Some are in fact non-system: xend, xtest, rdtscp, maybe more
+ * 0f 05 - syscall
+ * 0f 06 - clts (CPL0 insn)
+ * 0f 07 - sysret
+ * 0f 08 - invd (CPL0 insn)
+ * 0f 09 - wbinvd (CPL0 insn)
+ * 0f 0b - ud2
+ * 0f 30 - wrmsr (CPL0 insn) (then why rdmsr is allowed, it's also CPL0 insn?)
+ * 0f 34 - sysenter
+ * 0f 35 - sysexit
+ * 0f 37 - getsec
+ * 0f 78 - vmread (Intel VMX. CPL0 insn)
+ * 0f 79 - vmwrite (Intel VMX. CPL0 insn)
+ *	Note: with prefixes, these two opcodes are
+ *	extrq/insertq/AVX512 convert vector ops.
+ * 0f ae - group15: [f]xsave,[f]xrstor,[v]{ld,st}mxcsr,clflush[opt],
+ *	{rd,wr}{fs,gs}base,{s,l,m}fence.
+ *	Why? They are all user-executable.
+ */
 static volatile u32 good_2byte_insns[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 	/*      ----------------------------------------------         */
-	W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */
-	W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
-	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
-	W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
+	W(0x00, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1) | /* 00 */
+	W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
+	W(0x20, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
+	W(0x30, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) , /* 30 */
 	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
 	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
 	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */
-	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
+	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1) , /* 70 */
 	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
 	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
-	W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
-	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
+	W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
+	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
 	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
-	W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+	W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
 	W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */
-	W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0)   /* f0 */
+	W(0xf0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1)   /* f0 */
 	/*      ----------------------------------------------         */
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 };
 #undef W
 
 /*
- * opcodes we'll probably never support:
- *
- *  6c-6d, e4-e5, ec-ed - in
- *  6e-6f, e6-e7, ee-ef - out
- *  cc, cd - int3, int
- *  cf - iret
- *  d6 - illegal instruction
- *  f1 - int1/icebp
- *  f4 - hlt
- *  fa, fb - cli, sti
- *  0f - lar, lsl, syscall, clts, sysret, sysenter, sysexit, invd, wbinvd, ud2
- *
- * invalid opcodes in 64-bit mode:
- *
- *  06, 0e, 16, 1e, 27, 2f, 37, 3f, 60-62, 82, c4-c5, d4-d5
- *  63 - we support this opcode in x86_64 but not in i386.
- *
  * opcodes we may need to refine support for:
  *
  *  0f - 2-byte instructions: For many of these instructions, the validity

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-01-30 18:44 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-01-30 18:44 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e742f3dc0886a92403d578e8ac771e5e33d06d08 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, but also an event groups fix, two PMU 
driver fixes and a CPU model variant addition.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf evlist: Remove extraneous 'was' on error message
      perf symbols: Introduce method to iterate symbols ordered by name
      perf symbols: Introduce 'for' method to iterate over the symbols with a given name

Kan Liang (2):
      perf/x86/intel/uncore: Move uncore_box_init() out of driver initialization
      perf/x86/intel: Add model number for Airmont

Namhyung Kim (3):
      perf symbols: Return the first entry with a given name in find_by_name method
      perf probe: Do not rely on map__load() filter to find symbols
      perf probe: Fix probing kretprobes

Peter Zijlstra (1):
      perf: Tighten (and fix) the grouping condition

Rabin Vincent (2):
      perf annotate: Handle ins parsing failures
      perf annotate: Fix memory leaks in LOCK handling

Stephane Eranian (1):
      perf/rapl: Fix crash in rapl_scale()

Wang Nan (1):
      perf scripting perl: Force to use stdbool


 arch/x86/kernel/cpu/perf_event_intel.c            |  1 +
 arch/x86/kernel/cpu/perf_event_intel_rapl.c       |  2 +-
 arch/x86/kernel/cpu/perf_event_intel_uncore.c     |  9 ++----
 arch/x86/kernel/cpu/perf_event_intel_uncore.h     | 18 ++++++------
 include/linux/perf_event.h                        |  6 ----
 kernel/events/core.c                              | 15 ++++++++--
 tools/perf/scripts/perl/Perf-Trace-Util/Context.c |  5 +++-
 tools/perf/util/annotate.c                        | 18 +++++++++---
 tools/perf/util/evlist.c                          |  2 +-
 tools/perf/util/map.h                             | 16 +++++++++++
 tools/perf/util/probe-event.c                     | 34 +++++++++++------------
 tools/perf/util/symbol.c                          | 31 +++++++++++++++++++--
 tools/perf/util/symbol.h                          |  1 +
 13 files changed, 107 insertions(+), 51 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf019b74f..498b6d967138 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
 	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 6e434f8e5fc8..c4bb8b8e5017 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -142,7 +142,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+	return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 10b8d3eaaf15..c635b8b49e93 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
-	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu)
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0) {
-				uncore_box_init(box);
+			if (box && box->phys_id >= 0)
 				continue;
-			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			if (box) {
+			if (box)
 				box->phys_id = phys_id;
-				uncore_box_init(box);
-			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 863d9b02563e..6c8c1e7e69d8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	return box->pmu->type->num_counters;
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
+	uncore_box_init(box);
+
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61ca4b39..664de5a4ec46 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -450,11 +450,6 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
-enum perf_event_context_type {
-	task_context,
-	cpu_context,
-};
-
 /**
  * struct perf_event_context - event context structure
  *
@@ -462,7 +457,6 @@ enum perf_event_context_type {
  */
 struct perf_event_context {
 	struct pmu			*pmu;
-	enum perf_event_context_type	type;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835a0d85..19efcf13375a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6776,7 +6776,6 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 		__perf_event_init_context(&cpuctx->ctx);
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
-		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7420,7 +7419,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * task or CPU context:
 		 */
 		if (move_group) {
-			if (group_leader->ctx->type != ctx->type)
+			/*
+			 * Make sure we're both on the same task, or both
+			 * per-cpu events.
+			 */
+			if (group_leader->ctx->task != ctx->task)
+				goto err_context;
+
+			/*
+			 * Make sure we're both events for the same CPU;
+			 * grouping events for different CPUs is broken; since
+			 * you can never concurrently schedule them anyhow.
+			 */
+			if (group_leader->cpu != event->cpu)
 				goto err_context;
 		} else {
 			if (group_leader->ctx != ctx)
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 790ceba6ad3f..28431d1bbcf5 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -5,7 +5,10 @@
  *	ANY CHANGES MADE HERE WILL BE LOST! 
  *
  */
-
+#include <stdbool.h>
+#ifndef HAS_BOOL
+# define HAS_BOOL 1
+#endif
 #line 1 "Context.xs"
 /*
  * Context.xs.  XS interfaces for perf script.
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 79999ceaf2be..01bc4e23a2cf 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -177,14 +177,17 @@ static int lock__parse(struct ins_operands *ops)
 		goto out_free_ops;
 
 	ops->locked.ins = ins__find(name);
+	free(name);
+
 	if (ops->locked.ins == NULL)
 		goto out_free_ops;
 
 	if (!ops->locked.ins->ops)
 		return 0;
 
-	if (ops->locked.ins->ops->parse)
-		ops->locked.ins->ops->parse(ops->locked.ops);
+	if (ops->locked.ins->ops->parse &&
+	    ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+		goto out_free_ops;
 
 	return 0;
 
@@ -208,6 +211,13 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void lock__delete(struct ins_operands *ops)
 {
+	struct ins *ins = ops->locked.ins;
+
+	if (ins && ins->ops->free)
+		ins->ops->free(ops->locked.ops);
+	else
+		ins__delete(ops->locked.ops);
+
 	zfree(&ops->locked.ops);
 	zfree(&ops->target.raw);
 	zfree(&ops->target.name);
@@ -531,8 +541,8 @@ static void disasm_line__init_ins(struct disasm_line *dl)
 	if (!dl->ins->ops)
 		return;
 
-	if (dl->ins->ops->parse)
-		dl->ins->ops->parse(&dl->ops);
+	if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+		dl->ins = NULL;
 }
 
 static int disasm_line__parse(char *line, char **namep, char **rawp)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cbab1fb77b1d..2e507b5025a3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1445,7 +1445,7 @@ int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
 	case ENOENT:
 		scnprintf(buf, size, "%s",
 			  "Error:\tUnable to find debugfs\n"
-			  "Hint:\tWas your kernel was compiled with debugfs support?\n"
+			  "Hint:\tWas your kernel compiled with debugfs support?\n"
 			  "Hint:\tIs the debugfs filesystem mounted?\n"
 			  "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
 		break;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 6951a9d42339..0e42438b1e59 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -116,6 +116,22 @@ struct thread;
 #define map__for_each_symbol(map, pos, n)	\
 	dso__for_each_symbol(map->dso, pos, n, map->type)
 
+/* map__for_each_symbol_with_name - iterate over the symbols in the given map
+ *                                  that have the given name
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @sym_name: the symbol name
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @filter: to use when loading the DSO
+ */
+#define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
+	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
+	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos = symbol__next_by_name(pos))
+
+#define map__for_each_symbol_by_name(map, sym_name, pos)		\
+	__map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 94a717bf007d..919937eb0be2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -446,7 +446,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (tevs[i].point.address) {
+		if (tevs[i].point.address && !tevs[i].point.retprobe) {
 			tmp = strdup(reloc_sym->name);
 			if (!tmp)
 				return -ENOMEM;
@@ -2193,18 +2193,17 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	return ret;
 }
 
-static char *looking_function_name;
-static int num_matched_functions;
-
-static int probe_function_filter(struct map *map __maybe_unused,
-				      struct symbol *sym)
+static int find_probe_functions(struct map *map, char *name)
 {
-	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
-	    strcmp(looking_function_name, sym->name) == 0) {
-		num_matched_functions++;
-		return 0;
+	int found = 0;
+	struct symbol *sym;
+
+	map__for_each_symbol_by_name(map, name, sym) {
+		if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL)
+			found++;
 	}
-	return 1;
+
+	return found;
 }
 
 #define strdup_or_goto(str, label)	\
@@ -2222,10 +2221,10 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	struct kmap *kmap = NULL;
 	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
-	struct rb_node *nd;
 	struct probe_trace_event *tev;
 	struct perf_probe_point *pp = &pev->point;
 	struct probe_trace_point *tp;
+	int num_matched_functions;
 	int ret, i;
 
 	/* Init maps of given executable or kernel */
@@ -2242,10 +2241,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	 * Load matched symbols: Since the different local symbols may have
 	 * same name but different addresses, this lists all the symbols.
 	 */
-	num_matched_functions = 0;
-	looking_function_name = pp->function;
-	ret = map__load(map, probe_function_filter);
-	if (ret || num_matched_functions == 0) {
+	num_matched_functions = find_probe_functions(map, pp->function);
+	if (num_matched_functions == 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
 			target ? : "kernel");
 		ret = -ENOENT;
@@ -2257,7 +2254,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		goto out;
 	}
 
-	if (!pev->uprobes) {
+	if (!pev->uprobes && !pp->retprobe) {
 		kmap = map__kmap(map);
 		reloc_sym = kmap->ref_reloc_sym;
 		if (!reloc_sym) {
@@ -2275,7 +2272,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 	ret = 0;
-	map__for_each_symbol(map, sym, nd) {
+
+	map__for_each_symbol_by_name(map, pp->function, sym) {
 		tev = (*tevs) + ret;
 		tp = &tev->point;
 		if (ret == num_matched_functions) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c24c5b83156c..a194702a0a2f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -396,6 +396,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 					    const char *name)
 {
 	struct rb_node *n;
+	struct symbol_name_rb_node *s;
 
 	if (symbols == NULL)
 		return NULL;
@@ -403,7 +404,6 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 	n = symbols->rb_node;
 
 	while (n) {
-		struct symbol_name_rb_node *s;
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
@@ -414,10 +414,24 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		else if (cmp > 0)
 			n = n->rb_right;
 		else
-			return &s->sym;
+			break;
 	}
 
-	return NULL;
+	if (n == NULL)
+		return NULL;
+
+	/* return first symbol that has same name (if any) */
+	for (n = rb_prev(n); n; n = rb_prev(n)) {
+		struct symbol_name_rb_node *tmp;
+
+		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
+		if (strcmp(tmp->sym.name, s->sym.name))
+			break;
+
+		s = tmp;
+	}
+
+	return &s->sym;
 }
 
 struct symbol *dso__find_symbol(struct dso *dso,
@@ -436,6 +450,17 @@ struct symbol *dso__next_symbol(struct symbol *sym)
 	return symbols__next(sym);
 }
 
+struct symbol *symbol__next_by_name(struct symbol *sym)
+{
+	struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
+	struct rb_node *n = rb_next(&s->rb_node);
+
+	return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
+}
+
+ /*
+  * Teturns first symbol that matched with @name.
+  */
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9d602e9c6f59..1650dcb3a67b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -231,6 +231,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 				u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
+struct symbol *symbol__next_by_name(struct symbol *sym);
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 struct symbol *dso__next_symbol(struct symbol *sym);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-01-17 14:15 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-01-17 14:15 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d01de2389c0190f5959f0a1258a2e87d2fe4ca82 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, but also two PMU driver fixes.

 Thanks,

	Ingo

------------------>
Alexey Brodkin (1):
      perf tools: Fix statfs.f_type data type mismatch build error with uclibc

Arnaldo Carvalho de Melo (1):
      tools: Remove bitops/hweight usage of bits in tools/perf

Kan Liang (1):
      perf/x86/intel: Fix bug for "cycles:p" and "cycles:pp" on SLM

Namhyung Kim (4):
      perf probe: Propagate error code when write(2) failed
      perf tools: Fix building error in x86_64 when dwarf unwind is on
      perf machine: Fix __machine__findnew_thread() error path
      perf tools: Fix segfault for symbol annotation on TUI

Stephane Eranian (1):
      perf/rapl: Fix sysfs_show() initialization for RAPL PMU

Sukadev Bhattiprolu (1):
      perf tools powerpc: Use dwfl_report_elf() instead of offline.

Vineet Gupta (2):
      perf tools: Elide strlcpy warning with uclibc
      perf tools: Avoid build splat for syscall numbers with uclibc

Wang Nan (1):
      perf test: Fix dwarf unwind using libunwind.


 arch/x86/kernel/cpu/perf_event_intel_ds.c         |  4 +--
 arch/x86/kernel/cpu/perf_event_intel_rapl.c       | 44 ++++++++++++++++-------
 tools/include/asm-generic/bitops.h                |  2 ++
 tools/include/asm-generic/bitops/arch_hweight.h   |  1 +
 tools/include/asm-generic/bitops/const_hweight.h  |  1 +
 tools/include/asm-generic/bitops/hweight.h        |  7 ++++
 tools/include/linux/bitops.h                      |  7 +++-
 tools/lib/api/fs/debugfs.c                        |  2 +-
 tools/lib/api/fs/fs.c                             |  2 +-
 tools/perf/MANIFEST                               |  6 ++++
 tools/perf/Makefile.perf                          | 11 ++++--
 tools/perf/arch/powerpc/util/skip-callchain-idx.c | 19 +++++-----
 tools/perf/bench/sched-pipe.c                     |  2 +-
 tools/perf/builtin-top.c                          |  1 -
 tools/perf/config/Makefile                        |  2 +-
 tools/perf/config/Makefile.arch                   | 26 +++++++-------
 tools/perf/perf-sys.h                             |  1 -
 tools/perf/tests/dwarf-unwind.c                   | 36 +++++++++++++++++--
 tools/perf/util/annotate.h                        |  8 +----
 tools/perf/util/cache.h                           |  2 ++
 tools/perf/util/hweight.c                         | 31 ----------------
 tools/perf/util/include/asm/hweight.h             |  8 -----
 tools/perf/util/machine.c                         |  4 ++-
 tools/perf/util/probe-event.c                     |  4 ++-
 tools/perf/util/python-ext-sources                |  2 +-
 tools/perf/util/unwind-libunwind.c                | 28 ++++++++++++++-
 26 files changed, 165 insertions(+), 96 deletions(-)
 create mode 100644 tools/include/asm-generic/bitops/arch_hweight.h
 create mode 100644 tools/include/asm-generic/bitops/const_hweight.h
 create mode 100644 tools/include/asm-generic/bitops/hweight.h
 delete mode 100644 tools/perf/util/hweight.c
 delete mode 100644 tools/perf/util/include/asm/hweight.h

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3c895d480cd7..073983398364 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -568,8 +568,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
-	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
 	/* Allow all events as PEBS with no flags */
 	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 673f930c700f..6e434f8e5fc8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -103,6 +103,13 @@ static struct kobj_attribute format_attr_##_var =		\
 
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
+#define RAPL_EVENT_ATTR_STR(_name, v, str)				\
+static struct perf_pmu_events_attr event_attr_##v = {			\
+	.attr		= __ATTR(_name, 0444, rapl_sysfs_show, NULL),	\
+	.id		= 0,						\
+	.event_str	= str,						\
+};
+
 struct rapl_pmu {
 	spinlock_t	 lock;
 	int		 hw_unit;  /* 1/2^hw_unit Joule */
@@ -379,23 +386,36 @@ static struct attribute_group rapl_pmu_attr_group = {
 	.attrs = rapl_pmu_attrs,
 };
 
-EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
-EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
-EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
+static ssize_t rapl_sysfs_show(struct device *dev,
+			       struct device_attribute *attr,
+			       char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr = \
+		container_of(attr, struct perf_pmu_events_attr, attr);
+
+	if (pmu_attr->event_str)
+		return sprintf(page, "%s", pmu_attr->event_str);
+
+	return 0;
+}
+
+RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
+RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
+RAPL_EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
 
-EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
-EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
-EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
  */
-EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
 
 static struct attribute *rapl_events_srv_attr[] = {
 	EVENT_PTR(rapl_cores),
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 6eedba1f7732..653d1bad77de 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -22,6 +22,8 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
+#include <asm-generic/bitops/hweight.h>
+
 #include <asm-generic/bitops/atomic.h>
 
 #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000000..318bb2b202b0
--- /dev/null
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1 @@
+#include "../../../../include/asm-generic/bitops/arch_hweight.h"
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000000..0afd644aff83
--- /dev/null
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1 @@
+#include "../../../../include/asm-generic/bitops/const_hweight.h"
diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h
new file mode 100644
index 000000000000..290120c01a8e
--- /dev/null
+++ b/tools/include/asm-generic/bitops/hweight.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 26005a15e7e2..5ad9ee1dd7f6 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -1,9 +1,9 @@
 #ifndef _TOOLS_LINUX_BITOPS_H_
 #define _TOOLS_LINUX_BITOPS_H_
 
+#include <asm/types.h>
 #include <linux/kernel.h>
 #include <linux/compiler.h>
-#include <asm/hweight.h>
 
 #ifndef __WORDSIZE
 #define __WORDSIZE (__SIZEOF_LONG__ * 8)
@@ -19,6 +19,11 @@
 #define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 #define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE)
 
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
 /*
  * Include this here because some architectures need generic_ffs/fls in
  * scope
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
index a74fba6d7743..86ea2d7b8845 100644
--- a/tools/lib/api/fs/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
@@ -67,7 +67,7 @@ int debugfs_valid_mountpoint(const char *debugfs)
 
 	if (statfs(debugfs, &st_fs) < 0)
 		return -ENOENT;
-	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+	else if ((long)st_fs.f_type != (long)DEBUGFS_MAGIC)
 		return -ENOENT;
 
 	return 0;
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 65d9be3f9887..128ef6332a6b 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -79,7 +79,7 @@ static int fs__valid_mount(const char *fs, long magic)
 
 	if (statfs(fs, &st_fs) < 0)
 		return -ENOENT;
-	else if (st_fs.f_type != magic)
+	else if ((long)st_fs.f_type != magic)
 		return -ENOENT;
 
 	return 0;
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 83e2887f91a3..fbbfdc39271d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -6,12 +6,15 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
 tools/include/asm/bug.h
+tools/include/asm-generic/bitops/arch_hweight.h
 tools/include/asm-generic/bitops/atomic.h
+tools/include/asm-generic/bitops/const_hweight.h
 tools/include/asm-generic/bitops/__ffs.h
 tools/include/asm-generic/bitops/__fls.h
 tools/include/asm-generic/bitops/find.h
 tools/include/asm-generic/bitops/fls64.h
 tools/include/asm-generic/bitops/fls.h
+tools/include/asm-generic/bitops/hweight.h
 tools/include/asm-generic/bitops.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
@@ -19,6 +22,8 @@ tools/include/linux/export.h
 tools/include/linux/hash.h
 tools/include/linux/log2.h
 tools/include/linux/types.h
+include/asm-generic/bitops/arch_hweight.h
+include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
@@ -29,6 +34,7 @@ include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
 lib/find_next_bit.c
+lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 67a03a825b3c..aa6a50447c32 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -232,12 +232,15 @@ LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += ../include/linux/bitops.h
+LIB_H += ../include/asm-generic/bitops/arch_hweight.h
 LIB_H += ../include/asm-generic/bitops/atomic.h
+LIB_H += ../include/asm-generic/bitops/const_hweight.h
 LIB_H += ../include/asm-generic/bitops/find.h
 LIB_H += ../include/asm-generic/bitops/fls64.h
 LIB_H += ../include/asm-generic/bitops/fls.h
 LIB_H += ../include/asm-generic/bitops/__ffs.h
 LIB_H += ../include/asm-generic/bitops/__fls.h
+LIB_H += ../include/asm-generic/bitops/hweight.h
 LIB_H += ../include/asm-generic/bitops.h
 LIB_H += ../include/linux/compiler.h
 LIB_H += ../include/linux/log2.h
@@ -255,7 +258,6 @@ LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += ../include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
-LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
@@ -462,10 +464,12 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-ifeq ($(RAW_ARCH),x86_64)
+ifeq ($(ARCH), x86)
+ifeq ($(IS_64_BIT), 1)
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
@@ -743,6 +747,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
 $(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3bb50eac5542..0c370f81e002 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
 		return NULL;
 	}
 
-	result = dwarf_cfi_addrframe(cfi, pc, &frame);
+	result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
 	if (result) {
 		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
 		return NULL;
@@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
 		return NULL;
 	}
 
-	result = dwarf_cfi_addrframe(cfi, pc, &frame);
+	result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
 	if (result) {
 		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
 		return NULL;
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
  *		yet used)
  *	-1 in case of errors
  */
-static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
+static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc)
 {
 	int		rc = -1;
 	Dwfl		*dwfl;
@@ -155,6 +155,7 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
 	Dwarf_Addr	start = pc;
 	Dwarf_Addr	end = pc;
 	bool		signalp;
+	const char	*exec_file = dso->long_name;
 
 	dwfl = dso->dwfl;
 
@@ -165,8 +166,10 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
 			return -1;
 		}
 
-		if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) {
-			pr_debug("dwfl_report_offline() failed %s\n",
+		mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1,
+						map_start, false);
+		if (!mod) {
+			pr_debug("dwfl_report_elf() failed %s\n",
 						dwarf_errmsg(-1));
 			/*
 			 * We normally cache the DWARF debug info and never
@@ -256,10 +259,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 		return skip_slot;
 	}
 
-	rc = check_return_addr(dso, ip);
+	rc = check_return_addr(dso, al.map->start, ip);
 
-	pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
-				dso->long_name, chain->nr, ip, rc);
+	pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
+				dso->long_name, al.sym->name, ip, rc);
 
 	if (rc == 0) {
 		/*
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 07a8d7646a15..005cc283790c 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -19,12 +19,12 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/wait.h>
-#include <linux/unistd.h>
 #include <string.h>
 #include <errno.h>
 #include <assert.h>
 #include <sys/time.h>
 #include <sys/types.h>
+#include <sys/syscall.h>
 
 #include <pthread.h>
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 961cea183a83..616f0fcb4701 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -66,7 +66,6 @@
 #include <sys/utsname.h>
 #include <sys/mman.h>
 
-#include <linux/unistd.h>
 #include <linux/types.h>
 
 static volatile int done;
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5d4b039fe1ed..648e31ff4021 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -20,7 +20,7 @@ NO_PERF_REGS := 1
 
 # Additional ARCH settings for x86
 ifeq ($(ARCH),x86)
-  ifeq (${IS_X86_64}, 1)
+  ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index 851cd0172a76..ff95a68741d1 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -1,7 +1,7 @@
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
@@ -9,23 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/tile.*/tile/ )
 
 # Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-  override ARCH := x86
+ifeq ($(RAW_ARCH),i386)
+  ARCH ?= x86
 endif
 
-ifeq ($(ARCH),x86_64)
-  override ARCH := x86
-  IS_X86_64 := 0
-  ifeq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-    RAW_ARCH := x86_64
+ifeq ($(RAW_ARCH),x86_64)
+  ARCH ?= x86
+
+  ifneq (, $(findstring m32,$(CFLAGS)))
+    RAW_ARCH := x86_32
   endif
 endif
 
-ifeq (${IS_X86_64}, 1)
+ARCH ?= $(RAW_ARCH)
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
   IS_64_BIT := 1
-else ifeq ($(ARCH),x86)
-  IS_64_BIT := 0
 else
-  IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+  IS_64_BIT := 0
 endif
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index a3b13d7dc1d4..6ef68165c9db 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,7 +6,6 @@
 #include <sys/syscall.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
-#include <asm/unistd.h>
 
 #if defined(__i386__)
 #define mb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index ab28cca2cb97..0bf06bec68c7 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -11,6 +11,9 @@
 #include "thread.h"
 #include "callchain.h"
 
+/* For bsearch. We try to unwind functions in shared object. */
+#include <stdlib.h>
+
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
 			struct perf_sample *sample __maybe_unused,
@@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine)
 						  mmap_handler, machine, true);
 }
 
-#define MAX_STACK 6
+#define MAX_STACK 8
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
@@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	static const char *funcs[MAX_STACK] = {
 		"test__arch_unwind_sample",
 		"unwind_thread",
+		"compare",
+		"bsearch",
 		"krava_3",
 		"krava_2",
 		"krava_1",
@@ -88,10 +93,37 @@ static int unwind_thread(struct thread *thread)
 	return err;
 }
 
+static int global_unwind_retval = -INT_MAX;
+
+__attribute__ ((noinline))
+static int compare(void *p1, void *p2)
+{
+	/* Any possible value should be 'thread' */
+	struct thread *thread = *(struct thread **)p1;
+
+	if (global_unwind_retval == -INT_MAX)
+		global_unwind_retval = unwind_thread(thread);
+
+	return p1 - p2;
+}
+
 __attribute__ ((noinline))
 static int krava_3(struct thread *thread)
 {
-	return unwind_thread(thread);
+	struct thread *array[2] = {thread, thread};
+	void *fp = &bsearch;
+	/*
+	 * make _bsearch a volatile function pointer to
+	 * prevent potential optimization, which may expand
+	 * bsearch and call compare directly from this function,
+	 * instead of libc shared object.
+	 */
+	void *(*volatile _bsearch)(void *, void *, size_t,
+			size_t, int (*)(void *, void *));
+
+	_bsearch = fp;
+	_bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+	return global_unwind_retval;
 }
 
 __attribute__ ((noinline))
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 0784a9420528..cadbdc90a5cb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -116,11 +116,6 @@ struct annotation {
 	struct annotated_source *src;
 };
 
-struct sannotation {
-	struct annotation annotation;
-	struct symbol	  symbol;
-};
-
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
 {
 	return (((void *)&notes->src->histograms) +
@@ -129,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i
 
 static inline struct annotation *symbol__annotation(struct symbol *sym)
 {
-	struct sannotation *a = container_of(sym, struct sannotation, symbol);
-	return &a->annotation;
+	return (void *)sym - symbol_conf.priv_size;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 5cf9e1b5989d..d04d770d90f6 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
+#ifndef __UCLIBC__
 /* Matches the libc/libbsd function attribute so we declare this unconditionally: */
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
deleted file mode 100644
index 5c1d0d099f0d..000000000000
--- a/tools/perf/util/hweight.c
+++ /dev/null
@@ -1,31 +0,0 @@
-#include <linux/bitops.h>
-
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-unsigned int hweight32(unsigned int w)
-{
-	unsigned int res = w - ((w >> 1) & 0x55555555);
-	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
-	res = (res + (res >> 4)) & 0x0F0F0F0F;
-	res = res + (res >> 8);
-	return (res + (res >> 16)) & 0x000000FF;
-}
-
-unsigned long hweight64(__u64 w)
-{
-#if BITS_PER_LONG == 32
-	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
-#elif BITS_PER_LONG == 64
-	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
-	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
-	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
-	res = res + (res >> 8);
-	res = res + (res >> 16);
-	return (res + (res >> 32)) & 0x00000000000000FFul;
-#endif
-}
diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
deleted file mode 100644
index 36cf26d434a5..000000000000
--- a/tools/perf/util/include/asm/hweight.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef PERF_HWEIGHT_H
-#define PERF_HWEIGHT_H
-
-#include <linux/types.h>
-unsigned int hweight32(unsigned int w);
-unsigned long hweight64(__u64 w);
-
-#endif /* PERF_HWEIGHT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 94de3e48b490..1bca3a9f2b16 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);
-		machine->last_match = th;
 
 		/*
 		 * We have to initialize map_groups separately
@@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
+			rb_erase(&th->rb_node, &machine->threads);
 			thread__delete(th);
 			return NULL;
 		}
+
+		machine->last_match = th;
 	}
 
 	return th;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 7f9b8632e433..94a717bf007d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2052,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 	pr_debug("Writing event: %s\n", buf);
 	if (!probe_event_dry_run) {
 		ret = write(fd, buf, strlen(buf));
-		if (ret <= 0)
+		if (ret <= 0) {
+			ret = -errno;
 			pr_warning("Failed to write event: %s\n",
 				   strerror_r(errno, sbuf, sizeof(sbuf)));
+		}
 	}
 	free(buf);
 	return ret;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 16a475a7d492..6c6a6953fa93 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-util/hweight.c
+../../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 371219a6daf1..6edf535f65c2 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name)
 	return offset;
 }
 
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	int retval = 0;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return 0;
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out;
+
+	retval = (ehdr.e_type == ET_EXEC);
+
+out:
+	elf_end(elf);
+	pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+	return retval;
+}
+#endif
+
 struct table_entry {
 	u32 start_ip_offset;
 	u32 fde_offset;
@@ -322,8 +344,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+		int fd = dso__data_fd(map->dso, ui->machine);
+		int is_exec = elf_is_exec(fd, map->dso->name);
+		unw_word_t base = is_exec ? 0 : map->start;
+
 		memset(&di, 0, sizeof(di));
-		if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
 					   map->start, map->end))
 			return dwarf_search_unwind_table(as, ip, &di, pi,
 							 need_unwind_info, arg);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2015-01-11  8:42 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2015-01-11  8:42 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 5306c31c5733cb4a79cc002e0c3ad256fd439614 perf/x86/uncore/hsw-ep: Handle systems with only two SBOXes

Mostly tooling fixes, but also some kernel side fixes: uncore PMU 
driver fix, user regs sampling fix and an instruction decoder fix 
that unbreaks PEBS precise sampling.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86/uncore/hsw-ep: Handle systems with only two SBOXes

Andy Lutomirski (2):
      perf: Move task_pt_regs sampling into arch code
      perf/x86_64: Improve user regs sampling

Masami Hiramatsu (1):
      perf probe: Fix to fall back to find probe point in symbols

Namhyung Kim (8):
      perf report: Show progress bar for output resorting
      perf ui/tui: Print backtrace symbols when segfault occurs
      perf callchain: Append callchains only when requested
      perf probe: Fix crash in dwarf_getcfi_elf
      perf diff: Fix to sort by baseline field by default
      perf hists: Fix children sort key behavior
      perf callchain: Free callchains when hist entries are deleted
      perf hists browser: Fix segfault when showing callchain

Peter Zijlstra (1):
      x86: Fix off-by-one in instruction decoder

Taesoo Kim (1):
      perf list: Fix --raw-dump option


 arch/arm/kernel/perf_regs.c                        |  8 ++
 arch/arm64/kernel/perf_regs.c                      |  8 ++
 arch/x86/kernel/cpu/perf_event_intel_uncore.h      |  2 +-
 .../x86/kernel/cpu/perf_event_intel_uncore_snbep.c | 17 ++++
 arch/x86/kernel/perf_regs.c                        | 90 ++++++++++++++++++++++
 arch/x86/lib/insn.c                                |  2 +-
 include/linux/perf_event.h                         | 12 +--
 include/linux/perf_regs.h                          | 16 ++++
 kernel/events/core.c                               | 19 ++---
 tools/perf/builtin-annotate.c                      |  2 +-
 tools/perf/builtin-diff.c                          | 46 ++++++++++-
 tools/perf/builtin-list.c                          | 13 +++-
 tools/perf/builtin-report.c                        | 24 +++++-
 tools/perf/builtin-top.c                           |  4 +-
 tools/perf/tests/hists_cumulate.c                  | 66 ++++++++--------
 tools/perf/tests/hists_filter.c                    |  2 +-
 tools/perf/tests/hists_output.c                    | 10 +--
 tools/perf/ui/browsers/hists.c                     |  2 +-
 tools/perf/ui/hist.c                               |  3 +
 tools/perf/ui/tui/setup.c                          | 26 ++++++-
 tools/perf/util/callchain.c                        | 30 ++++++++
 tools/perf/util/callchain.h                        |  2 +
 tools/perf/util/hist.c                             | 18 ++++-
 tools/perf/util/hist.h                             |  2 +-
 tools/perf/util/probe-event.c                      |  6 +-
 tools/perf/util/probe-finder.c                     | 18 ++++-
 26 files changed, 371 insertions(+), 77 deletions(-)

diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c67cbc..592dda3f21ff 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad705587..3f62b35fb6f1 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 18eb78bbdd10..863d9b02563e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	2
+#define UNCORE_EXTRA_PCI_DEV_MAX	3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX		8
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 745b158e9a65..21af6149edf2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -891,6 +891,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2026,6 +2027,17 @@ void hswep_uncore_cpu_init(void)
 {
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+	/* Detect 6-8 core systems with only two SBOXes */
+	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+		u32 capid4;
+
+		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+				      0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			hswep_uncore_sbox.num_boxes = 2;
+	}
+
 	uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2287,6 +2299,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
 						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..781861cc5ee8 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	struct pt_regs *user_regs = task_pt_regs(current);
+
+	/*
+	 * If we're in an NMI that interrupted task_pt_regs setup, then
+	 * we can't sample user regs at all.  This check isn't really
+	 * sufficient, though, as we could be in an NMI inside an interrupt
+	 * that happened during task_pt_regs setup.
+	 */
+	if (regs->sp > (unsigned long)&user_regs->r11 &&
+	    regs->sp <= (unsigned long)(user_regs + 1)) {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
+		return;
+	}
+
+	/*
+	 * RIP, flags, and the argument registers are usually saved.
+	 * orig_ax is probably okay, too.
+	 */
+	regs_user_copy->ip = user_regs->ip;
+	regs_user_copy->cx = user_regs->cx;
+	regs_user_copy->dx = user_regs->dx;
+	regs_user_copy->si = user_regs->si;
+	regs_user_copy->di = user_regs->di;
+	regs_user_copy->r8 = user_regs->r8;
+	regs_user_copy->r9 = user_regs->r9;
+	regs_user_copy->r10 = user_regs->r10;
+	regs_user_copy->r11 = user_regs->r11;
+	regs_user_copy->orig_ax = user_regs->orig_ax;
+	regs_user_copy->flags = user_regs->flags;
+
+	/*
+	 * Don't even try to report the "rest" regs.
+	 */
+	regs_user_copy->bx = -1;
+	regs_user_copy->bp = -1;
+	regs_user_copy->r12 = -1;
+	regs_user_copy->r13 = -1;
+	regs_user_copy->r14 = -1;
+	regs_user_copy->r15 = -1;
+
+	/*
+	 * For this to be at all useful, we need a reasonable guess for
+	 * sp and the ABI.  Be careful: we're in NMI context, and we're
+	 * considering current to be the current task, so we should
+	 * be careful not to look at any other percpu variables that might
+	 * change during context switches.
+	 */
+	if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+	    task_thread_info(current)->status & TS_COMPAT) {
+		/* Easy case: we're in a compat syscall. */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	} else if (user_regs->orig_ax != -1) {
+		/*
+		 * We're probably in a 64-bit syscall.
+		 * Warning: this code is severely racy.  At least it's better
+		 * than just blindly copying user_regs.
+		 */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
+		regs_user_copy->sp = this_cpu_read(old_rsp);
+		regs_user_copy->cs = __USER_CS;
+		regs_user_copy->ss = __USER_DS;
+		regs_user_copy->cx = -1;  /* usually contains garbage */
+	} else {
+		/* We're probably in an interrupt or exception. */
+		regs_user->abi = user_64bit_mode(user_regs) ?
+			PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	}
+
+	regs_user->regs = regs_user_copy;
+}
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 2480978b31cc..1313ae6b478b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -28,7 +28,7 @@
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr)
+	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
 	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84ccb1f9..4f7a61ca4b39 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,11 +79,6 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs {
-	__u64		abi;
-	struct pt_regs	*regs;
-};
-
 struct task_struct;
 
 /*
@@ -610,7 +605,14 @@ struct perf_sample_data {
 		u32	reserved;
 	}				cpu_entry;
 	struct perf_callchain_entry	*callchain;
+
+	/*
+	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
+	 * on arch details.
+	 */
 	struct perf_regs		regs_user;
+	struct pt_regs			regs_user_copy;
+
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 } ____cacheline_aligned;
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 3c73d5fe18be..a5f98d53d732 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,11 +1,19 @@
 #ifndef _LINUX_PERF_REGS_H
 #define _LINUX_PERF_REGS_H
 
+struct perf_regs {
+	__u64		abi;
+	struct pt_regs	*regs;
+};
+
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy);
 #else
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
@@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_NONE;
 }
+
+static inline void perf_get_regs_user(struct perf_regs *regs_user,
+				      struct pt_regs *regs,
+				      struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_HAVE_PERF_REGS */
 #endif /* _LINUX_PERF_REGS_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2bebc..882f835a0d85 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs)
+				  struct pt_regs *regs,
+				  struct pt_regs *regs_user_copy)
 {
-	if (!user_mode(regs)) {
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		regs_user->abi  = perf_reg_abi(current);
+	if (user_mode(regs)) {
+		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
+	} else if (current->mm) {
+		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs);
+		perf_sample_regs_user(&data->regs_user, regs,
+				      &data->regs_user_copy);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e7417fe97a97..747f86103599 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		if (nr_samples > 0) {
 			total_nr_samples += nr_samples;
 			hists__collapse_resort(hists, NULL);
-			hists__output_resort(hists);
+			hists__output_resort(hists, NULL);
 
 			if (symbol_conf.event_group &&
 			    !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1ce425d101a9..1fd96c13f199 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -545,6 +545,42 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
 	return __hist_entry__cmp_compute(p_left, p_right, c);
 }
 
+static int64_t
+hist_entry__cmp_nop(struct hist_entry *left __maybe_unused,
+		    struct hist_entry *right __maybe_unused)
+{
+	return 0;
+}
+
+static int64_t
+hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right)
+{
+	if (sort_compute)
+		return 0;
+
+	if (left->stat.period == right->stat.period)
+		return 0;
+	return left->stat.period > right->stat.period ? 1 : -1;
+}
+
+static int64_t
+hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute(right, left, COMPUTE_DELTA);
+}
+
+static int64_t
+hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute(right, left, COMPUTE_RATIO);
+}
+
+static int64_t
+hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void insert_hist_entry_by_compute(struct rb_root *root,
 					 struct hist_entry *he,
 					 int c)
@@ -605,7 +641,7 @@ static void hists__process(struct hists *hists)
 		hists__precompute(hists);
 		hists__compute_resort(hists);
 	} else {
-		hists__output_resort(hists);
+		hists__output_resort(hists, NULL);
 	}
 
 	hists__fprintf(hists, true, 0, 0, 0, stdout);
@@ -1038,27 +1074,35 @@ static void data__hpp_register(struct data__file *d, int idx)
 	fmt->header = hpp__header;
 	fmt->width  = hpp__width;
 	fmt->entry  = hpp__entry_global;
+	fmt->cmp    = hist_entry__cmp_nop;
+	fmt->collapse = hist_entry__cmp_nop;
 
 	/* TODO more colors */
 	switch (idx) {
 	case PERF_HPP_DIFF__BASELINE:
 		fmt->color = hpp__color_baseline;
+		fmt->sort  = hist_entry__cmp_baseline;
 		break;
 	case PERF_HPP_DIFF__DELTA:
 		fmt->color = hpp__color_delta;
+		fmt->sort  = hist_entry__cmp_delta;
 		break;
 	case PERF_HPP_DIFF__RATIO:
 		fmt->color = hpp__color_ratio;
+		fmt->sort  = hist_entry__cmp_ratio;
 		break;
 	case PERF_HPP_DIFF__WEIGHTED_DIFF:
 		fmt->color = hpp__color_wdiff;
+		fmt->sort  = hist_entry__cmp_wdiff;
 		break;
 	default:
+		fmt->sort  = hist_entry__cmp_nop;
 		break;
 	}
 
 	init_header(d, dfmt);
 	perf_hpp__column_register(fmt);
+	perf_hpp__register_sort_field(fmt);
 }
 
 static void ui_init(void)
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 011195e38f21..198f3c3aff95 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -19,7 +19,9 @@
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int i;
-	const struct option list_options[] = {
+	bool raw_dump = false;
+	struct option list_options[] = {
+		OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
 		OPT_END()
 	};
 	const char * const list_usage[] = {
@@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
+	set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN);
+
 	argc = parse_options(argc, argv, list_options, list_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	setup_pager();
 
+	if (raw_dump) {
+		print_events(NULL, true);
+		return 0;
+	}
+
 	if (argc == 0) {
 		print_events(NULL, false);
 		return 0;
@@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(NULL, false);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, false);
-		else if (strcmp(argv[i], "--raw-dump") == 0)
-			print_events(NULL, true);
 		else {
 			char *sep = strchr(argv[i], ':'), *s;
 			int sep_idx;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 39367609c707..072ae8ad67fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -457,6 +457,19 @@ static void report__collapse_hists(struct report *rep)
 	ui_progress__finish();
 }
 
+static void report__output_resort(struct report *rep)
+{
+	struct ui_progress prog;
+	struct perf_evsel *pos;
+
+	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
+
+	evlist__for_each(rep->session->evlist, pos)
+		hists__output_resort(evsel__hists(pos), &prog);
+
+	ui_progress__finish();
+}
+
 static int __cmd_report(struct report *rep)
 {
 	int ret;
@@ -505,13 +518,20 @@ static int __cmd_report(struct report *rep)
 	if (session_done())
 		return 0;
 
+	/*
+	 * recalculate number of entries after collapsing since it
+	 * might be changed during the collapse phase.
+	 */
+	rep->nr_entries = 0;
+	evlist__for_each(session->evlist, pos)
+		rep->nr_entries += evsel__hists(pos)->nr_entries;
+
 	if (rep->nr_entries == 0) {
 		ui__error("The %s file has no samples!\n", file->path);
 		return 0;
 	}
 
-	evlist__for_each(session->evlist, pos)
-		hists__output_resort(evsel__hists(pos));
+	report__output_resort(rep);
 
 	return report__browse_hists(rep);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0aa7747ff139..961cea183a83 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -285,7 +285,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
@@ -554,7 +554,7 @@ static void perf_top__sort_new_samples(void *arg)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 }
 
 static void *display_thread_tui(void *arg)
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 614d5c4978ab..8d110dec393e 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -187,7 +187,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 	 * function since TEST_ASSERT_VAL() returns in case of failure.
 	 */
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("use callchain: %d, cumulate callchain: %d\n",
@@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 	 *   30.00%    10.00%     perf  perf           [.] cmd_record
 	 *   20.00%     0.00%     bash  libc           [.] malloc
 	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
-	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
-	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
 	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
-	 *   10.00%    10.00%     perf  libc           [.] free
 	 *   10.00%    10.00%     perf  libc           [.] malloc
-	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
 	 */
 	struct result expected[] = {
 		{ 7000, 2000, "perf", "perf",     "main" },
@@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		{ 3000, 1000, "perf", "perf",     "cmd_record" },
 		{ 2000,    0, "bash", "libc",     "malloc" },
 		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
-		{ 1000, 1000, "perf", "[kernel]", "schedule" },
-		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
 		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
 		{ 1000, 1000, "perf", "libc",     "free" },
 		{ 1000, 1000, "perf", "libc",     "malloc" },
-		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
 	};
 
 	symbol_conf.use_callchain = false;
@@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	 *                  malloc
 	 *                  main
 	 *
-	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
 	 *              |
-	 *              --- schedule
-	 *                  run_command
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
 	 *                  main
 	 *
 	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
@@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	 *                  run_command
 	 *                  main
 	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
 	 *   10.00%    10.00%     perf  libc           [.] free
 	 *              |
 	 *              --- free
@@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	 *                  run_command
 	 *                  main
 	 *
-	 *   10.00%    10.00%     bash  bash           [.] xmalloc
-	 *              |
-	 *              --- xmalloc
-	 *                  malloc
-	 *                  xmalloc     <--- NOTE: there's a cycle
-	 *                  malloc
-	 *                  xmalloc
-	 *                  main
-	 *
 	 */
 	struct result expected[] = {
 		{ 7000, 2000, "perf", "perf",     "main" },
@@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		{ 3000, 1000, "perf", "perf",     "cmd_record" },
 		{ 2000,    0, "bash", "libc",     "malloc" },
 		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
-		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
 		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
 		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
 		{ 1000, 1000, "perf", "libc",     "free" },
 		{ 1000, 1000, "perf", "libc",     "malloc" },
-		{ 1000, 1000, "bash", "bash",     "xmalloc" },
 	};
 	struct callchain_result expected_callchain[] = {
 		{
@@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 				{ "bash",     "main" }, },
 		},
 		{
-			3, {	{ "[kernel]", "schedule" },
-				{ "perf",     "run_command" },
-				{ "perf",     "main" }, },
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
 		},
 		{
 			3, {	{ "[kernel]", "sys_perf_event_open" },
@@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 				{ "perf",     "main" }, },
 		},
 		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
 			4, {	{ "libc",     "free" },
 				{ "perf",     "cmd_record" },
 				{ "perf",     "run_command" },
@@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 				{ "perf",     "run_command" },
 				{ "perf",     "main" }, },
 		},
-		{
-			6, {	{ "bash",     "xmalloc" },
-				{ "libc",     "malloc" },
-				{ "bash",     "xmalloc" },
-				{ "libc",     "malloc" },
-				{ "bash",     "xmalloc" },
-				{ "bash",     "main" }, },
-		},
 	};
 
 	symbol_conf.use_callchain = true;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 74f257a81265..59e53db7914c 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -138,7 +138,7 @@ int test__hists_filter(void)
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
-		hists__output_resort(hists);
+		hists__output_resort(hists, NULL);
 
 		if (verbose > 2) {
 			pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a748f2be1222..f5547610da02 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e6bb04b5b09b..788506eef567 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -550,7 +550,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = !!rb_next(node);
+	need_percent = node && rb_next(node);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index dc0d095f318c..482adae3cc44 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 		if (ret)
 			return ret;
 
+		if (a->thread != b->thread || !symbol_conf.use_callchain)
+			return 0;
+
 		ret = b->callchain->max_depth - a->callchain->max_depth;
 	}
 	return ret;
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 2f612562978c..3c38f25b1695 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,5 +1,8 @@
 #include <signal.h>
 #include <stdbool.h>
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
@@ -88,6 +91,25 @@ int ui__getch(int delay_secs)
 	return SLkp_getkey();
 }
 
+#ifdef HAVE_BACKTRACE_SUPPORT
+static void ui__signal_backtrace(int sig)
+{
+	void *stackdump[32];
+	size_t size;
+
+	ui__exit(false);
+	psignal(sig, "perf");
+
+	printf("-------- backtrace --------\n");
+	size = backtrace(stackdump, ARRAY_SIZE(stackdump));
+	backtrace_symbols_fd(stackdump, size, STDOUT_FILENO);
+
+	exit(0);
+}
+#else
+# define ui__signal_backtrace  ui__signal
+#endif
+
 static void ui__signal(int sig)
 {
 	ui__exit(false);
@@ -122,8 +144,8 @@ int ui__init(void)
 	ui_browser__init();
 	tui_progress__init();
 
-	signal(SIGSEGV, ui__signal);
-	signal(SIGFPE, ui__signal);
+	signal(SIGSEGV, ui__signal_backtrace);
+	signal(SIGFPE, ui__signal_backtrace);
 	signal(SIGINT, ui__signal);
 	signal(SIGQUIT, ui__signal);
 	signal(SIGTERM, ui__signal);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 64b377e591e4..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 
 	return bf;
 }
+
+static void free_callchain_node(struct callchain_node *node)
+{
+	struct callchain_list *list, *tmp;
+	struct callchain_node *child;
+	struct rb_node *n;
+
+	list_for_each_entry_safe(list, tmp, &node->val, list) {
+		list_del(&list->list);
+		free(list);
+	}
+
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = container_of(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+		rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+		free_callchain_node(child);
+		free(child);
+	}
+}
+
+void free_callchain(struct callchain_root *root)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index dbc08cf5f970..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
 
+void free_callchain(struct callchain_root *root);
+
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6e88b9e395df..182395546ddc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
+#include "ui/progress.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -303,7 +304,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 	size_t callchain_size = 0;
 	struct hist_entry *he;
 
-	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+	if (symbol_conf.use_callchain)
 		callchain_size = sizeof(struct callchain_root);
 
 	he = zalloc(sizeof(*he) + callchain_size);
@@ -736,7 +737,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	callchain_append(he->callchain, &callchain_cursor, sample->period);
+	hist_entry__append_callchain(he, sample);
 
 	/*
 	 * We need to re-initialize the cursor since callchain_append()
@@ -809,7 +810,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	callchain_append(he->callchain, &cursor, sample->period);
+	if (symbol_conf.use_callchain)
+		callchain_append(he->callchain, &cursor, sample->period);
 	return 0;
 }
 
@@ -945,6 +947,7 @@ void hist_entry__free(struct hist_entry *he)
 	zfree(&he->mem_info);
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
+	free_callchain(he->callchain);
 	free(he);
 }
 
@@ -987,6 +990,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		else
 			p = &(*p)->rb_right;
 	}
+	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
@@ -1024,7 +1028,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	if (!sort__need_collapse)
 		return;
 
+	hists->nr_entries = 0;
+
 	root = hists__get_rotate_entries_in(hists);
+
 	next = rb_first(root);
 
 	while (next) {
@@ -1119,7 +1126,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	rb_insert_color(&he->rb_node, entries);
 }
 
-void hists__output_resort(struct hists *hists)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
@@ -1148,6 +1155,9 @@ void hists__output_resort(struct hists *hists)
 
 		if (!n->filtered)
 			hists__calc_col_len(hists, n);
+
+		if (prog)
+			ui_progress__update(prog, 1);
 	}
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d0ef9a19a744..46bd50344f85 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -121,7 +121,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
-void hists__output_resort(struct hists *hists);
+void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28eb1417cb2a..7f9b8632e433 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
-		pr_warning("Probe point '%s' not found.\n",
+		pr_warning("Probe point '%s' not found in debuginfo.\n",
 			   synthesize_perf_probe_point(&pev->point));
-		return -ENOENT;
+		if (need_dwarf)
+			return -ENOENT;
+		return 0;
 	}
 	/* Error path : ntevs < 0 */
 	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c7918f83b300..b5247d777f0e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	int ret = 0;
 
 #if _ELFUTILS_PREREQ(0, 142)
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+
 	/* Get the call frame information from this dwarf */
-	pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
+	elf = dwarf_getelf(dbg->dbg);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		return -EINVAL;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+	    shdr.sh_type == SHT_PROGBITS) {
+		pf->cfi = dwarf_getcfi_elf(elf);
+	} else {
+		pf->cfi = dwarf_getcfi(dbg->dbg);
+	}
 #endif
 
 	off = 0;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-11-20  7:46 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-11-20  7:46 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 68055915c1c22489f9658bd2b7391bb11b2cf4e4 perf/x86/intel/uncore: Fix boot crash on SBOX PMU on Haswell-EP

Misc fixes: two Intel uncore driver fixes, a CPU-hotplug fix and 
a build dependencies fix.

 Thanks,

	Ingo

------------------>
Andi Kleen (2):
      perf/x86/intel/uncore: Fix IRP uncore register offsets on Haswell EP
      perf/x86/intel/uncore: Fix boot crash on SBOX PMU on Haswell-EP

Mark Rutland (1):
      perf: Fix corruption of sibling list with hotplug

Peter Zijlstra (Intel) (1):
      perf/x86: Fix embarrasing typo


 arch/x86/Kconfig                                   |  2 +-
 .../x86/kernel/cpu/perf_event_intel_uncore_snbep.c | 49 ++++++++++++++++++++--
 kernel/events/core.c                               |  8 ++--
 3 files changed, 51 insertions(+), 8 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ded8a6774ac9..41a503c15862 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -144,7 +144,7 @@ config INSTRUCTION_DECODER
 
 config PERF_EVENTS_INTEL_UNCORE
 	def_bool y
-	depends on PERF_EVENTS && SUP_SUP_INTEL && PCI
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
 
 config OUTPUT_FORMAT
 	string
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index adf138eac85c..f9ed429d6e4f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -486,14 +486,17 @@ static struct attribute_group snbep_uncore_qpi_format_group = {
 	.attrs = snbep_uncore_qpi_formats_attr,
 };
 
-#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
-	.init_box	= snbep_uncore_msr_init_box,		\
+#define __SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
 	.disable_box	= snbep_uncore_msr_disable_box,		\
 	.enable_box	= snbep_uncore_msr_enable_box,		\
 	.disable_event	= snbep_uncore_msr_disable_event,	\
 	.enable_event	= snbep_uncore_msr_enable_event,	\
 	.read_counter	= uncore_msr_read_counter
 
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	__SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),			\
+	.init_box	= snbep_uncore_msr_init_box		\
+
 static struct intel_uncore_ops snbep_uncore_msr_ops = {
 	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
@@ -1919,6 +1922,30 @@ static struct intel_uncore_type hswep_uncore_cbox = {
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
+/*
+ * Write SBOX Initialization register bit by bit to avoid spurious #GPs
+ */
+static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+
+	if (msr) {
+		u64 init = SNBEP_PMON_BOX_CTL_INT;
+		u64 flags = 0;
+		int i;
+
+		for_each_set_bit(i, (unsigned long *)&init, 64) {
+			flags |= (1ULL << i);
+			wrmsrl(msr, flags);
+		}
+	}
+}
+
+static struct intel_uncore_ops hswep_uncore_sbox_msr_ops = {
+	__SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.init_box		= hswep_uncore_sbox_msr_init_box
+};
+
 static struct attribute *hswep_uncore_sbox_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -1944,7 +1971,7 @@ static struct intel_uncore_type hswep_uncore_sbox = {
 	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
 	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
 	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
-	.ops			= &snbep_uncore_msr_ops,
+	.ops			= &hswep_uncore_sbox_msr_ops,
 	.format_group		= &hswep_uncore_sbox_format_group,
 };
 
@@ -2025,13 +2052,27 @@ static struct intel_uncore_type hswep_uncore_imc = {
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+static unsigned hswep_uncore_irp_ctrs[] = {0xa0, 0xa8, 0xb0, 0xb8};
+
+static u64 hswep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 count = 0;
+
+	pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+	pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+	return count;
+}
+
 static struct intel_uncore_ops hswep_uncore_irp_ops = {
 	.init_box	= snbep_uncore_pci_init_box,
 	.disable_box	= snbep_uncore_pci_disable_box,
 	.enable_box	= snbep_uncore_pci_enable_box,
 	.disable_event	= ivbep_uncore_irp_disable_event,
 	.enable_event	= ivbep_uncore_irp_enable_event,
-	.read_counter	= ivbep_uncore_irp_read_counter,
+	.read_counter	= hswep_uncore_irp_read_counter,
 };
 
 static struct intel_uncore_type hswep_uncore_irp = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2b02c9fda790..1cd5eef1fcdd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1562,8 +1562,10 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group
 
 	if (!task) {
 		/*
-		 * Per cpu events are removed via an smp call and
-		 * the removal is always successful.
+		 * Per cpu events are removed via an smp call. The removal can
+		 * fail if the CPU is currently offline, but in that case we
+		 * already called __perf_remove_from_context from
+		 * perf_event_exit_cpu.
 		 */
 		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
@@ -8117,7 +8119,7 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
-	struct remove_event re = { .detach_group = false };
+	struct remove_event re = { .detach_group = true };
 	struct perf_event_context *ctx = __info;
 
 	perf_pmu_rotate_stop(ctx->pmu);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2014-11-03  9:02 ` Paul Bolle
@ 2014-11-03 10:04   ` Peter Zijlstra
  0 siblings, 0 replies; 376+ messages in thread
From: Peter Zijlstra @ 2014-11-03 10:04 UTC (permalink / raw)
  To: Paul Bolle
  Cc: Andi Kleen, Valentin Rothberg, Ingo Molnar, Linus Torvalds,
	linux-kernel, Arnaldo Carvalho de Melo, Jiri Olsa,
	Thomas Gleixner, Andrew Morton

On Mon, Nov 03, 2014 at 10:02:01AM +0100, Paul Bolle wrote:
> > +config PERF_EVENTS_INTEL_UNCORE
> > +	def_bool y
> > +	depends on PERF_EVENTS && SUP_SUP_INTEL && PCI
> 
> One expects this to be fixed by s/SUP_SUP_INTEL/CPU_SUP_INTEL/.

Yeah, I have that fixed; lemme try and get it in tip.

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2014-10-31 11:13 Ingo Molnar
@ 2014-11-03  9:02 ` Paul Bolle
  2014-11-03 10:04   ` Peter Zijlstra
  0 siblings, 1 reply; 376+ messages in thread
From: Paul Bolle @ 2014-11-03  9:02 UTC (permalink / raw)
  To: Peter Zijlstra
  Cc: Andi Kleen, Valentin Rothberg, Ingo Molnar, Linus Torvalds,
	linux-kernel, Arnaldo Carvalho de Melo, Jiri Olsa,
	Thomas Gleixner, Andrew Morton

Peter,

On Fri, 2014-10-31 at 12:13 +0100, Ingo Molnar wrote:
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
> 
>    # HEAD: d785452c9972fac2808479eb561d5c426b6e7d3b Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
> 
>[...]
>
> Peter Zijlstra (2):
>       [...]
>       perf/x86: Fix compile warnings for intel_uncore

This was included in v3.18-rc3.

> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index f2327e88e07c..ded8a6774ac9 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -142,6 +142,10 @@ config INSTRUCTION_DECODER
>  	def_bool y
>  	depends on KPROBES || PERF_EVENTS || UPROBES
>  
> +config PERF_EVENTS_INTEL_UNCORE
> +	def_bool y
> +	depends on PERF_EVENTS && SUP_SUP_INTEL && PCI

Andi spotted this typo (see https://lkml.org/lkml/2014/10/28/455 ). So
did my local perl script when it hit next-20141029. But since this was
already discussed I didn't bother to mention it too.

One expects this to be fixed by s/SUP_SUP_INTEL/CPU_SUP_INTEL/. Perhaps
the fix is more complicated, but anyhow, the typo isn't fixed in
next-20141103 or, as far as I can tell, in tip.git. So I decided to
remind you to make sure this doesn't fall through the cracks.

> +
>  config OUTPUT_FORMAT
>  	string
>  	default "elf32-i386" if X86_32


Paul Bolle


^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-10-31 11:13 Ingo Molnar
  2014-11-03  9:02 ` Paul Bolle
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2014-10-31 11:13 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d785452c9972fac2808479eb561d5c426b6e7d3b Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, plus on the kernel side:

 - a revert for a newly introduced PMU driver which isn't
   complete yet and where we ran out of time with fixes (to be 
   tried again in v3.19) - this makes up for a large chunk of the 
   diffstat.

 - compilation warning fixes

 - a printk message fix

 - event_idx usage fixes/cleanups.

 Thanks,

	Ingo

------------------>
Andy Lutomirski (1):
      perf: Fix typos in sample code in the perf_event.h header

Ingo Molnar (1):
      perf/x86/intel: Revert incomplete and undocumented Broadwell client support

Jiri Olsa (7):
      perf tools: Fix report -F abort for data without branch info
      perf tools: Fix report -F in_tx for data without branch info
      perf tools: Fix report -F mispredict for data without branch info
      perf tools: Fix report -F symbol_to for data without branch info
      perf tools: Fix report -F symbol_from for data without branch info
      perf tools: Fix report -F dso_to for data without branch info
      perf tools: Fix report -F dso_from for data without branch info

Kan Liang (1):
      perf diff: Add missing hists__init() call at tool start

Masami Hiramatsu (1):
      perf probe: Trivial typo fix for --demangle

Namhyung Kim (1):
      perf callchain: Use global caching provided by libunwind

Peter Zijlstra (2):
      perf: Fix and clean up initialization of pmu::event_idx
      perf/x86: Fix compile warnings for intel_uncore

Peter Zijlstra (Intel) (1):
      perf: Fix bogus kernel printk

Wang Nan (1):
      perf tools: Make CPUINFO_PROC an array to support different kernel versions


 arch/powerpc/perf/hv-24x7.c            |   6 --
 arch/powerpc/perf/hv-gpci.c            |   6 --
 arch/s390/kernel/perf_cpum_sf.c        |   6 --
 arch/x86/Kconfig                       |   4 +
 arch/x86/kernel/cpu/Makefile           |   7 +-
 arch/x86/kernel/cpu/perf_event.c       |  14 +--
 arch/x86/kernel/cpu/perf_event.h       |   1 -
 arch/x86/kernel/cpu/perf_event_intel.c | 173 +--------------------------------
 include/uapi/linux/perf_event.h        |  14 +--
 kernel/events/core.c                   |  15 +--
 kernel/events/hw_breakpoint.c          |   7 --
 tools/perf/builtin-diff.c              |   5 +
 tools/perf/builtin-probe.c             |   2 +-
 tools/perf/perf-sys.h                  |  30 +++---
 tools/perf/util/header.c               |  27 +++--
 tools/perf/util/sort.c                 | 102 ++++++++++++++-----
 tools/perf/util/thread.c               |   3 +
 tools/perf/util/unwind-libunwind.c     |  12 +++
 tools/perf/util/unwind.h               |   3 +
 19 files changed, 158 insertions(+), 279 deletions(-)

diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 6c8710dd90c9..dba34088da28 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -417,11 +417,6 @@ static int h_24x7_event_add(struct perf_event *event, int flags)
 	return 0;
 }
 
-static int h_24x7_event_idx(struct perf_event *event)
-{
-	return 0;
-}
-
 static struct pmu h_24x7_pmu = {
 	.task_ctx_nr = perf_invalid_context,
 
@@ -433,7 +428,6 @@ static struct pmu h_24x7_pmu = {
 	.start       = h_24x7_event_start,
 	.stop        = h_24x7_event_stop,
 	.read        = h_24x7_event_update,
-	.event_idx   = h_24x7_event_idx,
 };
 
 static int hv_24x7_init(void)
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 15fc76c93022..a051fe946c63 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -246,11 +246,6 @@ static int h_gpci_event_init(struct perf_event *event)
 	return 0;
 }
 
-static int h_gpci_event_idx(struct perf_event *event)
-{
-	return 0;
-}
-
 static struct pmu h_gpci_pmu = {
 	.task_ctx_nr = perf_invalid_context,
 
@@ -262,7 +257,6 @@ static struct pmu h_gpci_pmu = {
 	.start       = h_gpci_event_start,
 	.stop        = h_gpci_event_stop,
 	.read        = h_gpci_event_update,
-	.event_idx   = h_gpci_event_idx,
 };
 
 static int hv_gpci_init(void)
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 08e761318c17..b878f12a9597 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1411,11 +1411,6 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags)
 	perf_pmu_enable(event->pmu);
 }
 
-static int cpumsf_pmu_event_idx(struct perf_event *event)
-{
-	return event->hw.idx;
-}
-
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
 
@@ -1458,7 +1453,6 @@ static struct pmu cpumf_sampling = {
 	.stop	      = cpumsf_pmu_stop,
 	.read	      = cpumsf_pmu_read,
 
-	.event_idx    = cpumsf_pmu_event_idx,
 	.attr_groups  = cpumsf_pmu_attr_groups,
 };
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f2327e88e07c..ded8a6774ac9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -142,6 +142,10 @@ config INSTRUCTION_DECODER
 	def_bool y
 	depends on KPROBES || PERF_EVENTS || UPROBES
 
+config PERF_EVENTS_INTEL_UNCORE
+	def_bool y
+	depends on PERF_EVENTS && SUP_SUP_INTEL && PCI
+
 config OUTPUT_FORMAT
 	string
 	default "elf32-i386" if X86_32
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 01d5453b5502..e27b49d7c922 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -39,9 +39,12 @@ obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
 endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_uncore_snb.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore_snbep.o perf_event_intel_uncore_nhmex.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_rapl.o
+
+obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= perf_event_intel_uncore.o \
+					   perf_event_intel_uncore_snb.o \
+					   perf_event_intel_uncore_snbep.o \
+					   perf_event_intel_uncore_nhmex.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1b8299dd3d91..143e5f5dc855 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -243,8 +243,9 @@ static bool check_hw_exists(void)
 
 msr_fail:
 	printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
-	printk(boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR
-	       "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
+	printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n",
+		boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR,
+		reg, val_new);
 
 	return false;
 }
@@ -444,12 +445,6 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
-		if (x86_pmu.limit_period(event, event->attr.sample_period) >
-				event->attr.sample_period)
-			return -EINVAL;
-	}
-
 	return x86_setup_perfctr(event);
 }
 
@@ -987,9 +982,6 @@ int x86_perf_event_set_period(struct perf_event *event)
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
-	if (x86_pmu.limit_period)
-		left = x86_pmu.limit_period(event, left);
-
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d98a34d435d7..fc5eb390b368 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -445,7 +445,6 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 	bool		late_ack;
-	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
 
 	/*
 	 * sysfs attrs
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a73947c53b65..944bf019b74f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,15 +220,6 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_bdw_event_constraints[] = {
-	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
-	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
-	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
-	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
-	EVENT_CONSTRAINT_END
-};
-
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -424,126 +415,6 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
-static __initconst const u64 hsw_hw_cache_event_ids
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
-		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(L1I ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
-		[ C(RESULT_ACCESS) ] = 0x1b7,
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
-                   L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x1b7,
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
-		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x1b7,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(DTLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
-		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
-		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(ITLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
-		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
- [ C(BPU ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
-		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
-};
-
-static __initconst const u64 hsw_hw_cache_extra_regs
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
-		[ C(RESULT_ACCESS) ] = 0x2d5,
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
-                   L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x3fbc0202d5ull,
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
-		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x3fbc020122ull,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
-};
-
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2034,24 +1905,6 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	return c;
 }
 
-/*
- * Broadwell:
- * The INST_RETIRED.ALL period always needs to have lowest
- * 6bits cleared (BDM57). It shall not use a period smaller
- * than 100 (BDM11). We combine the two to enforce
- * a min-period of 128.
- */
-static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
-{
-	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
-			X86_CONFIG(.event=0xc0, .umask=0x01)) {
-		if (left < 128)
-			left = 128;
-		left &= ~0x3fu;
-	}
-	return left;
-}
-
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -2692,8 +2545,8 @@ __init int intel_pmu_init(void)
 	case 69: /* 22nm Haswell ULT */
 	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 
@@ -2712,28 +2565,6 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
-	case 61: /* 14nm Broadwell Core-M */
-		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-
-		intel_pmu_lbr_init_snb();
-
-		x86_pmu.event_constraints = intel_bdw_event_constraints;
-		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
-		x86_pmu.extra_regs = intel_snbep_extra_regs;
-		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		/* all extra regs are per-cpu when HT is on */
-		x86_pmu.er_flags |= ERF_HAS_RSP_1;
-		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
-
-		x86_pmu.hw_config = hsw_hw_config;
-		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
-		x86_pmu.limit_period = bdw_limit_period;
-		pr_cont("Broadwell events, ");
-		break;
-
 	default:
 		switch (x86_pmu.version) {
 		case 1:
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 9269de254874..9d845404d875 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -364,7 +364,7 @@ struct perf_event_mmap_page {
 	/*
 	 * Bits needed to read the hw events in user-space.
 	 *
-	 *   u32 seq, time_mult, time_shift, idx, width;
+	 *   u32 seq, time_mult, time_shift, index, width;
 	 *   u64 count, enabled, running;
 	 *   u64 cyc, time_offset;
 	 *   s64 pmc = 0;
@@ -383,11 +383,11 @@ struct perf_event_mmap_page {
 	 *       time_shift  = pc->time_shift;
 	 *     }
 	 *
-	 *     idx = pc->index;
+	 *     index = pc->index;
 	 *     count = pc->offset;
-	 *     if (pc->cap_usr_rdpmc && idx) {
+	 *     if (pc->cap_user_rdpmc && index) {
 	 *       width = pc->pmc_width;
-	 *       pmc = rdpmc(idx - 1);
+	 *       pmc = rdpmc(index - 1);
 	 *     }
 	 *
 	 *     barrier();
@@ -415,7 +415,7 @@ struct perf_event_mmap_page {
 	};
 
 	/*
-	 * If cap_usr_rdpmc this field provides the bit-width of the value
+	 * If cap_user_rdpmc this field provides the bit-width of the value
 	 * read using the rdpmc() or equivalent instruction. This can be used
 	 * to sign extend the result like:
 	 *
@@ -439,10 +439,10 @@ struct perf_event_mmap_page {
 	 *
 	 * Where time_offset,time_mult,time_shift and cyc are read in the
 	 * seqcount loop described above. This delta can then be added to
-	 * enabled and possible running (if idx), improving the scaling:
+	 * enabled and possible running (if index), improving the scaling:
 	 *
 	 *   enabled += delta;
-	 *   if (idx)
+	 *   if (index)
 	 *     running += delta;
 	 *
 	 *   quot = count / running;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1425d07018de..2b02c9fda790 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6071,11 +6071,6 @@ static int perf_swevent_init(struct perf_event *event)
 	return 0;
 }
 
-static int perf_swevent_event_idx(struct perf_event *event)
-{
-	return 0;
-}
-
 static struct pmu perf_swevent = {
 	.task_ctx_nr	= perf_sw_context,
 
@@ -6085,8 +6080,6 @@ static struct pmu perf_swevent = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 #ifdef CONFIG_EVENT_TRACING
@@ -6204,8 +6197,6 @@ static struct pmu perf_tracepoint = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 static inline void perf_tp_register(void)
@@ -6431,8 +6422,6 @@ static struct pmu perf_cpu_clock = {
 	.start		= cpu_clock_event_start,
 	.stop		= cpu_clock_event_stop,
 	.read		= cpu_clock_event_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 /*
@@ -6511,8 +6500,6 @@ static struct pmu perf_task_clock = {
 	.start		= task_clock_event_start,
 	.stop		= task_clock_event_stop,
 	.read		= task_clock_event_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 static void perf_pmu_nop_void(struct pmu *pmu)
@@ -6542,7 +6529,7 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
 
 static int perf_event_idx_default(struct perf_event *event)
 {
-	return event->hw.idx + 1;
+	return 0;
 }
 
 /*
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 1559fb0b9296..9803a6600d49 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -605,11 +605,6 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
 	bp->hw.state = PERF_HES_STOPPED;
 }
 
-static int hw_breakpoint_event_idx(struct perf_event *bp)
-{
-	return 0;
-}
-
 static struct pmu perf_breakpoint = {
 	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */
 
@@ -619,8 +614,6 @@ static struct pmu perf_breakpoint = {
 	.start		= hw_breakpoint_start,
 	.stop		= hw_breakpoint_stop,
 	.read		= hw_breakpoint_pmu_read,
-
-	.event_idx	= hw_breakpoint_event_idx,
 };
 
 int __init init_hw_breakpoint(void)
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8c5c11ca8c53..25114c9a6801 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1142,6 +1142,11 @@ static int data_init(int argc, const char **argv)
 
 int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+	int ret = hists__init();
+
+	if (ret < 0)
+		return ret;
+
 	perf_config(perf_default_config, NULL);
 
 	argc = parse_options(argc, argv, options, diff_usage, 0);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 04412b4770a2..7af26acf06d9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -375,7 +375,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('x', "exec", NULL, "executable|path",
 			"target executable name or path", opt_set_target),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
-		    "Disable symbol demangling"),
+		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_END()
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 937e4324ad94..a3b13d7dc1d4 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -13,7 +13,7 @@
 #define wmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 336
 #endif
@@ -30,7 +30,7 @@
 #define wmb()		asm volatile("sfence" ::: "memory")
 #define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
@@ -47,14 +47,14 @@
 #define mb()		asm volatile ("sync" ::: "memory")
 #define wmb()		asm volatile ("sync" ::: "memory")
 #define rmb()		asm volatile ("sync" ::: "memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __s390__
 #define mb()		asm volatile("bcr 15,0" ::: "memory")
 #define wmb()		asm volatile("bcr 15,0" ::: "memory")
 #define rmb()		asm volatile("bcr 15,0" ::: "memory")
-#define CPUINFO_PROC	"vendor_id"
+#define CPUINFO_PROC	{"vendor_id"}
 #endif
 
 #ifdef __sh__
@@ -67,14 +67,14 @@
 # define wmb()		asm volatile("" ::: "memory")
 # define rmb()		asm volatile("" ::: "memory")
 #endif
-#define CPUINFO_PROC	"cpu type"
+#define CPUINFO_PROC	{"cpu type"}
 #endif
 
 #ifdef __hppa__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __sparc__
@@ -87,14 +87,14 @@
 #endif
 #define wmb()		asm volatile("":::"memory")
 #define rmb()		asm volatile("":::"memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __alpha__
 #define mb()		asm volatile("mb" ::: "memory")
 #define wmb()		asm volatile("wmb" ::: "memory")
 #define rmb()		asm volatile("mb" ::: "memory")
-#define CPUINFO_PROC	"cpu model"
+#define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __ia64__
@@ -102,7 +102,7 @@
 #define wmb()		asm volatile ("mf" ::: "memory")
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #endif
 
 #ifdef __arm__
@@ -113,7 +113,7 @@
 #define mb()		((void(*)(void))0xffff0fa0)()
 #define wmb()		((void(*)(void))0xffff0fa0)()
 #define rmb()		((void(*)(void))0xffff0fa0)()
-#define CPUINFO_PROC	"Processor"
+#define CPUINFO_PROC	{"model name", "Processor"}
 #endif
 
 #ifdef __aarch64__
@@ -133,28 +133,28 @@
 				: "memory")
 #define wmb()	mb()
 #define rmb()	mb()
-#define CPUINFO_PROC	"cpu model"
+#define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __arc__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"Processor"
+#define CPUINFO_PROC	{"Processor"}
 #endif
 
 #ifdef __metag__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"CPU"
+#define CPUINFO_PROC	{"CPU"}
 #endif
 
 #ifdef __xtensa__
 #define mb()		asm volatile("memw" ::: "memory")
 #define wmb()		asm volatile("memw" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"core ID"
+#define CPUINFO_PROC	{"core ID"}
 #endif
 
 #ifdef __tile__
@@ -162,7 +162,7 @@
 #define wmb()		asm volatile ("mf" ::: "memory")
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #endif
 
 #define barrier() asm volatile ("" ::: "memory")
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ce0de00399da..26f5b2fe5dc8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -579,16 +579,12 @@ static int write_version(int fd, struct perf_header *h __maybe_unused,
 	return do_write_string(fd, perf_version_string);
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
-		       struct perf_evlist *evlist __maybe_unused)
+static int __write_cpudesc(int fd, const char *cpuinfo_proc)
 {
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC NULL
-#endif
 	FILE *file;
 	char *buf = NULL;
 	char *s, *p;
-	const char *search = CPUINFO_PROC;
+	const char *search = cpuinfo_proc;
 	size_t len = 0;
 	int ret = -1;
 
@@ -638,6 +634,25 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
 	return ret;
 }
 
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC {"model name", }
+#endif
+	const char *cpuinfo_procs[] = CPUINFO_PROC;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
+		int ret;
+		ret = __write_cpudesc(fd, cpuinfo_procs[i]);
+		if (ret >= 0)
+			return ret;
+	}
+	return -1;
+}
+
+
 static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
 			struct perf_evlist *evlist __maybe_unused)
 {
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4906cd81cb56..9402885a77f3 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -373,6 +373,9 @@ struct sort_entry sort_cpu = {
 static int64_t
 sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return _sort__dso_cmp(left->branch_info->from.map,
 			      right->branch_info->from.map);
 }
@@ -380,13 +383,19 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return _hist_entry__dso_snprintf(he->branch_info->from.map,
-					 bf, size, width);
+	if (he->branch_info)
+		return _hist_entry__dso_snprintf(he->branch_info->from.map,
+						 bf, size, width);
+	else
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return _sort__dso_cmp(left->branch_info->to.map,
 			      right->branch_info->to.map);
 }
@@ -394,8 +403,11 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	return _hist_entry__dso_snprintf(he->branch_info->to.map,
-					 bf, size, width);
+	if (he->branch_info)
+		return _hist_entry__dso_snprintf(he->branch_info->to.map,
+						 bf, size, width);
+	else
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int64_t
@@ -404,6 +416,12 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 	struct addr_map_symbol *from_l = &left->branch_info->from;
 	struct addr_map_symbol *from_r = &right->branch_info->from;
 
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	from_l = &left->branch_info->from;
+	from_r = &right->branch_info->from;
+
 	if (!from_l->sym && !from_r->sym)
 		return _sort__addr_cmp(from_l->addr, from_r->addr);
 
@@ -413,8 +431,13 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int64_t
 sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct addr_map_symbol *to_l = &left->branch_info->to;
-	struct addr_map_symbol *to_r = &right->branch_info->to;
+	struct addr_map_symbol *to_l, *to_r;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	to_l = &left->branch_info->to;
+	to_r = &right->branch_info->to;
 
 	if (!to_l->sym && !to_r->sym)
 		return _sort__addr_cmp(to_l->addr, to_r->addr);
@@ -425,19 +448,27 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
 					 size_t size, unsigned int width)
 {
-	struct addr_map_symbol *from = &he->branch_info->from;
-	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
-					 he->level, bf, size, width);
+	if (he->branch_info) {
+		struct addr_map_symbol *from = &he->branch_info->from;
 
+		return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+						 he->level, bf, size, width);
+	}
+
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	struct addr_map_symbol *to = &he->branch_info->to;
-	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
-					 he->level, bf, size, width);
+	if (he->branch_info) {
+		struct addr_map_symbol *to = &he->branch_info->to;
 
+		return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+						 he->level, bf, size, width);
+	}
+
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 struct sort_entry sort_dso_from = {
@@ -471,11 +502,13 @@ struct sort_entry sort_sym_to = {
 static int64_t
 sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	const unsigned char mp = left->branch_info->flags.mispred !=
-					right->branch_info->flags.mispred;
-	const unsigned char p = left->branch_info->flags.predicted !=
-					right->branch_info->flags.predicted;
+	unsigned char mp, p;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
 
+	mp = left->branch_info->flags.mispred != right->branch_info->flags.mispred;
+	p  = left->branch_info->flags.predicted != right->branch_info->flags.predicted;
 	return mp || p;
 }
 
@@ -483,10 +516,12 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width){
 	static const char *out = "N/A";
 
-	if (he->branch_info->flags.predicted)
-		out = "N";
-	else if (he->branch_info->flags.mispred)
-		out = "Y";
+	if (he->branch_info) {
+		if (he->branch_info->flags.predicted)
+			out = "N";
+		else if (he->branch_info->flags.mispred)
+			out = "Y";
+	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
@@ -989,6 +1024,9 @@ struct sort_entry sort_mem_dcacheline = {
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.abort !=
 		right->branch_info->flags.abort;
 }
@@ -996,10 +1034,15 @@ sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	static const char *out = ".";
+	static const char *out = "N/A";
+
+	if (he->branch_info) {
+		if (he->branch_info->flags.abort)
+			out = "A";
+		else
+			out = ".";
+	}
 
-	if (he->branch_info->flags.abort)
-		out = "A";
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -1013,6 +1056,9 @@ struct sort_entry sort_abort = {
 static int64_t
 sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.in_tx !=
 		right->branch_info->flags.in_tx;
 }
@@ -1020,10 +1066,14 @@ sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	static const char *out = ".";
+	static const char *out = "N/A";
 
-	if (he->branch_info->flags.in_tx)
-		out = "T";
+	if (he->branch_info) {
+		if (he->branch_info->flags.in_tx)
+			out = "T";
+		else
+			out = ".";
+	}
 
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2b7b2d91c016..c41411726c7a 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -117,6 +117,9 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
+
+		if (exec)
+			unwind__flush_access(thread);
 	}
 
 	thread->comm_set = true;
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index e060386165c5..4d45c0dfe343 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -539,11 +539,23 @@ int unwind__prepare_access(struct thread *thread)
 		return -ENOMEM;
 	}
 
+	unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
 	thread__set_priv(thread, addr_space);
 
 	return 0;
 }
 
+void unwind__flush_access(struct thread *thread)
+{
+	unw_addr_space_t addr_space;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	addr_space = thread__priv(thread);
+	unw_flush_cache(addr_space, 0, 0);
+}
+
 void unwind__finish_access(struct thread *thread)
 {
 	unw_addr_space_t addr_space;
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index c17c4855bdbc..f50b737235eb 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -23,6 +23,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
 int unwind__prepare_access(struct thread *thread);
+void unwind__flush_access(struct thread *thread);
 void unwind__finish_access(struct thread *thread);
 #else
 static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
@@ -30,6 +31,7 @@ static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
 	return 0;
 }
 
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
 static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else
@@ -49,6 +51,7 @@ static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
 	return 0;
 }
 
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
 static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-09-19 10:46 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-09-19 10:46 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 3577af70a2ce4853d58e57d832e687d739281479 perf: Fix a race condition in perf_remove_from_context()

Two kernel side fixes: a kprobes fix and a 
perf_remove_from_context() fix (which does
not yet fix the migration bug which is WIP).

 Thanks,

	Ingo

------------------>
Cong Wang (1):
      perf: Fix a race condition in perf_remove_from_context()

Wang Nan (1):
      kprobes/x86: Free 'optinsn' cache when range check fails


 arch/x86/kernel/kprobes/opt.c |  4 +++-
 kernel/events/core.c          | 10 ++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index f304773285ae..f1314d0bcf0a 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -338,8 +338,10 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 	 * a relative jump.
 	 */
 	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
-	if (abs(rel) > 0x7fffffff)
+	if (abs(rel) > 0x7fffffff) {
+		__arch_remove_optimized_kprobe(op, 0);
 		return -ERANGE;
+	}
 
 	buf = (u8 *)op->optinsn.insn;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9c1ed002dbc..d640a8b4dcbc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1524,6 +1524,11 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -1967,6 +1972,11 @@ perf_install_in_context(struct perf_event_context *ctx,
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-08-24 20:25 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-08-24 20:25 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b3f207855f57b9c8f43a547a801340bb5cbc59e5 perf: Handle compat ioctl

A kprobes and a perf compat ioctl fix.

 Thanks,

	Ingo

------------------>
Masami Hiramatsu (1):
      kprobes: Skip kretprobe hit in NMI context to avoid deadlock

Pawel Moll (1):
      perf: Handle compat ioctl


 kernel/events/core.c | 23 ++++++++++++++++++++++-
 kernel/kprobes.c     | 13 ++++++++++++-
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cf24b3e42ec..f9c1ed002dbc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -41,6 +41,7 @@
 #include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/mman.h>
+#include <linux/compat.h>
 
 #include "internal.h"
 
@@ -3717,6 +3718,26 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+static long perf_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
+	case _IOC_NR(PERF_EVENT_IOC_ID):
+		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
+		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+			cmd &= ~IOCSIZE_MASK;
+			cmd |= sizeof(void *) << IOCSIZE_SHIFT;
+		}
+		break;
+	}
+	return perf_ioctl(file, cmd, arg);
+}
+#else
+# define perf_compat_ioctl NULL
+#endif
+
 int perf_event_task_enable(void)
 {
 	struct perf_event *event;
@@ -4222,7 +4243,7 @@ static const struct file_operations perf_fops = {
 	.read			= perf_read,
 	.poll			= perf_poll,
 	.unlocked_ioctl		= perf_ioctl,
-	.compat_ioctl		= perf_ioctl,
+	.compat_ioctl		= perf_compat_ioctl,
 	.mmap			= perf_mmap,
 	.fasync			= perf_fasync,
 };
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 734e9a7d280b..3995f546d0f3 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1778,7 +1778,18 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 	unsigned long hash, flags = 0;
 	struct kretprobe_instance *ri;
 
-	/*TODO: consider to only swap the RA after the last pre_handler fired */
+	/*
+	 * To avoid deadlocks, prohibit return probing in NMI contexts,
+	 * just skip the probe and increase the (inexact) 'nmissed'
+	 * statistical counter, so that the user is informed that
+	 * something happened:
+	 */
+	if (unlikely(in_nmi())) {
+		rp->nmissed++;
+		return 0;
+	}
+
+	/* TODO: consider to only swap the RA after the last pre_handler fired */
 	hash = hash_ptr(current, KPROBE_HASH_BITS);
 	raw_spin_lock_irqsave(&rp->lock, flags);
 	if (!hlist_empty(&rp->free_instances)) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-07-16 11:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-07-16 11:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 1f9a7268c67f0290837aada443d28fd953ddca90 perf: Do not allow optimized switch for non-cloned events

Tooling fixes and an Intel PMU driver fixlet.

 Thanks,

	Ingo

------------------>
HATAYAMA Daisuke (1):
      perf/x86/intel: ignore CondChgd bit to avoid false NMI handling

Jiri Olsa (2):
      perf tools: Fix segfault in cumulative.callchain report
      perf: Do not allow optimized switch for non-cloned events

Simon Que (1):
      perf symbols: Get kernel start address by symbol name


 arch/x86/kernel/cpu/perf_event_intel.c |  9 ++++++
 kernel/events/core.c                   |  2 +-
 tools/perf/ui/browsers/hists.c         | 21 +++++++++----
 tools/perf/util/machine.c              | 54 ++++++++++++++--------------------
 4 files changed, 48 insertions(+), 38 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index adb02aa..07846d7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1382,6 +1382,15 @@ again:
 	intel_pmu_lbr_read();
 
 	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a33d9a2b..b0c95f0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2320,7 +2320,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	next_parent = rcu_dereference(next_ctx->parent_ctx);
 
 	/* If neither context have a parent context; they cannot be clones. */
-	if (!parent && !next_parent)
+	if (!parent || !next_parent)
 		goto unlock;
 
 	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 52c03fb..04a229a 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -17,6 +17,7 @@
 #include "../util.h"
 #include "../ui.h"
 #include "map.h"
+#include "annotate.h"
 
 struct hist_browser {
 	struct ui_browser   b;
@@ -1593,13 +1594,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					 bi->to.sym->name) > 0)
 				annotate_t = nr_options++;
 		} else {
-
 			if (browser->selection != NULL &&
 			    browser->selection->sym != NULL &&
-			    !browser->selection->map->dso->annotate_warned &&
-				asprintf(&options[nr_options], "Annotate %s",
-					 browser->selection->sym->name) > 0)
-				annotate = nr_options++;
+			    !browser->selection->map->dso->annotate_warned) {
+				struct annotation *notes;
+
+				notes = symbol__annotation(browser->selection->sym);
+
+				if (notes->src &&
+				    asprintf(&options[nr_options], "Annotate %s",
+						 browser->selection->sym->name) > 0)
+					annotate = nr_options++;
+			}
 		}
 
 		if (thread != NULL &&
@@ -1656,6 +1662,7 @@ retry_popup_menu:
 
 		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
 			struct hist_entry *he;
+			struct annotation *notes;
 			int err;
 do_annotate:
 			if (!objdump_path && perf_session_env__lookup_objdump(env))
@@ -1679,6 +1686,10 @@ do_annotate:
 				he->ms.map = he->branch_info->to.map;
 			}
 
+			notes = symbol__annotation(he->ms.sym);
+			if (!notes->src)
+				continue;
+
 			/*
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 0e5fea9..c73e1fc 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -496,18 +496,6 @@ struct process_args {
 	u64 start;
 };
 
-static int symbol__in_kernel(void *arg, const char *name,
-			     char type __maybe_unused, u64 start)
-{
-	struct process_args *args = arg;
-
-	if (strchr(name, '['))
-		return 0;
-
-	args->start = start;
-	return 1;
-}
-
 static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
 					   size_t bufsz)
 {
@@ -517,27 +505,41 @@ static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
 		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
 }
 
-/* Figure out the start address of kernel map from /proc/kallsyms */
-static u64 machine__get_kernel_start_addr(struct machine *machine)
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
+/* Figure out the start address of kernel map from /proc/kallsyms.
+ * Returns the name of the start symbol in *symbol_name. Pass in NULL as
+ * symbol_name if it's not that important.
+ */
+static u64 machine__get_kernel_start_addr(struct machine *machine,
+					  const char **symbol_name)
 {
 	char filename[PATH_MAX];
-	struct process_args args;
+	int i;
+	const char *name;
+	u64 addr = 0;
 
 	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return 0;
 
-	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
-		return 0;
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
+
+	if (symbol_name)
+		*symbol_name = name;
 
-	return args.start;
+	return addr;
 }
 
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine);
+	u64 start = machine__get_kernel_start_addr(machine, NULL);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
@@ -852,23 +854,11 @@ static int machine__create_modules(struct machine *machine)
 	return 0;
 }
 
-const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
-
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
-	char filename[PATH_MAX];
 	const char *name;
-	u64 addr = 0;
-	int i;
-
-	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
-
-	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
-		addr = kallsyms__get_function_start(filename, name);
-		if (addr)
-			break;
-	}
+	u64 addr = machine__get_kernel_start_addr(machine, &name);
 	if (!addr)
 		return -1;
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-06-18 16:39 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-06-18 16:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: cf230918cda19532e4a5cc4f0d5c82fa7e5e94f6 Merge branch 'perf/core' into perf/urgent, to pick up the latest fixes

This is larger than usual: the main reason are the ARM symbol lookup 
speedups that came in late and were hard to resist. If it's not 
acceptable then I'll restructure it without those bits.

There's also a kprobes fix and various tooling fixes, plus the minimal 
re-enablement of the mmap2 support interface.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf tools: Emit more precise message for missing glibc static library
      perf tests: Show the inner make output when an error happens

Don Zickus (6):
      perf tools: Update mmap2 interface with protection and flag bits
      Revert "perf: Disable PERF_RECORD_MMAP2 support"
      perf report: Add mem-mode documentation to report command
      perf tools: Add cpumode to struct hist_entry
      perf tools: Add support to dynamically get cacheline size
      perf tools: Add dcacheline sort

Jiri Olsa (15):
      perf tools: Fix pipe check regression in attr event callback
      perf tools: Prettify the tags/TAGS/cscope targets output
      perf tools: Cache register accesses for unwind processing
      perf tools: Separate dso data related variables
      perf tools: Add data_fd into dso object
      perf tools: Add global list of opened dso objects
      perf tools: Add global count of opened dso objects
      perf tools: Cache dso data file descriptor
      perf tools: Add file size check and factor dso__data_read_offset
      perf tools: Allow to close dso fd in case of open failure
      perf tools: Add dso__data_* interface descriptons
      perf tests: Spawn child for each test
      perf tests: Allow reuse of test_file function
      perf tests: Add test for caching dso file descriptors
      perf tests: Add test for closing dso objects on EMFILE error

Masami Hiramatsu (5):
      perf probe: Improve error message for unknown member of data structure
      perf probe: Show error code and description in verbose mode
      perf probe: Improve an error message of perf probe --vars mode
      perf probe: Improve error messages in --line option
      x86/kprobes: Fix build errors and blacklist context_track_user

Namhyung Kim (2):
      perf script/python: Print array argument as string
      perf record: Fix to honor user freq/interval properly

Peter Zijlstra (1):
      perf: Pass protection and flags bits through mmap2 interface

Stanislav Fomichev (1):
      perf timechart: Reflow documentation

Steven Rostedt (1):
      tools lib traceevent: Add options to plugins

Steven Rostedt (Red Hat) (3):
      tools lib traceevent: Add flag to not load event plugins
      tools lib traceevent: Add options to function plugin
      tools lib traceevent: Added support for __get_bitmask() macro


 arch/x86/kernel/traps.c                            |   7 +-
 include/uapi/linux/perf_event.h                    |   1 +
 kernel/context_tracking.c                          |   3 +
 kernel/events/core.c                               |  37 ++-
 tools/lib/traceevent/event-parse.c                 | 113 +++++++++
 tools/lib/traceevent/event-parse.h                 |  25 +-
 tools/lib/traceevent/event-plugin.c                | 203 ++++++++++++++-
 tools/lib/traceevent/plugin_function.c             |  43 +++-
 tools/perf/Documentation/perf-report.txt           |  23 ++
 tools/perf/Documentation/perf-timechart.txt        |  41 ++-
 tools/perf/Makefile.perf                           |   6 +-
 tools/perf/builtin-inject.c                        |   2 +-
 tools/perf/builtin-probe.c                         |  23 +-
 tools/perf/config/Makefile                         |   6 +-
 tools/perf/perf.c                                  |   1 +
 tools/perf/tests/builtin-test.c                    |  42 +++-
 tools/perf/tests/dso-data.c                        | 214 +++++++++++++++-
 tools/perf/tests/dwarf-unwind.c                    |   2 +-
 tools/perf/tests/make                              |   7 +-
 tools/perf/tests/tests.h                           |   2 +
 tools/perf/util/dso.c                              | 279 +++++++++++++++++++--
 tools/perf/util/dso.h                              |  50 +++-
 tools/perf/util/event.c                            |  57 +++--
 tools/perf/util/event.h                            |   7 +
 tools/perf/util/evsel.c                            |   5 +-
 tools/perf/util/hist.c                             |   9 +-
 tools/perf/util/hist.h                             |   1 +
 tools/perf/util/machine.c                          |   4 +-
 tools/perf/util/map.c                              |   4 +-
 tools/perf/util/map.h                              |   4 +-
 tools/perf/util/perf_regs.c                        |  10 +-
 tools/perf/util/perf_regs.h                        |   4 +-
 tools/perf/util/probe-event.c                      |  13 +-
 tools/perf/util/probe-finder.c                     |  11 +-
 .../perf/util/scripting-engines/trace-event-perl.c |   1 +
 .../util/scripting-engines/trace-event-python.c    |   2 +
 tools/perf/util/sort.c                             | 107 ++++++++
 tools/perf/util/sort.h                             |   2 +
 tools/perf/util/unwind-libunwind.c                 |   2 -
 tools/perf/util/util.c                             |   1 +
 tools/perf/util/util.h                             |   1 +
 41 files changed, 1249 insertions(+), 126 deletions(-)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c6eb418..0d0e922 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -343,6 +343,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	if (poke_int3_handler(regs))
 		return;
 
+	prev_state = exception_enter();
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
@@ -351,9 +352,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 
 #ifdef CONFIG_KPROBES
 	if (kprobe_int3_handler(regs))
-		return;
+		goto exit;
 #endif
-	prev_state = exception_enter();
 
 	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 			SIGTRAP) == NOTIFY_STOP)
@@ -433,6 +433,8 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	unsigned long dr6;
 	int si_code;
 
+	prev_state = exception_enter();
+
 	get_debugreg(dr6, 6);
 
 	/* Filter out all the reserved bits which are preset to 1 */
@@ -465,7 +467,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	if (kprobe_debug_handler(regs))
 		goto exit;
 #endif
-	prev_state = exception_enter();
 
 	if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code,
 							SIGTRAP) == NOTIFY_STOP)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 5312fae..9269de2 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -705,6 +705,7 @@ enum perf_event_type {
 	 *	u32				min;
 	 *	u64				ino;
 	 *	u64				ino_generation;
+	 *	u32				prot, flags;
 	 *	char				filename[];
 	 * 	struct sample_id		sample_id;
 	 * };
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 019d450..5664985 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/hardirq.h>
 #include <linux/export.h>
+#include <linux/kprobes.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/context_tracking.h>
@@ -104,6 +105,7 @@ void context_tracking_user_enter(void)
 	}
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(context_tracking_user_enter);
 
 #ifdef CONFIG_PREEMPT
 /**
@@ -181,6 +183,7 @@ void context_tracking_user_exit(void)
 	}
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(context_tracking_user_exit);
 
 /**
  * __context_tracking_task_switch - context switch the syscall callbacks
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5fa58e4..a33d9a2b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -40,6 +40,7 @@
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
 #include <linux/module.h>
+#include <linux/mman.h>
 
 #include "internal.h"
 
@@ -5128,6 +5129,7 @@ struct perf_mmap_event {
 	int			maj, min;
 	u64			ino;
 	u64			ino_generation;
+	u32			prot, flags;
 
 	struct {
 		struct perf_event_header	header;
@@ -5169,6 +5171,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 		mmap_event->event_id.header.size += sizeof(mmap_event->min);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
+		mmap_event->event_id.header.size += sizeof(mmap_event->prot);
+		mmap_event->event_id.header.size += sizeof(mmap_event->flags);
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
@@ -5187,6 +5191,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 		perf_output_put(&handle, mmap_event->min);
 		perf_output_put(&handle, mmap_event->ino);
 		perf_output_put(&handle, mmap_event->ino_generation);
+		perf_output_put(&handle, mmap_event->prot);
+		perf_output_put(&handle, mmap_event->flags);
 	}
 
 	__output_copy(&handle, mmap_event->file_name,
@@ -5205,6 +5211,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	struct file *file = vma->vm_file;
 	int maj = 0, min = 0;
 	u64 ino = 0, gen = 0;
+	u32 prot = 0, flags = 0;
 	unsigned int size;
 	char tmp[16];
 	char *buf = NULL;
@@ -5235,6 +5242,28 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		gen = inode->i_generation;
 		maj = MAJOR(dev);
 		min = MINOR(dev);
+
+		if (vma->vm_flags & VM_READ)
+			prot |= PROT_READ;
+		if (vma->vm_flags & VM_WRITE)
+			prot |= PROT_WRITE;
+		if (vma->vm_flags & VM_EXEC)
+			prot |= PROT_EXEC;
+
+		if (vma->vm_flags & VM_MAYSHARE)
+			flags = MAP_SHARED;
+		else
+			flags = MAP_PRIVATE;
+
+		if (vma->vm_flags & VM_DENYWRITE)
+			flags |= MAP_DENYWRITE;
+		if (vma->vm_flags & VM_MAYEXEC)
+			flags |= MAP_EXECUTABLE;
+		if (vma->vm_flags & VM_LOCKED)
+			flags |= MAP_LOCKED;
+		if (vma->vm_flags & VM_HUGETLB)
+			flags |= MAP_HUGETLB;
+
 		goto got_name;
 	} else {
 		name = (char *)arch_vma_name(vma);
@@ -5275,6 +5304,8 @@ got_name:
 	mmap_event->min = min;
 	mmap_event->ino = ino;
 	mmap_event->ino_generation = gen;
+	mmap_event->prot = prot;
+	mmap_event->flags = flags;
 
 	if (!(vma->vm_flags & VM_EXEC))
 		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -5315,6 +5346,8 @@ void perf_event_mmap(struct vm_area_struct *vma)
 		/* .min (attr_mmap2 only) */
 		/* .ino (attr_mmap2 only) */
 		/* .ino_generation (attr_mmap2 only) */
+		/* .prot (attr_mmap2 only) */
+		/* .flags (attr_mmap2 only) */
 	};
 
 	perf_event_mmap_event(&mmap_event);
@@ -6897,10 +6930,6 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
-	/* disabled for now */
-	if (attr->mmap2)
-		return -EINVAL;
-
 	if (attr->__reserved_1)
 		return -EINVAL;
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index b83184f..93825a1 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -765,6 +765,9 @@ static void free_arg(struct print_arg *arg)
 	case PRINT_BSTRING:
 		free(arg->string.string);
 		break;
+	case PRINT_BITMASK:
+		free(arg->bitmask.bitmask);
+		break;
 	case PRINT_DYNAMIC_ARRAY:
 		free(arg->dynarray.index);
 		break;
@@ -2268,6 +2271,7 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 	case PRINT_FIELD ... PRINT_SYMBOL:
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		ret = 0;
@@ -2296,6 +2300,7 @@ static char *arg_eval (struct print_arg *arg)
 	case PRINT_FIELD ... PRINT_SYMBOL:
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		break;
@@ -2683,6 +2688,35 @@ process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
 	return EVENT_ERROR;
 }
 
+static enum event_type
+process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg,
+	    char **tok)
+{
+	enum event_type type;
+	char *token;
+
+	if (read_expect_type(EVENT_ITEM, &token) < 0)
+		goto out_free;
+
+	arg->type = PRINT_BITMASK;
+	arg->bitmask.bitmask = token;
+	arg->bitmask.offset = -1;
+
+	if (read_expected(EVENT_DELIM, ")") < 0)
+		goto out_err;
+
+	type = read_token(&token);
+	*tok = token;
+
+	return type;
+
+ out_free:
+	free_token(token);
+ out_err:
+	*tok = NULL;
+	return EVENT_ERROR;
+}
+
 static struct pevent_function_handler *
 find_func_handler(struct pevent *pevent, char *func_name)
 {
@@ -2797,6 +2831,10 @@ process_function(struct event_format *event, struct print_arg *arg,
 		free_token(token);
 		return process_str(event, arg, tok);
 	}
+	if (strcmp(token, "__get_bitmask") == 0) {
+		free_token(token);
+		return process_bitmask(event, arg, tok);
+	}
 	if (strcmp(token, "__get_dynamic_array") == 0) {
 		free_token(token);
 		return process_dynamic_array(event, arg, tok);
@@ -3324,6 +3362,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		return eval_type(val, arg, 0);
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 		return 0;
 	case PRINT_FUNC: {
 		struct trace_seq s;
@@ -3556,6 +3595,60 @@ static void print_str_to_seq(struct trace_seq *s, const char *format,
 		trace_seq_printf(s, format, str);
 }
 
+static void print_bitmask_to_seq(struct pevent *pevent,
+				 struct trace_seq *s, const char *format,
+				 int len_arg, const void *data, int size)
+{
+	int nr_bits = size * 8;
+	int str_size = (nr_bits + 3) / 4;
+	int len = 0;
+	char buf[3];
+	char *str;
+	int index;
+	int i;
+
+	/*
+	 * The kernel likes to put in commas every 32 bits, we
+	 * can do the same.
+	 */
+	str_size += (nr_bits - 1) / 32;
+
+	str = malloc(str_size + 1);
+	if (!str) {
+		do_warning("%s: not enough memory!", __func__);
+		return;
+	}
+	str[str_size] = 0;
+
+	/* Start out with -2 for the two chars per byte */
+	for (i = str_size - 2; i >= 0; i -= 2) {
+		/*
+		 * data points to a bit mask of size bytes.
+		 * In the kernel, this is an array of long words, thus
+		 * endianess is very important.
+		 */
+		if (pevent->file_bigendian)
+			index = size - (len + 1);
+		else
+			index = len;
+
+		snprintf(buf, 3, "%02x", *((unsigned char *)data + index));
+		memcpy(str + i, buf, 2);
+		len++;
+		if (!(len & 3) && i > 0) {
+			i--;
+			str[i] = ',';
+		}
+	}
+
+	if (len_arg >= 0)
+		trace_seq_printf(s, format, len_arg, str);
+	else
+		trace_seq_printf(s, format, str);
+
+	free(str);
+}
+
 static void print_str_arg(struct trace_seq *s, void *data, int size,
 			  struct event_format *event, const char *format,
 			  int len_arg, struct print_arg *arg)
@@ -3691,6 +3784,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	case PRINT_BSTRING:
 		print_str_to_seq(s, format, len_arg, arg->string.string);
 		break;
+	case PRINT_BITMASK: {
+		int bitmask_offset;
+		int bitmask_size;
+
+		if (arg->bitmask.offset == -1) {
+			struct format_field *f;
+
+			f = pevent_find_any_field(event, arg->bitmask.bitmask);
+			arg->bitmask.offset = f->offset;
+		}
+		bitmask_offset = data2host4(pevent, data + arg->bitmask.offset);
+		bitmask_size = bitmask_offset >> 16;
+		bitmask_offset &= 0xffff;
+		print_bitmask_to_seq(pevent, s, format, len_arg,
+				     data + bitmask_offset, bitmask_size);
+		break;
+	}
 	case PRINT_OP:
 		/*
 		 * The only op for string should be ? :
@@ -4822,6 +4932,9 @@ static void print_args(struct print_arg *args)
 	case PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
 		break;
+	case PRINT_BITMASK:
+		printf("__get_bitmask(%s)", args->bitmask.bitmask);
+		break;
 	case PRINT_TYPE:
 		printf("(%s)", args->typecast.type);
 		print_args(args->typecast.item);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index feab942..7a3873f 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -107,8 +107,8 @@ typedef int (*pevent_event_handler_func)(struct trace_seq *s,
 typedef int (*pevent_plugin_load_func)(struct pevent *pevent);
 typedef int (*pevent_plugin_unload_func)(struct pevent *pevent);
 
-struct plugin_option {
-	struct plugin_option		*next;
+struct pevent_plugin_option {
+	struct pevent_plugin_option	*next;
 	void				*handle;
 	char				*file;
 	char				*name;
@@ -135,7 +135,7 @@ struct plugin_option {
  * PEVENT_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
  *
- *   struct plugin_option PEVENT_PLUGIN_OPTIONS[] = {
+ *   struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
  *	{
  *		.name = "option-name",
  *		.plugin_alias = "overide-file-name", (optional)
@@ -208,6 +208,11 @@ struct print_arg_string {
 	int			offset;
 };
 
+struct print_arg_bitmask {
+	char			*bitmask;
+	int			offset;
+};
+
 struct print_arg_field {
 	char			*name;
 	struct format_field	*field;
@@ -274,6 +279,7 @@ enum print_arg_type {
 	PRINT_DYNAMIC_ARRAY,
 	PRINT_OP,
 	PRINT_FUNC,
+	PRINT_BITMASK,
 };
 
 struct print_arg {
@@ -288,6 +294,7 @@ struct print_arg {
 		struct print_arg_hex		hex;
 		struct print_arg_func		func;
 		struct print_arg_string		string;
+		struct print_arg_bitmask	bitmask;
 		struct print_arg_op		op;
 		struct print_arg_dynarray	dynarray;
 	};
@@ -354,6 +361,8 @@ enum pevent_func_arg_type {
 
 enum pevent_flag {
 	PEVENT_NSEC_OUTPUT		= 1,	/* output in NSECS */
+	PEVENT_DISABLE_SYS_PLUGINS	= 1 << 1,
+	PEVENT_DISABLE_PLUGINS		= 1 << 2,
 };
 
 #define PEVENT_ERRORS 							      \
@@ -410,9 +419,19 @@ enum pevent_errno {
 
 struct plugin_list;
 
+#define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
+
 struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
 void traceevent_unload_plugins(struct plugin_list *plugin_list,
 			       struct pevent *pevent);
+char **traceevent_plugin_list_options(void);
+void traceevent_plugin_free_options_list(char **list);
+int traceevent_plugin_add_options(const char *name,
+				  struct pevent_plugin_option *options);
+void traceevent_plugin_remove_options(struct pevent_plugin_option *options);
+void traceevent_print_plugins(struct trace_seq *s,
+			      const char *prefix, const char *suffix,
+			      const struct plugin_list *list);
 
 struct cmdline;
 struct cmdline_list;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index 0c8bf67..136162c 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -18,6 +18,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#include <stdio.h>
 #include <string.h>
 #include <dlfcn.h>
 #include <stdlib.h>
@@ -30,12 +31,207 @@
 
 #define LOCAL_PLUGIN_DIR ".traceevent/plugins"
 
+static struct registered_plugin_options {
+	struct registered_plugin_options	*next;
+	struct pevent_plugin_option		*options;
+} *registered_options;
+
+static struct trace_plugin_options {
+	struct trace_plugin_options	*next;
+	char				*plugin;
+	char				*option;
+	char				*value;
+} *trace_plugin_options;
+
 struct plugin_list {
 	struct plugin_list	*next;
 	char			*name;
 	void			*handle;
 };
 
+/**
+ * traceevent_plugin_list_options - get list of plugin options
+ *
+ * Returns an array of char strings that list the currently registered
+ * plugin options in the format of <plugin>:<option>. This list can be
+ * used by toggling the option.
+ *
+ * Returns NULL if there's no options registered. On error it returns
+ * INVALID_PLUGIN_LIST_OPTION
+ *
+ * Must be freed with traceevent_plugin_free_options_list().
+ */
+char **traceevent_plugin_list_options(void)
+{
+	struct registered_plugin_options *reg;
+	struct pevent_plugin_option *op;
+	char **list = NULL;
+	char *name;
+	int count = 0;
+
+	for (reg = registered_options; reg; reg = reg->next) {
+		for (op = reg->options; op->name; op++) {
+			char *alias = op->plugin_alias ? op->plugin_alias : op->file;
+			char **temp = list;
+
+			name = malloc(strlen(op->name) + strlen(alias) + 2);
+			if (!name)
+				goto err;
+
+			sprintf(name, "%s:%s", alias, op->name);
+			list = realloc(list, count + 2);
+			if (!list) {
+				list = temp;
+				free(name);
+				goto err;
+			}
+			list[count++] = name;
+			list[count] = NULL;
+		}
+	}
+	return list;
+
+ err:
+	while (--count >= 0)
+		free(list[count]);
+	free(list);
+
+	return INVALID_PLUGIN_LIST_OPTION;
+}
+
+void traceevent_plugin_free_options_list(char **list)
+{
+	int i;
+
+	if (!list)
+		return;
+
+	if (list == INVALID_PLUGIN_LIST_OPTION)
+		return;
+
+	for (i = 0; list[i]; i++)
+		free(list[i]);
+
+	free(list);
+}
+
+static int
+update_option(const char *file, struct pevent_plugin_option *option)
+{
+	struct trace_plugin_options *op;
+	char *plugin;
+
+	if (option->plugin_alias) {
+		plugin = strdup(option->plugin_alias);
+		if (!plugin)
+			return -1;
+	} else {
+		char *p;
+		plugin = strdup(file);
+		if (!plugin)
+			return -1;
+		p = strstr(plugin, ".");
+		if (p)
+			*p = '\0';
+	}
+
+	/* first look for named options */
+	for (op = trace_plugin_options; op; op = op->next) {
+		if (!op->plugin)
+			continue;
+		if (strcmp(op->plugin, plugin) != 0)
+			continue;
+		if (strcmp(op->option, option->name) != 0)
+			continue;
+
+		option->value = op->value;
+		option->set ^= 1;
+		goto out;
+	}
+
+	/* first look for unnamed options */
+	for (op = trace_plugin_options; op; op = op->next) {
+		if (op->plugin)
+			continue;
+		if (strcmp(op->option, option->name) != 0)
+			continue;
+
+		option->value = op->value;
+		option->set ^= 1;
+		break;
+	}
+
+ out:
+	free(plugin);
+	return 0;
+}
+
+/**
+ * traceevent_plugin_add_options - Add a set of options by a plugin
+ * @name: The name of the plugin adding the options
+ * @options: The set of options being loaded
+ *
+ * Sets the options with the values that have been added by user.
+ */
+int traceevent_plugin_add_options(const char *name,
+				  struct pevent_plugin_option *options)
+{
+	struct registered_plugin_options *reg;
+
+	reg = malloc(sizeof(*reg));
+	if (!reg)
+		return -1;
+	reg->next = registered_options;
+	reg->options = options;
+	registered_options = reg;
+
+	while (options->name) {
+		update_option(name, options);
+		options++;
+	}
+	return 0;
+}
+
+/**
+ * traceevent_plugin_remove_options - remove plugin options that were registered
+ * @options: Options to removed that were registered with traceevent_plugin_add_options
+ */
+void traceevent_plugin_remove_options(struct pevent_plugin_option *options)
+{
+	struct registered_plugin_options **last;
+	struct registered_plugin_options *reg;
+
+	for (last = &registered_options; *last; last = &(*last)->next) {
+		if ((*last)->options == options) {
+			reg = *last;
+			*last = reg->next;
+			free(reg);
+			return;
+		}
+	}
+}
+
+/**
+ * traceevent_print_plugins - print out the list of plugins loaded
+ * @s: the trace_seq descripter to write to
+ * @prefix: The prefix string to add before listing the option name
+ * @suffix: The suffix string ot append after the option name
+ * @list: The list of plugins (usually returned by traceevent_load_plugins()
+ *
+ * Writes to the trace_seq @s the list of plugins (files) that is
+ * returned by traceevent_load_plugins(). Use @prefix and @suffix for formating:
+ * @prefix = "  ", @suffix = "\n".
+ */
+void traceevent_print_plugins(struct trace_seq *s,
+			      const char *prefix, const char *suffix,
+			      const struct plugin_list *list)
+{
+	while (list) {
+		trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix);
+		list = list->next;
+	}
+}
+
 static void
 load_plugin(struct pevent *pevent, const char *path,
 	    const char *file, void *data)
@@ -148,12 +344,17 @@ load_plugins(struct pevent *pevent, const char *suffix,
 	char *path;
 	char *envdir;
 
+	if (pevent->flags & PEVENT_DISABLE_PLUGINS)
+		return;
+
 	/*
 	 * If a system plugin directory was defined,
 	 * check that first.
 	 */
 #ifdef PLUGIN_DIR
-	load_plugins_dir(pevent, suffix, PLUGIN_DIR, load_plugin, data);
+	if (!(pevent->flags & PEVENT_DISABLE_SYS_PLUGINS))
+		load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+				 load_plugin, data);
 #endif
 
 	/*
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 80ba4ff..a00ec19 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -33,6 +33,29 @@ static int cpus = -1;
 
 #define STK_BLK 10
 
+struct pevent_plugin_option plugin_options[] =
+{
+	{
+		.name = "parent",
+		.plugin_alias = "ftrace",
+		.description =
+		"Print parent of functions for function events",
+	},
+	{
+		.name = "indent",
+		.plugin_alias = "ftrace",
+		.description =
+		"Try to show function call indents, based on parents",
+		.set = 1,
+	},
+	{
+		.name = NULL,
+	}
+};
+
+static struct pevent_plugin_option *ftrace_parent = &plugin_options[0];
+static struct pevent_plugin_option *ftrace_indent = &plugin_options[1];
+
 static void add_child(struct func_stack *stack, const char *child, int pos)
 {
 	int i;
@@ -119,7 +142,8 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 
 	parent = pevent_find_function(pevent, pfunction);
 
-	index = add_and_get_index(parent, func, record->cpu);
+	if (parent && ftrace_indent->set)
+		index = add_and_get_index(parent, func, record->cpu);
 
 	trace_seq_printf(s, "%*s", index*3, "");
 
@@ -128,11 +152,13 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 	else
 		trace_seq_printf(s, "0x%llx", function);
 
-	trace_seq_printf(s, " <-- ");
-	if (parent)
-		trace_seq_printf(s, "%s", parent);
-	else
-		trace_seq_printf(s, "0x%llx", pfunction);
+	if (ftrace_parent->set) {
+		trace_seq_printf(s, " <-- ");
+		if (parent)
+			trace_seq_printf(s, "%s", parent);
+		else
+			trace_seq_printf(s, "0x%llx", pfunction);
+	}
 
 	return 0;
 }
@@ -141,6 +167,9 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 {
 	pevent_register_event_handler(pevent, -1, "ftrace", "function",
 				      function_handler, NULL);
+
+	traceevent_plugin_add_options("ftrace", plugin_options);
+
 	return 0;
 }
 
@@ -157,6 +186,8 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 		free(fstack[i].stack);
 	}
 
+	traceevent_plugin_remove_options(plugin_options);
+
 	free(fstack);
 	fstack = NULL;
 	cpus = -1;
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index cefdf43..d2b59af 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,22 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
+	If --mem-mode option is used, following sort keys are also available
+	(incompatible with --branch-stack):
+	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+	- symbol_daddr: name of data symbol being executed on at the time of sample
+	- dso_daddr: name of library or module containing the data being executed
+	on at the time of sample
+	- locked: whether the bus was locked at the time of sample
+	- tlb: type of tlb access for the data at the time of sample
+	- mem: type of memory access for the data at the time of sample
+	- snoop: type of snoop (if any) for the data at the time of sample
+	- dcacheline: the cacheline the data address is on at the time of sample
+
+	And default sort keys are changed to local_weight, mem, sym, dso,
+	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -260,6 +276,13 @@ OPTIONS
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
 
+--mem-mode::
+	Use the data addresses of samples in addition to instruction addresses
+	to build the histograms.  To generate meaningful output, the perf.data
+	file must have been obtained using perf record -d -W and using a
+	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
+	'perf mem' for simpler access.
+
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index bc5990c..5e0f986 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -43,27 +43,6 @@ TIMECHART OPTIONS
 
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
-
-EXAMPLES
---------
-
-$ perf timechart record git pull
-
-  [ perf record: Woken up 13 times to write data ]
-  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
-
-$ perf timechart
-
-  Written 10.2 seconds of trace to output.svg.
-
-Record system-wide timechart:
-
-  $ perf timechart record
-
-  then generate timechart and highlight 'gcc' tasks:
-
-  $ perf timechart --highlight gcc
-
 -n::
 --proc-num::
         Print task info for at least given number of tasks.
@@ -88,6 +67,26 @@ RECORD OPTIONS
 --callchain::
         Do call-graph (stack chain/backtrace) recording
 
+EXAMPLES
+--------
+
+$ perf timechart record git pull
+
+  [ perf record: Woken up 13 times to write data ]
+  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
+
+$ perf timechart
+
+  Written 10.2 seconds of trace to output.svg.
+
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ae20edf..9670a16 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -819,15 +819,15 @@ TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol
 TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
-	$(RM) TAGS
+	$(QUIET_GEN)$(RM) TAGS; \
 	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
 
 tags:
-	$(RM) tags
+	$(QUIET_GEN)$(RM) tags; \
 	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
-	$(RM) cscope*
+	$(QUIET_GEN)$(RM) cscope*; \
 	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
 
 ### Detect prefix changes
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6a3af00..16c7c11 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -72,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	if (ret)
 		return ret;
 
-	if (&inject->output.is_pipe)
+	if (!inject->output.is_pipe)
 		return 0;
 
 	return perf_event__repipe_synth(tool, event);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index cdcd4eb..c63fa29 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -288,6 +288,13 @@ static void cleanup_params(void)
 	memset(&params, 0, sizeof(params));
 }
 
+static void pr_err_with_code(const char *msg, int err)
+{
+	pr_err("%s", msg);
+	pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+	pr_err("\n");
+}
+
 static int
 __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -379,7 +386,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		ret = parse_probe_event_argv(argc, argv);
 		if (ret < 0) {
-			pr_err("  Error: Parse Error.  (%d)\n", ret);
+			pr_err_with_code("  Error: Command Parse Error.", ret);
 			return ret;
 		}
 	}
@@ -419,8 +426,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		ret = show_perf_probe_events();
 		if (ret < 0)
-			pr_err("  Error: Failed to show event list. (%d)\n",
-			       ret);
+			pr_err_with_code("  Error: Failed to show event list.", ret);
 		return ret;
 	}
 	if (params.show_funcs) {
@@ -445,8 +451,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		strfilter__delete(params.filter);
 		params.filter = NULL;
 		if (ret < 0)
-			pr_err("  Error: Failed to show functions."
-			       " (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
 	}
 
@@ -464,7 +469,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 		ret = show_line_range(&params.line_range, params.target);
 		if (ret < 0)
-			pr_err("  Error: Failed to show lines. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show lines.", ret);
 		return ret;
 	}
 	if (params.show_vars) {
@@ -485,7 +490,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		strfilter__delete(params.filter);
 		params.filter = NULL;
 		if (ret < 0)
-			pr_err("  Error: Failed to show vars. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show vars.", ret);
 		return ret;
 	}
 #endif
@@ -493,7 +498,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (params.dellist) {
 		ret = del_perf_probe_events(params.dellist);
 		if (ret < 0) {
-			pr_err("  Error: Failed to delete events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to delete events.", ret);
 			return ret;
 		}
 	}
@@ -504,7 +509,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 					    params.target,
 					    params.force_add);
 		if (ret < 0) {
-			pr_err("  Error: Failed to add events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
 	}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 4f100b5..f30ac5e 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -299,7 +299,11 @@ else
       NO_LIBUNWIND := 1
       NO_LIBDW_DWARF_UNWIND := 1
     else
-      msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+      ifneq ($(filter s% -static%,$(LDFLAGS),),)
+        msg := $(error No static glibc found, please install glibc-static);
+      else
+        msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]);
+      endif
     endif
   else
     ifndef NO_LIBDW_DWARF_UNWIND
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 78f7b92..95c58fc 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -458,6 +458,7 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
+	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
 
 	cmd = perf_extract_argv0_path(argv[0]);
 	if (!cmd)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 802e3cd..6f8b01b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -3,6 +3,8 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <unistd.h>
+#include <string.h>
 #include "builtin.h"
 #include "intlist.h"
 #include "tests.h"
@@ -50,10 +52,18 @@ static struct test {
 		.func = test__pmu,
 	},
 	{
-		.desc = "Test dso data interface",
+		.desc = "Test dso data read",
 		.func = test__dso_data,
 	},
 	{
+		.desc = "Test dso data cache",
+		.func = test__dso_data_cache,
+	},
+	{
+		.desc = "Test dso data reopen",
+		.func = test__dso_data_reopen,
+	},
+	{
 		.desc = "roundtrip evsel->name check",
 		.func = test__perf_evsel__roundtrip_name_test,
 	},
@@ -172,6 +182,34 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
 	return false;
 }
 
+static int run_test(struct test *test)
+{
+	int status, err = -1, child = fork();
+
+	if (child < 0) {
+		pr_err("failed to fork test: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (!child) {
+		pr_debug("test child forked, pid %d\n", getpid());
+		err = test->func();
+		exit(err);
+	}
+
+	wait(&status);
+
+	if (WIFEXITED(status)) {
+		err = WEXITSTATUS(status);
+		pr_debug("test child finished with %d\n", err);
+	} else if (WIFSIGNALED(status)) {
+		err = -1;
+		pr_debug("test child interrupted\n");
+	}
+
+	return err;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	int i = 0;
@@ -200,7 +238,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 
 		pr_debug("\n--- start ---\n");
-		err = tests[curr].func();
+		err = run_test(&tests[curr]);
 		pr_debug("---- end ----\n%s:", tests[curr].desc);
 
 		switch (err) {
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 3e6cb17..630808c 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -1,22 +1,27 @@
-#include "util.h"
-
 #include <stdlib.h>
 #include <linux/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <string.h>
-
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <api/fs/fs.h>
+#include "util.h"
 #include "machine.h"
 #include "symbol.h"
 #include "tests.h"
 
 static char *test_file(int size)
 {
-	static char buf_templ[] = "/tmp/test-XXXXXX";
+#define TEMPL "/tmp/perf-test-XXXXXX"
+	static char buf_templ[sizeof(TEMPL)];
 	char *templ = buf_templ;
 	int fd, i;
 	unsigned char *buf;
 
+	strcpy(buf_templ, TEMPL);
+#undef TEMPL
+
 	fd = mkstemp(templ);
 	if (fd < 0) {
 		perror("mkstemp failed");
@@ -150,3 +155,204 @@ int test__dso_data(void)
 	unlink(file);
 	return 0;
 }
+
+static long open_files_cnt(void)
+{
+	char path[PATH_MAX];
+	struct dirent *dent;
+	DIR *dir;
+	long nr = 0;
+
+	scnprintf(path, PATH_MAX, "%s/self/fd", procfs__mountpoint());
+	pr_debug("fd path: %s\n", path);
+
+	dir = opendir(path);
+	TEST_ASSERT_VAL("failed to open fd directory", dir);
+
+	while ((dent = readdir(dir)) != NULL) {
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		nr++;
+	}
+
+	closedir(dir);
+	return nr - 1;
+}
+
+static struct dso **dsos;
+
+static int dsos__create(int cnt, int size)
+{
+	int i;
+
+	dsos = malloc(sizeof(dsos) * cnt);
+	TEST_ASSERT_VAL("failed to alloc dsos array", dsos);
+
+	for (i = 0; i < cnt; i++) {
+		char *file;
+
+		file = test_file(size);
+		TEST_ASSERT_VAL("failed to get dso file", file);
+
+		dsos[i] = dso__new(file);
+		TEST_ASSERT_VAL("failed to get dso", dsos[i]);
+	}
+
+	return 0;
+}
+
+static void dsos__delete(int cnt)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		struct dso *dso = dsos[i];
+
+		unlink(dso->name);
+		dso__delete(dso);
+	}
+
+	free(dsos);
+}
+
+static int set_fd_limit(int n)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_NOFILE, &rlim))
+		return -1;
+
+	pr_debug("file limit %ld, new %d\n", (long) rlim.rlim_cur, n);
+
+	rlim.rlim_cur = n;
+	return setrlimit(RLIMIT_NOFILE, &rlim);
+}
+
+int test__dso_data_cache(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int dso_cnt, limit, i, fd;
+
+	memset(&machine, 0, sizeof(machine));
+
+	/* set as system limit */
+	limit = nr * 4;
+	TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit));
+
+	/* and this is now our dso open FDs limit + 1 extra */
+	dso_cnt = limit / 2 + 1;
+	TEST_ASSERT_VAL("failed to create dsos\n",
+		!dsos__create(dso_cnt, TEST_FILE_SIZE));
+
+	for (i = 0; i < (dso_cnt - 1); i++) {
+		struct dso *dso = dsos[i];
+
+		/*
+		 * Open dsos via dso__data_fd or dso__data_read_offset.
+		 * Both opens the data file and keep it open.
+		 */
+		if (i % 2) {
+			fd = dso__data_fd(dso, &machine);
+			TEST_ASSERT_VAL("failed to get fd", fd > 0);
+		} else {
+			#define BUFSIZE 10
+			u8 buf[BUFSIZE];
+			ssize_t n;
+
+			n = dso__data_read_offset(dso, &machine, 0, buf, BUFSIZE);
+			TEST_ASSERT_VAL("failed to read dso", n == BUFSIZE);
+		}
+	}
+
+	/* open +1 dso over the allowed limit */
+	fd = dso__data_fd(dsos[i], &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* should force the first one to be closed */
+	TEST_ASSERT_VAL("failed to close dsos[0]", dsos[0]->data.fd == -1);
+
+	/* cleanup everything */
+	dsos__delete(dso_cnt);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
+
+int test__dso_data_reopen(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int fd, fd_extra;
+
+#define dso_0 (dsos[0])
+#define dso_1 (dsos[1])
+#define dso_2 (dsos[2])
+
+	memset(&machine, 0, sizeof(machine));
+
+	/*
+	 * Test scenario:
+	 * - create 3 dso objects
+	 * - set process file descriptor limit to current
+	 *   files count + 3
+	 * - test that the first dso gets closed when we
+	 *   reach the files count limit
+	 */
+
+	/* Make sure we are able to open 3 fds anyway */
+	TEST_ASSERT_VAL("failed to set file limit",
+			!set_fd_limit((nr + 3)));
+
+	TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(3, TEST_FILE_SIZE));
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* open dso_1 */
+	fd = dso__data_fd(dso_1, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * open extra file descriptor and we just
+	 * reached the files count limit
+	 */
+	fd_extra = open("/dev/null", O_RDONLY);
+	TEST_ASSERT_VAL("failed to open extra fd", fd_extra > 0);
+
+	/* open dso_2 */
+	fd = dso__data_fd(dso_2, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_0 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_0", dso_0->data.fd == -1);
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_1 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_1", dso_1->data.fd == -1);
+
+	/* cleanup everything */
+	close(fd_extra);
+	dsos__delete(3);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 108f0cd..96adb73 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -15,7 +15,7 @@ static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			struct perf_sample *sample __maybe_unused,
 			struct machine *machine)
 {
-	return machine__process_mmap_event(machine, event, NULL);
+	return machine__process_mmap2_event(machine, event, NULL);
 }
 
 static int init_live_machine(struct machine *machine)
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2f92d6e..69a71ff 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -205,8 +205,7 @@ $(run):
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
-	rm -f $@ \
-	rm -rf $$TMP_DEST
+	rm -rf $@ $$TMP_DEST || (cat $@ ; false)
 
 $(run_O):
 	$(call clean)
@@ -217,9 +216,7 @@ $(run_O):
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
-	rm -f $@ && \
-	rm -rf $$TMP_O \
-	rm -rf $$TMP_DEST
+	rm -rf $@ $$TMP_O $$TMP_DEST || (cat $@ ; false)
 
 tarpkg:
 	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 022bb68..ed64790 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -28,6 +28,8 @@ int test__syscall_open_tp_fields(void);
 int test__pmu(void);
 int test__attr(void);
 int test__dso_data(void);
+int test__dso_data_cache(void);
+int test__dso_data_reopen(void);
 int test__parse_events(void);
 int test__hists_link(void);
 int test__python_use(void);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 64453d6..819f104 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,6 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
@@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
-static int open_dso(struct dso *dso, struct machine *machine)
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+	list_add_tail(&dso->data.open_entry, &dso__data_open);
+	dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+	list_del(&dso->data.open_entry);
+	WARN_ONCE(dso__data_open_cnt <= 0,
+		  "DSO data fd counter out of bounds.");
+	dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+	int fd;
+
+	do {
+		fd = open(name, O_RDONLY);
+		if (fd >= 0)
+			return fd;
+
+		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		if (!dso__data_open_cnt || errno != EMFILE)
+			break;
+
+		close_first_dso();
+	} while (1);
+
+	return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
 {
 	int fd;
 	char *root_dir = (char *)"";
@@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine)
 		return -EINVAL;
 	}
 
-	fd = open(name, O_RDONLY);
+	fd = do_open(name);
 	free(name);
 	return fd;
 }
 
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	int fd = __open_dso(dso, machine);
+
+	if (fd > 0) {
+		dso__list_add(dso);
+		/*
+		 * Check if we crossed the allowed number
+		 * of opened DSOs and close one if needed.
+		 */
+		check_data_close();
+	}
+
+	return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+	if (dso->data.fd >= 0) {
+		close(dso->data.fd);
+		dso->data.fd = -1;
+		dso->data.file_size = 0;
+		dso__list_del(dso);
+	}
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+	close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+	struct dso *dso;
+
+	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+	close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+	struct rlimit l;
+	rlim_t limit = 0;
+
+	/* Allow half of the current open fd limit. */
+	if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+		if (l.rlim_cur == RLIM_INFINITY)
+			limit = l.rlim_cur;
+		else
+			limit = l.rlim_cur / 2;
+	} else {
+		pr_err("failed to get fd limit\n");
+		limit = 1;
+	}
+
+	return limit;
+}
+
+static bool may_cache_fd(void)
+{
+	static rlim_t limit;
+
+	if (!limit)
+		limit = get_fd_limit();
+
+	if (limit == RLIM_INFINITY)
+		return true;
+
+	return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+	bool cache_fd = may_cache_fd();
+
+	if (!cache_fd)
+		close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+	close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
@@ -168,8 +331,13 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
-		return open_dso(dso, machine);
+	if (dso->data.fd >= 0)
+		return dso->data.fd;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+		dso->data.fd = open_dso(dso, machine);
+		return dso->data.fd;
+	}
 
 	do {
 		int fd;
@@ -178,7 +346,7 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 
 		fd = open_dso(dso, machine);
 		if (fd >= 0)
-			return fd;
+			return dso->data.fd = fd;
 
 	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
@@ -260,16 +428,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
-		 u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 	ssize_t ret;
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return -1;
 
 	do {
 		u64 cache_offset;
@@ -283,16 +445,16 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 		ret = -EINVAL;
 
-		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+		if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
 			break;
 
-		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
 		if (ret <= 0)
 			break;
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->cache, cache);
+		dso_cache__insert(&dso->data.cache, cache);
 
 		ret = dso_cache__memcpy(cache, offset, data, size);
 
@@ -301,24 +463,27 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 	if (ret <= 0)
 		free(cache);
 
-	close(fd);
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+			      u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->cache, offset);
+	cache = dso_cache__find(&dso->data.cache, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, machine, offset, data, size);
+		return dso_cache__read(dso, offset, data, size);
 }
 
-ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -326,7 +491,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, machine, offset, p, size);
+		ret = dso_cache_read(dso, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -346,6 +511,67 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	return r;
 }
 
+static int data_file_size(struct dso *dso)
+{
+	struct stat st;
+
+	if (!dso->data.file_size) {
+		if (fstat(dso->data.fd, &st)) {
+			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			return -1;
+		}
+		dso->data.file_size = st.st_size;
+	}
+
+	return 0;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+				u8 *data, ssize_t size)
+{
+	if (data_file_size(dso))
+		return -1;
+
+	/* Check the offset sanity. */
+	if (offset > dso->data.file_size)
+		return -1;
+
+	if (offset + size < offset)
+		return -1;
+
+	return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	if (dso__data_fd(dso, machine) < 0)
+		return -1;
+
+	return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size)
@@ -473,7 +699,8 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->cache = RB_ROOT;
+		dso->data.cache = RB_ROOT;
+		dso->data.fd = -1;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
@@ -485,6 +712,7 @@ struct dso *dso__new(const char *name)
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
+		INIT_LIST_HEAD(&dso->data.open_entry);
 	}
 
 	return dso;
@@ -506,7 +734,8 @@ void dso__delete(struct dso *dso)
 		dso->long_name_allocated = false;
 	}
 
-	dso_cache__free(&dso->cache);
+	dso__data_close(dso);
+	dso_cache__free(&dso->data.cache);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
 	free(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 38efe95..ad553ba 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -76,7 +76,6 @@ struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
-	struct rb_root	 cache;
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
@@ -99,6 +98,15 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+
+	/* dso data file */
+	struct {
+		struct rb_root	 cache;
+		int		 fd;
+		size_t		 file_size;
+		struct list_head open_entry;
+	} data;
+
 	char		 name[0];
 };
 
@@ -141,7 +149,47 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 
+/*
+ * The dso__data_* external interface provides following functions:
+ *   dso__data_fd
+ *   dso__data_close
+ *   dso__data_read_offset
+ *   dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ *   int fd = dso__data_fd(dso, machine);
+ *   USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ *   n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ *   dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
 int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size);
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 65795b8..d0281bd 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,4 +1,5 @@
 #include <linux/types.h>
+#include <sys/mman.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		return -1;
 	}
 
-	event->header.type = PERF_RECORD_MMAP;
+	event->header.type = PERF_RECORD_MMAP2;
 
 	while (1) {
 		char bf[BUFSIZ];
 		char prot[5];
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
+		unsigned int ino;
 		size_t size;
 		ssize_t n;
 
@@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
-		       &event->mmap.start, &event->mmap.len, prot,
-		       &event->mmap.pgoff,
-		       execname);
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
 		/*
  		 * Anon maps don't have the execname.
  		 */
-		if (n < 4)
+		if (n < 7)
 			continue;
+
+		event->mmap2.ino = (u64)ino;
+
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 		 */
@@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		else
 			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
+
 		if (prot[2] != 'x') {
 			if (!mmap_data || prot[0] != 'r')
 				continue;
@@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			strcpy(execname, anonstr);
 
 		size = strlen(execname) + 1;
-		memcpy(event->mmap.filename, execname, size);
+		memcpy(event->mmap2.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap.len -= event->mmap.start;
-		event->mmap.header.size = (sizeof(event->mmap) -
-					(sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.pid = tgid;
-		event->mmap.tid = pid;
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
 
 		if (process(tool, event, &synth_sample, machine) != 0) {
 			rc = -1;
@@ -612,12 +634,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n",
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
 		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
 		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
 		       event->mmap2.min, event->mmap2.ino,
 		       event->mmap2.ino_generation,
-		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+		       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+		       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+		       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
 		       event->mmap2.filename);
 }
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d970232..e5dd40a 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,6 +7,7 @@
 #include "../perf.h"
 #include "map.h"
 #include "build-id.h"
+#include "perf_regs.h"
 
 struct mmap_event {
 	struct perf_event_header header;
@@ -27,6 +28,8 @@ struct mmap2_event {
 	u32 min;
 	u64 ino;
 	u64 ino_generation;
+	u32 prot;
+	u32 flags;
 	char filename[PATH_MAX];
 };
 
@@ -87,6 +90,10 @@ struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
+
+	/* Cached values/mask filled by first register access. */
+	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_mask;
 };
 
 struct stack_dump {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5c28d82..8606175 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -589,10 +589,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	}
 
 	/*
-	 * We default some events to a 1 default interval. But keep
+	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
 			perf_evsel__set_sample_bit(evsel, PERIOD);
@@ -659,6 +659,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		perf_evsel__set_sample_bit(evsel, WEIGHT);
 
 	attr->mmap  = track;
+	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
 	if (opts->sample_transaction)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 5a0a4b2..30df618 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -128,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen + 1);
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
@@ -439,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
+		.cpu	 = al->cpu,
+		.cpumode = al->cpumode,
+		.ip	 = al->addr,
+		.level	 = al->level,
 		.stat = {
 			.nr_events = 1,
 			.period	= period,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d2bf035..742f49a 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -72,6 +72,7 @@ enum hist_column {
 	HISTC_MEM_TLB,
 	HISTC_MEM_LVL,
 	HISTC_MEM_SNOOP,
+	HISTC_MEM_DCACHELINE,
 	HISTC_TRANSACTION,
 	HISTC_NR_COLS, /* Last entry */
 };
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7409ac8..0e5fea9 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1060,6 +1060,8 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.pid, event->mmap2.maj,
 			event->mmap2.min, event->mmap2.ino,
 			event->mmap2.ino_generation,
+			event->mmap2.prot,
+			event->mmap2.flags,
 			event->mmap2.filename, type);
 
 	if (map == NULL)
@@ -1105,7 +1107,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
 	map = map__new(&machine->user_dsos, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			event->mmap.pid, 0, 0, 0, 0,
+			event->mmap.pid, 0, 0, 0, 0, 0, 0,
 			event->mmap.filename,
 			type);
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8ccbb32..25c571f 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -138,7 +138,7 @@ void map__init(struct map *map, enum map_type type,
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen, char *filename,
+		     u64 ino_gen, u32 prot, u32 flags, char *filename,
 		     enum map_type type)
 {
 	struct map *map = malloc(sizeof(*map));
@@ -157,6 +157,8 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		map->min = d_min;
 		map->ino = ino;
 		map->ino_generation = ino_gen;
+		map->prot = prot;
+		map->flags = flags;
 
 		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ae2d451..7758c72 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -35,6 +35,8 @@ struct map {
 	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
+	u32			prot;
+	u32			flags;
 	u64			pgoff;
 	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
@@ -118,7 +120,7 @@ void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen,
+		     u64 ino_gen, u32 prot, u32 flags,
 		     char *filename, enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a3539ef..43168fb 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,11 +1,15 @@
 #include <errno.h>
 #include "perf_regs.h"
+#include "event.h"
 
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if (regs->cache_mask & (1 << id))
+		goto out;
+
 	if (!(mask & (1 << id)))
 		return -EINVAL;
 
@@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 			idx++;
 	}
 
-	*valp = regs->regs[idx];
+	regs->cache_mask |= (1 << id);
+	regs->cache_regs[id] = regs->regs[idx];
+
+out:
+	*valp = regs->cache_regs[id];
 	return 0;
 }
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 79c78f7..980dbf7 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -2,7 +2,8 @@
 #define __PERF_REGS_H
 
 #include <linux/types.h>
-#include "event.h"
+
+struct regs_dump;
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
@@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
 #else
 #define PERF_REGS_MASK	0
+#define PERF_REGS_MAX	0
 
 static inline const char *perf_reg_name(int id __maybe_unused)
 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0d1542f..9a0a183 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	debuginfo__delete(dinfo);
-	if (ret == 0) {
+	if (ret == 0 || ret == -ENOENT) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
 	} else if (ret < 0) {
-		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		pr_warning("Debuginfo analysis failed.\n");
 		return ret;
 	}
 
@@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	ret = get_real_path(tmp, lr->comp_dir, &lr->path);
 	free(tmp);	/* Free old path */
 	if (ret < 0) {
-		pr_warning("Failed to find source file. (%d)\n", ret);
+		pr_warning("Failed to find source file path.\n");
 		return ret;
 	}
 
@@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
 						max_vls, externs);
 	if (ret <= 0) {
-		pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+		if (ret == 0 || ret == -ENOENT) {
+			pr_err("Failed to find the address of %s\n", buf);
+			ret = -ENOENT;
+		} else
+			pr_warning("Debuginfo analysis failed.\n");
 		goto end;
 	}
+
 	/* Some variables are found */
 	fprintf(stdout, "Available variables at %s\n", buf);
 	for (i = 0; i < ret; i++) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 9d8eb26..98e3047 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -573,14 +573,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
 		/* Search again in global variables */
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+			pr_warning("Failed to find '%s' in this function.\n",
+				   pf->pvar->var);
 			ret = -ENOENT;
 	}
 	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
-	if (ret < 0)
-		pr_warning("Failed to find '%s' in this function.\n",
-			   pf->pvar->var);
 	return ret;
 }
 
@@ -1281,7 +1280,11 @@ out:
 	return ret;
 }
 
-/* Find available variables at given probe point */
+/*
+ * Find available variables at given probe point
+ * Return the number of found probe points. Return 0 if there is no
+ * matched probe point. Return <0 if an error occurs.
+ */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
 				      struct variable_list **vls,
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e108207..af7da56 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -215,6 +215,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_STRING:
+	case PRINT_BITMASK:
 		break;
 	case PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cd9774d..1c41932 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -197,6 +197,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_FUNC:
+	case PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -622,6 +623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			fprintf(ofp, "%s=", f->name);
 			if (f->flags & FIELD_IS_STRING ||
 			    f->flags & FIELD_IS_FLAG ||
+			    f->flags & FIELD_IS_ARRAY ||
 			    f->flags & FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
 			else if (f->flags & FIELD_IS_SIGNED)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 45512ba..1ec57dd 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,3 +1,4 @@
+#include <sys/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -784,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
+static inline  u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	u64 l, r;
+	struct map *l_map, *r_map;
+
+	if (!left->mem_info)  return -1;
+	if (!right->mem_info) return 1;
+
+	/* group event types together */
+	if (left->cpumode > right->cpumode) return -1;
+	if (left->cpumode < right->cpumode) return 1;
+
+	l_map = left->mem_info->daddr.map;
+	r_map = right->mem_info->daddr.map;
+
+	/* if both are NULL, jump to sort on al_addr instead */
+	if (!l_map && !r_map)
+		goto addr;
+
+	if (!l_map) return -1;
+	if (!r_map) return 1;
+
+	if (l_map->maj > r_map->maj) return -1;
+	if (l_map->maj < r_map->maj) return 1;
+
+	if (l_map->min > r_map->min) return -1;
+	if (l_map->min < r_map->min) return 1;
+
+	if (l_map->ino > r_map->ino) return -1;
+	if (l_map->ino < r_map->ino) return 1;
+
+	if (l_map->ino_generation > r_map->ino_generation) return -1;
+	if (l_map->ino_generation < r_map->ino_generation) return 1;
+
+	/*
+	 * Addresses with no major/minor numbers are assumed to be
+	 * anonymous in userspace.  Sort those on pid then address.
+	 *
+	 * The kernel and non-zero major/minor mapped areas are
+	 * assumed to be unity mapped.  Sort those on address.
+	 */
+
+	if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
+	    (!(l_map->flags & MAP_SHARED)) &&
+	    !l_map->maj && !l_map->min && !l_map->ino &&
+	    !l_map->ino_generation) {
+		/* userspace anonymous */
+
+		if (left->thread->pid_ > right->thread->pid_) return -1;
+		if (left->thread->pid_ < right->thread->pid_) return 1;
+	}
+
+addr:
+	/* al_addr does all the right addr - start + offset calculations */
+	l = cl_address(left->mem_info->daddr.al_addr);
+	r = cl_address(right->mem_info->daddr.al_addr);
+
+	if (l > r) return -1;
+	if (l < r) return 1;
+
+	return 0;
+}
+
+static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+	char level = he->level;
+
+	if (he->mem_info) {
+		addr = cl_address(he->mem_info->daddr.al_addr);
+		map = he->mem_info->daddr.map;
+		sym = he->mem_info->daddr.sym;
+
+		/* print [s] for shared data mmaps */
+		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
+		     map && (map->type == MAP__VARIABLE) &&
+		    (map->flags & MAP_SHARED) &&
+		    (map->maj || map->min || map->ino ||
+		     map->ino_generation))
+			level = 's';
+		else if (!map)
+			level = 'X';
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size,
+					 width);
+}
+
 struct sort_entry sort_mispredict = {
 	.se_header	= "Branch Mispredicted",
 	.se_cmp		= sort__mispredict_cmp,
@@ -876,6 +975,13 @@ struct sort_entry sort_mem_snoop = {
 	.se_width_idx	= HISTC_MEM_SNOOP,
 };
 
+struct sort_entry sort_mem_dcacheline = {
+	.se_header	= "Data Cacheline",
+	.se_cmp		= sort__dcacheline_cmp,
+	.se_snprintf	= hist_entry__dcacheline_snprintf,
+	.se_width_idx	= HISTC_MEM_DCACHELINE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1043,6 +1149,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
 	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
 	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5bf0098..041f0c9 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -89,6 +89,7 @@ struct hist_entry {
 	u64			ip;
 	u64			transaction;
 	s32			cpu;
+	u8			cpumode;
 
 	struct hist_entry_diff	diff;
 
@@ -185,6 +186,7 @@ enum sort_type {
 	SORT_MEM_TLB,
 	SORT_MEM_LVL,
 	SORT_MEM_SNOOP,
+	SORT_MEM_DCACHELINE,
 };
 
 /*
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index bd5768d..25578b9 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -250,7 +250,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 
 	/* Check the .eh_frame section for unwinding info */
 	offset = elf_section_offset(fd, ".eh_frame_hdr");
-	close(fd);
 
 	if (offset)
 		ret = unwind_spec_ehframe(dso, machine, offset,
@@ -271,7 +270,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 
 	/* Check the .debug_frame section for unwinding info */
 	*offset = elf_section_offset(fd, ".debug_frame");
-	close(fd);
 
 	if (*offset)
 		return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7fff6be..95aefa7 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,6 +17,7 @@
  * XXX We need to find a better place for these things...
  */
 unsigned int page_size;
+int cacheline_size;
 
 bool test_attr__enabled;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b03da44..6686436 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -304,6 +304,7 @@ char *rtrim(char *s);
 void dump_stack(void);
 
 extern unsigned int page_size;
+extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-05-22  8:04 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-05-22  8:04 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b69cf53640da2b86439596118cfa95233154ee76 perf: Fix a race between ring_buffer_detach() and ring_buffer_attach()

The biggest changes are fixes for races that kept triggering Trinity 
crashes, plus liblockdep build fixes and smaller misc fixes.

... liblockdep bits in perf/urgent are a pull mistake - they should 
have been in locking/urgent - but by the time I noticed other commits 
were added and testing was done :-/ Sorry about that.

 Thanks,

	Ingo

------------------>
Jiri Olsa (1):
      perf: Prevent false warning in perf_swevent_add

Peter Zijlstra (4):
      perf: Fix race in removing an event
      perf: Fix perf_event_init_context()
      perf: Limit perf_event_attr::sample_period to 63 bits
      perf: Fix a race between ring_buffer_detach() and ring_buffer_attach()

S. Lockwood-Childs (1):
      tools/liblockdep: Build liblockdep from tools/Makefile

Sasha Levin (1):
      tools/liblockdep: Remove all build files when doing make clean

Yan, Zheng (1):
      perf/x86/intel: Fix Silvermont's event constraints


 arch/x86/kernel/cpu/perf_event_intel.c |   1 -
 include/linux/perf_event.h             |   2 +
 kernel/events/core.c                   | 174 +++++++++++++++++----------------
 tools/Makefile                         |   6 ++
 tools/lib/lockdep/Makefile             |   5 +-
 5 files changed, 102 insertions(+), 86 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa333d9..adb02aa 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -169,7 +169,6 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
-	FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
 	EVENT_CONSTRAINT_END
 };
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3356abc..3ef6ea1 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -402,6 +402,8 @@ struct perf_event {
 
 	struct ring_buffer		*rb;
 	struct list_head		rb_entry;
+	unsigned long			rcu_batches;
+	int				rcu_pending;
 
 	/* poll related */
 	wait_queue_head_t		waitq;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f83a71a..440eefc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1443,6 +1443,11 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+struct remove_event {
+	struct perf_event *event;
+	bool detach_group;
+};
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1451,12 +1456,15 @@ group_sched_out(struct perf_event *group_event,
  */
 static int __perf_remove_from_context(void *info)
 {
-	struct perf_event *event = info;
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
+	if (re->detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
 		ctx->is_active = 0;
@@ -1481,10 +1489,14 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
+	struct remove_event re = {
+		.event = event,
+		.detach_group = detach_group,
+	};
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -1493,12 +1505,12 @@ static void perf_remove_from_context(struct perf_event *event)
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, event);
+		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
 	}
 
 retry:
-	if (!task_function_call(task, __perf_remove_from_context, event))
+	if (!task_function_call(task, __perf_remove_from_context, &re))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -1515,6 +1527,8 @@ retry:
 	 * Since the task isn't running, its safe to remove the event, us
 	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
+	if (detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
@@ -3178,7 +3192,8 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void ring_buffer_put(struct ring_buffer *rb);
-static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb);
 
 static void unaccount_event_cpu(struct perf_event *event, int cpu)
 {
@@ -3238,8 +3253,6 @@ static void free_event(struct perf_event *event)
 	unaccount_event(event);
 
 	if (event->rb) {
-		struct ring_buffer *rb;
-
 		/*
 		 * Can happen when we close an event with re-directed output.
 		 *
@@ -3247,12 +3260,7 @@ static void free_event(struct perf_event *event)
 		 * over us; possibly making our ring_buffer_put() the last.
 		 */
 		mutex_lock(&event->mmap_mutex);
-		rb = event->rb;
-		if (rb) {
-			rcu_assign_pointer(event->rb, NULL);
-			ring_buffer_detach(event, rb);
-			ring_buffer_put(rb); /* could be last */
-		}
+		ring_buffer_attach(event, NULL);
 		mutex_unlock(&event->mmap_mutex);
 	}
 
@@ -3281,10 +3289,7 @@ int perf_event_release_kernel(struct perf_event *event)
 	 *     to trigger the AB-BA case.
 	 */
 	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	raw_spin_unlock_irq(&ctx->lock);
-	perf_remove_from_context(event);
+	perf_remove_from_context(event, true);
 	mutex_unlock(&ctx->mutex);
 
 	free_event(event);
@@ -3839,28 +3844,47 @@ unlock:
 static void ring_buffer_attach(struct perf_event *event,
 			       struct ring_buffer *rb)
 {
+	struct ring_buffer *old_rb = NULL;
 	unsigned long flags;
 
-	if (!list_empty(&event->rb_entry))
-		return;
+	if (event->rb) {
+		/*
+		 * Should be impossible, we set this when removing
+		 * event->rb_entry and wait/clear when adding event->rb_entry.
+		 */
+		WARN_ON_ONCE(event->rcu_pending);
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	if (list_empty(&event->rb_entry))
-		list_add(&event->rb_entry, &rb->event_list);
-	spin_unlock_irqrestore(&rb->event_lock, flags);
-}
+		old_rb = event->rb;
+		event->rcu_batches = get_state_synchronize_rcu();
+		event->rcu_pending = 1;
 
-static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
-{
-	unsigned long flags;
+		spin_lock_irqsave(&old_rb->event_lock, flags);
+		list_del_rcu(&event->rb_entry);
+		spin_unlock_irqrestore(&old_rb->event_lock, flags);
+	}
 
-	if (list_empty(&event->rb_entry))
-		return;
+	if (event->rcu_pending && rb) {
+		cond_synchronize_rcu(event->rcu_batches);
+		event->rcu_pending = 0;
+	}
+
+	if (rb) {
+		spin_lock_irqsave(&rb->event_lock, flags);
+		list_add_rcu(&event->rb_entry, &rb->event_list);
+		spin_unlock_irqrestore(&rb->event_lock, flags);
+	}
+
+	rcu_assign_pointer(event->rb, rb);
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_del_init(&event->rb_entry);
-	wake_up_all(&event->waitq);
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	if (old_rb) {
+		ring_buffer_put(old_rb);
+		/*
+		 * Since we detached before setting the new rb, so that we
+		 * could attach the new rb, we could have missed a wakeup.
+		 * Provide it now.
+		 */
+		wake_up_all(&event->waitq);
+	}
 }
 
 static void ring_buffer_wakeup(struct perf_event *event)
@@ -3929,7 +3953,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = ring_buffer_get(event);
 	struct user_struct *mmap_user = rb->mmap_user;
 	int mmap_locked = rb->mmap_locked;
 	unsigned long size = perf_data_size(rb);
@@ -3937,18 +3961,14 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	atomic_dec(&rb->mmap_count);
 
 	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
-		return;
+		goto out_put;
 
-	/* Detach current event from the buffer. */
-	rcu_assign_pointer(event->rb, NULL);
-	ring_buffer_detach(event, rb);
+	ring_buffer_attach(event, NULL);
 	mutex_unlock(&event->mmap_mutex);
 
 	/* If there's still other mmap()s of this buffer, we're done. */
-	if (atomic_read(&rb->mmap_count)) {
-		ring_buffer_put(rb); /* can't be last */
-		return;
-	}
+	if (atomic_read(&rb->mmap_count))
+		goto out_put;
 
 	/*
 	 * No other mmap()s, detach from all other events that might redirect
@@ -3978,11 +3998,9 @@ again:
 		 * still restart the iteration to make sure we're not now
 		 * iterating the wrong list.
 		 */
-		if (event->rb == rb) {
-			rcu_assign_pointer(event->rb, NULL);
-			ring_buffer_detach(event, rb);
-			ring_buffer_put(rb); /* can't be last, we still have one */
-		}
+		if (event->rb == rb)
+			ring_buffer_attach(event, NULL);
+
 		mutex_unlock(&event->mmap_mutex);
 		put_event(event);
 
@@ -4007,6 +4025,7 @@ again:
 	vma->vm_mm->pinned_vm -= mmap_locked;
 	free_uid(mmap_user);
 
+out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
@@ -4124,7 +4143,6 @@ again:
 	vma->vm_mm->pinned_vm += extra;
 
 	ring_buffer_attach(event, rb);
-	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
@@ -5408,6 +5426,9 @@ struct swevent_htable {
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
+
+	/* Keeps track of cpu being initialized/exited */
+	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -5654,8 +5675,14 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (WARN_ON_ONCE(!head))
+	if (!head) {
+		/*
+		 * We can race with cpu hotplug code. Do not
+		 * WARN if the cpu just got unplugged.
+		 */
+		WARN_ON_ONCE(swhash->online);
 		return -EINVAL;
+	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 
@@ -6914,7 +6941,7 @@ err_size:
 static int
 perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
-	struct ring_buffer *rb = NULL, *old_rb = NULL;
+	struct ring_buffer *rb = NULL;
 	int ret = -EINVAL;
 
 	if (!output_event)
@@ -6942,8 +6969,6 @@ set:
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
 
-	old_rb = event->rb;
-
 	if (output_event) {
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
@@ -6951,23 +6976,7 @@ set:
 			goto unlock;
 	}
 
-	if (old_rb)
-		ring_buffer_detach(event, old_rb);
-
-	if (rb)
-		ring_buffer_attach(event, rb);
-
-	rcu_assign_pointer(event->rb, rb);
-
-	if (old_rb) {
-		ring_buffer_put(old_rb);
-		/*
-		 * Since we detached before setting the new rb, so that we
-		 * could attach the new rb, we could have missed a wakeup.
-		 * Provide it now.
-		 */
-		wake_up_all(&event->waitq);
-	}
+	ring_buffer_attach(event, rb);
 
 	ret = 0;
 unlock:
@@ -7018,6 +7027,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;
+	} else {
+		if (attr.sample_period & (1ULL << 63))
+			return -EINVAL;
 	}
 
 	/*
@@ -7165,7 +7177,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader, false);
 
 		/*
 		 * Removing from the context ends up with disabled
@@ -7175,7 +7187,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling);
+			perf_remove_from_context(sibling, false);
 			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
@@ -7305,7 +7317,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock(&src_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event);
+		perf_remove_from_context(event, false);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
@@ -7367,13 +7379,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	if (child_event->parent) {
-		raw_spin_lock_irq(&child_ctx->lock);
-		perf_group_detach(child_event);
-		raw_spin_unlock_irq(&child_ctx->lock);
-	}
-
-	perf_remove_from_context(child_event);
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7724,6 +7730,8 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	 * swapped under us.
 	 */
 	parent_ctx = perf_pin_task_context(parent, ctxn);
+	if (!parent_ctx)
+		return 0;
 
 	/*
 	 * No need to check if parent_ctx != NULL here; since we saw
@@ -7835,6 +7843,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -7857,14 +7866,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
+	struct remove_event re = { .detach_group = false };
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
-		__perf_remove_from_context(event);
+	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(&re);
 	rcu_read_unlock();
 }
 
@@ -7892,6 +7901,7 @@ static void perf_event_exit_cpu(int cpu)
 	perf_event_exit_cpu_context(cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = false;
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
 }
diff --git a/tools/Makefile b/tools/Makefile
index bcae806..9a617ad 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -44,6 +44,9 @@ cpupower: FORCE
 cgroup firewire hv guest usb virtio vm net: FORCE
 	$(call descend,$@)
 
+liblockdep: FORCE
+	$(call descend,lib/lockdep)
+
 libapikfs: FORCE
 	$(call descend,lib/api)
 
@@ -91,6 +94,9 @@ cpupower_clean:
 cgroup_clean hv_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean:
 	$(call descend,$(@:_clean=),clean)
 
+liblockdep_clean:
+	$(call descend,lib/lockdep,clean)
+
 libapikfs_clean:
 	$(call descend,lib/api,clean)
 
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index cb09d3f..bba2f52 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -1,8 +1,7 @@
 # file format version
 FILE_VERSION = 1
 
-MAKEFLAGS += --no-print-directory
-LIBLOCKDEP_VERSION=$(shell make -sC ../../.. kernelversion)
+LIBLOCKDEP_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion)
 
 # Makefiles suck: This macro sets a default value of $(2) for the
 # variable named by $(1), unless the variable has been set by
@@ -231,7 +230,7 @@ install_lib: all_cmd
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d
 	$(RM) tags TAGS
 
 endif # skip-makefile

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-05-01  6:34 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-05-01  6:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 399f0c220a0ee97a5a9ea1a699a58fe2aacf2983 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/urgent

Mostly tooling fixes, plus an Intel RAPL PMU driver fix.

 Thanks,

	Ingo

------------------>
Jiri Olsa (5):
      perf tools: Disable libdw unwind for all but x86 arch
      perf tools: Use LDFLAGS instead of ALL_LDFLAGS
      perf tools: Fix bfd dependency libraries detection
      perf tests: Add static build make test
      perf tests x86: Fix stack map lookup in dwarf unwind test

Masanari Iida (1):
      perf tests x86: Fix memory leak in sample_ustack()

Mathias Krause (1):
      perf x86: Fix perf to use non-executable stack, again

Richard Yao (1):
      perf machine: Search for modules in %s/lib/modules/%s

Stephane Eranian (1):
      perf/x86: Fix RAPL rdmsrl_safe() usage

Steven Rostedt (2):
      tools lib traceevent: Fix backward compatibility macros for pevent filter enums
      tools lib traceevent: Fix memory leak in pretty_print()

Xia Kaixu (1):
      perf tools: Remove extra '/' character in events file path


 arch/x86/kernel/cpu/perf_event_intel_rapl.c |  3 +-
 tools/lib/api/fs/debugfs.c                  |  4 +--
 tools/lib/traceevent/event-parse.c          |  1 +
 tools/lib/traceevent/event-parse.h          |  4 +--
 tools/perf/Makefile.perf                    |  2 +-
 tools/perf/arch/x86/tests/dwarf-unwind.c    |  3 +-
 tools/perf/arch/x86/tests/regs_load.S       |  8 ++++-
 tools/perf/config/Makefile                  | 46 ++++++++++++++++++++++-------
 tools/perf/tests/make                       |  2 ++
 tools/perf/util/machine.c                   | 16 +++++++---
 10 files changed, 66 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 7c87424..619f769 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -543,7 +543,8 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
-	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+	/* protect rdmsrl() to handle virtualization */
+	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
 		return -1;
 
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
index 7c43479..a74fba6 100644
--- a/tools/lib/api/fs/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
@@ -12,8 +12,8 @@
 char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
 
 static const char * const debugfs_known_mountpoints[] = {
-	"/sys/kernel/debug/",
-	"/debug/",
+	"/sys/kernel/debug",
+	"/debug",
 	0,
 };
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index baec7d8..b83184f 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4344,6 +4344,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 					      format, len_arg, arg);
 				trace_seq_terminate(&p);
 				trace_seq_puts(s, p.buffer);
+				trace_seq_destroy(&p);
 				arg = arg->next;
 				break;
 			default:
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 791c539..feab942 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -876,8 +876,8 @@ struct event_filter {
 struct event_filter *pevent_filter_alloc(struct pevent *pevent);
 
 /* for backward compatibility */
-#define FILTER_NONE		PEVENT_ERRNO__FILTER_NOT_FOUND
-#define FILTER_NOEXIST		PEVENT_ERRNO__NO_FILTER
+#define FILTER_NONE		PEVENT_ERRNO__NO_FILTER
+#define FILTER_NOEXIST		PEVENT_ERRNO__FILTER_NOT_FOUND
 #define FILTER_MISS		PEVENT_ERRNO__FILTER_MISS
 #define FILTER_MATCH		PEVENT_ERRNO__FILTER_MATCH
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e969233..895edd3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -589,7 +589,7 @@ $(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H)
 	$(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $<
 
 $(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) -o $@ -shared $(ALL_LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
+	$(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
 
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index b602ad9..83bc238 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -23,9 +23,10 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_X86_SP];
 
-	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	map = map_groups__find(&thread->mg, MAP__VARIABLE, (u64) sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
+		free(buf);
 		return -1;
 	}
 
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
index 99167bf..60875d5 100644
--- a/tools/perf/arch/x86/tests/regs_load.S
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -1,4 +1,3 @@
-
 #include <linux/linkage.h>
 
 #define AX	 0
@@ -90,3 +89,10 @@ ENTRY(perf_regs_load)
 	ret
 ENDPROC(perf_regs_load)
 #endif
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index ee21fa9..802cf54 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -34,6 +34,14 @@ ifeq ($(ARCH),arm)
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
+# So far there's only x86 libdw unwind support merged in perf.
+# Disable it on all other architectures in case libdw unwind
+# support is detected in system. Add supported architectures
+# to the check.
+ifneq ($(ARCH),x86)
+  NO_LIBDW_DWARF_UNWIND := 1
+endif
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -109,6 +117,10 @@ CFLAGS += -Wall
 CFLAGS += -Wextra
 CFLAGS += -std=gnu99
 
+# Enforce a non-executable stack, as we may regress (again) in the future by
+# adding assembler files missing the .GNU-stack linker note.
+LDFLAGS += -Wl,-z,noexecstack
+
 EXTLIBS = -lelf -lpthread -lrt -lm -ldl
 
 ifneq ($(OUTPUT),)
@@ -186,7 +198,10 @@ VF_FEATURE_TESTS =			\
 	stackprotector-all		\
 	timerfd				\
 	libunwind-debug-frame		\
-	bionic
+	bionic				\
+	liberty				\
+	liberty-z			\
+	cplus-demangle
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
@@ -504,7 +519,21 @@ else
 endif
 
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd -lz -liberty
+  EXTLIBS += -lbfd
+
+  # call all detections now so we get correct
+  # status in VF output
+  $(call feature_check,liberty)
+  $(call feature_check,liberty-z)
+  $(call feature_check,cplus-demangle)
+
+  ifeq ($(feature-liberty), 1)
+    EXTLIBS += -liberty
+  else
+    ifeq ($(feature-liberty-z), 1)
+      EXTLIBS += -liberty -lz
+    endif
+  endif
 endif
 
 ifdef NO_DEMANGLE
@@ -515,15 +544,10 @@ else
     CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
   else
     ifneq ($(feature-libbfd), 1)
-      $(call feature_check,liberty)
-      ifeq ($(feature-liberty), 1)
-        EXTLIBS += -lbfd -liberty
-      else
-        $(call feature_check,liberty-z)
-        ifeq ($(feature-liberty-z), 1)
-          EXTLIBS += -lbfd -liberty -lz
-        else
-          $(call feature_check,cplus-demangle)
+      ifneq ($(feature-liberty), 1)
+        ifneq ($(feature-liberty-z), 1)
+          # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT
+          # or any of 'bfd iberty z' trinity
           ifeq ($(feature-cplus-demangle), 1)
             EXTLIBS += -liberty
             CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 5daeae1..2f92d6e 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -46,6 +46,7 @@ make_install_man    := install-man
 make_install_html   := install-html
 make_install_info   := install-info
 make_install_pdf    := install-pdf
+make_static         := LDFLAGS=-static
 
 # all the NO_* variable combined
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
@@ -87,6 +88,7 @@ run += make_install_bin
 # run += make_install_info
 # run += make_install_pdf
 run += make_minimal
+run += make_static
 
 ifneq ($(call has,ctags),)
 run += make_tags
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index a53cd0b..27c2a5e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -717,7 +717,7 @@ static char *get_kernel_version(const char *root_dir)
 }
 
 static int map_groups__set_modules_path_dir(struct map_groups *mg,
-				const char *dir_name)
+				const char *dir_name, int depth)
 {
 	struct dirent *dent;
 	DIR *dir = opendir(dir_name);
@@ -742,7 +742,15 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 			    !strcmp(dent->d_name, ".."))
 				continue;
 
-			ret = map_groups__set_modules_path_dir(mg, path);
+			/* Do not follow top-level source and build symlinks */
+			if (depth == 0) {
+				if (!strcmp(dent->d_name, "source") ||
+				    !strcmp(dent->d_name, "build"))
+					continue;
+			}
+
+			ret = map_groups__set_modules_path_dir(mg, path,
+							       depth + 1);
 			if (ret < 0)
 				goto out;
 		} else {
@@ -786,11 +794,11 @@ static int machine__set_modules_path(struct machine *machine)
 	if (!version)
 		return -1;
 
-	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s",
 		 machine->root_dir, version);
 	free(version);
 
-	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 
 static int machine__create_module(void *arg, const char *name, u64 start)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-04-20  8:02 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-04-20  8:02 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Jiri Olsa, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: fd741edc25600e1660abd00b5c1bbe967018c6a0 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/urgent

Three small tooling fixes.

 Thanks,

	Ingo

------------------>
Adrien BAK (1):
      perf tools: Improve error reporting

Alexander Yarygin (1):
      perf kvm: Fix 'Min time' counting in report command

Vladimir Nikulichev (1):
      perf tools: Adjust symbols in VDSO


 tools/perf/builtin-kvm.c     | 1 +
 tools/perf/builtin-record.c  | 2 +-
 tools/perf/util/data.c       | 9 ++++++++-
 tools/perf/util/symbol-elf.c | 2 ++
 4 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 21c164b..0f1e5a2 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -404,6 +404,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
 	}
 
 	event->key = *key;
+	init_stats(&event->total.stats);
 	return event;
 }
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index eb524f9..8ce62ef 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -374,7 +374,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	session = perf_session__new(file, false, NULL);
 	if (session == NULL) {
-		pr_err("Not enough memory for reading perf file header\n");
+		pr_err("Perf session creation failed.\n");
 		return -1;
 	}
 
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 1fbcd8b..55de44e 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -86,10 +86,17 @@ static int open_file_read(struct perf_data_file *file)
 
 static int open_file_write(struct perf_data_file *file)
 {
+	int fd;
+
 	if (check_backup(file))
 		return -1;
 
-	return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+
+	if (fd < 0)
+		pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+
+	return fd;
 }
 
 static int open_file(struct perf_data_file *file)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3b7dbf5..6864661 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "vdso.h"
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
@@ -618,6 +619,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		GElf_Shdr shdr;
 		ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				ehdr.e_type == ET_REL ||
+				is_vdso_map(dso->short_name) ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-04-19 10:41 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-04-19 10:41 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 24223657806a0ebd0ae5c9caaf7b021091889cf2 perf/x86/intel: Use rdmsrl_safe() when initializing RAPL PMU

Two kernel side fixes:

 - an Intel uncore PMU driver potential crash fix
 - a kprobes/perf-call-graph interaction fix

 Thanks,

	Ingo

------------------>
Masami Hiramatsu (1):
      kprobes/x86: Fix page-fault handling logic

Venkatesh Srinivas (1):
      perf/x86/intel: Use rdmsrl_safe() when initializing RAPL PMU


 arch/x86/kernel/cpu/perf_event_intel_rapl.c | 12 +++++++++---
 arch/x86/kernel/kprobes/core.c              | 16 +++++++---------
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 4b9a9e9..7c87424 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -535,6 +535,7 @@ static int rapl_cpu_prepare(int cpu)
 	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
 	int phys_id = topology_physical_package_id(cpu);
 	u64 ms;
+	u64 msr_rapl_power_unit_bits;
 
 	if (pmu)
 		return 0;
@@ -542,6 +543,9 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
+	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+		return -1;
+
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
 		return -1;
@@ -555,8 +559,7 @@ static int rapl_cpu_prepare(int cpu)
 	 *
 	 * we cache in local PMU instance
 	 */
-	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
-	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 	pmu->pmu = &rapl_pmu_class;
 
 	/*
@@ -677,7 +680,9 @@ static int __init rapl_pmu_init(void)
 	cpu_notifier_register_begin();
 
 	for_each_online_cpu(cpu) {
-		rapl_cpu_prepare(cpu);
+		ret = rapl_cpu_prepare(cpu);
+		if (ret)
+			goto out;
 		rapl_cpu_init(cpu);
 	}
 
@@ -700,6 +705,7 @@ static int __init rapl_pmu_init(void)
 		hweight32(rapl_cntr_mask),
 		ktime_to_ms(pmu->timer_interval));
 
+out:
 	cpu_notifier_register_done();
 
 	return 0;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 79a3f96..61b17dc 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -897,9 +897,10 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
-	switch (kcb->kprobe_status) {
-	case KPROBE_HIT_SS:
-	case KPROBE_REENTER:
+	if (unlikely(regs->ip == (unsigned long)cur->ainsn.insn)) {
+		/* This must happen on single-stepping */
+		WARN_ON(kcb->kprobe_status != KPROBE_HIT_SS &&
+			kcb->kprobe_status != KPROBE_REENTER);
 		/*
 		 * We are here because the instruction being single
 		 * stepped caused a page fault. We reset the current
@@ -914,9 +915,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		else
 			reset_current_kprobe();
 		preempt_enable_no_resched();
-		break;
-	case KPROBE_HIT_ACTIVE:
-	case KPROBE_HIT_SSDONE:
+	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
+		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
 		/*
 		 * We increment the nmissed count for accounting,
 		 * we can also use npre/npostfault count for accounting
@@ -945,10 +945,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * fixup routine could not handle it,
 		 * Let do_page_fault() fix it.
 		 */
-		break;
-	default:
-		break;
 	}
+
 	return 0;
 }
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-04-16 13:04 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-04-16 13:04 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Jiri Olsa, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: ad466db5b0c302e85ad96c42a43194c234cbd862 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/urgent

Tooling fixes, plus a simple hardware-enablement patch for the Intel 
RAPL PMU (energy use measurement) on Haswell CPUs, which I hope is 
still fine at this stage.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf tools: Fix double free in perf test 21 (code-reading.c)

Andi Kleen (1):
      perf stat: Initialize statistics correctly

Arnaldo Carvalho de Melo (2):
      perf callchains: Disable unwind libraries when libelf isn't found
      MAINTAINERS: Change e-mail to kernel.org one

Cody P Schafer (1):
      perf tools: Instead of redirecting flex output, use -o

Masami Hiramatsu (1):
      perf probe: Fix to handle errors in line_range searching

Namhyung Kim (5):
      perf top: Fix documentation of invalid -s option
      tools lib traceevent: Print event name when show warning if possible
      tools lib traceevent: Do not call warning() directly
      perf probe: Fix --line option behavior
      perf probe: Use dwarf_getcfi_elf() instead of dwarf_getcfi()

Ramkumar Ramachandra (4):
      perf tools: Pick up libdw without explicit LIBDW_DIR
      perf bench: Update manpage to mention numa and futex
      perf bench: Fix segfault at the end of an 'all' execution
      perf bench: Set more defaults in the 'numa' suite

Vince Weaver (1):
      perf/x86: Enable DRAM RAPL support on Intel Haswell


 MAINTAINERS                                 |   2 +-
 arch/x86/kernel/cpu/perf_event_intel_rapl.c |  33 ++++++++-
 tools/lib/traceevent/event-parse.c          | 109 +++++++++++++++++-----------
 tools/perf/Documentation/perf-bench.txt     |  22 ++++++
 tools/perf/Documentation/perf-top.txt       |   1 -
 tools/perf/Makefile.perf                    |   4 +-
 tools/perf/bench/numa.c                     |   4 +
 tools/perf/builtin-stat.c                   |  11 ++-
 tools/perf/config/Makefile                  |   7 +-
 tools/perf/tests/code-reading.c             |   1 +
 tools/perf/util/probe-finder.c              |  15 ++--
 11 files changed, 148 insertions(+), 61 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6dc67b1..80399ff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6782,7 +6782,7 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@redhat.com>
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
+M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 059218e..4b9a9e9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -59,7 +59,7 @@
 #define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
 #define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
 #define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT	3	/* DRAM */
+#define RAPL_IDX_PP1_NRG_STAT	3	/* gpu */
 #define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
 
 /* Clients have PP0, PKG */
@@ -72,6 +72,12 @@
 			 1<<RAPL_IDX_PKG_NRG_STAT|\
 			 1<<RAPL_IDX_RAM_NRG_STAT)
 
+/* Servers have PP0, PKG, RAM, PP1 */
+#define RAPL_IDX_HSW	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT|\
+			 1<<RAPL_IDX_PP1_NRG_STAT)
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -425,6 +431,24 @@ static struct attribute *rapl_events_cln_attr[] = {
 	NULL,
 };
 
+static struct attribute *rapl_events_hsw_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_gpu),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_gpu_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_gpu_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
 static struct attribute_group rapl_pmu_events_group = {
 	.name = "events",
 	.attrs = NULL, /* patched at runtime */
@@ -631,11 +655,14 @@ static int __init rapl_pmu_init(void)
 	switch (boot_cpu_data.x86_model) {
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
-	case 60: /* Haswell */
-	case 69: /* Haswell-Celeron */
 		rapl_cntr_mask = RAPL_IDX_CLN;
 		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
 		break;
+	case 60: /* Haswell */
+	case 69: /* Haswell-Celeron */
+		rapl_cntr_mask = RAPL_IDX_HSW;
+		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
+		break;
 	case 45: /* Sandy Bridge-EP */
 	case 62: /* IvyTown */
 		rapl_cntr_mask = RAPL_IDX_SRV;
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 1587ea39..baec7d8 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -50,6 +50,18 @@ static int show_warning = 1;
 			warning(fmt, ##__VA_ARGS__);	\
 	} while (0)
 
+#define do_warning_event(event, fmt, ...)			\
+	do {							\
+		if (!show_warning)				\
+			continue;				\
+								\
+		if (event)					\
+			warning("[%s:%s] " fmt, event->system,	\
+				event->name, ##__VA_ARGS__);	\
+		else						\
+			warning(fmt, ##__VA_ARGS__);		\
+	} while (0)
+
 static void init_input_buf(const char *buf, unsigned long long size)
 {
 	input_buf = buf;
@@ -1355,7 +1367,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		}
 
 		if (!field->type) {
-			do_warning("%s: no type found", __func__);
+			do_warning_event(event, "%s: no type found", __func__);
 			goto fail;
 		}
 		field->name = last_token;
@@ -1402,7 +1414,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				free_token(token);
 				type = read_token(&token);
 				if (type == EVENT_NONE) {
-					do_warning("failed to find token");
+					do_warning_event(event, "failed to find token");
 					goto fail;
 				}
 			}
@@ -1636,7 +1648,7 @@ process_cond(struct event_format *event, struct print_arg *top, char **tok)
 	right = alloc_arg();
 
 	if (!arg || !left || !right) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		/* arg will be freed at out_free */
 		free_arg(left);
 		free_arg(right);
@@ -1686,7 +1698,7 @@ process_array(struct event_format *event, struct print_arg *top, char **tok)
 
 	arg = alloc_arg();
 	if (!arg) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		/* '*tok' is set to top->op.op.  No need to free. */
 		*tok = NULL;
 		return EVENT_ERROR;
@@ -1792,7 +1804,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 	if (arg->type == PRINT_OP && !arg->op.left) {
 		/* handle single op */
 		if (token[1]) {
-			do_warning("bad op token %s", token);
+			do_warning_event(event, "bad op token %s", token);
 			goto out_free;
 		}
 		switch (token[0]) {
@@ -1802,7 +1814,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		case '-':
 			break;
 		default:
-			do_warning("bad op token %s", token);
+			do_warning_event(event, "bad op token %s", token);
 			goto out_free;
 
 		}
@@ -1888,7 +1900,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 			char *new_atom;
 
 			if (left->type != PRINT_ATOM) {
-				do_warning("bad pointer type");
+				do_warning_event(event, "bad pointer type");
 				goto out_free;
 			}
 			new_atom = realloc(left->atom.atom,
@@ -1930,7 +1942,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		type = process_array(event, arg, tok);
 
 	} else {
-		do_warning("unknown op '%s'", token);
+		do_warning_event(event, "unknown op '%s'", token);
 		event->flags |= EVENT_FL_FAILED;
 		/* the arg is now the left side */
 		goto out_free;
@@ -1951,7 +1963,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 	return type;
 
 out_warn_free:
-	do_warning("%s: not enough memory!", __func__);
+	do_warning_event(event, "%s: not enough memory!", __func__);
 out_free:
 	free_token(token);
 	*tok = NULL;
@@ -2385,7 +2397,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 
 	field = alloc_arg();
 	if (!field) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		goto out_free;
 	}
 
@@ -2438,7 +2450,7 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 
 	field = alloc_arg();
 	if (!field) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		goto out_free;
 	}
 
@@ -2477,7 +2489,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 
 	field = alloc_arg();
 	if (!field) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		goto out_free;
 	}
 
@@ -2492,7 +2504,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 
 	field = alloc_arg();
 	if (!field) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		*tok = NULL;
 		return EVENT_ERROR;
 	}
@@ -2555,7 +2567,7 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 	free_token(token);
 	arg = alloc_arg();
 	if (!arg) {
-		do_warning("%s: not enough memory!", __func__);
+		do_warning_event(event, "%s: not enough memory!", __func__);
 		*tok = NULL;
 		return EVENT_ERROR;
 	}
@@ -2614,13 +2626,14 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
 
 		/* prevous must be an atom */
 		if (arg->type != PRINT_ATOM) {
-			do_warning("previous needed to be PRINT_ATOM");
+			do_warning_event(event, "previous needed to be PRINT_ATOM");
 			goto out_free;
 		}
 
 		item_arg = alloc_arg();
 		if (!item_arg) {
-			do_warning("%s: not enough memory!", __func__);
+			do_warning_event(event, "%s: not enough memory!",
+					 __func__);
 			goto out_free;
 		}
 
@@ -2721,21 +2734,24 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	for (i = 0; i < func->nr_args; i++) {
 		farg = alloc_arg();
 		if (!farg) {
-			do_warning("%s: not enough memory!", __func__);
+			do_warning_event(event, "%s: not enough memory!",
+					 __func__);
 			return EVENT_ERROR;
 		}
 
 		type = process_arg(event, farg, &token);
 		if (i < (func->nr_args - 1)) {
 			if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
-				warning("Error: function '%s()' expects %d arguments but event %s only uses %d",
+				do_warning_event(event,
+					"Error: function '%s()' expects %d arguments but event %s only uses %d",
 					func->name, func->nr_args,
 					event->name, i + 1);
 				goto err;
 			}
 		} else {
 			if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
-				warning("Error: function '%s()' only expects %d arguments but event %s has more",
+				do_warning_event(event,
+					"Error: function '%s()' only expects %d arguments but event %s has more",
 					func->name, func->nr_args, event->name);
 				goto err;
 			}
@@ -2792,7 +2808,7 @@ process_function(struct event_format *event, struct print_arg *arg,
 		return process_func_handler(event, func, arg, tok);
 	}
 
-	do_warning("function %s not defined", token);
+	do_warning_event(event, "function %s not defined", token);
 	free_token(token);
 	return EVENT_ERROR;
 }
@@ -2878,7 +2894,7 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 
 	case EVENT_ERROR ... EVENT_NEWLINE:
 	default:
-		do_warning("unexpected type %d", type);
+		do_warning_event(event, "unexpected type %d", type);
 		return EVENT_ERROR;
 	}
 	*tok = token;
@@ -2901,7 +2917,8 @@ static int event_read_print_args(struct event_format *event, struct print_arg **
 
 		arg = alloc_arg();
 		if (!arg) {
-			do_warning("%s: not enough memory!", __func__);
+			do_warning_event(event, "%s: not enough memory!",
+					 __func__);
 			return -1;
 		}
 
@@ -3481,11 +3498,12 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 	return val;
 
 out_warning_op:
-	do_warning("%s: unknown op '%s'", __func__, arg->op.op);
+	do_warning_event(event, "%s: unknown op '%s'", __func__, arg->op.op);
 	return 0;
 
 out_warning_field:
-	do_warning("%s: field %s not found", __func__, arg->field.name);
+	do_warning_event(event, "%s: field %s not found",
+			 __func__, arg->field.name);
 	return 0;
 }
 
@@ -3591,7 +3609,8 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		}
 		str = malloc(len + 1);
 		if (!str) {
-			do_warning("%s: not enough memory!", __func__);
+			do_warning_event(event, "%s: not enough memory!",
+					 __func__);
 			return;
 		}
 		memcpy(str, data + field->offset, len);
@@ -3697,7 +3716,8 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	return;
 
 out_warning_field:
-	do_warning("%s: field %s not found", __func__, arg->field.name);
+	do_warning_event(event, "%s: field %s not found",
+			 __func__, arg->field.name);
 }
 
 static unsigned long long
@@ -3742,14 +3762,16 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 			trace_seq_terminate(&str);
 			string = malloc(sizeof(*string));
 			if (!string) {
-				do_warning("%s(%d): malloc str", __func__, __LINE__);
+				do_warning_event(event, "%s(%d): malloc str",
+						 __func__, __LINE__);
 				goto out_free;
 			}
 			string->next = strings;
 			string->str = strdup(str.buffer);
 			if (!string->str) {
 				free(string);
-				do_warning("%s(%d): malloc str", __func__, __LINE__);
+				do_warning_event(event, "%s(%d): malloc str",
+						 __func__, __LINE__);
 				goto out_free;
 			}
 			args[i] = (uintptr_t)string->str;
@@ -3761,7 +3783,7 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 			 * Something went totally wrong, this is not
 			 * an input error, something in this code broke.
 			 */
-			do_warning("Unexpected end of arguments\n");
+			do_warning_event(event, "Unexpected end of arguments\n");
 			goto out_free;
 		}
 		farg = farg->next;
@@ -3811,12 +3833,12 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	if (!field) {
 		field = pevent_find_field(event, "buf");
 		if (!field) {
-			do_warning("can't find buffer field for binary printk");
+			do_warning_event(event, "can't find buffer field for binary printk");
 			return NULL;
 		}
 		ip_field = pevent_find_field(event, "ip");
 		if (!ip_field) {
-			do_warning("can't find ip field for binary printk");
+			do_warning_event(event, "can't find ip field for binary printk");
 			return NULL;
 		}
 		pevent->bprint_buf_field = field;
@@ -3830,7 +3852,8 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	 */
 	args = alloc_arg();
 	if (!args) {
-		do_warning("%s(%d): not enough memory!", __func__, __LINE__);
+		do_warning_event(event, "%s(%d): not enough memory!",
+				 __func__, __LINE__);
 		return NULL;
 	}
 	arg = args;
@@ -3896,7 +3919,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				bptr += vsize;
 				arg = alloc_arg();
 				if (!arg) {
-					do_warning("%s(%d): not enough memory!",
+					do_warning_event(event, "%s(%d): not enough memory!",
 						   __func__, __LINE__);
 					goto out_free;
 				}
@@ -3919,7 +3942,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 			case 's':
 				arg = alloc_arg();
 				if (!arg) {
-					do_warning("%s(%d): not enough memory!",
+					do_warning_event(event, "%s(%d): not enough memory!",
 						   __func__, __LINE__);
 					goto out_free;
 				}
@@ -3959,7 +3982,7 @@ get_bprint_format(void *data, int size __maybe_unused,
 	if (!field) {
 		field = pevent_find_field(event, "fmt");
 		if (!field) {
-			do_warning("can't find format field for binary printk");
+			do_warning_event(event, "can't find format field for binary printk");
 			return NULL;
 		}
 		pevent->bprint_fmt_field = field;
@@ -4003,8 +4026,8 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
 		arg->field.field =
 			pevent_find_any_field(event, arg->field.name);
 		if (!arg->field.field) {
-			do_warning("%s: field %s not found",
-				   __func__, arg->field.name);
+			do_warning_event(event, "%s: field %s not found",
+					 __func__, arg->field.name);
 			return;
 		}
 	}
@@ -4176,7 +4199,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 			case '*':
 				/* The argument is the length. */
 				if (!arg) {
-					do_warning("no argument match");
+					do_warning_event(event, "no argument match");
 					event->flags |= EVENT_FL_FAILED;
 					goto out_failed;
 				}
@@ -4213,7 +4236,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 			case 'X':
 			case 'u':
 				if (!arg) {
-					do_warning("no argument match");
+					do_warning_event(event, "no argument match");
 					event->flags |= EVENT_FL_FAILED;
 					goto out_failed;
 				}
@@ -4223,7 +4246,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 
 				/* should never happen */
 				if (len > 31) {
-					do_warning("bad format!");
+					do_warning_event(event, "bad format!");
 					event->flags |= EVENT_FL_FAILED;
 					len = 31;
 				}
@@ -4290,13 +4313,13 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 						trace_seq_printf(s, format, (long long)val);
 					break;
 				default:
-					do_warning("bad count (%d)", ls);
+					do_warning_event(event, "bad count (%d)", ls);
 					event->flags |= EVENT_FL_FAILED;
 				}
 				break;
 			case 's':
 				if (!arg) {
-					do_warning("no matching argument");
+					do_warning_event(event, "no matching argument");
 					event->flags |= EVENT_FL_FAILED;
 					goto out_failed;
 				}
@@ -4306,7 +4329,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 
 				/* should never happen */
 				if (len > 31) {
-					do_warning("bad format!");
+					do_warning_event(event, "bad format!");
 					event->flags |= EVENT_FL_FAILED;
 					len = 31;
 				}
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 7065cd6..4464ad7 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -48,6 +48,12 @@ SUBSYSTEM
 'mem'::
 	Memory access performance.
 
+'numa'::
+	NUMA scheduling and MM benchmarks.
+
+'futex'::
+	Futex stressing benchmarks.
+
 'all'::
 	All benchmark subsystems.
 
@@ -187,6 +193,22 @@ Show only the result with page faults before memset.
 --no-prefault::
 Show only the result without page faults before memset.
 
+SUITES FOR 'numa'
+~~~~~~~~~~~~~~~~~
+*mem*::
+Suite for evaluating NUMA workloads.
+
+SUITES FOR 'futex'
+~~~~~~~~~~~~~~~~~~
+*hash*::
+Suite for evaluating hash tables.
+
+*wake*::
+Suite for evaluating wake calls.
+
+*requeue*::
+Suite for evaluating requeue calls.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index cdd8d49..976b00c 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -87,7 +87,6 @@ Default is to monitor all CPUS.
 --realtime=<priority>::
 	Collect data with this RT SCHED_FIFO priority.
 
--s <symbol>::
 --sym-annotate=<symbol>::
         Annotate this symbol.
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 50d875d..e969233 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -192,13 +192,13 @@ endif
 export PERL_PATH
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
-	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
+	$(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
-	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
+	$(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
 	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 97d86d8..ebfa163 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1593,6 +1593,10 @@ static void init_params(struct params *p, const char *name, int argc, const char
 	p->data_rand_walk		= true;
 	p->nr_loops			= -1;
 	p->init_random			= true;
+	p->mb_global_str		= "1";
+	p->nr_proc			= 1;
+	p->nr_threads			= 1;
+	p->nr_secs			= 5;
 	p->run_all			= argc == 1;
 }
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8b0e1c9..65a151e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -174,13 +174,20 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
-	memset(evsel->priv, 0, sizeof(struct perf_stat));
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
 }
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
-	return evsel->priv == NULL ? -ENOMEM : 0;
+	if (evsel == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
 }
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c234182..ee21fa9 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -65,10 +65,9 @@ ifndef NO_LIBELF
   ifdef LIBDW_DIR
     LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
     LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-
-    FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-    FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
   endif
+  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 endif
 
 # include ARCH specific config
@@ -278,6 +277,8 @@ else
       NO_LIBELF := 1
       NO_DWARF := 1
       NO_DEMANGLE := 1
+      NO_LIBUNWIND := 1
+      NO_LIBDW_DWARF_UNWIND := 1
     else
       msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
     endif
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 653a8fe..bfb1869 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -504,6 +504,7 @@ static int do_test_code_reading(bool try_kcore)
 		if (ret < 0) {
 			if (!excl_kernel) {
 				excl_kernel = true;
+				perf_evlist__set_maps(evlist, NULL, NULL);
 				perf_evlist__delete(evlist);
 				evlist = NULL;
 				continue;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df02386..5627621 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -985,7 +985,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 #if _ELFUTILS_PREREQ(0, 142)
 	/* Get the call frame information from this dwarf */
-	pf->cfi = dwarf_getcfi(dbg->dbg);
+	pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
 #endif
 
 	off = 0;
@@ -1441,13 +1441,15 @@ static int line_range_walk_cb(const char *fname, int lineno,
 			      void *data)
 {
 	struct line_finder *lf = data;
+	int err;
 
 	if ((strtailcmp(fname, lf->fname) != 0) ||
 	    (lf->lno_s > lineno || lf->lno_e < lineno))
 		return 0;
 
-	if (line_range_add_line(fname, lineno, lf->lr) < 0)
-		return -EINVAL;
+	err = line_range_add_line(fname, lineno, lf->lr);
+	if (err < 0 && err != -EEXIST)
+		return err;
 
 	return 0;
 }
@@ -1473,14 +1475,15 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
 static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	find_line_range_by_line(in_die, data);
+	int ret = find_line_range_by_line(in_die, data);
 
 	/*
 	 * We have to check all instances of inlined function, because
 	 * some execution paths can be optimized out depends on the
-	 * function argument of instances
+	 * function argument of instances. However, if an error occurs,
+	 * it should be handled by the caller.
 	 */
-	return 0;
+	return ret < 0 ? ret : 0;
 }
 
 /* Search function definition from function name */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-03-22  9:06 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-03-22  9:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7c144bfbf89d612f0c62b7e71056fb687b068455 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Two oneliner 'perf bench' tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf bench numa: Make no args mean 'run all tests'

Patrick Palka (1):
      perf bench: Fix NULL pointer dereference in "perf bench all"


 tools/perf/bench/numa.c    | 1 +
 tools/perf/builtin-bench.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d4c83c6..97d86d8 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1593,6 +1593,7 @@ static void init_params(struct params *p, const char *name, int argc, const char
 	p->data_rand_walk		= true;
 	p->nr_loops			= -1;
 	p->init_random			= true;
+	p->run_all			= argc == 1;
 }
 
 static int run_bench_numa(const char *name, const char **argv)
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index e47f90c..8a987d2 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -76,7 +76,7 @@ static struct collection collections[] = {
 
 /* Iterate over all benchmarks within a collection: */
 #define for_each_bench(coll, bench) \
-	for (bench = coll->benchmarks; bench->name; bench++)
+	for (bench = coll->benchmarks; bench && bench->name; bench++)
 
 static void dump_benchmarks(struct collection *coll)
 {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-03-16 16:34 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-03-16 16:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b7b4839d93e50adccef29eccb694807cdcb8bee3 perf/x86: Fix leak in uncore_type_init failure paths

Misc smaller fixes.

 Thanks,

	Ingo

------------------>
Ben Hutchings (1):
      perf trace: Decode architecture-specific signal numbers

Dave Jones (1):
      perf/x86: Fix leak in uncore_type_init failure paths

Don Zickus (1):
      perf machine: Use map as success in ip__resolve_ams

Jiri Olsa (1):
      perf symbols: Fix crash in elf_section_by_name


 arch/x86/kernel/cpu/perf_event_intel_uncore.c |  3 ++-
 tools/perf/builtin-trace.c                    | 10 +++++++++-
 tools/perf/util/machine.c                     |  2 +-
 tools/perf/util/symbol-elf.c                  |  6 +++---
 4 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c88f7f4..047f540 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -3334,6 +3334,8 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 	if (!pmus)
 		return -ENOMEM;
 
+	type->pmus = pmus;
+
 	type->unconstrainted = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
 				0, type->num_counters, 0, 0);
@@ -3369,7 +3371,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
-	type->pmus = pmus;
 	return 0;
 fail:
 	uncore_type_exit(type);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6aa6fb6..f954c26 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -825,7 +825,6 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal
 	P_SIGNUM(PIPE);
 	P_SIGNUM(ALRM);
 	P_SIGNUM(TERM);
-	P_SIGNUM(STKFLT);
 	P_SIGNUM(CHLD);
 	P_SIGNUM(CONT);
 	P_SIGNUM(STOP);
@@ -841,6 +840,15 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal
 	P_SIGNUM(IO);
 	P_SIGNUM(PWR);
 	P_SIGNUM(SYS);
+#ifdef SIGEMT
+	P_SIGNUM(EMT);
+#endif
+#ifdef SIGSTKFLT
+	P_SIGNUM(STKFLT);
+#endif
+#ifdef SIGSWI
+	P_SIGNUM(SWI);
+#endif
 	default: break;
 	}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c872991..620a198 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1213,7 +1213,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 		 */
 		thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
 				ip, &al);
-		if (al.sym)
+		if (al.map)
 			goto found;
 	}
 found:
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3e9f336..516d19f 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -151,15 +151,15 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 
 		gelf_getshdr(sec, shp);
 		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-		if (!strcmp(name, str)) {
+		if (str && !strcmp(name, str)) {
 			if (idx)
 				*idx = cnt;
-			break;
+			return sec;
 		}
 		++cnt;
 	}
 
-	return sec;
+	return NULL;
 }
 
 #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-03-02  8:51 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-03-02  8:51 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: af76815a31adc75dd9526230affdd678e65ac59f Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc fixes, most of them on the tooling side.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf tools: fix BFD detection on opensuse

Jiri Olsa (1):
      perf tools: Fix strict alias issue for find_first_bit

Namhyung Kim (2):
      perf annotate: Check availability of annotate when processing samples
      perf symbols: Destroy unused symsrcs

Peter Zijlstra (2):
      perf/x86: Fix event scheduling
      perf: Fix hotplug splat


 arch/x86/kernel/cpu/perf_event.c          |  3 +++
 kernel/events/core.c                      | 12 +++++-----
 tools/perf/builtin-report.c               | 40 ++++++++++++++++++-------------
 tools/perf/builtin-top.c                  |  6 +++--
 tools/perf/config/Makefile                |  2 +-
 tools/perf/config/feature-checks/Makefile |  2 +-
 tools/perf/util/annotate.c                |  9 ++++++-
 tools/perf/util/annotate.h                |  2 ++
 tools/perf/util/include/linux/bitops.h    |  4 +++-
 tools/perf/util/symbol.c                  |  2 ++
 10 files changed, 54 insertions(+), 28 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 895604f..79f9f84 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1192,6 +1192,9 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
 
+			if (i >= cpuc->n_events - cpuc->n_added)
+				--cpuc->n_added;
+
 			if (x86_pmu.put_event_constraints)
 				x86_pmu.put_event_constraints(cpuc, event);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6..fa0b2d4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7856,14 +7856,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 static void __perf_event_exit_context(void *__info)
 {
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
+	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(event);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7887,11 +7887,11 @@ static void perf_event_exit_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3c53ec2..02f985f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -113,14 +113,16 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati
 	if (!he)
 		return -ENOMEM;
 
-	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	if (err)
-		goto out;
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
 
-	mx = he->mem_info;
-	err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-	if (err)
-		goto out;
+		mx = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+		if (err)
+			goto out;
+	}
 
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -164,14 +166,18 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc
 		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
 					1, 1, 0);
 		if (he) {
-			bx = he->branch_info;
-			err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
-			if (err)
-				goto out;
-
-			err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
-			if (err)
-				goto out;
+			if (ui__has_annotation()) {
+				bx = he->branch_info;
+				err = addr_map_symbol__inc_samples(&bx->from,
+								   evsel->idx);
+				if (err)
+					goto out;
+
+				err = addr_map_symbol__inc_samples(&bx->to,
+								   evsel->idx);
+				if (err)
+					goto out;
+			}
 
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -205,7 +211,9 @@ static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evs
 	if (err)
 		goto out;
 
-	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 out:
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 76cd510..5f989a7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -176,7 +176,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 {
 	struct annotation *notes;
 	struct symbol *sym;
-	int err;
+	int err = 0;
 
 	if (he == NULL || he->ms.sym == NULL ||
 	    ((top->sym_filter_entry == NULL ||
@@ -190,7 +190,9 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 		return;
 
 	ip = he->ms.map->map_ip(he->ms.map, ip);
-	err = hist_entry__inc_addr_samples(he, counter, ip);
+
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c48d449..0331ea2 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -478,7 +478,7 @@ else
 endif
 
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd
+  EXTLIBS += -lbfd -lz -liberty
 endif
 
 ifdef NO_DEMANGLE
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 12e5513..523b7bc 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -121,7 +121,7 @@ test-libpython-version.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
 test-libbfd.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
 
 test-liberty.bin:
 	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 469eb67..3aa555f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -8,6 +8,8 @@
  */
 
 #include "util.h"
+#include "ui/ui.h"
+#include "sort.h"
 #include "build-id.h"
 #include "color.h"
 #include "cache.h"
@@ -489,7 +491,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 {
 	struct annotation *notes;
 
-	if (sym == NULL || use_browser != 1 || !sort__has_sym)
+	if (sym == NULL)
 		return 0;
 
 	notes = symbol__annotation(sym);
@@ -1399,3 +1401,8 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize)
 {
 	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
 }
+
+bool ui__has_annotation(void)
+{
+	return use_browser == 1 && sort__has_sym;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index b2aef59..56ad4f5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -151,6 +151,8 @@ void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void disasm__purge(struct list_head *head);
 
+bool ui__has_annotation(void);
+
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines);
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 45cf10a..dadfa7e 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -87,13 +87,15 @@ static __always_inline unsigned long __ffs(unsigned long word)
 	return num;
 }
 
+typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
+
 /*
  * Find the first set bit in a memory region.
  */
 static inline unsigned long
 find_first_bit(const unsigned long *addr, unsigned long size)
 {
-	const unsigned long *p = addr;
+	long_alias_t *p = (long_alias_t *) addr;
 	unsigned long result = 0;
 	unsigned long tmp;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a9d758a..e89afc0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1336,6 +1336,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 			if (syms_ss && runtime_ss)
 				break;
+		} else {
+			symsrc__destroy(ss);
 		}
 
 	}

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-02-22 19:16 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-02-22 19:16 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: a9d3f94ec7708427b9f05a65246d3fd6e287fa51 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc fixlets from all around the place.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf trace: Fix ioctl 'request' beautifier build problems on !(i386 || x86_64) arches

Ben Hutchings (1):
      perf trace: Add fallback definition of EFD_SEMAPHORE

Jiri Olsa (1):
      perf tools: Handle PERF_RECORD_HEADER_EVENT_TYPE properly

Markus Metzger (1):
      perf, nmi: Fix unknown NMI warning

Masami Hiramatsu (1):
      perf probe: Do not add offset twice to uprobe address

Peter Zijlstra (3):
      perf/x86/intel/p6: Add userspace RDPMC quirk for PPro
      perf/x86: Fix Userspace RDPMC switch
      perf/x86: Correctly use FEATURE_PDCM

Stephane Eranian (1):
      perf/x86/uncore: Fix IVT/SNB-EP uncore CBOX NID filter table

Vince Weaver (1):
      perf list: Fix checking for supported events on older kernels


 arch/x86/kernel/cpu/perf_event.c              |  8 +++--
 arch/x86/kernel/cpu/perf_event.h              |  1 +
 arch/x86/kernel/cpu/perf_event_intel.c        | 11 ++----
 arch/x86/kernel/cpu/perf_event_intel_uncore.c | 10 +++++-
 arch/x86/kernel/cpu/perf_event_p6.c           | 48 ++++++++++++++++++---------
 tools/perf/builtin-trace.c                    | 22 ++++++++++++
 tools/perf/util/parse-events.c                | 17 ++++++++--
 tools/perf/util/probe-event.c                 |  2 +-
 tools/perf/util/session.c                     |  6 ++++
 9 files changed, 96 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b886451..895604f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1521,6 +1521,8 @@ static int __init init_hw_perf_events(void)
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
+	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
 	for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
 		quirk->func();
 
@@ -1534,7 +1536,6 @@ static int __init init_hw_perf_events(void)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
 				   0, x86_pmu.num_counters, 0, 0);
 
-	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
 	if (x86_pmu.event_attrs)
@@ -1820,9 +1821,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 	if (ret)
 		return ret;
 
+	if (x86_pmu.attr_rdpmc_broken)
+		return -ENOTSUPP;
+
 	if (!!val != !!x86_pmu.attr_rdpmc) {
 		x86_pmu.attr_rdpmc = !!val;
-		smp_call_function(change_rdpmc, (void *)val, 1);
+		on_each_cpu(change_rdpmc, (void *)val, 1);
 	}
 
 	return count;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index c1a8618..4972c24 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -409,6 +409,7 @@ struct x86_pmu {
 	/*
 	 * sysfs attrs
 	 */
+	int		attr_rdpmc_broken;
 	int		attr_rdpmc;
 	struct attribute **format_attrs;
 	struct attribute **event_attrs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0fa4f24..aa333d9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1361,10 +1361,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
-	if (!status) {
-		intel_pmu_enable_all(0);
-		return handled;
-	}
+	if (!status)
+		goto done;
 
 	loops = 0;
 again:
@@ -2310,10 +2308,7 @@ __init int intel_pmu_init(void)
 	if (version > 1)
 		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
 
-	/*
-	 * v2 and above have a perf capabilities MSR
-	 */
-	if (version > 1) {
+	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
 
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 29c2487..c88f7f4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -501,8 +501,11 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
@@ -1178,10 +1181,15 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index b1e2fe1..7c1a0c0 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -231,31 +231,49 @@ static __initconst const struct x86_pmu p6_pmu = {
 
 };
 
+static __init void p6_pmu_rdpmc_quirk(void)
+{
+	if (boot_cpu_data.x86_mask < 9) {
+		/*
+		 * PPro erratum 26; fixed in stepping 9 and above.
+		 */
+		pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n");
+		x86_pmu.attr_rdpmc_broken = 1;
+		x86_pmu.attr_rdpmc = 0;
+	}
+}
+
 __init int p6_pmu_init(void)
 {
+	x86_pmu = p6_pmu;
+
 	switch (boot_cpu_data.x86_model) {
-	case 1:
-	case 3:  /* Pentium Pro */
-	case 5:
-	case 6:  /* Pentium II */
-	case 7:
-	case 8:
-	case 11: /* Pentium III */
-	case 9:
-	case 13:
-		/* Pentium M */
+	case  1: /* Pentium Pro */
+		x86_add_quirk(p6_pmu_rdpmc_quirk);
+		break;
+
+	case  3: /* Pentium II - Klamath */
+	case  5: /* Pentium II - Deschutes */
+	case  6: /* Pentium II - Mendocino */
 		break;
+
+	case  7: /* Pentium III - Katmai */
+	case  8: /* Pentium III - Coppermine */
+	case 10: /* Pentium III Xeon */
+	case 11: /* Pentium III - Tualatin */
+		break;
+
+	case  9: /* Pentium M - Banias */
+	case 13: /* Pentium M - Dothan */
+		break;
+
 	default:
-		pr_cont("unsupported p6 CPU model %d ",
-			boot_cpu_data.x86_model);
+		pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model);
 		return -ENODEV;
 	}
 
-	x86_pmu = p6_pmu;
-
 	memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
 		sizeof(hw_cache_event_ids));
 
-
 	return 0;
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 896f270..6aa6fb6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -37,6 +37,10 @@
 # define MADV_UNMERGEABLE	13
 #endif
 
+#ifndef EFD_SEMAPHORE
+# define EFD_SEMAPHORE		1
+#endif
+
 struct tp_field {
 	int offset;
 	union {
@@ -279,6 +283,11 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
 
 #define SCA_STRARRAY syscall_arg__scnprintf_strarray
 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches as soon as the ioctl beautifier
+ * 	  gets rewritten to support all arches.
+ */
 static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
 						 struct syscall_arg *arg)
 {
@@ -286,6 +295,7 @@ static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
 }
 
 #define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
+#endif /* defined(__i386__) || defined(__x86_64__) */
 
 static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
 					struct syscall_arg *arg);
@@ -839,6 +849,10 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal
 
 #define SCA_SIGNUM syscall_arg__scnprintf_signum
 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
 #define TCGETS		0x5401
 
 static const char *tioctls[] = {
@@ -860,6 +874,7 @@ static const char *tioctls[] = {
 };
 
 static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
+#endif /* defined(__i386__) || defined(__x86_64__) */
 
 #define STRARRAY(arg, name, array) \
 	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
@@ -941,9 +956,16 @@ static struct syscall_fmt {
 	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
 	{ .name	    = "ioctl",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
 			     [1] = SCA_STRHEXARRAY, /* cmd */
 			     [2] = SCA_HEX, /* arg */ },
 	  .arg_parm	 = { [1] = &strarray__tioctls, /* cmd */ }, },
+#else
+			     [2] = SCA_HEX, /* arg */ }, },
+#endif
 	{ .name	    = "kill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "linkat",	    .errmsg = true,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d248fca..1e15df1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1091,12 +1091,12 @@ int is_valid_tracepoint(const char *event_string)
 static bool is_event_supported(u8 type, unsigned config)
 {
 	bool ret = true;
+	int open_return;
 	struct perf_evsel *evsel;
 	struct perf_event_attr attr = {
 		.type = type,
 		.config = config,
 		.disabled = 1,
-		.exclude_kernel = 1,
 	};
 	struct {
 		struct thread_map map;
@@ -1108,7 +1108,20 @@ static bool is_event_supported(u8 type, unsigned config)
 
 	evsel = perf_evsel__new(&attr);
 	if (evsel) {
-		ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+		open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->attr.exclude_kernel = 1;
+			ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+		}
 		perf_evsel__delete(evsel);
 	}
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a8a9b6c..d8b048c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -336,8 +336,8 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 		return ret;
 
 	for (i = 0; i < ntevs && ret >= 0; i++) {
+		/* point.address is the addres of point.symbol + point.offset */
 		offset = tevs[i].point.address - stext;
-		offset += tevs[i].point.offset;
 		tevs[i].point.offset = 0;
 		zfree(&tevs[i].point.symbol);
 		ret = e_snprintf(buf, 32, "0x%lx", offset);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b39a48..5da6ce7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1008,6 +1008,12 @@ static int perf_session__process_user_event(struct perf_session *session, union
 		if (err == 0)
 			perf_session__set_id_hdr_size(session);
 		return err;
+	case PERF_RECORD_HEADER_EVENT_TYPE:
+		/*
+		 * Depreceated, but we need to handle it for sake
+		 * of old data files create in pipe mode.
+		 */
+		return 0;
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-02-09  8:01 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-02-09  8:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 2737fce8bc8dea2852289df29b4f92e6a7fb7c91 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling fixes, mostly related to the KASLR fallout, but also other 
fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (9):
      perf symbols: Fix symbol annotation for relocated kernel
      perf tools: Add kallsyms__get_function_start()
      perf machine: Add machine__get_kallsyms_filename()
      perf machine: Set up ref_reloc_sym in machine__create_kernel_maps()
      perf record: Get ref_reloc_sym from kernel map
      perf symbols: Prevent the use of kcore if the kernel has moved
      perf tests: No need to set up ref_reloc_sym
      perf tools: Adjust kallsyms for relocated kernel
      perf buildid-cache: Check relocation when checking for existing kcore

Avi Kivity (1):
      perf tools: Demangle kernel and kernel module symbols too

Baruch Siach (1):
      perf/doc: Remove mention of non-existent set_perf_event_pending() from design.txt

Francesco Fusco (1):
      perf tools: Fix include for non x86 architectures

Peter Zijlstra (1):
      perf tools: Fix AAAAARGH64 memory barriers


 tools/perf/builtin-buildid-cache.c  | 33 ++++++++++++++++---
 tools/perf/builtin-record.c         | 10 ++----
 tools/perf/design.txt               |  1 -
 tools/perf/perf.h                   |  4 +--
 tools/perf/tests/vmlinux-kallsyms.c | 10 ------
 tools/perf/util/event.c             | 36 ++++++++++----------
 tools/perf/util/event.h             |  6 ++--
 tools/perf/util/include/asm/hash.h  |  6 ++++
 tools/perf/util/machine.c           | 42 +++++++++++++++++++-----
 tools/perf/util/machine.h           |  2 ++
 tools/perf/util/map.c               |  5 +--
 tools/perf/util/map.h               |  1 +
 tools/perf/util/symbol-elf.c        |  4 ++-
 tools/perf/util/symbol.c            | 65 +++++++++++++++++++++++++++++++++----
 14 files changed, 162 insertions(+), 63 deletions(-)
 create mode 100644 tools/perf/util/include/asm/hash.h

diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index cfede86..b22dbb1 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -63,11 +63,35 @@ static int build_id_cache__kcore_dir(char *dir, size_t sz)
 	return 0;
 }
 
+static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
+{
+	char from[PATH_MAX];
+	char to[PATH_MAX];
+	const char *name;
+	u64 addr1 = 0, addr2 = 0;
+	int i;
+
+	scnprintf(from, sizeof(from), "%s/kallsyms", from_dir);
+	scnprintf(to, sizeof(to), "%s/kallsyms", to_dir);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr1 = kallsyms__get_function_start(from, name);
+		if (addr1)
+			break;
+	}
+
+	if (name)
+		addr2 = kallsyms__get_function_start(to, name);
+
+	return addr1 == addr2;
+}
+
 static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 					  size_t to_dir_sz)
 {
 	char from[PATH_MAX];
 	char to[PATH_MAX];
+	char to_subdir[PATH_MAX];
 	struct dirent *dent;
 	int ret = -1;
 	DIR *d;
@@ -86,10 +110,11 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 			continue;
 		scnprintf(to, sizeof(to), "%s/%s/modules", to_dir,
 			  dent->d_name);
-		if (!compare_proc_modules(from, to)) {
-			scnprintf(to, sizeof(to), "%s/%s", to_dir,
-				  dent->d_name);
-			strlcpy(to_dir, to, to_dir_sz);
+		scnprintf(to_subdir, sizeof(to_subdir), "%s/%s",
+			  to_dir, dent->d_name);
+		if (!compare_proc_modules(from, to) &&
+		    same_kallsyms_reloc(from_dir, to_subdir)) {
+			strlcpy(to_dir, to_subdir, to_dir_sz);
 			ret = 0;
 			break;
 		}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3c394bf..af47531 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -287,10 +287,7 @@ static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
 	 * have no _text sometimes.
 	 */
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine, "_text");
-	if (err < 0)
-		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-							 machine, "_stext");
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
@@ -457,10 +454,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine, "_text");
-	if (err < 0)
-		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-							 machine, "_stext");
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record kernel reference relocation symbol\n"
 		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index 67e5d0c..63a0e6f 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -454,7 +454,6 @@ So to start with, in order to add HAVE_PERF_EVENTS to your Kconfig, you
 will need at least this:
 	- asm/perf_event.h - a basic stub will suffice at first
 	- support for atomic64 types (and associated helper functions)
-	- set_perf_event_pending() implemented
 
 If your architecture does have hardware capabilities, you can override the
 weak stub hw_perf_event_init() to register hardware counters.
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 7daa806..e84fa26 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -100,8 +100,8 @@
 
 #ifdef __aarch64__
 #define mb()		asm volatile("dmb ish" ::: "memory")
-#define wmb()		asm volatile("dmb ishld" ::: "memory")
-#define rmb()		asm volatile("dmb ishst" ::: "memory")
+#define wmb()		asm volatile("dmb ishst" ::: "memory")
+#define rmb()		asm volatile("dmb ishld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 2bd13ed..3d90880 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -26,7 +26,6 @@ int test__vmlinux_matches_kallsyms(void)
 	struct map *kallsyms_map, *vmlinux_map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
-	struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
 	u64 mem_start, mem_end;
 
 	/*
@@ -70,14 +69,6 @@ int test__vmlinux_matches_kallsyms(void)
 	 */
 	kallsyms_map = machine__kernel_map(&kallsyms, type);
 
-	sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
-	if (sym == NULL) {
-		pr_debug("dso__find_symbol_by_name ");
-		goto out;
-	}
-
-	ref_reloc_sym.addr = UM(sym->start);
-
 	/*
 	 * Step 5:
 	 *
@@ -89,7 +80,6 @@ int test__vmlinux_matches_kallsyms(void)
 	}
 
 	vmlinux_map = machine__kernel_map(&vmlinux, type);
-	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
 
 	/*
 	 * Step 6:
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1fc1c2f..b0f3ca8 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -470,23 +470,32 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	return 1;
 }
 
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
+		return 0;
+
+	return args.start;
+}
+
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
-				       struct machine *machine,
-				       const char *symbol_name)
+				       struct machine *machine)
 {
 	size_t size;
-	const char *filename, *mmap_name;
-	char path[PATH_MAX];
+	const char *mmap_name;
 	char name_buff[PATH_MAX];
 	struct map *map;
+	struct kmap *kmap;
 	int err;
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
-	struct process_symbol_args args = { .name = symbol_name, };
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -502,30 +511,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		 * see kernel/perf_event.c __perf_event_mmap
 		 */
 		event->header.misc = PERF_RECORD_MISC_KERNEL;
-		filename = "/proc/kallsyms";
 	} else {
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-		if (machine__is_default_guest(machine))
-			filename = (char *) symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
-	}
-
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
-		free(event);
-		return -ENOENT;
 	}
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
+	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", mmap_name, symbol_name) + 1;
+			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
 	size = PERF_ALIGN(size, sizeof(u64));
 	event->mmap.header.type = PERF_RECORD_MMAP;
 	event->mmap.header.size = (sizeof(event->mmap) -
 			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
-	event->mmap.pgoff = args.start;
+	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
 	event->mmap.start = map->start;
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index faf6e21..851fa06 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -214,8 +214,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 				   struct machine *machine, bool mmap_data);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
-				       struct machine *machine,
-				       const char *symbol_name);
+				       struct machine *machine);
 
 int perf_event__synthesize_modules(struct perf_tool *tool,
 				   perf_event__handler_t process,
@@ -279,4 +278,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name);
+
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
new file mode 100644
index 0000000..d82b170b
--- /dev/null
+++ b/tools/perf/util/include/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ded7459..c872991 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -496,19 +496,22 @@ static int symbol__in_kernel(void *arg, const char *name,
 	return 1;
 }
 
+static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+					   size_t bufsz)
+{
+	if (machine__is_default_guest(machine))
+		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
+	else
+		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
+}
+
 /* Figure out the start address of kernel map from /proc/kallsyms */
 static u64 machine__get_kernel_start_addr(struct machine *machine)
 {
-	const char *filename;
-	char path[PATH_MAX];
+	char filename[PATH_MAX];
 	struct process_args args;
 
-	if (machine__is_default_guest(machine))
-		filename = (char *)symbol_conf.default_guest_kallsyms;
-	else {
-		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-		filename = path;
-	}
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return 0;
@@ -829,9 +832,25 @@ static int machine__create_modules(struct machine *machine)
 	return 0;
 }
 
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
+	char filename[PATH_MAX];
+	const char *name;
+	u64 addr = 0;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
+	if (!addr)
+		return -1;
 
 	if (kernel == NULL ||
 	    __machine__create_kernel_maps(machine, kernel) < 0)
@@ -850,6 +869,13 @@ int machine__create_kernel_maps(struct machine *machine)
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
 	map_groups__fixup_end(&machine->kmaps);
+
+	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
+					     addr)) {
+		machine__destroy_kernel_maps(machine);
+		return -1;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 4771330..f77e91e 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -18,6 +18,8 @@ union perf_event;
 #define	HOST_KERNEL_ID			(-1)
 #define	DEFAULT_GUEST_KERNEL_ID		(0)
 
+extern const char *ref_reloc_sym_names[];
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 3b97513..39cd2d0 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -39,6 +39,7 @@ void map__init(struct map *map, enum map_type type,
 	map->start    = start;
 	map->end      = end;
 	map->pgoff    = pgoff;
+	map->reloc    = 0;
 	map->dso      = dso;
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
@@ -288,7 +289,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
 	if (map->dso->rel)
 		return rip - map->pgoff;
 
-	return map->unmap_ip(map, rip);
+	return map->unmap_ip(map, rip) - map->reloc;
 }
 
 /**
@@ -311,7 +312,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	if (map->dso->rel)
 		return map->unmap_ip(map, ip + map->pgoff);
 
-	return ip;
+	return ip + map->reloc;
 }
 
 void map_groups__init(struct map_groups *mg)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 18068c6..257e513 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -36,6 +36,7 @@ struct map {
 	bool			erange_warned;
 	u32			priv;
 	u64			pgoff;
+	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
 	u64			ino;      /* only valid for MMAP2 record */
 	u64			ino_generation;/* only valid for MMAP2 record */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 7594567..3e9f336 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -751,6 +751,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			if (strcmp(elf_name, kmap->ref_reloc_sym->name))
 				continue;
 			kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+			map->reloc = kmap->ref_reloc_sym->addr -
+				     kmap->ref_reloc_sym->unrelocated_addr;
 			break;
 		}
 	}
@@ -922,6 +924,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				  (u64)shdr.sh_offset);
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
+new_symbol:
 		/*
 		 * We need to figure out if the object was created from C++ sources
 		 * DWARF DW_compile_unit has this, but we don't always have access
@@ -933,7 +936,6 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
-new_symbol:
 		f = symbol__new(sym.st_value, sym.st_size,
 				GELF_ST_BIND(sym.st_info), elf_name);
 		free(demangled);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 39ce9ad..a9d758a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -627,7 +627,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *dso, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
@@ -692,6 +692,12 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map,
 			char dso_name[PATH_MAX];
 			struct dso *ndso;
 
+			if (delta) {
+				/* Kernel was relocated at boot time */
+				pos->start -= delta;
+				pos->end -= delta;
+			}
+
 			if (count == 0) {
 				curr_map = map;
 				goto filter_symbol;
@@ -721,6 +727,10 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map,
 			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
 			map_groups__insert(kmaps, curr_map);
 			++kernel_range;
+		} else if (delta) {
+			/* Kernel was relocated at boot time */
+			pos->start -= delta;
+			pos->end -= delta;
 		}
 filter_symbol:
 		if (filter && filter(curr_map, pos)) {
@@ -976,6 +986,23 @@ static int validate_kcore_modules(const char *kallsyms_filename,
 	return 0;
 }
 
+static int validate_kcore_addresses(const char *kallsyms_filename,
+				    struct map *map)
+{
+	struct kmap *kmap = map__kmap(map);
+
+	if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) {
+		u64 start;
+
+		start = kallsyms__get_function_start(kallsyms_filename,
+						     kmap->ref_reloc_sym->name);
+		if (start != kmap->ref_reloc_sym->addr)
+			return -EINVAL;
+	}
+
+	return validate_kcore_modules(kallsyms_filename, map);
+}
+
 struct kcore_mapfn_data {
 	struct dso *dso;
 	enum map_type type;
@@ -1019,8 +1046,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 					     kallsyms_filename))
 		return -EINVAL;
 
-	/* All modules must be present at their original addresses */
-	if (validate_kcore_modules(kallsyms_filename, map))
+	/* Modules and kernel must be present at their original addresses */
+	if (validate_kcore_addresses(kallsyms_filename, map))
 		return -EINVAL;
 
 	md.dso = dso;
@@ -1113,15 +1140,41 @@ out_err:
 	return -EINVAL;
 }
 
+/*
+ * If the kernel is relocated at boot time, kallsyms won't match.  Compute the
+ * delta based on the relocation reference symbol.
+ */
+static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+{
+	struct kmap *kmap = map__kmap(map);
+	u64 addr;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
+		return 0;
+
+	addr = kallsyms__get_function_start(filename,
+					    kmap->ref_reloc_sym->name);
+	if (!addr)
+		return -1;
+
+	*delta = addr - kmap->ref_reloc_sym->addr;
+	return 0;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
+	u64 delta = 0;
+
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return -1;
 
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
+	if (kallsyms__delta(map, filename, &delta))
+		return -1;
+
 	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
 
@@ -1133,7 +1186,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (!dso__load_kcore(dso, map, filename))
 		return dso__split_kallsyms_for_kcore(dso, map, filter);
 	else
-		return dso__split_kallsyms(dso, map, filter);
+		return dso__split_kallsyms(dso, map, delta, filter);
 }
 
 static int dso__load_perf_map(struct dso *dso, struct map *map,
@@ -1424,7 +1477,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 			continue;
 		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
 			  "%s/%s/kallsyms", dir, dent->d_name);
-		if (!validate_kcore_modules(kallsyms_filename, map)) {
+		if (!validate_kcore_addresses(kallsyms_filename, map)) {
 			strlcpy(dir, kallsyms_filename, dir_sz);
 			ret = 0;
 			break;
@@ -1479,7 +1532,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 		if (fd != -1) {
 			close(fd);
 			/* If module maps match go with /proc/kallsyms */
-			if (!validate_kcore_modules("/proc/kallsyms", map))
+			if (!validate_kcore_addresses("/proc/kallsyms", map))
 				goto proc_kallsyms;
 		}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-01-25  7:30 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-01-25  7:30 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 993e5ee67a90c7b6a5dbb61b9c31df2955afff46 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

A handful of tooling fixes.

 Thanks,

	Ingo

------------------>
Alan Cox (1):
      perf tools: Ensure sscanf does not overrun the "mem" field

Baruch Siach (1):
      perf tools: Add support for the xtensa architecture

Josh Boyer (1):
      perf tools: Fix traceevent plugin path definitions

Masami Hiramatsu (1):
      perf symbols: Load map before using map->map_ip()

Namhyung Kim (1):
      perf symbols: Fix JIT symbol resolution on heap

Stanislav Fomichev (2):
      perf timechart: Fix wrong SVG height
      perf session: Free cpu_map in perf_session__cpu_bitmap

Stephane Eranian (3):
      perf stat: fix NULL pointer reference bug with event unit
      perf evsel: Remove duplicate member zeroing after free
      perf stat: Fix memory corruption of xyarray when cpumask is used


 tools/lib/traceevent/Makefile  |  2 +-
 tools/perf/builtin-timechart.c |  3 +++
 tools/perf/config/Makefile     |  2 +-
 tools/perf/perf.h              |  7 +++++++
 tools/perf/util/evlist.c       |  7 +++++--
 tools/perf/util/evsel.c        |  1 -
 tools/perf/util/header.c       |  2 +-
 tools/perf/util/map.c          |  7 ++++---
 tools/perf/util/parse-events.c |  2 +-
 tools/perf/util/pmu.c          | 24 ++++++++++++++++++++----
 tools/perf/util/pmu.h          |  2 +-
 tools/perf/util/session.c      | 10 +++++++---
 12 files changed, 51 insertions(+), 18 deletions(-)

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 56d52a3..005c9cc 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -63,7 +63,7 @@ endif
 endif
 
 ifeq ($(set_plugin_dir),1)
-PLUGIN_DIR = -DPLUGIN_DIR="$(DESTDIR)/$(plugin_dir)"
+PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
 PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
 endif
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 652af0b..25526d6 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1045,6 +1045,9 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 		thresh /= 10;
 	} while (!process_filter && thresh && count < tchart->proc_num);
 
+	if (!tchart->proc_num)
+		count = 0;
+
 	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
 	svg_time_grid();
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index d604e50..c48d449 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -600,5 +600,5 @@ perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 # Otherwise we install plugins into the global $(libdir).
 ifdef DESTDIR
 plugindir=$(libdir)/traceevent/plugins
-plugindir_SQ= $(subst ','\'',$(prefix)/$(plugindir))
+plugindir_SQ= $(subst ','\'',$(plugindir))
 endif
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 3c2f213..7daa806 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -132,6 +132,13 @@
 #define CPUINFO_PROC	"CPU"
 #endif
 
+#ifdef __xtensa__
+#define mb()		asm volatile("memw" ::: "memory")
+#define wmb()		asm volatile("memw" ::: "memory")
+#define rmb()		asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"core ID"
+#endif
+
 #define barrier() asm volatile ("" ::: "memory")
 
 #ifndef cpu_relax
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 40bd2c0..59ef280 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1003,9 +1003,12 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int ncpus = cpu_map__nr(evlist->cpus);
 	int nthreads = thread_map__nr(evlist->threads);
+	int n;
 
-	evlist__for_each_reverse(evlist, evsel)
-		perf_evsel__close(evsel, ncpus, nthreads);
+	evlist__for_each_reverse(evlist, evsel) {
+		n = evsel->cpus ? evsel->cpus->nr : ncpus;
+		perf_evsel__close(evsel, n, nthreads);
+	}
 }
 
 int perf_evlist__open(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 22e18a2..55407c5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1081,7 +1081,6 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 	perf_evsel__close_fd(evsel, ncpus, nthreads);
 	perf_evsel__free_fd(evsel);
-	evsel->fd = NULL;
 }
 
 static struct {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index bb3e0ed..893f8e2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -930,7 +930,7 @@ static int write_topo_node(int fd, int node)
 		/* skip over invalid lines */
 		if (!strchr(buf, ':'))
 			continue;
-		if (sscanf(buf, "%*s %*d %s %"PRIu64, field, &mem) != 2)
+		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
 			goto done;
 		if (!strcmp(field, "MemTotal:"))
 			mem_total = mem;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 9b9bd71..3b97513 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -69,7 +69,7 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		map->ino = ino;
 		map->ino_generation = ino_gen;
 
-		if (anon) {
+		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
 		}
@@ -93,7 +93,7 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 			 * functions still return NULL, and we avoid the
 			 * unnecessary map__load warning.
 			 */
-			if (no_dso)
+			if (type != MAP__FUNCTION)
 				dso__set_loaded(dso, map->type);
 		}
 	}
@@ -386,7 +386,8 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 {
 	struct map *map = map_groups__find(mg, type, addr);
 
-	if (map != NULL) {
+	/* Ensure map is loaded before using map->map_ip */
+	if (map != NULL && map__load(map, filter) >= 0) {
 		if (mapp != NULL)
 			*mapp = map;
 		return map__find_symbol(map, map->map_ip(map, addr), filter);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a7f1b6a..d248fca 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -635,7 +635,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	struct perf_event_attr attr;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
-	char *unit;
+	const char *unit;
 	double scale;
 
 	pmu = perf_pmu__find(name);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d9cab4d..b752ecb 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -105,7 +105,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
-	char *lc;
+	const char *lc;
 
 	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -609,7 +609,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 
 
 static int check_unit_scale(struct perf_pmu_alias *alias,
-			    char **unit, double *scale)
+			    const char **unit, double *scale)
 {
 	/*
 	 * Only one term in event definition can
@@ -634,14 +634,18 @@ static int check_unit_scale(struct perf_pmu_alias *alias,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  char **unit, double *scale)
+			  const char **unit, double *scale)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	/*
+	 * Mark unit and scale as not set
+	 * (different from default values, see below)
+	 */
 	*unit   = NULL;
-	*scale  = 0;
+	*scale  = 0.0;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -658,6 +662,18 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		list_del(&term->list);
 		free(term);
 	}
+
+	/*
+	 * if no unit or scale foundin aliases, then
+	 * set defaults as for evsel
+	 * unit cannot left to NULL
+	 */
+	if (*unit == NULL)
+		*unit   = "";
+
+	if (*scale == 0.0)
+		*scale  = 1.0;
+
 	return 0;
 }
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 9183380..8b64125 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -29,7 +29,7 @@ int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  char **unit, double *scale);
+			  const char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				  struct list_head *head_terms);
 int perf_pmu_wrap(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7acc03e..0b39a48 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1573,7 +1573,7 @@ next:
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap)
 {
-	int i;
+	int i, err = -1;
 	struct cpu_map *map;
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
@@ -1602,13 +1602,17 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 		if (cpu >= MAX_NR_CPUS) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu);
-			return -1;
+			goto out_delete_map;
 		}
 
 		set_bit(cpu, cpu_bitmap);
 	}
 
-	return 0;
+	err = 0;
+
+out_delete_map:
+	cpu_map__delete(map);
+	return err;
 }
 
 void perf_session__fprintf_info(struct perf_session *session, FILE *fp,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2014-01-19 12:08 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2014-01-19 12:08 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	H. Peter Anvin, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: bee09ed91cacdbffdbcd3b05de8409c77ec9fcd6 perf/x86/amd/ibs: Fix waking up from S3 for AMD family 10h

It contains:

 - an s2ram related fix on AMD systems

 - a perf fault handling bug that is relatively old but which has
   become much easier to trigger in v3.13 after commit e00b12e64be9.

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      x86, mm, perf: Allow recursive faults from interrupts

Robert Richter (1):
      perf/x86/amd/ibs: Fix waking up from S3 for AMD family 10h


 arch/x86/kernel/cpu/perf_event_amd_ibs.c | 53 +++++++++++++++++++++++++++-----
 arch/x86/mm/fault.c                      | 18 +++++++++++
 2 files changed, 63 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index e09f0bf..4b8e4d3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/ptrace.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/apic.h>
 
@@ -816,6 +817,18 @@ out:
 	return ret;
 }
 
+static void ibs_eilvt_setup(void)
+{
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+}
+
 static inline int get_ibs_lvt_offset(void)
 {
 	u64 val;
@@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy)
 		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
 }
 
+#ifdef CONFIG_PM
+
+static int perf_ibs_suspend(void)
+{
+	clear_APIC_ibs(NULL);
+	return 0;
+}
+
+static void perf_ibs_resume(void)
+{
+	ibs_eilvt_setup();
+	setup_APIC_ibs(NULL);
+}
+
+static struct syscore_ops perf_ibs_syscore_ops = {
+	.resume		= perf_ibs_resume,
+	.suspend	= perf_ibs_suspend,
+};
+
+static void perf_ibs_pm_init(void)
+{
+	register_syscore_ops(&perf_ibs_syscore_ops);
+}
+
+#else
+
+static inline void perf_ibs_pm_init(void) { }
+
+#endif
+
 static int
 perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
@@ -877,18 +920,12 @@ static __init int amd_ibs_init(void)
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	/*
-	 * Force LVT offset assignment for family 10h: The offsets are
-	 * not assigned by the BIOS for this family, so the OS is
-	 * responsible for doing it. If the OS assignment fails, fall
-	 * back to BIOS settings and try to setup this.
-	 */
-	if (boot_cpu_data.x86 == 0x10)
-		force_ibs_eilvt_setup();
+	ibs_eilvt_setup();
 
 	if (!ibs_eilvt_valid())
 		goto out;
 
+	perf_ibs_pm_init();
 	get_online_cpus();
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ff85bb..9d591c8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -641,6 +641,20 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs)) {
+		/*
+		 * Any interrupt that takes a fault gets the fixup. This makes
+		 * the below recursive fault logic only apply to a faults from
+		 * task context.
+		 */
+		if (in_interrupt())
+			return;
+
+		/*
+		 * Per the above we're !in_interrupt(), aka. task context.
+		 *
+		 * In this case we need to make sure we're not recursively
+		 * faulting through the emulate_vsyscall() logic.
+		 */
 		if (current_thread_info()->sig_on_uaccess_error && signal) {
 			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
@@ -649,6 +663,10 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address, tsk, 0);
 		}
+
+		/*
+		 * Barring that, we can do the fixup and be happy.
+		 */
 		return;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-12-19 16:52 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-12-19 16:52 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, H. Peter Anvin,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 189b84fb54490ae24111124346a8e63f8e019385 perf: Document the new transaction sample type

An ABI documentation fix, and a mixed-PMU perf-info-corruption fix.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf: Disable all pmus on unthrottling and rescheduling

Vince Weaver (1):
      perf: Document the new transaction sample type


 include/uapi/linux/perf_event.h |  1 +
 kernel/events/core.c            | 21 ++++++++++++++++++---
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e1802d6..959d454 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -679,6 +679,7 @@ enum perf_event_type {
 	 *
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72348dc..f574401 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1396,6 +1396,8 @@ event_sched_out(struct perf_event *event,
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return;
 
+	perf_pmu_disable(event->pmu);
+
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -1412,6 +1414,8 @@ event_sched_out(struct perf_event *event,
 		ctx->nr_freq--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
+
+	perf_pmu_enable(event->pmu);
 }
 
 static void
@@ -1652,6 +1656,7 @@ event_sched_in(struct perf_event *event,
 		 struct perf_event_context *ctx)
 {
 	u64 tstamp = perf_event_time(event);
+	int ret = 0;
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
@@ -1674,10 +1679,13 @@ event_sched_in(struct perf_event *event,
 	 */
 	smp_wmb();
 
+	perf_pmu_disable(event->pmu);
+
 	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
-		return -EAGAIN;
+		ret = -EAGAIN;
+		goto out;
 	}
 
 	event->tstamp_running += tstamp - event->tstamp_stopped;
@@ -1693,7 +1701,10 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
-	return 0;
+out:
+	perf_pmu_enable(event->pmu);
+
+	return ret;
 }
 
 static int
@@ -2743,6 +2754,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		perf_pmu_disable(event->pmu);
+
 		hwc = &event->hw;
 
 		if (hwc->interrupts == MAX_INTERRUPTS) {
@@ -2752,7 +2765,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
-			continue;
+			goto next;
 
 		/*
 		 * stop the event and update event->count
@@ -2774,6 +2787,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 			perf_adjust_period(event, period, delta, false);
 
 		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
+	next:
+		perf_pmu_enable(event->pmu);
 	}
 
 	perf_pmu_enable(ctx->pmu);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-12-02 14:39 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-12-02 14:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, H. Peter Anvin

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e98a6e59dff885eb387163b1a7abe019a44ba90b Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc kernel and tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools lib traceevent: Fix conversion of pointer to integer of different size

Frederic Weisbecker (1):
      perf tools: Tag thread comm as overriden

Namhyung Kim (2):
      perf header: Fix bogus group name
      perf header: Fix possible memory leaks in process_group_desc()

Peter Zijlstra (2):
      ftrace, perf: Avoid infinite event generation loop
      perf: Remove fragile swevent hlist optimization

Steven Rostedt (1):
      tools lib traceevent: Fix use of multiple options in processing field

Vince Weaver (1):
      perf/trace: Properly use u64 to hold event_id


 arch/x86/include/asm/trace/irq_vectors.h | 11 +++++++++++
 include/linux/ftrace_event.h             | 16 ++++++++++++++++
 include/linux/tracepoint.h               |  4 ++++
 include/trace/ftrace.h                   |  7 +++++++
 kernel/events/core.c                     |  8 --------
 kernel/trace/trace_event_perf.c          |  8 +++++++-
 tools/lib/traceevent/event-parse.c       | 25 ++++++++++++++++++++++---
 tools/perf/util/header.c                 |  6 ++++--
 tools/perf/util/thread.c                 | 11 +++++------
 9 files changed, 76 insertions(+), 20 deletions(-)

diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 2874df2..4cab890 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -72,6 +72,17 @@ DEFINE_IRQ_VECTOR_EVENT(x86_platform_ipi);
 DEFINE_IRQ_VECTOR_EVENT(irq_work);
 
 /*
+ * We must dis-allow sampling irq_work_exit() because perf event sampling
+ * itself can cause irq_work, which would lead to an infinite loop;
+ *
+ *  1) irq_work_exit happens
+ *  2) generates perf sample
+ *  3) generates irq_work
+ *  4) goto 1
+ */
+TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0);
+
+/*
  * call_function - called when entering/exiting a call function interrupt
  * vector handler
  */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 9abbe63..8c9b7a1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -248,6 +248,9 @@ struct ftrace_event_call {
 #ifdef CONFIG_PERF_EVENTS
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
+
+	int	(*perf_perm)(struct ftrace_event_call *,
+			     struct perf_event *);
 #endif
 };
 
@@ -317,6 +320,19 @@ struct ftrace_event_file {
 	}								\
 	early_initcall(trace_init_flags_##name);
 
+#define __TRACE_EVENT_PERF_PERM(name, expr...)				\
+	static int perf_perm_##name(struct ftrace_event_call *tp_event, \
+				    struct perf_event *p_event)		\
+	{								\
+		return ({ expr; });					\
+	}								\
+	static int __init trace_init_perf_perm_##name(void)		\
+	{								\
+		event_##name.perf_perm = &perf_perm_##name;		\
+		return 0;						\
+	}								\
+	early_initcall(trace_init_perf_perm_##name);
+
 #define PERF_MAX_TRACE_SIZE	2048
 
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index ebeab36..f16dc0a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -267,6 +267,8 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define TRACE_EVENT_FLAGS(event, flag)
 
+#define TRACE_EVENT_PERF_PERM(event, expr...)
+
 #endif /* DECLARE_TRACE */
 
 #ifndef TRACE_EVENT
@@ -399,4 +401,6 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define TRACE_EVENT_FLAGS(event, flag)
 
+#define TRACE_EVENT_PERF_PERM(event, expr...)
+
 #endif /* ifdef TRACE_EVENT (see note above) */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 52594b2..6b852f6 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -90,6 +90,10 @@
 #define TRACE_EVENT_FLAGS(name, value)					\
 	__TRACE_EVENT_FLAGS(name, value)
 
+#undef TRACE_EVENT_PERF_PERM
+#define TRACE_EVENT_PERF_PERM(name, expr...)				\
+	__TRACE_EVENT_PERF_PERM(name, expr)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 
@@ -140,6 +144,9 @@
 #undef TRACE_EVENT_FLAGS
 #define TRACE_EVENT_FLAGS(event, flag)
 
+#undef TRACE_EVENT_PERF_PERM
+#define TRACE_EVENT_PERF_PERM(event, expr...)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d724e77..72348dc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5680,11 +5680,6 @@ static void swevent_hlist_put(struct perf_event *event)
 {
 	int cpu;
 
-	if (event->cpu != -1) {
-		swevent_hlist_put_cpu(event, event->cpu);
-		return;
-	}
-
 	for_each_possible_cpu(cpu)
 		swevent_hlist_put_cpu(event, cpu);
 }
@@ -5718,9 +5713,6 @@ static int swevent_hlist_get(struct perf_event *event)
 	int err;
 	int cpu, failed_cpu;
 
-	if (event->cpu != -1)
-		return swevent_hlist_get_cpu(event, event->cpu);
-
 	get_online_cpus();
 	for_each_possible_cpu(cpu) {
 		err = swevent_hlist_get_cpu(event, cpu);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 78e27e3..e854f42 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,12 @@ static int	total_ref_count;
 static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	if (tp_event->perf_perm) {
+		int ret = tp_event->perf_perm(tp_event, p_event);
+		if (ret)
+			return ret;
+	}
+
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event) &&
 	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
@@ -173,7 +179,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 int perf_trace_init(struct perf_event *p_event)
 {
 	struct ftrace_event_call *tp_event;
-	int event_id = p_event->attr.config;
+	u64 event_id = p_event->attr.config;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 0362d57..217c82e 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1606,6 +1606,24 @@ process_arg(struct event_format *event, struct print_arg *arg, char **tok)
 static enum event_type
 process_op(struct event_format *event, struct print_arg *arg, char **tok);
 
+/*
+ * For __print_symbolic() and __print_flags, we need to completely
+ * evaluate the first argument, which defines what to print next.
+ */
+static enum event_type
+process_field_arg(struct event_format *event, struct print_arg *arg, char **tok)
+{
+	enum event_type type;
+
+	type = process_arg(event, arg, tok);
+
+	while (type == EVENT_OP) {
+		type = process_op(event, arg, tok);
+	}
+
+	return type;
+}
+
 static enum event_type
 process_cond(struct event_format *event, struct print_arg *top, char **tok)
 {
@@ -2371,7 +2389,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 		goto out_free;
 	}
 
-	type = process_arg(event, field, &token);
+	type = process_field_arg(event, field, &token);
 
 	/* Handle operations in the first argument */
 	while (type == EVENT_OP)
@@ -2424,7 +2442,8 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 		goto out_free;
 	}
 
-	type = process_arg(event, field, &token);
+	type = process_field_arg(event, field, &token);
+
 	if (test_type_token(type, token, EVENT_DELIM, ","))
 		goto out_free_field;
 
@@ -3446,7 +3465,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		 * is in the bottom half of the 32 bit field.
 		 */
 		offset &= 0xffff;
-		val = (unsigned long long)(data + offset);
+		val = (unsigned long long)((unsigned long)data + offset);
 		break;
 	default: /* not sure what to do there */
 		return 0;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 369c036..1cd0357 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2078,8 +2078,10 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 		if (evsel->idx == (int) desc[i].leader_idx) {
 			evsel->leader = evsel;
 			/* {anon_group} is a dummy name */
-			if (strcmp(desc[i].name, "{anon_group}"))
+			if (strcmp(desc[i].name, "{anon_group}")) {
 				evsel->group_name = desc[i].name;
+				desc[i].name = NULL;
+			}
 			evsel->nr_members = desc[i].nr_members;
 
 			if (i >= nr_groups || nr > 0) {
@@ -2105,7 +2107,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 
 	ret = 0;
 out_free:
-	while ((int) --i >= 0)
+	for (i = 0; i < nr_groups; i++)
 		free(desc[i].name);
 	free(desc);
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index cd8e2f5..49eaf1d 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -70,14 +70,13 @@ int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
 	/* Override latest entry if it had no specific time coverage */
 	if (!curr->start) {
 		comm__override(curr, str, timestamp);
-		return 0;
+	} else {
+		new = comm__new(str, timestamp);
+		if (!new)
+			return -ENOMEM;
+		list_add(&new->list, &thread->comm_list);
 	}
 
-	new = comm__new(str, timestamp);
-	if (!new)
-		return -ENOMEM;
-
-	list_add(&new->list, &thread->comm_list);
 	thread->comm_set = true;
 
 	return 0;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-11-15 19:46 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-11-15 19:46 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, H. Peter Anvin, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 89b4be142bf2491a94af325f5206fc2f2aa18960 Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling changes only: it includes the ARM tooling fixlets, various 
other fixes, smaller updates, minor cleanups.

 Thanks,

	Ingo

------------------>

Adrian Hunter (1):
      perf record: Add an option to force per-cpu mmaps

Arnaldo Carvalho de Melo (4):
      perf tools: Use perf_evlist__{first,last}, perf_evsel__next
      perf evsel: Introduce perf_evsel__prev() method
      perf symbols: Limit max callchain using max_stack on DWARF unwinding too
      perf ui browser: Fix segfault caused by off by one handling END key

Azat Khuzhin (1):
      perf probe: Add '--demangle'/'--no-demangle'

Davidlohr Bueso (1):
      perf tools: Remove trivial extra semincolon

Don Zickus (1):
      perf tools: Synthesize anon MMAP records again

Ingo Molnar (5):
      Merge branch 'linus' into perf/urgent
      tools/perf/build: Fix timerfd feature check
      tools/perf/build: Fix feature-libunwind-debug-frame handling
      perf top: Add missing newline if the 'uid' is invalid
      Merge tag 'perf-core-for-mingo' of git://git.kernel.org/.../acme/linux into perf/urgent

Pekka Enberg (1):
      perf trace: Tweak summary output


 tools/perf/Documentation/perf-record.txt    |  6 ++++++
 tools/perf/builtin-probe.c                  |  2 ++
 tools/perf/builtin-record.c                 |  2 ++
 tools/perf/builtin-top.c                    |  4 ++--
 tools/perf/builtin-trace.c                  | 10 +++++-----
 tools/perf/config/Makefile                  | 14 ++++++++++----
 tools/perf/config/feature-checks/Makefile   |  3 +++
 tools/perf/config/feature-checks/test-all.c |  4 ----
 tools/perf/tests/parse-events.c             |  3 +--
 tools/perf/ui/browser.c                     |  4 ++--
 tools/perf/ui/browsers/hists.c              | 11 +++++------
 tools/perf/util/event.c                     |  6 ++++--
 tools/perf/util/evlist.c                    |  6 ++++--
 tools/perf/util/evsel.c                     |  4 ++--
 tools/perf/util/evsel.h                     |  5 +++++
 tools/perf/util/machine.c                   |  2 +-
 tools/perf/util/target.h                    |  1 +
 tools/perf/util/unwind.c                    |  9 +++++----
 tools/perf/util/unwind.h                    |  5 +++--
 19 files changed, 63 insertions(+), 38 deletions(-)


^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-11-01  9:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-11-01  9:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e8a923cc1fff6e627f906655ad52ee694ef2f6d7 perf/x86: Fix NMI measurements

Two fixes:

 - Fix 'NMI handler took too long to run' false positives. [ Genuine 
   NMI overhead speedups will come for v3.13, this commit only fixes 
   a measurement bug. ]

 - Fix perf ring-buffer missed barrier causing (rare) ring-buffer
   data corruption on ppc64.

 Thanks,

	Ingo

------------------>
Peter Zijlstra (2):
      perf: Fix perf ring buffer memory ordering
      perf/x86: Fix NMI measurements


 arch/x86/kernel/cpu/perf_event.c |  6 +++---
 arch/x86/kernel/nmi.c            |  4 ++--
 include/uapi/linux/perf_event.h  | 12 +++++++-----
 kernel/events/ring_buffer.c      | 31 +++++++++++++++++++++++++++----
 4 files changed, 39 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9d84491..8a87a32 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void)
 static int __kprobes
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	int ret;
 	u64 start_clock;
 	u64 finish_clock;
+	int ret;
 
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
-	start_clock = local_clock();
+	start_clock = sched_clock();
 	ret = x86_pmu.handle_irq(regs);
-	finish_clock = local_clock();
+	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ba77ebc..6fcb49c 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 		u64 before, delta, whole_msecs;
 		int remainder_ns, decimal_msecs, thishandled;
 
-		before = local_clock();
+		before = sched_clock();
 		thishandled = a->handler(type, regs);
 		handled += thishandled;
-		delta = local_clock() - before;
+		delta = sched_clock() - before;
 		trace_nmi_handler(a->handler, (int)delta, thishandled);
 
 		if (delta < nmi_longest_ns)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 009a655..2fc1602 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -456,13 +456,15 @@ struct perf_event_mmap_page {
 	/*
 	 * Control data for the mmap() data buffer.
 	 *
-	 * User-space reading the @data_head value should issue an rmb(), on
-	 * SMP capable platforms, after reading this value -- see
-	 * perf_event_wakeup().
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
 	 *
 	 * When the mapping is PROT_WRITE the @data_tail value should be
-	 * written by userspace to reflect the last read data. In this case
-	 * the kernel will not over-write unread data.
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
 	 */
 	__u64   data_head;		/* head in the data section */
 	__u64	data_tail;		/* user-space written tail */
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index cd55144..9c2ddfb 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -87,10 +87,31 @@ again:
 		goto out;
 
 	/*
-	 * Publish the known good head. Rely on the full barrier implied
-	 * by atomic_dec_and_test() order the rb->head read and this
-	 * write.
+	 * Since the mmap() consumer (userspace) can run on a different CPU:
+	 *
+	 *   kernel				user
+	 *
+	 *   READ ->data_tail			READ ->data_head
+	 *   smp_mb()	(A)			smp_rmb()	(C)
+	 *   WRITE $data			READ $data
+	 *   smp_wmb()	(B)			smp_mb()	(D)
+	 *   STORE ->data_head			WRITE ->data_tail
+	 *
+	 * Where A pairs with D, and B pairs with C.
+	 *
+	 * I don't think A needs to be a full barrier because we won't in fact
+	 * write data until we see the store from userspace. So we simply don't
+	 * issue the data WRITE until we observe it. Be conservative for now.
+	 *
+	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * from the tail WRITE.
+	 *
+	 * For B a WMB is sufficient since it separates two WRITEs, and for C
+	 * an RMB is sufficient since it separates two READs.
+	 *
+	 * See perf_output_begin().
 	 */
+	smp_wmb();
 	rb->user_page->data_head = head;
 
 	/*
@@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output_handle *handle,
 		 * Userspace could choose to issue a mb() before updating the
 		 * tail pointer. So that all reads will be completed before the
 		 * write is issued.
+		 *
+		 * See perf_output_put_handle().
 		 */
 		tail = ACCESS_ONCE(rb->user_page->data_tail);
-		smp_rmb();
+		smp_mb();
 		offset = head = local_read(&rb->head);
 		head += size;
 		if (unlikely(!perf_output_space(rb, tail, offset, head)))

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-29  9:50           ` Stephane Eranian
  2013-10-29 10:06             ` Ingo Molnar
@ 2013-10-29 12:47             ` Arnaldo Carvalho de Melo
  1 sibling, 0 replies; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-10-29 12:47 UTC (permalink / raw)
  To: Stephane Eranian
  Cc: Markus Trippelsdorf, Ingo Molnar, Linus Torvalds, LKML,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

Em Tue, Oct 29, 2013 at 10:50:30AM +0100, Stephane Eranian escreveu:
> On Mon, Oct 28, 2013 at 1:42 PM, Arnaldo Carvalho de Melo wrote:
> > Em Mon, Oct 28, 2013 at 09:34:11AM -0300, Arnaldo Carvalho de Melo escreveu:
> >> And then, when reverting it, Stephane forgot to match the number number
> >> of expected entries to be matched/assigned from 8 to 5, can you try with
> >> the following patch instead?

> > Does the wording on this commit log sounds about right to you?

> Thanks for fixing this issue.

You're welcome! :-)

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-29  9:50           ` Stephane Eranian
@ 2013-10-29 10:06             ` Ingo Molnar
  2013-10-29 12:47             ` Arnaldo Carvalho de Melo
  1 sibling, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-10-29 10:06 UTC (permalink / raw)
  To: Stephane Eranian
  Cc: Arnaldo Carvalho de Melo, Markus Trippelsdorf, Linus Torvalds,
	LKML, Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Stephane Eranian <eranian@google.com> wrote:

> On Mon, Oct 28, 2013 at 1:42 PM, Arnaldo Carvalho de Melo
> <acme@ghostprotocols.net> wrote:
> > Em Mon, Oct 28, 2013 at 09:34:11AM -0300, Arnaldo Carvalho de Melo escreveu:
> >> And then, when reverting it, Stephane forgot to match the number number
> >> of expected entries to be matched/assigned from 8 to 5, can you try with
> >> the following patch instead?
> >
> > Does the wording on this commit log sounds about right to you?
> >
> Thanks for fixing this issue.

Thanks guys for testing it - I just sent the pending fixes to Linus 
so it should soon be resolved upstream as well.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-10-29 10:04 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-10-29 10:04 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: cd65718712469ad844467250e8fad20a5838baae Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

It contains five tooling fixes:

 - fix a remaining mmap2 assumption which resulted in perf top output breakage
 - fix mmap ring-buffer processing bug that corrupts data
 - fix for a severe python scripting memory leak
 - fix broken (and user-visible) -g option handling
 - fix stdio output

The diffstat size is larger than what we'd like to see this late :-/

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf tools: Fix up /proc/PID/maps parsing

Jiri Olsa (3):
      perf hists: Add color overhead for stdio output buffer
      perf record: Split -g and --call-graph
      perf top: Split -G and --call-graph

Joseph Schuchart (1):
      perf script python: Fix mem leak due to missing Py_DECREFs on dict entries

Zhouyi Zhou (1):
      perf tools: Fixup mmap event consumption


 tools/perf/Documentation/perf-record.txt           | 14 ++++-
 tools/perf/Documentation/perf-top.txt              | 18 ++----
 tools/perf/builtin-kvm.c                           |  7 +++
 tools/perf/builtin-record.c                        | 73 +++++++++++++++-------
 tools/perf/builtin-top.c                           | 33 +++++-----
 tools/perf/builtin-trace.c                         |  8 ++-
 tools/perf/tests/code-reading.c                    |  1 +
 tools/perf/tests/keep-tracking.c                   |  1 +
 tools/perf/tests/mmap-basic.c                      |  1 +
 tools/perf/tests/open-syscall-tp-fields.c          |  4 +-
 tools/perf/tests/perf-record.c                     |  2 +
 tools/perf/tests/perf-time-to-tsc.c                |  4 +-
 tools/perf/tests/sw-clock.c                        |  4 +-
 tools/perf/tests/task-exit.c                       |  6 +-
 tools/perf/ui/stdio/hist.c                         |  9 ++-
 tools/perf/util/callchain.h                        |  3 +
 tools/perf/util/event.c                            |  2 +-
 tools/perf/util/evlist.c                           | 13 +++-
 tools/perf/util/evlist.h                           |  2 +
 tools/perf/util/hist.h                             | 13 ++++
 tools/perf/util/python.c                           |  2 +
 .../util/scripting-engines/trace-event-python.c    | 37 +++++++----
 22 files changed, 176 insertions(+), 81 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e297b74..ca0d3d9 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -90,8 +90,20 @@ OPTIONS
 	Number of mmap data pages. Must be a power of two.
 
 -g::
+	Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-	Do call-graph (stack chain/backtrace) recording.
+	Setup and enable call-graph (stack chain/backtrace) recording,
+	implies -g.
+
+	Allows specifying "fp" (frame pointer) or "dwarf"
+	(DWARF's CFI - Call Frame Information) as the method to collect
+	the information used to show the call graphs.
+
+	In some systems, where binaries are build with gcc
+	--fomit-frame-pointer, using the "fp" method will produce bogus
+	call graphs, using "dwarf", if available (perf tools linked to
+	the libunwind library) should be used instead.
 
 -q::
 --quiet::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 58d6598..6a118e7 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -140,20 +140,12 @@ Default is to monitor all CPUS.
 --asm-raw::
 	Show raw instruction encoding of assembly instructions.
 
--G [type,min,order]::
+-G::
+	Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-        Display call chains using type, min percent threshold and order.
-	type can be either:
-	- flat: single column, linear exposure of call chains.
-	- graph: use a graph tree, displaying absolute overhead rates.
-	- fractal: like graph, but displays relative rates. Each branch of
-		 the tree is considered as a new profiled object.
-
-	order can be either:
-	- callee: callee based call graph.
-	- caller: inverted caller based call graph.
-
-	Default: fractal,0.5,callee.
+	Setup and enable call-graph (stack chain/backtrace) recording,
+	implies -G.
 
 --ignore-callees=<regex>::
         Ignore callees of the function(s) matching the given regex.
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 935d522..fbc2888 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -888,11 +888,18 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
 		err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
 		if (err) {
+			perf_evlist__mmap_consume(kvm->evlist, idx);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}
 
 		err = perf_session_queue_event(kvm->session, event, &sample, 0);
+		/*
+		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
+		 *        point to it, and it'll get possibly overwritten by the kernel.
+		 */
+		perf_evlist__mmap_consume(kvm->evlist, idx);
+
 		if (err) {
 			pr_err("Failed to enqueue sample: %d\n", err);
 			return -1;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a41ac415..d046514 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -712,21 +712,12 @@ static int get_stack_size(char *str, unsigned long *_size)
 }
 #endif /* LIBUNWIND_SUPPORT */
 
-int record_parse_callchain_opt(const struct option *opt,
-			       const char *arg, int unset)
+int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
 {
-	struct perf_record_opts *opts = opt->value;
 	char *tok, *name, *saveptr = NULL;
 	char *buf;
 	int ret = -1;
 
-	/* --no-call-graph */
-	if (unset)
-		return 0;
-
-	/* We specified default option if none is provided. */
-	BUG_ON(!arg);
-
 	/* We need buffer that we know we can write to. */
 	buf = malloc(strlen(arg) + 1);
 	if (!buf)
@@ -764,13 +755,9 @@ int record_parse_callchain_opt(const struct option *opt,
 				ret = get_stack_size(tok, &size);
 				opts->stack_dump_size = size;
 			}
-
-			if (!ret)
-				pr_debug("callchain: stack dump size %d\n",
-					 opts->stack_dump_size);
 #endif /* LIBUNWIND_SUPPORT */
 		} else {
-			pr_err("callchain: Unknown -g option "
+			pr_err("callchain: Unknown --call-graph option "
 			       "value: %s\n", arg);
 			break;
 		}
@@ -778,13 +765,52 @@ int record_parse_callchain_opt(const struct option *opt,
 	} while (0);
 
 	free(buf);
+	return ret;
+}
+
+static void callchain_debug(struct perf_record_opts *opts)
+{
+	pr_debug("callchain: type %d\n", opts->call_graph);
 
+	if (opts->call_graph == CALLCHAIN_DWARF)
+		pr_debug("callchain: stack dump size %d\n",
+			 opts->stack_dump_size);
+}
+
+int record_parse_callchain_opt(const struct option *opt,
+			       const char *arg,
+			       int unset)
+{
+	struct perf_record_opts *opts = opt->value;
+	int ret;
+
+	/* --no-call-graph */
+	if (unset) {
+		opts->call_graph = CALLCHAIN_NONE;
+		pr_debug("callchain: disabled\n");
+		return 0;
+	}
+
+	ret = record_parse_callchain(arg, opts);
 	if (!ret)
-		pr_debug("callchain: type %d\n", opts->call_graph);
+		callchain_debug(opts);
 
 	return ret;
 }
 
+int record_callchain_opt(const struct option *opt,
+			 const char *arg __maybe_unused,
+			 int unset __maybe_unused)
+{
+	struct perf_record_opts *opts = opt->value;
+
+	if (opts->call_graph == CALLCHAIN_NONE)
+		opts->call_graph = CALLCHAIN_FP;
+
+	callchain_debug(opts);
+	return 0;
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -813,12 +839,12 @@ static struct perf_record record = {
 	},
 };
 
-#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
+#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
 
 #ifdef LIBUNWIND_SUPPORT
-const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
 #else
-const char record_callchain_help[] = CALLCHAIN_HELP "[fp]";
+const char record_callchain_help[] = CALLCHAIN_HELP "fp";
 #endif
 
 /*
@@ -858,9 +884,12 @@ const struct option record_options[] = {
 		     "number of mmap data pages"),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts,
-			     "mode[,dump_size]", record_callchain_help,
-			     &record_parse_callchain_opt, "fp"),
+	OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
+			   NULL, "enables call-graph recording" ,
+			   &record_callchain_opt),
+	OPT_CALLBACK(0, "call-graph", &record.opts,
+		     "mode[,dump_size]", record_callchain_help,
+		     &record_parse_callchain_opt),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2122141..5a11f13 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -810,7 +810,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		ret = perf_evlist__parse_sample(top->evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
-			continue;
+			goto next_event;
 		}
 
 		evsel = perf_evlist__id2evsel(session->evlist, sample.id);
@@ -825,13 +825,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		case PERF_RECORD_MISC_USER:
 			++top->us_samples;
 			if (top->hide_user_symbols)
-				continue;
+				goto next_event;
 			machine = &session->machines.host;
 			break;
 		case PERF_RECORD_MISC_KERNEL:
 			++top->kernel_samples;
 			if (top->hide_kernel_symbols)
-				continue;
+				goto next_event;
 			machine = &session->machines.host;
 			break;
 		case PERF_RECORD_MISC_GUEST_KERNEL:
@@ -847,7 +847,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			 */
 			/* Fall thru */
 		default:
-			continue;
+			goto next_event;
 		}
 
 
@@ -859,6 +859,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			machine__process_event(machine, event);
 		} else
 			++session->stats.nr_unknown_events;
+next_event:
+		perf_evlist__mmap_consume(top->evlist, idx);
 	}
 }
 
@@ -1016,16 +1018,16 @@ out_delete:
 }
 
 static int
-parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	/*
-	 * --no-call-graph
-	 */
-	if (unset)
-		return 0;
-
 	symbol_conf.use_callchain = true;
+	return record_callchain_opt(opt, arg, unset);
+}
 
+static int
+parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+{
+	symbol_conf.use_callchain = true;
 	return record_parse_callchain_opt(opt, arg, unset);
 }
 
@@ -1106,9 +1108,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
-			     "mode[,dump_size]", record_callchain_help,
-			     &parse_callchain_opt, "fp"),
+	OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+			   NULL, "enables call-graph recording",
+			   &callchain_opt),
+	OPT_CALLBACK(0, "call-graph", &top.record_opts,
+		     "mode[,dump_size]", record_callchain_help,
+		     &parse_callchain_opt),
 	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
 		   "ignore callees of these functions in call graphs",
 		   report_parse_ignore_callees_opt),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 71aa3e3..99c8d9a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -987,7 +987,7 @@ again:
 			err = perf_evlist__parse_sample(evlist, event, &sample);
 			if (err) {
 				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
-				continue;
+				goto next_event;
 			}
 
 			if (trace->base_time == 0)
@@ -1001,18 +1001,20 @@ again:
 			evsel = perf_evlist__id2evsel(evlist, sample.id);
 			if (evsel == NULL) {
 				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
-				continue;
+				goto next_event;
 			}
 
 			if (sample.raw_data == NULL) {
 				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
 				       perf_evsel__name(evsel), sample.tid,
 				       sample.cpu, sample.raw_size);
-				continue;
+				goto next_event;
 			}
 
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
 
 			if (done)
 				goto out_unmap_evlist;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 6fb781d..e3fedfa 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -290,6 +290,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
+			perf_evlist__mmap_consume(evlist, i);
 			if (ret < 0)
 				return ret;
 		}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index d444ea2..376c356 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -36,6 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
+			perf_evlist__mmap_consume(evlist, i);
 		}
 	}
 	return found;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index c4185b9..a7232c2 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -122,6 +122,7 @@ int test__basic_mmap(void)
 			goto out_munmap;
 		}
 		nr_events[evsel->idx]++;
+		perf_evlist__mmap_consume(evlist, 0);
 	}
 
 	err = 0;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index fc5b9fc..524b221 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -77,8 +77,10 @@ int test__syscall_open_tp_fields(void)
 
 				++nr_events;
 
-				if (type != PERF_RECORD_SAMPLE)
+				if (type != PERF_RECORD_SAMPLE) {
+					perf_evlist__mmap_consume(evlist, i);
 					continue;
+				}
 
 				err = perf_evsel__parse_sample(evsel, event, &sample);
 				if (err) {
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index b8a7056..7923b06 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -263,6 +263,8 @@ int test__PERF_RECORD(void)
 						 type);
 					++errs;
 				}
+
+				perf_evlist__mmap_consume(evlist, i);
 			}
 		}
 
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 0ab61b1..4ca1b93 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -122,7 +122,7 @@ int test__perf_time_to_tsc(void)
 			if (event->header.type != PERF_RECORD_COMM ||
 			    (pid_t)event->comm.pid != getpid() ||
 			    (pid_t)event->comm.tid != getpid())
-				continue;
+				goto next_event;
 
 			if (strcmp(event->comm.comm, comm1) == 0) {
 				CHECK__(perf_evsel__parse_sample(evsel, event,
@@ -134,6 +134,8 @@ int test__perf_time_to_tsc(void)
 								 &sample));
 				comm2_time = sample.time;
 			}
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
 		}
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 2e41e2d..6e2b44e 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)
-			continue;
+			goto next_event;
 
 		err = perf_evlist__parse_sample(evlist, event, &sample);
 		if (err < 0) {
@@ -88,6 +88,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 		total_periods += sample.period;
 		nr_samples++;
+next_event:
+		perf_evlist__mmap_consume(evlist, 0);
 	}
 
 	if ((u64) nr_samples == total_periods) {
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 28fe589..a3e6487 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -96,10 +96,10 @@ int test__task_exit(void)
 
 retry:
 	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
-		if (event->header.type != PERF_RECORD_EXIT)
-			continue;
+		if (event->header.type == PERF_RECORD_EXIT)
+			nr_exit++;
 
-		nr_exit++;
+		perf_evlist__mmap_consume(evlist, 0);
 	}
 
 	if (!exited || !nr_exit) {
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 194e2f4..6c15268 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -315,8 +315,7 @@ static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 }
 
 static int hist_entry__period_snprintf(struct perf_hpp *hpp,
-				       struct hist_entry *he,
-				       bool color)
+				       struct hist_entry *he)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
@@ -338,7 +337,7 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp,
 		} else
 			first = false;
 
-		if (color && fmt->color)
+		if (perf_hpp__use_color() && fmt->color)
 			ret = fmt->color(fmt, hpp, he);
 		else
 			ret = fmt->entry(fmt, hpp, he);
@@ -358,12 +357,11 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		.buf		= bf,
 		.size		= size,
 	};
-	bool color = !symbol_conf.field_sep;
 
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
 
-	ret = hist_entry__period_snprintf(&hpp, he, color);
+	ret = hist_entry__period_snprintf(&hpp, he);
 	hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
 
 	ret = fprintf(fp, "%s\n", bf);
@@ -482,6 +480,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 print_entries:
 	linesz = hists__sort_list_width(hists) + 3 + 1;
+	linesz += perf_hpp__color_overhead();
 	line = malloc(linesz);
 	if (line == NULL) {
 		ret = -1;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 2b585bc..9e99060 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -147,6 +147,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 
 struct option;
 
+int record_parse_callchain(const char *arg, struct perf_record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
+int record_callchain_opt(const struct option *opt, const char *arg, int unset);
+
 extern const char record_callchain_help[];
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 63df031..49096ea 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -213,7 +213,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		       &event->mmap.pgoff,
 		       execname);
 
-		if (n != 8)
+		if (n != 5)
 			continue;
 
 		if (prot[2] != 'x')
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f9f77be..e584cd3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -545,12 +545,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 	md->prev = old;
 
-	if (!evlist->overwrite)
-		perf_mmap__write_tail(md, old);
-
 	return event;
 }
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+	if (!evlist->overwrite) {
+		struct perf_mmap *md = &evlist->mmap[idx];
+		unsigned int old = md->prev;
+
+		perf_mmap__write_tail(md, old);
+	}
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
 	if (evlist->mmap[idx].base != NULL) {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 880d713..206d093 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -89,6 +89,8 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
+
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1329b6b..ce8dc61 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -5,6 +5,7 @@
 #include <pthread.h>
 #include "callchain.h"
 #include "header.h"
+#include "color.h"
 
 extern struct callchain_param callchain_param;
 
@@ -175,6 +176,18 @@ void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
 
+static inline size_t perf_hpp__use_color(void)
+{
+	return !symbol_conf.field_sep;
+}
+
+static inline size_t perf_hpp__color_overhead(void)
+{
+	return perf_hpp__use_color() ?
+	       (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX
+	       : 0;
+}
+
 struct perf_evlist;
 
 struct hist_browser_timer {
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 71b5412..2ac4bc9 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -822,6 +822,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
+		perf_evlist__mmap_consume(evlist, cpu);
+
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cc75a3c..95d91a0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name)
 	Py_FatalError("problem in Python trace event handler");
 }
 
+/*
+ * Insert val into into the dictionary and decrement the reference counter.
+ * This is necessary for dictionaries since PyDict_SetItemString() does not 
+ * steal a reference, as opposed to PyTuple_SetItem().
+ */
+static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val)
+{
+	PyDict_SetItemString(dict, key, val);
+	Py_DECREF(val);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event
 		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
 		PyTuple_SetItem(t, n++, PyString_FromString(comm));
 	} else {
-		PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
-		PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
-		PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
-		PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
-		PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+		pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
+		pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
+		pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
+		pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
+		pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
 	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
@@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event
 		if (handler)
 			PyTuple_SetItem(t, n++, obj);
 		else
-			PyDict_SetItemString(dict, field->name, obj);
+			pydict_set_item_string_decref(dict, field->name, obj);
 
 	}
 	if (!handler)
@@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event
 	if (!handler || !PyCallable_Check(handler))
 		goto exit;
 
-	PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
-	PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+	pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
 			(const char *)&evsel->attr, sizeof(evsel->attr)));
-	PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
 			(const char *)sample, sizeof(*sample)));
-	PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
 			(const char *)sample->raw_data, sample->raw_size));
-	PyDict_SetItemString(dict, "comm",
+	pydict_set_item_string_decref(dict, "comm",
 			PyString_FromString(thread->comm));
 	if (al->map) {
-		PyDict_SetItemString(dict, "dso",
+		pydict_set_item_string_decref(dict, "dso",
 			PyString_FromString(al->map->dso->name));
 	}
 	if (al->sym) {
-		PyDict_SetItemString(dict, "symbol",
+		pydict_set_item_string_decref(dict, "symbol",
 			PyString_FromString(al->sym->name));
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-28 12:42         ` Arnaldo Carvalho de Melo
  2013-10-28 12:59           ` Markus Trippelsdorf
@ 2013-10-29  9:50           ` Stephane Eranian
  2013-10-29 10:06             ` Ingo Molnar
  2013-10-29 12:47             ` Arnaldo Carvalho de Melo
  1 sibling, 2 replies; 376+ messages in thread
From: Stephane Eranian @ 2013-10-29  9:50 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Markus Trippelsdorf, Ingo Molnar, Linus Torvalds, LKML,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Mon, Oct 28, 2013 at 1:42 PM, Arnaldo Carvalho de Melo
<acme@ghostprotocols.net> wrote:
> Em Mon, Oct 28, 2013 at 09:34:11AM -0300, Arnaldo Carvalho de Melo escreveu:
>> And then, when reverting it, Stephane forgot to match the number number
>> of expected entries to be matched/assigned from 8 to 5, can you try with
>> the following patch instead?
>
> Does the wording on this commit log sounds about right to you?
>
Thanks for fixing this issue.

> - Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-28 12:42         ` Arnaldo Carvalho de Melo
@ 2013-10-28 12:59           ` Markus Trippelsdorf
  2013-10-29  9:50           ` Stephane Eranian
  1 sibling, 0 replies; 376+ messages in thread
From: Markus Trippelsdorf @ 2013-10-28 12:59 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Stephane Eranian

On 2013.10.28 at 09:42 -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Oct 28, 2013 at 09:34:11AM -0300, Arnaldo Carvalho de Melo escreveu:
> > And then, when reverting it, Stephane forgot to match the number number
> > of expected entries to be matched/assigned from 8 to 5, can you try with
> > the following patch instead?
> 
> Does the wording on this commit log sounds about right to you?

Yes. Your patch is fine. Thanks.

-- 
Markus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-28 12:34       ` Arnaldo Carvalho de Melo
@ 2013-10-28 12:42         ` Arnaldo Carvalho de Melo
  2013-10-28 12:59           ` Markus Trippelsdorf
  2013-10-29  9:50           ` Stephane Eranian
  0 siblings, 2 replies; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-10-28 12:42 UTC (permalink / raw)
  To: Markus Trippelsdorf
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Stephane Eranian

[-- Attachment #1: Type: text/plain, Size: 332 bytes --]

Em Mon, Oct 28, 2013 at 09:34:11AM -0300, Arnaldo Carvalho de Melo escreveu:
> And then, when reverting it, Stephane forgot to match the number number
> of expected entries to be matched/assigned from 8 to 5, can you try with
> the following patch instead?

Does the wording on this commit log sounds about right to you?

- Arnaldo

[-- Attachment #2: a.patch --]
[-- Type: text/plain, Size: 1478 bytes --]

commit 2fd869f08aec5a8e4cbf01bc3fa345c4e53342d7
Author: Arnaldo Carvalho de Melo <acme@redhat.com>
Date:   Mon Oct 28 09:38:12 2013 -0300

    perf tools: Fix up /proc/PID/maps parsing
    
    When introducing support for MMAP2 we considered more parts of each map
    representation in /proc/PID/maps, and when disabling it we forgot to
    reduce the number of expected parsed/assigned entries in the sscanf
    call, fix it to expect the right number of desired fields, 5.
    
    Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
    Based-on-a-patch-by: Markus Trippelsdorf <markus@trippelsdorf.de>
    Cc: Adrian Hunter <adrian.hunter@intel.com>
    Cc: David Ahern <dsahern@gmail.com>
    Cc: Frederic Weisbecker <fweisbec@gmail.com>
    Cc: Jiri Olsa <jolsa@redhat.com>
    Cc: Mike Galbraith <efault@gmx.de>
    Cc: Paul Mackerras <paulus@samba.org>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Cc: Stephane Eranian <eranian@google.com>
    Link: http://lkml.kernel.org/n/tip-vrbo1wik997ahjzl1chm3bdm@git.kernel.org
    Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 63df031fc9c7..49096ea58a15 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -213,7 +213,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		       &event->mmap.pgoff,
 		       execname);
 
-		if (n != 8)
+		if (n != 5)
 			continue;
 
 		if (prot[2] != 'x')

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-28  9:34     ` Markus Trippelsdorf
@ 2013-10-28 12:34       ` Arnaldo Carvalho de Melo
  2013-10-28 12:42         ` Arnaldo Carvalho de Melo
  0 siblings, 1 reply; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-10-28 12:34 UTC (permalink / raw)
  To: Markus Trippelsdorf
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Stephane Eranian

Em Mon, Oct 28, 2013 at 10:34:30AM +0100, Markus Trippelsdorf escreveu:
> On 2013.10.28 at 10:02 +0100, Markus Trippelsdorf wrote:
> > On 2013.10.28 at 09:28 +0100, Markus Trippelsdorf wrote:
> > > On 2013.10.26 at 14:24 +0200, Ingo Molnar wrote:
> > > >  - Reversal of the new 'MMAP2' extended mmap record ABI, introduced 

> > > commit 3090ffb5a2515990182f3f55b0688a7817325488
> > > Author: Stephane Eranian <eranian@google.com>

> > >     perf: Disable PERF_RECORD_MMAP2 support

> The following patch fixes the issue:
 
> diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
>  		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
> -		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
> +		sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
>  		       &event->mmap.start, &event->mmap.len, prot,
>  		       &event->mmap.pgoff,
>  		       execname);
  
> -		if (n != 8)
> -			continue;
> -

Yeah, this one was added in the patch that introduced MMAP2 support in
the tooling side, it was unrelated to what the patch needed, i.e. should
have come in a separate patch, checking sscanf number of itens
successfully matched/assigned.

And then, when reverting it, Stephane forgot to match the number number
of expected entries to be matched/assigned from 8 to 5, can you try with
the following patch instead?

- Arnaldo

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 63df031fc9c7..49096ea58a15 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -213,7 +213,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		       &event->mmap.pgoff,
 		       execname);
 
-		if (n != 8)
+		if (n != 5)
 			continue;
 
 		if (prot[2] != 'x')

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-28  9:02   ` ------------------------------ Markus Trippelsdorf
@ 2013-10-28  9:34     ` Markus Trippelsdorf
  2013-10-28 12:34       ` Arnaldo Carvalho de Melo
  0 siblings, 1 reply; 376+ messages in thread
From: Markus Trippelsdorf @ 2013-10-28  9:34 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton,
	Stephane Eranian

On 2013.10.28 at 10:02 +0100, ------------------------------ Markus Trippelsdorf wrote:
> On 2013.10.28 at 09:28 +0100, Markus Trippelsdorf wrote:
> > On 2013.10.26 at 14:24 +0200, Ingo Molnar wrote:
> > >  - Reversal of the new 'MMAP2' extended mmap record ABI, introduced 
> > >    in this merge window. (Patches were proposed to fix it but it was
> > >    all a bit late and we felt it's safer to just delay the ABI one
> > >    more kernel release and do it right.)
> > 
> > commit 3090ffb5a2515990182f3f55b0688a7817325488
> > Author: Stephane Eranian <eranian@google.com>
> > Date:   Thu Oct 17 19:32:15 2013 +0200
> > 
> >     perf: Disable PERF_RECORD_MMAP2 support
> > 
> > The commit above breaks "perf top" on my system, because it causes only
> > [kernel] symbols to show up in the list. When I revert the commit I get
> > the usual mixture of userspace and kernel symbols in the list.

The following patch fixes the issue:

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 63df031fc9c7..811f3950654d 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -199,7 +199,6 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
 		size_t size;
-		ssize_t n;
 
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
@@ -208,14 +207,11 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
+		sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
 		       &event->mmap.start, &event->mmap.len, prot,
 		       &event->mmap.pgoff,
 		       execname);
 
-		if (n != 8)
-			continue;
-
 		if (prot[2] != 'x')
 			continue;
 
-- 
Markus

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-28  8:28 ` Markus Trippelsdorf
@ 2013-10-28  9:02   ` ------------------------------ Markus Trippelsdorf
  2013-10-28  9:34     ` Markus Trippelsdorf
  0 siblings, 1 reply; 376+ messages in thread
From: ------------------------------ Markus Trippelsdorf @ 2013-10-28  9:02 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton,
	Stephane Eranian

On 2013.10.28 at 09:28 +0100, Markus Trippelsdorf wrote:
> On 2013.10.26 at 14:24 +0200, Ingo Molnar wrote:
> >  - Reversal of the new 'MMAP2' extended mmap record ABI, introduced 
> >    in this merge window. (Patches were proposed to fix it but it was
> >    all a bit late and we felt it's safer to just delay the ABI one
> >    more kernel release and do it right.)
> 
> commit 3090ffb5a2515990182f3f55b0688a7817325488
> Author: Stephane Eranian <eranian@google.com>
> Date:   Thu Oct 17 19:32:15 2013 +0200
> 
>     perf: Disable PERF_RECORD_MMAP2 support
> 
> The commit above breaks "perf top" on my system, because it causes only
> [kernel] symbols to show up in the list. When I revert the commit I get
> the usual mixture of userspace and kernel symbols in the list.

Forgot to mention that this happens on an otherwise idle machine. If I
run CPU intensive apps they'll show up eventually.

Example (current Linus tree):

   PerfTop:     593 irqs/sec  kernel:80.6%  exact:  0.0% [4000Hz cycles],  (all, 4 CPUs)
----------------------------------------------------------------------------------------------

    57.75%  [kernel]          [k] amd_e400_idle
    28.66%  [unknown]         [.] 0x0000000000450bc8
     1.51%  [kernel]          [k] kallsyms_expand_symbol.const
     1.22%  [kernel]          [k] cpu_startup_entry
     1.13%  [kernel]          [k] number.isra.1
     0.77%  [kernel]          [k] clear_page_c
     0.74%  [kernel]          [k] memcpy
     0.46%  [kernel]          [k] task_waking_fair
     0.45%  [kernel]          [k] _raw_spin_lock_irqsave
     0.42%  [kernel]          [k] _raw_spin_unlock_irqrestore
     0.39%  [kernel]          [k] format_decode
     0.34%  [kernel]          [k] do_sys_poll
     0.31%  [kernel]          [k] current_kernel_time
     0.30%  [kernel]          [k] vsnprintf
     0.29%  [kernel]          [k] native_apic_mem_write
     0.28%  [kernel]          [k] select_task_rq_fair
     0.26%  [kernel]          [k] swiotlb_free_coherent
     0.26%  [kernel]          [k] irq_entries_start
     0.2n%  [kernel]          [k] strnlen

With the commit above reverted:

   PerfTop:     907 irqs/sec  kernel:73.3%  exact:  0.0% [4000Hz cycles],  (all, 4 CPUs)
-----------------------------------------------------------------------------------------------

    30.89%  [kernel]                    [k] amd_e400_idle
     6.88%  [unknown]                   [.] 0x00007f346f2ef3a6
     5.22%  libc-2.18.90.so             [.] strcmp
     3.65%  libc-2.18.90.so             [.] strstr
     2.65%  libbfd-2.24.51.20131018.so  [.] d_print_comp.part.8
     2.61%  perf                        [.] symbols__insert
     2.18%  [kernel]                    [k] cpu_startup_entry
     1.82%  perf                        [.] symbol_filter
     1.73%  perf                        [.] rb_next
     1.58%  libc-2.18.90.so             [.] critical_factorization
     1.34%  libelf-0.156.so             [.] gelf_getsym
     1.28%  libQtGui.so.4.8.5           [.] qt_alphargbblit_quint32(QRasterBuffer*, int, int, unsigned int, unsigned int const*, int, int, int, QClipData
     1.25%  libc-2.18.90.so             [.] __libc_calloc
     1.17%  libc-2.18.90.so             [.] _int_malloc
     1.15%  libc-2.18.90.so             [.] strchr
     0.97%  xmobar                      [.] 0x000000000000c922
     0.97%  [kernel]                    [k] number.isra.1
     0.96%  libpthread-2.18.90.so       [.] pthread_rwlock_rdlock
     0.96%  libc-2.18.90.so             [.] memcpy@@GLIBC_2.14
     0.94%  perf                        [.] dso__load_sym
     0.93%  libc-2.18.90.so             [.] memchr
     0.84%  libbfd-2.24.51.20131018.so  [.] d_name
     0.75%  [kernel]                    [k] clear_page_c
     0.73%  libpthread-2.18.90.so       [.] pthread_rwlock_unlock
     0.66%  libc-2.18.90.so             [.] memset

-- 
Markus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-10-26 12:24 Ingo Molnar
@ 2013-10-28  8:28 ` Markus Trippelsdorf
  2013-10-28  9:02   ` ------------------------------ Markus Trippelsdorf
  0 siblings, 1 reply; 376+ messages in thread
From: Markus Trippelsdorf @ 2013-10-28  8:28 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton,
	Stephane Eranian

On 2013.10.26 at 14:24 +0200, Ingo Molnar wrote:
>  - Reversal of the new 'MMAP2' extended mmap record ABI, introduced 
>    in this merge window. (Patches were proposed to fix it but it was
>    all a bit late and we felt it's safer to just delay the ABI one
>    more kernel release and do it right.)

commit 3090ffb5a2515990182f3f55b0688a7817325488
Author: Stephane Eranian <eranian@google.com>
Date:   Thu Oct 17 19:32:15 2013 +0200

    perf: Disable PERF_RECORD_MMAP2 support

The commit above breaks "perf top" on my system, because it causes only
[kernel] symbols to show up in the list. When I revert the commit I get
the usual mixture of userspace and kernel symbols in the list.

-- 
Markus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-10-26 12:24 Ingo Molnar
  2013-10-28  8:28 ` Markus Trippelsdorf
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-10-26 12:24 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e4f8eaad70ea186b8da290c99239dce721a34f88 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

The tree contains three fixes:

 - Two tooling fixes

 - Reversal of the new 'MMAP2' extended mmap record ABI, introduced 
   in this merge window. (Patches were proposed to fix it but it was
   all a bit late and we felt it's safer to just delay the ABI one
   more kernel release and do it right.)

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf scripting perl: Fix build error on Fedora 12

Masami Hiramatsu (1):
      perf probe: Fix to initialize fname always before use it

Stephane Eranian (1):
      perf: Disable PERF_RECORD_MMAP2 support


 kernel/events/core.c                               |  4 +++
 tools/perf/util/event.c                            | 30 ++++++++++------------
 tools/perf/util/evsel.c                            |  1 -
 tools/perf/util/probe-finder.c                     |  2 +-
 .../perf/util/scripting-engines/trace-event-perl.c |  2 +-
 5 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d49a9d2..953c143 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6767,6 +6767,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
+	/* disabled for now */
+	if (attr->mmap2)
+		return -EINVAL;
+
 	if (attr->__reserved_1)
 		return -EINVAL;
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9b393e7..63df031 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -187,7 +187,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		return -1;
 	}
 
-	event->header.type = PERF_RECORD_MMAP2;
+	event->header.type = PERF_RECORD_MMAP;
 	/*
 	 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 	 */
@@ -198,7 +198,6 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		char prot[5];
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
-		unsigned int ino;
 		size_t size;
 		ssize_t n;
 
@@ -209,13 +208,10 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
-		       &event->mmap2.start, &event->mmap2.len, prot,
-		       &event->mmap2.pgoff, &event->mmap2.maj,
-		       &event->mmap2.min,
-		       &ino, execname);
-
-		event->mmap2.ino = (u64)ino;
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
+		       &event->mmap.start, &event->mmap.len, prot,
+		       &event->mmap.pgoff,
+		       execname);
 
 		if (n != 8)
 			continue;
@@ -227,15 +223,15 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			strcpy(execname, anonstr);
 
 		size = strlen(execname) + 1;
-		memcpy(event->mmap2.filename, execname, size);
+		memcpy(event->mmap.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap2.len -= event->mmap.start;
-		event->mmap2.header.size = (sizeof(event->mmap2) -
-					(sizeof(event->mmap2.filename) - size));
-		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-		event->mmap2.header.size += machine->id_hdr_size;
-		event->mmap2.pid = tgid;
-		event->mmap2.tid = pid;
+		event->mmap.len -= event->mmap.start;
+		event->mmap.header.size = (sizeof(event->mmap) -
+					(sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+		event->mmap.header.size += machine->id_hdr_size;
+		event->mmap.pid = tgid;
+		event->mmap.tid = pid;
 
 		if (process(tool, event, &synth_sample, machine) != 0) {
 			rc = -1;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0ce9feb..9f1ef9b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -678,7 +678,6 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		attr->sample_type	|= PERF_SAMPLE_WEIGHT;
 
 	attr->mmap  = track;
-	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
 	/*
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c09e0a9..f069273 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1357,10 +1357,10 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
 			goto post;
 		}
 
+		fname = dwarf_decl_file(&spdie);
 		if (addr == (unsigned long)baseaddr) {
 			/* Function entry - Relative line number is 0 */
 			lineno = baseline;
-			fname = dwarf_decl_file(&spdie);
 			goto post;
 		}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index a85e4ae..c0c9795 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 
 	event = find_cache_event(evsel);
 	if (!event)
-		die("ug! no event found for type %" PRIu64, evsel->attr.config);
+		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
 	pid = raw_field_value(event, "common_pid", data);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-10-08 12:12 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-10-08 12:12 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 1651d120baddf68846188bcdf0ef5350068436cf Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Various fixlets:

 - On the kernel side:

    - fix a race
    - fix a bug in the handling of the perf ring-buffer data page

 - On the tooling side:

    - fix the handling of certain corrupted perf.data files
    - fix a bug in 'perf probe'
    - fix a bug in 'perf record + perf sched'
    - fix a bug in 'make install'
    - fix a bug in libaudit feature-detection on certain distros

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf tools: Fix libaudit test
      perf tools: Fix installation of libexec components

David Ahern (1):
      perf tools: Add default handler for mmap2 events

Masami Hiramatsu (1):
      perf probe: Fix to find line information for probe list

Namhyung Kim (2):
      perf stat: Set child_pid after perf_evlist__prepare_workload()
      perf session: Fix infinite loop on invalid perf.data file

Peter Zijlstra (2):
      perf: Fix perf_pmu_migrate_context
      perf/x86: Clean up cap_user_time* setting


 arch/x86/kernel/cpu/perf_event.c    | 11 +++------
 include/linux/perf_event.h          | 24 +++++++++++++++++-
 kernel/events/core.c                |  6 ++---
 tools/perf/Makefile                 |  1 +
 tools/perf/builtin-stat.c           |  1 +
 tools/perf/config/feature-tests.mak |  2 +-
 tools/perf/util/dwarf-aux.c         | 25 ++++++++++++++++---
 tools/perf/util/dwarf-aux.h         |  6 ++++-
 tools/perf/util/header.c            | 12 +++++++++
 tools/perf/util/probe-finder.c      | 49 +++++++++++++++++++++++++------------
 tools/perf/util/session.c           |  4 ++-
 11 files changed, 106 insertions(+), 35 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 897783b..9d84491 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+	if (!sched_clock_stable)
 		return;
 
 	userpg->cap_user_time = 1;
@@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
-	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = this_cpu_read(cyc2ns_offset);
-	}
+	userpg->cap_user_time_zero = 1;
+	userpg->time_zero = this_cpu_read(cyc2ns_offset);
 }
 
 /*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 866e85c..c8ba627 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -294,9 +294,31 @@ struct ring_buffer;
  */
 struct perf_event {
 #ifdef CONFIG_PERF_EVENTS
-	struct list_head		group_entry;
+	/*
+	 * entry onto perf_event_context::event_list;
+	 *   modifications require ctx->lock
+	 *   RCU safe iterations.
+	 */
 	struct list_head		event_entry;
+
+	/*
+	 * XXX: group_entry and sibling_list should be mutually exclusive;
+	 * either you're a sibling on a group, or you're the group leader.
+	 * Rework the code to always use the same list element.
+	 *
+	 * Locked for modification by both ctx->mutex and ctx->lock; holding
+	 * either sufficies for read.
+	 */
+	struct list_head		group_entry;
 	struct list_head		sibling_list;
+
+	/*
+	 * We need storage to track the entries in perf_pmu_migrate_context; we
+	 * cannot use the event_entry because of RCU and we want to keep the
+	 * group in tact which avoids us using the other two entries.
+	 */
+	struct list_head		migrate_entry;
+
 	struct hlist_node		hlist_entry;
 	int				nr_siblings;
 	int				group_flags;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cb4238e..d49a9d2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7234,15 +7234,15 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 		perf_remove_from_context(event);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
-		list_add(&event->event_entry, &events);
+		list_add(&event->migrate_entry, &events);
 	}
 	mutex_unlock(&src_ctx->mutex);
 
 	synchronize_rcu();
 
 	mutex_lock(&dst_ctx->mutex);
-	list_for_each_entry_safe(event, tmp, &events, event_entry) {
-		list_del(&event->event_entry);
+	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+		list_del(&event->migrate_entry);
 		if (event->state >= PERF_EVENT_STATE_OFF)
 			event->state = PERF_EVENT_STATE_INACTIVE;
 		account_event_cpu(event, dst_cpu);
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3a0ff7f..64c043b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -770,6 +770,7 @@ check: $(OUTPUT)common-cmds.h
 install-bin: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
+	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f686d5f..5098f14 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -457,6 +457,7 @@ static int __run_perf_stat(int argc, const char **argv)
 			perror("failed to prepare workload");
 			return -1;
 		}
+		child_pid = evsel_list->workload.pid;
 	}
 
 	if (group)
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index d5a8dd4..f793057 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -219,7 +219,7 @@ define SOURCE_LIBAUDIT
 
 int main(void)
 {
-	printf(\"error message: %s\n\", audit_errno_to_name(0));
+	printf(\"error message: %s\", audit_errno_to_name(0));
 	return audit_open();
 }
 endef
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index e23bde1..7defd77 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -426,7 +426,7 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
  * @die_mem: a buffer for result DIE
  *
  * Search a non-inlined function DIE which includes @addr. Stores the
- * DIE to @die_mem and returns it if found. Returns NULl if failed.
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
  */
 Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem)
@@ -454,15 +454,32 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 }
 
 /**
+ * die_find_top_inlinefunc - Search the top inlined function at given address
+ * @sp_die: a subprogram DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search an inlined function DIE which includes @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ * Even if several inlined functions are expanded recursively, this
+ * doesn't trace it down, and returns the topmost one.
+ */
+Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				   Dwarf_Die *die_mem)
+{
+	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+}
+
+/**
  * die_find_inlinefunc - Search an inlined function at given address
- * @cu_die: a CU DIE which including @addr
+ * @sp_die: a subprogram DIE which including @addr
  * @addr: target address
  * @die_mem: a buffer for result DIE
  *
  * Search an inlined function DIE which includes @addr. Stores the
- * DIE to @die_mem and returns it if found. Returns NULl if failed.
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
  * If several inlined functions are expanded recursively, this trace
- * it and returns deepest one.
+ * it down and returns deepest one.
  */
 Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 			       Dwarf_Die *die_mem)
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 8658d41..b4fe90c 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -79,7 +79,11 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
-/* Search an inlined function including given address */
+/* Search the top inlined function including given address */
+extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+					  Dwarf_Die *die_mem);
+
+/* Search the deepest inlined function including given address */
 extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 				      Dwarf_Die *die_mem);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ce69901..c3e5a3b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2768,6 +2768,18 @@ int perf_session__read_header(struct perf_session *session)
 	if (perf_file_header__read(&f_header, header, fd) < 0)
 		return -EINVAL;
 
+	/*
+	 * Sanity check that perf.data was written cleanly; data size is
+	 * initialized to 0 and updated only if the on_exit function is run.
+	 * If data size is still 0 then the file contains only partial
+	 * information.  Just warn user and process it as much as it can.
+	 */
+	if (f_header.data.size == 0) {
+		pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
+			   "Was the 'perf record' command properly terminated?\n",
+			   session->filename);
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 371476c..c09e0a9 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1327,8 +1327,8 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
 				struct perf_probe_point *ppt)
 {
 	Dwarf_Die cudie, spdie, indie;
-	Dwarf_Addr _addr, baseaddr;
-	const char *fname = NULL, *func = NULL, *tmp;
+	Dwarf_Addr _addr = 0, baseaddr = 0;
+	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
 
 	/* Adjust address with bias */
@@ -1349,27 +1349,36 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
 	/* Find a corresponding function (name, baseline and baseaddr) */
 	if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
 		/* Get function entry information */
-		tmp = dwarf_diename(&spdie);
-		if (!tmp ||
+		func = basefunc = dwarf_diename(&spdie);
+		if (!func ||
 		    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
-		    dwarf_decl_line(&spdie, &baseline) != 0)
+		    dwarf_decl_line(&spdie, &baseline) != 0) {
+			lineno = 0;
 			goto post;
-		func = tmp;
+		}
 
-		if (addr == (unsigned long)baseaddr)
+		if (addr == (unsigned long)baseaddr) {
 			/* Function entry - Relative line number is 0 */
 			lineno = baseline;
-		else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-					     &indie)) {
+			fname = dwarf_decl_file(&spdie);
+			goto post;
+		}
+
+		/* Track down the inline functions step by step */
+		while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr,
+						&indie)) {
+			/* There is an inline function */
 			if (dwarf_entrypc(&indie, &_addr) == 0 &&
-			    _addr == addr)
+			    _addr == addr) {
 				/*
 				 * addr is at an inline function entry.
 				 * In this case, lineno should be the call-site
-				 * line number.
+				 * line number. (overwrite lineinfo)
 				 */
 				lineno = die_get_call_lineno(&indie);
-			else {
+				fname = die_get_call_file(&indie);
+				break;
+			} else {
 				/*
 				 * addr is in an inline function body.
 				 * Since lineno points one of the lines
@@ -1377,19 +1386,27 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
 				 * be the entry line of the inline function.
 				 */
 				tmp = dwarf_diename(&indie);
-				if (tmp &&
-				    dwarf_decl_line(&spdie, &baseline) == 0)
-					func = tmp;
+				if (!tmp ||
+				    dwarf_decl_line(&indie, &baseline) != 0)
+					break;
+				func = tmp;
+				spdie = indie;
 			}
 		}
+		/* Verify the lineno and baseline are in a same file */
+		tmp = dwarf_decl_file(&spdie);
+		if (!tmp || strcmp(tmp, fname) != 0)
+			lineno = 0;
 	}
 
 post:
 	/* Make a relative line number or an offset */
 	if (lineno)
 		ppt->line = lineno - baseline;
-	else if (func)
+	else if (basefunc) {
 		ppt->offset = addr - (unsigned long)baseaddr;
+		func = basefunc;
+	}
 
 	/* Duplicate strings */
 	if (func) {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 70ffa41..568b750 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -256,6 +256,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->sample = process_event_sample_stub;
 	if (tool->mmap == NULL)
 		tool->mmap = process_event_stub;
+	if (tool->mmap2 == NULL)
+		tool->mmap2 = process_event_stub;
 	if (tool->comm == NULL)
 		tool->comm = process_event_stub;
 	if (tool->fork == NULL)
@@ -1310,7 +1312,7 @@ int __perf_session__process_events(struct perf_session *session,
 	file_offset = page_offset;
 	head = data_offset - page_offset;
 
-	if (data_offset + data_size < file_size)
+	if (data_size && (data_offset + data_size < file_size))
 		file_size = data_offset + data_size;
 
 	progress_next = file_size / 16;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-30 18:54       ` Andi Kleen
@ 2013-10-01  8:42         ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-10-01  8:42 UTC (permalink / raw)
  To: Andi Kleen
  Cc: Markus Trippelsdorf, Linus Torvalds, linux-kernel,
	Peter Zijlstra, Arnaldo Carvalho de Melo,
	Arnaldo Carvalho de Melo


* Andi Kleen <ak@linux.intel.com> wrote:

> > > Hmm, works for me. In fact I wrote it to fix a perf top issue.
> >
> > What 'issue' and why wasn't it described in the changelog more 
> > accurately?
> >
> > The blurb you wrote in the changelog:
> > 
> > | The libbfd C++ demangler doesn't seem to deal with cloned functions, 
> > | like symbol.clone.NUM.
> > |
> > | Just strip the dot part before demangling and add it back later.
> > 
> > Only alludes to a C++ symbol resolution annoyance and thus isn't very 
> > informative.
> 
> The issue was that I saw a long unreadable line noise string in 
> report/top, instead of a demangled function. After I stripped the 
> postfix I got the demangled symbol as expected.

We obviously don't want to trade output annoyances for crashes, nor does 
it justify the code uglies you introduced with the patch - which made the 
code obviously unrobust.

My guess would be that maybe it's the cast of a const pointer that 
possibly broke GCC's aliasing detection on Markus's system or so. But 
maybe there's a more direct bug in the code as well, the code you added is 
too ugly to be reviewed efficiently, please send a cleaned up version.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-30  6:27     ` Ingo Molnar
@ 2013-09-30 18:54       ` Andi Kleen
  2013-10-01  8:42         ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Andi Kleen @ 2013-09-30 18:54 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Markus Trippelsdorf, Linus Torvalds, linux-kernel,
	Peter Zijlstra, Arnaldo Carvalho de Melo,
	Arnaldo Carvalho de Melo

> The blurb you wrote in the changelog:
> 
> | The libbfd C++ demangler doesn't seem to deal with cloned functions, 
> | like symbol.clone.NUM.
> |
> | Just strip the dot part before demangling and add it back later.
> 
> Only alludes to a C++ symbol resolution annoyance and thus isn't very 
> informative.

The issue was that I saw a long unreadable line noise string in report/top,
instead of a demangled function. After I stripped the postfix I got the demangled
symbol as expected.

-Andi
-- 
ak@linux.intel.com -- Speaking for myself only

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-29 21:33   ` Andi Kleen
  2013-09-29 22:47     ` Markus Trippelsdorf
@ 2013-09-30  6:27     ` Ingo Molnar
  2013-09-30 18:54       ` Andi Kleen
  1 sibling, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-30  6:27 UTC (permalink / raw)
  To: Andi Kleen
  Cc: Markus Trippelsdorf, Linus Torvalds, linux-kernel,
	Peter Zijlstra, Arnaldo Carvalho de Melo,
	Arnaldo Carvalho de Melo


* Andi Kleen <ak@linux.intel.com> wrote:

> > breaks "perf top" on my machine. I just see a gray screen with no text
> > at all. Sometimes the following error messages are printed:
> >  *** Error in `perf': invalid fastbin entry (free): 0x00000000029b18c0 ***
> >  *** Error in `perf': malloc(): memory corruption (fast): 0x0000000000ee0b10 ***
> 
> Hmm, works for me. In fact I wrote it to fix a perf top issue.

What 'issue' and why wasn't it described in the changelog more accurately?

The blurb you wrote in the changelog:

| The libbfd C++ demangler doesn't seem to deal with cloned functions, 
| like symbol.clone.NUM.
|
| Just strip the dot part before demangling and add it back later.

Only alludes to a C++ symbol resolution annoyance and thus isn't very 
informative.

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-29 21:33   ` Andi Kleen
@ 2013-09-29 22:47     ` Markus Trippelsdorf
  2013-09-30  6:27     ` Ingo Molnar
  1 sibling, 0 replies; 376+ messages in thread
From: Markus Trippelsdorf @ 2013-09-29 22:47 UTC (permalink / raw)
  To: Andi Kleen
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Arnaldo Carvalho de Melo

On 2013.09.29 at 14:33 -0700, Andi Kleen wrote:
> > breaks "perf top" on my machine. I just see a gray screen with no text
> > at all. Sometimes the following error messages are printed:
> >  *** Error in `perf': invalid fastbin entry (free): 0x00000000029b18c0 ***
> >  *** Error in `perf': malloc(): memory corruption (fast): 0x0000000000ee0b10 ***
> 
> Hmm, works for me. In fact I wrote it to fix a perf top issue.
> 
> What does valgrind say?

Here's the -fsanitize=address output instead:

markus@x4 perf % perf top --stdio 2>&1 | asan_symbolize.py
=================================================================
==24617== ERROR: AddressSanitizer: heap-buffer-overflow on address 0x600c0000b638 at pc 0x7f2683fad79d bp 0x7fffbb8ec3b0 sp 0x7fffbb8ebb70
WRITE of size 9 at 0x600c0000b638 thread T0
    #0 0x7f2683fad79c in __interceptor_strcpy ??:?
    #1 0x4e422c in strcpy /usr/include/bits/string3.h:104
    #2 0x4ddeff in dso__load /usr/src/linux/tools/perf/util/symbol.c:1085
    #3 0x509058 in map__load /usr/src/linux/tools/perf/util/map.c:159
    #4 0x49fa6b in perf_event__preprocess_sample /usr/src/linux/tools/perf/util/event.c:762
    #5 0x455fa0 in perf_event__process_sample /usr/src/linux/tools/perf/builtin-top.c:719
    #6 0x45be8e in perf_top__mmap_read /usr/src/linux/tools/perf/builtin-top.c:870
    #7 0x41f88d in run_builtin /usr/src/linux/tools/perf/perf.c:319
    #8 0x41bc05 in run_argv /usr/src/linux/tools/perf/perf.c:376
    #9 0x7f2682d41a74 in __libc_start_main /home/markus/glibc/csu/libc-start.c:269
    #10 0x41e948 in _start /home/markus/glibc/csu/../sysdeps/x86_64/start.S:122
0x600c0000b63d is located 0 bytes to the right of 61-byte region [0x600c0000b600,0x600c0000b63d)
allocated by thread T0 here:
    #0 0x7f2683fb6d6f in __interceptor_realloc ??:?
    #1 0x4e420f in dso__load_sym /usr/src/linux/tools/perf/util/symbol-elf.c:951
    #2 0x4ddeff in dso__load /usr/src/linux/tools/perf/util/symbol.c:1085
    #3 0x509058 in map__load /usr/src/linux/tools/perf/util/map.c:159
    #4 0x49fa6b in perf_event__preprocess_sample /usr/src/linux/tools/perf/util/event.c:762
    #5 0x455fa0 in perf_event__process_sample /usr/src/linux/tools/perf/builtin-top.c:719
    #6 0x45be8e in perf_top__mmap_read /usr/src/linux/tools/perf/builtin-top.c:870
    #7 0x41f88d in run_builtin /usr/src/linux/tools/perf/perf.c:319
    #8 0x41bc05 in run_argv /usr/src/linux/tools/perf/perf.c:376
    #9 0x7f2682d41a74 in __libc_start_main /home/markus/glibc/csu/libc-start.c:269
Shadow bytes around the buggy address:
  0x0c01ffff9670: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x0c01ffff9680: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x0c01ffff9690: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x0c01ffff96a0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x0c01ffff96b0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
=>0x0c01ffff96c0: 00 00 00 00 00 00 00[05]fa fa fa fa fd fd fd fd
  0x0c01ffff96d0: fd fd fd fd fa fa fa fa fd fd fd fd fd fd fd fd
  0x0c01ffff96e0: fa fa fa fa fd fd fd fd fd fd fd fa fa fa fa fa
  0x0c01ffff96f0: fd fd fd fd fd fd fd fd fa fa fa fa fd fd fd fd
  0x0c01ffff9700: fd fd fd fd fa fa fa fa fd fd fd fd fd fd fd fd
  0x0c01ffff9710: fa fa fa fa fd fd fd fd fd fd fd fd fa fa fa fa
Shadow byte legend (one shadow byte represents 8 application bytes):
  Addressable:           00
  Partially addressable: 01 02 03 04 05 06 07
  Heap left redzone:     fa
  Heap righ redzone:     fb
  Freed Heap region:     fd
  Stack left redzone:    f1
  Stack mid redzone:     f2
  Stack right redzone:   f3
  Stack partial redzone: f4
  Stack after return:    f5
  Stack use after scope: f8
  Global redzone:        f9
  Global init order:     f6
  Poisoned by user:      f7
  ASan internal:         fe
==24617== ABORTING

And please note that cloned functions are demangled just fine on my machine
even without your patch, e.g.:

 10.61%  libQtGui.so.4.8.5   [.] QFontEngineFT::stringToCMap(QChar const*, int, QGlyphLayout*, int*, QFlags<QTextEngine::ShaperFlag>) const [clone .part.20]

-- 
Markus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-29 11:47 ` Markus Trippelsdorf
@ 2013-09-29 21:33   ` Andi Kleen
  2013-09-29 22:47     ` Markus Trippelsdorf
  2013-09-30  6:27     ` Ingo Molnar
  0 siblings, 2 replies; 376+ messages in thread
From: Andi Kleen @ 2013-09-29 21:33 UTC (permalink / raw)
  To: Markus Trippelsdorf
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Arnaldo Carvalho de Melo

> breaks "perf top" on my machine. I just see a gray screen with no text
> at all. Sometimes the following error messages are printed:
>  *** Error in `perf': invalid fastbin entry (free): 0x00000000029b18c0 ***
>  *** Error in `perf': malloc(): memory corruption (fast): 0x0000000000ee0b10 ***

Hmm, works for me. In fact I wrote it to fix a perf top issue.

What does valgrind say?

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-28 18:03 Ingo Molnar
@ 2013-09-29 11:47 ` Markus Trippelsdorf
  2013-09-29 21:33   ` Andi Kleen
  0 siblings, 1 reply; 376+ messages in thread
From: Markus Trippelsdorf @ 2013-09-29 11:47 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Andi Kleen, Arnaldo Carvalho de Melo

On 2013.09.28 at 20:03 +0200, Ingo Molnar wrote:
> Andi Kleen (1):
>       perf symbols: Demangle cloned functions

The commit above e95ab53645:

 commit de95ab53645a2f0015e0f68ee723f18dce2b8b51
 Author: Andi Kleen <ak@linux.intel.com>
 Date:   Thu Sep 12 08:16:38 2013 -0700

     perf symbols: Demangle cloned functions

breaks "perf top" on my machine. I just see a gray screen with no text
at all. Sometimes the following error messages are printed:
 *** Error in `perf': invalid fastbin entry (free): 0x00000000029b18c0 ***
 *** Error in `perf': malloc(): memory corruption (fast): 0x0000000000ee0b10 ***

Reverting the commit "fixes" the issue.

-- 
Markus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-09-28 18:03 Ingo Molnar
  2013-09-29 11:47 ` Markus Trippelsdorf
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-28 18:03 UTC (permalink / raw)
  To: Linus Torvalds; +Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 8a3da6c7d0031fcb6a0d17f9c7a68b0e01f52855 perf/x86: Fix PMU detection printout when no PMU is detected

A couple of tooling fixlets and a PMU detection printout fix.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf machine: Fix path unpopulated in machine__create_modules()

Andi Kleen (1):
      perf symbols: Demangle cloned functions

David Ahern (2):
      perf trace: Add mmap2 handler
      perf tools: Explicitly add libdl dependency

Ingo Molnar (1):
      perf/x86: Fix PMU detection printout when no PMU is detected

Jiri Olsa (1):
      perf kmem: Make it work again on non NUMA machines

Masami Hiramatsu (1):
      perf probe: Fix probing symbols with optimization suffix


 arch/x86/kernel/cpu/perf_event.c |  2 +-
 tools/perf/builtin-kmem.c        |  2 +-
 tools/perf/builtin-trace.c       |  1 +
 tools/perf/config/Makefile       |  2 +-
 tools/perf/util/machine.c        |  2 +-
 tools/perf/util/probe-finder.c   | 77 +++++++++++++++++++++-------------------
 tools/perf/util/probe-finder.h   |  3 ++
 tools/perf/util/symbol-elf.c     | 27 +++++++++++++-
 8 files changed, 75 insertions(+), 41 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a9c606b..897783b 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		break;
 	default:
-		return 0;
+		err = -ENOTSUPP;
 	}
 	if (err != 0) {
 		pr_cont("no PMU driver, software events only.\n");
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index c2dff9c..9b5f077 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -101,7 +101,7 @@ static int setup_cpunode_map(void)
 
 	dir1 = opendir(PATH_SYS_NODE);
 	if (!dir1)
-		return -1;
+		return 0;
 
 	while ((dent1 = readdir(dir1)) != NULL) {
 		if (dent1->d_type != DT_DIR ||
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index fd48534..71aa3e3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1055,6 +1055,7 @@ static int trace__replay(struct trace *trace)
 
 	trace->tool.sample	  = trace__process_sample;
 	trace->tool.mmap	  = perf_event__process_mmap;
+	trace->tool.mmap2	  = perf_event__process_mmap2;
 	trace->tool.comm	  = perf_event__process_comm;
 	trace->tool.exit	  = perf_event__process_exit;
 	trace->tool.fork	  = perf_event__process_fork;
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 346ee92..5f6f9b3 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -87,7 +87,7 @@ CFLAGS += -Wall
 CFLAGS += -Wextra
 CFLAGS += -std=gnu99
 
-EXTLIBS = -lelf -lpthread -lrt -lm
+EXTLIBS = -lelf -lpthread -lrt -lm -ldl
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
   CFLAGS += -fstack-protector-all
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 933d14f..6188d28 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -792,7 +792,7 @@ static int machine__create_modules(struct machine *machine)
 		modules = path;
 	}
 
-	if (symbol__restricted_filename(path, "/proc/modules"))
+	if (symbol__restricted_filename(modules, "/proc/modules"))
 		return -1;
 
 	file = fopen(modules, "r");
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 20c7299..371476c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -118,7 +118,6 @@ static const Dwfl_Callbacks offline_callbacks = {
 static int debuginfo__init_offline_dwarf(struct debuginfo *self,
 					 const char *path)
 {
-	Dwfl_Module *mod;
 	int fd;
 
 	fd = open(path, O_RDONLY);
@@ -129,11 +128,11 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *self,
 	if (!self->dwfl)
 		goto error;
 
-	mod = dwfl_report_offline(self->dwfl, "", "", fd);
-	if (!mod)
+	self->mod = dwfl_report_offline(self->dwfl, "", "", fd);
+	if (!self->mod)
 		goto error;
 
-	self->dbg = dwfl_module_getdwarf(mod, &self->bias);
+	self->dbg = dwfl_module_getdwarf(self->mod, &self->bias);
 	if (!self->dbg)
 		goto error;
 
@@ -676,37 +675,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 }
 
 /* Convert subprogram DIE to trace point */
-static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
-				  bool retprobe, struct probe_trace_point *tp)
+static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
+				  Dwarf_Addr paddr, bool retprobe,
+				  struct probe_trace_point *tp)
 {
 	Dwarf_Addr eaddr, highaddr;
-	const char *name;
-
-	/* Copy the name of probe point */
-	name = dwarf_diename(sp_die);
-	if (name) {
-		if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-			pr_warning("Failed to get entry address of %s\n",
-				   dwarf_diename(sp_die));
-			return -ENOENT;
-		}
-		if (dwarf_highpc(sp_die, &highaddr) != 0) {
-			pr_warning("Failed to get end address of %s\n",
-				   dwarf_diename(sp_die));
-			return -ENOENT;
-		}
-		if (paddr > highaddr) {
-			pr_warning("Offset specified is greater than size of %s\n",
-				   dwarf_diename(sp_die));
-			return -EINVAL;
-		}
-		tp->symbol = strdup(name);
-		if (tp->symbol == NULL)
-			return -ENOMEM;
-		tp->offset = (unsigned long)(paddr - eaddr);
-	} else
-		/* This function has no name. */
-		tp->offset = (unsigned long)paddr;
+	GElf_Sym sym;
+	const char *symbol;
+
+	/* Verify the address is correct */
+	if (dwarf_entrypc(sp_die, &eaddr) != 0) {
+		pr_warning("Failed to get entry address of %s\n",
+			   dwarf_diename(sp_die));
+		return -ENOENT;
+	}
+	if (dwarf_highpc(sp_die, &highaddr) != 0) {
+		pr_warning("Failed to get end address of %s\n",
+			   dwarf_diename(sp_die));
+		return -ENOENT;
+	}
+	if (paddr > highaddr) {
+		pr_warning("Offset specified is greater than size of %s\n",
+			   dwarf_diename(sp_die));
+		return -EINVAL;
+	}
+
+	/* Get an appropriate symbol from symtab */
+	symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+	if (!symbol) {
+		pr_warning("Failed to find symbol at 0x%lx\n",
+			   (unsigned long)paddr);
+		return -ENOENT;
+	}
+	tp->offset = (unsigned long)(paddr - sym.st_value);
+	tp->symbol = strdup(symbol);
+	if (!tp->symbol)
+		return -ENOMEM;
 
 	/* Return probe must be on the head of a subprogram */
 	if (retprobe) {
@@ -1149,7 +1153,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	tev = &tf->tevs[tf->ntevs++];
 
 	/* Trace point should be converted from subprogram DIE */
-	ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+	ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
 				     pf->pev->point.retprobe, &tev->point);
 	if (ret < 0)
 		return ret;
@@ -1181,7 +1185,7 @@ int debuginfo__find_trace_events(struct debuginfo *self,
 {
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
-			.max_tevs = max_tevs};
+			.mod = self->mod, .max_tevs = max_tevs};
 	int ret;
 
 	/* Allocate result tevs array */
@@ -1250,7 +1254,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 	vl = &af->vls[af->nvls++];
 
 	/* Trace point should be converted from subprogram DIE */
-	ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+	ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr,
 				     pf->pev->point.retprobe, &vl->point);
 	if (ret < 0)
 		return ret;
@@ -1289,6 +1293,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self,
 {
 	struct available_var_finder af = {
 			.pf = {.pev = pev, .callback = add_available_vars},
+			.mod = self->mod,
 			.max_vls = max_vls, .externs = externs};
 	int ret;
 
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 17e94d0..3b7d630 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -23,6 +23,7 @@ static inline int is_c_varname(const char *name)
 /* debug information structure */
 struct debuginfo {
 	Dwarf		*dbg;
+	Dwfl_Module	*mod;
 	Dwfl		*dwfl;
 	Dwarf_Addr	bias;
 };
@@ -77,6 +78,7 @@ struct probe_finder {
 
 struct trace_event_finder {
 	struct probe_finder	pf;
+	Dwfl_Module		*mod;		/* For solving symbols */
 	struct probe_trace_event *tevs;		/* Found trace events */
 	int			ntevs;		/* Number of trace events */
 	int			max_tevs;	/* Max number of trace events */
@@ -84,6 +86,7 @@ struct trace_event_finder {
 
 struct available_var_finder {
 	struct probe_finder	pf;
+	Dwfl_Module		*mod;		/* For solving symbols */
 	struct variable_list	*vls;		/* Found variable lists */
 	int			nvls;		/* Number of variable lists */
 	int			max_vls;	/* Max no. of variable lists */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a9c829b..d2a888e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -928,8 +928,33 @@ int dso__load_sym(struct dso *dso, struct map *map,
 		 * to it...
 		 */
 		if (symbol_conf.demangle) {
-			demangled = bfd_demangle(NULL, elf_name,
+			/*
+			 * The demangler doesn't deal with cloned functions.
+			 * XXXX.clone.NUM or similar
+			 * Strip the dot part and readd it later.
+			 */
+			char *p = (char *)elf_name, *dot;
+			dot = strchr(elf_name, '.');
+			if (dot) {
+				p = strdup(elf_name);
+				if (!p)
+					goto new_symbol;
+				dot = strchr(p, '.');
+				*dot = 0;
+			}
+
+			demangled = bfd_demangle(NULL, p,
 						 DMGL_PARAMS | DMGL_ANSI);
+			if (dot)
+				*dot = '.';
+			if (demangled && dot) {
+				demangled = realloc(demangled, strlen(demangled) + strlen(dot) + 1);
+				if (!demangled)
+					goto new_symbol;
+				strcpy(demangled + (dot - p), dot);
+			}
+			if (p != elf_name)
+				free(p);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-09-25 18:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-09-25 18:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: cf3b425dd8d99e01214515a6754f9e69ecc6dce8 perf/x86/intel: Add model number for Avoton Silvermont

Assorted standalone fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (3):
      perf annotate: Fix objdump line parsing offset validation
      perf tools: Fix buildid cache handling of kallsyms with kcore
      perf tools: Fix compile with libelf without get_phdrnum

Arnaldo Carvalho de Melo (1):
      perf session: Check for SIGINT in more loops

Ingo Molnar (3):
      perf tools: Sharpen the libaudit dependencies test
      perf tools: Fill in new definitions for madvise()/mmap() flags
      perf tools: Fix old GCC build error in trace-event-parse.c:parse_proc_kallsyms()

Masami Hiramatsu (1):
      perf probe: Fix finder to find lines of given function

Peter Zijlstra (2):
      perf: Update ABI comment
      perf: Fix capabilities bitfield compatibility in 'struct perf_event_mmap_page'

Vinson Lee (1):
      tools lib lk: Uninclude linux/magic.h in debugfs.c

Yan, Zheng (2):
      perf/x86/intel/uncore: Don't use smp_processor_id() in validate_group()
      perf/x86/intel: Add model number for Avoton Silvermont


 arch/x86/kernel/cpu/perf_event.c              | 10 +++----
 arch/x86/kernel/cpu/perf_event_intel.c        |  1 +
 arch/x86/kernel/cpu/perf_event_intel_uncore.c | 10 +++----
 include/uapi/linux/perf_event.h               | 15 ++++++----
 kernel/events/core.c                          | 21 ++++++++++++++
 tools/lib/lk/debugfs.c                        |  1 -
 tools/perf/arch/x86/util/tsc.c                |  6 ++--
 tools/perf/builtin-inject.c                   |  2 --
 tools/perf/builtin-report.c                   |  5 ++--
 tools/perf/builtin-script.c                   |  2 --
 tools/perf/builtin-trace.c                    | 17 +++++++++++
 tools/perf/config/Makefile                    |  3 ++
 tools/perf/config/feature-tests.mak           | 10 +++++++
 tools/perf/util/annotate.c                    |  2 +-
 tools/perf/util/dwarf-aux.c                   | 19 +++++++++++++
 tools/perf/util/dwarf-aux.h                   |  3 ++
 tools/perf/util/header.c                      | 41 ++++++++++++++++++---------
 tools/perf/util/hist.c                        |  2 ++
 tools/perf/util/probe-finder.c                | 12 ++++----
 tools/perf/util/session.c                     |  9 ++++--
 tools/perf/util/session.h                     |  4 +++
 tools/perf/util/symbol-elf.c                  | 16 +++++++++++
 tools/perf/util/trace-event-parse.c           |  2 +-
 23 files changed, 164 insertions(+), 49 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84..a9c606b 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1883,9 +1883,9 @@ static struct pmu pmu = {
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
-	userpg->cap_usr_time = 0;
-	userpg->cap_usr_time_zero = 0;
-	userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		return;
 
-	userpg->cap_usr_time = 1;
+	userpg->cap_user_time = 1;
 	userpg->time_mult = this_cpu_read(cyc2ns);
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
 	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_usr_time_zero = 1;
+		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = this_cpu_read(cyc2ns_offset);
 	}
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9db76c3..f31a165 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* Atom 22nm "Silvermont" */
+	case 77: /* Avoton "Silvermont" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 8ed4458..4118f9f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
 	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
-	box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu));
+	box = kzalloc_node(size, GFP_KERNEL, node);
 	if (!box)
 		return NULL;
 
@@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
-	fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
 
@@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
-	box = uncore_alloc_box(type, 0);
+	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
 
@@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 			if (pmu->func_id < 0)
 				pmu->func_id = j;
 
-			box = uncore_alloc_box(type, cpu);
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				return -ENOMEM;
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 40a1fb8..009a655 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -380,10 +380,13 @@ struct perf_event_mmap_page {
 	union {
 		__u64	capabilities;
 		struct {
-			__u64	cap_usr_time		: 1,
-				cap_usr_rdpmc		: 1,
-				cap_usr_time_zero	: 1,
-				cap_____res		: 61;
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
 		};
 	};
 
@@ -442,12 +445,13 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u64	__reserved[119];	/* align to 1k */
+	__u8	__reserved[118*8+4];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.
@@ -528,6 +532,7 @@ enum perf_event_type {
 	 *	u64				len;
 	 *	u64				pgoff;
 	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_MMAP			= 1,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b6..cb4238e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
 	*running = ctx_time - event->tstamp_running;
 }
 
+static void perf_event_init_userpage(struct perf_event *event)
+{
+	struct perf_event_mmap_page *userpg;
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	if (!rb)
+		goto unlock;
+
+	userpg = rb->user_page;
+
+	/* Allow new userspace to detect that bit 0 is deprecated */
+	userpg->cap_bit0_is_deprecated = 1;
+	userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+	rcu_read_unlock();
+}
+
 void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
@@ -4044,6 +4064,7 @@ again:
 	ring_buffer_attach(event, rb);
 	rcu_assign_pointer(event->rb, rb);
 
+	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
 
 unlock:
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c
index 099e7cd..7c43479 100644
--- a/tools/lib/lk/debugfs.c
+++ b/tools/lib/lk/debugfs.c
@@ -5,7 +5,6 @@
 #include <stdbool.h>
 #include <sys/vfs.h>
 #include <sys/mount.h>
-#include <linux/magic.h>
 #include <linux/kernel.h>
 
 #include "debugfs.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 9570c2b..b2519e4 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc)
 {
-	bool cap_usr_time_zero;
+	bool cap_user_time_zero;
 	u32 seq;
 	int i = 0;
 
@@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 		tc->time_mult = pc->time_mult;
 		tc->time_shift = pc->time_shift;
 		tc->time_zero = pc->time_zero;
-		cap_usr_time_zero = pc->cap_usr_time_zero;
+		cap_user_time_zero = pc->cap_user_time_zero;
 		rmb();
 		if (pc->lock == seq && !(seq & 1))
 			break;
@@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 		}
 	}
 
-	if (!cap_usr_time_zero)
+	if (!cap_user_time_zero)
 		return -EOPNOTSUPP;
 
 	return 0;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 423875c..afe377b 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -321,8 +321,6 @@ found:
 	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8e50d8d..72eae74 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -401,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 	return 0;
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -568,6 +566,9 @@ static int __cmd_report(struct perf_report *rep)
 		}
 	}
 
+	if (session_done())
+		return 0;
+
 	if (nr_samples == 0) {
 		ui__error("The %s file has no samples!\n", session->filename);
 		return 0;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7f31a3d..9c333ff 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -553,8 +553,6 @@ static struct perf_tool perf_script = {
 	.ordering_requires_timestamps = true,
 };
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f5aa637..fd48534 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,6 +16,23 @@
 #include <sys/mman.h>
 #include <linux/futex.h>
 
+/* For older distros: */
+#ifndef MAP_STACK
+# define MAP_STACK		0x20000
+#endif
+
+#ifndef MADV_HWPOISON
+# define MADV_HWPOISON		100
+#endif
+
+#ifndef MADV_MERGEABLE
+# define MADV_MERGEABLE		12
+#endif
+
+#ifndef MADV_UNMERGEABLE
+# define MADV_UNMERGEABLE	13
+#endif
+
 static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
 					 unsigned long arg,
 					 u8 arg_idx __maybe_unused,
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 214e17e..346ee92 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -180,6 +180,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
 ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
   CFLAGS += -DLIBELF_MMAP
 endif
+ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y)
+  CFLAGS += -DHAVE_ELF_GETPHDRNUM
+endif
 
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 708fb8e..d5a8dd4 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -61,6 +61,15 @@ int main(void)
 }
 endef
 
+define SOURCE_ELF_GETPHDRNUM
+#include <libelf.h>
+int main(void)
+{
+	size_t dst;
+	return elf_getphdrnum(0, &dst);
+}
+endef
+
 ifndef NO_SLANG
 define SOURCE_SLANG
 #include <slang.h>
@@ -210,6 +219,7 @@ define SOURCE_LIBAUDIT
 
 int main(void)
 {
+	printf(\"error message: %s\n\", audit_errno_to_name(0));
 	return audit_open();
 }
 endef
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index bfc5a27..7eae548 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 		    end = map__rip_2objdump(map, sym->end);
 
 		offset = line_ip - start;
-		if (offset < 0 || (u64)line_ip > end)
+		if ((u64)line_ip < start || (u64)line_ip > end)
 			offset = -1;
 		else
 			parsed_line = tmp2 + 1;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 3e5f543..e23bde1 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die)
 }
 
 /**
+ * die_is_func_def - Ensure that this DIE is a subprogram and definition
+ * @dw_die: a DIE
+ *
+ * Ensure that this DIE is a subprogram and NOT a declaration. This
+ * returns true if @dw_die is a function definition.
+ **/
+bool die_is_func_def(Dwarf_Die *dw_die)
+{
+	Dwarf_Attribute attr;
+
+	return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
+		dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+}
+
+/**
  * die_get_data_member_location - Get the data-member offset
  * @mb_die: a DIE of a member of a data structure
  * @offs: The offset of the member in the data structure
@@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
 	struct __addr_die_search_param *ad = data;
 
+	/*
+	 * Since a declaration entry doesn't has given pc, this always returns
+	 * function definition entry.
+	 */
 	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
 	    dwarf_haspc(fn_die, ad->addr)) {
 		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 6ce1717..8658d41 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
 extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 			int (*callback)(Dwarf_Die *, void *), void *data);
 
+/* Ensure that this DIE is a subprogram and definition (not declaration) */
+extern bool die_is_func_def(Dwarf_Die *dw_die);
+
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26441d0..ce69901 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -199,9 +199,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
-				u16 misc, int fd)
+static int __dsos__write_buildid_table(struct list_head *head,
+				       struct machine *machine,
+				       pid_t pid, u16 misc, int fd)
 {
+	char nm[PATH_MAX];
 	struct dso *pos;
 
 	dsos__for_each_with_build_id(pos, head) {
@@ -215,6 +217,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
 		if (is_vdso_map(pos->short_name)) {
 			name = (char *) VDSO__MAP_NAME;
 			name_len = sizeof(VDSO__MAP_NAME) + 1;
+		} else if (dso__is_kcore(pos)) {
+			machine__mmap_name(machine, nm, sizeof(nm));
+			name = nm;
+			name_len = strlen(nm) + 1;
 		} else {
 			name = pos->long_name;
 			name_len = pos->long_name_len + 1;
@@ -240,10 +246,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 		umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
-					  kmisc, fd);
+	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+					  machine->pid, kmisc, fd);
 	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos,
+		err = __dsos__write_buildid_table(&machine->user_dsos, machine,
 						  machine->pid, umisc, fd);
 	return err;
 }
@@ -375,23 +381,31 @@ out_free:
 	return err;
 }
 
-static int dso__cache_build_id(struct dso *dso, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       const char *debugdir)
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
 	bool is_vdso = is_vdso_map(dso->short_name);
+	char *name = dso->long_name;
+	char nm[PATH_MAX];
 
-	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
-				     dso->long_name, debugdir,
-				     is_kallsyms, is_vdso);
+	if (dso__is_kcore(dso)) {
+		is_kallsyms = true;
+		machine__mmap_name(machine, nm, sizeof(nm));
+		name = nm;
+	}
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+				     debugdir, is_kallsyms, is_vdso);
 }
 
-static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+static int __dsos__cache_build_ids(struct list_head *head,
+				   struct machine *machine, const char *debugdir)
 {
 	struct dso *pos;
 	int err = 0;
 
 	dsos__for_each_with_build_id(pos, head)
-		if (dso__cache_build_id(pos, debugdir))
+		if (dso__cache_build_id(pos, machine, debugdir))
 			err = -1;
 
 	return err;
@@ -399,8 +413,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
 
 static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+					  debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
 	return ret;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 46a0d35..9ff6cf3 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -611,6 +611,8 @@ void hists__collapse_resort(struct hists *hists)
 	next = rb_first(root);
 
 	while (next) {
+		if (session_done())
+			break;
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index be03293..20c7299 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -734,7 +734,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	}
 
 	/* If not a real subprogram, find a real one */
-	if (dwarf_tag(sc_die) != DW_TAG_subprogram) {
+	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
 			pr_warning("Failed to find probe point in any "
 				   "functions.\n");
@@ -980,12 +980,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	struct dwarf_callback_param *param = data;
 	struct probe_finder *pf = param->data;
 	struct perf_probe_point *pp = &pf->pev->point;
-	Dwarf_Attribute attr;
 
 	/* Check tag and diename */
-	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
-	    !die_compare_name(sp_die, pp->function) ||
-	    dwarf_attr(sp_die, DW_AT_declaration, &attr))
+	if (!die_is_func_def(sp_die) ||
+	    !die_compare_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
@@ -1474,7 +1472,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 	return 0;
 }
 
-/* Search function from function name */
+/* Search function definition from function name */
 static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
 	struct dwarf_callback_param *param = data;
@@ -1485,7 +1483,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
-	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
+	if (die_is_func_def(sp_die) &&
 	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 51f5edf..70ffa41 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -531,6 +531,9 @@ static int flush_sample_queue(struct perf_session *s,
 		return 0;
 
 	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (session_done())
+			return 0;
+
 		if (iter->timestamp > limit)
 			break;
 
@@ -1160,7 +1163,6 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 	}
 }
 
-#define session_done()	(*(volatile int *)(&session_done))
 volatile int session_done;
 
 static int __perf_session__process_pipe_events(struct perf_session *self,
@@ -1372,10 +1374,13 @@ more:
 				    "Processing events...");
 	}
 
+	err = 0;
+	if (session_done())
+		goto out_err;
+
 	if (file_pos < file_size)
 		goto more;
 
-	err = 0;
 	/* do the final flush for ordered samples */
 	session->ordered_samples.next_flush = ULLONG_MAX;
 	err = flush_sample_queue(session, tool);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3aa75fb..04bf737 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -124,4 +124,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 #define perf_session__set_tracepoints_handlers(session, array) \
 	__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
+
+extern volatile int session_done;
+
+#define session_done()	(*(volatile int *)(&session_done))
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a7b9ab5..a9c829b 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -8,6 +8,22 @@
 #include "symbol.h"
 #include "debug.h"
 
+#ifndef HAVE_ELF_GETPHDRNUM
+static int elf_getphdrnum(Elf *elf, size_t *dst)
+{
+	GElf_Ehdr gehdr;
+	GElf_Ehdr *ehdr;
+
+	ehdr = gelf_getehdr(elf, &gehdr);
+	if (!ehdr)
+		return -1;
+
+	*dst = ehdr->e_phnum;
+
+	return 0;
+}
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index fe7a27d..e9e1c03 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -186,7 +186,7 @@ void parse_proc_kallsyms(struct pevent *pevent,
 	char *next = NULL;
 	char *addr_str;
 	char *mod;
-	char *fmt;
+	char *fmt = NULL;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-09-18 16:06 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-09-18 16:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: a8e0108cac181a7b141dacaa99ea52efaf9b5f07 perf: Fix UAPI export of PERF_EVENT_IOC_ID

Two small fixes.

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      perf/x86/intel: Fix Silvermont offcore masks

Vince Weaver (1):
      perf: Fix UAPI export of PERF_EVENT_IOC_ID


 arch/x86/kernel/cpu/perf_event_intel.c | 4 ++--
 include/uapi/linux/perf_event.h        | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index c62d883..9db76c3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -899,8 +899,8 @@ static __initconst const u64 atom_hw_cache_event_ids
 static struct extra_reg intel_slm_extra_regs[] __read_mostly =
 {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
-	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffff, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffff, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ca1d90b..40a1fb8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -324,7 +324,7 @@ struct perf_event_attr {
 #define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
 #define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
 #define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
-#define PERF_EVENT_IOC_ID		_IOR('$', 7, u64 *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-13  9:45                         ` Ingo Molnar
@ 2013-09-13 17:15                           ` Jean Pihet
  0 siblings, 0 replies; 376+ messages in thread
From: Jean Pihet @ 2013-09-13 17:15 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: David Ahern, Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton

On 13 September 2013 11:45, Ingo Molnar <mingo@kernel.org> wrote:
>
> * Jean Pihet <jean.pihet@linaro.org> wrote:
>
>> Hi,
>>
>> On 13 September 2013 07:09, Ingo Molnar <mingo@kernel.org> wrote:
>> >
>> > * David Ahern <dsahern@gmail.com> wrote:
>> >
>> >> > By default a simple 'make' should build perf to the maximum extent
>> >> > possible, with no other input required from the user - with warnings
>> >> > displayed as package install suggestions.
>> >>
>> >> By default there is no config. Autoprobing generates a first one or a
>> >> user can specify a defconfig.
>> >
>> > This could work if there's not two but three states for individual
>> > features:
>> >
>> >   - autoprobe
>> >   - on
>> >   - off
>> >
>> > and if autoprobe, if a system feature has been probed successfully,
>> > automatically turned 'autoprobe' entries into 'on'.
>> >
>> > That would give us the best of all worlds - autodetection, configurability
>> > and caching:
>> >
>> >  - initial user types 'make' and gets a .config that has almost all
>> >    entries 'on', a few 'autoprobe'.
>> >
>> >  - once the user installs a dependency, the corresponding .config entry
>> >    turns into 'on'.
>> >
>> >  - the regular user or developers would have libraries that turn all
>> >    entries in the .config to 'on'.
>> >
>> >  - if a user is genuinely uninterested in a feature, he can mark it 'off',
>> >    which would then stay off permanently. This could also be used by
>> >    embedded/specialized builds.
>> >
>> >  - other specialized users, like distro builds, could use a .config with
>> >    all entries 'on' and could enforce the presence of all dependencies for
>> >    a successful build. [We could add 'make allyesconfig' to help that.]
>>
>> Is there a way to detect the presence of a dependency and _also_ check
>> its version? Some new features are depending on a recent version of a
>> library, e.g. dwarf unwinding depends on libunwind >= 1.1 (cf.
>> http://www.spinics.net/lists/kernel/msg1598951.html).
>
> Yeah, see the testcases in tools/perf/config/feature-tests.mak, they
> typically include the latest library API usages, which will fail on older
> versions.
Ok!
I just sent a patch to feature-tests.mak for the newly added dwarf
unwinding feature ('perf tools: Check libunwind for availability of
dwarf parsing feature').

Thanks,
Jean

>
> That kind of 'does it actually work?' test is a lot more robust than
> explicit version checks, and combined with caching it should be fast and
> parallelizable as well. (One of the problems of the current simple
> implementation of the feature tests is that they are 20 serial tests with
> no parallelization.)
>
> Thanks,
>
>         Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-13  9:32                       ` Jean Pihet
@ 2013-09-13  9:45                         ` Ingo Molnar
  2013-09-13 17:15                           ` Jean Pihet
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-13  9:45 UTC (permalink / raw)
  To: Jean Pihet
  Cc: David Ahern, Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton


* Jean Pihet <jean.pihet@linaro.org> wrote:

> Hi,
> 
> On 13 September 2013 07:09, Ingo Molnar <mingo@kernel.org> wrote:
> >
> > * David Ahern <dsahern@gmail.com> wrote:
> >
> >> > By default a simple 'make' should build perf to the maximum extent
> >> > possible, with no other input required from the user - with warnings
> >> > displayed as package install suggestions.
> >>
> >> By default there is no config. Autoprobing generates a first one or a
> >> user can specify a defconfig.
> >
> > This could work if there's not two but three states for individual
> > features:
> >
> >   - autoprobe
> >   - on
> >   - off
> >
> > and if autoprobe, if a system feature has been probed successfully,
> > automatically turned 'autoprobe' entries into 'on'.
> >
> > That would give us the best of all worlds - autodetection, configurability
> > and caching:
> >
> >  - initial user types 'make' and gets a .config that has almost all
> >    entries 'on', a few 'autoprobe'.
> >
> >  - once the user installs a dependency, the corresponding .config entry
> >    turns into 'on'.
> >
> >  - the regular user or developers would have libraries that turn all
> >    entries in the .config to 'on'.
> >
> >  - if a user is genuinely uninterested in a feature, he can mark it 'off',
> >    which would then stay off permanently. This could also be used by
> >    embedded/specialized builds.
> >
> >  - other specialized users, like distro builds, could use a .config with
> >    all entries 'on' and could enforce the presence of all dependencies for
> >    a successful build. [We could add 'make allyesconfig' to help that.]
> 
> Is there a way to detect the presence of a dependency and _also_ check 
> its version? Some new features are depending on a recent version of a 
> library, e.g. dwarf unwinding depends on libunwind >= 1.1 (cf. 
> http://www.spinics.net/lists/kernel/msg1598951.html).

Yeah, see the testcases in tools/perf/config/feature-tests.mak, they 
typically include the latest library API usages, which will fail on older 
versions.

That kind of 'does it actually work?' test is a lot more robust than 
explicit version checks, and combined with caching it should be fast and 
parallelizable as well. (One of the problems of the current simple 
implementation of the feature tests is that they are 20 serial tests with 
no parallelization.)

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-13  5:09                     ` Ingo Molnar
@ 2013-09-13  9:32                       ` Jean Pihet
  2013-09-13  9:45                         ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Jean Pihet @ 2013-09-13  9:32 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: David Ahern, Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton

Hi,

On 13 September 2013 07:09, Ingo Molnar <mingo@kernel.org> wrote:
>
> * David Ahern <dsahern@gmail.com> wrote:
>
>> > By default a simple 'make' should build perf to the maximum extent
>> > possible, with no other input required from the user - with warnings
>> > displayed as package install suggestions.
>>
>> By default there is no config. Autoprobing generates a first one or a
>> user can specify a defconfig.
>
> This could work if there's not two but three states for individual
> features:
>
>   - autoprobe
>   - on
>   - off
>
> and if autoprobe, if a system feature has been probed successfully,
> automatically turned 'autoprobe' entries into 'on'.
>
> That would give us the best of all worlds - autodetection, configurability
> and caching:
>
>  - initial user types 'make' and gets a .config that has almost all
>    entries 'on', a few 'autoprobe'.
>
>  - once the user installs a dependency, the corresponding .config entry
>    turns into 'on'.
>
>  - the regular user or developers would have libraries that turn all
>    entries in the .config to 'on'.
>
>  - if a user is genuinely uninterested in a feature, he can mark it 'off',
>    which would then stay off permanently. This could also be used by
>    embedded/specialized builds.
>
>  - other specialized users, like distro builds, could use a .config with
>    all entries 'on' and could enforce the presence of all dependencies for
>    a successful build. [We could add 'make allyesconfig' to help that.]

Is there a way to detect the presence of a dependency and _also_ check
its version? Some new features are depending on a recent version of a
library, e.g. dwarf unwinding depends on libunwind >= 1.1 (cf.
http://www.spinics.net/lists/kernel/msg1598951.html).

Thanks,
Jean

>
> Thanks,
>
>         Ingo
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 22:10                   ` David Ahern
@ 2013-09-13  5:09                     ` Ingo Molnar
  2013-09-13  9:32                       ` Jean Pihet
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-13  5:09 UTC (permalink / raw)
  To: David Ahern
  Cc: Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton


* David Ahern <dsahern@gmail.com> wrote:

> > By default a simple 'make' should build perf to the maximum extent 
> > possible, with no other input required from the user - with warnings 
> > displayed as package install suggestions.
> 
> By default there is no config. Autoprobing generates a first one or a 
> user can specify a defconfig.

This could work if there's not two but three states for individual 
features:

  - autoprobe
  - on
  - off

and if autoprobe, if a system feature has been probed successfully, 
automatically turned 'autoprobe' entries into 'on'.

That would give us the best of all worlds - autodetection, configurability 
and caching:

 - initial user types 'make' and gets a .config that has almost all
   entries 'on', a few 'autoprobe'.

 - once the user installs a dependency, the corresponding .config entry
   turns into 'on'.

 - the regular user or developers would have libraries that turn all
   entries in the .config to 'on'.

 - if a user is genuinely uninterested in a feature, he can mark it 'off', 
   which would then stay off permanently. This could also be used by
   embedded/specialized builds.

 - other specialized users, like distro builds, could use a .config with
   all entries 'on' and could enforce the presence of all dependencies for 
   a successful build. [We could add 'make allyesconfig' to help that.]

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 21:18                 ` Ingo Molnar
@ 2013-09-12 22:10                   ` David Ahern
  2013-09-13  5:09                     ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: David Ahern @ 2013-09-12 22:10 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton

On 9/12/13 2:18 PM, Ingo Molnar wrote:
>> kconf approach of course:
>>    https://lkml.org/lkml/2013/4/1/600
>> (minus the manual steps in that RFC).
>
> I'm not sure what the end stage is where you'd like to arrive, but I don't
> think that forcing a separate configuration pass is an improvement :-/

once I have a working config -- say one for a target (minimal build) and 
one for analysis (more but not all features -- eg., no gtk) I never see 
auto-probing again. At best some new feature (config) comes along and 
the config has to be updated again, but kconf only inquires about new 
features.

>
> By default a simple 'make' should build perf to the maximum extent
> possible, with no other input required from the user - with warnings
> displayed as package install suggestions.

By default there is no config. Autoprobing generates a first one or a 
user can specify a defconfig.

David

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 21:09               ` David Ahern
@ 2013-09-12 21:18                 ` Ingo Molnar
  2013-09-12 22:10                   ` David Ahern
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 21:18 UTC (permalink / raw)
  To: David Ahern
  Cc: Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton


* David Ahern <dsahern@gmail.com> wrote:

> On 9/12/13 1:46 PM, Ingo Molnar wrote:
> >>>Mind outlining the approach you are thinking about?
> >>>
> >>>Firstly, please don't even think about autotools. (Just forget it exists.)
> >>
> >>hehe, no, that wasn't considered.
> >
> >/phew! :-)
> 
> kconf approach of course:
>   https://lkml.org/lkml/2013/4/1/600
> (minus the manual steps in that RFC).

I'm not sure what the end stage is where you'd like to arrive, but I don't 
think that forcing a separate configuration pass is an improvement :-/

By default a simple 'make' should build perf to the maximum extent 
possible, with no other input required from the user - with warnings 
displayed as package install suggestions.

This:

 Enable newt-based TUI (NEWT) [N/y] (NEW) y
 Enable GTK-based UI (GTK2) [N/y] (NEW) n
 Enable support for Bionic (e.g., Android platform) (BIONIC) [N/y] (NEW)
 Development support for libc is available - glibc or bionic (LIBC) [N/y] 
 (NEW) y
   Enable support for libelf (LIBELF) [N/y] (NEW) y
     Enable support for libunwind (LIBUNWIND) [N/y] (NEW) y
     Enable support for dwarf (DWARF) [N/y] (NEW) y
     Enable support for demangle (DEMANGLE) [N/y] (NEW) y
 Enable support for perl scripting engine (LIBPERL) [N/y] (NEW) y
 Enable support for python scripting engine (LIBPYTHON) [N/y] (NEW) y
 Enable support for libaudit (LIBAUDIT) [N/y/?] (NEW) y
 Enable support for libnuma (LIBNUMA) [N/y/?] (NEW) y
 Enable support for stack backtrace debugging (BACKTRACE) [N/y] (NEW) y

would be useful only as long as each listed option is actually 
_buildable_. I.e. it should not be possible for the user to configure perf 
in a way that makes the build fail.

I.e. this should go on top of a feature detection logic, allowing further 
customization, for features that the user might want to turn off.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:46             ` Ingo Molnar
@ 2013-09-12 21:09               ` David Ahern
  2013-09-12 21:18                 ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: David Ahern @ 2013-09-12 21:09 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton

On 9/12/13 1:46 PM, Ingo Molnar wrote:
>>> Mind outlining the approach you are thinking about?
>>>
>>> Firstly, please don't even think about autotools. (Just forget it exists.)
>>
>> hehe, no, that wasn't considered.
>
> /phew! :-)

kconf approach of course:
   https://lkml.org/lkml/2013/4/1/600
(minus the manual steps in that RFC).

David

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:52             ` Linus Torvalds
@ 2013-09-12 21:01               ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 21:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Thu, Sep 12, 2013 at 1:49 PM, Ingo Molnar <mingo@kernel.org> wrote:
> >
> >
> > I think the window of breakage is relatively small (you managed to hit 
> > it), but should we add a quirk for this?
> 
> Was the breakage entirely inside the merge window? ie no released 
> kernels?

Absolutely! Starts at commit 0d99b7087324, stops at commit d008d5258e9c, 
all inside the merge window.

> If so, just ignore it.

Ok, great!

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:49           ` Ingo Molnar
@ 2013-09-12 20:52             ` Linus Torvalds
  2013-09-12 21:01               ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-09-12 20:52 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Thu, Sep 12, 2013 at 1:49 PM, Ingo Molnar <mingo@kernel.org> wrote:
>
>
> I think the window of breakage is relatively small (you managed to hit
> it), but should we add a quirk for this?

Was the breakage entirely inside the merge window? ie no released kernels?

If so, just ignore it.

             Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:38         ` Linus Torvalds
@ 2013-09-12 20:49           ` Ingo Molnar
  2013-09-12 20:52             ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:49 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Thu, Sep 12, 2013 at 1:33 PM, Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Hm, just to make sure, are you running a (very fresh) kernel that has this
> > fix included:
> >
> > d008d5258e9c perf: Fix up MMAP2 buffer space reservation
> 
> I've rebooted about five times since that report, so I'm not sure..
> 
> [ Short time passes ]
> 
> Hmm. That "reproducible" error is no longer reproducible for me on 
> current git (68f0d9d92e54). So if you fixed something recently, it's 
> possible I was running a pre-perf-pull kernel and an after-perf-pull 
> "perf" binary.

Yeah, so I think prior merging d008d5258e9c you'd see those artifacts with 
new, MMAP2-aware perf tooling. Both older kernels would work fine with any 
version of the tooling, and old tooling would work fine. Only new tooling 
used on a kernel within the breakage window would be exposed to this.

I think the window of breakage is relatively small (you managed to hit 
it), but should we add a quirk for this?

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:38           ` Arnaldo Carvalho de Melo
@ 2013-09-12 20:46             ` Ingo Molnar
  2013-09-12 21:09               ` David Ahern
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:46 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: David Ahern, Linus Torvalds, Linux Kernel Mailing List,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Arnaldo Carvalho de Melo <acme@ghostprotocols.net> wrote:

> Em Thu, Sep 12, 2013 at 10:18:55PM +0200, Ingo Molnar escreveu:
> > * David Ahern <dsahern@gmail.com> wrote:
> > 
> > > On 9/12/13 11:43 AM, Arnaldo Carvalho de Melo wrote:
> > 
> > > > Its something that annoys me as well, but not so much as to make me 
> > > > figure out how to make those be done only if some source file changed.
> > > 
> > > Jiri and I have both taken stabs at a config-based build rather than 
> > > probing. Just need to finish it.
> > 
> > Mind outlining the approach you are thinking about?
> > 
> > Firstly, please don't even think about autotools. (Just forget it exists.)
> 
> hehe, no, that wasn't considered.

/phew! :-)

> > Secondly, the way perf tries to build by auto-detecting the build 
> > environment and auto-disabling bits it cannot build just yet is pretty 
> > powerful. The core bits will build on just about any system, and our 
> > fallbacks are really good.
> 
> That would remain as:
> 
> make -C tools/perf autoconfig
>  
> > The result is that perf will build on just about any random system, 
> > without the user having to install any dependency. It would be really 
> > sad to lose that aspect.
> 
> we will not

But it would be nice to keep building as simple as 'make'.

So I don't think splitting out the feature tests into a separate pass, to 
be done manually by the user, is a step forward.

Speeding them up by caching their results, while cleaning up the 
presentation of the testcases, on the other hand, would be a (big!) step 
forward.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:31           ` Ingo Molnar
@ 2013-09-12 20:43             ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:43 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: David Ahern, Linus Torvalds, Linux Kernel Mailing List,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Ingo Molnar <mingo@kernel.org> wrote:

> Instead of having 20 testcases crammed into a single Makefile:
> 
> comet:~/tip/tools/perf> git grep -w main config/feature-tests.mak 
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(int argc, char *argv[])
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> config/feature-tests.mak:int main(void)
> 
> Why not put those into 20x standalone .c files and try to build them as 
> an explicit make command attempt from within the main Makefile? If the 
> build fails then the feature flag is set to off, if it succeeds it's 
> defined.
> 
> That makes feature tests generally easier to debug, easier to understand 
> and generally easier to extend as well.
> 
> 'Feature test binaries' that are already built will be 'cached' 
> automatically, and the result of their build attempt will be a quick 
> success.

A successfull 'make' attempt of a target file within a separate, simple 
Makefile is very, very fast:

 comet:~/tip/tools/power/x86/turbostat> perf stat --null --sync --repeat 10 
 make turbostat
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.
 make: `turbostat' is up to date.

  Performance counter stats for 'make turbostat' (10 runs):

        0.002146182 seconds time elapsed                                          ( +-  0.35% )

That's 2 msecs only. 20 such tests will take less than 50 msecs in the 
'cached' case.

Thanks,

	Ingo


^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:18         ` Ingo Molnar
@ 2013-09-12 20:38           ` Arnaldo Carvalho de Melo
  2013-09-12 20:46             ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-09-12 20:38 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: David Ahern, Linus Torvalds, Linux Kernel Mailing List,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

Em Thu, Sep 12, 2013 at 10:18:55PM +0200, Ingo Molnar escreveu:
> * David Ahern <dsahern@gmail.com> wrote:
> 
> > On 9/12/13 11:43 AM, Arnaldo Carvalho de Melo wrote:
> 
> > > Its something that annoys me as well, but not so much as to make me 
> > > figure out how to make those be done only if some source file changed.
> > 
> > Jiri and I have both taken stabs at a config-based build rather than 
> > probing. Just need to finish it.
> 
> Mind outlining the approach you are thinking about?
> 
> Firstly, please don't even think about autotools. (Just forget it exists.)

hehe, no, that wasn't considered.
 
> Secondly, the way perf tries to build by auto-detecting the build 
> environment and auto-disabling bits it cannot build just yet is pretty 
> powerful. The core bits will build on just about any system, and our 
> fallbacks are really good.

That would remain as:

make -C tools/perf autoconfig
 
> The result is that perf will build on just about any random system, 
> without the user having to install any dependency. It would be really sad 
> to lose that aspect.

we will not

> What I think would work best is what I outlined in the previous mail: to 
> cache successful feature test results and only re-do unsuccessful tests: 
> those are the ones that are expected to turn into successful tests in the 
> future, once the missing dependencies are installed.

that is an optimization to 'make autoconfig', i.e. what we have now,
improved.
 
> Since most tests succeed even on a sparsely installed system, this trick 
> alone will speed up the checks big time.
> 
> Furthermore, this method would encourage people to install the 
> dependencies - and perf developers, who do many repeat builds after 
> trivial one-file changes, will typically have all dependencies installed 
> anyway, so for them such a caching feature would result in totally cached 
> feature tests and very fast build times.

What he mentioned is the multiple attempts at doing:

make -C tools/perf menuconfig

and use kbuild to allow one to select what he/she wants to build, i.e.
using the kernel config system in perf.

In that case the feature checks would be triggered only for the features
selected, not for all perf currently selectable features.

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:33       ` Ingo Molnar
@ 2013-09-12 20:38         ` Linus Torvalds
  2013-09-12 20:49           ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-09-12 20:38 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Thu, Sep 12, 2013 at 1:33 PM, Ingo Molnar <mingo@kernel.org> wrote:
>
> Hm, just to make sure, are you running a (very fresh) kernel that has this
> fix included:
>
> d008d5258e9c perf: Fix up MMAP2 buffer space reservation

I've rebooted about five times since that report, so I'm not sure..

[ Short time passes ]

Hmm. That "reproducible" error is no longer reproducible for me on
current git (68f0d9d92e54). So if you fixed something recently, it's
possible I was running a pre-perf-pull kernel and an after-perf-pull
"perf" binary.

              Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:51     ` Linus Torvalds
@ 2013-09-12 20:33       ` Ingo Molnar
  2013-09-12 20:38         ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:33 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Thu, Sep 12, 2013 at 11:10 AM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
> >
> > But at least the "make install" problem is repeatable, though.
> 
> And now this new problem is repeatable too:
> 
>   # On a fully built kernel tree
>   perf record -g -e cycles:pp make -j
> 
> results in
> 
>   [ perf record: Woken up 27 times to write data ]
>   [ perf record: Captured and wrote 7.980 MB perf.data (~348659 samples) ]
>   0x1b4e0 [0]: failed to process type: -1970637019
> 
> where that number changes randomly, ie I get
> 
>   0x28dc58 [0]: failed to process type: 99257493
>   0x4100 [0]: failed to process type: -1144359783
>   0x29050 [0]: failed to process type: -972156963
>   ..
> 
> looks like perhaps some uninitialized variable somewhere?
> 
> Recording performance profiles of other (simpler?) loads still seems to 
> work. So it's something about that "make -j" that makes it crap out 
> (note that the tree is fully built, so not a lot actually gets *done*, 
> and the thing only takes a few seconds)

Hm, just to make sure, are you running a (very fresh) kernel that has this 
fix included:

d008d5258e9c perf: Fix up MMAP2 buffer space reservation

?

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 20:02         ` Arnaldo Carvalho de Melo
@ 2013-09-12 20:31           ` Ingo Molnar
  2013-09-12 20:43             ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:31 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: David Ahern, Linus Torvalds, Linux Kernel Mailing List,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Arnaldo Carvalho de Melo <acme@ghostprotocols.net> wrote:

> Em Thu, Sep 12, 2013 at 12:58:28PM -0700, David Ahern escreveu:
> > On 9/12/13 11:43 AM, Arnaldo Carvalho de Melo wrote:
> >
> > > Its something that annoys me as well, but not so much as to make me 
> > > figure out how to make those be done only if some source file 
> > > changed.
> > 
> > Jiri and I have both taken stabs at a config-based build rather than 
> > probing. Just need to finish it.
> 
> But even then it would be nice to have a:
> 
> make autoconfig
> 
> That is what we have now, but only then we would try to do all that 
> probing. Caching it somehow, as Ingo suggested, would get the best of 
> both worlds.

Caching should be relatively straightforward: I'd suggest splitting up all 
the feature tests current present in tools/perf/config/feature-tests.mak 
into separate .c files which build into working binaries.

Instead of having 20 testcases crammed into a single Makefile:

comet:~/tip/tools/perf> git grep -w main config/feature-tests.mak 
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(int argc, char *argv[])
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)
config/feature-tests.mak:int main(void)

Why not put those into 20x standalone .c files and try to build them as an 
explicit make command attempt from within the main Makefile? If the build 
fails then the feature flag is set to off, if it succeeds it's defined.

That makes feature tests generally easier to debug, easier to understand 
and generally easier to extend as well.

'Feature test binaries' that are already built will be 'cached' 
automatically, and the result of their build attempt will be a quick 
success.

This is relatively simple, well-known, powerful and I see no reason why it 
wouldn't work. No separate config language or special files are needed - 
just .c files, binaries and a Makefile.

'make clean' would get rid of the binaries.

[ It could even be made to work against package removal if we really 
  wanted to: if there's a common, known include file related to the 
  feature (such as /usr/include/libaudit.h), then that include file
  could be added to the feature-test binary's list of dependencies. If the
  package is removed and the include file goes away, then the dependency
  breaks automatically and the binary is 'rebuilt', auto-detecting the
  failed dependency. ]

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 19:58       ` David Ahern
  2013-09-12 20:02         ` Arnaldo Carvalho de Melo
@ 2013-09-12 20:18         ` Ingo Molnar
  2013-09-12 20:38           ` Arnaldo Carvalho de Melo
  1 sibling, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:18 UTC (permalink / raw)
  To: David Ahern
  Cc: Arnaldo Carvalho de Melo, Linus Torvalds,
	Linux Kernel Mailing List, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton


* David Ahern <dsahern@gmail.com> wrote:

> On 9/12/13 11:43 AM, Arnaldo Carvalho de Melo wrote:

> > Its something that annoys me as well, but not so much as to make me 
> > figure out how to make those be done only if some source file changed.
> 
> Jiri and I have both taken stabs at a config-based build rather than 
> probing. Just need to finish it.

Mind outlining the approach you are thinking about?

Firstly, please don't even think about autotools. (Just forget it exists.)

Secondly, the way perf tries to build by auto-detecting the build 
environment and auto-disabling bits it cannot build just yet is pretty 
powerful. The core bits will build on just about any system, and our 
fallbacks are really good.

The result is that perf will build on just about any random system, 
without the user having to install any dependency. It would be really sad 
to lose that aspect.

What I think would work best is what I outlined in the previous mail: to 
cache successful feature test results and only re-do unsuccessful tests: 
those are the ones that are expected to turn into successful tests in the 
future, once the missing dependencies are installed.

Since most tests succeed even on a sparsely installed system, this trick 
alone will speed up the checks big time.

Furthermore, this method would encourage people to install the 
dependencies - and perf developers, who do many repeat builds after 
trivial one-file changes, will typically have all dependencies installed 
anyway, so for them such a caching feature would result in totally cached 
feature tests and very fast build times.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:10   ` Linus Torvalds
  2013-09-12 18:43     ` Arnaldo Carvalho de Melo
  2013-09-12 18:51     ` Linus Torvalds
@ 2013-09-12 20:10     ` Ingo Molnar
  2 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 20:10 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Thu, Sep 12, 2013 at 11:03 AM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
> >
> > When I compiled "perf" at the same time as doing a big kernel compile,
> > the kernel compile failed
> 
> Oops. That may actually have been me being a bit *too* eager with a 
> "make allmodconfig" build. I can't reproduce it, and I'm starting to 
> suspect that I instead had two kernel compiles going, not one kernel 
> compile and a tools/perf/ compile.

Btw., building perf in parallel to an ongoing kernel compile is something 
I do almost daily, and I never saw problems due to that. A perf build is 
not supposed to cause any side effect on the kernel build and vice versa.

So in general it should just work.

>   "Yo Dawg, I heard you like kernel compiles, so I put a kernel compile 
> in your kernel compile so that you can compile the kernel while you 
> compile the kernel".

Heh, accidental dual kernel builds within the same kernel tree is 
something I have a _lot_ of involuntary experience with, and I usually 
recognize the error message patterns straight away ;-)

As a kernel hacker one learns useful skills all the time!

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 19:58       ` David Ahern
@ 2013-09-12 20:02         ` Arnaldo Carvalho de Melo
  2013-09-12 20:31           ` Ingo Molnar
  2013-09-12 20:18         ` Ingo Molnar
  1 sibling, 1 reply; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-09-12 20:02 UTC (permalink / raw)
  To: David Ahern
  Cc: Linus Torvalds, Ingo Molnar, Linux Kernel Mailing List,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

Em Thu, Sep 12, 2013 at 12:58:28PM -0700, David Ahern escreveu:
> On 9/12/13 11:43 AM, Arnaldo Carvalho de Melo wrote:
> >Its something that annoys me as well, but not so much as to make me
> >figure out how to make those be done only if some source file changed.
> 
> Jiri and I have both taken stabs at a config-based build rather than
> probing. Just need to finish it.

But even then it would be nice to have a:

make autoconfig

That is what we have now, but only then we would try to do all that
probing. Caching it somehow, as Ingo suggested, would get the best of
both worlds.

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:43     ` Arnaldo Carvalho de Melo
  2013-09-12 19:12       ` Arnaldo Carvalho de Melo
  2013-09-12 19:55       ` Ingo Molnar
@ 2013-09-12 19:58       ` David Ahern
  2013-09-12 20:02         ` Arnaldo Carvalho de Melo
  2013-09-12 20:18         ` Ingo Molnar
  2 siblings, 2 replies; 376+ messages in thread
From: David Ahern @ 2013-09-12 19:58 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Linus Torvalds, Ingo Molnar, Linux Kernel Mailing List,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On 9/12/13 11:43 AM, Arnaldo Carvalho de Melo wrote:
> Its something that annoys me as well, but not so much as to make me
> figure out how to make those be done only if some source file changed.

Jiri and I have both taken stabs at a config-based build rather than 
probing. Just need to finish it.

David

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:43     ` Arnaldo Carvalho de Melo
  2013-09-12 19:12       ` Arnaldo Carvalho de Melo
@ 2013-09-12 19:55       ` Ingo Molnar
  2013-09-12 19:58       ` David Ahern
  2 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 19:55 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Linus Torvalds, Linux Kernel Mailing List, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton


* Arnaldo Carvalho de Melo <acme@ghostprotocols.net> wrote:

> Em Thu, Sep 12, 2013 at 11:10:37AM -0700, Linus Torvalds escreveu:
> > On Thu, Sep 12, 2013 at 11:03 AM, Linus Torvalds <torvalds@linux-foundation.org> wrote:
> > > When I compiled "perf" at the same time as doing a big kernel compile,
> > > the kernel compile failed
>  
> > Oops. That may actually have been me being a bit *too* eager with a
> > "make allmodconfig" build. I can't reproduce it, and I'm starting to
> > suspect that I instead had two kernel compiles going, not one kernel
> > compile and a tools/perf/ compile.
>  
> >   "Yo Dawg, I heard you like kernel compiles, so I put a kernel
> > compile in your kernel compile so that you can compile the kernel
> > while you compile the kernel".
> 
> :-)
>  
> > But at least the "make install" problem is repeatable, though.
> 
> Well, I just tried it, and the only thing that gets rebuilt are the CHK 
> environment tests that try to figure out what can be built into perf, 
> i.e. perl, python, libaudit, etc.
> 
> Its something that annoys me as well, but not so much as to make me 
> figure out how to make those be done only if some source file changed.
> 
> But then, if you remove, say, libelf from your system so that you get a 
> perf tool that uses just /proc/kallsyms, it wouldn't detect it...

I don't think package removal is a particularly common usecase.

> Perhaps in that case we should say: want a new build with a different 
> environment? Do a 'make clean' first.

Exactly. The most common pattern is:

   make
   # see warnings about missing dependencies
   install missing packages

   make
   # no warnings, happy camper

Downgrades, package removals almost never happen in real life, let alone 
in typical build flows.

So in the simplest approximation, if we detected just the best-case: 'all 
libraries are present, we can do a full build' case and cached that fact 
across builds (and cleared the cached flag on 'make clean'), that would 
help speeding up the main usecase already.

But a cached flag per _successful_ config/feature-tests.mak testcase would 
work well too. I.e. only repeat checks that failed in the past. Once it 
succeeds there's no need to re-check.

Independent of all this is the the bug of repeat checks Linus noticed, 
that's indeed annoying and should be fixed separately of any feature test 
cache.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 19:12       ` Arnaldo Carvalho de Melo
@ 2013-09-12 19:13         ` Linus Torvalds
  0 siblings, 0 replies; 376+ messages in thread
From: Linus Torvalds @ 2013-09-12 19:13 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Ingo Molnar, Linux Kernel Mailing List, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

On Thu, Sep 12, 2013 at 12:12 PM, Arnaldo Carvalho de Melo
<acme@ghostprotocols.net> wrote:
>
> We probably got all this from the 'git' makefile, checking how it is done
> there these days...

I suspect it's the same.

The thing I was really complaining about is how slow "make install"
is, since it seems to redo most everything I already did...

           Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:43     ` Arnaldo Carvalho de Melo
@ 2013-09-12 19:12       ` Arnaldo Carvalho de Melo
  2013-09-12 19:13         ` Linus Torvalds
  2013-09-12 19:55       ` Ingo Molnar
  2013-09-12 19:58       ` David Ahern
  2 siblings, 1 reply; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-09-12 19:12 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Linux Kernel Mailing List, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Em Thu, Sep 12, 2013 at 03:43:41PM -0300, Arnaldo Carvalho de Melo escreveu:
> But if I do it as a normal user and then try installing as root... it
> behaves like you described, duh :-\
> 
> Because of this:
> 
>     * new build flags or prefix
> 
> Will check...

This is the cause:


### Detect prefix changes
TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)

$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
        @FLAGS='$(TRACK_CFLAGS)'; \
            if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
                echo 1>&2 "    * new build flags or prefix"; \
                echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
            fi

That "prefix" thing, i.e.:

             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)


As user it is:

/home/acme/bin:libexec/perf-core:share/perf-core/templates:/home/acme

while as root it becomes:

/root/bin:libexec/perf-core:share/perf-core/templates:/root

And that causes the whole thing to be rebuilt when going from 'make' as normal
user to 'make install' as root.

All the other things in that TRACK_CFLAGS part is equal.

We probably got all this from the 'git' makefile, checking how it is done
there these days...

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:10   ` Linus Torvalds
  2013-09-12 18:43     ` Arnaldo Carvalho de Melo
@ 2013-09-12 18:51     ` Linus Torvalds
  2013-09-12 20:33       ` Ingo Molnar
  2013-09-12 20:10     ` Ingo Molnar
  2 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-09-12 18:51 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Thu, Sep 12, 2013 at 11:10 AM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> But at least the "make install" problem is repeatable, though.

And now this new problem is repeatable too:

  # On a fully built kernel tree
  perf record -g -e cycles:pp make -j

results in

  [ perf record: Woken up 27 times to write data ]
  [ perf record: Captured and wrote 7.980 MB perf.data (~348659 samples) ]
  0x1b4e0 [0]: failed to process type: -1970637019

where that number changes randomly, ie I get

  0x28dc58 [0]: failed to process type: 99257493
  0x4100 [0]: failed to process type: -1144359783
  0x29050 [0]: failed to process type: -972156963
  ..

looks like perhaps some uninitialized variable somewhere?

Recording performance profiles of other (simpler?) loads still seems
to work. So it's something about that "make -j" that makes it crap out
(note that the tree is fully built, so not a lot actually gets *done*,
and the thing only takes a few seconds)

               Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:10   ` Linus Torvalds
@ 2013-09-12 18:43     ` Arnaldo Carvalho de Melo
  2013-09-12 19:12       ` Arnaldo Carvalho de Melo
                         ` (2 more replies)
  2013-09-12 18:51     ` Linus Torvalds
  2013-09-12 20:10     ` Ingo Molnar
  2 siblings, 3 replies; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2013-09-12 18:43 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Linux Kernel Mailing List, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Em Thu, Sep 12, 2013 at 11:10:37AM -0700, Linus Torvalds escreveu:
> On Thu, Sep 12, 2013 at 11:03 AM, Linus Torvalds <torvalds@linux-foundation.org> wrote:
> > When I compiled "perf" at the same time as doing a big kernel compile,
> > the kernel compile failed
 
> Oops. That may actually have been me being a bit *too* eager with a
> "make allmodconfig" build. I can't reproduce it, and I'm starting to
> suspect that I instead had two kernel compiles going, not one kernel
> compile and a tools/perf/ compile.
 
>   "Yo Dawg, I heard you like kernel compiles, so I put a kernel
> compile in your kernel compile so that you can compile the kernel
> while you compile the kernel".

:-)
 
> But at least the "make install" problem is repeatable, though.

Well, I just tried it, and the only thing that gets rebuilt are the CHK
environment tests that try to figure out what can be built into perf,
i.e. perl, python, libaudit, etc.

Its something that annoys me as well, but not so much as to make me
figure out how to make those be done only if some source file changed.

But then, if you remove, say, libelf from your system so that you get a
perf tool that uses just /proc/kallsyms, it wouldn't detect it...

Perhaps in that case we should say: want a new build with a different
environment? Do a 'make clean' first.

But if I do it as a normal user and then try installing as root... it
behaves like you described, duh :-\

Because of this:

    * new build flags or prefix

Will check...

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 18:03 ` Linus Torvalds
@ 2013-09-12 18:10   ` Linus Torvalds
  2013-09-12 18:43     ` Arnaldo Carvalho de Melo
                       ` (2 more replies)
  0 siblings, 3 replies; 376+ messages in thread
From: Linus Torvalds @ 2013-09-12 18:10 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Thu, Sep 12, 2013 at 11:03 AM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> When I compiled "perf" at the same time as doing a big kernel compile,
> the kernel compile failed

Oops. That may actually have been me being a bit *too* eager with a
"make allmodconfig" build. I can't reproduce it, and I'm starting to
suspect that I instead had two kernel compiles going, not one kernel
compile and a tools/perf/ compile.

  "Yo Dawg, I heard you like kernel compiles, so I put a kernel
compile in your kernel compile so that you can compile the kernel
while you compile the kernel".

But at least the "make install" problem is repeatable, though.

              Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-09-12 13:38 Ingo Molnar
@ 2013-09-12 18:03 ` Linus Torvalds
  2013-09-12 18:10   ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-09-12 18:03 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linux Kernel Mailing List, Arnaldo Carvalho de Melo,
	Peter Zijlstra, Thomas Gleixner, Andrew Morton

On Thu, Sep 12, 2013 at 6:38 AM, Ingo Molnar <mingo@kernel.org> wrote:
>
> Various fixes. (The -g perf report lockup you reported is only partially
> addressed, patches that fix the excessive runtime are still being worked
> on.)

So I pulled this and compiled a new version, and I have a new
complaint. The _bug_ probably is not new, but it happened because I
was compiling the tools/perf/ subdirectory while another terminal was
busy doing a "make allmodconfig" test build (hey, sue me, I do a lot
of them during the merge window).

When I compiled "perf" at the same time as doing a big kernel compile,
the kernel compile failed! I got a few odd "No such file or directory"
for temporary object files in the kernel build. That's not nice. Why
does "make" in the perf tools mess up a "make" of the main kernel?
That implies that the perf tools aren't really independent, and they
try to make at least part of the top-level build. Very annoying.

Another annoyance during that make was that "make install" seems to
want to re-make the thing I just built. That's absolutely horrible,
even if I've seen too many broken projects do that. Now, for perf it's
not as horrible as for some (because you can do "make install" as a
normal user), but it's still a pattern that needs to be called out and
needs to die. It's not just that it slows down "make install", it's
also that a normal pattern *should* be that you build things as a
normal user, and do "make install" as root.

            Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-09-12 13:38 Ingo Molnar
  2013-09-12 18:03 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-09-12 13:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: dbc33f7016747bfce64f3d1e3af63f1251fcbf85 perf/x86: Fix uncore PCI fixed counter handling

Various fixes. (The -g perf report lockup you reported is only partially 
addressed, patches that fix the excessive runtime are still being worked 
on.)

 Thanks,

	Ingo

------------------>
Adrian Hunter (4):
      perf tools: Add test for parsing with no sample_id_all bit
      perf evlist: Fix parsing with no sample_id_all bit set
      perf evlist: Fix id pos in perf_evlist__open()
      perf kvm: Fix sample_type manipulation

Arnaldo Carvalho de Melo (4):
      perf trace: Check control+C more often
      perf hists: Fix formatting of long symbol names
      perf trace: Handle perf.data files with no tracepoints
      perf: Fix up MMAP2 buffer space reservation

Jiri Olsa (1):
      perf session: Separate progress bar update when processing events

Kyle McMartin (1):
      perf trace: Check if MAP_32BIT is defined

Oleg Nesterov (1):
      uprobes: Fix utask->depth accounting in handle_trampoline()

Stephane Eranian (3):
      perf tools: Add attr->mmap2 support
      perf/x86: Add constraint for IVB CYCLE_ACTIVITY:CYCLES_LDM_PENDING
      perf/x86: Fix uncore PCI fixed counter handling


 arch/x86/kernel/cpu/perf_event_intel.c        |   1 +
 arch/x86/kernel/cpu/perf_event_intel_uncore.c |   6 +-
 kernel/events/core.c                          |   1 +
 kernel/events/uprobes.c                       |   4 +-
 tools/perf/Makefile                           |   3 +-
 tools/perf/builtin-annotate.c                 |   1 +
 tools/perf/builtin-inject.c                   |  15 ++++
 tools/perf/builtin-kvm.c                      |  18 ++---
 tools/perf/builtin-mem.c                      |   1 +
 tools/perf/builtin-report.c                   |   1 +
 tools/perf/builtin-script.c                   |   1 +
 tools/perf/builtin-trace.c                    |   5 ++
 tools/perf/tests/builtin-test.c               |   4 +
 tools/perf/tests/parse-no-sample-id-all.c     | 108 ++++++++++++++++++++++++++
 tools/perf/tests/perf-record.c                |  15 +++-
 tools/perf/tests/tests.h                      |   1 +
 tools/perf/ui/stdio/hist.c                    |  23 ++++--
 tools/perf/util/build-id.c                    |   1 +
 tools/perf/util/event.c                       |  56 ++++++++++---
 tools/perf/util/event.h                       |  19 +++++
 tools/perf/util/evlist.c                      |  21 ++++-
 tools/perf/util/evsel.c                       |  16 +++-
 tools/perf/util/header.c                      |   3 +
 tools/perf/util/machine.c                     |  53 ++++++++++++-
 tools/perf/util/machine.h                     |   1 +
 tools/perf/util/map.c                         |   8 +-
 tools/perf/util/map.h                         |   8 +-
 tools/perf/util/session.c                     |  68 ++++++++--------
 tools/perf/util/tool.h                        |   1 +
 29 files changed, 381 insertions(+), 82 deletions(-)
 create mode 100644 tools/perf/tests/parse-no-sample-id-all.c

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0abf674..c62d883 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -124,6 +124,7 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
 	INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index fd8011e..8ed4458 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2808,7 +2808,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
 			return c;
 	}
 
-	if (event->hw.config == ~0ULL)
+	if (event->attr.config == UNCORE_FIXED_EVENT)
 		return &constraint_fixed;
 
 	if (type->constraints) {
@@ -3112,7 +3112,9 @@ static int uncore_pmu_event_init(struct perf_event *event)
 		 */
 		if (pmu->type->single_fixed && pmu->pmu_idx > 0)
 			return -EINVAL;
-		hwc->config = ~0ULL;
+
+		/* fixed counters have event field hardcoded to zero */
+		hwc->config = 0ULL;
 	} else {
 		hwc->config = event->attr.config & pmu->type->event_mask;
 		if (pmu->type->ops->hw_config) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2207efc..dd236b6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5039,6 +5039,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 		mmap_event->event_id.header.size += sizeof(mmap_event->maj);
 		mmap_event->event_id.header.size += sizeof(mmap_event->min);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino);
+		mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f356974..ad8e1bd 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1682,12 +1682,10 @@ static bool handle_trampoline(struct pt_regs *regs)
 		tmp = ri;
 		ri = ri->next;
 		kfree(tmp);
+		utask->depth--;
 
 		if (!chained)
 			break;
-
-		utask->depth--;
-
 		BUG_ON(!ri);
 	}
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index c5dc1ad..3a0ff7f 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -394,6 +394,8 @@ ifeq ($(ARCH),x86)
 LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
 endif
 LIB_OBJS += $(OUTPUT)tests/code-reading.o
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
+LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -439,7 +441,6 @@ PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
 ifneq ($(OUTPUT),)
   CFLAGS += -I$(OUTPUT)
 endif
-LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 
 ifdef NO_LIBELF
 EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index f988d38..5ebd0c3 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -277,6 +277,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample	= process_sample_event,
 			.mmap	= perf_event__process_mmap,
+			.mmap2	= perf_event__process_mmap2,
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9b336fd..423875c 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -123,6 +123,19 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_mmap2(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_mmap2(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -339,6 +352,7 @@ static int __cmd_inject(struct perf_inject *inject)
 
 	if (inject->build_ids || inject->sched_stat) {
 		inject->tool.mmap	  = perf_event__repipe_mmap;
+		inject->tool.mmap2	  = perf_event__repipe_mmap2;
 		inject->tool.fork	  = perf_event__repipe_fork;
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
@@ -390,6 +404,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		= perf_event__repipe_sample,
 			.mmap		= perf_event__repipe,
+			.mmap2		= perf_event__repipe,
 			.comm		= perf_event__repipe,
 			.fork		= perf_event__repipe,
 			.exit		= perf_event__repipe,
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 47b3540..935d522 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1165,16 +1165,16 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 		struct perf_event_attr *attr = &pos->attr;
 
 		/* make sure these *are* set */
-		attr->sample_type |= PERF_SAMPLE_TID;
-		attr->sample_type |= PERF_SAMPLE_TIME;
-		attr->sample_type |= PERF_SAMPLE_CPU;
-		attr->sample_type |= PERF_SAMPLE_RAW;
+		perf_evsel__set_sample_bit(pos, TID);
+		perf_evsel__set_sample_bit(pos, TIME);
+		perf_evsel__set_sample_bit(pos, CPU);
+		perf_evsel__set_sample_bit(pos, RAW);
 		/* make sure these are *not*; want as small a sample as possible */
-		attr->sample_type &= ~PERF_SAMPLE_PERIOD;
-		attr->sample_type &= ~PERF_SAMPLE_IP;
-		attr->sample_type &= ~PERF_SAMPLE_CALLCHAIN;
-		attr->sample_type &= ~PERF_SAMPLE_ADDR;
-		attr->sample_type &= ~PERF_SAMPLE_READ;
+		perf_evsel__reset_sample_bit(pos, PERIOD);
+		perf_evsel__reset_sample_bit(pos, IP);
+		perf_evsel__reset_sample_bit(pos, CALLCHAIN);
+		perf_evsel__reset_sample_bit(pos, ADDR);
+		perf_evsel__reset_sample_bit(pos, READ);
 		attr->mmap = 0;
 		attr->comm = 0;
 		attr->task = 0;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 791b432..253133a 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -190,6 +190,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		= process_sample_event,
 			.mmap		= perf_event__process_mmap,
+			.mmap2		= perf_event__process_mmap2,
 			.comm		= perf_event__process_comm,
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9725aa3..8e50d8d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -744,6 +744,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		 = process_sample_event,
 			.mmap		 = perf_event__process_mmap,
+			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 93a34ce..7f31a3d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -542,6 +542,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_script = {
 	.sample		 = process_sample_event,
 	.mmap		 = perf_event__process_mmap,
+	.mmap2		 = perf_event__process_mmap2,
 	.comm		 = perf_event__process_comm,
 	.exit		 = perf_event__process_exit,
 	.fork		 = perf_event__process_fork,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b6f0725..f5aa637 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -100,7 +100,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	P_MMAP_FLAG(SHARED);
 	P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
 	P_MMAP_FLAG(32BIT);
+#endif
 	P_MMAP_FLAG(ANONYMOUS);
 	P_MMAP_FLAG(DENYWRITE);
 	P_MMAP_FLAG(EXECUTABLE);
@@ -994,6 +996,9 @@ again:
 
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
+
+			if (done)
+				goto out_unmap_evlist;
 		}
 	}
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8bbeba3..1e67437 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -112,6 +112,10 @@ static struct test {
 		.func = test__keep_tracking,
 	},
 	{
+		.desc = "Test parsing with no sample_id_all bit set",
+		.func = test__parse_no_sample_id_all,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
new file mode 100644
index 0000000..e117b6c
--- /dev/null
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -0,0 +1,108 @@
+#include <sys/types.h>
+#include <stddef.h>
+
+#include "tests.h"
+
+#include "event.h"
+#include "evlist.h"
+#include "header.h"
+#include "util.h"
+
+static int process_event(struct perf_evlist **pevlist, union perf_event *event)
+{
+	struct perf_sample sample;
+
+	if (event->header.type == PERF_RECORD_HEADER_ATTR) {
+		if (perf_event__process_attr(NULL, event, pevlist)) {
+			pr_debug("perf_event__process_attr failed\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return -1;
+
+	if (!*pevlist)
+		return -1;
+
+	if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int process_events(union perf_event **events, size_t count)
+{
+	struct perf_evlist *evlist = NULL;
+	int err = 0;
+	size_t i;
+
+	for (i = 0; i < count && !err; i++)
+		err = process_event(&evlist, events[i]);
+
+	if (evlist)
+		perf_evlist__delete(evlist);
+
+	return err;
+}
+
+struct test_attr_event {
+	struct attr_event attr;
+	u64 id;
+};
+
+/**
+ * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
+ *
+ * This function tests parsing data produced on kernel's that do not support the
+ * sample_id_all bit.  Without the sample_id_all bit, non-sample events (such as
+ * mmap events) do not have an id sample appended, and consequently logic
+ * designed to determine the id will not work.  That case happens when there is
+ * more than one selected event, so this test processes three events: 2
+ * attributes representing the selected events and one mmap event.
+ *
+ * Return: %0 on success, %-1 if the test fails.
+ */
+int test__parse_no_sample_id_all(void)
+{
+	int err;
+
+	struct test_attr_event event1 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 1,
+	};
+	struct test_attr_event event2 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 2,
+	};
+	struct mmap_event event3 = {
+		.header = {
+			.type = PERF_RECORD_MMAP,
+			.size = sizeof(struct mmap_event),
+		},
+	};
+	union perf_event *events[] = {
+		(union perf_event *)&event1,
+		(union perf_event *)&event2,
+		(union perf_event *)&event3,
+	};
+
+	err = process_events(events, ARRAY_SIZE(events));
+	if (err)
+		return -1;
+
+	return 0;
+}
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 72d8881..b8a7056 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -50,7 +50,7 @@ int test__PERF_RECORD(void)
 	struct perf_sample sample;
 	const char *cmd = "sleep";
 	const char *argv[] = { cmd, "1", NULL, };
-	char *bname;
+	char *bname, *mmap_filename;
 	u64 prev_time = 0;
 	bool found_cmd_mmap = false,
 	     found_libc_mmap = false,
@@ -212,6 +212,7 @@ int test__PERF_RECORD(void)
 
 				if ((type == PERF_RECORD_COMM ||
 				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2 ||
 				     type == PERF_RECORD_FORK ||
 				     type == PERF_RECORD_EXIT) &&
 				     (pid_t)event->comm.pid != evlist->workload.pid) {
@@ -220,7 +221,8 @@ int test__PERF_RECORD(void)
 				}
 
 				if ((type == PERF_RECORD_COMM ||
-				     type == PERF_RECORD_MMAP) &&
+				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2) &&
 				     event->comm.pid != event->comm.tid) {
 					pr_debug("%s with different pid/tid!\n", name);
 					++errs;
@@ -236,7 +238,12 @@ int test__PERF_RECORD(void)
 				case PERF_RECORD_EXIT:
 					goto found_exit;
 				case PERF_RECORD_MMAP:
-					bname = strrchr(event->mmap.filename, '/');
+					mmap_filename = event->mmap.filename;
+					goto check_bname;
+				case PERF_RECORD_MMAP2:
+					mmap_filename = event->mmap2.filename;
+				check_bname:
+					bname = strrchr(mmap_filename, '/');
 					if (bname != NULL) {
 						if (!found_cmd_mmap)
 							found_cmd_mmap = !strcmp(bname + 1, cmd);
@@ -245,7 +252,7 @@ int test__PERF_RECORD(void)
 						if (!found_ld_mmap)
 							found_ld_mmap = !strncmp(bname + 1, "ld", 2);
 					} else if (!found_vdso_mmap)
-						found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
+						found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
 					break;
 
 				case PERF_RECORD_SAMPLE:
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c048b58..e0ac713 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -39,5 +39,6 @@ int test__perf_time_to_tsc(void);
 int test__code_reading(void);
 int test__sample_parsing(void);
 int test__keep_tracking(void);
+int test__parse_no_sample_id_all(void);
 
 #endif /* TESTS_H */
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 5b4fb33..194e2f4 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -350,9 +350,9 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp,
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
-			       struct hists *hists, FILE *fp)
+			       struct hists *hists,
+			       char *bf, size_t bfsz, FILE *fp)
 {
-	char bf[512];
 	int ret;
 	struct perf_hpp hpp = {
 		.buf		= bf,
@@ -360,8 +360,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	};
 	bool color = !symbol_conf.field_sep;
 
-	if (size == 0 || size > sizeof(bf))
-		size = hpp.size = sizeof(bf);
+	if (size == 0 || size > bfsz)
+		size = hpp.size = bfsz;
 
 	ret = hist_entry__period_snprintf(&hpp, he, color);
 	hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
@@ -392,6 +392,8 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		.ptr	= hists_to_evsel(hists),
 	};
 	bool first = true;
+	size_t linesz;
+	char *line = NULL;
 
 	init_rem_hits();
 
@@ -479,6 +481,13 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		goto out;
 
 print_entries:
+	linesz = hists__sort_list_width(hists) + 3 + 1;
+	line = malloc(linesz);
+	if (line == NULL) {
+		ret = -1;
+		goto out;
+	}
+
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent = h->stat.period * 100.0 /
@@ -490,10 +499,10 @@ print_entries:
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, hists, fp);
+		ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
 
 		if (max_rows && ++nr_rows >= max_rows)
-			goto out;
+			break;
 
 		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(&h->thread->mg,
@@ -501,6 +510,8 @@ print_entries:
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
+
+	free(line);
 out:
 	free(rem_sq_bracket);
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index fb58409..7ded71d 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -67,6 +67,7 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 struct perf_tool build_id__mark_dso_hit_ops = {
 	.sample	= build_id__mark_dso_hit,
 	.mmap	= perf_event__process_mmap,
+	.mmap2	= perf_event__process_mmap2,
 	.fork	= perf_event__process_fork,
 	.exit	= perf_event__exit_del_thread,
 	.attr		 = perf_event__process_attr,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8d51f21..9b393e7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -11,6 +11,7 @@
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
 	[PERF_RECORD_MMAP]			= "MMAP",
+	[PERF_RECORD_MMAP2]			= "MMAP2",
 	[PERF_RECORD_LOST]			= "LOST",
 	[PERF_RECORD_COMM]			= "COMM",
 	[PERF_RECORD_EXIT]			= "EXIT",
@@ -186,7 +187,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		return -1;
 	}
 
-	event->header.type = PERF_RECORD_MMAP;
+	event->header.type = PERF_RECORD_MMAP2;
 	/*
 	 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 	 */
@@ -197,7 +198,9 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		char prot[5];
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
+		unsigned int ino;
 		size_t size;
+		ssize_t n;
 
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
@@ -206,9 +209,16 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
-		       &event->mmap.start, &event->mmap.len, prot,
-		       &event->mmap.pgoff, execname);
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
+		event->mmap2.ino = (u64)ino;
+
+		if (n != 8)
+			continue;
 
 		if (prot[2] != 'x')
 			continue;
@@ -217,15 +227,15 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			strcpy(execname, anonstr);
 
 		size = strlen(execname) + 1;
-		memcpy(event->mmap.filename, execname, size);
+		memcpy(event->mmap2.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap.len -= event->mmap.start;
-		event->mmap.header.size = (sizeof(event->mmap) -
-					   (sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.pid = tgid;
-		event->mmap.tid = pid;
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
 
 		if (process(tool, event, &synth_sample, machine) != 0) {
 			rc = -1;
@@ -527,6 +537,17 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 		       event->mmap.len, event->mmap.pgoff, event->mmap.filename);
 }
 
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %s\n",
+		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
+		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
+		       event->mmap2.min, event->mmap2.ino,
+		       event->mmap2.ino_generation,
+		       event->mmap2.filename);
+}
+
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample __maybe_unused,
@@ -535,6 +556,14 @@ int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
 	return machine__process_mmap_event(machine, event);
 }
 
+int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample __maybe_unused,
+			     struct machine *machine)
+{
+	return machine__process_mmap2_event(machine, event);
+}
+
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, "(%d:%d):(%d:%d)\n",
@@ -574,6 +603,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP:
 		ret += perf_event__fprintf_mmap(event, fp);
 		break;
+	case PERF_RECORD_MMAP2:
+		ret += perf_event__fprintf_mmap2(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 93130d8..c67ecc4 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -17,6 +17,19 @@ struct mmap_event {
 	char filename[PATH_MAX];
 };
 
+struct mmap2_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+	u64 start;
+	u64 len;
+	u64 pgoff;
+	u32 maj;
+	u32 min;
+	u64 ino;
+	u64 ino_generation;
+	char filename[PATH_MAX];
+};
+
 struct comm_event {
 	struct perf_event_header header;
 	u32 pid, tid;
@@ -159,6 +172,7 @@ struct tracing_data_event {
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
+	struct mmap2_event		mmap2;
 	struct comm_event		comm;
 	struct fork_event		fork;
 	struct lost_event		lost;
@@ -208,6 +222,10 @@ int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_event__process_mmap2(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
 int perf_event__process_fork(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -238,6 +256,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b8727ae..f9f77be 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -64,6 +64,16 @@ void perf_evlist__set_id_pos(struct perf_evlist *evlist)
 	evlist->is_pos = first->is_pos;
 }
 
+static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node)
+		perf_evsel__calc_id_pos(evsel);
+
+	perf_evlist__set_id_pos(evlist);
+}
+
 static void perf_evlist__purge(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos, *n;
@@ -446,20 +456,25 @@ static int perf_evlist__event2id(struct perf_evlist *evlist,
 static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 						   union perf_event *event)
 {
+	struct perf_evsel *first = perf_evlist__first(evlist);
 	struct hlist_head *head;
 	struct perf_sample_id *sid;
 	int hash;
 	u64 id;
 
 	if (evlist->nr_entries == 1)
-		return perf_evlist__first(evlist);
+		return first;
+
+	if (!first->attr.sample_id_all &&
+	    event->header.type != PERF_RECORD_SAMPLE)
+		return first;
 
 	if (perf_evlist__event2id(evlist, event, &id))
 		return NULL;
 
 	/* Synthesized events have an id of zero */
 	if (!id)
-		return perf_evlist__first(evlist);
+		return first;
 
 	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
 	head = &evlist->heads[hash];
@@ -915,6 +930,8 @@ int perf_evlist__open(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int err;
 
+	perf_evlist__update_id_pos(evlist);
+
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
 		if (err < 0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3612183..0ce9feb 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -27,6 +27,7 @@
 static struct {
 	bool sample_id_all;
 	bool exclude_guest;
+	bool mmap2;
 } perf_missing_features;
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
@@ -676,8 +677,9 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	if (opts->sample_weight)
 		attr->sample_type	|= PERF_SAMPLE_WEIGHT;
 
-	attr->mmap = track;
-	attr->comm = track;
+	attr->mmap  = track;
+	attr->mmap2 = track && !perf_missing_features.mmap2;
+	attr->comm  = track;
 
 	/*
 	 * XXX see the function comment above
@@ -1016,6 +1018,8 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	}
 
 fallback_missing_features:
+	if (perf_missing_features.mmap2)
+		evsel->attr.mmap2 = 0;
 	if (perf_missing_features.exclude_guest)
 		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
 retry_sample_id:
@@ -1080,8 +1084,11 @@ try_fallback:
 	if (err != -EINVAL || cpu > 0 || thread > 0)
 		goto out_close;
 
-	if (!perf_missing_features.exclude_guest &&
-	    (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+	if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+		perf_missing_features.mmap2 = true;
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.exclude_guest &&
+		   (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
 		perf_missing_features.exclude_guest = true;
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.sample_id_all) {
@@ -1925,6 +1932,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 		if_print(exclude_hv);
 		if_print(exclude_idle);
 		if_print(mmap);
+		if_print(mmap2);
 		if_print(comm);
 		if_print(freq);
 		if_print(inherit_stat);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a33197a..26441d0 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1351,6 +1351,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 
 		fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip);
 
+		fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2);
+		fprintf(fp, ", attr_mmap  = %d", evsel->attr.mmap);
+		fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data);
 		if (evsel->ids) {
 			fprintf(fp, ", id = {");
 			for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 1dca61f..933d14f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -997,6 +997,54 @@ out_problem:
 	return -1;
 }
 
+int machine__process_mmap2_event(struct machine *machine,
+				 union perf_event *event)
+{
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct thread *thread;
+	struct map *map;
+	enum map_type type;
+	int ret = 0;
+
+	if (dump_trace)
+		perf_event__fprintf_mmap2(event, stdout);
+
+	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    cpumode == PERF_RECORD_MISC_KERNEL) {
+		ret = machine__process_kernel_mmap_event(machine, event);
+		if (ret < 0)
+			goto out_problem;
+		return 0;
+	}
+
+	thread = machine__findnew_thread(machine, event->mmap2.pid,
+					event->mmap2.pid);
+	if (thread == NULL)
+		goto out_problem;
+
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
+		type = MAP__VARIABLE;
+	else
+		type = MAP__FUNCTION;
+
+	map = map__new(&machine->user_dsos, event->mmap2.start,
+			event->mmap2.len, event->mmap2.pgoff,
+			event->mmap2.pid, event->mmap2.maj,
+			event->mmap2.min, event->mmap2.ino,
+			event->mmap2.ino_generation,
+			event->mmap2.filename, type);
+
+	if (map == NULL)
+		goto out_problem;
+
+	thread__insert_map(thread, map);
+	return 0;
+
+out_problem:
+	dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
+	return 0;
+}
+
 int machine__process_mmap_event(struct machine *machine, union perf_event *event)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -1028,7 +1076,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
 	map = map__new(&machine->user_dsos, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			event->mmap.pid, event->mmap.filename,
+			event->mmap.pid, 0, 0, 0, 0,
+			event->mmap.filename,
 			type);
 
 	if (map == NULL)
@@ -1101,6 +1150,8 @@ int machine__process_event(struct machine *machine, union perf_event *event)
 		ret = machine__process_comm_event(machine, event); break;
 	case PERF_RECORD_MMAP:
 		ret = machine__process_mmap_event(machine, event); break;
+	case PERF_RECORD_MMAP2:
+		ret = machine__process_mmap2_event(machine, event); break;
 	case PERF_RECORD_FORK:
 		ret = machine__process_fork_event(machine, event); break;
 	case PERF_RECORD_EXIT:
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 0df925b..58a6be1 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -45,6 +45,7 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 int machine__process_fork_event(struct machine *machine, union perf_event *event);
 int machine__process_lost_event(struct machine *machine, union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event);
+int machine__process_mmap2_event(struct machine *machine, union perf_event *event);
 int machine__process_event(struct machine *machine, union perf_event *event);
 
 typedef void (*machine__process_t)(struct machine *machine, void *data);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 9e8304c..4f6680d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -48,7 +48,8 @@ void map__init(struct map *map, enum map_type type,
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
-		     u64 pgoff, u32 pid, char *filename,
+		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+		     u64 ino_gen, char *filename,
 		     enum map_type type)
 {
 	struct map *map = malloc(sizeof(*map));
@@ -62,6 +63,11 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		vdso = is_vdso_map(filename);
 		no_dso = is_no_dso_memory(filename);
 
+		map->maj = d_maj;
+		map->min = d_min;
+		map->ino = ino;
+		map->ino_generation = ino_gen;
+
 		if (anon) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2cc93cb..4886ca2 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -36,6 +36,9 @@ struct map {
 	bool			erange_warned;
 	u32			priv;
 	u64			pgoff;
+	u32			maj, min; /* only valid for MMAP2 record */
+	u64			ino;      /* only valid for MMAP2 record */
+	u64			ino_generation;/* only valid for MMAP2 record */
 
 	/* ip -> dso rip */
 	u64			(*map_ip)(struct map *, u64);
@@ -88,8 +91,9 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
-		     u64 pgoff, u32 pid, char *filename,
-		     enum map_type type);
+		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+		     u64 ino_gen,
+		     char *filename, enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1fc0c62..51f5edf 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -351,6 +351,25 @@ static void perf_event__mmap_swap(union perf_event *event,
 	}
 }
 
+static void perf_event__mmap2_swap(union perf_event *event,
+				  bool sample_id_all)
+{
+	event->mmap2.pid   = bswap_32(event->mmap2.pid);
+	event->mmap2.tid   = bswap_32(event->mmap2.tid);
+	event->mmap2.start = bswap_64(event->mmap2.start);
+	event->mmap2.len   = bswap_64(event->mmap2.len);
+	event->mmap2.pgoff = bswap_64(event->mmap2.pgoff);
+	event->mmap2.maj   = bswap_32(event->mmap2.maj);
+	event->mmap2.min   = bswap_32(event->mmap2.min);
+	event->mmap2.ino   = bswap_64(event->mmap2.ino);
+
+	if (sample_id_all) {
+		void *data = &event->mmap2.filename;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
+}
 static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
 {
 	event->fork.pid	 = bswap_32(event->fork.pid);
@@ -455,6 +474,7 @@ typedef void (*perf_event__swap_op)(union perf_event *event,
 
 static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_MMAP]		  = perf_event__mmap_swap,
+	[PERF_RECORD_MMAP2]		  = perf_event__mmap2_swap,
 	[PERF_RECORD_COMM]		  = perf_event__comm_swap,
 	[PERF_RECORD_FORK]		  = perf_event__task_swap,
 	[PERF_RECORD_EXIT]		  = perf_event__task_swap,
@@ -504,6 +524,7 @@ static int flush_sample_queue(struct perf_session *s,
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
 	unsigned idx = 0, progress_next = os->nr_samples / 16;
+	bool show_progress = limit == ULLONG_MAX;
 	int ret;
 
 	if (!tool->ordered_samples || !limit)
@@ -526,7 +547,7 @@ static int flush_sample_queue(struct perf_session *s,
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
 		list_add(&iter->list, &os->sample_cache);
-		if (++idx >= progress_next) {
+		if (show_progress && (++idx >= progress_next)) {
 			progress_next += os->nr_samples / 16;
 			ui_progress__update(idx, os->nr_samples,
 					    "Processing time ordered events...");
@@ -850,7 +871,8 @@ static struct machine *
 	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
-		if (event->header.type == PERF_RECORD_MMAP)
+		if (event->header.type == PERF_RECORD_MMAP
+		    || event->header.type == PERF_RECORD_MMAP2)
 			pid = event->mmap.pid;
 		else
 			pid = sample->pid;
@@ -977,6 +999,8 @@ static int perf_session_deliver_event(struct perf_session *session,
 						    sample, evsel, machine);
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
+	case PERF_RECORD_MMAP2:
+		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
 	case PERF_RECORD_FORK:
@@ -1619,52 +1643,26 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 					     const struct perf_evsel_str_handler *assocs,
 					     size_t nr_assocs)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct event_format *format;
 	struct perf_evsel *evsel;
-	char *tracepoint, *name;
 	size_t i;
 	int err;
 
 	for (i = 0; i < nr_assocs; i++) {
-		err = -ENOMEM;
-		tracepoint = strdup(assocs[i].name);
-		if (tracepoint == NULL)
-			goto out;
-
-		err = -ENOENT;
-		name = strchr(tracepoint, ':');
-		if (name == NULL)
-			goto out_free;
-
-		*name++ = '\0';
-		format = pevent_find_event_by_name(session->pevent,
-						   tracepoint, name);
-		if (format == NULL) {
-			/*
-			 * Adding a handler for an event not in the session,
-			 * just ignore it.
-			 */
-			goto next;
-		}
-
-		evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id);
+		/*
+		 * Adding a handler for an event not in the session,
+		 * just ignore it.
+		 */
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name);
 		if (evsel == NULL)
-			goto next;
+			continue;
 
 		err = -EEXIST;
 		if (evsel->handler.func != NULL)
-			goto out_free;
+			goto out;
 		evsel->handler.func = assocs[i].handler;
-next:
-		free(tracepoint);
 	}
 
 	err = 0;
 out:
 	return err;
-
-out_free:
-	free(tracepoint);
-	goto out;
 }
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 62b16b6..4385816 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -29,6 +29,7 @@ struct perf_tool {
 	event_sample	sample,
 			read;
 	event_op	mmap,
+			mmap2,
 			comm,
 			fork,
 			exit,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-08-13 16:51 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-08-13 16:51 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 0499bd867bd17c0a88963551a1583b8efc7b03d7 perf/x86: Add Haswell ULT model number used in Macbook Air and other systems

Two small fixlets.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86: Add Haswell ULT model number used in Macbook Air and other systems

Vince Weaver (1):
      perf/x86: Fix intel QPI uncore event definitions


 arch/x86/kernel/cpu/perf_event_intel.c        | 1 +
 arch/x86/kernel/cpu/perf_event_intel_uncore.c | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index fbc9210..a45d8d4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2270,6 +2270,7 @@ __init int intel_pmu_init(void)
 	case 70:
 	case 71:
 	case 63:
+	case 69:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index cad791d..1fb6c72 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = {
 static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
 	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x02,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x03,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
 	{ /* end: all zeroes */ },
 };
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-07-10  8:52 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-07-10  8:52 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: e5302920da9ef23f9d19d4e9ac85704cc25bee7a perf: Fix interrupt handler timing harness

Two small fixlets.

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      perf/x86/amd: Do not print an error when the device is not present

Stephane Eranian (1):
      perf: Fix interrupt handler timing harness


 arch/x86/kernel/cpu/perf_event_amd_iommu.c | 4 +---
 kernel/events/core.c                       | 4 ++--
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
index 0db655e..639d128 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
@@ -491,10 +491,8 @@ static struct perf_amd_iommu __perf_iommu = {
 static __init int amd_iommu_pc_init(void)
 {
 	/* Make sure the IOMMU PC resource is available */
-	if (!amd_iommu_pc_supported()) {
-		pr_err("perf: amd_iommu PMU not installed. No support!\n");
+	if (!amd_iommu_pc_supported())
 		return -ENODEV;
-	}
 
 	_init_perf_amd_iommu(&__perf_iommu, "amd_iommu");
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1db3af9..1833bc5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -182,7 +182,7 @@ void update_perf_cpu_limits(void)
 	u64 tmp = perf_sample_period_ns;
 
 	tmp *= sysctl_perf_cpu_time_max_percent;
-	tmp = do_div(tmp, 100);
+	do_div(tmp, 100);
 	atomic_set(&perf_sample_allowed_ns, tmp);
 }
 
@@ -232,7 +232,7 @@ DEFINE_PER_CPU(u64, running_sample_length);
 void perf_sample_event_took(u64 sample_len_ns)
 {
 	u64 avg_local_sample_len;
-	u64 local_samples_len = __get_cpu_var(running_sample_length);
+	u64 local_samples_len;
 
 	if (atomic_read(&perf_sample_allowed_ns) == 0)
 		return;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-06-26  8:52 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-06-26  8:52 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: c790b0ad23f427c7522ffed264706238c57c007e hw_breakpoint: Use cpu_possible_mask in {reserve,release}_bp_slot()

Three small fixlets.

 Thanks,

	Ingo

------------------>
Masami Hiramatsu (1):
      kprobes: Fix arch_prepare_kprobe to handle copy insn failures

Oleg Nesterov (2):
      hw_breakpoint: Fix cpu check in task_bp_pinned(cpu)
      hw_breakpoint: Use cpu_possible_mask in {reserve,release}_bp_slot()


 arch/x86/kernel/kprobes/core.c | 14 ++++++++++----
 kernel/events/hw_breakpoint.c  |  6 +++---
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 9895a9a..211bce4 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -365,10 +365,14 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 	return insn.length;
 }
 
-static void __kprobes arch_copy_kprobe(struct kprobe *p)
+static int __kprobes arch_copy_kprobe(struct kprobe *p)
 {
+	int ret;
+
 	/* Copy an instruction with recovering if other optprobe modifies it.*/
-	__copy_instruction(p->ainsn.insn, p->addr);
+	ret = __copy_instruction(p->ainsn.insn, p->addr);
+	if (!ret)
+		return -EINVAL;
 
 	/*
 	 * __copy_instruction can modify the displacement of the instruction,
@@ -384,6 +388,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = p->ainsn.insn[0];
+
+	return 0;
 }
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
@@ -397,8 +403,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	p->ainsn.insn = get_insn_slot();
 	if (!p->ainsn.insn)
 		return -ENOMEM;
-	arch_copy_kprobe(p);
-	return 0;
+
+	return arch_copy_kprobe(p);
 }
 
 void __kprobes arch_arm_kprobe(struct kprobe *p)
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index a64f8ae..20185ea 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -120,7 +120,7 @@ static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
 	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
 		if (iter->hw.bp_target == tsk &&
 		    find_slot_idx(iter) == type &&
-		    cpu == iter->cpu)
+		    (iter->cpu < 0 || cpu == iter->cpu))
 			count += hw_breakpoint_weight(iter);
 	}
 
@@ -149,7 +149,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		return;
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		unsigned int nr;
 
 		nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
@@ -235,7 +235,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 	if (cpu >= 0) {
 		toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	} else {
-		for_each_online_cpu(cpu)
+		for_each_possible_cpu(cpu)
 			toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-06-20  8:58 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-06-20  8:58 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: f1a527899ef0a8a241eb3bea619eb2e29d797f44 perf/x86: Fix broken PEBS-LL support on SNB-EP/IVB-EP

Four fixes. The mmap ones are unfortunately larger than desired - fuzzing 
uncovered bugs that needed perf context life time management changes to 
fix properly.

Thanks,

	Ingo

------------------>
Masami Hiramatsu (1):
      kprobes: Fix to free gone and unused optprobes

Peter Zijlstra (2):
      perf: Fix perf mmap bugs
      perf: Fix mmap() accounting hole

Stephane Eranian (1):
      perf/x86: Fix broken PEBS-LL support on SNB-EP/IVB-EP


 arch/x86/kernel/cpu/perf_event_intel.c |   2 +-
 include/linux/perf_event.h             |   3 +-
 kernel/events/core.c                   | 233 +++++++++++++++++++++++----------
 kernel/events/internal.h               |   4 +
 kernel/kprobes.c                       |  30 +++--
 5 files changed, 187 insertions(+), 85 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f60d41f..a9e2207 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -165,13 +165,13 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
-	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
 static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f463a46..c5b6dbf 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -389,8 +389,7 @@ struct perf_event {
 	/* mmap bits */
 	struct mutex			mmap_mutex;
 	atomic_t			mmap_count;
-	int				mmap_locked;
-	struct user_struct		*mmap_user;
+
 	struct ring_buffer		*rb;
 	struct list_head		rb_entry;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9dc297f..b391907 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -196,9 +196,6 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
-static void ring_buffer_attach(struct perf_event *event,
-			       struct ring_buffer *rb);
-
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -2918,6 +2915,7 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void ring_buffer_put(struct ring_buffer *rb);
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);
 
 static void free_event(struct perf_event *event)
 {
@@ -2942,15 +2940,30 @@ static void free_event(struct perf_event *event)
 		if (has_branch_stack(event)) {
 			static_key_slow_dec_deferred(&perf_sched_events);
 			/* is system-wide event */
-			if (!(event->attach_state & PERF_ATTACH_TASK))
+			if (!(event->attach_state & PERF_ATTACH_TASK)) {
 				atomic_dec(&per_cpu(perf_branch_stack_events,
 						    event->cpu));
+			}
 		}
 	}
 
 	if (event->rb) {
-		ring_buffer_put(event->rb);
-		event->rb = NULL;
+		struct ring_buffer *rb;
+
+		/*
+		 * Can happen when we close an event with re-directed output.
+		 *
+		 * Since we have a 0 refcount, perf_mmap_close() will skip
+		 * over us; possibly making our ring_buffer_put() the last.
+		 */
+		mutex_lock(&event->mmap_mutex);
+		rb = event->rb;
+		if (rb) {
+			rcu_assign_pointer(event->rb, NULL);
+			ring_buffer_detach(event, rb);
+			ring_buffer_put(rb); /* could be last */
+		}
+		mutex_unlock(&event->mmap_mutex);
 	}
 
 	if (is_cgroup_event(event))
@@ -3188,30 +3201,13 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	unsigned int events = POLL_HUP;
 
 	/*
-	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
-	 * grabs the rb reference but perf_event_set_output() overrides it.
-	 * Here is the timeline for two threads T1, T2:
-	 * t0: T1, rb = rcu_dereference(event->rb)
-	 * t1: T2, old_rb = event->rb
-	 * t2: T2, event->rb = new rb
-	 * t3: T2, ring_buffer_detach(old_rb)
-	 * t4: T1, ring_buffer_attach(rb1)
-	 * t5: T1, poll_wait(event->waitq)
-	 *
-	 * To avoid this problem, we grab mmap_mutex in perf_poll()
-	 * thereby ensuring that the assignment of the new ring buffer
-	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 * Pin the event->rb by taking event->mmap_mutex; otherwise
+	 * perf_event_set_output() can swizzle our rb and make us miss wakeups.
 	 */
 	mutex_lock(&event->mmap_mutex);
-
-	rcu_read_lock();
-	rb = rcu_dereference(event->rb);
-	if (rb) {
-		ring_buffer_attach(event, rb);
+	rb = event->rb;
+	if (rb)
 		events = atomic_xchg(&rb->poll, 0);
-	}
-	rcu_read_unlock();
-
 	mutex_unlock(&event->mmap_mutex);
 
 	poll_wait(file, &event->waitq, wait);
@@ -3521,16 +3517,12 @@ static void ring_buffer_attach(struct perf_event *event,
 		return;
 
 	spin_lock_irqsave(&rb->event_lock, flags);
-	if (!list_empty(&event->rb_entry))
-		goto unlock;
-
-	list_add(&event->rb_entry, &rb->event_list);
-unlock:
+	if (list_empty(&event->rb_entry))
+		list_add(&event->rb_entry, &rb->event_list);
 	spin_unlock_irqrestore(&rb->event_lock, flags);
 }
 
-static void ring_buffer_detach(struct perf_event *event,
-			       struct ring_buffer *rb)
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
 {
 	unsigned long flags;
 
@@ -3549,13 +3541,10 @@ static void ring_buffer_wakeup(struct perf_event *event)
 
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (!rb)
-		goto unlock;
-
-	list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
-		wake_up_all(&event->waitq);
-
-unlock:
+	if (rb) {
+		list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+			wake_up_all(&event->waitq);
+	}
 	rcu_read_unlock();
 }
 
@@ -3584,18 +3573,10 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
-	struct perf_event *event, *n;
-	unsigned long flags;
-
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
-		list_del_init(&event->rb_entry);
-		wake_up_all(&event->waitq);
-	}
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	WARN_ON_ONCE(!list_empty(&rb->event_list));
 
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
@@ -3605,26 +3586,100 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 	struct perf_event *event = vma->vm_file->private_data;
 
 	atomic_inc(&event->mmap_count);
+	atomic_inc(&event->rb->mmap_count);
 }
 
+/*
+ * A buffer can be mmap()ed multiple times; either directly through the same
+ * event, or through other events by use of perf_event_set_output().
+ *
+ * In order to undo the VM accounting done by perf_mmap() we need to destroy
+ * the buffer here, where we still have a VM context. This means we need
+ * to detach all events redirecting to us.
+ */
 static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
-		unsigned long size = perf_data_size(event->rb);
-		struct user_struct *user = event->mmap_user;
-		struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = event->rb;
+	struct user_struct *mmap_user = rb->mmap_user;
+	int mmap_locked = rb->mmap_locked;
+	unsigned long size = perf_data_size(rb);
+
+	atomic_dec(&rb->mmap_count);
+
+	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
+		return;
 
-		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->pinned_vm -= event->mmap_locked;
-		rcu_assign_pointer(event->rb, NULL);
-		ring_buffer_detach(event, rb);
+	/* Detach current event from the buffer. */
+	rcu_assign_pointer(event->rb, NULL);
+	ring_buffer_detach(event, rb);
+	mutex_unlock(&event->mmap_mutex);
+
+	/* If there's still other mmap()s of this buffer, we're done. */
+	if (atomic_read(&rb->mmap_count)) {
+		ring_buffer_put(rb); /* can't be last */
+		return;
+	}
+
+	/*
+	 * No other mmap()s, detach from all other events that might redirect
+	 * into the now unreachable buffer. Somewhat complicated by the
+	 * fact that rb::event_lock otherwise nests inside mmap_mutex.
+	 */
+again:
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
+		if (!atomic_long_inc_not_zero(&event->refcount)) {
+			/*
+			 * This event is en-route to free_event() which will
+			 * detach it and remove it from the list.
+			 */
+			continue;
+		}
+		rcu_read_unlock();
+
+		mutex_lock(&event->mmap_mutex);
+		/*
+		 * Check we didn't race with perf_event_set_output() which can
+		 * swizzle the rb from under us while we were waiting to
+		 * acquire mmap_mutex.
+		 *
+		 * If we find a different rb; ignore this event, a next
+		 * iteration will no longer find it on the list. We have to
+		 * still restart the iteration to make sure we're not now
+		 * iterating the wrong list.
+		 */
+		if (event->rb == rb) {
+			rcu_assign_pointer(event->rb, NULL);
+			ring_buffer_detach(event, rb);
+			ring_buffer_put(rb); /* can't be last, we still have one */
+		}
 		mutex_unlock(&event->mmap_mutex);
+		put_event(event);
 
-		ring_buffer_put(rb);
-		free_uid(user);
+		/*
+		 * Restart the iteration; either we're on the wrong list or
+		 * destroyed its integrity by doing a deletion.
+		 */
+		goto again;
 	}
+	rcu_read_unlock();
+
+	/*
+	 * It could be there's still a few 0-ref events on the list; they'll
+	 * get cleaned up by free_event() -- they'll also still have their
+	 * ref on the rb and will free it whenever they are done with it.
+	 *
+	 * Aside from that, this buffer is 'fully' detached and unmapped,
+	 * undo the VM accounting.
+	 */
+
+	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	vma->vm_mm->pinned_vm -= mmap_locked;
+	free_uid(mmap_user);
+
+	ring_buffer_put(rb); /* could be last */
 }
 
 static const struct vm_operations_struct perf_mmap_vmops = {
@@ -3674,12 +3729,24 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
+again:
 	mutex_lock(&event->mmap_mutex);
 	if (event->rb) {
-		if (event->rb->nr_pages == nr_pages)
-			atomic_inc(&event->rb->refcount);
-		else
+		if (event->rb->nr_pages != nr_pages) {
 			ret = -EINVAL;
+			goto unlock;
+		}
+
+		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
+			/*
+			 * Raced against perf_mmap_close() through
+			 * perf_event_set_output(). Try again, hope for better
+			 * luck.
+			 */
+			mutex_unlock(&event->mmap_mutex);
+			goto again;
+		}
+
 		goto unlock;
 	}
 
@@ -3720,12 +3787,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		ret = -ENOMEM;
 		goto unlock;
 	}
-	rcu_assign_pointer(event->rb, rb);
+
+	atomic_set(&rb->mmap_count, 1);
+	rb->mmap_locked = extra;
+	rb->mmap_user = get_current_user();
 
 	atomic_long_add(user_extra, &user->locked_vm);
-	event->mmap_locked = extra;
-	event->mmap_user = get_current_user();
-	vma->vm_mm->pinned_vm += event->mmap_locked;
+	vma->vm_mm->pinned_vm += extra;
+
+	ring_buffer_attach(event, rb);
+	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_update_userpage(event);
 
@@ -3734,7 +3805,11 @@ unlock:
 		atomic_inc(&event->mmap_count);
 	mutex_unlock(&event->mmap_mutex);
 
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	/*
+	 * Since pinned accounting is per vm we cannot allow fork() to copy our
+	 * vma.
+	 */
+	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_ops = &perf_mmap_vmops;
 
 	return ret;
@@ -6412,6 +6487,8 @@ set:
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
 
+	old_rb = event->rb;
+
 	if (output_event) {
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
@@ -6419,16 +6496,28 @@ set:
 			goto unlock;
 	}
 
-	old_rb = event->rb;
-	rcu_assign_pointer(event->rb, rb);
 	if (old_rb)
 		ring_buffer_detach(event, old_rb);
+
+	if (rb)
+		ring_buffer_attach(event, rb);
+
+	rcu_assign_pointer(event->rb, rb);
+
+	if (old_rb) {
+		ring_buffer_put(old_rb);
+		/*
+		 * Since we detached before setting the new rb, so that we
+		 * could attach the new rb, we could have missed a wakeup.
+		 * Provide it now.
+		 */
+		wake_up_all(&event->waitq);
+	}
+
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
 
-	if (old_rb)
-		ring_buffer_put(old_rb);
 out:
 	return ret;
 }
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index eb675c4..ca65997 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -31,6 +31,10 @@ struct ring_buffer {
 	spinlock_t			event_lock;
 	struct list_head		event_list;
 
+	atomic_t			mmap_count;
+	unsigned long			mmap_locked;
+	struct user_struct		*mmap_user;
+
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
 };
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3fed7f0..bddf3b2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -467,6 +467,7 @@ static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
 /* Optimization staging list, protected by kprobe_mutex */
 static LIST_HEAD(optimizing_list);
 static LIST_HEAD(unoptimizing_list);
+static LIST_HEAD(freeing_list);
 
 static void kprobe_optimizer(struct work_struct *work);
 static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
@@ -504,7 +505,7 @@ static __kprobes void do_optimize_kprobes(void)
  * Unoptimize (replace a jump with a breakpoint and remove the breakpoint
  * if need) kprobes listed on unoptimizing_list.
  */
-static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
+static __kprobes void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
@@ -515,9 +516,9 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
 	/* Ditto to do_optimize_kprobes */
 	get_online_cpus();
 	mutex_lock(&text_mutex);
-	arch_unoptimize_kprobes(&unoptimizing_list, free_list);
+	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
-	list_for_each_entry_safe(op, tmp, free_list, list) {
+	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
 		/* Disarm probes if marked disabled */
 		if (kprobe_disabled(&op->kp))
 			arch_disarm_kprobe(&op->kp);
@@ -536,11 +537,11 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
 }
 
 /* Reclaim all kprobes on the free_list */
-static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list)
+static __kprobes void do_free_cleaned_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
-	list_for_each_entry_safe(op, tmp, free_list, list) {
+	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
 		BUG_ON(!kprobe_unused(&op->kp));
 		list_del_init(&op->list);
 		free_aggr_kprobe(&op->kp);
@@ -556,8 +557,6 @@ static __kprobes void kick_kprobe_optimizer(void)
 /* Kprobe jump optimizer */
 static __kprobes void kprobe_optimizer(struct work_struct *work)
 {
-	LIST_HEAD(free_list);
-
 	mutex_lock(&kprobe_mutex);
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
@@ -566,7 +565,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 	 * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
 	 * kprobes before waiting for quiesence period.
 	 */
-	do_unoptimize_kprobes(&free_list);
+	do_unoptimize_kprobes();
 
 	/*
 	 * Step 2: Wait for quiesence period to ensure all running interrupts
@@ -581,7 +580,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 	do_optimize_kprobes();
 
 	/* Step 4: Free cleaned kprobes after quiesence period */
-	do_free_cleaned_kprobes(&free_list);
+	do_free_cleaned_kprobes();
 
 	mutex_unlock(&module_mutex);
 	mutex_unlock(&kprobe_mutex);
@@ -723,8 +722,19 @@ static void __kprobes kill_optimized_kprobe(struct kprobe *p)
 	if (!list_empty(&op->list))
 		/* Dequeue from the (un)optimization queue */
 		list_del_init(&op->list);
-
 	op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+
+	if (kprobe_unused(p)) {
+		/* Enqueue if it is unused */
+		list_add(&op->list, &freeing_list);
+		/*
+		 * Remove unused probes from the hash list. After waiting
+		 * for synchronization, this probe is reclaimed.
+		 * (reclaiming is done by do_free_cleaned_kprobes().)
+		 */
+		hlist_del_rcu(&op->kp.hlist);
+	}
+
 	/* Don't touch the code, because it is already freed. */
 	arch_remove_optimized_kprobe(op);
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-05-05 10:10 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-05-05 10:10 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 7cc23cd6c0c7d7f4bee057607e7ce01568925717 perf/x86/intel/lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL

Misc fixes plus a small hw-enablement patch for Intel IB model 58 uncore 
events.

 Thanks,

	Ingo

------------------>
Jan-Simon Möller (1):
      perf/x86/intel: Fix unintended variable name reuse

Jiri Olsa (1):
      perf: Fix vmalloc ring buffer pages handling

Li Fei (1):
      x86: Eliminate irq_mis_count counted in arch_irq_stat

Peter Zijlstra (3):
      perf/x86: Blacklist all MEM_*_RETIRED events for Ivy Bridge
      perf/x86/intel/lbr: Fix LBR filter
      perf/x86/intel/lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL

Vince Weaver (2):
      perf/x86/intel: Fix typo in perf_event_intel_uncore.c
      perf/x86/intel: Add support for IvyBridge model 58 Uncore


 arch/x86/kernel/cpu/perf_event_intel.c        | 13 +++++++++----
 arch/x86/kernel/cpu/perf_event_intel_lbr.c    | 27 ++++++++++++++++++++++-----
 arch/x86/kernel/cpu/perf_event_intel_uncore.c | 19 ++++++++++---------
 arch/x86/kernel/irq.c                         |  4 ----
 kernel/events/ring_buffer.c                   | 14 ++++++++++----
 5 files changed, 51 insertions(+), 26 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index cc45deb..4a0a462 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -125,10 +125,15 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
-	INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /*  MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+	/*
+	 * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT
+	 * siblings; disable these events because they can corrupt unrelated
+	 * counters.
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index da02e9c..d978353 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -310,7 +310,7 @@ void intel_pmu_lbr_read(void)
  * - in case there is no HW filter
  * - in case the HW filter has errata or limitations
  */
-static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 {
 	u64 br_type = event->attr.branch_sample_type;
 	int mask = 0;
@@ -318,8 +318,11 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	if (br_type & PERF_SAMPLE_BRANCH_USER)
 		mask |= X86_BR_USER;
 
-	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
+	if (br_type & PERF_SAMPLE_BRANCH_KERNEL) {
+		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
 		mask |= X86_BR_KERNEL;
+	}
 
 	/* we ignore BRANCH_HV here */
 
@@ -339,6 +342,8 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	 * be used by fixup code for some CPU
 	 */
 	event->hw.branch_reg.reg = mask;
+
+	return 0;
 }
 
 /*
@@ -386,7 +391,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
 	/*
 	 * setup SW LBR filter
 	 */
-	intel_pmu_setup_sw_lbr_filter(event);
+	ret = intel_pmu_setup_sw_lbr_filter(event);
+	if (ret)
+		return ret;
 
 	/*
 	 * setup HW LBR filter, if any
@@ -442,8 +449,18 @@ static int branch_type(unsigned long from, unsigned long to)
 			return X86_BR_NONE;
 
 		addr = buf;
-	} else
-		addr = (void *)from;
+	} else {
+		/*
+		 * The LBR logs any address in the IP, even if the IP just
+		 * faulted. This means userspace can control the from address.
+		 * Ensure we don't blindy read any address by validating it is
+		 * a known text address.
+		 */
+		if (kernel_text_address(from))
+			addr = (void *)from;
+		else
+			return X86_BR_NONE;
+	}
 
 	/*
 	 * decoder needs to know the ABI especially
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index b43200d..45f6d13 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2428,7 +2428,7 @@ static void __init uncore_types_exit(struct intel_uncore_type **types)
 static int __init uncore_type_init(struct intel_uncore_type *type)
 {
 	struct intel_uncore_pmu *pmus;
-	struct attribute_group *events_group;
+	struct attribute_group *attr_group;
 	struct attribute **attrs;
 	int i, j;
 
@@ -2455,19 +2455,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 		while (type->event_descs[i].attr.attr.name)
 			i++;
 
-		events_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
-					sizeof(*events_group), GFP_KERNEL);
-		if (!events_group)
+		attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
+					sizeof(*attr_group), GFP_KERNEL);
+		if (!attr_group)
 			goto fail;
 
-		attrs = (struct attribute **)(events_group + 1);
-		events_group->name = "events";
-		events_group->attrs = attrs;
+		attrs = (struct attribute **)(attr_group + 1);
+		attr_group->name = "events";
+		attr_group->attrs = attrs;
 
 		for (j = 0; j < i; j++)
 			attrs[j] = &type->event_descs[j].attr.attr;
 
-		type->events_group = events_group;
+		type->events_group = attr_group;
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
@@ -2853,11 +2853,12 @@ static int __init uncore_cpu_init(void)
 		msr_uncores = nhm_msr_uncores;
 		break;
 	case 42: /* Sandy Bridge */
+	case 58: /* Ivy Bridge */
 		if (snb_uncore_cbox.num_boxes > max_cores)
 			snb_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snb_msr_uncores;
 		break;
-	case 45: /* Sandy Birdge-EP */
+	case 45: /* Sandy Bridge-EP */
 		if (snbep_uncore_cbox.num_boxes > max_cores)
 			snbep_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snbep_msr_uncores;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e4595f1..84b7789 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -165,10 +165,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 u64 arch_irq_stat(void)
 {
 	u64 sum = atomic_read(&irq_err_count);
-
-#ifdef CONFIG_X86_IO_APIC
-	sum += atomic_read(&irq_mis_count);
-#endif
 	return sum;
 }
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 97fddb0..cd55144 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -326,11 +326,16 @@ void rb_free(struct ring_buffer *rb)
 }
 
 #else
+static int data_page_nr(struct ring_buffer *rb)
+{
+	return rb->nr_pages << page_order(rb);
+}
 
 struct page *
 perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
 {
-	if (pgoff > (1UL << page_order(rb)))
+	/* The '>' counts in the user page. */
+	if (pgoff > data_page_nr(rb))
 		return NULL;
 
 	return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE);
@@ -350,10 +355,11 @@ static void rb_free_work(struct work_struct *work)
 	int i, nr;
 
 	rb = container_of(work, struct ring_buffer, work);
-	nr = 1 << page_order(rb);
+	nr = data_page_nr(rb);
 
 	base = rb->user_page;
-	for (i = 0; i < nr + 1; i++)
+	/* The '<=' counts in the user page. */
+	for (i = 0; i <= nr; i++)
 		perf_mmap_unmark_page(base + (i * PAGE_SIZE));
 
 	vfree(base);
@@ -387,7 +393,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	rb->user_page = all_buf;
 	rb->data_pages[0] = all_buf + PAGE_SIZE;
 	rb->page_order = ilog2(nr_pages);
-	rb->nr_pages = 1;
+	rb->nr_pages = !!nr_pages;
 
 	ring_buffer_init(rb, watermark, flags);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-04-21  8:16 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-04-21  8:16 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: f1923820c447e986a9da0fc6bf60c1dccdf0408e perf/x86: Fix offcore_rsp valid mask for SNB/IVB

Misc fixes.

 Thanks,

	Ingo

------------------>
Stephane Eranian (1):
      perf/x86: Fix offcore_rsp valid mask for SNB/IVB

Tommi Rantala (1):
      perf: Treat attr.config as u64 in perf_swevent_init()


 arch/x86/kernel/cpu/perf_event_intel.c | 20 ++++++++++++++++----
 kernel/events/core.c                   |  2 +-
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index dab7580..cc45deb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -153,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 };
 
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -2097,7 +2103,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 45)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
@@ -2123,7 +2132,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_ivb_event_constraints;
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 62)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7e0962e..4d3124b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5331,7 +5331,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 
 static int perf_swevent_init(struct perf_event *event)
 {
-	int event_id = event->attr.config;
+	u64 event_id = event->attr.config;
 
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-04-14 15:20 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-04-14 15:20 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: c481420248c6730246d2a1b1773d5d7007ae0835 perf: Fix error return code

Misc fixlets.

 Thanks,

	Ingo

------------------>
Chen Gang (3):
      perf: Fix strncpy() use, always make sure it's NUL terminated
      perf: Fix strncpy() use, use strlcpy() instead of strncpy()
      ftrace: Fix strncpy() use, use strlcpy() instead of strncpy()

Stephane Eranian (2):
      perf/x86: Fix uninitialized pt_regs in intel_pmu_drain_bts_buffer()
      perf: Fix ring_buffer perf_output_space() boundary calculation

Wei Yongjun (1):
      perf: Fix error return code


 arch/x86/kernel/cpu/perf_event_intel_ds.c |  3 ++-
 kernel/events/core.c                      |  4 +++-
 kernel/events/internal.h                  |  2 +-
 kernel/events/ring_buffer.c               | 22 ++++++++++++++++++----
 kernel/trace/ftrace.c                     |  4 ++--
 kernel/trace/trace.c                      |  4 ++--
 6 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a..f71c9f0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void)
 	if (top <= at)
 		return 0;
 
+	memset(&regs, 0, sizeof(regs));
+
 	ds->bts_index = ds->bts_buffer_base;
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
-	regs.ip     = 0;
 
 	/*
 	 * Prepare a generic sample, i.e. fill in the invariant fields.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 59412d0..7e0962e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4737,7 +4737,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	} else {
 		if (arch_vma_name(mmap_event->vma)) {
 			name = strncpy(tmp, arch_vma_name(mmap_event->vma),
-				       sizeof(tmp));
+				       sizeof(tmp) - 1);
+			tmp[sizeof(tmp) - 1] = '\0';
 			goto got_name;
 		}
 
@@ -5986,6 +5987,7 @@ skip_type:
 	if (pmu->pmu_cpu_context)
 		goto got_cpu_context;
 
+	ret = -ENOMEM;
 	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
 	if (!pmu->pmu_cpu_context)
 		goto free_dev;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index d56a64c..eb675c4 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -16,7 +16,7 @@ struct ring_buffer {
 	int				page_order;	/* allocation order  */
 #endif
 	int				nr_pages;	/* nr of data pages  */
-	int				writable;	/* are we writable   */
+	int				overwrite;	/* can overwrite itself */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 23cb34f..97fddb0 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -18,12 +18,24 @@
 static bool perf_output_space(struct ring_buffer *rb, unsigned long tail,
 			      unsigned long offset, unsigned long head)
 {
-	unsigned long mask;
+	unsigned long sz = perf_data_size(rb);
+	unsigned long mask = sz - 1;
 
-	if (!rb->writable)
+	/*
+	 * check if user-writable
+	 * overwrite : over-write its own tail
+	 * !overwrite: buffer possibly drops events.
+	 */
+	if (rb->overwrite)
 		return true;
 
-	mask = perf_data_size(rb) - 1;
+	/*
+	 * verify that payload is not bigger than buffer
+	 * otherwise masking logic may fail to detect
+	 * the "not enough space" condition
+	 */
+	if ((head - offset) > sz)
+		return false;
 
 	offset = (offset - tail) & mask;
 	head   = (head   - tail) & mask;
@@ -212,7 +224,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->watermark = max_size / 2;
 
 	if (flags & RING_BUFFER_WRITABLE)
-		rb->writable = 1;
+		rb->overwrite = 0;
+	else
+		rb->overwrite = 1;
 
 	atomic_set(&rb->refcount, 1);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6893d5a..db14374 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3441,14 +3441,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
 
 static int __init set_ftrace_notrace(char *str)
 {
-	strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+	strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
 __setup("ftrace_notrace=", set_ftrace_notrace);
 
 static int __init set_ftrace_filter(char *str)
 {
-	strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+	strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
 __setup("ftrace_filter=", set_ftrace_filter);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4f1dade..3f5046a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -132,7 +132,7 @@ static char *default_bootup_tracer;
 
 static int __init set_cmdline_ftrace(char *str)
 {
-	strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+	strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
 	/* We are using ftrace early, expand it */
 	ring_buffer_expanded = 1;
@@ -162,7 +162,7 @@ static char *trace_boot_options __initdata;
 
 static int __init set_trace_boot_options(char *str)
 {
-	strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+	strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
 	trace_boot_options = trace_boot_options_buf;
 	return 0;
 }


^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-03-21  9:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-03-21  9:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: fd4a5aef002bb57e8a35ed34d8a878034b9bde94 perf/x86: Add SNB/SNB-EP scheduling constraints for cycle_activity event

A fair chunk of the linecount comes from a fix for a tracing bug that 
corrupts latency tracing buffers when the overwrite mode is changed on
the fly - the rest is mostly assorted fewliner fixlets.

Thanks,

	Ingo

------------------>
Ananth N Mavinakayanahalli (1):
      perf probe: Fix segfault

Jack Mitchell (1):
      libtraceevent: Remove hard coded include to /usr/local/include in Makefile

Jiri Olsa (1):
      perf record: Fix -C option

Marcin Slusarz (1):
      perf tools: check if -DFORTIFY_SOURCE=2 is allowed

Masami Hiramatsu (2):
      kprobes: Make hash_64() as always inlined
      kprobes/x86: Check Interrupt Flag modifier when registering probe

Michael Ellerman (2):
      perf annotate: Fix build with NO_NEWT=1
      perf report: Fix build with NO_NEWT=1

Namhyung Kim (2):
      perf: Reset hwc->last_period on sw clock events
      perf: Generate EXIT event only once per task context

Stephane Eranian (1):
      perf/x86: Add SNB/SNB-EP scheduling constraints for cycle_activity event

Steven Rostedt (Red Hat) (5):
      tracing: Fix race in snapshot swapping
      tracing: Fix free of probe entry by calling call_rcu_sched()
      tracing: Protect tracer flags with trace_types_lock
      tracing: Keep overwrite in sync between regular and snapshot buffers
      tracing: Prevent buffer overwrite disabled for latency tracers

Sukadev Bhattiprolu (1):
      perf/POWER7: Create a sysfs format entry for Power7 events

Vinson Lee (1):
      perf tools: Fix LIBNUMA build with glibc 2.12 and older.


 arch/powerpc/perf/power7-pmu.c         | 13 ++++++++
 arch/x86/include/asm/kprobes.h         |  1 +
 arch/x86/kernel/cpu/perf_event_intel.c |  4 +++
 arch/x86/kernel/kprobes/core.c         |  5 ++-
 include/linux/hash.h                   |  3 +-
 kernel/events/core.c                   |  8 +++--
 kernel/trace/ftrace.c                  |  4 +--
 kernel/trace/trace.c                   | 59 +++++++++++++++++++++++++++-------
 kernel/trace/trace.h                   |  6 ++++
 kernel/trace/trace_irqsoff.c           | 19 ++++++++---
 kernel/trace/trace_sched_wakeup.c      | 18 ++++++++---
 tools/lib/traceevent/Makefile          |  2 +-
 tools/perf/Makefile                    |  8 ++++-
 tools/perf/bench/bench.h               | 24 ++++++++++++++
 tools/perf/builtin-record.c            |  6 ++--
 tools/perf/util/hist.h                 |  5 +--
 tools/perf/util/strlist.c              |  2 +-
 17 files changed, 152 insertions(+), 35 deletions(-)

diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index b554879..3c475d6 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -420,7 +420,20 @@ static struct attribute_group power7_pmu_events_group = {
 	.attrs = power7_events_attr,
 };
 
+PMU_FORMAT_ATTR(event, "config:0-19");
+
+static struct attribute *power7_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+struct attribute_group power7_pmu_format_group = {
+	.name = "format",
+	.attrs = power7_pmu_format_attr,
+};
+
 static const struct attribute_group *power7_pmu_attr_groups[] = {
+	&power7_pmu_format_group,
 	&power7_pmu_events_group,
 	NULL,
 };
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index d3ddd17..5a6d287 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -77,6 +77,7 @@ struct arch_specific_insn {
 	 * a post_handler or break_handler).
 	 */
 	int boostable;
+	bool if_modifier;
 };
 
 struct arch_optimized_insn {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 529c893..dab7580 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -101,6 +101,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3f06e61..7bfe318 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -375,6 +375,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 	else
 		p->ainsn.boostable = -1;
 
+	/* Check whether the instruction modifies Interrupt Flag or not */
+	p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
+
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = p->ainsn.insn[0];
 }
@@ -434,7 +437,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
 		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	if (is_IF_modifier(p->ainsn.insn))
+	if (p->ainsn.if_modifier)
 		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
 }
 
diff --git a/include/linux/hash.h b/include/linux/hash.h
index 61c97ae..f09a0ae 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -15,6 +15,7 @@
  */
 
 #include <asm/types.h>
+#include <linux/compiler.h>
 
 /* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
 #define GOLDEN_RATIO_PRIME_32 0x9e370001UL
@@ -31,7 +32,7 @@
 #error Wordsize not 32 or 64
 #endif
 
-static inline u64 hash_64(u64 val, unsigned int bits)
+static __always_inline u64 hash_64(u64 val, unsigned int bits)
 {
 	u64 hash = val;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b0cd865..59412d0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4434,12 +4434,15 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 			if (ctxn < 0)
 				goto next;
 			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+			if (ctx)
+				perf_event_task_ctx(ctx, task_event);
 		}
-		if (ctx)
-			perf_event_task_ctx(ctx, task_event);
 next:
 		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
+	if (task_event->task_ctx)
+		perf_event_task_ctx(task_event->task_ctx, task_event);
+
 	rcu_read_unlock();
 }
 
@@ -5647,6 +5650,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
 		event->attr.sample_period = NSEC_PER_SEC / freq;
 		hwc->sample_period = event->attr.sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
+		hwc->last_period = hwc->sample_period;
 		event->attr.freq = 0;
 	}
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ab25b88..6893d5a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3104,8 +3104,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 					continue;
 			}
 
-			hlist_del(&entry->node);
-			call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+			hlist_del_rcu(&entry->node);
+			call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
 		}
 	}
 	__disable_ftrace_function_probe();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1f835a8..4f1dade 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -704,7 +704,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-	struct ring_buffer *buf = tr->buffer;
+	struct ring_buffer *buf;
 
 	if (trace_stop_count)
 		return;
@@ -719,6 +719,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	arch_spin_lock(&ftrace_max_lock);
 
+	buf = tr->buffer;
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
@@ -2880,11 +2881,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 	return -EINVAL;
 }
 
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+	if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+		return -1;
+
+	return 0;
+}
+
+int set_tracer_flag(unsigned int mask, int enabled)
 {
 	/* do nothing if flag is already set */
 	if (!!(trace_flags & mask) == !!enabled)
-		return;
+		return 0;
+
+	/* Give the tracer a chance to approve the change */
+	if (current_trace->flag_changed)
+		if (current_trace->flag_changed(current_trace, mask, !!enabled))
+			return -EINVAL;
 
 	if (enabled)
 		trace_flags |= mask;
@@ -2894,18 +2909,24 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
 
-	if (mask == TRACE_ITER_OVERWRITE)
+	if (mask == TRACE_ITER_OVERWRITE) {
 		ring_buffer_change_overwrite(global_trace.buffer, enabled);
+#ifdef CONFIG_TRACER_MAX_TRACE
+		ring_buffer_change_overwrite(max_tr.buffer, enabled);
+#endif
+	}
 
 	if (mask == TRACE_ITER_PRINTK)
 		trace_printk_start_stop_comm(enabled);
+
+	return 0;
 }
 
 static int trace_set_options(char *option)
 {
 	char *cmp;
 	int neg = 0;
-	int ret = 0;
+	int ret = -ENODEV;
 	int i;
 
 	cmp = strstrip(option);
@@ -2915,19 +2936,20 @@ static int trace_set_options(char *option)
 		cmp += 2;
 	}
 
+	mutex_lock(&trace_types_lock);
+
 	for (i = 0; trace_options[i]; i++) {
 		if (strcmp(cmp, trace_options[i]) == 0) {
-			set_tracer_flags(1 << i, !neg);
+			ret = set_tracer_flag(1 << i, !neg);
 			break;
 		}
 	}
 
 	/* If no option could be set, test the specific tracer options */
-	if (!trace_options[i]) {
-		mutex_lock(&trace_types_lock);
+	if (!trace_options[i])
 		ret = set_tracer_option(current_trace, cmp, neg);
-		mutex_unlock(&trace_types_lock);
-	}
+
+	mutex_unlock(&trace_types_lock);
 
 	return ret;
 }
@@ -2937,6 +2959,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
 {
 	char buf[64];
+	int ret;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
@@ -2946,7 +2969,9 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 
 	buf[cnt] = 0;
 
-	trace_set_options(buf);
+	ret = trace_set_options(buf);
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -3250,6 +3275,9 @@ static int tracing_set_tracer(const char *buf)
 		goto out;
 
 	trace_branch_disable();
+
+	current_trace->enabled = false;
+
 	if (current_trace->reset)
 		current_trace->reset(tr);
 
@@ -3294,6 +3322,7 @@ static int tracing_set_tracer(const char *buf)
 	}
 
 	current_trace = t;
+	current_trace->enabled = true;
 	trace_branch_enable(tr);
  out:
 	mutex_unlock(&trace_types_lock);
@@ -4780,7 +4809,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (val != 0 && val != 1)
 		return -EINVAL;
-	set_tracer_flags(1 << index, val);
+
+	mutex_lock(&trace_types_lock);
+	ret = set_tracer_flag(1 << index, val);
+	mutex_unlock(&trace_types_lock);
+
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 57d7e53..2081971 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -283,11 +283,15 @@ struct tracer {
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
+	/* Return 0 if OK with change, else return non-zero */
+	int			(*flag_changed)(struct tracer *tracer,
+						u32 mask, int set);
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	bool			print_max;
 	bool			use_max_tr;
 	bool			allocated_snapshot;
+	bool			enabled;
 };
 
 
@@ -943,6 +947,8 @@ extern const char *__stop___trace_bprintk_fmt[];
 
 void trace_printk_init_buffers(void);
 void trace_printk_start_comm(void);
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(unsigned int mask, int enabled);
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 713a2ca..443b25b 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,7 @@ enum {
 
 static int trace_type __read_mostly;
 
-static int save_lat_flag;
+static int save_flags;
 
 static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
 static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -558,8 +558,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	irqsoff_trace = tr;
@@ -573,10 +576,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_irqsoff_tracer(tr, is_graph());
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
@@ -609,6 +615,7 @@ static struct tracer irqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
 #endif
@@ -642,6 +649,7 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
 #endif
@@ -677,6 +685,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 75aa97f..fde652c 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr);
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
 static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
-static int save_lat_flag;
+static int save_flags;
 
 #define TRACE_DISPLAY_GRAPH     1
 
@@ -540,8 +540,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	wakeup_trace = tr;
@@ -563,12 +566,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_wakeup_tracer(tr);
 	/* make sure we put back any tasks we are tracing */
 	wakeup_reset(tr);
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
@@ -594,6 +600,7 @@ static struct tracer wakeup_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
@@ -615,6 +622,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index a20e320..0b0a907 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -122,7 +122,7 @@ export Q VERBOSE
 
 EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
 
-INCLUDES = -I. -I/usr/local/include $(CONFIG_INCLUDES)
+INCLUDES = -I. $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -Wall
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index a2108ca..bb74c79 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -95,7 +95,7 @@ ifeq ("$(origin DEBUG)", "command line")
   PERF_DEBUG = $(DEBUG)
 endif
 ifndef PERF_DEBUG
-  CFLAGS_OPTIMIZE = -O6 -D_FORTIFY_SOURCE=2
+  CFLAGS_OPTIMIZE = -O6
 endif
 
 ifdef PARSER_DEBUG
@@ -180,6 +180,12 @@ ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-W
        CFLAGS := $(CFLAGS) -Wvolatile-register-var
 endif
 
+ifndef PERF_DEBUG
+	ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y)
+		CFLAGS := $(CFLAGS) -D_FORTIFY_SOURCE=2
+	endif
+endif
+
 ### --- END CONFIGURATION SECTION ---
 
 ifeq ($(srctree),)
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index a5223e6..0fdc852 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -1,6 +1,30 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+/*
+ * The madvise transparent hugepage constants were added in glibc
+ * 2.13. For compatibility with older versions of glibc, define these
+ * tokens if they are not already defined.
+ *
+ * PA-RISC uses different madvise values from other architectures and
+ * needs to be special-cased.
+ */
+#ifdef __hppa__
+# ifndef MADV_HUGEPAGE
+#  define MADV_HUGEPAGE		67
+# endif
+# ifndef MADV_NOHUGEPAGE
+#  define MADV_NOHUGEPAGE	68
+# endif
+#else
+# ifndef MADV_HUGEPAGE
+#  define MADV_HUGEPAGE		14
+# endif
+# ifndef MADV_NOHUGEPAGE
+#  define MADV_NOHUGEPAGE	15
+# endif
+#endif
+
 extern int bench_numa(int argc, const char **argv, const char *prefix);
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 774c907..f1a939e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -573,13 +573,15 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 					 perf_event__synthesize_guest_os, tool);
 	}
 
-	if (!opts->target.system_wide)
+	if (perf_target__has_task(&opts->target))
 		err = perf_event__synthesize_thread_map(tool, evsel_list->threads,
 						  process_synthesized_event,
 						  machine);
-	else
+	else if (perf_target__has_cpu(&opts->target))
 		err = perf_event__synthesize_threads(tool, process_synthesized_event,
 					       machine);
+	else /* command specified */
+		err = 0;
 
 	if (err != 0)
 		goto out_delete_session;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 3862468..226a4ae 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -208,8 +208,9 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 	return 0;
 }
 
-#define K_LEFT -1
-#define K_RIGHT -2
+#define K_LEFT  -1000
+#define K_RIGHT -2000
+#define K_SWITCH_INPUT_DATA -3000
 #endif
 
 #ifdef GTK2_SUPPORT
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 55433aa..eabdce0 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -143,7 +143,7 @@ struct strlist *strlist__new(bool dupstr, const char *list)
 		slist->rblist.node_delete = strlist__node_delete;
 
 		slist->dupstr	 = dupstr;
-		if (slist && strlist__parse_list(slist, list) != 0)
+		if (list && strlist__parse_list(slist, list) != 0)
 			goto out_error;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-15  8:01                     ` Stephane Eranian
@ 2013-03-15 10:50                       ` Stephane Eranian
  0 siblings, 0 replies; 376+ messages in thread
From: Stephane Eranian @ 2013-03-15 10:50 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Fri, Mar 15, 2013 at 9:01 AM, Stephane Eranian <eranian@google.com> wrote:
> On Fri, Mar 15, 2013 at 2:06 AM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
>> On Thu, Mar 14, 2013 at 5:24 PM, Stephane Eranian <eranian@google.com> wrote:
>>>
>>> I bet if you force the affinity of your perf record to be on
>>> a CPU other than CPU0, you will not get the crash.
>>>
>>> This is what I am seeing now. I appears on resume,
>>> CPU0 hotplug callbacks for perf_events are not invoked
>>> leaving DS_AREA MSR to 0.
>>>
>>> Can you confirm on your machine?
>>
>> I'm not even going to bother confirming it, because I think you're
>> right, and I think the reason is clear: the DS initialization code
>> uses the CPU_UP notifiers.
>>
> Ok, I instrumented the pebs_enable() function and I confirm that
> DS_AREA=0 on resume.
>
> So what seems broken here for me is that on suspend, the cpu notifier
> ends up calling fini_debug_store() to clear DS_AREA for CPU0. But
> on resume, the same notifier does NOT call the init_debug_store().
> I don't understand this asymmetry. You either do neither or you do
> both.
>
Ok, corrections. I ran some more tests. On the suspend path, the cpu
notifier is not called for CPU0. However when the machine comes back
up, DS_AREA is  0 which is the power-up default value. And given that
the notifier is not called for CPU0, that is the value we inherit later on
and which causes the crash.

>
>> And that's sufficient for CPU hotplug, which is what suspend/resume
>> ends up doing for all but the boot CPU. But the boot CPU is not
>> hotplugged.
>>
>> Using CPU_UP notifiers is wrong, and they get called too late anyway.
>>
>> The code should use a real resume method. Or, better yet, just do it
>> right, and do it from __restore_processor_state().
>>
I will produce a patch to use this function, it's simple enough.

>> Those f*cking CPU notifiers are a pain in the ass, and the tend to be
>> invariably broken, and they have their own idiotic hacks that are
>> equally broken (ie that x86_pmu_notifier() thing seems to make up its
>> own suspend/resume with
>> "x86_pmu.cpu_prepare/cpu_starting/cpu_dying/cpu_dead" things.
>>
>> I guess we could make the BP do a fake cpu notifier thing around the
>> suspend of the boot processor as well, but most of the per-CPU stuff
>> seems to be perfectly fine without it (ie mtrr, apic, etc etc all use
>> the suspend/resume infrastructure) and doesn't need that kind of
>> stuff.
>>
>>                 Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-15  1:06                   ` Linus Torvalds
@ 2013-03-15  8:01                     ` Stephane Eranian
  2013-03-15 10:50                       ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-15  8:01 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Fri, Mar 15, 2013 at 2:06 AM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
> On Thu, Mar 14, 2013 at 5:24 PM, Stephane Eranian <eranian@google.com> wrote:
>>
>> I bet if you force the affinity of your perf record to be on
>> a CPU other than CPU0, you will not get the crash.
>>
>> This is what I am seeing now. I appears on resume,
>> CPU0 hotplug callbacks for perf_events are not invoked
>> leaving DS_AREA MSR to 0.
>>
>> Can you confirm on your machine?
>
> I'm not even going to bother confirming it, because I think you're
> right, and I think the reason is clear: the DS initialization code
> uses the CPU_UP notifiers.
>
Ok, I instrumented the pebs_enable() function and I confirm that
DS_AREA=0 on resume.

So what seems broken here for me is that on suspend, the cpu notifier
ends up calling fini_debug_store() to clear DS_AREA for CPU0. But
on resume, the same notifier does NOT call the init_debug_store().
I don't understand this asymmetry. You either do neither or you do
both.


> And that's sufficient for CPU hotplug, which is what suspend/resume
> ends up doing for all but the boot CPU. But the boot CPU is not
> hotplugged.
>
> Using CPU_UP notifiers is wrong, and they get called too late anyway.
>
> The code should use a real resume method. Or, better yet, just do it
> right, and do it from __restore_processor_state().
>
> Those f*cking CPU notifiers are a pain in the ass, and the tend to be
> invariably broken, and they have their own idiotic hacks that are
> equally broken (ie that x86_pmu_notifier() thing seems to make up its
> own suspend/resume with
> "x86_pmu.cpu_prepare/cpu_starting/cpu_dying/cpu_dead" things.
>
> I guess we could make the BP do a fake cpu notifier thing around the
> suspend of the boot processor as well, but most of the per-CPU stuff
> seems to be perfectly fine without it (ie mtrr, apic, etc etc all use
> the suspend/resume infrastructure) and doesn't need that kind of
> stuff.
>
>                 Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-15  0:24                 ` Stephane Eranian
@ 2013-03-15  1:06                   ` Linus Torvalds
  2013-03-15  8:01                     ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-03-15  1:06 UTC (permalink / raw)
  To: Stephane Eranian
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 5:24 PM, Stephane Eranian <eranian@google.com> wrote:
>
> I bet if you force the affinity of your perf record to be on
> a CPU other than CPU0, you will not get the crash.
>
> This is what I am seeing now. I appears on resume,
> CPU0 hotplug callbacks for perf_events are not invoked
> leaving DS_AREA MSR to 0.
>
> Can you confirm on your machine?

I'm not even going to bother confirming it, because I think you're
right, and I think the reason is clear: the DS initialization code
uses the CPU_UP notifiers.

And that's sufficient for CPU hotplug, which is what suspend/resume
ends up doing for all but the boot CPU. But the boot CPU is not
hotplugged.

Using CPU_UP notifiers is wrong, and they get called too late anyway.

The code should use a real resume method. Or, better yet, just do it
right, and do it from __restore_processor_state().

Those f*cking CPU notifiers are a pain in the ass, and the tend to be
invariably broken, and they have their own idiotic hacks that are
equally broken (ie that x86_pmu_notifier() thing seems to make up its
own suspend/resume with
"x86_pmu.cpu_prepare/cpu_starting/cpu_dying/cpu_dead" things.

I guess we could make the BP do a fake cpu notifier thing around the
suspend of the boot processor as well, but most of the per-CPU stuff
seems to be perfectly fine without it (ie mtrr, apic, etc etc all use
the suspend/resume infrastructure) and doesn't need that kind of
stuff.

                Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 23:11               ` Stephane Eranian
@ 2013-03-15  0:24                 ` Stephane Eranian
  2013-03-15  1:06                   ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-15  0:24 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

Linus,

I bet if you force the affinity of your perf record to be on
a CPU other than CPU0, you will not get the crash.

This is what I am seeing now. I appears on resume,
CPU0 hotplug callbacks for perf_events are not invoked
leaving DS_AREA MSR to 0.

Can you confirm on your machine?



On Fri, Mar 15, 2013 at 12:11 AM, Stephane Eranian <eranian@google.com> wrote:
> On Thu, Mar 14, 2013 at 11:53 PM, Stephane Eranian <eranian@google.com> wrote:
>> On Thu, Mar 14, 2013 at 11:42 PM, Stephane Eranian <eranian@google.com> wrote:
>>> On Thu, Mar 14, 2013 at 11:19 PM, Stephane Eranian <eranian@google.com> wrote:
>>>> On Thu, Mar 14, 2013 at 11:17 PM, Linus Torvalds
>>>> <torvalds@linux-foundation.org> wrote:
>>>>> On Thu, Mar 14, 2013 at 3:09 PM, Stephane Eranian <eranian@google.com> wrote:
>>>>>>
>>>>>> Could be related to suspend/resume. But were you running perf across
>>>>>> that resume/suspend cycle?
>>>>>
>>>>> No.
>>>>>
>>>>> In most cases I was running a perf record before and after (but not
>>>>> *while* suspending)
>>>>>
>>>>> In at least one other crash, I didn't run perf before at all, so the
>>>>> first time I used perf was after the resume.
>>>>>
>>>>> So in no cases did I actually have any perf stuff active over the
>>>>> suspend itself.
>>>>>
>>>> Ok, simpler test case then.
>>>>
>>>>>> Let's see if we can reproduce the problem on the same ChromeBook you
>>>>>> have. Don't have one myself.
>>>>>
>>>>> I don't imagine it should be about chromebook per se, because afaik
>>>>> all of pmu suspend/resume is done by the kernel, no firmware involved.
>>>>>
>>>>> So I'd assume it should happen with any IvyBridge.
>>>>>
>>>> Will try on a desktop IvyBridge too.
>>>
>>> Ok, it happens on my IVB desktop too, so I can investigate...
>>
>> It's not specific to IVB either, it hangs on my Nehalem desktop as well.
>
> Looks related to PEBS. If I drop the :pp the machine does not hang. Even
> a single :p hangs it. So it is possible something is not properly
> restored in the
> DS state after a resume or is corrupted by the suspend.

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 22:53             ` Stephane Eranian
@ 2013-03-14 23:11               ` Stephane Eranian
  2013-03-15  0:24                 ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-14 23:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 11:53 PM, Stephane Eranian <eranian@google.com> wrote:
> On Thu, Mar 14, 2013 at 11:42 PM, Stephane Eranian <eranian@google.com> wrote:
>> On Thu, Mar 14, 2013 at 11:19 PM, Stephane Eranian <eranian@google.com> wrote:
>>> On Thu, Mar 14, 2013 at 11:17 PM, Linus Torvalds
>>> <torvalds@linux-foundation.org> wrote:
>>>> On Thu, Mar 14, 2013 at 3:09 PM, Stephane Eranian <eranian@google.com> wrote:
>>>>>
>>>>> Could be related to suspend/resume. But were you running perf across
>>>>> that resume/suspend cycle?
>>>>
>>>> No.
>>>>
>>>> In most cases I was running a perf record before and after (but not
>>>> *while* suspending)
>>>>
>>>> In at least one other crash, I didn't run perf before at all, so the
>>>> first time I used perf was after the resume.
>>>>
>>>> So in no cases did I actually have any perf stuff active over the
>>>> suspend itself.
>>>>
>>> Ok, simpler test case then.
>>>
>>>>> Let's see if we can reproduce the problem on the same ChromeBook you
>>>>> have. Don't have one myself.
>>>>
>>>> I don't imagine it should be about chromebook per se, because afaik
>>>> all of pmu suspend/resume is done by the kernel, no firmware involved.
>>>>
>>>> So I'd assume it should happen with any IvyBridge.
>>>>
>>> Will try on a desktop IvyBridge too.
>>
>> Ok, it happens on my IVB desktop too, so I can investigate...
>
> It's not specific to IVB either, it hangs on my Nehalem desktop as well.

Looks related to PEBS. If I drop the :pp the machine does not hang. Even
a single :p hangs it. So it is possible something is not properly
restored in the
DS state after a resume or is corrupted by the suspend.

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 22:42           ` Stephane Eranian
@ 2013-03-14 22:53             ` Stephane Eranian
  2013-03-14 23:11               ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-14 22:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 11:42 PM, Stephane Eranian <eranian@google.com> wrote:
> On Thu, Mar 14, 2013 at 11:19 PM, Stephane Eranian <eranian@google.com> wrote:
>> On Thu, Mar 14, 2013 at 11:17 PM, Linus Torvalds
>> <torvalds@linux-foundation.org> wrote:
>>> On Thu, Mar 14, 2013 at 3:09 PM, Stephane Eranian <eranian@google.com> wrote:
>>>>
>>>> Could be related to suspend/resume. But were you running perf across
>>>> that resume/suspend cycle?
>>>
>>> No.
>>>
>>> In most cases I was running a perf record before and after (but not
>>> *while* suspending)
>>>
>>> In at least one other crash, I didn't run perf before at all, so the
>>> first time I used perf was after the resume.
>>>
>>> So in no cases did I actually have any perf stuff active over the
>>> suspend itself.
>>>
>> Ok, simpler test case then.
>>
>>>> Let's see if we can reproduce the problem on the same ChromeBook you
>>>> have. Don't have one myself.
>>>
>>> I don't imagine it should be about chromebook per se, because afaik
>>> all of pmu suspend/resume is done by the kernel, no firmware involved.
>>>
>>> So I'd assume it should happen with any IvyBridge.
>>>
>> Will try on a desktop IvyBridge too.
>
> Ok, it happens on my IVB desktop too, so I can investigate...

It's not specific to IVB either, it hangs on my Nehalem desktop as well.

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 22:19         ` Stephane Eranian
@ 2013-03-14 22:42           ` Stephane Eranian
  2013-03-14 22:53             ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-14 22:42 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 11:19 PM, Stephane Eranian <eranian@google.com> wrote:
> On Thu, Mar 14, 2013 at 11:17 PM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
>> On Thu, Mar 14, 2013 at 3:09 PM, Stephane Eranian <eranian@google.com> wrote:
>>>
>>> Could be related to suspend/resume. But were you running perf across
>>> that resume/suspend cycle?
>>
>> No.
>>
>> In most cases I was running a perf record before and after (but not
>> *while* suspending)
>>
>> In at least one other crash, I didn't run perf before at all, so the
>> first time I used perf was after the resume.
>>
>> So in no cases did I actually have any perf stuff active over the
>> suspend itself.
>>
> Ok, simpler test case then.
>
>>> Let's see if we can reproduce the problem on the same ChromeBook you
>>> have. Don't have one myself.
>>
>> I don't imagine it should be about chromebook per se, because afaik
>> all of pmu suspend/resume is done by the kernel, no firmware involved.
>>
>> So I'd assume it should happen with any IvyBridge.
>>
> Will try on a desktop IvyBridge too.

Ok, it happens on my IVB desktop too, so I can investigate...

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 22:17       ` Linus Torvalds
@ 2013-03-14 22:19         ` Stephane Eranian
  2013-03-14 22:42           ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-14 22:19 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 11:17 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
> On Thu, Mar 14, 2013 at 3:09 PM, Stephane Eranian <eranian@google.com> wrote:
>>
>> Could be related to suspend/resume. But were you running perf across
>> that resume/suspend cycle?
>
> No.
>
> In most cases I was running a perf record before and after (but not
> *while* suspending)
>
> In at least one other crash, I didn't run perf before at all, so the
> first time I used perf was after the resume.
>
> So in no cases did I actually have any perf stuff active over the
> suspend itself.
>
Ok, simpler test case then.

>> Let's see if we can reproduce the problem on the same ChromeBook you
>> have. Don't have one myself.
>
> I don't imagine it should be about chromebook per se, because afaik
> all of pmu suspend/resume is done by the kernel, no firmware involved.
>
> So I'd assume it should happen with any IvyBridge.
>
Will try on a desktop IvyBridge too.

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 22:09     ` Stephane Eranian
@ 2013-03-14 22:17       ` Linus Torvalds
  2013-03-14 22:19         ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-03-14 22:17 UTC (permalink / raw)
  To: Stephane Eranian
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 3:09 PM, Stephane Eranian <eranian@google.com> wrote:
>
> Could be related to suspend/resume. But were you running perf across
> that resume/suspend cycle?

No.

In most cases I was running a perf record before and after (but not
*while* suspending)

In at least one other crash, I didn't run perf before at all, so the
first time I used perf was after the resume.

So in no cases did I actually have any perf stuff active over the
suspend itself.

> Let's see if we can reproduce the problem on the same ChromeBook you
> have. Don't have one myself.

I don't imagine it should be about chromebook per se, because afaik
all of pmu suspend/resume is done by the kernel, no firmware involved.

So I'd assume it should happen with any IvyBridge.

            Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 21:06   ` Linus Torvalds
@ 2013-03-14 22:09     ` Stephane Eranian
  2013-03-14 22:17       ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Stephane Eranian @ 2013-03-14 22:09 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton, Linux Kernel Mailing List

Hi,


On Thu, Mar 14, 2013 at 10:06 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> On Thu, Mar 14, 2013 at 1:32 PM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
> >
> > And to make things interesting, I seem to be able to only reproduce
> > this *after* a suspend cycle. That may be just happenstance, since it
> > seemed to be hard to replicate and most of the time it has happened
> > under X with no messages visible at all, but that *seems* to be the
> > pattern.
> >
> > And the one time I got it to happen on the text console, things
> > scrolled off (watchdog warnings due to lockups), but I did get a NULL
> > pointer dereference in intel_pmu_enable_all().
> >
> > I'll try to reproduce it and get a picture,
>
> Theory more or less confirmed.
>
> It does need a suspend/resume cycle, and I have a picture. The oops
> happens immediately when trying to do any perf work after the first
> suspend, before suspending I seem to be able to reliably use perf. It
> could still be just random flakiness, but I don't think so.
>
Could be related to suspend/resume. But were you running perf across
that resume/suspend cycle?



But still don't see how a wrmsrl could corrupt a cpuc.


>
> The NULL pointer dereference is at intel_pmu_enable_all+0x4d/0xa0 for
> me, which seems to be the load of the
>
>     if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
>
> thing. It says
>
>    BUG: unable to handle NULL pointer dereference at 0000000000000028
>
> But that error makes no sense. The code at that EIP is
>
>   48 8b 83 00 02 00 00 mov    0x200(%rbx),%rax     <-- trapping instruction
>
> and the value printed out for %rbx is 0xffff80014f20b8e0, so it should
> *not* be a NULL pointer dereference (and "cpuc" was also used just
> before the wrmsrl).


>
> So I suspect that the "wrmsrl" that was just before that instruction
> does something odd, and the PMU is in some odd state, so that the NULL
> pointer dereference actually has something to do with *that*, rather
> than the instruction itself.
>
> The callchain looks normal. It's
>
>   finish_task_switch ->
>     __perf_event_task_sched_in ->
>       perf_event_context_sched_in ->
>         perf_pmu_enable ->
>           x86_pmu_enable ->
>             intel_pmu_enable_all()
>
> The immediately preceding wrmsrl was done with rax=0xf, rdx=0x7,
> rcx=0x38f according to the register dump (but the picture isn't great,
> so the numbers aren't 100% reliable).
>
Value 0x38f for GLOBAL_CTRL is valid. And 0x70000000f is valid too
for the counter bitmask (4 generic counters + 3 fixed counters).

Let's see if we can reproduce the problem on the same ChromeBook you
have. Don't have one myself.

> Does this give any clues?
>
>              Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-03-14 20:32 ` Linus Torvalds
@ 2013-03-14 21:06   ` Linus Torvalds
  2013-03-14 22:09     ` Stephane Eranian
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-03-14 21:06 UTC (permalink / raw)
  To: Ingo Molnar, Stephane Eranian
  Cc: Arnaldo Carvalho de Melo, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton, Linux Kernel Mailing List

On Thu, Mar 14, 2013 at 1:32 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> And to make things interesting, I seem to be able to only reproduce
> this *after* a suspend cycle. That may be just happenstance, since it
> seemed to be hard to replicate and most of the time it has happened
> under X with no messages visible at all, but that *seems* to be the
> pattern.
>
> And the one time I got it to happen on the text console, things
> scrolled off (watchdog warnings due to lockups), but I did get a NULL
> pointer dereference in intel_pmu_enable_all().
>
> I'll try to reproduce it and get a picture,

Theory more or less confirmed.

It does need a suspend/resume cycle, and I have a picture. The oops
happens immediately when trying to do any perf work after the first
suspend, before suspending I seem to be able to reliably use perf. It
could still be just random flakiness, but I don't think so.

The NULL pointer dereference is at intel_pmu_enable_all+0x4d/0xa0 for
me, which seems to be the load of the

    if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))

thing. It says

   BUG: unable to handle NULL pointer dereference at 0000000000000028

But that error makes no sense. The code at that EIP is

  48 8b 83 00 02 00 00 mov    0x200(%rbx),%rax     <-- trapping instruction

and the value printed out for %rbx is 0xffff80014f20b8e0, so it should
*not* be a NULL pointer dereference (and "cpuc" was also used just
before the wrmsrl).

So I suspect that the "wrmsrl" that was just before that instruction
does something odd, and the PMU is in some odd state, so that the NULL
pointer dereference actually has something to do with *that*, rather
than the instruction itself.

The callchain looks normal. It's

  finish_task_switch ->
    __perf_event_task_sched_in ->
      perf_event_context_sched_in ->
        perf_pmu_enable ->
          x86_pmu_enable ->
            intel_pmu_enable_all()

The immediately preceding wrmsrl was done with rax=0xf, rdx=0x7,
rcx=0x38f according to the register dump (but the picture isn't great,
so the numbers aren't 100% reliable).

Does this give any clues?

             Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2013-02-26  7:02 Ingo Molnar
@ 2013-03-14 20:32 ` Linus Torvalds
  2013-03-14 21:06   ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2013-03-14 20:32 UTC (permalink / raw)
  To: Ingo Molnar, Stephane Eranian
  Cc: Arnaldo Carvalho de Melo, Peter Zijlstra, Thomas Gleixner,
	Andrew Morton, Linux Kernel Mailing List

On Mon, Feb 25, 2013 at 11:02 PM, Ingo Molnar <mingo@kernel.org> wrote:
>
> Stephane Eranian (1):
>       perf/x86: Add Intel IvyBridge event scheduling constraints

So thanks to my new Chromebook, I'm trying to do perf stuff on
IvyBridge. I was hoping the whole exact cycle counting would work
better, since the last machine it was reliable for me was my old
Westmere desktop, and my previous laptop (Sandybridge MacBook Air)
didn't work very well due to CPU errata.

Sadly, my new Ivybridge laptop doesn't seem to do very well either,
but I suspect it's the kernel, not the hardware this time. A simple

    perf record -f -e cycles:pp make -j

in the kernel directory (fully built kernel, so the load doesn't
actually go crazy despite the "-j") will *sometimes* totally hang the
machine with current git.

I get a NULL pointer dereference in intel_pmu_enable_all, so I don't
think it's a hardware bug.

And to make things interesting, I seem to be able to only reproduce
this *after* a suspend cycle. That may be just happenstance, since it
seemed to be hard to replicate and most of the time it has happened
under X with no messages visible at all, but that *seems* to be the
pattern.

And the one time I got it to happen on the text console, things
scrolled off (watchdog warnings due to lockups), but I did get a NULL
pointer dereference in intel_pmu_enable_all().

I'll try to reproduce it and get a picture, but thought I'd send out
the email with just this, since maybe the "suspend cycle" plus "NULL
pointer in intel_pmu_enable_all()" makes somebody go "Duh!", or at
least replicate it...

                  Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-03-11 14:28 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-03-11 14:28 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: cb16b91a449afd01b85ec4e59f30449d11c4acd7 s390: Fix a header dependencies related build error

Misc minor fixes mostly related to tracing.

 Thanks,

	Ingo

------------------>
Hiraku Toyooka (1):
      tracing: update documentation of snapshot utility

Li Zefan (1):
      s390: Fix a header dependencies related build error

Steven Rostedt (1):
      ftrace: Update the kconfig for DYNAMIC_FTRACE

Steven Rostedt (Red Hat) (2):
      tracing: Add help of snapshot feature when snapshot is empty
      tracing: Do not return EINVAL in snapshot when not allocated


 Documentation/trace/ftrace.txt |  2 +-
 arch/s390/include/asm/cpu_mf.h |  1 +
 kernel/trace/Kconfig           | 24 ++++++++++++++----------
 kernel/trace/trace.c           | 27 ++++++++++++++++++++++++---
 4 files changed, 40 insertions(+), 14 deletions(-)

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 53d6a3c..a372304 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1873,7 +1873,7 @@ feature:
 
 	status\input  |     0      |     1      |    else    |
 	--------------+------------+------------+------------+
-	not allocated |(do nothing)| alloc+swap |   EINVAL   |
+	not allocated |(do nothing)| alloc+swap |(do nothing)|
 	--------------+------------+------------+------------+
 	allocated     |    free    |    swap    |   clear    |
 	--------------+------------+------------+------------+
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 35f0020..c7c9bf6 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -12,6 +12,7 @@
 #ifndef _ASM_S390_CPU_MF_H
 #define _ASM_S390_CPU_MF_H
 
+#include <linux/errno.h>
 #include <asm/facility.h>
 
 #define CPU_MF_INT_SF_IAE	(1 << 31)	/* invalid entry address */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 3656756..b516a8e 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,24 +429,28 @@ config PROBE_EVENTS
 	def_bool n
 
 config DYNAMIC_FTRACE
-	bool "enable/disable ftrace tracepoints dynamically"
+	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
 	default y
 	help
-          This option will modify all the calls to ftrace dynamically
-	  (will patch them out of the binary image and replace them
-	  with a No-Op instruction) as they are called. A table is
-	  created to dynamically enable them again.
+	  This option will modify all the calls to function tracing
+	  dynamically (will patch them out of the binary image and
+	  replace them with a No-Op instruction) on boot up. During
+	  compile time, a table is made of all the locations that ftrace
+	  can function trace, and this table is linked into the kernel
+	  image. When this is enabled, functions can be individually
+	  enabled, and the functions not enabled will not affect
+	  performance of the system.
+
+	  See the files in /sys/kernel/debug/tracing:
+	    available_filter_functions
+	    set_ftrace_filter
+	    set_ftrace_notrace
 
 	  This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
 	  otherwise has native performance as long as no tracing is active.
 
-	  The changes to the code are done by a kernel thread that
-	  wakes up once a second and checks to see if any ftrace calls
-	  were made. If so, it runs stop_machine (stops all CPUS)
-	  and modifies the code to jump over the call to ftrace.
-
 config DYNAMIC_FTRACE_WITH_REGS
 	def_bool y
 	depends on DYNAMIC_FTRACE
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c2e2c23..1f835a8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2400,6 +2400,27 @@ static void test_ftrace_alive(struct seq_file *m)
 	seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
 }
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
+{
+	if (iter->trace->allocated_snapshot)
+		seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
+	else
+		seq_printf(m, "#\n# * Snapshot is freed *\n#\n");
+
+	seq_printf(m, "# Snapshot commands:\n");
+	seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
+	seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
+	seq_printf(m, "#                      Takes a snapshot of the main buffer.\n");
+	seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
+	seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
+	seq_printf(m, "#                       is not a '0' or '1')\n");
+}
+#else
+/* Should never be called */
+static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { }
+#endif
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2411,7 +2432,9 @@ static int s_show(struct seq_file *m, void *v)
 			seq_puts(m, "#\n");
 			test_ftrace_alive(m);
 		}
-		if (iter->trace && iter->trace->print_header)
+		if (iter->snapshot && trace_empty(iter))
+			print_snapshot_help(m, iter);
+		else if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
 		else
 			trace_default_header(m);
@@ -4144,8 +4167,6 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	default:
 		if (current_trace->allocated_snapshot)
 			tracing_reset_online_cpus(&max_tr);
-		else
-			ret = -EINVAL;
 		break;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-02-26  7:02 Ingo Molnar
  2013-03-14 20:32 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2013-02-26  7:02 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: ff1fb5f6b4925a536ffb8171e5f2dbd01ccfeb97 Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent

 Thanks,

	Ingo

------------------>
Stephane Eranian (1):
      perf/x86: Add Intel IvyBridge event scheduling constraints

Steven Rostedt (1):
      tracing/syscalls: Allow archs to ignore tracing compat syscalls

Steven Rostedt (Red Hat) (1):
      ftrace: Call ftrace cleanup module notifier after all other notifiers


 arch/x86/include/asm/ftrace.h          | 24 ++++++++++++++++++
 arch/x86/include/asm/thread_info.h     |  1 -
 arch/x86/kernel/cpu/perf_event_intel.c | 23 ++++++++++++++++-
 kernel/trace/ftrace.c                  | 46 +++++++++++++++++++++++-----------
 kernel/trace/trace_syscalls.c          | 43 +++++++++++++++++++++++++++----
 5 files changed, 116 insertions(+), 21 deletions(-)

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 86cb51e..0525a8b 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -72,4 +72,28 @@ int ftrace_int3_handler(struct pt_regs *regs);
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+
+#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
+#include <asm/compat.h>
+
+/*
+ * Because ia32 syscalls do not map to x86_64 syscall numbers
+ * this screws up the trace output when tracing a ia32 task.
+ * Instead of reporting bogus syscalls, just do not trace them.
+ *
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+	if (is_compat_task())
+		return true;
+	return false;
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
+#endif /* !__ASSEMBLY__  && !COMPILE_OFFSETS */
+
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2d946e6..2cd056e 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -20,7 +20,6 @@
 struct task_struct;
 struct exec_domain;
 #include <asm/processor.h>
-#include <asm/ftrace.h>
 #include <linux/atomic.h>
 
 struct thread_info {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 4914e94..529c893 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -107,6 +107,27 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
+{
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
+	INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
+	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /*  MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+	EVENT_CONSTRAINT_END
+};
+
 static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
@@ -2095,7 +2116,7 @@ __init int intel_pmu_init(void)
 
 		intel_pmu_lbr_init_snb();
 
-		x86_pmu.event_constraints = intel_snb_event_constraints;
+		x86_pmu.event_constraints = intel_ivb_event_constraints;
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
 		x86_pmu.extra_regs = intel_snb_extra_regs;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ce8c3d6..98ca94a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3996,37 +3996,51 @@ static void ftrace_init_module(struct module *mod,
 	ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
+static int ftrace_module_notify_enter(struct notifier_block *self,
+				      unsigned long val, void *data)
 {
 	struct module *mod = data;
 
-	switch (val) {
-	case MODULE_STATE_COMING:
+	if (val == MODULE_STATE_COMING)
 		ftrace_init_module(mod, mod->ftrace_callsites,
 				   mod->ftrace_callsites +
 				   mod->num_ftrace_callsites);
-		break;
-	case MODULE_STATE_GOING:
+	return 0;
+}
+
+static int ftrace_module_notify_exit(struct notifier_block *self,
+				     unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	if (val == MODULE_STATE_GOING)
 		ftrace_release_mod(mod);
-		break;
-	}
 
 	return 0;
 }
 #else
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
+static int ftrace_module_notify_enter(struct notifier_block *self,
+				      unsigned long val, void *data)
+{
+	return 0;
+}
+static int ftrace_module_notify_exit(struct notifier_block *self,
+				     unsigned long val, void *data)
 {
 	return 0;
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_nb = {
-	.notifier_call = ftrace_module_notify,
+struct notifier_block ftrace_module_enter_nb = {
+	.notifier_call = ftrace_module_notify_enter,
 	.priority = INT_MAX,	/* Run before anything that can use kprobes */
 };
 
+struct notifier_block ftrace_module_exit_nb = {
+	.notifier_call = ftrace_module_notify_exit,
+	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
+};
+
 extern unsigned long __start_mcount_loc[];
 extern unsigned long __stop_mcount_loc[];
 
@@ -4058,9 +4072,13 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_nb);
+	ret = register_module_notifier(&ftrace_module_enter_nb);
+	if (ret)
+		pr_warning("Failed to register trace ftrace module enter notifier\n");
+
+	ret = register_module_notifier(&ftrace_module_exit_nb);
 	if (ret)
-		pr_warning("Failed to register trace ftrace module notifier\n");
+		pr_warning("Failed to register trace ftrace module exit notifier\n");
 
 	set_ftrace_early_filters();
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5329e13e..7a809e3 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
 #include <trace/syscall.h>
 #include <trace/events/syscalls.h>
+#include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>	/* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
@@ -47,6 +48,38 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 }
 #endif
 
+#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+/*
+ * Some architectures that allow for 32bit applications
+ * to run on a 64bit kernel, do not map the syscalls for
+ * the 32bit tasks the same as they do for 64bit tasks.
+ *
+ *     *cough*x86*cough*
+ *
+ * In such a case, instead of reporting the wrong syscalls,
+ * simply ignore them.
+ *
+ * For an arch to ignore the compat syscalls it needs to
+ * define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as
+ * define the function arch_trace_is_compat_syscall() to let
+ * the tracing system know that it should ignore it.
+ */
+static int
+trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	if (unlikely(arch_trace_is_compat_syscall(regs)))
+		return -1;
+
+	return syscall_get_nr(task, regs);
+}
+#else
+static inline int
+trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	return syscall_get_nr(task, regs);
+}
+#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */
+
 static __init struct syscall_metadata *
 find_syscall_meta(unsigned long syscall)
 {
@@ -276,10 +309,10 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	int size;
 	int syscall_nr;
+	int size;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_enter_syscalls))
@@ -313,7 +346,7 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	struct ring_buffer *buffer;
 	int syscall_nr;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_exit_syscalls))
@@ -502,7 +535,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int rctx;
 	int size;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
@@ -578,7 +611,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int rctx;
 	int size;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2013-02-04 18:20 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2013-02-04 18:20 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 0231bb5336758426b44ccd798ccd3c5419c95d58 perf: Fix event group context move

Three fixlets and two small (and low risk) hw-enablement 
changes.

 Thanks,

	Ingo

------------------>
Andrew Morton (1):
      arch/x86/tools/insn_sanity.c: Identify source of messages

Jiri Olsa (1):
      perf: Fix event group context move

ShuoX Liu (1):
      perf/x86: Enable Intel Lincroft/Penwell/Cloverview Atom support

Youquan Song (1):
      x86/perf: Add IvyBridge EP support

yangyongqiang (1):
      perf/x86: Fix P6 driver section warning


 arch/x86/kernel/cpu/perf_event_intel.c |  6 +++++-
 arch/x86/kernel/cpu/perf_event_p6.c    |  2 +-
 arch/x86/tools/insn_sanity.c           | 10 ++++++++--
 kernel/events/core.c                   | 20 ++++++++++++++++++--
 4 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 93b9e11..4914e94 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2019,7 +2019,10 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 28: /* Atom */
-	case 54: /* Cedariew */
+	case 38: /* Lincroft */
+	case 39: /* Penwell */
+	case 53: /* Cloverview */
+	case 54: /* Cedarview */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2084,6 +2087,7 @@ __init int intel_pmu_init(void)
 		pr_cont("SandyBridge events, ");
 		break;
 	case 58: /* IvyBridge */
+	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index f2af39f..4820c23 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -19,7 +19,7 @@ static const u64 p6_perfmon_event_map[] =
 
 };
 
-static __initconst u64 p6_hw_cache_event_ids
+static u64 p6_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index cc2f8c1..872eb60 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -55,7 +55,7 @@ static FILE		*input_file;	/* Input file name */
 static void usage(const char *err)
 {
 	if (err)
-		fprintf(stderr, "Error: %s\n\n", err);
+		fprintf(stderr, "%s: Error: %s\n\n", prog, err);
 	fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog);
 	fprintf(stderr, "\t-y	64bit mode\n");
 	fprintf(stderr, "\t-n	32bit mode\n");
@@ -269,7 +269,13 @@ int main(int argc, char **argv)
 		insns++;
 	}
 
-	fprintf(stdout, "%s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", (errors) ? "Failure" : "Success", insns, (input_file) ? "given" : "random", errors, seed);
+	fprintf(stdout, "%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
+		prog,
+		(errors) ? "Failure" : "Success",
+		insns,
+		(input_file) ? "given" : "random",
+		errors,
+		seed);
 
 	return errors ? 1 : 0;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 301079d..7b6646a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -908,6 +908,15 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 }
 
 /*
+ * Initialize event state based on the perf_event_attr::disabled.
+ */
+static inline void perf_event__state_init(struct perf_event *event)
+{
+	event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF :
+					      PERF_EVENT_STATE_INACTIVE;
+}
+
+/*
  * Called at perf_event creation and when events are attached/detached from a
  * group.
  */
@@ -6179,8 +6188,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	event->overflow_handler	= overflow_handler;
 	event->overflow_handler_context = context;
 
-	if (attr->disabled)
-		event->state = PERF_EVENT_STATE_OFF;
+	perf_event__state_init(event);
 
 	pmu = NULL;
 
@@ -6609,9 +6617,17 @@ SYSCALL_DEFINE5(perf_event_open,
 
 		mutex_lock(&gctx->mutex);
 		perf_remove_from_context(group_leader);
+
+		/*
+		 * Removing from the context ends up with disabled
+		 * event. What we want here is event in the initial
+		 * startup state, ready to be add into new context.
+		 */
+		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
 			perf_remove_from_context(sibling);
+			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-12-01 11:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-12-01 11:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: fd6da696f38b00ffeae1185d6f0ec5d4ab3b472d Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

This is mostly about unbreaking architectures that took the UAPI 
changes in the v3.7 cycle, plus misc fixes.

 Thanks,

	Ingo

------------------>
David Howells (5):
      x86: Export asm/{svm.h,vmx.h,perf_regs.h}
      tools: Define a Makefile function to do subdir processing
      tools: Honour the O= flag when tool build called from a higher Makefile
      tools: Pass the target in descend
      perf: Make perf build for x86 with UAPI disintegration applied

Michael Neuling (1):
      perf, powerpc: Fix hw breakpoints returning -ENOSPC

Namhyung Kim (2):
      perf header: Fix numa topology printing
      perf tools: Fix strbuf_addf() when the buffer needs to grow

Sukadev Bhattiprolu (1):
      perf powerpc: Use uapi/unistd.h to fix build error

Xiao Guangrong (2):
      perf kvm: Rename perf_kvm to perf_kvm_stat
      perf kvm: Fix building perf kvm on non x86 arches


 Makefile                                |   6 +-
 arch/x86/include/asm/Kbuild             |   3 +
 include/linux/hw_breakpoint.h           |  31 +-------
 include/uapi/linux/Kbuild               |   1 +
 include/uapi/linux/hw_breakpoint.h      |  30 ++++++++
 kernel/events/hw_breakpoint.c           |  12 ++--
 tools/Makefile                          |  24 +++----
 tools/perf/Makefile                     |  29 +++++++-
 tools/perf/arch/x86/include/perf_regs.h |   2 +-
 tools/perf/builtin-kvm.c                | 121 ++++++++++++++++++--------------
 tools/perf/builtin-test.c               |   2 +-
 tools/perf/perf.h                       |  16 +----
 tools/perf/util/evsel.c                 |   4 +-
 tools/perf/util/evsel.h                 |   3 +-
 tools/perf/util/header.c                |   2 +
 tools/perf/util/header.h                |   2 +-
 tools/perf/util/parse-events-test.c     |   2 +-
 tools/perf/util/parse-events.c          |   2 +-
 tools/perf/util/parse-events.h          |   2 +-
 tools/perf/util/pmu.h                   |   2 +-
 tools/perf/util/session.h               |   2 +-
 tools/perf/util/strbuf.c                |   8 +--
 tools/scripts/Makefile.include          |  23 +++++-
 23 files changed, 194 insertions(+), 135 deletions(-)
 create mode 100644 include/uapi/linux/hw_breakpoint.h

diff --git a/Makefile b/Makefile
index 42d0e56..71dc31e 100644
--- a/Makefile
+++ b/Makefile
@@ -1321,10 +1321,12 @@ kernelversion:
 
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= -C $(src)/tools/
+	$(Q)mkdir -p $(objtree)/tools
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= O=$(objtree) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= -C $(src)/tools/ $*
+	$(Q)mkdir -p $(objtree)/tools
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= O=$(objtree) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 66e5f0e..79fd8a3 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += mce.h
 header-y += msr-index.h
 header-y += msr.h
 header-y += mtrr.h
+header-y += perf_regs.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
 header-y += posix_types_x32.h
@@ -19,8 +20,10 @@ header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
 header-y += sigcontext32.h
+header-y += svm.h
 header-y += ucontext.h
 header-y += vm86.h
+header-y += vmx.h
 header-y += vsyscall.h
 
 genhdr-y += unistd_32.h
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 6ae9c63..0464c85 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -1,35 +1,8 @@
 #ifndef _LINUX_HW_BREAKPOINT_H
 #define _LINUX_HW_BREAKPOINT_H
 
-enum {
-	HW_BREAKPOINT_LEN_1 = 1,
-	HW_BREAKPOINT_LEN_2 = 2,
-	HW_BREAKPOINT_LEN_4 = 4,
-	HW_BREAKPOINT_LEN_8 = 8,
-};
-
-enum {
-	HW_BREAKPOINT_EMPTY	= 0,
-	HW_BREAKPOINT_R		= 1,
-	HW_BREAKPOINT_W		= 2,
-	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
-	HW_BREAKPOINT_X		= 4,
-	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
-};
-
-enum bp_type_idx {
-	TYPE_INST 	= 0,
-#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
-	TYPE_DATA	= 0,
-#else
-	TYPE_DATA	= 1,
-#endif
-	TYPE_MAX
-};
-
-#ifdef __KERNEL__
-
 #include <linux/perf_event.h>
+#include <uapi/linux/hw_breakpoint.h>
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 
@@ -151,6 +124,4 @@ static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
 }
 
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#endif /* __KERNEL__ */
-
 #endif /* _LINUX_HW_BREAKPOINT_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index e194387..19e765f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -415,3 +415,4 @@ header-y += wireless.h
 header-y += x25.h
 header-y += xattr.h
 header-y += xfrm.h
+header-y += hw_breakpoint.h
diff --git a/include/uapi/linux/hw_breakpoint.h b/include/uapi/linux/hw_breakpoint.h
new file mode 100644
index 0000000..b04000a
--- /dev/null
+++ b/include/uapi/linux/hw_breakpoint.h
@@ -0,0 +1,30 @@
+#ifndef _UAPI_LINUX_HW_BREAKPOINT_H
+#define _UAPI_LINUX_HW_BREAKPOINT_H
+
+enum {
+	HW_BREAKPOINT_LEN_1 = 1,
+	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
+};
+
+#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 9a7b487..fe8a916 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -111,14 +111,16 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
  * Count the number of breakpoints of the same type and same task.
  * The given event must be not on the list.
  */
-static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
+static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
 {
 	struct task_struct *tsk = bp->hw.bp_target;
 	struct perf_event *iter;
 	int count = 0;
 
 	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
-		if (iter->hw.bp_target == tsk && find_slot_idx(iter) == type)
+		if (iter->hw.bp_target == tsk &&
+		    find_slot_idx(iter) == type &&
+		    cpu == iter->cpu)
 			count += hw_breakpoint_weight(iter);
 	}
 
@@ -141,7 +143,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		if (!tsk)
 			slots->pinned += max_task_bp_pinned(cpu, type);
 		else
-			slots->pinned += task_bp_pinned(bp, type);
+			slots->pinned += task_bp_pinned(cpu, bp, type);
 		slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
 
 		return;
@@ -154,7 +156,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		if (!tsk)
 			nr += max_task_bp_pinned(cpu, type);
 		else
-			nr += task_bp_pinned(bp, type);
+			nr += task_bp_pinned(cpu, bp, type);
 
 		if (nr > slots->pinned)
 			slots->pinned = nr;
@@ -188,7 +190,7 @@ static void toggle_bp_task_slot(struct perf_event *bp, int cpu, bool enable,
 	int old_idx = 0;
 	int idx = 0;
 
-	old_count = task_bp_pinned(bp, type);
+	old_count = task_bp_pinned(cpu, bp, type);
 	old_idx = old_count - 1;
 	idx = old_idx + weight;
 
diff --git a/tools/Makefile b/tools/Makefile
index 3ae4394..1f9a529 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -31,44 +31,44 @@ help:
 	@echo '  clean: a summary clean target to clean _all_ folders'
 
 cpupower: FORCE
-	$(QUIET_SUBDIR0)power/$@/ $(QUIET_SUBDIR1)
+	$(call descend,power/$@)
 
 firewire lguest perf usb virtio vm: FORCE
-	$(QUIET_SUBDIR0)$@/ $(QUIET_SUBDIR1)
+	$(call descend,$@)
 
 selftests: FORCE
-	$(QUIET_SUBDIR0)testing/$@/ $(QUIET_SUBDIR1)
+	$(call descend,testing/$@)
 
 turbostat x86_energy_perf_policy: FORCE
-	$(QUIET_SUBDIR0)power/x86/$@/ $(QUIET_SUBDIR1)
+	$(call descend,power/x86/$@)
 
 cpupower_install:
-	$(QUIET_SUBDIR0)power/$(@:_install=)/ $(QUIET_SUBDIR1) install
+	$(call descend,power/$(@:_install=),install)
 
 firewire_install lguest_install perf_install usb_install virtio_install vm_install:
-	$(QUIET_SUBDIR0)$(@:_install=)/ $(QUIET_SUBDIR1) install
+	$(call descend,$(@:_install=),install)
 
 selftests_install:
-	$(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) install
+	$(call descend,testing/$(@:_clean=),install)
 
 turbostat_install x86_energy_perf_policy_install:
-	$(QUIET_SUBDIR0)power/x86/$(@:_install=)/ $(QUIET_SUBDIR1) install
+	$(call descend,power/x86/$(@:_install=),install)
 
 install: cpupower_install firewire_install lguest_install perf_install \
 		selftests_install turbostat_install usb_install virtio_install \
 		vm_install x86_energy_perf_policy_install
 
 cpupower_clean:
-	$(QUIET_SUBDIR0)power/cpupower/ $(QUIET_SUBDIR1) clean
+	$(call descend,power/cpupower,clean)
 
 firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
-	$(QUIET_SUBDIR0)$(@:_clean=)/ $(QUIET_SUBDIR1) clean
+	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
-	$(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) clean
+	$(call descend,testing/$(@:_clean=),clean)
 
 turbostat_clean x86_energy_perf_policy_clean:
-	$(QUIET_SUBDIR0)power/x86/$(@:_clean=)/ $(QUIET_SUBDIR1) clean
+	$(call descend,power/x86/$(@:_clean=),clean)
 
 clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \
 		turbostat_clean usb_clean virtio_clean vm_clean \
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 00deed4d..0a619af 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -169,7 +169,34 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+endif
+
+BASIC_CFLAGS = \
+	-Iutil/include \
+	-Iarch/$(ARCH)/include \
+	$(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \
+	-I$(srctree)/arch/$(ARCH)/include/uapi \
+	-I$(srctree)/arch/$(ARCH)/include \
+	$(if $(objtree),-I$(objtree)/include/generated/uapi) \
+	-I$(srctree)/include/uapi \
+	-I$(srctree)/include \
+	-I$(OUTPUT)util \
+	-Iutil \
+	-I. \
+	-I$(TRACE_EVENT_DIR) \
+	-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 46fc9f1..7fcdcdb 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -3,7 +3,7 @@
 
 #include <stdlib.h>
 #include "../../util/types.h"
-#include "../../../../../arch/x86/include/asm/perf_regs.h"
+#include <asm/perf_regs.h>
 
 #ifndef ARCH_X86_64
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 260abc5..283b439 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -22,9 +22,10 @@
 #include <pthread.h>
 #include <math.h>
 
-#include "../../arch/x86/include/asm/svm.h"
-#include "../../arch/x86/include/asm/vmx.h"
-#include "../../arch/x86/include/asm/kvm.h"
+#if defined(__i386__) || defined(__x86_64__)
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
 
 struct event_key {
 	#define INVALID_KEY     (~0ULL)
@@ -58,7 +59,7 @@ struct kvm_event_key {
 };
 
 
-struct perf_kvm;
+struct perf_kvm_stat;
 
 struct kvm_events_ops {
 	bool (*is_begin_event)(struct perf_evsel *evsel,
@@ -66,7 +67,7 @@ struct kvm_events_ops {
 			       struct event_key *key);
 	bool (*is_end_event)(struct perf_evsel *evsel,
 			     struct perf_sample *sample, struct event_key *key);
-	void (*decode_key)(struct perf_kvm *kvm, struct event_key *key,
+	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
 			   char decode[20]);
 	const char *name;
 };
@@ -79,7 +80,7 @@ struct exit_reasons_table {
 #define EVENTS_BITS		12
 #define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
 
-struct perf_kvm {
+struct perf_kvm_stat {
 	struct perf_tool    tool;
 	struct perf_session *session;
 
@@ -146,7 +147,7 @@ static struct exit_reasons_table svm_exit_reasons[] = {
 	SVM_EXIT_REASONS
 };
 
-static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code)
+static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
 {
 	int i = kvm->exit_reasons_size;
 	struct exit_reasons_table *tbl = kvm->exit_reasons;
@@ -162,7 +163,7 @@ static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code)
 	return "UNKNOWN";
 }
 
-static void exit_event_decode_key(struct perf_kvm *kvm,
+static void exit_event_decode_key(struct perf_kvm_stat *kvm,
 				  struct event_key *key,
 				  char decode[20])
 {
@@ -228,7 +229,7 @@ static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
 	return false;
 }
 
-static void mmio_event_decode_key(struct perf_kvm *kvm __maybe_unused,
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				  struct event_key *key,
 				  char decode[20])
 {
@@ -271,7 +272,7 @@ static bool ioport_event_end(struct perf_evsel *evsel,
 	return kvm_entry_event(evsel);
 }
 
-static void ioport_event_decode_key(struct perf_kvm *kvm __maybe_unused,
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				    struct event_key *key,
 				    char decode[20])
 {
@@ -286,7 +287,7 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
-static bool register_kvm_events_ops(struct perf_kvm *kvm)
+static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
 {
 	bool ret = true;
 
@@ -311,7 +312,7 @@ struct vcpu_event_record {
 };
 
 
-static void init_kvm_event_record(struct perf_kvm *kvm)
+static void init_kvm_event_record(struct perf_kvm_stat *kvm)
 {
 	int i;
 
@@ -360,7 +361,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
 	return event;
 }
 
-static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm,
+static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm,
 					       struct event_key *key)
 {
 	struct kvm_event *event;
@@ -381,7 +382,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm,
 	return event;
 }
 
-static bool handle_begin_event(struct perf_kvm *kvm,
+static bool handle_begin_event(struct perf_kvm_stat *kvm,
 			       struct vcpu_event_record *vcpu_record,
 			       struct event_key *key, u64 timestamp)
 {
@@ -425,7 +426,7 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
 	return true;
 }
 
-static bool handle_end_event(struct perf_kvm *kvm,
+static bool handle_end_event(struct perf_kvm_stat *kvm,
 			     struct vcpu_event_record *vcpu_record,
 			     struct event_key *key,
 			     u64 timestamp)
@@ -486,7 +487,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 	return thread->priv;
 }
 
-static bool handle_kvm_event(struct perf_kvm *kvm,
+static bool handle_kvm_event(struct perf_kvm_stat *kvm,
 			     struct thread *thread,
 			     struct perf_evsel *evsel,
 			     struct perf_sample *sample)
@@ -541,7 +542,7 @@ static struct kvm_event_key keys[] = {
 	{ NULL, NULL }
 };
 
-static bool select_key(struct perf_kvm *kvm)
+static bool select_key(struct perf_kvm_stat *kvm)
 {
 	int i;
 
@@ -577,7 +578,8 @@ static void insert_to_result(struct rb_root *result, struct kvm_event *event,
 	rb_insert_color(&event->rb, result);
 }
 
-static void update_total_count(struct perf_kvm *kvm, struct kvm_event *event)
+static void
+update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event)
 {
 	int vcpu = kvm->trace_vcpu;
 
@@ -590,7 +592,7 @@ static bool event_is_valid(struct kvm_event *event, int vcpu)
 	return !!get_event_count(event, vcpu);
 }
 
-static void sort_result(struct perf_kvm *kvm)
+static void sort_result(struct perf_kvm_stat *kvm)
 {
 	unsigned int i;
 	int vcpu = kvm->trace_vcpu;
@@ -627,7 +629,7 @@ static void print_vcpu_info(int vcpu)
 		pr_info("VCPU %d:\n\n", vcpu);
 }
 
-static void print_result(struct perf_kvm *kvm)
+static void print_result(struct perf_kvm_stat *kvm)
 {
 	char decode[20];
 	struct kvm_event *event;
@@ -670,7 +672,8 @@ static int process_sample_event(struct perf_tool *tool,
 				struct machine *machine)
 {
 	struct thread *thread = machine__findnew_thread(machine, sample->tid);
-	struct perf_kvm *kvm = container_of(tool, struct perf_kvm, tool);
+	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
+						 tool);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
@@ -701,7 +704,7 @@ static int get_cpu_isa(struct perf_session *session)
 	return isa;
 }
 
-static int read_events(struct perf_kvm *kvm)
+static int read_events(struct perf_kvm_stat *kvm)
 {
 	int ret;
 
@@ -750,7 +753,7 @@ static bool verify_vcpu(int vcpu)
 	return true;
 }
 
-static int kvm_events_report_vcpu(struct perf_kvm *kvm)
+static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
 {
 	int ret = -EINVAL;
 	int vcpu = kvm->trace_vcpu;
@@ -798,7 +801,8 @@ static const char * const record_args[] = {
 		_p;			\
 	})
 
-static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv)
+static int
+kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
@@ -821,7 +825,8 @@ static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int kvm_events_report(struct perf_kvm *kvm, int argc, const char **argv)
+static int
+kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
 	const struct option kvm_events_report_options[] = {
 		OPT_STRING(0, "event", &kvm->report_event, "report event",
@@ -864,24 +869,37 @@ static void print_kvm_stat_usage(void)
 	printf("\nOtherwise, it is the alias of 'perf stat':\n");
 }
 
-static int kvm_cmd_stat(struct perf_kvm *kvm, int argc, const char **argv)
+static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 {
+	struct perf_kvm_stat kvm = {
+		.file_name = file_name,
+
+		.trace_vcpu	= -1,
+		.report_event	= "vmexit",
+		.sort_key	= "sample",
+
+		.exit_reasons = svm_exit_reasons,
+		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
+		.exit_reasons_isa = "SVM",
+	};
+
 	if (argc == 1) {
 		print_kvm_stat_usage();
 		goto perf_stat;
 	}
 
 	if (!strncmp(argv[1], "rec", 3))
-		return kvm_events_record(kvm, argc - 1, argv + 1);
+		return kvm_events_record(&kvm, argc - 1, argv + 1);
 
 	if (!strncmp(argv[1], "rep", 3))
-		return kvm_events_report(kvm, argc - 1 , argv + 1);
+		return kvm_events_report(&kvm, argc - 1 , argv + 1);
 
 perf_stat:
 	return cmd_stat(argc, argv, NULL);
 }
+#endif
 
-static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv)
+static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -890,7 +908,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv)
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("record");
 	rec_argv[i++] = strdup("-o");
-	rec_argv[i++] = strdup(kvm->file_name);
+	rec_argv[i++] = strdup(file_name);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -899,7 +917,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv)
+static int __cmd_report(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -908,7 +926,7 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv)
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("report");
 	rec_argv[i++] = strdup("-i");
-	rec_argv[i++] = strdup(kvm->file_name);
+	rec_argv[i++] = strdup(file_name);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -917,7 +935,8 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv)
 	return cmd_report(i, rec_argv, NULL);
 }
 
-static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv)
+static int
+__cmd_buildid_list(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -926,7 +945,7 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv)
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("buildid-list");
 	rec_argv[i++] = strdup("-i");
-	rec_argv[i++] = strdup(kvm->file_name);
+	rec_argv[i++] = strdup(file_name);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -937,20 +956,12 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv)
 
 int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	struct perf_kvm kvm = {
-		.trace_vcpu	= -1,
-		.report_event	= "vmexit",
-		.sort_key	= "sample",
-
-		.exit_reasons = svm_exit_reasons,
-		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
-		.exit_reasons_isa = "SVM",
-	};
+	const char *file_name;
 
 	const struct option kvm_options[] = {
-		OPT_STRING('i', "input", &kvm.file_name, "file",
+		OPT_STRING('i', "input", &file_name, "file",
 			   "Input file name"),
-		OPT_STRING('o', "output", &kvm.file_name, "file",
+		OPT_STRING('o', "output", &file_name, "file",
 			   "Output file name"),
 		OPT_BOOLEAN(0, "guest", &perf_guest,
 			    "Collect guest os data"),
@@ -985,32 +996,34 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!perf_host)
 		perf_guest = 1;
 
-	if (!kvm.file_name) {
+	if (!file_name) {
 		if (perf_host && !perf_guest)
-			kvm.file_name = strdup("perf.data.host");
+			file_name = strdup("perf.data.host");
 		else if (!perf_host && perf_guest)
-			kvm.file_name = strdup("perf.data.guest");
+			file_name = strdup("perf.data.guest");
 		else
-			kvm.file_name = strdup("perf.data.kvm");
+			file_name = strdup("perf.data.kvm");
 
-		if (!kvm.file_name) {
+		if (!file_name) {
 			pr_err("Failed to allocate memory for filename\n");
 			return -ENOMEM;
 		}
 	}
 
 	if (!strncmp(argv[0], "rec", 3))
-		return __cmd_record(&kvm, argc, argv);
+		return __cmd_record(file_name, argc, argv);
 	else if (!strncmp(argv[0], "rep", 3))
-		return __cmd_report(&kvm, argc, argv);
+		return __cmd_report(file_name, argc, argv);
 	else if (!strncmp(argv[0], "diff", 4))
 		return cmd_diff(argc, argv, NULL);
 	else if (!strncmp(argv[0], "top", 3))
 		return cmd_top(argc, argv, NULL);
 	else if (!strncmp(argv[0], "buildid-list", 12))
-		return __cmd_buildid_list(&kvm, argc, argv);
+		return __cmd_buildid_list(file_name, argc, argv);
+#if defined(__i386__) || defined(__x86_64__)
 	else if (!strncmp(argv[0], "stat", 4))
-		return kvm_cmd_stat(&kvm, argc, argv);
+		return kvm_cmd_stat(file_name, argc, argv);
+#endif
 	else
 		usage_with_options(kvm_usage, kvm_options);
 
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 484f26c..5acd6e8 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -15,7 +15,7 @@
 #include "util/thread_map.h"
 #include "util/pmu.h"
 #include "event-parse.h"
-#include "../../include/linux/hw_breakpoint.h"
+#include <linux/hw_breakpoint.h>
 
 #include <sys/mman.h>
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index c50985e..238f923 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -5,8 +5,9 @@ struct winsize;
 
 void get_term_dimensions(struct winsize *ws);
 
+#include <asm/unistd.h>
+
 #if defined(__i386__)
-#include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	"model name"
@@ -16,7 +17,6 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #if defined(__x86_64__)
-#include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	"model name"
@@ -26,20 +26,17 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __powerpc__
-#include "../../arch/powerpc/include/asm/unistd.h"
 #define rmb()		asm volatile ("sync" ::: "memory")
 #define cpu_relax()	asm volatile ("" ::: "memory");
 #define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __s390__
-#include "../../arch/s390/include/asm/unistd.h"
 #define rmb()		asm volatile("bcr 15,0" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory");
 #endif
 
 #ifdef __sh__
-#include "../../arch/sh/include/asm/unistd.h"
 #if defined(__SH4A__) || defined(__SH5__)
 # define rmb()		asm volatile("synco" ::: "memory")
 #else
@@ -50,35 +47,30 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __hppa__
-#include "../../arch/parisc/include/asm/unistd.h"
 #define rmb()		asm volatile("" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory");
 #define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __sparc__
-#include "../../arch/sparc/include/uapi/asm/unistd.h"
 #define rmb()		asm volatile("":::"memory")
 #define cpu_relax()	asm volatile("":::"memory")
 #define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __alpha__
-#include "../../arch/alpha/include/asm/unistd.h"
 #define rmb()		asm volatile("mb" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory")
 #define CPUINFO_PROC	"cpu model"
 #endif
 
 #ifdef __ia64__
-#include "../../arch/ia64/include/asm/unistd.h"
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
 #define CPUINFO_PROC	"model name"
 #endif
 
 #ifdef __arm__
-#include "../../arch/arm/include/asm/unistd.h"
 /*
  * Use the __kuser_memory_barrier helper in the CPU helper page. See
  * arch/arm/kernel/entry-armv.S in the kernel source for details.
@@ -89,13 +81,11 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __aarch64__
-#include "../../arch/arm64/include/asm/unistd.h"
 #define rmb()		asm volatile("dmb ld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
 #ifdef __mips__
-#include "../../arch/mips/include/asm/unistd.h"
 #define rmb()		asm volatile(					\
 				".set	mips2\n\t"			\
 				"sync\n\t"				\
@@ -112,7 +102,7 @@ void get_term_dimensions(struct winsize *ws);
 #include <sys/types.h>
 #include <sys/syscall.h>
 
-#include "../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include "util/types.h"
 #include <stdbool.h>
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 618d411..d144d46 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -18,8 +18,8 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
-#include "../../../include/linux/hw_breakpoint.h"
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
 #include "perf_regs.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6f94d6d..d99b476 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -3,7 +3,8 @@
 
 #include <linux/list.h>
 #include <stdbool.h>
-#include "../../../include/uapi/linux/perf_event.h"
+#include <stddef.h>
+#include <linux/perf_event.h>
 #include "types.h"
 #include "xyarray.h"
 #include "cgroup.h"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 7daad23..566b84c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1378,6 +1378,8 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
 
 		str = tmp + 1;
 		fprintf(fp, "# node%u cpu list : %s\n", c, str);
+
+		str += strlen(str) + 1;
 	}
 	return;
 error:
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 879d215..9bc0078 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
 #include "types.h"
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index 516ecd9..6ef213b 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -3,7 +3,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "sysfs.h"
-#include "../../../include/linux/hw_breakpoint.h"
+#include <linux/hw_breakpoint.h>
 
 #define TEST_ASSERT_VAL(text, cond) \
 do { \
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 75c7b0f..6b6d03e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,4 +1,4 @@
-#include "../../../include/linux/hw_breakpoint.h"
+#include <linux/hw_breakpoint.h>
 #include "util.h"
 #include "../perf.h"
 #include "evlist.h"
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 839230c..2820c40 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <stdbool.h>
 #include "types.h"
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include "types.h"
 
 struct list_head;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 39f3aba..fdeb8ac 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -2,7 +2,7 @@
 #define __PMU_H
 
 #include <linux/bitops.h>
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index dd64261..0eae00a 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -7,7 +7,7 @@
 #include "symbol.h"
 #include "thread.h"
 #include <linux/rbtree.h>
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 
 struct sample_queue;
 struct ip_callchain;
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 2eeb51b..cfa9068 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -90,17 +90,17 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
 	if (!strbuf_avail(sb))
 		strbuf_grow(sb, 64);
 	va_start(ap, fmt);
-	len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
 	va_end(ap);
 	if (len < 0)
-		die("your vscnprintf is broken");
+		die("your vsnprintf is broken");
 	if (len > strbuf_avail(sb)) {
 		strbuf_grow(sb, len);
 		va_start(ap, fmt);
-		len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
 		va_end(ap);
 		if (len > strbuf_avail(sb)) {
-			die("this should not happen, your snprintf is broken");
+			die("this should not happen, your vsnprintf is broken");
 		}
 	}
 	strbuf_setlen(sb, sb->len + len);
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 96ce80a..2964b96 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,8 +1,11 @@
-ifeq ("$(origin O)", "command line")
+ifeq ($(origin O), command line)
 	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
 	ABSOLUTE_O := $(shell cd $(O) ; pwd)
-	OUTPUT := $(ABSOLUTE_O)/
+	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
+ifeq ($(objtree),)
+	objtree := $(O)
+endif
 endif
 
 ifneq ($(OUTPUT),)
@@ -41,7 +44,16 @@ else
 NO_SUBDIR = :
 endif
 
-QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
+#
+# Define a callable command for descending to a new directory
+#
+# Call by doing: $(call descend,directory[,target])
+#
+descend = \
+	+mkdir -p $(OUTPUT)$(1) && \
+	$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
+
+QUIET_SUBDIR0  = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
 QUIET_SUBDIR1  =
 
 ifneq ($(findstring $(MAKEFLAGS),s),s)
@@ -56,5 +68,10 @@ ifndef V
 			 $(MAKE) $(PRINT_DIR) -C $$subdir
 	QUIET_FLEX     = @echo '   ' FLEX $@;
 	QUIET_BISON    = @echo '   ' BISON $@;
+
+	descend = \
+		@echo '   ' DESCEND $(1); \
+		mkdir -p $(OUTPUT)$(1) && \
+		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
 endif
 endif

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-10-26 14:44 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-10-26 14:44 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Steven Rostedt, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 64dfab8e83644902ad2fd559a56c411b47e3ef3c perf/x86: Remove unused variable in nhmex_rbox_alter_er()

Most of the kernel diffstat relates to a group of Intel P6 and 
KNC (Xeon-Phi Knights Corner) PMU driver fixes, neither of which 
is in heavy use, so we took the fixes.

The rest is diverse smallish fixes to the tooling and kernel 
side.

 Thanks,

	Ingo

------------------>
Andre Przywara (1):
      x86/perf: Fix virtualization sanity check

Arnaldo Carvalho de Melo (2):
      perf trace: Validate syscall id before growing syscall table
      perf trace: Check if sample raw_data field is set

Jiri Olsa (1):
      perf test: Fix exclude_guest parse events tests

Luigi Semenzato (1):
      perf tools: do not flush maps on COMM for perf report

Namhyung Kim (1):
      perf help: Fix --help for builtins

Srivatsa S. Bhat (2):
      perf, cpu hotplug: Run CPU_STARTING notifiers with irqs disabled
      perf, cpu hotplug: Use cached value of smp_processor_id()

Vince Weaver (6):
      perf/x86: Fix P6 FP_ASSIST event constraint
      perf/x86: Update/fix generic events on P6 PMU
      perf/x86: Remove P6 cpuc->enabled check
      perf/x86: Make Intel KNC use full 40-bit width of counters
      perf/x86: Remove cpuc->enable check on Intl KNC event enable/disable
      perf/x86: Enable overflow on Intel KNC with a custom knc_pmu_handle_irq()

Wei Yongjun (1):
      perf/x86: Remove unused variable in nhmex_rbox_alter_er()

Yan, Zheng (1):
      perf/x86/uncore: Handle pci_read_config_dword() errors


 arch/x86/kernel/cpu/perf_event.c              |  10 +-
 arch/x86/kernel/cpu/perf_event_intel_uncore.c |  45 +++++----
 arch/x86/kernel/cpu/perf_event_knc.c          |  93 ++++++++++++++++---
 arch/x86/kernel/cpu/perf_event_p6.c           | 127 +++++++++++++++++++++++---
 include/linux/perf_event.h                    |  10 +-
 tools/perf/builtin-help.c                     |   2 +-
 tools/perf/builtin-trace.c                    |  18 +++-
 tools/perf/util/parse-events-test.c           |  12 ++-
 tools/perf/util/thread.c                      |   1 -
 9 files changed, 257 insertions(+), 61 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3373f84..4a3374e 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -208,12 +208,14 @@ static bool check_hw_exists(void)
 	}
 
 	/*
-	 * Now write a value and read it back to see if it matches,
-	 * this is needed to detect certain hardware emulators (qemu/kvm)
-	 * that don't trap on the MSR access and always return 0s.
+	 * Read the current value, change it and read it back to see if it
+	 * matches, this is needed to detect certain hardware emulators
+	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
-	val = 0xabcdUL;
 	reg = x86_pmu_event_addr(0);
+	if (rdmsrl_safe(reg, &val))
+		goto msr_fail;
+	val ^= 0xffffUL;
 	ret = wrmsrl_safe(reg, val);
 	ret |= rdmsrl_safe(reg, &val_new);
 	if (ret || val != val_new)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 5df8d32..3cf3d97 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -118,22 +118,24 @@ static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config;
+	u32 config = 0;
 
-	pci_read_config_dword(pdev, box_ctl, &config);
-	config |= SNBEP_PMON_BOX_CTL_FRZ;
-	pci_write_config_dword(pdev, box_ctl, config);
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config |= SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
 }
 
 static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config;
+	u32 config = 0;
 
-	pci_read_config_dword(pdev, box_ctl, &config);
-	config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-	pci_write_config_dword(pdev, box_ctl, config);
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
 }
 
 static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -156,7 +158,7 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
-	u64 count;
+	u64 count = 0;
 
 	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
 	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
@@ -603,11 +605,12 @@ static struct pci_driver snbep_uncore_pci_driver = {
 /*
  * build pci bus to socket mapping
  */
-static void snbep_pci2phy_map_init(void)
+static int snbep_pci2phy_map_init(void)
 {
 	struct pci_dev *ubox_dev = NULL;
 	int i, bus, nodeid;
-	u32 config;
+	int err = 0;
+	u32 config = 0;
 
 	while (1) {
 		/* find the UBOX device */
@@ -618,10 +621,14 @@ static void snbep_pci2phy_map_init(void)
 			break;
 		bus = ubox_dev->bus->number;
 		/* get the Node ID of the local register */
-		pci_read_config_dword(ubox_dev, 0x40, &config);
+		err = pci_read_config_dword(ubox_dev, 0x40, &config);
+		if (err)
+			break;
 		nodeid = config;
 		/* get the Node ID mapping */
-		pci_read_config_dword(ubox_dev, 0x54, &config);
+		err = pci_read_config_dword(ubox_dev, 0x54, &config);
+		if (err)
+			break;
 		/*
 		 * every three bits in the Node ID mapping register maps
 		 * to a particular node.
@@ -633,7 +640,11 @@ static void snbep_pci2phy_map_init(void)
 			}
 		}
 	};
-	return;
+
+	if (ubox_dev)
+		pci_dev_put(ubox_dev);
+
+	return err ? pcibios_err_to_errno(err) : 0;
 }
 /* end of Sandy Bridge-EP uncore support */
 
@@ -1547,7 +1558,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	int port;
 
 	/* adjust the main event selector and extra register index */
 	if (reg1->idx % 2) {
@@ -1559,7 +1569,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 	}
 
 	/* adjust extra register config */
-	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
 	switch (reg1->idx % 6) {
 	case 2:
 		/* shift the 8~15 bits to the 0~7 bits */
@@ -2578,9 +2587,11 @@ static int __init uncore_pci_init(void)
 
 	switch (boot_cpu_data.x86_model) {
 	case 45: /* Sandy Bridge-EP */
+		ret = snbep_pci2phy_map_init();
+		if (ret)
+			return ret;
 		pci_uncores = snbep_pci_uncores;
 		uncore_pci_driver = &snbep_uncore_pci_driver;
-		snbep_pci2phy_map_init();
 		break;
 	default:
 		return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 7c46bfd..4b7731b 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -3,6 +3,8 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 
+#include <asm/hardirq.h>
+
 #include "perf_event.h"
 
 static const u64 knc_perfmon_event_map[] =
@@ -173,30 +175,100 @@ static void knc_pmu_enable_all(int added)
 static inline void
 knc_pmu_disable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
-	if (cpuc->enabled)
-		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+	val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 
 	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
 }
 
 static void knc_pmu_enable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+	val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
 	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
 }
 
+static inline u64 knc_pmu_get_status(void)
+{
+	u64 status;
+
+	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
+
+	return status;
+}
+
+static inline void knc_pmu_ack_status(u64 ack)
+{
+	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
+}
+
+static int knc_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	int handled = 0;
+	int bit, loops;
+	u64 status;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+
+	knc_pmu_disable_all();
+
+	status = knc_pmu_get_status();
+	if (!status) {
+		knc_pmu_enable_all(0);
+		return handled;
+	}
+
+	loops = 0;
+again:
+	knc_pmu_ack_status(status);
+	if (++loops > 100) {
+		WARN_ONCE(1, "perf: irq loop stuck!\n");
+		perf_event_print_debug();
+		goto done;
+	}
+
+	inc_irq_stat(apic_perf_irqs);
+
+	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+		struct perf_event *event = cpuc->events[bit];
+
+		handled++;
+
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+
+		if (!intel_pmu_save_and_restart(event))
+			continue;
+
+		perf_sample_data_init(&data, 0, event->hw.last_period);
+
+		if (perf_event_overflow(event, &data, regs))
+			x86_pmu_stop(event, 0);
+	}
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	status = knc_pmu_get_status();
+	if (status)
+		goto again;
+
+done:
+	knc_pmu_enable_all(0);
+
+	return handled;
+}
+
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -214,7 +286,7 @@ static struct attribute *intel_knc_formats_attr[] = {
 
 static __initconst struct x86_pmu knc_pmu = {
 	.name			= "knc",
-	.handle_irq		= x86_pmu_handle_irq,
+	.handle_irq		= knc_pmu_handle_irq,
 	.disable_all		= knc_pmu_disable_all,
 	.enable_all		= knc_pmu_enable_all,
 	.enable			= knc_pmu_enable_event,
@@ -226,12 +298,11 @@ static __initconst struct x86_pmu knc_pmu = {
 	.event_map		= knc_pmu_event_map,
 	.max_events             = ARRAY_SIZE(knc_perfmon_event_map),
 	.apic			= 1,
-	.max_period		= (1ULL << 31) - 1,
+	.max_period		= (1ULL << 39) - 1,
 	.version		= 0,
 	.num_counters		= 2,
-	/* in theory 40 bits, early silicon is buggy though */
-	.cntval_bits		= 32,
-	.cntval_mask		= (1ULL << 32) - 1,
+	.cntval_bits		= 40,
+	.cntval_mask		= (1ULL << 40) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= knc_event_constraints,
 	.format_attrs		= intel_knc_formats_attr,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index e4dd0f7..7d0270b 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -8,13 +8,106 @@
  */
 static const u64 p6_perfmon_event_map[] =
 {
-  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,
-  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,
-  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
-  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,	/* CPU_CLK_UNHALTED */
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,	/* INST_RETIRED     */
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,	/* L2_RQSTS:M:E:S:I */
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,	/* L2_RQSTS:I       */
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,	/* BR_INST_RETIRED  */
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,	/* BR_MISS_PRED_RETIRED */
+  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,	/* BUS_DRDY_CLOCKS  */
+  [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a2,	/* RESOURCE_STALLS  */
+
+};
+
+static __initconst u64 p6_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0043,	/* DATA_MEM_REFS       */
+                [ C(RESULT_MISS)   ] = 0x0045,	/* DCU_LINES_IN        */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x0f29,	/* L2_LD:M:E:S:I       */
+	},
+        [ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+        },
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080,	/* IFU_IFETCH         */
+		[ C(RESULT_MISS)   ] = 0x0f28,	/* L2_IFETCH:M:E:S:I  */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x0025,	/* L2_M_LINES_INM     */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0043,	/* DATA_MEM_REFS      */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080,	/* IFU_IFETCH         */
+		[ C(RESULT_MISS)   ] = 0x0085,	/* ITLB_MISS          */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4,	/* BR_INST_RETIRED      */
+		[ C(RESULT_MISS)   ] = 0x00c5,	/* BR_MISS_PRED_RETIRED */
+        },
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
 };
 
 static u64 p6_pmu_event_map(int hw_event)
@@ -34,7 +127,7 @@ static struct event_constraint p6_event_constraints[] =
 {
 	INTEL_EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
 	INTEL_EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
-	INTEL_EVENT_CONSTRAINT(0x11, 0x1),	/* FP_ASSIST */
+	INTEL_EVENT_CONSTRAINT(0x11, 0x2),	/* FP_ASSIST */
 	INTEL_EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
 	INTEL_EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
 	INTEL_EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
@@ -64,25 +157,25 @@ static void p6_pmu_enable_all(int added)
 static inline void
 p6_pmu_disable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val = P6_NOP_EVENT;
 
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
-
 	(void)wrmsrl_safe(hwc->config_base, val);
 }
 
 static void p6_pmu_enable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+
+	/*
+	 * p6 only has a global event enable, set on PerfEvtSel0
+	 * We "disable" events by programming P6_NOP_EVENT
+	 * and we rely on p6_pmu_enable_all() being called
+	 * to actually enable the events.
+	 */
 
 	(void)wrmsrl_safe(hwc->config_base, val);
 }
@@ -158,5 +251,9 @@ __init int p6_pmu_init(void)
 
 	x86_pmu = p6_pmu;
 
+	memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
+		sizeof(hw_cache_event_ids));
+
+
 	return 0;
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2e90235..6bfb2faa 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -803,12 +803,16 @@ static inline void perf_event_task_tick(void)				{ }
 do {									\
 	static struct notifier_block fn##_nb __cpuinitdata =		\
 		{ .notifier_call = fn, .priority = CPU_PRI_PERF };	\
+	unsigned long cpu = smp_processor_id();				\
+	unsigned long flags;						\
 	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,			\
-		(void *)(unsigned long)smp_processor_id());		\
+		(void *)(unsigned long)cpu);				\
+	local_irq_save(flags);						\
 	fn(&fn##_nb, (unsigned long)CPU_STARTING,			\
-		(void *)(unsigned long)smp_processor_id());		\
+		(void *)(unsigned long)cpu);				\
+	local_irq_restore(flags);					\
 	fn(&fn##_nb, (unsigned long)CPU_ONLINE,				\
-		(void *)(unsigned long)smp_processor_id());		\
+		(void *)(unsigned long)cpu);				\
 	register_cpu_notifier(&fn##_nb);				\
 } while (0)
 
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 411ee56..178b88a 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -414,7 +414,7 @@ static int show_html_page(const char *perf_cmd)
 int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	bool show_all = false;
-	enum help_format help_format = HELP_FORMAT_NONE;
+	enum help_format help_format = HELP_FORMAT_MAN;
 	struct option builtin_help_options[] = {
 	OPT_BOOLEAN('a', "all", &show_all, "print all available commands"),
 	OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dec8ced..7aaee39 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -56,6 +56,10 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 {
 	char tp_name[128];
 	struct syscall *sc;
+	const char *name = audit_syscall_to_name(id, trace->audit_machine);
+
+	if (name == NULL)
+		return -1;
 
 	if (id > trace->syscalls.max) {
 		struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));
@@ -75,11 +79,8 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	}
 
 	sc = trace->syscalls.table + id;
-	sc->name = audit_syscall_to_name(id, trace->audit_machine);
-	if (sc->name == NULL)
-		return -1;
-
-	sc->fmt = syscall_fmt__find(sc->name);
+	sc->name = name;
+	sc->fmt  = syscall_fmt__find(sc->name);
 
 	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
 	sc->tp_format = event_format__new("syscalls", tp_name);
@@ -267,6 +268,13 @@ again:
 			if (evlist->threads->map[0] == -1 || evlist->threads->nr > 1)
 				printf("%d ", sample.tid);
 
+			if (sample.raw_data == NULL) {
+				printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
+				       perf_evsel__name(evsel), sample.tid,
+				       sample.cpu, sample.raw_size);
+				continue;
+			}
+
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
 		}
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index 28c18d1..516ecd9 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -513,7 +513,8 @@ static int test__group1(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
@@ -599,7 +600,8 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
@@ -662,7 +664,8 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
@@ -676,7 +679,8 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fb4b7ea..8b3e593 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -39,7 +39,6 @@ int thread__set_comm(struct thread *self, const char *comm)
 	err = self->comm == NULL ? -ENOMEM : 0;
 	if (!err) {
 		self->comm_set = true;
-		map_groups__flush(&self->mg);
 	}
 	return err;
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-10-23 11:02 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-10-23 11:02 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Oleg Nesterov, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: ef8ff74ed8dd9d4b3ba8cb9f2fc927a27c697a8b Merge branch 'tip/perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent

Most of these are uprobes race fixes from Oleg, and their 
preparatory cleanups. (It's larger than what I'd normally send 
for an -rc kernel, but they looked significant enough to not 
delay them.)

There's also an oprofile fix and an uncore PMU fix.

 Thanks,

	Ingo

------------------>
Dan Carpenter (1):
      oprofile, x86: Fix wrapping bug in op_x86_get_ctrl()

Oleg Nesterov (19):
      uprobes: Do not leak UTASK_BP_HIT if find_active_uprobe() fails
      uprobes: Do not setup ->active_uprobe/state prematurely
      uprobes: Fix UPROBE_SKIP_SSTEP checks in handle_swbp()
      uprobes: Kill UTASK_BP_HIT state
      uprobes: Move clear_thread_flag(TIF_UPROBE) to uprobe_notify_resume()
      uprobes: Change write_opcode() to use FOLL_FORCE
      uprobes: Change valid_vma() to demand VM_MAYEXEC rather than VM_EXEC
      uprobes: Restrict valid_vma(false) to skip VM_SHARED vmas
      uprobes: Kill set_swbp()->is_swbp_at_addr()
      uprobes: Introduce copy_opcode(), kill read_opcode()
      uprobes: Kill set_orig_insn()->is_swbp_at_addr()
      uprobes: Simplify is_swbp_at_addr(), remove stale comments
      uprobes/x86: Only rep+nop can be emulated correctly
      uprobes: Don't return success if alloc_uprobe() fails
      uprobes: Do not delete uprobe if uprobe_unregister() fails
      uprobes: Fix handle_swbp() vs unregister() + register() race
      uprobes: Introduce prepare_uprobe()
      uprobes: Fix prepare_uprobe() race with itself
      uprobes: Fix the racy uprobe->flags manipulation

Vaibhav Nagarnaik (1):
      ring-buffer: Check for uninitialized cpu buffer before resizing

Yan, Zheng (1):
      perf/x86: Disable uncore on virtualized CPUs


 arch/x86/kernel/cpu/perf_event_intel_uncore.c |   3 +
 arch/x86/kernel/signal.c                      |   4 +-
 arch/x86/kernel/uprobes.c                     |  16 +-
 arch/x86/oprofile/nmi_int.c                   |   2 +-
 include/linux/uprobes.h                       |  11 -
 kernel/events/uprobes.c                       | 345 ++++++++++++--------------
 kernel/trace/ring_buffer.c                    |   4 +
 7 files changed, 173 insertions(+), 212 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 99d96a4..5df8d32 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2926,6 +2926,9 @@ static int __init intel_uncore_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return -ENODEV;
 
+	if (cpu_has_hypervisor)
+		return -ENODEV;
+
 	ret = uncore_pci_init();
 	if (ret)
 		goto fail;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 29ad351..70b27ee 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -824,10 +824,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		mce_notify_process();
 #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
 
-	if (thread_info_flags & _TIF_UPROBE) {
-		clear_thread_flag(TIF_UPROBE);
+	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
-	}
 
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 9538f00..aafa555 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -651,31 +651,19 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 /*
  * Skip these instructions as per the currently known x86 ISA.
- * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 }
+ * rep=0x66*; nop=0x90
  */
 static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	int i;
 
 	for (i = 0; i < MAX_UINSN_BYTES; i++) {
-		if ((auprobe->insn[i] == 0x66))
+		if (auprobe->insn[i] == 0x66)
 			continue;
 
 		if (auprobe->insn[i] == 0x90)
 			return true;
 
-		if (i == (MAX_UINSN_BYTES - 1))
-			break;
-
-		if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x1f))
-			return true;
-
-		if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x19))
-			return true;
-
-		if ((auprobe->insn[i] == 0x87) && (auprobe->insn[i+1] == 0xc0))
-			return true;
-
 		break;
 	}
 	return false;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 26b8a85..48768df 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -55,7 +55,7 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 	val |= counter_config->extra;
 	event &= model->event_mask ? model->event_mask : 0xFF;
 	val |= event & 0xFF;
-	val |= (event & 0x0F00) << 24;
+	val |= (u64)(event & 0x0F00) << 24;
 
 	return val;
 }
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index e6f0331..2459457 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -35,16 +35,6 @@ struct inode;
 # include <asm/uprobes.h>
 #endif
 
-/* flags that denote/change uprobes behaviour */
-
-/* Have a copy of original instruction */
-#define UPROBE_COPY_INSN	0x1
-
-/* Dont run handlers when first register/ last unregister in progress*/
-#define UPROBE_RUN_HANDLER	0x2
-/* Can skip singlestep */
-#define UPROBE_SKIP_SSTEP	0x4
-
 struct uprobe_consumer {
 	int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
 	/*
@@ -59,7 +49,6 @@ struct uprobe_consumer {
 #ifdef CONFIG_UPROBES
 enum uprobe_task_state {
 	UTASK_RUNNING,
-	UTASK_BP_HIT,
 	UTASK_SSTEP,
 	UTASK_SSTEP_ACK,
 	UTASK_SSTEP_TRAPPED,
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 98256bc..5cc4e7e 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -78,15 +78,23 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
  */
 static atomic_t uprobe_events = ATOMIC_INIT(0);
 
+/* Have a copy of original instruction */
+#define UPROBE_COPY_INSN	0
+/* Dont run handlers when first register/ last unregister in progress*/
+#define UPROBE_RUN_HANDLER	1
+/* Can skip singlestep */
+#define UPROBE_SKIP_SSTEP	2
+
 struct uprobe {
 	struct rb_node		rb_node;	/* node in the rb tree */
 	atomic_t		ref;
 	struct rw_semaphore	consumer_rwsem;
+	struct mutex		copy_mutex;	/* TODO: kill me and UPROBE_COPY_INSN */
 	struct list_head	pending_list;
 	struct uprobe_consumer	*consumers;
 	struct inode		*inode;		/* Also hold a ref to inode */
 	loff_t			offset;
-	int			flags;
+	unsigned long		flags;
 	struct arch_uprobe	arch;
 };
 
@@ -100,17 +108,12 @@ struct uprobe {
  */
 static bool valid_vma(struct vm_area_struct *vma, bool is_register)
 {
-	if (!vma->vm_file)
-		return false;
-
-	if (!is_register)
-		return true;
+	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED;
 
-	if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED))
-				== (VM_READ|VM_EXEC))
-		return true;
+	if (is_register)
+		flags |= VM_WRITE;
 
-	return false;
+	return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC;
 }
 
 static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
@@ -193,19 +196,44 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn)
 	return *insn == UPROBE_SWBP_INSN;
 }
 
+static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode)
+{
+	void *kaddr = kmap_atomic(page);
+	memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE);
+	kunmap_atomic(kaddr);
+}
+
+static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode)
+{
+	uprobe_opcode_t old_opcode;
+	bool is_swbp;
+
+	copy_opcode(page, vaddr, &old_opcode);
+	is_swbp = is_swbp_insn(&old_opcode);
+
+	if (is_swbp_insn(new_opcode)) {
+		if (is_swbp)		/* register: already installed? */
+			return 0;
+	} else {
+		if (!is_swbp)		/* unregister: was it changed by us? */
+			return 0;
+	}
+
+	return 1;
+}
+
 /*
  * NOTE:
  * Expect the breakpoint instruction to be the smallest size instruction for
  * the architecture. If an arch has variable length instruction and the
  * breakpoint instruction is not of the smallest length instruction
- * supported by that architecture then we need to modify read_opcode /
+ * supported by that architecture then we need to modify is_swbp_at_addr and
  * write_opcode accordingly. This would never be a problem for archs that
  * have fixed length instructions.
  */
 
 /*
  * write_opcode - write the opcode at a given virtual address.
- * @auprobe: arch breakpointing information.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
@@ -216,8 +244,8 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn)
  * For mm @mm, write the opcode at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
-			unsigned long vaddr, uprobe_opcode_t opcode)
+static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
+			uprobe_opcode_t opcode)
 {
 	struct page *old_page, *new_page;
 	void *vaddr_old, *vaddr_new;
@@ -226,10 +254,14 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 retry:
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
+	ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
 	if (ret <= 0)
 		return ret;
 
+	ret = verify_opcode(old_page, vaddr, &opcode);
+	if (ret <= 0)
+		goto put_old;
+
 	ret = -ENOMEM;
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 	if (!new_page)
@@ -264,63 +296,6 @@ put_old:
 }
 
 /**
- * read_opcode - read the opcode at a given virtual address.
- * @mm: the probed process address space.
- * @vaddr: the virtual address to read the opcode.
- * @opcode: location to store the read opcode.
- *
- * Called with mm->mmap_sem held (for read and with a reference to
- * mm.
- *
- * For mm @mm, read the opcode at @vaddr and store it in @opcode.
- * Return 0 (success) or a negative errno.
- */
-static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode)
-{
-	struct page *page;
-	void *vaddr_new;
-	int ret;
-
-	ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
-	if (ret <= 0)
-		return ret;
-
-	vaddr_new = kmap_atomic(page);
-	vaddr &= ~PAGE_MASK;
-	memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE);
-	kunmap_atomic(vaddr_new);
-
-	put_page(page);
-
-	return 0;
-}
-
-static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
-{
-	uprobe_opcode_t opcode;
-	int result;
-
-	if (current->mm == mm) {
-		pagefault_disable();
-		result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
-								sizeof(opcode));
-		pagefault_enable();
-
-		if (likely(result == 0))
-			goto out;
-	}
-
-	result = read_opcode(mm, vaddr, &opcode);
-	if (result)
-		return result;
-out:
-	if (is_swbp_insn(&opcode))
-		return 1;
-
-	return 0;
-}
-
-/**
  * set_swbp - store breakpoint at a given address.
  * @auprobe: arch specific probepoint information.
  * @mm: the probed process address space.
@@ -331,18 +306,7 @@ out:
  */
 int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	int result;
-	/*
-	 * See the comment near uprobes_hash().
-	 */
-	result = is_swbp_at_addr(mm, vaddr);
-	if (result == 1)
-		return 0;
-
-	if (result)
-		return result;
-
-	return write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+	return write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
 }
 
 /**
@@ -357,16 +321,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	int result;
-
-	result = is_swbp_at_addr(mm, vaddr);
-	if (!result)
-		return -EINVAL;
-
-	if (result != 1)
-		return result;
-
-	return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+	return write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
 }
 
 static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -473,7 +428,7 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe)
 	spin_unlock(&uprobes_treelock);
 
 	/* For now assume that the instruction need not be single-stepped */
-	uprobe->flags |= UPROBE_SKIP_SSTEP;
+	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
 
 	return u;
 }
@@ -495,6 +450,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	uprobe->inode = igrab(inode);
 	uprobe->offset = offset;
 	init_rwsem(&uprobe->consumer_rwsem);
+	mutex_init(&uprobe->copy_mutex);
 
 	/* add to uprobes_tree, sorted on inode:offset */
 	cur_uprobe = insert_uprobe(uprobe);
@@ -515,7 +471,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 {
 	struct uprobe_consumer *uc;
 
-	if (!(uprobe->flags & UPROBE_RUN_HANDLER))
+	if (!test_bit(UPROBE_RUN_HANDLER, &uprobe->flags))
 		return;
 
 	down_read(&uprobe->consumer_rwsem);
@@ -621,29 +577,43 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp)
 	return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset);
 }
 
-/*
- * How mm->uprobes_state.count gets updated
- * uprobe_mmap() increments the count if
- * 	- it successfully adds a breakpoint.
- * 	- it cannot add a breakpoint, but sees that there is a underlying
- * 	  breakpoint (via a is_swbp_at_addr()).
- *
- * uprobe_munmap() decrements the count if
- * 	- it sees a underlying breakpoint, (via is_swbp_at_addr)
- * 	  (Subsequent uprobe_unregister wouldnt find the breakpoint
- * 	  unless a uprobe_mmap kicks in, since the old vma would be
- * 	  dropped just after uprobe_munmap.)
- *
- * uprobe_register increments the count if:
- * 	- it successfully adds a breakpoint.
- *
- * uprobe_unregister decrements the count if:
- * 	- it sees a underlying breakpoint and removes successfully.
- * 	  (via is_swbp_at_addr)
- * 	  (Subsequent uprobe_munmap wouldnt find the breakpoint
- * 	  since there is no underlying breakpoint after the
- * 	  breakpoint removal.)
- */
+static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
+				struct mm_struct *mm, unsigned long vaddr)
+{
+	int ret = 0;
+
+	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
+		return ret;
+
+	mutex_lock(&uprobe->copy_mutex);
+	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
+		goto out;
+
+	ret = copy_insn(uprobe, file);
+	if (ret)
+		goto out;
+
+	ret = -ENOTSUPP;
+	if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
+		goto out;
+
+	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
+	if (ret)
+		goto out;
+
+	/* write_opcode() assumes we don't cross page boundary */
+	BUG_ON((uprobe->offset & ~PAGE_MASK) +
+			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
+
+	smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
+
+ out:
+	mutex_unlock(&uprobe->copy_mutex);
+
+	return ret;
+}
+
 static int
 install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 			struct vm_area_struct *vma, unsigned long vaddr)
@@ -661,24 +631,9 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	if (!uprobe->consumers)
 		return 0;
 
-	if (!(uprobe->flags & UPROBE_COPY_INSN)) {
-		ret = copy_insn(uprobe, vma->vm_file);
-		if (ret)
-			return ret;
-
-		if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
-			return -ENOTSUPP;
-
-		ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
-		if (ret)
-			return ret;
-
-		/* write_opcode() assumes we don't cross page boundary */
-		BUG_ON((uprobe->offset & ~PAGE_MASK) +
-				UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
-
-		uprobe->flags |= UPROBE_COPY_INSN;
-	}
+	ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr);
+	if (ret)
+		return ret;
 
 	/*
 	 * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
@@ -697,15 +652,15 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
-static void
+static int
 remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
 	/* can happen if uprobe_register() fails */
 	if (!test_bit(MMF_HAS_UPROBES, &mm->flags))
-		return;
+		return 0;
 
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
-	set_orig_insn(&uprobe->arch, mm, vaddr);
+	return set_orig_insn(&uprobe->arch, mm, vaddr);
 }
 
 /*
@@ -820,7 +775,7 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 		struct mm_struct *mm = info->mm;
 		struct vm_area_struct *vma;
 
-		if (err)
+		if (err && is_register)
 			goto free;
 
 		down_write(&mm->mmap_sem);
@@ -836,7 +791,7 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 		if (is_register)
 			err = install_breakpoint(uprobe, mm, vma, info->vaddr);
 		else
-			remove_breakpoint(uprobe, mm, info->vaddr);
+			err |= remove_breakpoint(uprobe, mm, info->vaddr);
 
  unlock:
 		up_write(&mm->mmap_sem);
@@ -893,13 +848,15 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	mutex_lock(uprobes_hash(inode));
 	uprobe = alloc_uprobe(inode, offset);
 
-	if (uprobe && !consumer_add(uprobe, uc)) {
+	if (!uprobe) {
+		ret = -ENOMEM;
+	} else if (!consumer_add(uprobe, uc)) {
 		ret = __uprobe_register(uprobe);
 		if (ret) {
 			uprobe->consumers = NULL;
 			__uprobe_unregister(uprobe);
 		} else {
-			uprobe->flags |= UPROBE_RUN_HANDLER;
+			set_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
 		}
 	}
 
@@ -932,7 +889,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
 	if (consumer_del(uprobe, uc)) {
 		if (!uprobe->consumers) {
 			__uprobe_unregister(uprobe);
-			uprobe->flags &= ~UPROBE_RUN_HANDLER;
+			clear_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
 		}
 	}
 
@@ -1393,10 +1350,11 @@ bool uprobe_deny_signal(void)
  */
 static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
 {
-	if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
-		return true;
-
-	uprobe->flags &= ~UPROBE_SKIP_SSTEP;
+	if (test_bit(UPROBE_SKIP_SSTEP, &uprobe->flags)) {
+		if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
+			return true;
+		clear_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
+	}
 	return false;
 }
 
@@ -1419,6 +1377,30 @@ static void mmf_recalc_uprobes(struct mm_struct *mm)
 	clear_bit(MMF_HAS_UPROBES, &mm->flags);
 }
 
+static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
+{
+	struct page *page;
+	uprobe_opcode_t opcode;
+	int result;
+
+	pagefault_disable();
+	result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
+							sizeof(opcode));
+	pagefault_enable();
+
+	if (likely(result == 0))
+		goto out;
+
+	result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
+	if (result < 0)
+		return result;
+
+	copy_opcode(page, vaddr, &opcode);
+	put_page(page);
+ out:
+	return is_swbp_insn(&opcode);
+}
+
 static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 {
 	struct mm_struct *mm = current->mm;
@@ -1489,38 +1471,41 @@ static void handle_swbp(struct pt_regs *regs)
 		}
 		return;
 	}
+	/*
+	 * TODO: move copy_insn/etc into _register and remove this hack.
+	 * After we hit the bp, _unregister + _register can install the
+	 * new and not-yet-analyzed uprobe at the same address, restart.
+	 */
+	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
+	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
+		goto restart;
 
 	utask = current->utask;
 	if (!utask) {
 		utask = add_utask();
 		/* Cannot allocate; re-execute the instruction. */
 		if (!utask)
-			goto cleanup_ret;
+			goto restart;
 	}
-	utask->active_uprobe = uprobe;
+
 	handler_chain(uprobe, regs);
-	if (uprobe->flags & UPROBE_SKIP_SSTEP && can_skip_sstep(uprobe, regs))
-		goto cleanup_ret;
+	if (can_skip_sstep(uprobe, regs))
+		goto out;
 
-	utask->state = UTASK_SSTEP;
 	if (!pre_ssout(uprobe, regs, bp_vaddr)) {
 		arch_uprobe_enable_step(&uprobe->arch);
+		utask->active_uprobe = uprobe;
+		utask->state = UTASK_SSTEP;
 		return;
 	}
 
-cleanup_ret:
-	if (utask) {
-		utask->active_uprobe = NULL;
-		utask->state = UTASK_RUNNING;
-	}
-	if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
-
-		/*
-		 * cannot singlestep; cannot skip instruction;
-		 * re-execute the instruction.
-		 */
-		instruction_pointer_set(regs, bp_vaddr);
-
+restart:
+	/*
+	 * cannot singlestep; cannot skip instruction;
+	 * re-execute the instruction.
+	 */
+	instruction_pointer_set(regs, bp_vaddr);
+out:
 	put_uprobe(uprobe);
 }
 
@@ -1552,13 +1537,12 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 }
 
 /*
- * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag.  (and on
- * subsequent probe hits on the thread sets the state to UTASK_BP_HIT) and
- * allows the thread to return from interrupt.
+ * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and
+ * allows the thread to return from interrupt. After that handle_swbp()
+ * sets utask->active_uprobe.
  *
- * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag and
- * also sets the state to UTASK_SSTEP_ACK and allows the thread to return from
- * interrupt.
+ * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag
+ * and allows the thread to return from interrupt.
  *
  * While returning to userspace, thread notices the TIF_UPROBE flag and calls
  * uprobe_notify_resume().
@@ -1567,11 +1551,13 @@ void uprobe_notify_resume(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
 
+	clear_thread_flag(TIF_UPROBE);
+
 	utask = current->utask;
-	if (!utask || utask->state == UTASK_BP_HIT)
-		handle_swbp(regs);
-	else
+	if (utask && utask->active_uprobe)
 		handle_singlestep(utask, regs);
+	else
+		handle_swbp(regs);
 }
 
 /*
@@ -1580,17 +1566,10 @@ void uprobe_notify_resume(struct pt_regs *regs)
  */
 int uprobe_pre_sstep_notifier(struct pt_regs *regs)
 {
-	struct uprobe_task *utask;
-
 	if (!current->mm || !test_bit(MMF_HAS_UPROBES, &current->mm->flags))
 		return 0;
 
-	utask = current->utask;
-	if (utask)
-		utask->state = UTASK_BP_HIT;
-
 	set_thread_flag(TIF_UPROBE);
-
 	return 1;
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b32ed0e..b979426 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1567,6 +1567,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 
 		put_online_cpus();
 	} else {
+		/* Make sure this CPU has been intitialized */
+		if (!cpumask_test_cpu(cpu_id, buffer->cpumask))
+			goto out;
+
 		cpu_buffer = buffer->buffers[cpu_id];
 
 		if (nr_pages == cpu_buffer->nr_pages)


^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-10-20  0:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-10-20  0:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 45bff41a9a6f22af28e4ba22f83c87f619e573a8 perf python: Properly link with libtraceevent

Assorted small fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf python: Initialize 'page_size' variable
      perf python: Link with libtraceevent
      perf hists browser: Add back callchain folding symbol
      perf python: Properly link with libtraceevent

David Ahern (1):
      perf tool: Precise mode requires exclude_guest

David Miller (1):
      perf tools: Fix build on sparc.

Namhyung Kim (3):
      perf tools: Fix segfault when using srcline sort key
      perf tools: Remove warnings on JIT samples for srcline sort key
      perf hists browser: Fix off-by-two bug on the first column

Peter Zijlstra (1):
      perf: Require exclude_guest to use PEBS - kernel side enforcement

Steven Rostedt (2):
      lib tools traceevent: Add back pevent assignment in __pevent_parse_format()
      tools lib traceevent: Fix missed freeing of subargs in free_arg() in filter


 arch/x86/kernel/cpu/perf_event.c    |  6 ++++++
 tools/lib/traceevent/event-parse.c  |  9 ++++++---
 tools/lib/traceevent/parse-filter.c | 15 +++++++++++++++
 tools/perf/Makefile                 | 24 +++++++++++++-----------
 tools/perf/perf.h                   |  2 +-
 tools/perf/ui/browsers/hists.c      |  6 ++++--
 tools/perf/util/parse-events.c      |  3 +++
 tools/perf/util/setup.py            |  2 ++
 tools/perf/util/sort.c              |  6 ++++++
 9 files changed, 56 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 915b876..3373f84 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -338,6 +338,9 @@ int x86_setup_perfctr(struct perf_event *event)
 		/* BTS is currently only allowed for user-mode. */
 		if (!attr->exclude_kernel)
 			return -EOPNOTSUPP;
+
+		if (!attr->exclude_guest)
+			return -EOPNOTSUPP;
 	}
 
 	hwc->config |= config;
@@ -380,6 +383,9 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.precise_ip) {
 		int precise = 0;
 
+		if (!event->attr.exclude_guest)
+			return -EOPNOTSUPP;
+
 		/* Support for constant skid */
 		if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
 			precise++;
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 47264b4..f2989c5 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2602,6 +2602,9 @@ find_func_handler(struct pevent *pevent, char *func_name)
 {
 	struct pevent_function_handler *func;
 
+	if (!pevent)
+		return NULL;
+
 	for (func = pevent->func_handlers; func; func = func->next) {
 		if (strcmp(func->name, func_name) == 0)
 			break;
@@ -4938,6 +4941,9 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
 		goto event_alloc_failed;
 	}
 
+	/* Add pevent to event so that it can be referenced */
+	event->pevent = pevent;
+
 	ret = event_read_format(event);
 	if (ret < 0) {
 		ret = PEVENT_ERRNO__READ_FORMAT_FAILED;
@@ -5041,9 +5047,6 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 	if (event == NULL)
 		return ret;
 
-	/* Add pevent to event so that it can be referenced */
-	event->pevent = pevent;
-
 	if (add_event(pevent, event)) {
 		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
 		goto event_add_failed;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index ad17855..5ea4326 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -209,7 +209,16 @@ static void free_arg(struct filter_arg *arg)
 	switch (arg->type) {
 	case FILTER_ARG_NONE:
 	case FILTER_ARG_BOOLEAN:
+		break;
+
 	case FILTER_ARG_NUM:
+		free_arg(arg->num.left);
+		free_arg(arg->num.right);
+		break;
+
+	case FILTER_ARG_EXP:
+		free_arg(arg->exp.left);
+		free_arg(arg->exp.right);
 		break;
 
 	case FILTER_ARG_STR:
@@ -218,6 +227,12 @@ static void free_arg(struct filter_arg *arg)
 		free(arg->str.buffer);
 		break;
 
+	case FILTER_ARG_VALUE:
+		if (arg->value.type == FILTER_STRING ||
+		    arg->value.type == FILTER_CHAR)
+			free(arg->value.str);
+		break;
+
 	case FILTER_ARG_OP:
 		free_arg(arg->op.left);
 		free_arg(arg->op.right);
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index f7c968a..00deed4d 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -184,9 +184,22 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
+TRACE_EVENT_DIR = ../lib/traceevent/
+
+ifneq ($(OUTPUT),)
+	TE_PATH=$(OUTPUT)
+else
+	TE_PATH=$(TRACE_EVENT_DIR)
+endif
+
+LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
+TE_LIB := -L$(TE_PATH) -ltraceevent
+
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
 
+export LIBTRACEEVENT
+
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
@@ -198,17 +211,6 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
-TRACE_EVENT_DIR = ../lib/traceevent/
-
-ifneq ($(OUTPUT),)
-	TE_PATH=$(OUTPUT)
-else
-	TE_PATH=$(TRACE_EVENT_DIR)
-endif
-
-LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
-TE_LIB := -L$(TE_PATH) -ltraceevent
-
 #
 # Single 'perf' binary right now:
 #
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2762877..c50985e 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -57,7 +57,7 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __sparc__
-#include "../../arch/sparc/include/asm/unistd.h"
+#include "../../arch/sparc/include/uapi/asm/unistd.h"
 #define rmb()		asm volatile("":::"memory")
 #define cpu_relax()	asm volatile("":::"memory")
 #define CPUINFO_PROC	"cpu"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 0568536..ef2f93c 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -610,6 +610,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	char folded_sign = ' ';
 	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
 	off_t row_offset = entry->row_offset;
+	bool first = true;
 
 	if (current_entry) {
 		browser->he_selection = entry;
@@ -633,10 +634,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			if (!perf_hpp__format[i].cond)
 				continue;
 
-			if (i) {
+			if (!first) {
 				slsmg_printf("  ");
 				width -= 2;
 			}
+			first = false;
 
 			if (perf_hpp__format[i].color) {
 				hpp.ptr = &percent;
@@ -645,7 +647,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 
 				ui_browser__set_percent_color(&browser->b, percent, current_entry);
 
-				if (i == 0 && symbol_conf.use_callchain) {
+				if (i == PERF_HPP__OVERHEAD && symbol_conf.use_callchain) {
 					slsmg_printf("%c ", folded_sign);
 					width -= 2;
 				}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index aed38e4..75c7b0f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -690,6 +690,9 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 			eH = 0;
 		} else if (*str == 'p') {
 			precise++;
+			/* use of precise requires exclude_guest */
+			if (!exclude_GH)
+				eG = 1;
 		} else
 			break;
 
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index d0f9f29..73d5102 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -23,6 +23,7 @@ cflags += getenv('CFLAGS', '').split()
 
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
+libtraceevent = getenv('LIBTRACEEVENT')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -31,6 +32,7 @@ perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
+		  extra_objects = [libtraceevent],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b5b1b92..cfd1c0f 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -260,6 +260,12 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 	if (path != NULL)
 		goto out_path;
 
+	if (!self->ms.map)
+		goto out_ip;
+
+	if (!strncmp(self->ms.map->dso->long_name, "/tmp/perf-", 10))
+		goto out_ip;
+
 	snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64,
 		 self->ms.map->dso->long_name, self->ip);
 	fp = popen(cmd, "r");

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-09-21 19:08 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-09-21 19:08 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 85f2a2ef1d0ab99523e0b947a2b723f5650ed6aa tracing: Don't call page_to_pfn() if page is NULL

Small perf fixlets.

 Thanks,

	Ingo

------------------>
Robert Richter (1):
      perf/x86/ibs: Check syscall attribute flags

Stephane Eranian (2):
      perf/x86: Export Sandy Bridge uncore clockticks event in sysfs
      perf/x86: Fix Intel Ivy Bridge support

Wen Congyang (1):
      tracing: Don't call page_to_pfn() if page is NULL


 arch/x86/kernel/cpu/perf_event.h              |  2 ++
 arch/x86/kernel/cpu/perf_event_amd_ibs.c      | 12 ++++++++++++
 arch/x86/kernel/cpu/perf_event_intel.c        | 24 +++++++++++++++++++++++-
 arch/x86/kernel/cpu/perf_event_intel_ds.c     | 14 ++++++++++++++
 arch/x86/kernel/cpu/perf_event_intel_uncore.c |  6 ++++++
 include/linux/perf_event.h                    |  2 ++
 include/trace/events/kmem.h                   |  4 ++--
 7 files changed, 61 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6605a81..8b6defe 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[];
 
 extern struct event_constraint intel_snb_pebs_event_constraints[];
 
+extern struct event_constraint intel_ivb_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 7bfb5be..eebd5ff 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -209,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
 	return -EOPNOTSUPP;
 }
 
+static const struct perf_event_attr ibs_notsupp = {
+	.exclude_user	= 1,
+	.exclude_kernel	= 1,
+	.exclude_hv	= 1,
+	.exclude_idle	= 1,
+	.exclude_host	= 1,
+	.exclude_guest	= 1,
+};
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -229,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event)
 	if (event->pmu != &perf_ibs->pmu)
 		return -ENOENT;
 
+	if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
+		return -EINVAL;
+
 	if (config & ~perf_ibs->config_mask)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0d3d63a..6bca492 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2048,7 +2048,6 @@ __init int intel_pmu_init(void)
 	case 42: /* SandyBridge */
 	case 45: /* SandyBridge, "Romely-EP" */
 		x86_add_quirk(intel_sandybridge_quirk);
-	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
@@ -2073,6 +2072,29 @@ __init int intel_pmu_init(void)
 
 		pr_cont("SandyBridge events, ");
 		break;
+	case 58: /* IvyBridge */
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_snb_event_constraints;
+		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		x86_pmu.extra_regs = intel_snb_extra_regs;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+
+		pr_cont("IvyBridge events, ");
+		break;
+
 
 	default:
 		switch (x86_pmu.version) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index e38d97b..826054a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_ivb_pebs_event_constraints[] = {
+        INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+        INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+        INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+        INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+        EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0a55710..38e4894 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static struct uncore_event_desc snb_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+	{ /* end: all zeroes */ },
+};
+
 static struct attribute *snb_uncore_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = {
 	.constraints	= snb_uncore_cbox_constraints,
 	.ops		= &snb_uncore_msr_ops,
 	.format_group	= &snb_uncore_format_group,
+	.event_descs	= snb_uncore_events,
 };
 
 static struct intel_uncore_type *snb_msr_uncores[] = {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 33ed9d6..bdb4161 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -274,6 +274,8 @@ struct perf_event_attr {
 	__u64	branch_sample_type; /* enum branch_sample_type */
 };
 
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
 /*
  * Ioctls that can be done on a perf event fd:
  */
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 5f889f1..08fa272 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -214,7 +214,7 @@ TRACE_EVENT(mm_page_alloc,
 
 	TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s",
 		__entry->page,
-		page_to_pfn(__entry->page),
+		__entry->page ? page_to_pfn(__entry->page) : 0,
 		__entry->order,
 		__entry->migratetype,
 		show_gfp_flags(__entry->gfp_flags))
@@ -240,7 +240,7 @@ DECLARE_EVENT_CLASS(mm_page,
 
 	TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d",
 		__entry->page,
-		page_to_pfn(__entry->page),
+		__entry->page ? page_to_pfn(__entry->page) : 0,
 		__entry->order,
 		__entry->migratetype,
 		__entry->order == 0)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-09-13 14:39 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-09-13 14:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: e4390fa632d7c592e68e8106b7daea923ac995f5 Merge branch 'urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile into perf/urgent

This tree includes various fixes.

 Thanks,

	Ingo

------------------>
Al Viro (1):
      perf_event: Switch to internal refcount, fix race with close()

K.Prasad (1):
      perf/hwpb: Invoke __perf_event_disable() if interrupts are already disabled

Robert Richter (1):
      oprofile, s390: Fix uninitialized memory access when writing to oprofilefs

Stephane Eranian (2):
      perf/x86: Fix microcode revision check for SNB-PEBS
      perf/x86: Enable Intel Cedarview Atom suppport


 arch/s390/oprofile/init.c                  | 10 ++---
 arch/x86/kernel/cpu/perf_event_intel.c     |  1 +
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |  3 +-
 arch/x86/kernel/microcode_core.c           |  3 ++
 include/linux/perf_event.h                 |  4 +-
 kernel/events/core.c                       | 64 ++++++++++++++++--------------
 kernel/events/hw_breakpoint.c              | 11 ++++-
 7 files changed, 58 insertions(+), 38 deletions(-)

diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index a1e9d69..584b936 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -169,7 +169,7 @@ static ssize_t hw_interval_write(struct file *file, char const __user *buf,
 	if (*offset)
 		return -EINVAL;
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val < oprofile_min_interval)
 		oprofile_hw_interval = oprofile_min_interval;
@@ -212,7 +212,7 @@ static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val != 0)
 		return -EINVAL;
@@ -243,7 +243,7 @@ static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -278,7 +278,7 @@ static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -317,7 +317,7 @@ static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e..0d3d63a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 28: /* Atom */
+	case 54: /* Cedariew */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b426..da02e9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
 	 * to have an operational LBR which can freeze
 	 * on PMU interrupt
 	 */
-	if (boot_cpu_data.x86_mask < 10) {
+	if (boot_cpu_data.x86_model == 28
+	    && boot_cpu_data.x86_mask < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62..9e5bcf1 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
+	if (ret > 0)
+		perf_check_microcode();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7602ccb..33ed9d6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -926,7 +926,7 @@ struct perf_event {
 	struct hw_perf_event		hw;
 
 	struct perf_event_context	*ctx;
-	struct file			*filp;
+	atomic_long_t			refcount;
 
 	/*
 	 * These accumulate total time (in nanoseconds) that children
@@ -1296,6 +1296,7 @@ extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
+extern int __perf_event_disable(void *info);
 extern void perf_event_task_tick(void);
 #else
 static inline void
@@ -1334,6 +1335,7 @@ static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
 static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
+static inline int __perf_event_disable(void *info)			{ return -1; }
 static inline void perf_event_task_tick(void)				{ }
 #endif
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b7935fc..7fee567 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1253,7 +1253,7 @@ retry:
 /*
  * Cross CPU call to disable a performance event
  */
-static int __perf_event_disable(void *info)
+int __perf_event_disable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -2935,12 +2935,12 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 /*
  * Called when the last reference to the file is gone.
  */
-static int perf_release(struct inode *inode, struct file *file)
+static void put_event(struct perf_event *event)
 {
-	struct perf_event *event = file->private_data;
 	struct task_struct *owner;
 
-	file->private_data = NULL;
+	if (!atomic_long_dec_and_test(&event->refcount))
+		return;
 
 	rcu_read_lock();
 	owner = ACCESS_ONCE(event->owner);
@@ -2975,7 +2975,13 @@ static int perf_release(struct inode *inode, struct file *file)
 		put_task_struct(owner);
 	}
 
-	return perf_event_release_kernel(event);
+	perf_event_release_kernel(event);
+}
+
+static int perf_release(struct inode *inode, struct file *file)
+{
+	put_event(file->private_data);
+	return 0;
 }
 
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
@@ -3227,7 +3233,7 @@ unlock:
 
 static const struct file_operations perf_fops;
 
-static struct perf_event *perf_fget_light(int fd, int *fput_needed)
+static struct file *perf_fget_light(int fd, int *fput_needed)
 {
 	struct file *file;
 
@@ -3241,7 +3247,7 @@ static struct perf_event *perf_fget_light(int fd, int *fput_needed)
 		return ERR_PTR(-EBADF);
 	}
 
-	return file->private_data;
+	return file;
 }
 
 static int perf_event_set_output(struct perf_event *event,
@@ -3273,19 +3279,21 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
 	{
+		struct file *output_file = NULL;
 		struct perf_event *output_event = NULL;
 		int fput_needed = 0;
 		int ret;
 
 		if (arg != -1) {
-			output_event = perf_fget_light(arg, &fput_needed);
-			if (IS_ERR(output_event))
-				return PTR_ERR(output_event);
+			output_file = perf_fget_light(arg, &fput_needed);
+			if (IS_ERR(output_file))
+				return PTR_ERR(output_file);
+			output_event = output_file->private_data;
 		}
 
 		ret = perf_event_set_output(event, output_event);
 		if (output_event)
-			fput_light(output_event->filp, fput_needed);
+			fput_light(output_file, fput_needed);
 
 		return ret;
 	}
@@ -5950,6 +5958,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	mutex_init(&event->mmap_mutex);
 
+	atomic_long_set(&event->refcount, 1);
 	event->cpu		= cpu;
 	event->attr		= *attr;
 	event->group_leader	= group_leader;
@@ -6260,12 +6269,12 @@ SYSCALL_DEFINE5(perf_event_open,
 		return event_fd;
 
 	if (group_fd != -1) {
-		group_leader = perf_fget_light(group_fd, &fput_needed);
-		if (IS_ERR(group_leader)) {
-			err = PTR_ERR(group_leader);
+		group_file = perf_fget_light(group_fd, &fput_needed);
+		if (IS_ERR(group_file)) {
+			err = PTR_ERR(group_file);
 			goto err_fd;
 		}
-		group_file = group_leader->filp;
+		group_leader = group_file->private_data;
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
 		if (flags & PERF_FLAG_FD_NO_GROUP)
@@ -6402,7 +6411,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		put_ctx(gctx);
 	}
 
-	event->filp = event_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 
@@ -6496,7 +6504,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err_free;
 	}
 
-	event->filp = NULL;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 	perf_install_in_context(ctx, event, cpu);
@@ -6578,7 +6585,7 @@ static void sync_child_event(struct perf_event *child_event,
 	 * Release the parent event, if this was the last
 	 * reference to it.
 	 */
-	fput(parent_event->filp);
+	put_event(parent_event);
 }
 
 static void
@@ -6654,9 +6661,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 *
 	 *   __perf_event_exit_task()
 	 *     sync_child_event()
-	 *       fput(parent_event->filp)
-	 *         perf_release()
-	 *           mutex_lock(&ctx->mutex)
+	 *       put_event()
+	 *         mutex_lock(&ctx->mutex)
 	 *
 	 * But since its the parent context it won't be the same instance.
 	 */
@@ -6724,7 +6730,7 @@ static void perf_free_event(struct perf_event *event,
 	list_del_init(&event->child_list);
 	mutex_unlock(&parent->child_mutex);
 
-	fput(parent->filp);
+	put_event(parent);
 
 	perf_group_detach(event);
 	list_del_event(event, ctx);
@@ -6804,6 +6810,12 @@ inherit_event(struct perf_event *parent_event,
 				           NULL, NULL);
 	if (IS_ERR(child_event))
 		return child_event;
+
+	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+		free_event(child_event);
+		return NULL;
+	}
+
 	get_ctx(child_ctx);
 
 	/*
@@ -6845,14 +6857,6 @@ inherit_event(struct perf_event *parent_event,
 	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
 
 	/*
-	 * Get a reference to the parent filp - we will fput it
-	 * when the child event exits. This is safe to do because
-	 * we are in the parent and we know that the filp still
-	 * exists and has a nonzero count:
-	 */
-	atomic_long_inc(&parent_event->filp->f_count);
-
-	/*
 	 * Link this into the parent event's child list
 	 */
 	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index bb38c4d..9a7b487 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -453,7 +453,16 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	int old_type = bp->attr.bp_type;
 	int err = 0;
 
-	perf_event_disable(bp);
+	/*
+	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
+	 * will not be possible to raise IPIs that invoke __perf_event_disable.
+	 * So call the function directly after making sure we are targeting the
+	 * current task.
+	 */
+	if (irqs_disabled() && bp->ctx && bp->ctx->task == current)
+		__perf_event_disable(bp);
+	else
+		perf_event_disable(bp);
 
 	bp->attr.bp_addr = attr->bp_addr;
 	bp->attr.bp_type = attr->bp_type;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-08-23 10:59 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-08-23 10:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: f5042d037544215de530a375431c3fca60140823 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

This tree contains misc fixlets: a perf script python binding 
fix, a uprobes fix and a syscall tracing fix.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf tools: Add missing files to build the python binding

Oleg Nesterov (1):
      uprobes: Fix mmap_region()'s mm->mm_rb corruption if uprobe_mmap() fails

Will Deacon (1):
      tracing/syscalls: Fix perf syscall tracing when syscall_nr == -1


 kernel/fork.c                      | 4 ++--
 kernel/trace/trace_syscalls.c      | 4 ++++
 mm/mmap.c                          | 5 ++---
 tools/perf/util/python-ext-sources | 2 ++
 4 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 3bd2280..2c8857e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -455,8 +455,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (retval)
 			goto out;
 
-		if (file && uprobe_mmap(tmp))
-			goto out;
+		if (file)
+			uprobe_mmap(tmp);
 	}
 	/* a new mm has just been created */
 	arch_dup_mmap(oldmm, mm);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 60e4d78..6b245f64 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -506,6 +506,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
 
@@ -580,6 +582,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index e3e8691..52e08fc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1356,9 +1356,8 @@ out:
 	} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
 		make_pages_present(addr, addr + len);
 
-	if (file && uprobe_mmap(vma))
-		/* matching probes but cannot insert */
-		goto unmap_and_free_vma;
+	if (file)
+		uprobe_mmap(vma);
 
 	return addr;
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 2884e67..2133628 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,10 +10,12 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
 util/cgroup.c
 util/debugfs.c
+util/rblist.c
 util/strlist.c
 ../../lib/rbtree.c

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-08-20  9:08 Ingo Molnar
@ 2012-08-21  7:59 ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-08-21  7:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton


* Ingo Molnar <mingo@kernel.org> wrote:

> Linus,
> 
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
> 
>    HEAD: 26a4f3c08de49c1437a7b7f97693cf22d8c31656 perf/x86: disable PEBS on a guest entry.

The missing description:

Small fixes for merge window fallout, plus a (smallish)
hw-enablement patch for the new uncore PMU driver,
enabling Intel Westmere-EX support.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-08-20  9:08 Ingo Molnar
  2012-08-21  7:59 ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2012-08-20  9:08 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 26a4f3c08de49c1437a7b7f97693cf22d8c31656 perf/x86: disable PEBS on a guest entry.

 Thanks,

	Ingo

------------------>
Borislav Petkov (1):
      perf, x86: Fix uncore_types_exit section mismatch

Gleb Natapov (1):
      perf/x86: disable PEBS on a guest entry.

Yan, Zheng (2):
      perf/x86: Fixes for Nehalem-EX uncore driver
      perf/x86: Add Intel Westmere-EX uncore support


 arch/x86/kernel/cpu/perf_event_intel.c        |  10 +-
 arch/x86/kernel/cpu/perf_event_intel_uncore.c | 253 ++++++++++++++------------
 arch/x86/kernel/cpu/perf_event_intel_uncore.h |  46 +++--
 3 files changed, 165 insertions(+), 144 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3823669..7f2739e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1522,8 +1522,16 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
 	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
 	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+	/*
+	 * If PMU counter has PEBS enabled it is not enough to disable counter
+	 * on a guest entry since PEBS memory write can overshoot guest entry
+	 * and corrupt guest memory. Disabling PEBS solves the problem.
+	 */
+	arr[1].msr = MSR_IA32_PEBS_ENABLE;
+	arr[1].host = cpuc->pebs_enabled;
+	arr[1].guest = 0;
 
-	*nr = 1;
+	*nr = 2;
 	return arr;
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 7563fda..0a55710 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -796,7 +796,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = {
 
 DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
 DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
-DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63");
 DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
 
@@ -902,16 +901,21 @@ static struct attribute_group nhmex_uncore_cbox_format_group = {
 	.attrs = nhmex_uncore_cbox_formats_attr,
 };
 
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
 static struct intel_uncore_type nhmex_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 6,
-	.num_boxes		= 8,
+	.num_boxes		= 10,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
 	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
 	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
 	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_C_MSR_OFFSET,
+	.msr_offsets		= nhmex_cbox_msr_offsets,
 	.pair_ctr_ctl		= 1,
 	.ops			= &nhmex_uncore_ops,
 	.format_group		= &nhmex_uncore_cbox_format_group
@@ -1032,24 +1036,22 @@ static struct intel_uncore_type nhmex_uncore_bbox = {
 
 static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
-	if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) {
-		reg1->config = event->attr.config1;
-		reg2->config = event->attr.config2;
-	} else {
-		reg1->config = ~0ULL;
-		reg2->config = ~0ULL;
-	}
+	/* only TO_R_PROG_EV event uses the match/mask register */
+	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+	    NHMEX_S_EVENT_TO_R_PROG_EV)
+		return 0;
 
 	if (box->pmu->pmu_idx == 0)
 		reg1->reg = NHMEX_S0_MSR_MM_CFG;
 	else
 		reg1->reg = NHMEX_S1_MSR_MM_CFG;
-
 	reg1->idx = 0;
-
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
 	return 0;
 }
 
@@ -1059,8 +1061,8 @@ static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
-	wrmsrl(reg1->reg, 0);
-	if (reg1->config != ~0ULL || reg2->config != ~0ULL) {
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, 0);
 		wrmsrl(reg1->reg + 1, reg1->config);
 		wrmsrl(reg1->reg + 2, reg2->config);
 		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
@@ -1074,7 +1076,6 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
 	&format_attr_thresh8.attr,
-	&format_attr_mm_cfg.attr,
 	&format_attr_match.attr,
 	&format_attr_mask.attr,
 	NULL,
@@ -1142,6 +1143,9 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
 	EVENT_EXTRA_END
 };
 
+/* Nehalem-EX or Westmere-EX ? */
+bool uncore_nhmex;
+
 static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
 {
 	struct intel_uncore_extra_reg *er;
@@ -1171,18 +1175,29 @@ static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64
 		return false;
 
 	/* mask of the shared fields */
-	mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	if (uncore_nhmex)
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	else
+		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
 	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
 
 	raw_spin_lock_irqsave(&er->lock, flags);
 	/* add mask of the non-shared field if it's in use */
-	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8))
-		mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+		if (uncore_nhmex)
+			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	}
 
 	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
 		atomic_add(1 << (idx * 8), &er->ref);
-		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
-			NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		if (uncore_nhmex)
+			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
 		er->config &= ~mask;
 		er->config |= (config & mask);
 		ret = true;
@@ -1216,7 +1231,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
 
 	/* get the non-shared control bits and shift them */
 	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (uncore_nhmex)
+		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	else
+		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
 	if (new_idx > orig_idx) {
 		idx = new_idx - orig_idx;
 		config <<= 3 * idx;
@@ -1226,6 +1244,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
 	}
 
 	/* add the shared control bits back */
+	if (uncore_nhmex)
+		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	else
+		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
 	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
 	if (modify) {
 		/* adjust the main event selector */
@@ -1264,7 +1286,8 @@ again:
 	}
 
 	/* for the match/mask registers */
-	if ((uncore_box_is_fake(box) || !reg2->alloc) &&
+	if (reg2->idx != EXTRA_REG_NONE &&
+	    (uncore_box_is_fake(box) || !reg2->alloc) &&
 	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
 		goto fail;
 
@@ -1278,7 +1301,8 @@ again:
 		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
 			nhmex_mbox_alter_er(event, idx[0], true);
 		reg1->alloc |= alloc;
-		reg2->alloc = 1;
+		if (reg2->idx != EXTRA_REG_NONE)
+			reg2->alloc = 1;
 	}
 	return NULL;
 fail:
@@ -1342,9 +1366,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	struct extra_reg *er;
 	unsigned msr;
 	int reg_idx = 0;
-
-	if (WARN_ON_ONCE(reg1->idx != -1))
-		return -EINVAL;
 	/*
 	 * The mbox events may require 2 extra MSRs at the most. But only
 	 * the lower 32 bits in these MSRs are significant, so we can use
@@ -1355,11 +1376,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
-		if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) ||
-		    er->idx == __BITS_VALUE(reg1->idx, 1, 8))
-			continue;
-		if (WARN_ON_ONCE(reg_idx >= 2))
-			return -EINVAL;
 
 		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
 		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
@@ -1368,6 +1384,8 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 		/* always use the 32~63 bits to pass the PLD config */
 		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
 			reg_idx = 1;
+		else if (WARN_ON_ONCE(reg_idx > 0))
+			return -EINVAL;
 
 		reg1->idx &= ~(0xff << (reg_idx * 8));
 		reg1->reg &= ~(0xffff << (reg_idx * 16));
@@ -1376,17 +1394,21 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event
 		reg1->config = event->attr.config1;
 		reg_idx++;
 	}
-	/* use config2 to pass the filter config */
-	reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
-	if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
-		reg2->config = event->attr.config2;
-	else
-		reg2->config = ~0ULL;
-	if (box->pmu->pmu_idx == 0)
-		reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
-	else
-		reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
-
+	/*
+	 * The mbox only provides ability to perform address matching
+	 * for the PLD events.
+	 */
+	if (reg_idx == 2) {
+		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+			reg2->config = event->attr.config2;
+		else
+			reg2->config = ~0ULL;
+		if (box->pmu->pmu_idx == 0)
+			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+		else
+			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+	}
 	return 0;
 }
 
@@ -1422,34 +1444,36 @@ static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct per
 		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
 			nhmex_mbox_shared_reg_config(box, idx));
 
-	wrmsrl(reg2->reg, 0);
-	if (reg2->config != ~0ULL) {
-		wrmsrl(reg2->reg + 1,
-			reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
-		wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
-			(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
-		wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+	if (reg2->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg2->reg, 0);
+		if (reg2->config != ~0ULL) {
+			wrmsrl(reg2->reg + 1,
+				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+		}
 	}
 
 	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
 }
 
-DEFINE_UNCORE_FORMAT_ATTR(count_mode,	count_mode,	"config:2-3");
-DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode,	"config:4-5");
-DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,	wrap_mode,	"config:6");
-DEFINE_UNCORE_FORMAT_ATTR(flag_mode,	flag_mode,	"config:7");
-DEFINE_UNCORE_FORMAT_ATTR(inc_sel,	inc_sel,	"config:9-13");
-DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,	set_flag_sel,	"config:19-21");
-DEFINE_UNCORE_FORMAT_ATTR(filter_cfg,	filter_cfg,	"config2:63");
-DEFINE_UNCORE_FORMAT_ATTR(filter_match,	filter_match,	"config2:0-33");
-DEFINE_UNCORE_FORMAT_ATTR(filter_mask,	filter_mask,	"config2:34-61");
-DEFINE_UNCORE_FORMAT_ATTR(dsp,		dsp,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(thr,		thr,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(fvc,		fvc,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pgt,		pgt,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(map,		map,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(iss,		iss,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pld,		pld,		"config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
 
 static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	&format_attr_count_mode.attr,
@@ -1458,7 +1482,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	&format_attr_flag_mode.attr,
 	&format_attr_inc_sel.attr,
 	&format_attr_set_flag_sel.attr,
-	&format_attr_filter_cfg.attr,
+	&format_attr_filter_cfg_en.attr,
 	&format_attr_filter_match.attr,
 	&format_attr_filter_mask.attr,
 	&format_attr_dsp.attr,
@@ -1482,6 +1506,12 @@ static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
 	{ /* end: all zeroes */ },
 };
 
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+	{ /* end: all zeroes */ },
+};
+
 static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
 	NHMEX_UNCORE_OPS_COMMON_INIT(),
 	.enable_event	= nhmex_mbox_msr_enable_event,
@@ -1513,7 +1543,7 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	int port;
 
-	/* adjust the main event selector */
+	/* adjust the main event selector and extra register index */
 	if (reg1->idx % 2) {
 		reg1->idx--;
 		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
@@ -1522,29 +1552,17 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
 	}
 
-	/* adjust address or config of extra register */
+	/* adjust extra register config */
 	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
 	switch (reg1->idx % 6) {
-	case 0:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
-		break;
-	case 1:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
-		break;
 	case 2:
-		/* the 8~15 bits to the 0~7 bits */
+		/* shift the 8~15 bits to the 0~7 bits */
 		reg1->config >>= 8;
 		break;
 	case 3:
-		/* the 0~7 bits to the 8~15 bits */
+		/* shift the 0~7 bits to the 8~15 bits */
 		reg1->config <<= 8;
 		break;
-	case 4:
-		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
-		break;
-	case 5:
-		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
-		break;
 	};
 }
 
@@ -1671,7 +1689,7 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
 	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int port, idx;
+	int idx;
 
 	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
 		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
@@ -1681,27 +1699,11 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	reg1->idx = idx;
 	reg1->config = event->attr.config1;
 
-	port = idx / 6 + box->pmu->pmu_idx * 4;
-	idx %= 6;
-	switch (idx) {
-	case 0:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
-		break;
-	case 1:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
-		break;
-	case 2:
-	case 3:
-		reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port);
-		break;
+	switch (idx % 6) {
 	case 4:
 	case 5:
-		if (idx == 4)
-			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
-		else
-			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
-		reg2->config = event->attr.config2;
 		hwc->config |= event->attr.config & (~0ULL << 32);
+		reg2->config = event->attr.config2;
 		break;
 	};
 	return 0;
@@ -1727,28 +1729,34 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx, er_idx;
+	int idx, port;
 
-	idx = reg1->idx % 6;
-	er_idx = idx;
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
+	idx = reg1->idx;
+	port = idx / 6 + box->pmu->pmu_idx * 4;
 
-	switch (idx) {
+	switch (idx % 6) {
 	case 0:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+		break;
 	case 1:
-		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
 		break;
 	case 2:
 	case 3:
-		wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx));
+		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+			nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5));
 		break;
 	case 4:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+		break;
 	case 5:
-		wrmsrl(reg1->reg, reg1->config);
-		wrmsrl(reg1->reg + 1, hwc->config >> 32);
-		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
 		break;
 	};
 
@@ -1756,8 +1764,8 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
 		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
 }
 
-DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
 DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
@@ -2303,6 +2311,7 @@ int uncore_pmu_event_init(struct perf_event *event)
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
 
 	if (event->attr.config == UNCORE_FIXED_EVENT) {
 		/* no fixed counter */
@@ -2373,7 +2382,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type)
 	type->attr_groups[1] = NULL;
 }
 
-static void uncore_types_exit(struct intel_uncore_type **types)
+static void __init uncore_types_exit(struct intel_uncore_type **types)
 {
 	int i;
 	for (i = 0; types[i]; i++)
@@ -2814,7 +2823,13 @@ static int __init uncore_cpu_init(void)
 			snbep_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snbep_msr_uncores;
 		break;
-	case 46:
+	case 46: /* Nehalem-EX */
+		uncore_nhmex = true;
+	case 47: /* Westmere-EX aka. Xeon E7 */
+		if (!uncore_nhmex)
+			nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+		if (nhmex_uncore_cbox.num_boxes > max_cores)
+			nhmex_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = nhmex_msr_uncores;
 		break;
 	default:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index c9e5dc5..5b81c18 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -230,6 +230,7 @@
 #define NHMEX_S1_MSR_MASK			0xe5a
 
 #define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV		0
 
 /* NHM-EX Mbox */
 #define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
@@ -275,18 +276,12 @@
 		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
 		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
 
-
-#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK	0x1f
-#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK	(0x7 << 5)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK	(0x7 << 8)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR	(1 << 23)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK			\
-		(NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK  |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
 #define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (11 + 3 * (n)))
 
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (12 + 3 * (n)))
+
 /*
  * use the 9~13 bits to select event If the 7th bit is not set,
  * otherwise use the 19~21 bits to select event.
@@ -368,6 +363,7 @@ struct intel_uncore_type {
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
 	unsigned pair_ctr_ctl:1;
+	unsigned *msr_offsets;
 	struct event_constraint unconstrainted;
 	struct event_constraint *constraints;
 	struct intel_uncore_pmu *pmus;
@@ -485,29 +481,31 @@ unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx)
 	return idx * 8 + box->pmu->type->perf_ctr;
 }
 
-static inline
-unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_box_offset(struct intel_uncore_box *box)
+{
+	struct intel_uncore_pmu *pmu = box->pmu;
+	return pmu->type->msr_offsets ?
+		pmu->type->msr_offsets[pmu->pmu_idx] :
+		pmu->type->msr_offset * pmu->pmu_idx;
+}
+
+static inline unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
 {
 	if (!box->pmu->type->box_ctl)
 		return 0;
-	return box->pmu->type->box_ctl +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->box_ctl + uncore_msr_box_offset(box);
 }
 
-static inline
-unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
 {
 	if (!box->pmu->type->fixed_ctl)
 		return 0;
-	return box->pmu->type->fixed_ctl +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box);
 }
 
-static inline
-unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 {
-	return box->pmu->type->fixed_ctr +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
 }
 
 static inline
@@ -515,7 +513,7 @@ unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
 	return box->pmu->type->event_ctl +
 		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+		uncore_msr_box_offset(box);
 }
 
 static inline
@@ -523,7 +521,7 @@ unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
 	return box->pmu->type->perf_ctr +
 		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+		uncore_msr_box_offset(box);
 }
 
 static inline

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-08-05 17:43 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-08-05 17:43 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 8a06bf14008fbf55a86105b8569494f4beeb8762 Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

This tree fixes:

 * Make clean brace expansion fix for some shells, from Palmer Cox

 * Warn user just once per guest kernel when not finding kernel info,
   from David Ahern

 * perf test fix from Jiri Olsa

 * Fix error handling on event creation in perf top, from David Ahern

 * Fix check on perf_target__strnerror, from Namhyung Kim

 * Save the whole cmdline, from David Ahern

There's this infrastructure change:

 * Prep work for the DWARF CFI post unwinder, so that it doesn't
   uses perf_session in lots of places, just evlist/evsel is enough.

which is a late infrastructure changes that prepare for future 
feature work - we wanted it upstream to simplify the 
fixes/development patch flows.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (7):
      perf evsel: Precalculate the sample size
      perf session: Use perf_evlist__sample_type more extensively
      perf session: Use perf_evlist__sample_id_all more extensively
      perf session: Use perf_evlist__id_hdr_size more extensively
      perf evlist: Introduce perf_evlist__parse_sample
      perf evsel: Adopt parse_sample method from perf_event
      perf session: Remove no longer used synthesize_sample method

David Ahern (7):
      perf top: Error handling for counter creation should parallel perf-record
      perf tool: Save cmdline from user in file header vs what is passed to record
      perf kvm: Use strtol for walking guestmount directory
      perf tools: Introducing rblist
      perf tools: Change strlist to use the new rblist
      perf tools: Introduce intlist
      perf kvm top: Limit guest kernel info message to once

Jiri Olsa (2):
      perf test: Fix parse events automated tests
      perf symbols: Fix array sizes for binary types arrays

Namhyung Kim (1):
      perf target: Fix check on buffer size

Palmer Cox (1):
      perf tools: Remove brace expansion from clean target


 tools/perf/Makefile                 |   7 +-
 tools/perf/builtin-record.c         |   4 +-
 tools/perf/builtin-report.c         |   5 +-
 tools/perf/builtin-test.c           |  19 ++----
 tools/perf/builtin-top.c            |  23 +++++--
 tools/perf/util/event.h             |   3 -
 tools/perf/util/evlist.c            |   7 ++
 tools/perf/util/evlist.h            |   3 +
 tools/perf/util/evsel.c             |  15 +++--
 tools/perf/util/evsel.h             |  10 +--
 tools/perf/util/header.c            |   9 +++
 tools/perf/util/intlist.c           | 101 ++++++++++++++++++++++++++++
 tools/perf/util/intlist.h           |  75 +++++++++++++++++++++
 tools/perf/util/parse-events-test.c |  12 ++--
 tools/perf/util/parse-options.c     |   3 +
 tools/perf/util/python.c            |   6 +-
 tools/perf/util/rblist.c            | 107 +++++++++++++++++++++++++++++
 tools/perf/util/rblist.h            |  47 +++++++++++++
 tools/perf/util/session.c           |  48 +++++++------
 tools/perf/util/session.h           |  24 +------
 tools/perf/util/strlist.c           | 130 ++++++++++++++----------------------
 tools/perf/util/strlist.h           |  11 +--
 tools/perf/util/symbol.c            |  14 +++-
 tools/perf/util/target.c            |   2 +-
 24 files changed, 498 insertions(+), 187 deletions(-)
 create mode 100644 tools/perf/util/intlist.c
 create mode 100644 tools/perf/util/intlist.h
 create mode 100644 tools/perf/util/rblist.c
 create mode 100644 tools/perf/util/rblist.h

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 77f124f..35655c3 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -319,6 +319,8 @@ LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
 LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
+LIB_H += util/rblist.h
+LIB_H += util/intlist.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -383,6 +385,8 @@ LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
 LIB_OBJS += $(OUTPUT)util/cgroup.o
 LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/rblist.o
+LIB_OBJS += $(OUTPUT)util/intlist.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
@@ -983,7 +987,8 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
-	$(RM) $(OUTPUT)util/*-{bison,flex}*
+	$(RM) $(OUTPUT)util/*-bison*
+	$(RM) $(OUTPUT)util/*-flex*
 	$(python-clean)
 
 .PHONY: all install clean strip $(LIBTRACEEVENT)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f5a6452..4db6e1b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -313,7 +313,7 @@ try_again:
 		}
  	}
 
-	perf_session__update_sample_type(session);
+	perf_session__set_id_hdr_size(session);
 }
 
 static int process_buildids(struct perf_record *rec)
@@ -844,8 +844,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	struct perf_record *rec = &record;
 	char errbuf[BUFSIZ];
 
-	perf_header__set_cmdline(argc, argv);
-
 	evsel_list = perf_evlist__new(NULL, NULL);
 	if (evsel_list == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 69b1c11..7c88a24 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -249,8 +249,9 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
+	u64 sample_type = perf_evlist__sample_type(self->evlist);
 
-	if (!self->fd_pipe && !(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
 			ui__error("Selected --sort parent, but no "
 				    "callchain data. Did you call "
@@ -274,7 +275,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 
 	if (sort__branch_mode == 1) {
 		if (!self->fd_pipe &&
-		    !(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
 			ui__error("Selected -b but no branch data. "
 				  "Did you call perf record without -b?\n");
 			return -1;
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index d909eb7..1d592f5 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -478,7 +478,6 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
@@ -563,8 +562,7 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
@@ -661,12 +659,12 @@ static int test__PERF_RECORD(void)
 	const char *cmd = "sleep";
 	const char *argv[] = { cmd, "1", NULL, };
 	char *bname;
-	u64 sample_type, prev_time = 0;
+	u64 prev_time = 0;
 	bool found_cmd_mmap = false,
 	     found_libc_mmap = false,
 	     found_vdso_mmap = false,
 	     found_ld_mmap = false;
-	int err = -1, errs = 0, i, wakeups = 0, sample_size;
+	int err = -1, errs = 0, i, wakeups = 0;
 	u32 cpu;
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
 
@@ -757,13 +755,6 @@ static int test__PERF_RECORD(void)
 	}
 
 	/*
-	 * We'll need these two to parse the PERF_SAMPLE_* fields in each
-	 * event.
-	 */
-	sample_type = perf_evlist__sample_type(evlist);
-	sample_size = __perf_evsel__sample_size(sample_type);
-
-	/*
 	 * Now that all is properly set up, enable the events, they will
 	 * count just on workload.pid, which will start...
 	 */
@@ -788,9 +779,7 @@ static int test__PERF_RECORD(void)
 				if (type < PERF_RECORD_MAX)
 					nr_events[type]++;
 
-				err = perf_event__parse_sample(event, sample_type,
-							       sample_size, true,
-							       &sample, false);
+				err = perf_evlist__parse_sample(evlist, event, &sample, false);
 				if (err < 0) {
 					if (verbose)
 						perf_event__fprintf(event, stderr);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 35e86c6..68cd61e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -38,6 +38,7 @@
 #include "util/cpumap.h"
 #include "util/xyarray.h"
 #include "util/sort.h"
+#include "util/intlist.h"
 
 #include "util/debug.h"
 
@@ -706,8 +707,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	int err;
 
 	if (!machine && perf_guest) {
-		pr_err("Can't find guest [%d]'s kernel information\n",
-			event->ip.pid);
+		static struct intlist *seen;
+
+		if (!seen)
+			seen = intlist__new();
+
+		if (!intlist__has_entry(seen, event->ip.pid)) {
+			pr_err("Can't find guest [%d]'s kernel information\n",
+				event->ip.pid);
+			intlist__add(seen, event->ip.pid);
+		}
 		return;
 	}
 
@@ -811,7 +820,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	int ret;
 
 	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-		ret = perf_session__parse_sample(session, event, &sample);
+		ret = perf_evlist__parse_sample(top->evlist, event, &sample, false);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
 			continue;
@@ -943,8 +952,10 @@ try_again:
 			 * based cpu-clock-tick sw counter, which
 			 * is always available even if no PMU support:
 			 */
-			if (attr->type == PERF_TYPE_HARDWARE &&
-			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			if ((err == ENOENT || err == ENXIO) &&
+			    (attr->type == PERF_TYPE_HARDWARE) &&
+			    (attr->config == PERF_COUNT_HW_CPU_CYCLES)) {
+
 				if (verbose)
 					ui__warning("Cycles event not supported,\n"
 						    "trying to fall back to cpu-clock-ticks\n");
@@ -1032,7 +1043,7 @@ static int __cmd_top(struct perf_top *top)
 					       &top->session->host_machine);
 	perf_top__start_counters(top);
 	top->session->evlist = top->evlist;
-	perf_session__update_sample_type(top->session);
+	perf_session__set_id_hdr_size(top->session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1b19728..d84870b 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -197,9 +197,6 @@ int perf_event__preprocess_sample(const union perf_event *self,
 
 const char *perf_event__name(unsigned int id);
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample, bool swapped);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3edfd34..9b38681 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -881,3 +881,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped)
+{
+	struct perf_evsel *e = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return perf_evsel__parse_sample(e, event, sample, swapped);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 40d4d3c..528c1ac 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -122,6 +122,9 @@ u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
 
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped);
+
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e817713..2eaae14 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -20,7 +20,7 @@
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
-int __perf_evsel__sample_size(u64 sample_type)
+static int __perf_evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -53,6 +53,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->attr	   = *attr;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
+	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
@@ -728,10 +729,10 @@ static bool sample_overlap(const union perf_event *event,
 	return false;
 }
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data, bool swapped)
 {
+	u64 type = evsel->attr.sample_type;
 	const u64 *array;
 
 	/*
@@ -746,14 +747,14 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	data->period = 1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
-		if (!sample_id_all)
+		if (!evsel->attr.sample_id_all)
 			return 0;
 		return perf_event__parse_id_sample(event, type, data, swapped);
 	}
 
 	array = event->sample.array;
 
-	if (sample_size + sizeof(event->header) > event->header.size)
+	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
 	if (type & PERF_SAMPLE_IP) {
@@ -895,7 +896,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[1] = sample->tid;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
@@ -930,7 +931,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[0] = sample->cpu;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val64 = bswap_64(u.val64);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 67cc503..b559929 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -65,6 +65,7 @@ struct perf_evsel {
 		void		*func;
 		void		*data;
 	} handler;
+	unsigned int		sample_size;
 	bool 			supported;
 };
 
@@ -177,13 +178,8 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-int __perf_evsel__sample_size(u64 sample_type);
-
-static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
-{
-	return __perf_evsel__sample_size(evsel->attr.sample_type);
-}
-
 void hists__init(struct hists *hists);
 
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+			     struct perf_sample *sample, bool swapped);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3a6d204..74ea3c2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -174,6 +174,15 @@ perf_header__set_cmdline(int argc, const char **argv)
 {
 	int i;
 
+	/*
+	 * If header_argv has already been set, do not override it.
+	 * This allows a command to set the cmdline, parse args and
+	 * then call another builtin function that implements a
+	 * command -- e.g, cmd_kvm calling cmd_record.
+	 */
+	if (header_argv)
+		return 0;
+
 	header_argc = (u32)argc;
 
 	/* do not include NULL termination */
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
new file mode 100644
index 0000000..fd530dc
--- /dev/null
+++ b/tools/perf/util/intlist.c
@@ -0,0 +1,101 @@
+/*
+ * Based on intlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+
+#include "intlist.h"
+
+static struct rb_node *intlist__node_new(struct rblist *rblist __used,
+					 const void *entry)
+{
+	int i = (int)((long)entry);
+	struct rb_node *rc = NULL;
+	struct int_node *node = malloc(sizeof(*node));
+
+	if (node != NULL) {
+		node->i = i;
+		rc = &node->rb_node;
+	}
+
+	return rc;
+}
+
+static void int_node__delete(struct int_node *ilist)
+{
+	free(ilist);
+}
+
+static void intlist__node_delete(struct rblist *rblist __used,
+				 struct rb_node *rb_node)
+{
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	int_node__delete(node);
+}
+
+static int intlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	int i = (int)((long)entry);
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	return node->i - i;
+}
+
+int intlist__add(struct intlist *ilist, int i)
+{
+	return rblist__add_node(&ilist->rblist, (void *)((long)i));
+}
+
+void intlist__remove(struct intlist *ilist __used, struct int_node *node)
+{
+	int_node__delete(node);
+}
+
+struct int_node *intlist__find(struct intlist *ilist, int i)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
+
+struct intlist *intlist__new(void)
+{
+	struct intlist *ilist = malloc(sizeof(*ilist));
+
+	if (ilist != NULL) {
+		rblist__init(&ilist->rblist);
+		ilist->rblist.node_cmp    = intlist__node_cmp;
+		ilist->rblist.node_new    = intlist__node_new;
+		ilist->rblist.node_delete = intlist__node_delete;
+	}
+
+	return ilist;
+}
+
+void intlist__delete(struct intlist *ilist)
+{
+	if (ilist != NULL)
+		rblist__delete(&ilist->rblist);
+}
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node;
+
+	rb_node = rblist__entry(&ilist->rblist, idx);
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
new file mode 100644
index 0000000..6d63ab9
--- /dev/null
+++ b/tools/perf/util/intlist.h
@@ -0,0 +1,75 @@
+#ifndef __PERF_INTLIST_H
+#define __PERF_INTLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+#include "rblist.h"
+
+struct int_node {
+	struct rb_node rb_node;
+	int i;
+};
+
+struct intlist {
+	struct rblist rblist;
+};
+
+struct intlist *intlist__new(void);
+void intlist__delete(struct intlist *ilist);
+
+void intlist__remove(struct intlist *ilist, struct int_node *in);
+int intlist__add(struct intlist *ilist, int i);
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx);
+struct int_node *intlist__find(struct intlist *ilist, int i);
+
+static inline bool intlist__has_entry(struct intlist *ilist, int i)
+{
+	return intlist__find(ilist, i) != NULL;
+}
+
+static inline bool intlist__empty(const struct intlist *ilist)
+{
+	return rblist__empty(&ilist->rblist);
+}
+
+static inline unsigned int intlist__nr_entries(const struct intlist *ilist)
+{
+	return rblist__nr_entries(&ilist->rblist);
+}
+
+/* For intlist iteration */
+static inline struct int_node *intlist__first(struct intlist *ilist)
+{
+	struct rb_node *rn = rb_first(&ilist->rblist.entries);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+static inline struct int_node *intlist__next(struct int_node *in)
+{
+	struct rb_node *rn;
+	if (!in)
+		return NULL;
+	rn = rb_next(&in->rb_node);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+
+/**
+ * intlist_for_each      - iterate over a intlist
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each(pos, ilist)	\
+	for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
+
+/**
+ * intlist_for_each_safe - iterate over a intlist safe against removal of
+ *                         int_node
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @n:		another &struct int_node to use as temporary storage.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each_safe(pos, n, ilist)	\
+	for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
+	     pos = n, n = intlist__next(n))
+#endif /* __PERF_INTLIST_H */
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index 1b997d2..127d648 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -13,6 +13,9 @@ do { \
 	} \
 } while (0)
 
+#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
+			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -21,8 +24,7 @@ static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
-		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
-		evsel->attr.sample_type);
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
 	return 0;
 }
@@ -37,8 +39,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 		TEST_ASSERT_VAL("wrong type",
 			PERF_TYPE_TRACEPOINT == evsel->attr.type);
 		TEST_ASSERT_VAL("wrong sample_type",
-			(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU)
-			== evsel->attr.sample_type);
+			PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 		TEST_ASSERT_VAL("wrong sample_period",
 			1 == evsel->attr.sample_period);
 	}
@@ -428,8 +429,7 @@ static int test__checkevent_list(struct perf_evlist *evlist)
 	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
-		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
-		evsel->attr.sample_type);
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 99d02aa..594f8fa 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "parse-options.h"
 #include "cache.h"
+#include "header.h"
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
@@ -413,6 +414,8 @@ int parse_options(int argc, const char **argv, const struct option *options,
 {
 	struct parse_opt_ctx_t ctx;
 
+	perf_header__set_cmdline(argc, argv);
+
 	parse_options_start(&ctx, argc, argv, flags);
 	switch (parse_options_step(&ctx, options, usagestr)) {
 	case PARSE_OPT_HELP:
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index e03b58a..0688bfb 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -797,17 +797,13 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 	event = perf_evlist__mmap_read(evlist, cpu);
 	if (event != NULL) {
-		struct perf_evsel *first;
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		first = list_entry(evlist->entries.next, struct perf_evsel, node);
-		err = perf_event__parse_sample(event, first->attr.sample_type,
-					       perf_evsel__sample_size(first),
-					       sample_id_all, &pevent->sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &pevent->sample, false);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
new file mode 100644
index 0000000..0171fb6
--- /dev/null
+++ b/tools/perf/util/rblist.c
@@ -0,0 +1,107 @@
+/*
+ * Based on strlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "rblist.h"
+
+int rblist__add_node(struct rblist *rblist, const void *new_entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL, *new_node;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, new_entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return -EEXIST;
+	}
+
+	new_node = rblist->node_new(rblist, new_entry);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	rb_link_node(new_node, parent, p);
+	rb_insert_color(new_node, &rblist->entries);
+	++rblist->nr_entries;
+
+	return 0;
+}
+
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
+{
+	rb_erase(rb_node, &rblist->entries);
+	rblist->node_delete(rblist, rb_node);
+}
+
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return parent;
+	}
+
+	return NULL;
+}
+
+void rblist__init(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		rblist->entries	 = RB_ROOT;
+		rblist->nr_entries = 0;
+	}
+
+	return;
+}
+
+void rblist__delete(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+		while (next) {
+			pos = next;
+			next = rb_next(pos);
+			rb_erase(pos, &rblist->entries);
+			rblist->node_delete(rblist, pos);
+		}
+		free(rblist);
+	}
+}
+
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx)
+{
+	struct rb_node *node;
+
+	for (node = rb_first(&rblist->entries); node; node = rb_next(node)) {
+		if (!idx--)
+			return node;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
new file mode 100644
index 0000000..6d0cae5
--- /dev/null
+++ b/tools/perf/util/rblist.h
@@ -0,0 +1,47 @@
+#ifndef __PERF_RBLIST_H
+#define __PERF_RBLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+/*
+ * create node structs of the form:
+ * struct my_node {
+ *     struct rb_node rb_node;
+ *     ... my data ...
+ * };
+ *
+ * create list structs of the form:
+ * struct mylist {
+ *     struct rblist rblist;
+ *     ... my data ...
+ * };
+ */
+
+struct rblist {
+	struct rb_root entries;
+	unsigned int   nr_entries;
+
+	int (*node_cmp)(struct rb_node *rbn, const void *entry);
+	struct rb_node *(*node_new)(struct rblist *rlist, const void *new_entry);
+	void (*node_delete)(struct rblist *rblist, struct rb_node *rb_node);
+};
+
+void rblist__init(struct rblist *rblist);
+void rblist__delete(struct rblist *rblist);
+int rblist__add_node(struct rblist *rblist, const void *new_entry);
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx);
+
+static inline bool rblist__empty(const struct rblist *rblist)
+{
+	return rblist->nr_entries == 0;
+}
+
+static inline unsigned int rblist__nr_entries(const struct rblist *rblist)
+{
+	return rblist->nr_entries;
+}
+
+#endif /* __PERF_RBLIST_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8e4f075..2437fb0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -80,14 +80,12 @@ out_close:
 	return -1;
 }
 
-void perf_session__update_sample_type(struct perf_session *self)
+void perf_session__set_id_hdr_size(struct perf_session *session)
 {
-	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = __perf_evsel__sample_size(self->sample_type);
-	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
-	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
-	self->host_machine.id_hdr_size = self->id_hdr_size;
-	machines__set_id_hdr_size(&self->machines, self->id_hdr_size);
+	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+
+	session->host_machine.id_hdr_size = id_hdr_size;
+	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -147,7 +145,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
 			goto out_delete;
-		perf_session__update_sample_type(self);
+		perf_session__set_id_hdr_size(self);
 	} else if (mode == O_WRONLY) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
@@ -158,7 +156,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !self->sample_id_all) {
+	    tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_samples = false;
 	}
@@ -673,7 +671,8 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ret = perf_session__parse_sample(s, iter->event, &sample);
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
+						s->header.needs_swap);
 		if (ret)
 			pr_err("Can't parse sample, err = %d\n", ret);
 		else
@@ -865,16 +864,18 @@ static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
+	u64 sample_type = perf_evlist__sample_type(session->evlist);
+
 	if (event->header.type != PERF_RECORD_SAMPLE &&
-	    !session->sample_id_all) {
+	    !perf_evlist__sample_id_all(session->evlist)) {
 		fputs("-1 -1 ", stdout);
 		return;
 	}
 
-	if ((session->sample_type & PERF_SAMPLE_CPU))
+	if ((sample_type & PERF_SAMPLE_CPU))
 		printf("%u ", sample->cpu);
 
-	if (session->sample_type & PERF_SAMPLE_TIME)
+	if (sample_type & PERF_SAMPLE_TIME)
 		printf("%" PRIu64 " ", sample->time);
 }
 
@@ -899,6 +900,8 @@ static void dump_event(struct perf_session *session, union perf_event *event,
 static void dump_sample(struct perf_session *session, union perf_event *event,
 			struct perf_sample *sample)
 {
+	u64 sample_type;
+
 	if (!dump_trace)
 		return;
 
@@ -906,10 +909,12 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
+	sample_type = perf_evlist__sample_type(session->evlist);
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
 
-	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 		branch_stack__printf(sample);
 }
 
@@ -1006,7 +1011,7 @@ static int perf_session__preprocess_sample(struct perf_session *session,
 					   union perf_event *event, struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+	    !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
 		return 0;
 
 	if (!ip_callchain__valid(sample->callchain, event)) {
@@ -1030,7 +1035,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(event, &session->evlist);
 		if (err == 0)
-			perf_session__update_sample_type(session);
+			perf_session__set_id_hdr_size(session);
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		return tool->event_type(tool, event);
@@ -1065,7 +1070,7 @@ static int perf_session__process_event(struct perf_session *session,
 	int ret;
 
 	if (session->header.needs_swap)
-		event_swap(event, session->sample_id_all);
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
@@ -1078,7 +1083,8 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	ret = perf_session__parse_sample(session, event, &sample);
+	ret = perf_evlist__parse_sample(session->evlist, event, &sample,
+					session->header.needs_swap);
 	if (ret)
 		return ret;
 
@@ -1389,9 +1395,9 @@ int perf_session__process_events(struct perf_session *self,
 	return err;
 }
 
-bool perf_session__has_traces(struct perf_session *self, const char *msg)
+bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(self->sample_type & PERF_SAMPLE_RAW)) {
+	if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
 		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
 		return false;
 	}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7c435bd..1f7ec87 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -41,13 +41,9 @@ struct perf_session {
 	 *	  perf.data file.
 	 */
 	struct hists		hists;
-	u64			sample_type;
-	int			sample_size;
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
-	bool			sample_id_all;
-	u16			id_hdr_size;
 	int			cwdlen;
 	char			*cwd;
 	struct ordered_samples	ordered_samples;
@@ -86,7 +82,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *self);
 
-void perf_session__update_sample_type(struct perf_session *self);
+void perf_session__set_id_hdr_size(struct perf_session *session);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
@@ -130,24 +126,6 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 
-static inline int perf_session__parse_sample(struct perf_session *session,
-					     const union perf_event *event,
-					     struct perf_sample *sample)
-{
-	return perf_event__parse_sample(event, session->sample_type,
-					session->sample_size,
-					session->sample_id_all, sample,
-					session->header.needs_swap);
-}
-
-static inline int perf_session__synthesize_sample(struct perf_session *session,
-						  union perf_event *event,
-						  const struct perf_sample *sample)
-{
-	return perf_event__synthesize_sample(event, session->sample_type,
-					     sample, session->header.needs_swap);
-}
-
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 6783a20..95856ff 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -10,23 +10,28 @@
 #include <stdlib.h>
 #include <string.h>
 
-static struct str_node *str_node__new(const char *s, bool dupstr)
+static
+struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
 {
-	struct str_node *self = malloc(sizeof(*self));
+	const char *s = entry;
+	struct rb_node *rc = NULL;
+	struct strlist *strlist = container_of(rblist, struct strlist, rblist);
+	struct str_node *snode = malloc(sizeof(*snode));
 
-	if (self != NULL) {
-		if (dupstr) {
+	if (snode != NULL) {
+		if (strlist->dupstr) {
 			s = strdup(s);
 			if (s == NULL)
 				goto out_delete;
 		}
-		self->s = s;
+		snode->s = s;
+		rc = &snode->rb_node;
 	}
 
-	return self;
+	return rc;
 
 out_delete:
-	free(self);
+	free(snode);
 	return NULL;
 }
 
@@ -37,36 +42,26 @@ static void str_node__delete(struct str_node *self, bool dupstr)
 	free(self);
 }
 
-int strlist__add(struct strlist *self, const char *new_entry)
+static
+void strlist__node_delete(struct rblist *rblist, struct rb_node *rb_node)
 {
-	struct rb_node **p = &self->entries.rb_node;
-	struct rb_node *parent = NULL;
-	struct str_node *sn;
-
-	while (*p != NULL) {
-		int rc;
-
-		parent = *p;
-		sn = rb_entry(parent, struct str_node, rb_node);
-		rc = strcmp(sn->s, new_entry);
-
-		if (rc > 0)
-			p = &(*p)->rb_left;
-		else if (rc < 0)
-			p = &(*p)->rb_right;
-		else
-			return -EEXIST;
-	}
+	struct strlist *slist = container_of(rblist, struct strlist, rblist);
+	struct str_node *snode = container_of(rb_node, struct str_node, rb_node);
 
-	sn = str_node__new(new_entry, self->dupstr);
-	if (sn == NULL)
-		return -ENOMEM;
+	str_node__delete(snode, slist->dupstr);
+}
 
-	rb_link_node(&sn->rb_node, parent, p);
-	rb_insert_color(&sn->rb_node, &self->entries);
-	++self->nr_entries;
+static int strlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	const char *str = entry;
+	struct str_node *snode = container_of(rb_node, struct str_node, rb_node);
+
+	return strcmp(snode->s, str);
+}
 
-	return 0;
+int strlist__add(struct strlist *self, const char *new_entry)
+{
+	return rblist__add_node(&self->rblist, new_entry);
 }
 
 int strlist__load(struct strlist *self, const char *filename)
@@ -96,34 +91,20 @@ out:
 	return err;
 }
 
-void strlist__remove(struct strlist *self, struct str_node *sn)
+void strlist__remove(struct strlist *slist, struct str_node *snode)
 {
-	rb_erase(&sn->rb_node, &self->entries);
-	str_node__delete(sn, self->dupstr);
+	str_node__delete(snode, slist->dupstr);
 }
 
-struct str_node *strlist__find(struct strlist *self, const char *entry)
+struct str_node *strlist__find(struct strlist *slist, const char *entry)
 {
-	struct rb_node **p = &self->entries.rb_node;
-	struct rb_node *parent = NULL;
-
-	while (*p != NULL) {
-		struct str_node *sn;
-		int rc;
-
-		parent = *p;
-		sn = rb_entry(parent, struct str_node, rb_node);
-		rc = strcmp(sn->s, entry);
-
-		if (rc > 0)
-			p = &(*p)->rb_left;
-		else if (rc < 0)
-			p = &(*p)->rb_right;
-		else
-			return sn;
-	}
+	struct str_node *snode = NULL;
+	struct rb_node *rb_node = rblist__find(&slist->rblist, entry);
 
-	return NULL;
+	if (rb_node)
+		snode = container_of(rb_node, struct str_node, rb_node);
+
+	return snode;
 }
 
 static int strlist__parse_list_entry(struct strlist *self, const char *s)
@@ -156,9 +137,12 @@ struct strlist *strlist__new(bool dupstr, const char *slist)
 	struct strlist *self = malloc(sizeof(*self));
 
 	if (self != NULL) {
-		self->entries	 = RB_ROOT;
+		rblist__init(&self->rblist);
+		self->rblist.node_cmp    = strlist__node_cmp;
+		self->rblist.node_new    = strlist__node_new;
+		self->rblist.node_delete = strlist__node_delete;
+
 		self->dupstr	 = dupstr;
-		self->nr_entries = 0;
 		if (slist && strlist__parse_list(self, slist) != 0)
 			goto out_error;
 	}
@@ -171,30 +155,18 @@ out_error:
 
 void strlist__delete(struct strlist *self)
 {
-	if (self != NULL) {
-		struct str_node *pos;
-		struct rb_node *next = rb_first(&self->entries);
-
-		while (next) {
-			pos = rb_entry(next, struct str_node, rb_node);
-			next = rb_next(&pos->rb_node);
-			strlist__remove(self, pos);
-		}
-		self->entries = RB_ROOT;
-		free(self);
-	}
+	if (self != NULL)
+		rblist__delete(&self->rblist);
 }
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx)
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx)
 {
-	struct rb_node *nd;
+	struct str_node *snode = NULL;
+	struct rb_node *rb_node;
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
-		struct str_node *pos = rb_entry(nd, struct str_node, rb_node);
+	rb_node = rblist__entry(&slist->rblist, idx);
+	if (rb_node)
+		snode = container_of(rb_node, struct str_node, rb_node);
 
-		if (!idx--)
-			return pos;
-	}
-
-	return NULL;
+	return snode;
 }
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index 3ba8390..dd9f922 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -4,14 +4,15 @@
 #include <linux/rbtree.h>
 #include <stdbool.h>
 
+#include "rblist.h"
+
 struct str_node {
 	struct rb_node rb_node;
 	const char     *s;
 };
 
 struct strlist {
-	struct rb_root entries;
-	unsigned int   nr_entries;
+	struct rblist rblist;
 	bool	       dupstr;
 };
 
@@ -32,18 +33,18 @@ static inline bool strlist__has_entry(struct strlist *self, const char *entry)
 
 static inline bool strlist__empty(const struct strlist *self)
 {
-	return self->nr_entries == 0;
+	return rblist__empty(&self->rblist);
 }
 
 static inline unsigned int strlist__nr_entries(const struct strlist *self)
 {
-	return self->nr_entries;
+	return rblist__nr_entries(&self->rblist);
 }
 
 /* For strlist iteration */
 static inline struct str_node *strlist__first(struct strlist *self)
 {
-	struct rb_node *rn = rb_first(&self->entries);
+	struct rb_node *rn = rb_first(&self->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index fdad4eee..8b63b67 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -64,7 +64,7 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
-#define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab)
+#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
 static enum dso_binary_type binary_type_data[] = {
 	DSO_BINARY_TYPE__BUILD_ID_CACHE,
@@ -72,7 +72,7 @@ static enum dso_binary_type binary_type_data[] = {
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
-#define DSO_BINARY_TYPE__DATA_CNT sizeof(binary_type_data)
+#define DSO_BINARY_TYPE__DATA_CNT ARRAY_SIZE(binary_type_data)
 
 int dso__name_len(const struct dso *dso)
 {
@@ -2875,6 +2875,7 @@ int machines__create_guest_kernel_maps(struct rb_root *machines)
 	int i, items = 0;
 	char path[PATH_MAX];
 	pid_t pid;
+	char *endp;
 
 	if (symbol_conf.default_guest_vmlinux_name ||
 	    symbol_conf.default_guest_modules ||
@@ -2891,7 +2892,14 @@ int machines__create_guest_kernel_maps(struct rb_root *machines)
 				/* Filter out . and .. */
 				continue;
 			}
-			pid = atoi(namelist[i]->d_name);
+			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
+			if ((*endp != '\0') ||
+			    (endp == namelist[i]->d_name) ||
+			    (errno == ERANGE)) {
+				pr_debug("invalid directory (%s). Skipping.\n",
+					 namelist[i]->d_name);
+				continue;
+			}
 			sprintf(path, "%s/%s/proc/kallsyms",
 				symbol_conf.guestmount,
 				namelist[i]->d_name);
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3f59c49..051eaa6 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -110,7 +110,7 @@ int perf_target__strerror(struct perf_target *target, int errnum,
 	int idx;
 	const char *msg;
 
-	BUG_ON(buflen > 0);
+	BUG_ON(buflen == 0);
 
 	if (errnum >= 0) {
 		const char *err = strerror_r(errnum, buf, buflen);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-08-03 16:40 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-08-03 16:40 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: e6dab5ffab59e910ec0e3355f4a6f29f7a7be474 perf/trace: Add ability to set a target task for events

Fix merge window fallout and fix sleep profiling (this was 
always broken, so it's not a fix for the merge window - we can 
skip this one from the head of the tree).

 Thanks,

	Ingo

------------------>
Andrew Morton (1):
      perf/x86/intel/uncore: Make UNCORE_PMU_HRTIMER_INTERVAL 64-bit

Andrew Vagin (1):
      perf/trace: Add ability to set a target task for events

Peter Zijlstra (1):
      perf/x86: Fix USER/KERNEL tagging of samples properly


 arch/x86/include/asm/perf_event.h             |   11 ++-
 arch/x86/kernel/cpu/perf_event.c              |   89 ++++++++++++++++++++++---
 arch/x86/kernel/cpu/perf_event.h              |   20 ++++++
 arch/x86/kernel/cpu/perf_event_amd_ibs.c      |    4 +-
 arch/x86/kernel/cpu/perf_event_intel_ds.c     |    7 +-
 arch/x86/kernel/cpu/perf_event_intel_uncore.h |    2 +-
 include/linux/ftrace_event.h                  |    5 +-
 include/linux/perf_event.h                    |    3 +-
 include/trace/events/sched.h                  |    4 ++
 include/trace/ftrace.h                        |    6 +-
 kernel/events/callchain.c                     |    9 ++-
 kernel/events/core.c                          |   30 ++++++++-
 kernel/events/internal.h                      |    3 +-
 kernel/trace/trace_event_perf.c               |    2 +-
 kernel/trace/trace_kprobe.c                   |    6 +-
 kernel/trace/trace_syscalls.c                 |    4 +-
 kernel/trace/trace_uprobe.c                   |    2 +-
 17 files changed, 175 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index dab3935..cb4e43b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -196,11 +196,16 @@ static inline u32 get_ibs_caps(void) { return 0; }
 extern void perf_events_lapic_init(void);
 
 /*
- * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
- * This flag is otherwise unused and ABI specified to be 0, so nobody should
- * care what we do with it.
+ * Abuse bits {3,5} of the cpu eflags register. These flags are otherwise
+ * unused and ABI specified to be 0, so nobody should care what we do with
+ * them.
+ *
+ * EXACT - the IP points to the exact instruction that triggered the
+ *         event (HW bugs exempt).
+ * VM    - original X86_VM_MASK; see set_linear_ip().
  */
 #define PERF_EFLAGS_EXACT	(1UL << 3)
+#define PERF_EFLAGS_VM		(1UL << 5)
 
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 29557aa..915b876 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -32,6 +32,8 @@
 #include <asm/smp.h>
 #include <asm/alternative.h>
 #include <asm/timer.h>
+#include <asm/desc.h>
+#include <asm/ldt.h>
 
 #include "perf_event.h"
 
@@ -1738,6 +1740,29 @@ valid_user_frame(const void __user *fp, unsigned long size)
 	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
 }
 
+static unsigned long get_segment_base(unsigned int segment)
+{
+	struct desc_struct *desc;
+	int idx = segment >> 3;
+
+	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		if (idx > LDT_ENTRIES)
+			return 0;
+
+		if (idx > current->active_mm->context.size)
+			return 0;
+
+		desc = current->active_mm->context.ldt;
+	} else {
+		if (idx > GDT_ENTRIES)
+			return 0;
+
+		desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+	}
+
+	return get_desc_base(desc + idx);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
@@ -1746,13 +1771,17 @@ static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
 	/* 32-bit process in 64-bit kernel. */
+	unsigned long ss_base, cs_base;
 	struct stack_frame_ia32 frame;
 	const void __user *fp;
 
 	if (!test_thread_flag(TIF_IA32))
 		return 0;
 
-	fp = compat_ptr(regs->bp);
+	cs_base = get_segment_base(regs->cs);
+	ss_base = get_segment_base(regs->ss);
+
+	fp = compat_ptr(ss_base + regs->bp);
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
@@ -1765,8 +1794,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
-		perf_callchain_store(entry, frame.return_address);
-		fp = compat_ptr(frame.next_frame);
+		perf_callchain_store(entry, cs_base + frame.return_address);
+		fp = compat_ptr(ss_base + frame.next_frame);
 	}
 	return 1;
 }
@@ -1789,6 +1818,12 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 	}
 
+	/*
+	 * We don't know what to do with VM86 stacks.. ignore them for now.
+	 */
+	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
+		return;
+
 	fp = (void __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
@@ -1816,16 +1851,50 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	}
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+/*
+ * Deal with code segment offsets for the various execution modes:
+ *
+ *   VM86 - the good olde 16 bit days, where the linear address is
+ *          20 bits and we use regs->ip + 0x10 * regs->cs.
+ *
+ *   IA32 - Where we need to look at GDT/LDT segment descriptor tables
+ *          to figure out what the 32bit base address is.
+ *
+ *    X32 - has TIF_X32 set, but is running in x86_64
+ *
+ * X86_64 - CS,DS,SS,ES are all zero based.
+ */
+static unsigned long code_segment_base(struct pt_regs *regs)
 {
-	unsigned long ip;
+	/*
+	 * If we are in VM86 mode, add the segment offset to convert to a
+	 * linear address.
+	 */
+	if (regs->flags & X86_VM_MASK)
+		return 0x10 * regs->cs;
+
+	/*
+	 * For IA32 we look at the GDT/LDT segment base to convert the
+	 * effective IP to a linear address.
+	 */
+#ifdef CONFIG_X86_32
+	if (user_mode(regs) && regs->cs != __USER_CS)
+		return get_segment_base(regs->cs);
+#else
+	if (test_thread_flag(TIF_IA32)) {
+		if (user_mode(regs) && regs->cs != __USER32_CS)
+			return get_segment_base(regs->cs);
+	}
+#endif
+	return 0;
+}
 
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		ip = perf_guest_cbs->get_guest_ip();
-	else
-		ip = instruction_pointer(regs);
+		return perf_guest_cbs->get_guest_ip();
 
-	return ip;
+	return regs->ip + code_segment_base(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
@@ -1838,7 +1907,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
 	} else {
-		if (!kernel_ip(regs->ip))
+		if (user_mode(regs))
 			misc |= PERF_RECORD_MISC_USER;
 		else
 			misc |= PERF_RECORD_MISC_KERNEL;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 821d53b..6605a81 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -516,6 +516,26 @@ static inline bool kernel_ip(unsigned long ip)
 #endif
 }
 
+/*
+ * Not all PMUs provide the right context information to place the reported IP
+ * into full context. Specifically segment registers are typically not
+ * supplied.
+ *
+ * Assuming the address is a linear address (it is for IBS), we fake the CS and
+ * vm86 mode using the known zero-based code segment and 'fix up' the registers
+ * to reflect this.
+ *
+ * Intel PEBS/LBR appear to typically provide the effective address, nothing
+ * much we can do about that but pray and treat it like a linear address.
+ */
+static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
+{
+	regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS;
+	if (regs->flags & X86_VM_MASK)
+		regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
+	regs->ip = ip;
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index da9bcdc..7bfb5be 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -13,6 +13,8 @@
 
 #include <asm/apic.h>
 
+#include "perf_event.h"
+
 static u32 ibs_caps;
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
@@ -536,7 +538,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 	} else {
-		instruction_pointer_set(&regs, ibs_data.regs[1]);
+		set_linear_ip(&regs, ibs_data.regs[1]);
 		regs.flags |= PERF_EFLAGS_EXACT;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 629ae0b..e38d97b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -499,7 +499,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	 * We sampled a branch insn, rewind using the LBR stack
 	 */
 	if (ip == to) {
-		regs->ip = from;
+		set_linear_ip(regs, from);
 		return 1;
 	}
 
@@ -529,7 +529,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	} while (to < ip);
 
 	if (to == ip) {
-		regs->ip = old_to;
+		set_linear_ip(regs, old_to);
 		return 1;
 	}
 
@@ -569,7 +569,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
 	 */
 	regs = *iregs;
-	regs.ip = pebs->ip;
+	regs.flags = pebs->flags;
+	set_linear_ip(&regs, pebs->ip);
 	regs.bp = pebs->bp;
 	regs.sp = pebs->sp;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index f385189..c9e5dc5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -5,7 +5,7 @@
 #include "perf_event.h"
 
 #define UNCORE_PMU_NAME_LEN		32
-#define UNCORE_PMU_HRTIMER_INTERVAL	(60 * NSEC_PER_SEC)
+#define UNCORE_PMU_HRTIMER_INTERVAL	(60LL * NSEC_PER_SEC)
 
 #define UNCORE_FIXED_EVENT		0xff
 #define UNCORE_PMC_IDX_MAX_GENERIC	8
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index af961d6..642928c 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -306,9 +306,10 @@ extern void *perf_trace_buf_prepare(int size, unsigned short type,
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-		       u64 count, struct pt_regs *regs, void *head)
+		       u64 count, struct pt_regs *regs, void *head,
+		       struct task_struct *task)
 {
-	perf_tp_event(addr, count, raw_data, size, regs, head, rctx);
+	perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task);
 }
 #endif
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 76c5c8b..7602ccb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1272,7 +1272,8 @@ static inline bool perf_paranoid_kernel(void)
 extern void perf_event_init(void);
 extern void perf_tp_event(u64 addr, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
-			  struct hlist_head *head, int rctx);
+			  struct hlist_head *head, int rctx,
+			  struct task_struct *task);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index ea7a203..5a8671e 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -73,6 +73,9 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		__entry->prio		= p->prio;
 		__entry->success	= success;
 		__entry->target_cpu	= task_cpu(p);
+	)
+	TP_perf_assign(
+		__perf_task(p);
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
@@ -325,6 +328,7 @@ DECLARE_EVENT_CLASS(sched_stat_template,
 	)
 	TP_perf_assign(
 		__perf_count(delay);
+		__perf_task(tsk);
 	),
 
 	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c6bc2fa..a763888 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -712,6 +712,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 #undef __perf_count
 #define __perf_count(c) __count = (c)
 
+#undef __perf_task
+#define __perf_task(t) __task = (t)
+
 #undef TP_perf_assign
 #define TP_perf_assign(args...) args
 
@@ -725,6 +728,7 @@ perf_trace_##call(void *__data, proto)					\
 	struct ftrace_raw_##call *entry;				\
 	struct pt_regs __regs;						\
 	u64 __addr = 0, __count = 1;					\
+	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
 	int __entry_size;						\
 	int __data_size;						\
@@ -752,7 +756,7 @@ perf_trace_##call(void *__data, proto)					\
 									\
 	head = this_cpu_ptr(event_call->perf_events);			\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, &__regs, head);				\
+		__count, &__regs, head, __task);			\
 }
 
 /*
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 6581a04..98d4597 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -153,7 +153,8 @@ put_callchain_entry(int rctx)
 	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
 }
 
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+struct perf_callchain_entry *
+perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
 	int rctx;
 	struct perf_callchain_entry *entry;
@@ -178,6 +179,12 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	}
 
 	if (regs) {
+		/*
+		 * Disallow cross-task user callchains.
+		 */
+		if (event->ctx->task && event->ctx->task != current)
+			goto exit_put;
+
 		perf_callchain_store(entry, PERF_CONTEXT_USER);
 		perf_callchain_user(entry, regs);
 	}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f1cf0ed..b7935fc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4039,7 +4039,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
-		data->callchain = perf_callchain(regs);
+		data->callchain = perf_callchain(event, regs);
 
 		if (data->callchain)
 			size += data->callchain->nr;
@@ -5209,7 +5209,8 @@ static int perf_tp_event_match(struct perf_event *event,
 }
 
 void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
-		   struct pt_regs *regs, struct hlist_head *head, int rctx)
+		   struct pt_regs *regs, struct hlist_head *head, int rctx,
+		   struct task_struct *task)
 {
 	struct perf_sample_data data;
 	struct perf_event *event;
@@ -5228,6 +5229,31 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 			perf_swevent_event(event, count, &data, regs);
 	}
 
+	/*
+	 * If we got specified a target task, also iterate its context and
+	 * deliver this event there too.
+	 */
+	if (task && task != current) {
+		struct perf_event_context *ctx;
+		struct trace_entry *entry = record;
+
+		rcu_read_lock();
+		ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]);
+		if (!ctx)
+			goto unlock;
+
+		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->attr.type != PERF_TYPE_TRACEPOINT)
+				continue;
+			if (event->attr.config != entry->type)
+				continue;
+			if (perf_tp_event_match(event, &data, regs))
+				perf_swevent_event(event, count, &data, regs);
+		}
+unlock:
+		rcu_read_unlock();
+	}
+
 	perf_swevent_put_recursion_context(rctx);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index b0b107f..a096c19 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -101,7 +101,8 @@ __output_copy(struct perf_output_handle *handle,
 }
 
 /* Callchain handling */
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+extern struct perf_callchain_entry *
+perf_callchain(struct perf_event *event, struct pt_regs *regs);
 extern int get_callchain_buffers(void);
 extern void put_callchain_buffers(void);
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index fee3752..8a6d2ee 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -281,7 +281,7 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
 
 	head = this_cpu_ptr(event_function.perf_events);
 	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
-			      1, &regs, head);
+			      1, &regs, head, NULL);
 
 #undef ENTRY_SIZE
 }
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b31d3d5..1a21170 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1002,7 +1002,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	head = this_cpu_ptr(call->perf_events);
-	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
+	perf_trace_buf_submit(entry, size, rctx,
+					entry->ip, 1, regs, head, NULL);
 }
 
 /* Kretprobe profile handler */
@@ -1033,7 +1034,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	head = this_cpu_ptr(call->perf_events);
-	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
+	perf_trace_buf_submit(entry, size, rctx,
+					entry->ret_ip, 1, regs, head, NULL);
 }
 #endif	/* CONFIG_PERF_EVENTS */
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 96fc733..60e4d78 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -532,7 +532,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 			       (unsigned long *)&rec->args);
 
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
-	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
+	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
 int perf_sysenter_enable(struct ftrace_event_call *call)
@@ -608,7 +608,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->ret = syscall_get_return_value(current, regs);
 
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
-	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
+	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
 int perf_sysexit_enable(struct ftrace_event_call *call)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 2b36ac6..03003cd 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -670,7 +670,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
 
 	head = this_cpu_ptr(call->perf_events);
-	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
+	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL);
 
  out:
 	preempt_enable();

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-07-14  7:51 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-07-14  7:51 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 25c037d64e7a0a8effb562babb2b6218829134ac Merge branch 'tip/perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent

 Thanks,

	Ingo

------------------>
David Ahern (3):
      perf script: Fix format regression due to libtraceevent merge
      perf kvm: Fix regression with guest machine creation
      perf kvm: Fix segfault with report and mixed guestmount use

Vaibhav Nagarnaik (2):
      ring-buffer: Fix crash due to uninitialized new_pages list head
      ring-buffer: Fix accounting of entries when removing pages


 kernel/trace/ring_buffer.c          |    6 +++---
 tools/perf/util/map.c               |   29 +++++++++++++++--------------
 tools/perf/util/session.c           |    2 +-
 tools/perf/util/trace-event-parse.c |    3 +--
 4 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1d0f6a8..f765465 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1075,6 +1075,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 	rb_init_page(bpage->page);
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+	INIT_LIST_HEAD(&cpu_buffer->new_pages);
 
 	ret = rb_allocate_pages(cpu_buffer, nr_pages);
 	if (ret < 0)
@@ -1346,10 +1347,9 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
 			 * If something was added to this page, it was full
 			 * since it is not the tail page. So we deduct the
 			 * bytes consumed in ring buffer from here.
-			 * No need to update overruns, since this page is
-			 * deleted from ring buffer and its entries are
-			 * already accounted for.
+			 * Increment overrun to account for the lost events.
 			 */
+			local_add(page_entries, &cpu_buffer->overrun);
 			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
 		}
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 35ae568..a1f4e36 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -669,25 +669,26 @@ struct machine *machines__find(struct rb_root *self, pid_t pid)
 struct machine *machines__findnew(struct rb_root *self, pid_t pid)
 {
 	char path[PATH_MAX];
-	const char *root_dir;
+	const char *root_dir = "";
 	struct machine *machine = machines__find(self, pid);
 
-	if (!machine || machine->pid != pid) {
-		if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID)
-			root_dir = "";
-		else {
-			if (!symbol_conf.guestmount)
-				goto out;
-			sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
-			if (access(path, R_OK)) {
-				pr_err("Can't access file %s\n", path);
-				goto out;
-			}
-			root_dir = path;
+	if (machine && (machine->pid == pid))
+		goto out;
+
+	if ((pid != HOST_KERNEL_ID) &&
+	    (pid != DEFAULT_GUEST_KERNEL_ID) &&
+	    (symbol_conf.guestmount)) {
+		sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+		if (access(path, R_OK)) {
+			pr_err("Can't access file %s\n", path);
+			machine = NULL;
+			goto out;
 		}
-		machine = machines__add(self, pid, root_dir);
+		root_dir = path;
 	}
 
+	machine = machines__add(self, pid, root_dir);
+
 out:
 	return machine;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c3e399b..56142d0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -926,7 +926,7 @@ static struct machine *
 		else
 			pid = event->ip.pid;
 
-		return perf_session__find_machine(session, pid);
+		return perf_session__findnew_machine(session, pid);
 	}
 
 	return perf_session__find_host_machine(session);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index df2fddb..5dd3b5e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -198,9 +198,8 @@ void print_trace_event(int cpu, void *data, int size)
 	record.data = data;
 
 	trace_seq_init(&s);
-	pevent_print_event(pevent, &s, &record);
+	pevent_event_info(&s, event, &record);
 	trace_seq_do_printf(&s);
-	printf("\n");
 }
 
 void print_event(int cpu, void *data, int size, unsigned long long nsecs,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-23  0:51               ` Arjan van de Ven
  2012-06-23  1:57                 ` Steven Rostedt
@ 2012-06-23 18:25                 ` H. Peter Anvin
  1 sibling, 0 replies; 376+ messages in thread
From: H. Peter Anvin @ 2012-06-23 18:25 UTC (permalink / raw)
  To: Arjan van de Ven
  Cc: Steven Rostedt, Hagen Paul Pfeifer, Linus Torvalds, Ingo Molnar,
	linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

On 06/22/2012 05:51 PM, Arjan van de Ven wrote:
> 
> if it's truely an official nop, it will take decoder bandwidth obviously
> (which can decode 3 to 4 instructions per cycle, depending on the
> brand/model of CPU and the total size in bytes of these instructions).
> likewise, at the end of the out of order pipeline, NOPs may take a
> retirement slot (again 3 to 4 instructions per cycle)
> 
> icache is there as well, and if the NOP actually changes cpu flags (some
> of the less fortunate ones do) that can create a false data dependency.
> 

If it changes CPU flags it's most definitely not a NOP.

Either way, the 0F 1F ops are official, and listed in the SDM.

	-hpa


^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-23  0:51               ` Arjan van de Ven
@ 2012-06-23  1:57                 ` Steven Rostedt
  2012-06-23 18:25                 ` H. Peter Anvin
  1 sibling, 0 replies; 376+ messages in thread
From: Steven Rostedt @ 2012-06-23  1:57 UTC (permalink / raw)
  To: Arjan van de Ven
  Cc: Hagen Paul Pfeifer, Linus Torvalds, Ingo Molnar, linux-kernel,
	Peter Zijlstra, Arnaldo Carvalho de Melo, Thomas Gleixner,
	Andrew Morton, H. Peter Anvin

On Fri, 2012-06-22 at 17:51 -0700, Arjan van de Ven wrote:

> I would also worry about the compiler being able to inline a function
> containing one of these, but that's a compiler thing, not a CPU type of
> thing.

You missed the beginning of the thread where we talked about the fact
that gcc will not put a mcount (or fentry) in an inlined function, so
that's not a worry.

-- Steve



^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 23:18             ` Steven Rostedt
@ 2012-06-23  0:51               ` Arjan van de Ven
  2012-06-23  1:57                 ` Steven Rostedt
  2012-06-23 18:25                 ` H. Peter Anvin
  0 siblings, 2 replies; 376+ messages in thread
From: Arjan van de Ven @ 2012-06-23  0:51 UTC (permalink / raw)
  To: Steven Rostedt
  Cc: Hagen Paul Pfeifer, Linus Torvalds, Ingo Molnar, linux-kernel,
	Peter Zijlstra, Arnaldo Carvalho de Melo, Thomas Gleixner,
	Andrew Morton, H. Peter Anvin

On 6/22/2012 4:18 PM, Steven Rostedt wrote:
> How so? It's not a C function call (like the -finstrument-functions
> produces). It's an assembly function call. The only differences between
> having ftrace enabled and ftrace disabled with -mfentry is that you get
> a 5 byte nop at the start of each traceable function. Sure, it might put
> a little pressure on the icache, but from the benchmarks I've run, the
> impact has all been within the noise.
> 
> I've been told that it doesn't even hurt the pipeline. But I've Cc'd hpa
> and Arjan for their comments. How much impact does a 5 byte nop at the
> start of each function really have on the normal operations of the
> kernel?
> 

if it's truely an official nop, it will take decoder bandwidth obviously
(which can decode 3 to 4 instructions per cycle, depending on the
brand/model of CPU and the total size in bytes of these instructions).
likewise, at the end of the out of order pipeline, NOPs may take a
retirement slot (again 3 to 4 instructions per cycle)

icache is there as well, and if the NOP actually changes cpu flags (some
of the less fortunate ones do) that can create a false data dependency.


I would also worry about the compiler being able to inline a function
containing one of these, but that's a compiler thing, not a CPU type of
thing.


^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
       [not found]           ` <86448d73-2e19-416f-8104-ce72aa5d76eb@email.android.com>
@ 2012-06-22 23:18             ` Steven Rostedt
  2012-06-23  0:51               ` Arjan van de Ven
  0 siblings, 1 reply; 376+ messages in thread
From: Steven Rostedt @ 2012-06-22 23:18 UTC (permalink / raw)
  To: Hagen Paul Pfeifer
  Cc: Linus Torvalds, Ingo Molnar, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton,
	H. Peter Anvin, Arjan van de Ven

On Fri, 2012-06-22 at 22:08 +0200, Hagen Paul Pfeifer wrote:
> Rephrase "do not help": it helps for the framepointer aspect, no
> doubt. So mfentry is superior in that aspect. But it still generates a
> function call.

It generates a function call that at boot up is converted to a 5 byte
nop. The output ends up being:

00000000000008c3 <schedule>:
 8c3:   0f 1f 44 00 00          nop
 8c8:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 8cf:   00 00 
                        8cd: R_X86_64_32S       current_task
 8d1:   57                      push   %rdi
 8d2:   48 8b 10                mov    (%rax),%rdx
 8d5:   48 85 d2                test   %rdx,%rdx
 8d8:   74 45                   je     91f <schedule+0x5c>
 8da:   48 83 b8 60 06 00 00    cmpq   $0x0,0x660(%rax)
 8e1:   00 
 8e2:   75 3b                   jne    91f <schedule+0x5c>

>  Which in turn affects code generation.

How so? It's not a C function call (like the -finstrument-functions
produces). It's an assembly function call. The only differences between
having ftrace enabled and ftrace disabled with -mfentry is that you get
a 5 byte nop at the start of each traceable function. Sure, it might put
a little pressure on the icache, but from the benchmarks I've run, the
impact has all been within the noise.

I've been told that it doesn't even hurt the pipeline. But I've Cc'd hpa
and Arjan for their comments. How much impact does a 5 byte nop at the
start of each function really have on the normal operations of the
kernel?

>  That was the second concern of Linus, regarding mcount.

Again, the only difference is those 5 bytes. There's no other code
generation difference that I know of.

-- Steve




^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 19:06       ` Hagen Paul Pfeifer
@ 2012-06-22 19:54         ` Steven Rostedt
       [not found]           ` <86448d73-2e19-416f-8104-ce72aa5d76eb@email.android.com>
  0 siblings, 1 reply; 376+ messages in thread
From: Steven Rostedt @ 2012-06-22 19:54 UTC (permalink / raw)
  To: Hagen Paul Pfeifer
  Cc: Linus Torvalds, Ingo Molnar, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

On Fri, 2012-06-22 at 21:06 +0200, Hagen Paul Pfeifer wrote:

> >I may be more sensitive to this than most, because I look at profiles
> >and the function prologue just looks very ugly with the call mcount
> >thing. Ugh.
> 
> Yes, ugh. Even Stevens -mfentry replacement do not change things here.

Why doesn't -mfentry help here? The link I showed still had frame
pointers enabled. With -mfentry, frame pointers do not need to be
enabled. And my latest patches do not automatically enable frame
pointers when enabling function tracing if -mfentry is supported.

I just ran a bunch of compiles against kernel/sched/core.c:

no pg, no mfentry, no fp:

0000000000000882 <schedule>:
 882:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 889:   00 00 
                        887: R_X86_64_32S       current_task
 88b:   57                      push   %rdi
 88c:   48 8b 10                mov    (%rax),%rdx
 88f:   48 85 d2                test   %rdx,%rdx
 892:   74 45                   je     8d9 <schedule+0x57>
 894:   48 83 b8 60 06 00 00    cmpq   $0x0,0x660(%rax)
 89b:   00 
 89c:   75 3b                   jne    8d9 <schedule+0x57>
 89e:   48 8b b8 60 0e 00 00    mov    0xe60(%rax),%rdi
 8a5:   31 c0                   xor    %eax,%eax
 8a7:   48 85 ff                test   %rdi,%rdi
 8aa:   74 1a                   je     8c6 <schedule+0x44>
 8ac:   48 8d 57 08             lea    0x8(%rdi),%rdx
 8b0:   48 39 57 08             cmp    %rdx,0x8(%rdi)
 8b4:   b0 01                   mov    $0x1,%al
 8b6:   75 0e                   jne    8c6 <schedule+0x44>
 8b8:   48 8d 47 18             lea    0x18(%rdi),%rax
 8bc:   48 39 47 18             cmp    %rax,0x18(%rdi)
 8c0:   0f 95 c0                setne  %al
 8c3:   0f b6 c0                movzbl %al,%eax
 8c6:   85 c0                   test   %eax,%eax
 8c8:   74 0f                   je     8d9 <schedule+0x57>
 8ca:   48 85 ff                test   %rdi,%rdi
 8cd:   74 0a                   je     8d9 <schedule+0x57>
 8cf:   be 01 00 00 00          mov    $0x1,%esi
 8d4:   e8 00 00 00 00          callq  8d9 <schedule+0x57>
                        8d5: R_X86_64_PC32      blk_flush_plug_list-0x4
 8d9:   e8 70 f9 ff ff          callq  24e <__schedule>
 8de:   5e                      pop    %rsi
 8df:   c3                      retq   


no pg, no mfentry, with fp:

00000000000008cb <schedule>:
 8cb:   55                      push   %rbp
 8cc:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 8d3:   00 00 
                        8d1: R_X86_64_32S       current_task
 8d5:   48 8b 10                mov    (%rax),%rdx
 8d8:   48 89 e5                mov    %rsp,%rbp
 8db:   48 85 d2                test   %rdx,%rdx
 8de:   74 45                   je     925 <schedule+0x5a>
 8e0:   48 83 b8 60 06 00 00    cmpq   $0x0,0x660(%rax)
 8e7:   00 
 8e8:   75 3b                   jne    925 <schedule+0x5a>
 8ea:   48 8b b8 60 0e 00 00    mov    0xe60(%rax),%rdi
 8f1:   31 c0                   xor    %eax,%eax
 8f3:   48 85 ff                test   %rdi,%rdi
 8f6:   74 1a                   je     912 <schedule+0x47>
 8f8:   48 8d 57 08             lea    0x8(%rdi),%rdx
 8fc:   48 39 57 08             cmp    %rdx,0x8(%rdi)
 900:   b0 01                   mov    $0x1,%al
 902:   75 0e                   jne    912 <schedule+0x47>
 904:   48 8d 47 18             lea    0x18(%rdi),%rax
 908:   48 39 47 18             cmp    %rax,0x18(%rdi)
 90c:   0f 95 c0                setne  %al
 90f:   0f b6 c0                movzbl %al,%eax
 912:   85 c0                   test   %eax,%eax
 914:   74 0f                   je     925 <schedule+0x5a>
 916:   48 85 ff                test   %rdi,%rdi
 919:   74 0a                   je     925 <schedule+0x5a>
 91b:   be 01 00 00 00          mov    $0x1,%esi
 920:   e8 00 00 00 00          callq  925 <schedule+0x5a>
                        921: R_X86_64_PC32      blk_flush_plug_list-0x4
 925:   e8 41 f9 ff ff          callq  26b <__schedule>
 92a:   5d                      pop    %rbp
 92b:   c3                      retq   

The above is our basis. Now lets look at the current -pg

with pg, no mfentry, with fp:

000000000000090c <schedule>:
 90c:   55                      push   %rbp
 90d:   48 89 e5                mov    %rsp,%rbp
 910:   e8 00 00 00 00          callq  915 <schedule+0x9>
                        911: R_X86_64_PC32      mcount-0x4
 915:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 91c:   00 00 
                        91a: R_X86_64_32S       current_task
 91e:   48 8b 10                mov    (%rax),%rdx
 921:   48 85 d2                test   %rdx,%rdx
 924:   74 45                   je     96b <schedule+0x5f>
 926:   48 83 b8 60 06 00 00    cmpq   $0x0,0x660(%rax)
 92d:   00 
 92e:   75 3b                   jne    96b <schedule+0x5f>
 930:   48 8b b8 60 0e 00 00    mov    0xe60(%rax),%rdi
 937:   31 c0                   xor    %eax,%eax
 939:   48 85 ff                test   %rdi,%rdi
 93c:   74 1a                   je     958 <schedule+0x4c>
 93e:   48 8d 57 08             lea    0x8(%rdi),%rdx
 942:   48 39 57 08             cmp    %rdx,0x8(%rdi)
 946:   b0 01                   mov    $0x1,%al
 948:   75 0e                   jne    958 <schedule+0x4c>
 94a:   48 8d 47 18             lea    0x18(%rdi),%rax
 94e:   48 39 47 18             cmp    %rax,0x18(%rdi)
 952:   0f 95 c0                setne  %al
 955:   0f b6 c0                movzbl %al,%eax
 958:   85 c0                   test   %eax,%eax
 95a:   74 0f                   je     96b <schedule+0x5f>
 95c:   48 85 ff                test   %rdi,%rdi
 95f:   74 0a                   je     96b <schedule+0x5f>
 961:   be 01 00 00 00          mov    $0x1,%esi
 966:   e8 00 00 00 00          callq  96b <schedule+0x5f>
                        967: R_X86_64_PC32      blk_flush_plug_list-0x4
 96b:   e8 37 f9 ff ff          callq  2a7 <__schedule>
 970:   5d                      pop    %rbp
 971:   c3                      retq   

Looks like %rsp is saved in %rbp here as well as the call to mcount.

-pg must have frame pointers when -mfentry is not included, so there is
no 'with pg, no mfentry, no fp'. Now lets look at mfentry:

with pg, with mfentry, with fp:

000000000000090c <schedule>:
 90c:   e8 00 00 00 00          callq  911 <schedule+0x5>
                        90d: R_X86_64_PC32      __fentry__-0x4
 911:   55                      push   %rbp
 912:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 919:   00 00 
                        917: R_X86_64_32S       current_task
 91b:   48 8b 10                mov    (%rax),%rdx
 91e:   48 89 e5                mov    %rsp,%rbp
 921:   48 85 d2                test   %rdx,%rdx
 924:   74 45                   je     96b <schedule+0x5f>
 926:   48 83 b8 60 06 00 00    cmpq   $0x0,0x660(%rax)
 92d:   00 
 92e:   75 3b                   jne    96b <schedule+0x5f>
 930:   48 8b b8 60 0e 00 00    mov    0xe60(%rax),%rdi
 937:   31 c0                   xor    %eax,%eax
 939:   48 85 ff                test   %rdi,%rdi
 93c:   74 1a                   je     958 <schedule+0x4c>
 93e:   48 8d 57 08             lea    0x8(%rdi),%rdx
 942:   48 39 57 08             cmp    %rdx,0x8(%rdi)
 946:   b0 01                   mov    $0x1,%al
 948:   75 0e                   jne    958 <schedule+0x4c>
 94a:   48 8d 47 18             lea    0x18(%rdi),%rax
 94e:   48 39 47 18             cmp    %rax,0x18(%rdi)
 952:   0f 95 c0                setne  %al
 955:   0f b6 c0                movzbl %al,%eax
 958:   85 c0                   test   %eax,%eax
 95a:   74 0f                   je     96b <schedule+0x5f>
 95c:   48 85 ff                test   %rdi,%rdi
 95f:   74 0a                   je     96b <schedule+0x5f>
 961:   be 01 00 00 00          mov    $0x1,%esi
 966:   e8 00 00 00 00          callq  96b <schedule+0x5f>
                        967: R_X86_64_PC32      blk_flush_plug_list-0x4
 96b:   e8 37 f9 ff ff          callq  2a7 <__schedule>
 970:   5d                      pop    %rbp
 971:   c3                      retq   


It is identical with non -pg and frame pointers, except that we added a
call to fentry in the start of the function.

with pg, with fentry, no fp:

00000000000008c3 <schedule>:
 8c3:   e8 00 00 00 00          callq  8c8 <schedule+0x5>
                        8c4: R_X86_64_PC32      __fentry__-0x4
 8c8:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 8cf:   00 00 
                        8cd: R_X86_64_32S       current_task
 8d1:   57                      push   %rdi
 8d2:   48 8b 10                mov    (%rax),%rdx
 8d5:   48 85 d2                test   %rdx,%rdx
 8d8:   74 45                   je     91f <schedule+0x5c>
 8da:   48 83 b8 60 06 00 00    cmpq   $0x0,0x660(%rax)
 8e1:   00 
 8e2:   75 3b                   jne    91f <schedule+0x5c>
 8e4:   48 8b b8 60 0e 00 00    mov    0xe60(%rax),%rdi
 8eb:   31 c0                   xor    %eax,%eax
 8ed:   48 85 ff                test   %rdi,%rdi
 8f0:   74 1a                   je     90c <schedule+0x49>
 8f2:   48 8d 57 08             lea    0x8(%rdi),%rdx
 8f6:   48 39 57 08             cmp    %rdx,0x8(%rdi)
 8fa:   b0 01                   mov    $0x1,%al
 8fc:   75 0e                   jne    90c <schedule+0x49>
 8fe:   48 8d 47 18             lea    0x18(%rdi),%rax
 902:   48 39 47 18             cmp    %rax,0x18(%rdi)
 906:   0f 95 c0                setne  %al
 909:   0f b6 c0                movzbl %al,%eax
 90c:   85 c0                   test   %eax,%eax
 90e:   74 0f                   je     91f <schedule+0x5c>
 910:   48 85 ff                test   %rdi,%rdi
 913:   74 0a                   je     91f <schedule+0x5c>
 915:   be 01 00 00 00          mov    $0x1,%esi
 91a:   e8 00 00 00 00          callq  91f <schedule+0x5c>
                        91b: R_X86_64_PC32      blk_flush_plug_list-0x4
 91f:   e8 66 f9 ff ff          callq  28a <__schedule>
 924:   5e                      pop    %rsi
 925:   c3                      retq   

Now here's the big difference from -pg. This is identical to compiling
without frame pointers with the exception of the fentry call at the
start of the function.

Now what's the issue with function prologues with -mfentry?

-- Steve



^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 18:52     ` Linus Torvalds
@ 2012-06-22 19:06       ` Hagen Paul Pfeifer
  2012-06-22 19:54         ` Steven Rostedt
  0 siblings, 1 reply; 376+ messages in thread
From: Hagen Paul Pfeifer @ 2012-06-22 19:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Steven Rostedt, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

* Linus Torvalds | 2012-06-22 11:52:43 [-0700]:

>So even stubbed out, it's quite noticeable. The call causes the
>function prologue to change quite a bit.
>
>That's actually especially true with newer versions of gcc that
>*finally* seem to have done the "don't always generate the full
>prologue if some case doesn't need it" optimization. So functions that
>have early-out conditions (quite common) will exit before even having
>done the prologue, and without doing the whole frame pointer setup
>etc.
>
>Except if mcount generation is on. Then gcc will always do the
>prologue and frame pointer setup before doing the mcount, because
>mcount wants it.
>
>So it really isn't just the extra call instruction.
>
>I may be more sensitive to this than most, because I look at profiles
>and the function prologue just looks very ugly with the call mcount
>thing. Ugh.

Yes, ugh. Even Stevens -mfentry replacement do not change things here. Maybe
this performance problem should addressed on another level: distributors
should build there kernel with disabled ftrace support. Kprobes and function
tracing should be sufficient for 98% of their customers.

I see no compiler (gcc) way around this performance issue. Maybe you/Steven
should restart a G+ poll ... ;)

Hagen


^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 18:38   ` Hagen Paul Pfeifer
@ 2012-06-22 18:52     ` Linus Torvalds
  2012-06-22 19:06       ` Hagen Paul Pfeifer
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2012-06-22 18:52 UTC (permalink / raw)
  To: Hagen Paul Pfeifer
  Cc: Ingo Molnar, Steven Rostedt, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

On Fri, Jun 22, 2012 at 11:38 AM, Hagen Paul Pfeifer <hagen@jauu.net> wrote:
>>
>>Because that mcount thing is expensive as hell, if people haven't
>>noticed (and I'm not talking about just the call instruction that I
>>think we can stub out - it changes code generation in other ways too).
>>And it looks like distros enable it by default, which annoys my
>>performance-optimizing soul deeply.
>
> Isn't it stubed out already? Already replaced by nops at boot time by
> ftrace_code_disable() and friends!? But yes, there may be spots where the
> additional mcount() call avoid optimization.

So even stubbed out, it's quite noticeable. The call causes the
function prologue to change quite a bit.

That's actually especially true with newer versions of gcc that
*finally* seem to have done the "don't always generate the full
prologue if some case doesn't need it" optimization. So functions that
have early-out conditions (quite common) will exit before even having
done the prologue, and without doing the whole frame pointer setup
etc.

Except if mcount generation is on. Then gcc will always do the
prologue and frame pointer setup before doing the mcount, because
mcount wants it.

So it really isn't just the extra call instruction.

I may be more sensitive to this than most, because I look at profiles
and the function prologue just looks very ugly with the call mcount
thing. Ugh.

                  Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 18:07 ` Linus Torvalds
  2012-06-22 18:38   ` Hagen Paul Pfeifer
@ 2012-06-22 18:50   ` Steven Rostedt
  1 sibling, 0 replies; 376+ messages in thread
From: Steven Rostedt @ 2012-06-22 18:50 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton,
	Masami Hiramatsu, Andi Kleen

On Fri, 2012-06-22 at 11:07 -0700, Linus Torvalds wrote:
> On Fri, Jun 22, 2012 at 6:36 AM, Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Steven Rostedt (1):
> >      ftrace: Make all inline tags also include notrace
> 
> Btw, this is something I've been wondering about: function call
> tracing and inlining seems to be fundamentally incompatible.

True that the -pg option never adds the mcount call to any function that
gets inlined. But just an FYI, the alternative -finstrument-functions,
which traces both start and stop of the function, even does inlined
functions. Which one one of the reasons I totally avoided it.

> 
> And gcc can (and does, depending on version and details) inline pretty
> much any static function, whether we mark it inline or not.

Right, which means that those do not get traced either.

> 
> Now, there's no question that we don't want inlined functions to be
> traced, but that actually means that the *logical* thing would be to
> try to somehow tell gcc to not ever do the whole stupid mcount thing
> for functions that *might* be inlined - and at least be consistent
> about it.

Hmm, I'm not sure how to tell gcc that :-/

> 
> IOW, is there some way to get the mcount thing to only happen for
> functions that either have their address taken, or have external
> visibility?
> 
> Because that mcount thing is expensive as hell, if people haven't
> noticed (and I'm not talking about just the call instruction that I
> think we can stub out

It is stubbed out. Has been since day one, when DYNAMIC_FTRACE is
supported and enabled.

>  - it changes code generation in other ways too).

One thing it does, which I hate, is that it enables (forces) frame
pointers.

> And it looks like distros enable it by default, which annoys my
> performance-optimizing soul deeply.

We have been working on an alternative. That is the -mfentry, and I have
working code that is still in the testing phase (and looking good!).

When you add -mfentry with -pg instead of calling mcount, which comes
after the frame pointer has been set up, it calls fentry, as the very
first instruction in the function. It should not interfere with any
other code generation.

The -mfentry is supported since gcc 4.6.0 and only for x86 (thanks to
Andi Kleen for doing this. Here's my first email that described it a
little (I've been working on various versions, but it has settled down
recently):

https://lkml.org/lkml/2011/2/9/271

Back then, one of the issues I worried about was its interaction with
kprobes. As kprobes commonly are inserted at the first instruction of a
function, and kprobes could not be inserted at a ftrace nop, this would
cause issues for users wanting to insert their probe at the beginning of
the function.

But Masami has already helped me in fixing this up. Both the kprobes
issue and the fentry and no framepointers code is working well. I was
going to push it for 3.7 so that I can vindicate it a bit more.

Here's my last RFC patch set for the kprobes/ftrace work. Where kprobes
can actually be optimized by using the ftrace infrastructure.

https://lkml.org/lkml/2012/6/12/668

-- Steve


> 
> So doing it a bit less would be lovely.
> 
>                       Linus



^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 18:07 ` Linus Torvalds
@ 2012-06-22 18:38   ` Hagen Paul Pfeifer
  2012-06-22 18:52     ` Linus Torvalds
  2012-06-22 18:50   ` Steven Rostedt
  1 sibling, 1 reply; 376+ messages in thread
From: Hagen Paul Pfeifer @ 2012-06-22 18:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, Steven Rostedt, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

* Linus Torvalds | 2012-06-22 11:07:01 [-0700]:

>And gcc can (and does, depending on version and details) inline pretty
>much any static function, whether we mark it inline or not.
>
>Now, there's no question that we don't want inlined functions to be
>traced, but that actually means that the *logical* thing would be to
>try to somehow tell gcc to not ever do the whole stupid mcount thing
>for functions that *might* be inlined - and at least be consistent
>about it.
>
>IOW, is there some way to get the mcount thing to only happen for
>functions that either have their address taken, or have external
>visibility?
>
>Because that mcount thing is expensive as hell, if people haven't
>noticed (and I'm not talking about just the call instruction that I
>think we can stub out - it changes code generation in other ways too).
>And it looks like distros enable it by default, which annoys my
>performance-optimizing soul deeply.

Isn't it stubed out already? Already replaced by nops at boot time by
ftrace_code_disable() and friends!? But yes, there may be spots where the
additional mcount() call avoid optimization.

Hagen

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2012-06-22 13:36 Ingo Molnar
@ 2012-06-22 18:07 ` Linus Torvalds
  2012-06-22 18:38   ` Hagen Paul Pfeifer
  2012-06-22 18:50   ` Steven Rostedt
  0 siblings, 2 replies; 376+ messages in thread
From: Linus Torvalds @ 2012-06-22 18:07 UTC (permalink / raw)
  To: Ingo Molnar, Steven Rostedt
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

On Fri, Jun 22, 2012 at 6:36 AM, Ingo Molnar <mingo@kernel.org> wrote:
>
> Steven Rostedt (1):
>      ftrace: Make all inline tags also include notrace

Btw, this is something I've been wondering about: function call
tracing and inlining seems to be fundamentally incompatible.

And gcc can (and does, depending on version and details) inline pretty
much any static function, whether we mark it inline or not.

Now, there's no question that we don't want inlined functions to be
traced, but that actually means that the *logical* thing would be to
try to somehow tell gcc to not ever do the whole stupid mcount thing
for functions that *might* be inlined - and at least be consistent
about it.

IOW, is there some way to get the mcount thing to only happen for
functions that either have their address taken, or have external
visibility?

Because that mcount thing is expensive as hell, if people haven't
noticed (and I'm not talking about just the call instruction that I
think we can stub out - it changes code generation in other ways too).
And it looks like distros enable it by default, which annoys my
performance-optimizing soul deeply.

So doing it a bit less would be lovely.

                      Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-06-22 13:36 Ingo Molnar
  2012-06-22 18:07 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2012-06-22 13:36 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 6921a575c9f26f7ea274aaea3b78967810ce5513 Merge branch 'tip/perf/urgent-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf tools: Fix synthesizing tracepoint names from the perf.data headers

David Ahern (1):
      perf tools: Fix endianity swapping for adds_features bitmask

Salman Qazi (1):
      perf: Use css_tryget() to avoid propping up css refcount

Stephane Eranian (1):
      perf stat: Fix default output file

Steven Rostedt (1):
      ftrace: Make all inline tags also include notrace


 include/linux/compiler-gcc.h           |    6 ++--
 kernel/events/core.c                   |   10 +++++--
 tools/perf/builtin-stat.c              |    8 +++++-
 tools/perf/util/header.c               |   48 +++++++++++++++++++++++++++-----
 tools/perf/util/include/linux/bitops.h |    2 ++
 tools/perf/util/session.c              |   10 +++++++
 tools/perf/util/session.h              |    1 +
 7 files changed, 71 insertions(+), 14 deletions(-)

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index e5834aa..6a6d7ae 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -47,9 +47,9 @@
  */
 #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \
     !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-# define inline		inline		__attribute__((always_inline))
-# define __inline__	__inline__	__attribute__((always_inline))
-# define __inline	__inline	__attribute__((always_inline))
+# define inline		inline		__attribute__((always_inline)) notrace
+# define __inline__	__inline__	__attribute__((always_inline)) notrace
+# define __inline	__inline	__attribute__((always_inline)) notrace
 #else
 /* A lot of inline functions can cause havoc with function tracing */
 # define inline		inline		notrace
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f85c015..d7d71d6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event)
 	return !event->cgrp || event->cgrp == cpuctx->cgrp;
 }
 
-static inline void perf_get_cgroup(struct perf_event *event)
+static inline bool perf_tryget_cgroup(struct perf_event *event)
 {
-	css_get(&event->cgrp->css);
+	return css_tryget(&event->cgrp->css);
 }
 
 static inline void perf_put_cgroup(struct perf_event *event)
@@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	event->cgrp = cgrp;
 
 	/* must be done before we fput() the file */
-	perf_get_cgroup(event);
+	if (!perf_tryget_cgroup(event)) {
+		event->cgrp = NULL;
+		ret = -ENOENT;
+		goto out;
+	}
 
 	/*
 	 * all events in a group must monitor
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2625899..07b5c77 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1179,6 +1179,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		fprintf(stderr, "cannot use both --output and --log-fd\n");
 		usage_with_options(stat_usage, options);
 	}
+
+	if (output_fd < 0) {
+		fprintf(stderr, "argument to --log-fd must be a > 0\n");
+		usage_with_options(stat_usage, options);
+	}
+
 	if (!output) {
 		struct timespec tm;
 		mode = append_file ? "a" : "w";
@@ -1190,7 +1196,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		}
 		clock_gettime(CLOCK_REALTIME, &tm);
 		fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
-	} else if (output_fd != 2) {
+	} else if (output_fd > 0) {
 		mode = append_file ? "a" : "w";
 		output = fdopen(output_fd, mode);
 		if (!output) {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 2dd5edf..e909d43 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1942,7 +1942,6 @@ int perf_file_header__read(struct perf_file_header *header,
 		else
 			return -1;
 	} else if (ph->needs_swap) {
-		unsigned int i;
 		/*
 		 * feature bitmap is declared as an array of unsigned longs --
 		 * not good since its size can differ between the host that
@@ -1958,14 +1957,17 @@ int perf_file_header__read(struct perf_file_header *header,
 		 * file), punt and fallback to the original behavior --
 		 * clearing all feature bits and setting buildid.
 		 */
-		for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i)
-			header->adds_features[i] = bswap_64(header->adds_features[i]);
+		mem_bswap_64(&header->adds_features,
+			    BITS_TO_U64(HEADER_FEAT_BITS));
 
 		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
-			for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) {
-				header->adds_features[i] = bswap_64(header->adds_features[i]);
-				header->adds_features[i] = bswap_32(header->adds_features[i]);
-			}
+			/* unswap as u64 */
+			mem_bswap_64(&header->adds_features,
+				    BITS_TO_U64(HEADER_FEAT_BITS));
+
+			/* unswap as u32 */
+			mem_bswap_32(&header->adds_features,
+				    BITS_TO_U32(HEADER_FEAT_BITS));
 		}
 
 		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
@@ -2091,6 +2093,35 @@ static int read_attr(int fd, struct perf_header *ph,
 	return ret <= 0 ? -1 : 0;
 }
 
+static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
+{
+	struct event_format *event = trace_find_event(evsel->attr.config);
+	char bf[128];
+
+	if (event == NULL)
+		return -1;
+
+	snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
+	evsel->name = strdup(bf);
+	if (event->name == NULL)
+		return -1;
+
+	return 0;
+}
+
+static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
+		    perf_evsel__set_tracepoint_name(pos))
+			return -1;
+	}
+
+	return 0;
+}
+
 int perf_session__read_header(struct perf_session *session, int fd)
 {
 	struct perf_header *header = &session->header;
@@ -2172,6 +2203,9 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
 	lseek(fd, header->data_offset, SEEK_SET);
 
+	if (perf_evlist__set_tracepoint_names(session->evlist))
+		goto out_delete_evlist;
+
 	header->frozen = 1;
 	return 0;
 out_errno:
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index f1584833..587a230 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -8,6 +8,8 @@
 #define BITS_PER_LONG __WORDSIZE
 #define BITS_PER_BYTE           8
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2600916..c3e399b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -442,6 +442,16 @@ static void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 }
+ 
+void mem_bswap_32(void *src, int byte_size)
+{
+	u32 *m = src;
+	while (byte_size > 0) {
+		*m = bswap_32(*m);
+		byte_size -= sizeof(u32);
+		++m;
+	}
+}
 
 void mem_bswap_64(void *src, int byte_size)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7a5434c..0c702e3 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -80,6 +80,7 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
 void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *self);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-06-15 18:48 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-06-15 18:48 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: a70270468234749741c5893ae78e5bb524771402 watchdog: Quiet down the boot messages

 Thanks,

	Ingo

------------------>
Don Zickus (1):
      watchdog: Quiet down the boot messages

Stephane Eranian (1):
      perf/x86: Fix broken LBR fixup code

Steven Rostedt (1):
      tracing: Have tracing_off() actually turn tracing off


 arch/x86/lib/usercopy.c |  2 +-
 kernel/trace/trace.c    |  2 +-
 kernel/watchdog.c       | 19 ++++++++++++++++++-
 3 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 677b1ed..4f74d94 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -22,7 +22,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
-	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+	if (__range_not_ok(from, n, TASK_SIZE))
 		return len;
 
 	do {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 68032c6..49249c2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
 void tracing_off(void)
 {
 	if (global_trace.buffer)
-		ring_buffer_record_on(global_trace.buffer);
+		ring_buffer_record_off(global_trace.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index e5e1d85..4b1dfba 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -372,6 +372,13 @@ static int watchdog(void *unused)
 
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
 static int watchdog_nmi_enable(int cpu)
 {
 	struct perf_event_attr *wd_attr;
@@ -390,11 +397,21 @@ static int watchdog_nmi_enable(int cpu)
 
 	/* Try to register using hardware perf events */
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+	/* save cpu0 error for future comparision */
+	if (cpu == 0 && IS_ERR(event))
+		cpu0_err = PTR_ERR(event);
+
 	if (!IS_ERR(event)) {
-		pr_info("enabled, takes one hw-pmu counter.\n");
+		/* only print for cpu0 or different than cpu0 */
+		if (cpu == 0 || cpu0_err)
+			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
 		goto out_save;
 	}
 
+	/* skip displaying the same error again */
+	if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+		return PTR_ERR(event);
 
 	/* vary the KERN level based on the returned errno */
 	if (PTR_ERR(event) == -EOPNOTSUPP)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-06-08  9:20 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-06-08  9:20 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: db0dc75d6403b6663c0eab4c6ccb672eb9b2ed72 perf/x86: Check user address explicitly in copy_from_user_nmi()

A bit larger than what I'd wish for - half of it is due to hw 
driver updates to Intel Ivy-Bridge which info got recently 
released, cycles:pp should work there now too, amongst other 
things. (but we are generally making exceptions for hardware 
enablement of this type.)

There are also callchain fixes in it - responding to mostly 
theoretical (but valid) concerns. The tooling side sports 
perf.data endianness/portability fixes which did not make 
it for the merge window - and various other fixes as well.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (5):
      perf report: Use the right symbol for annotation
      perf annotate browser: Fix help window entry for navigating to hottest line
      perf stat: Initialize default events wrt exclude_{guest,host}
      perf tools: Fix make tarballs
      perf tools: Make --version show kernel version instead of pull req tag

Arun Sharma (4):
      perf/x86: Allow multiple stacks
      perf: Limit callchains to 127
      perf/x86: Check if user fp is valid
      perf/x86: Check user address explicitly in copy_from_user_nmi()

Avik Sil (1):
      perf tools: Fix pager on minimal-install embedded systems

David Ahern (1):
      perf script: Fix regression in callchain dso name

Jiri Olsa (3):
      perf symbols: Handle different endians properly during symbol load
      perf session: Handle endianity swap on sample_id_all header data
      perf evsel: Fix 32 bit values endianity swap for sample_id_all header

Masami Hiramatsu (1):
      x86/decoder: Fix bsr/bsf/jmpe decoding with operand-size prefix

Namhyung Kim (5):
      perf callchain: Make callchain cursors TLS
      perf tools: Check if callchain is corrupted
      perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP
      perf evlist: Pass third argument to ioctl explicitly
      perf: Remove duplicate invocation on perf_event_for_each

Peter Zijlstra (4):
      perf/x86: Fix Intel shared extra MSR allocation
      perf/x86: Implement cycles:p for SNB/IVB
      perf/x86: Enable/Add IvyBridge hardware support
      perf/x86: Update SNB PEBS constraints

Srikar Dronamraju (2):
      perf symbols: Check for valid dso before creating map
      perf uprobes: Remove unnecessary check before strlist__delete


 arch/x86/include/asm/uaccess.h            |  12 +--
 arch/x86/kernel/cpu/perf_event.c          |  11 ++-
 arch/x86/kernel/cpu/perf_event.h          |   2 +
 arch/x86/kernel/cpu/perf_event_intel.c    | 145 ++++++++++++++++++++++--------
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   9 +-
 arch/x86/lib/usercopy.c                   |   4 +
 arch/x86/lib/x86-opcode-map.txt           |   8 +-
 arch/x86/tools/gen-insn-attr-x86.awk      |  14 +--
 include/linux/perf_event.h                |   4 +-
 kernel/events/core.c                      |   1 -
 tools/perf/MANIFEST                       |   2 +
 tools/perf/builtin-report.c               |   4 +-
 tools/perf/builtin-stat.c                 |   8 +-
 tools/perf/builtin-top.c                  |   2 +-
 tools/perf/design.txt                     |   7 +-
 tools/perf/ui/browsers/annotate.c         |   2 +-
 tools/perf/util/PERF-VERSION-GEN          |   2 +-
 tools/perf/util/callchain.c               |   2 +
 tools/perf/util/callchain.h               |   2 +
 tools/perf/util/evlist.c                  |  17 +++-
 tools/perf/util/evlist.h                  |   4 +
 tools/perf/util/evsel.c                   |  29 ++++--
 tools/perf/util/hist.c                    |   7 +-
 tools/perf/util/hist.h                    |   2 -
 tools/perf/util/pager.c                   |   4 +
 tools/perf/util/probe-event.c             |   8 +-
 tools/perf/util/session.c                 |  97 +++++++++++++++-----
 tools/perf/util/symbol.c                  |  38 +++++++-
 tools/perf/util/symbol.h                  |  30 +++++++
 29 files changed, 357 insertions(+), 120 deletions(-)

diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 04cd688..e1f3a17 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,9 +33,8 @@
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
 #define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) 	\
+	((unsigned long __force)(addr) < user_addr_max())
 
 /*
  * Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
 
-#define __range_not_ok(addr, size)					\
+#define __range_not_ok(addr, size, limit)				\
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
 	    : "=&r" (flag), "=r" (roksum)				\
 	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
+	      "rm" (limit));						\
 	flag;								\
 })
 
@@ -77,7 +76,8 @@
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
 
 /*
  * The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6d..c4706cf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
 		if (!cpuc->shared_regs)
 			goto error;
 	}
+	cpuc->is_fake = 1;
 	return cpuc;
 error:
 	free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (bytes != sizeof(frame))
 			break;
 
-		if (fp < compat_ptr(regs->sp))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		if (bytes != sizeof(frame))
 			break;
 
-		if ((unsigned long)fp < regs->sp)
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf..7241e2f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -117,6 +117,7 @@ struct cpu_hw_events {
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
 
 	unsigned int		group_flag;
+	int			is_fake;
 
 	/*
 	 * Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
+	void		(*pebs_aliases)(struct perf_event *event);
 
 	/*
 	 * Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546e..187c294 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
 {
 	if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
-		return false;
+		return idx;
 
-	if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
-		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01bb;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
-		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
-	} else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+	if (idx == EXTRA_REG_RSP_0)
+		return EXTRA_REG_RSP_1;
+
+	if (idx == EXTRA_REG_RSP_1)
+		return EXTRA_REG_RSP_0;
+
+	return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+	event->hw.extra_reg.idx = idx;
+
+	if (idx == EXTRA_REG_RSP_0) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
 		event->hw.config |= 0x01b7;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+	} else if (idx == EXTRA_REG_RSP_1) {
+		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+		event->hw.config |= 0x01bb;
+		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
 	}
-
-	if (event->hw.extra_reg.idx == orig_idx)
-		return false;
-
-	return true;
 }
 
 /*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
 	struct event_constraint *c = &emptyconstraint;
 	struct er_account *era;
 	unsigned long flags;
-	int orig_idx = reg->idx;
+	int idx = reg->idx;
 
-	/* already allocated shared msr */
-	if (reg->alloc)
+	/*
+	 * reg->alloc can be set due to existing state, so for fake cpuc we
+	 * need to ignore this, otherwise we might fail to allocate proper fake
+	 * state for this extra reg constraint. Also see the comment below.
+	 */
+	if (reg->alloc && !cpuc->is_fake)
 		return NULL; /* call x86_get_event_constraint() */
 
 again:
-	era = &cpuc->shared_regs->regs[reg->idx];
+	era = &cpuc->shared_regs->regs[idx];
 	/*
 	 * we use spin_lock_irqsave() to avoid lockdep issues when
 	 * passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
 
 	if (!atomic_read(&era->ref) || era->config == reg->config) {
 
+		/*
+		 * If its a fake cpuc -- as per validate_{group,event}() we
+		 * shouldn't touch event state and we can avoid doing so
+		 * since both will only call get_event_constraints() once
+		 * on each event, this avoids the need for reg->alloc.
+		 *
+		 * Not doing the ER fixup will only result in era->reg being
+		 * wrong, but since we won't actually try and program hardware
+		 * this isn't a problem either.
+		 */
+		if (!cpuc->is_fake) {
+			if (idx != reg->idx)
+				intel_fixup_er(event, idx);
+
+			/*
+			 * x86_schedule_events() can call get_event_constraints()
+			 * multiple times on events in the case of incremental
+			 * scheduling(). reg->alloc ensures we only do the ER
+			 * allocation once.
+			 */
+			reg->alloc = 1;
+		}
+
 		/* lock in msr value */
 		era->config = reg->config;
 		era->reg = reg->reg;
@@ -1180,17 +1213,17 @@ again:
 		/* one more user */
 		atomic_inc(&era->ref);
 
-		/* no need to reallocate during incremental event scheduling */
-		reg->alloc = 1;
-
 		/*
 		 * need to call x86_get_event_constraint()
 		 * to check if associated event has constraints
 		 */
 		c = NULL;
-	} else if (intel_try_alt_er(event, orig_idx)) {
-		raw_spin_unlock_irqrestore(&era->lock, flags);
-		goto again;
+	} else {
+		idx = intel_alt_er(idx);
+		if (idx != reg->idx) {
+			raw_spin_unlock_irqrestore(&era->lock, flags);
+			goto again;
+		}
 	}
 	raw_spin_unlock_irqrestore(&era->lock, flags);
 
@@ -1204,11 +1237,14 @@ __intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
 	struct er_account *era;
 
 	/*
-	 * only put constraint if extra reg was actually
-	 * allocated. Also takes care of event which do
-	 * not use an extra shared reg
+	 * Only put constraint if extra reg was actually allocated. Also takes
+	 * care of event which do not use an extra shared reg.
+	 *
+	 * Also, if this is a fake cpuc we shouldn't touch any event state
+	 * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+	 * either since it'll be thrown out.
 	 */
-	if (!reg->alloc)
+	if (!reg->alloc || cpuc->is_fake)
 		return;
 
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
 {
-	int ret = x86_pmu_hw_config(event);
-
-	if (ret)
-		return ret;
-
-	if (event->attr.precise_ip &&
-	    (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
 		/*
 		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
 		 * (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 */
 		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
 
+		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+		event->hw.config = alt_config;
+	}
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+		/*
+		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+		 * (0x003c) so that we can use it with PEBS.
+		 *
+		 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+		 * PEBS capable. However we can use UOPS_RETIRED.ALL
+		 * (0x01c2), which is a PEBS capable event, to get the same
+		 * count.
+		 *
+		 * UOPS_RETIRED.ALL counts the number of cycles that retires
+		 * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+		 * larger than the maximum number of micro-ops that can be
+		 * retired per cycle (4) and then inverting the condition, we
+		 * count all cycles that retire 16 or less micro-ops, which
+		 * is every cycle.
+		 *
+		 * Thereby we gain a PEBS capable cycle counter.
+		 */
+		u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+		x86_pmu.pebs_aliases(event);
 
 	if (intel_pmu_needs_lbr_smpl(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
+	.pebs_aliases		= intel_pebs_aliases_core2,
 
 	.format_attrs		= intel_arch3_formats_attr,
 
@@ -1840,8 +1909,9 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
-		x86_add_quirk(intel_sandybridge_quirk);
 	case 45: /* SandyBridge, "Romely-EP" */
+		x86_add_quirk(intel_sandybridge_quirk);
+	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -1849,6 +1919,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
 		x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5a3edc2..35e2192 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index f61ee67..677b1ed 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/word-at-a-time.h>
+#include <linux/sched.h>
 
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
+	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+		return len;
+
 	do {
 		ret = __get_user_pages_fast(addr, 1, 0, &page);
 		if (!ret)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 8191379..5d7e51f 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -28,7 +28,7 @@
 #  - (66): the last prefix is 0x66
 #  - (F3): the last prefix is 0xF3
 #  - (F2): the last prefix is 0xF2
-#
+#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 
 Table: one byte opcode
 Referrer:
@@ -515,12 +515,12 @@ b4: LFS Gv,Mp
 b5: LGS Gv,Mp
 b6: MOVZX Gv,Eb
 b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
 b9: Grp10 (1A)
 ba: Grp8 Ev,Ib (1A)
 bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
 be: MOVSX Gv,Eb
 bf: MOVSX Gv,Ew
 # 0x0f 0xc0-0xcf
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5f6a5b6..ddcf39b 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -66,9 +66,10 @@ BEGIN {
 	rex_expr = "^REX(\\.[XRWB]+)*"
 	fpu_expr = "^ESC" # TODO
 
-	lprefix1_expr = "\\(66\\)"
+	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\(F2\\)"
+	lprefix3_expr = "\\((F2|!F3)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
 	# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, lprefix1_expr)) {
 			lptable1[idx] = add_flags(lptable1[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix2_expr)) {
+		}
+		if (match(ext, lprefix2_expr)) {
 			lptable2[idx] = add_flags(lptable2[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix3_expr)) {
+		}
+		if (match(ext, lprefix3_expr)) {
 			lptable3[idx] = add_flags(lptable3[idx],flags)
 			variant = "INAT_VARIANT"
-		} else {
+		}
+		if (!match(ext, lprefix_expr)){
 			table[idx] = add_flags(table[idx],flags)
 		}
 	}
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f325786..45db49f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -555,6 +555,8 @@ enum perf_event_type {
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
+#define PERF_MAX_STACK_DEPTH		127
+
 enum perf_callchain_context {
 	PERF_CONTEXT_HV			= (__u64)-32,
 	PERF_CONTEXT_KERNEL		= (__u64)-128,
@@ -609,8 +611,6 @@ struct perf_guest_info_callbacks {
 #include <linux/sysfs.h>
 #include <asm/local.h>
 
-#define PERF_MAX_STACK_DEPTH		255
-
 struct perf_callchain_entry {
 	__u64				nr;
 	__u64				ip[PERF_MAX_STACK_DEPTH];
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5b06cbb..f85c015 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3181,7 +3181,6 @@ static void perf_event_for_each(struct perf_event *event,
 	event = event->group_leader;
 
 	perf_event_for_each_child(event, func);
-	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
 		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 5476bc0..b4b572e 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,4 +1,6 @@
 tools/perf
+tools/scripts
+tools/lib/traceevent
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8c767c6..25249f7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -152,7 +152,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 
 	if (symbol_conf.use_callchain) {
 		err = callchain_append(he->callchain,
-				       &evsel->hists.callchain_cursor,
+				       &callchain_cursor,
 				       sample->period);
 		if (err)
 			return err;
@@ -162,7 +162,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	 * so we don't allocated the extra space needed because the stdio
 	 * code will not use it.
 	 */
-	if (al->sym != NULL && use_browser > 0) {
+	if (he->ms.sym != NULL && use_browser > 0) {
 		struct annotation *notes = symbol__annotation(he->ms.sym);
 
 		assert(evsel != NULL);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 62ae30d..2625899 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1129,7 +1129,7 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (!evsel_list->nr_entries) {
-		if (perf_evlist__add_attrs_array(evsel_list, default_attrs) < 0)
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
 			return -1;
 	}
 
@@ -1139,21 +1139,21 @@ static int add_default_attributes(void)
 		return 0;
 
 	/* Append detailed run extra attributes: */
-	if (perf_evlist__add_attrs_array(evsel_list, detailed_attrs) < 0)
+	if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
 		return -1;
 
 	if (detailed_run < 2)
 		return 0;
 
 	/* Append very detailed run extra attributes: */
-	if (perf_evlist__add_attrs_array(evsel_list, very_detailed_attrs) < 0)
+	if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
 		return -1;
 
 	if (detailed_run < 3)
 		return 0;
 
 	/* Append very, very detailed run extra attributes: */
-	return perf_evlist__add_attrs_array(evsel_list, very_very_detailed_attrs);
+	return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 871b540..6bb0277 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -787,7 +787,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		}
 
 		if (symbol_conf.use_callchain) {
-			err = callchain_append(he->callchain, &evsel->hists.callchain_cursor,
+			err = callchain_append(he->callchain, &callchain_cursor,
 					       sample->period);
 			if (err)
 				return;
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index bd0bb1b..67e5d0c 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -409,14 +409,15 @@ Counters can be enabled and disabled in two ways: via ioctl and via
 prctl.  When a counter is disabled, it doesn't count or generate
 events but does continue to exist and maintain its count value.
 
-An individual counter or counter group can be enabled with
+An individual counter can be enabled with
 
-	ioctl(fd, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
 
 or disabled with
 
-	ioctl(fd, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
 
+For a counter group, pass PERF_IOC_FLAG_GROUP as the third argument.
 Enabling or disabling the leader of a group enables or disables the
 whole group; that is, while the group leader is disabled, none of the
 counters in the group will count.  Enabling or disabling a member of a
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4deea6a..34b1c46 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -668,7 +668,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 		"q/ESC/CTRL+C  Exit\n\n"
 		"->            Go to target\n"
 		"<-            Exit\n"
-		"h             Cycle thru hottest instructions\n"
+		"H             Cycle thru hottest instructions\n"
 		"j             Toggle showing jump to target arrows\n"
 		"J             Toggle showing number of jump sources on targets\n"
 		"n             Search next string\n"
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index ad73300..95264f3 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -12,7 +12,7 @@ LF='
 # First check if there is a .git to get the version from git describe
 # otherwise try to get the version from the kernel makefile
 if test -d ../../.git -o -f ../../.git &&
-	VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+	VN=$(git describe --match 'v[0-9].[0-9]*' --abbrev=4 HEAD 2>/dev/null) &&
 	case "$VN" in
 	*$LF*) (exit 1) ;;
 	v[0-9]*)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9f7106a..3a6bff4 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -18,6 +18,8 @@
 #include "util.h"
 #include "callchain.h"
 
+__thread struct callchain_cursor callchain_cursor;
+
 bool ip_callchain__valid(struct ip_callchain *chain,
 			 const union perf_event *event)
 {
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 7f9c0f1..3bdb407 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -76,6 +76,8 @@ struct callchain_cursor {
 	struct callchain_cursor_node	*curr;
 };
 
+extern __thread struct callchain_cursor callchain_cursor;
+
 static inline void callchain_init(struct callchain_root *root)
 {
 	INIT_LIST_HEAD(&root->node.siblings);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4ac5f5a..7400fb3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -159,6 +159,17 @@ out_delete_partial_list:
 	return -1;
 }
 
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+				     struct perf_event_attr *attrs, size_t nr_attrs)
+{
+	size_t i;
+
+	for (i = 0; i < nr_attrs; i++)
+		event_attr_init(attrs + i);
+
+	return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+}
+
 static int trace_event__id(const char *evname)
 {
 	char *filename, *colon;
@@ -263,7 +274,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			for (thread = 0; thread < evlist->threads->nr; thread++)
-				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE);
+				ioctl(FD(pos, cpu, thread),
+				      PERF_EVENT_IOC_DISABLE, 0);
 		}
 	}
 }
@@ -276,7 +288,8 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			for (thread = 0; thread < evlist->threads->nr; thread++)
-				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+				ioctl(FD(pos, cpu, thread),
+				      PERF_EVENT_IOC_ENABLE, 0);
 		}
 	}
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 58abb63..989bee9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,8 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
 int perf_evlist__add_default(struct perf_evlist *evlist);
 int perf_evlist__add_attrs(struct perf_evlist *evlist,
 			   struct perf_event_attr *attrs, size_t nr_attrs);
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+				     struct perf_event_attr *attrs, size_t nr_attrs);
 int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
 				 const char *tracepoints[], size_t nr_tracepoints);
 int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
@@ -62,6 +64,8 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
 
 #define perf_evlist__add_attrs_array(evlist, array) \
 	perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
+#define perf_evlist__add_default_attrs(evlist, array) \
+	__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
 #define perf_evlist__add_tracepoints_array(evlist, array) \
 	perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 91d1913..9f6cebd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -494,16 +494,24 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel,
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
-				       struct perf_sample *sample)
+				       struct perf_sample *sample,
+				       bool swapped)
 {
 	const u64 *array = event->sample.array;
+	union u64_swap u;
 
 	array += ((event->header.size -
 		   sizeof(event->header)) / sizeof(u64)) - 1;
 
 	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		sample->cpu = *p;
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		sample->cpu = u.val32[0];
 		array--;
 	}
 
@@ -523,9 +531,16 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		sample->pid = p[0];
-		sample->tid = p[1];
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		sample->pid = u.val32[0];
+		sample->tid = u.val32[1];
 	}
 
 	return 0;
@@ -562,7 +577,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!sample_id_all)
 			return 0;
-		return perf_event__parse_id_sample(event, type, data);
+		return perf_event__parse_id_sample(event, type, data, swapped);
 	}
 
 	array = event->sample.array;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 1293b5e..514e2a4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -378,7 +378,7 @@ void hist_entry__free(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool hists__collapse_insert_entry(struct hists *hists,
+static bool hists__collapse_insert_entry(struct hists *hists __used,
 					 struct rb_root *root,
 					 struct hist_entry *he)
 {
@@ -397,8 +397,9 @@ static bool hists__collapse_insert_entry(struct hists *hists,
 			iter->period += he->period;
 			iter->nr_events += he->nr_events;
 			if (symbol_conf.use_callchain) {
-				callchain_cursor_reset(&hists->callchain_cursor);
-				callchain_merge(&hists->callchain_cursor, iter->callchain,
+				callchain_cursor_reset(&callchain_cursor);
+				callchain_merge(&callchain_cursor,
+						iter->callchain,
 						he->callchain);
 			}
 			hist_entry__free(he);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index cfc64e2..34bb556 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -67,8 +67,6 @@ struct hists {
 	struct events_stats	stats;
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
-	/* Best would be to reuse the session callchain cursor */
-	struct callchain_cursor	callchain_cursor;
 };
 
 struct hist_entry *__hists__add_entry(struct hists *self,
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 1915de2..3322b84 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -57,6 +57,10 @@ void setup_pager(void)
 	}
 	if (!pager)
 		pager = getenv("PAGER");
+	if (!pager) {
+		if (!access("/usr/bin/pager", X_OK))
+			pager = "/usr/bin/pager";
+	}
 	if (!pager)
 		pager = "less";
 	else if (!*pager || !strcmp(pager, "cat"))
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 59dccc9..0dda25d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2164,16 +2164,12 @@ int del_perf_probe_events(struct strlist *dellist)
 
 error:
 	if (kfd >= 0) {
-		if (namelist)
-			strlist__delete(namelist);
-
+		strlist__delete(namelist);
 		close(kfd);
 	}
 
 	if (ufd >= 0) {
-		if (unamelist)
-			strlist__delete(unamelist);
-
+		strlist__delete(unamelist);
 		close(ufd);
 	}
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 93d355d..2600916 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -288,7 +288,8 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 	return bi;
 }
 
-int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
+int machine__resolve_callchain(struct machine *self,
+			       struct perf_evsel *evsel __used,
 			       struct thread *thread,
 			       struct ip_callchain *chain,
 			       struct symbol **parent)
@@ -297,7 +298,12 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 	unsigned int i;
 	int err;
 
-	callchain_cursor_reset(&evsel->hists.callchain_cursor);
+	callchain_cursor_reset(&callchain_cursor);
+
+	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+		pr_warning("corrupted callchain. skipping...\n");
+		return 0;
+	}
 
 	for (i = 0; i < chain->nr; i++) {
 		u64 ip;
@@ -317,7 +323,14 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 			case PERF_CONTEXT_USER:
 				cpumode = PERF_RECORD_MISC_USER;	break;
 			default:
-				break;
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				callchain_cursor_reset(&callchain_cursor);
+				return 0;
 			}
 			continue;
 		}
@@ -333,7 +346,7 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 				break;
 		}
 
-		err = callchain_cursor_append(&evsel->hists.callchain_cursor,
+		err = callchain_cursor_append(&callchain_cursor,
 					      ip, al.map, al.sym);
 		if (err)
 			return err;
@@ -441,37 +454,65 @@ void mem_bswap_64(void *src, int byte_size)
 	}
 }
 
-static void perf_event__all64_swap(union perf_event *event)
+static void swap_sample_id_all(union perf_event *event, void *data)
+{
+	void *end = (void *) event + event->header.size;
+	int size = end - data;
+
+	BUG_ON(size % sizeof(u64));
+	mem_bswap_64(data, size);
+}
+
+static void perf_event__all64_swap(union perf_event *event,
+				   bool sample_id_all __used)
 {
 	struct perf_event_header *hdr = &event->header;
 	mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
 }
 
-static void perf_event__comm_swap(union perf_event *event)
+static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
 {
 	event->comm.pid = bswap_32(event->comm.pid);
 	event->comm.tid = bswap_32(event->comm.tid);
+
+	if (sample_id_all) {
+		void *data = &event->comm.comm;
+
+		data += ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
 }
 
-static void perf_event__mmap_swap(union perf_event *event)
+static void perf_event__mmap_swap(union perf_event *event,
+				  bool sample_id_all)
 {
 	event->mmap.pid	  = bswap_32(event->mmap.pid);
 	event->mmap.tid	  = bswap_32(event->mmap.tid);
 	event->mmap.start = bswap_64(event->mmap.start);
 	event->mmap.len	  = bswap_64(event->mmap.len);
 	event->mmap.pgoff = bswap_64(event->mmap.pgoff);
+
+	if (sample_id_all) {
+		void *data = &event->mmap.filename;
+
+		data += ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
 }
 
-static void perf_event__task_swap(union perf_event *event)
+static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
 {
 	event->fork.pid	 = bswap_32(event->fork.pid);
 	event->fork.tid	 = bswap_32(event->fork.tid);
 	event->fork.ppid = bswap_32(event->fork.ppid);
 	event->fork.ptid = bswap_32(event->fork.ptid);
 	event->fork.time = bswap_64(event->fork.time);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->fork + 1);
 }
 
-static void perf_event__read_swap(union perf_event *event)
+static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 {
 	event->read.pid		 = bswap_32(event->read.pid);
 	event->read.tid		 = bswap_32(event->read.tid);
@@ -479,6 +520,9 @@ static void perf_event__read_swap(union perf_event *event)
 	event->read.time_enabled = bswap_64(event->read.time_enabled);
 	event->read.time_running = bswap_64(event->read.time_running);
 	event->read.id		 = bswap_64(event->read.id);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->read + 1);
 }
 
 static u8 revbyte(u8 b)
@@ -530,7 +574,8 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
 }
 
-static void perf_event__hdr_attr_swap(union perf_event *event)
+static void perf_event__hdr_attr_swap(union perf_event *event,
+				      bool sample_id_all __used)
 {
 	size_t size;
 
@@ -541,18 +586,21 @@ static void perf_event__hdr_attr_swap(union perf_event *event)
 	mem_bswap_64(event->attr.id, size);
 }
 
-static void perf_event__event_type_swap(union perf_event *event)
+static void perf_event__event_type_swap(union perf_event *event,
+					bool sample_id_all __used)
 {
 	event->event_type.event_type.event_id =
 		bswap_64(event->event_type.event_type.event_id);
 }
 
-static void perf_event__tracing_data_swap(union perf_event *event)
+static void perf_event__tracing_data_swap(union perf_event *event,
+					  bool sample_id_all __used)
 {
 	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
-typedef void (*perf_event__swap_op)(union perf_event *event);
+typedef void (*perf_event__swap_op)(union perf_event *event,
+				    bool sample_id_all);
 
 static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_MMAP]		  = perf_event__mmap_swap,
@@ -986,6 +1034,15 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	}
 }
 
+static void event_swap(union perf_event *event, bool sample_id_all)
+{
+	perf_event__swap_op swap;
+
+	swap = perf_event__swap_ops[event->header.type];
+	if (swap)
+		swap(event, sample_id_all);
+}
+
 static int perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
@@ -994,9 +1051,8 @@ static int perf_session__process_event(struct perf_session *session,
 	struct perf_sample sample;
 	int ret;
 
-	if (session->header.needs_swap &&
-	    perf_event__swap_ops[event->header.type])
-		perf_event__swap_ops[event->header.type](event);
+	if (session->header.needs_swap)
+		event_swap(event, session->sample_id_all);
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
@@ -1428,7 +1484,6 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 			  int print_sym, int print_dso, int print_symoffset)
 {
 	struct addr_location al;
-	struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
 	struct callchain_cursor_node *node;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample,
@@ -1446,10 +1501,10 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 				error("Failed to resolve callchain. Skipping\n");
 			return;
 		}
-		callchain_cursor_commit(cursor);
+		callchain_cursor_commit(&callchain_cursor);
 
 		while (1) {
-			node = callchain_cursor_current(cursor);
+			node = callchain_cursor_current(&callchain_cursor);
 			if (!node)
 				break;
 
@@ -1460,12 +1515,12 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 			}
 			if (print_dso) {
 				printf(" (");
-				map__fprintf_dsoname(al.map, stdout);
+				map__fprintf_dsoname(node->map, stdout);
 				printf(")");
 			}
 			printf("\n");
 
-			callchain_cursor_advance(cursor);
+			callchain_cursor_advance(&callchain_cursor);
 		}
 
 	} else {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e2ba885..3e2e5ea 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -323,6 +323,7 @@ struct dso *dso__new(const char *name)
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
 		dso->kernel = DSO_TYPE_USER;
+		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
 	}
 
@@ -1156,6 +1157,33 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
 	return -1;
 }
 
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+	static unsigned int const endian = 1;
+
+	dso->needs_swap = DSO_SWAP__NO;
+
+	switch (eidata) {
+	case ELFDATA2LSB:
+		/* We are big endian, DSO is little endian. */
+		if (*(unsigned char const *)&endian != 1)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	case ELFDATA2MSB:
+		/* We are little endian, DSO is big endian. */
+		if (*(unsigned char const *)&endian != 0)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	default:
+		pr_err("unrecognized DSO data encoding %d\n", eidata);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 			 int fd, symbol_filter_t filter, int kmodule,
 			 int want_symtab)
@@ -1187,6 +1215,9 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 		goto out_elf_end;
 	}
 
+	if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+		goto out_elf_end;
+
 	/* Always reject images with a mismatched build-id: */
 	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
@@ -1272,7 +1303,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 		if (opdsec && sym.st_shndx == opdidx) {
 			u32 offset = sym.st_value - opdshdr.sh_addr;
 			u64 *opd = opddata->d_buf + offset;
-			sym.st_value = *opd;
+			sym.st_value = DSO__SWAP(dso, u64, *opd);
 			sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
 		}
 
@@ -2786,8 +2817,11 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 
 struct map *dso__new_map(const char *name)
 {
+	struct map *map = NULL;
 	struct dso *dso = dso__new(name);
-	struct map *map = map__new2(0, dso, MAP__FUNCTION);
+
+	if (dso)
+		map = map__new2(0, dso, MAP__FUNCTION);
 
 	return map;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5649d63..af0752b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -9,6 +9,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
+#include <byteswap.h>
 
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
@@ -160,11 +161,18 @@ enum dso_kernel_type {
 	DSO_TYPE_GUEST_KERNEL
 };
 
+enum dso_swap_type {
+	DSO_SWAP__UNSET,
+	DSO_SWAP__NO,
+	DSO_SWAP__YES,
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	enum dso_kernel_type	kernel;
+	enum dso_swap_type	needs_swap;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
@@ -182,6 +190,28 @@ struct dso {
 	char		 name[0];
 };
 
+#define DSO__SWAP(dso, type, val)			\
+({							\
+	type ____r = val;				\
+	BUG_ON(dso->needs_swap == DSO_SWAP__UNSET);	\
+	if (dso->needs_swap == DSO_SWAP__YES) {		\
+		switch (sizeof(____r)) {		\
+		case 2:					\
+			____r = bswap_16(val);		\
+			break;				\
+		case 4:					\
+			____r = bswap_32(val);		\
+			break;				\
+		case 8:					\
+			____r = bswap_64(val);		\
+			break;				\
+		default:				\
+			BUG_ON(1);			\
+		}					\
+	}						\
+	____r;						\
+})
+
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-05-30 15:39 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-05-30 15:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 59cd358a7a5b2f6b61faa01dae6cfda3830ac62a Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (9):
      perf evlist: Explicititely initialize input_name
      perf tools: Do not use _FORTIFY_SOURCE when DEBUG=1 is specified
      perf top: Fix counter name fixup when fallbacking to cpu-clock
      perf tools: Reconstruct event with modifiers from perf_event_attr
      perf annotate browser: The idx_asm field should be used in asm only view
      perf annotate browser: Make feature toggles global
      perf config: Allow '_' in config file variable names
      perf annotate browser: Read perf config file for settings
      perf ui browser: Stop using 'self'

Franck Bui-Huu (1):
      perf tools: fix thread_map__new_by_pid_str() memory leak in error path

Namhyung Kim (8):
      tools lib traceevent: Fix a possible memory leak
      tools lib traceevent: Fix a possibly wrong memory dereference
      tools lib traceevent: Fix freeing arg on process_dynamic_array()
      tools lib traceevent: Use proper function parameter type
      tools lib traceevent: Fix signature of create_arg_item()
      tools lib traceevent: Silence compiler warning on 32bit build
      perf ui: Make --stdio default when TUI is not supported
      perf tools: Convert critical messages to ui__error()

Stefan Hajnoczi (1):
      tools lib traceevent: Allow expressions in __print_symbolic() fields

Stephane Eranian (1):
      perf record: Fix branch_stack type in perf_record_opts

Steven Rostedt (1):
      ring-buffer: Check for valid buffer before changing size


 kernel/trace/ring_buffer.c                  |   5 +
 tools/lib/traceevent/event-parse.c          |  22 +-
 tools/lib/traceevent/parse-filter.c         |   7 +-
 tools/perf/Documentation/perfconfig.example |   8 +
 tools/perf/Makefile                         |   4 +-
 tools/perf/builtin-annotate.c               |   2 +-
 tools/perf/builtin-evlist.c                 |   2 +-
 tools/perf/builtin-record.c                 |  14 +-
 tools/perf/builtin-report.c                 |  14 +-
 tools/perf/builtin-top.c                    |  24 +-
 tools/perf/perf.h                           |   2 +-
 tools/perf/ui/browser.c                     | 182 +++++++--------
 tools/perf/ui/browser.h                     |   1 +
 tools/perf/ui/browsers/annotate.c           | 262 +++++++++++++--------
 tools/perf/ui/browsers/hists.c              | 338 ++++++++++++++--------------
 tools/perf/ui/setup.c                       |   1 +
 tools/perf/util/config.c                    |   2 +-
 tools/perf/util/evsel.c                     |  90 ++++++++
 tools/perf/util/evsel.h                     |   3 +
 tools/perf/util/parse-events.c              |  27 +--
 tools/perf/util/thread_map.c                |  21 +-
 21 files changed, 615 insertions(+), 416 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6420cda..1d0f6a8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1486,6 +1486,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 	if (!buffer)
 		return size;
 
+	/* Make sure the requested buffer exists */
+	if (cpu_id != RING_BUFFER_ALL_CPUS &&
+	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
+		return size;
+
 	size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	size *= BUF_PAGE_SIZE;
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 9985349..5548282 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1434,8 +1434,11 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 fail:
 	free_token(token);
 fail_expect:
-	if (field)
+	if (field) {
+		free(field->type);
+		free(field->name);
 		free(field);
+	}
 	return -1;
 }
 
@@ -1712,6 +1715,8 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 		if (set_op_prio(arg) == -1) {
 			event->flags |= EVENT_FL_FAILED;
+			/* arg->op.op (= token) will be freed at out_free */
+			arg->op.op = NULL;
 			goto out_free;
 		}
 
@@ -2124,6 +2129,13 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 
 		free_token(token);
 		type = process_arg(event, arg, &token);
+
+		if (type == EVENT_OP)
+			type = process_op(event, arg, &token);
+
+		if (type == EVENT_ERROR)
+			goto out_free;
+
 		if (test_type_token(type, token, EVENT_DELIM, ","))
 			goto out_free;
 
@@ -2288,17 +2300,18 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 	arg = alloc_arg();
 	type = process_arg(event, arg, &token);
 	if (type == EVENT_ERROR)
-		goto out_free;
+		goto out_free_arg;
 
 	if (!test_type_token(type, token, EVENT_OP, "]"))
-		goto out_free;
+		goto out_free_arg;
 
 	free_token(token);
 	type = read_token_item(tok);
 	return type;
 
+ out_free_arg:
+	free_arg(arg);
  out_free:
-	free(arg);
 	free_token(token);
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -3362,6 +3375,7 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 			break;
 		}
 		farg = farg->next;
+		param = param->next;
 	}
 
 	ret = (*func_handle->func)(s, args);
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 2d40c5e..dfcfe2c 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -325,9 +325,8 @@ static void free_events(struct event_list *events)
 }
 
 static struct filter_arg *
-create_arg_item(struct event_format *event,
-		const char *token, enum filter_arg_type type,
-		char **error_str)
+create_arg_item(struct event_format *event, const char *token,
+		enum event_type type, char **error_str)
 {
 	struct format_field *field;
 	struct filter_arg *arg;
@@ -1585,7 +1584,7 @@ get_value(struct event_format *event,
 		const char *name;
 
 		name = get_comm(event, record);
-		return (unsigned long long)name;
+		return (unsigned long)name;
 	}
 
 	pevent_read_number_field(field, record->data, &val);
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
index 42c6fd2..767ea24 100644
--- a/tools/perf/Documentation/perfconfig.example
+++ b/tools/perf/Documentation/perfconfig.example
@@ -19,3 +19,11 @@
 
 	# Default, disable using /dev/null
 	dir = /root/.debug
+
+[annotate]
+
+	# Defaults
+	hide_src_code = false
+	use_offset = true
+	jump_arrows = true
+	show_nr_jumps = false
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1d3d513..0eee64c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -80,7 +80,7 @@ ifeq ("$(origin DEBUG)", "command line")
   PERF_DEBUG = $(DEBUG)
 endif
 ifndef PERF_DEBUG
-  CFLAGS_OPTIMIZE = -O6
+  CFLAGS_OPTIMIZE = -O6 -D_FORTIFY_SOURCE=2
 endif
 
 ifdef PARSER_DEBUG
@@ -89,7 +89,7 @@ ifdef PARSER_DEBUG
 	PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
 endif
 
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 ALL_LDFLAGS = $(LDFLAGS)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 806e0a2..67522cf 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -215,7 +215,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	}
 
 	if (total_nr_samples == 0) {
-		ui__warning("The %s file has no samples!\n", session->filename);
+		ui__error("The %s file has no samples!\n", session->filename);
 		goto out_delete;
 	}
 out_delete:
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index e52d77e..acd78dc 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -116,7 +116,7 @@ static const char * const evlist_usage[] = {
 int cmd_evlist(int argc, const char **argv, const char *prefix __used)
 {
 	struct perf_attr_details details = { .verbose = false, };
-	const char *input_name;
+	const char *input_name = NULL;
 	const struct option options[] = {
 		OPT_STRING('i', "input", &input_name, "file",
 			    "Input file name"),
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e5cb084..f95840d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -264,7 +264,7 @@ try_again:
 			}
 
 			if (err == ENOENT) {
-				ui__warning("The %s event is not supported.\n",
+				ui__error("The %s event is not supported.\n",
 					    event_name(pos));
 				exit(EXIT_FAILURE);
 			}
@@ -858,8 +858,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		usage_with_options(record_usage, record_options);
 
 	if (rec->force && rec->append_file) {
-		fprintf(stderr, "Can't overwrite and append at the same time."
-				" You need to choose between -f and -A");
+		ui__error("Can't overwrite and append at the same time."
+			  " You need to choose between -f and -A");
 		usage_with_options(record_usage, record_options);
 	} else if (rec->append_file) {
 		rec->write_mode = WRITE_APPEND;
@@ -868,8 +868,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (nr_cgroups && !rec->opts.target.system_wide) {
-		fprintf(stderr, "cgroup monitoring only available in"
-			" system-wide mode\n");
+		ui__error("cgroup monitoring only available in"
+			  " system-wide mode\n");
 		usage_with_options(record_usage, record_options);
 	}
 
@@ -905,7 +905,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		int saved_errno = errno;
 
 		perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
-		ui__warning("%s", errbuf);
+		ui__error("%s", errbuf);
 
 		err = -saved_errno;
 		goto out_free_fd;
@@ -933,7 +933,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	else if (rec->opts.freq) {
 		rec->opts.default_interval = rec->opts.freq;
 	} else {
-		fprintf(stderr, "frequency and count are zero, aborting\n");
+		ui__error("frequency and count are zero, aborting\n");
 		err = -EINVAL;
 		goto out_free_fd;
 	}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d58e414..8c767c6 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -251,13 +251,13 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 
 	if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
-			ui__warning("Selected --sort parent, but no "
+			ui__error("Selected --sort parent, but no "
 				    "callchain data. Did you call "
 				    "'perf record' without -g?\n");
 			return -EINVAL;
 		}
 		if (symbol_conf.use_callchain) {
-			ui__warning("Selected -g but no callchain data. Did "
+			ui__error("Selected -g but no callchain data. Did "
 				    "you call 'perf record' without -g?\n");
 			return -1;
 		}
@@ -266,17 +266,15 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 		   !symbol_conf.use_callchain) {
 			symbol_conf.use_callchain = true;
 			if (callchain_register_param(&callchain_param) < 0) {
-				ui__warning("Can't register callchain "
-					    "params.\n");
+				ui__error("Can't register callchain params.\n");
 				return -EINVAL;
 			}
 	}
 
 	if (sort__branch_mode == 1) {
 		if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
-			fprintf(stderr, "selected -b but no branch data."
-					" Did you call perf record without"
-					" -b?\n");
+			ui__error("Selected -b but no branch data. "
+				  "Did you call perf record without -b?\n");
 			return -1;
 		}
 	}
@@ -420,7 +418,7 @@ static int __cmd_report(struct perf_report *rep)
 	}
 
 	if (nr_samples == 0) {
-		ui__warning("The %s file has no samples!\n", session->filename);
+		ui__error("The %s file has no samples!\n", session->filename);
 		goto out_delete;
 	}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6031dce..871b540 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -953,22 +953,22 @@ try_again:
 				attr->config = PERF_COUNT_SW_CPU_CLOCK;
 				if (counter->name) {
 					free(counter->name);
-					counter->name = strdup(event_name(counter));
+					counter->name = NULL;
 				}
 				goto try_again;
 			}
 
 			if (err == ENOENT) {
-				ui__warning("The %s event is not supported.\n",
+				ui__error("The %s event is not supported.\n",
 					    event_name(counter));
 				goto out_err;
 			} else if (err == EMFILE) {
-				ui__warning("Too many events are opened.\n"
+				ui__error("Too many events are opened.\n"
 					    "Try again after reducing the number of events\n");
 				goto out_err;
 			}
 
-			ui__warning("The sys_perf_event_open() syscall "
+			ui__error("The sys_perf_event_open() syscall "
 				    "returned with %d (%s).  /bin/dmesg "
 				    "may provide additional information.\n"
 				    "No CONFIG_PERF_EVENTS=y kernel support "
@@ -978,7 +978,7 @@ try_again:
 	}
 
 	if (perf_evlist__mmap(evlist, top->mmap_pages, false) < 0) {
-		ui__warning("Failed to mmap with %d (%s)\n",
+		ui__error("Failed to mmap with %d (%s)\n",
 			    errno, strerror(errno));
 		goto out_err;
 	}
@@ -994,12 +994,12 @@ static int perf_top__setup_sample_type(struct perf_top *top)
 {
 	if (!top->sort_has_symbols) {
 		if (symbol_conf.use_callchain) {
-			ui__warning("Selected -g but \"sym\" not present in --sort/-s.");
+			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
 			return -EINVAL;
 		}
 	} else if (!top->dont_use_callchains && callchain_param.mode != CHAIN_NONE) {
 		if (callchain_register_param(&callchain_param) < 0) {
-			ui__warning("Can't register callchain params.\n");
+			ui__error("Can't register callchain params.\n");
 			return -EINVAL;
 		}
 	}
@@ -1041,7 +1041,7 @@ static int __cmd_top(struct perf_top *top)
 
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
-		printf("Could not create display thread.\n");
+		ui__error("Could not create display thread.\n");
 		exit(-1);
 	}
 
@@ -1050,7 +1050,7 @@ static int __cmd_top(struct perf_top *top)
 
 		param.sched_priority = top->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
-			printf("Could not set realtime priority.\n");
+			ui__error("Could not set realtime priority.\n");
 			exit(-1);
 		}
 	}
@@ -1274,7 +1274,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		int saved_errno = errno;
 
 		perf_target__strerror(&top.target, status, errbuf, BUFSIZ);
-		ui__warning("%s", errbuf);
+		ui__error("%s", errbuf);
 
 		status = -saved_errno;
 		goto out_delete_evlist;
@@ -1288,7 +1288,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 
 	if (!top.evlist->nr_entries &&
 	    perf_evlist__add_default(top.evlist) < 0) {
-		pr_err("Not enough memory for event selector list\n");
+		ui__error("Not enough memory for event selector list\n");
 		return -ENOMEM;
 	}
 
@@ -1305,7 +1305,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 	else if (top.freq) {
 		top.default_interval = top.freq;
 	} else {
-		fprintf(stderr, "frequency and count are zero, aborting\n");
+		ui__error("frequency and count are zero, aborting\n");
 		exit(EXIT_FAILURE);
 	}
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 14f1034..f960ccb 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -227,7 +227,7 @@ struct perf_record_opts {
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;
-	int	     branch_stack;
+	u64          branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
 };
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index cde4d0f..1818a53 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -35,16 +35,16 @@ int ui_browser__set_color(struct ui_browser *browser, int color)
 	return ret;
 }
 
-void ui_browser__set_percent_color(struct ui_browser *self,
+void ui_browser__set_percent_color(struct ui_browser *browser,
 				   double percent, bool current)
 {
-	 int color = ui_browser__percent_color(self, percent, current);
-	 ui_browser__set_color(self, color);
+	 int color = ui_browser__percent_color(browser, percent, current);
+	 ui_browser__set_color(browser, color);
 }
 
-void ui_browser__gotorc(struct ui_browser *self, int y, int x)
+void ui_browser__gotorc(struct ui_browser *browser, int y, int x)
 {
-	SLsmg_gotorc(self->y + y, self->x + x);
+	SLsmg_gotorc(browser->y + y, browser->x + x);
 }
 
 static struct list_head *
@@ -73,23 +73,23 @@ ui_browser__list_head_filter_prev_entries(struct ui_browser *browser,
 	return NULL;
 }
 
-void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence)
+void ui_browser__list_head_seek(struct ui_browser *browser, off_t offset, int whence)
 {
-	struct list_head *head = self->entries;
+	struct list_head *head = browser->entries;
 	struct list_head *pos;
 
-	if (self->nr_entries == 0)
+	if (browser->nr_entries == 0)
 		return;
 
 	switch (whence) {
 	case SEEK_SET:
-		pos = ui_browser__list_head_filter_entries(self, head->next);
+		pos = ui_browser__list_head_filter_entries(browser, head->next);
 		break;
 	case SEEK_CUR:
-		pos = self->top;
+		pos = browser->top;
 		break;
 	case SEEK_END:
-		pos = ui_browser__list_head_filter_prev_entries(self, head->prev);
+		pos = ui_browser__list_head_filter_prev_entries(browser, head->prev);
 		break;
 	default:
 		return;
@@ -99,18 +99,18 @@ void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whenc
 
 	if (offset > 0) {
 		while (offset-- != 0)
-			pos = ui_browser__list_head_filter_entries(self, pos->next);
+			pos = ui_browser__list_head_filter_entries(browser, pos->next);
 	} else {
 		while (offset++ != 0)
-			pos = ui_browser__list_head_filter_prev_entries(self, pos->prev);
+			pos = ui_browser__list_head_filter_prev_entries(browser, pos->prev);
 	}
 
-	self->top = pos;
+	browser->top = pos;
 }
 
-void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence)
+void ui_browser__rb_tree_seek(struct ui_browser *browser, off_t offset, int whence)
 {
-	struct rb_root *root = self->entries;
+	struct rb_root *root = browser->entries;
 	struct rb_node *nd;
 
 	switch (whence) {
@@ -118,7 +118,7 @@ void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence)
 		nd = rb_first(root);
 		break;
 	case SEEK_CUR:
-		nd = self->top;
+		nd = browser->top;
 		break;
 	case SEEK_END:
 		nd = rb_last(root);
@@ -135,23 +135,23 @@ void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence)
 			nd = rb_prev(nd);
 	}
 
-	self->top = nd;
+	browser->top = nd;
 }
 
-unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self)
+unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser)
 {
 	struct rb_node *nd;
 	int row = 0;
 
-	if (self->top == NULL)
-                self->top = rb_first(self->entries);
+	if (browser->top == NULL)
+                browser->top = rb_first(browser->entries);
 
-	nd = self->top;
+	nd = browser->top;
 
 	while (nd != NULL) {
-		ui_browser__gotorc(self, row, 0);
-		self->write(self, nd, row);
-		if (++row == self->height)
+		ui_browser__gotorc(browser, row, 0);
+		browser->write(browser, nd, row);
+		if (++row == browser->height)
 			break;
 		nd = rb_next(nd);
 	}
@@ -159,17 +159,17 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self)
 	return row;
 }
 
-bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row)
+bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row)
 {
-	return self->top_idx + row == self->index;
+	return browser->top_idx + row == browser->index;
 }
 
-void ui_browser__refresh_dimensions(struct ui_browser *self)
+void ui_browser__refresh_dimensions(struct ui_browser *browser)
 {
-	self->width = SLtt_Screen_Cols - 1;
-	self->height = SLtt_Screen_Rows - 2;
-	self->y = 1;
-	self->x = 0;
+	browser->width = SLtt_Screen_Cols - 1;
+	browser->height = SLtt_Screen_Rows - 2;
+	browser->y = 1;
+	browser->x = 0;
 }
 
 void ui_browser__handle_resize(struct ui_browser *browser)
@@ -225,10 +225,10 @@ bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text)
 	return key == K_ENTER || toupper(key) == 'Y';
 }
 
-void ui_browser__reset_index(struct ui_browser *self)
+void ui_browser__reset_index(struct ui_browser *browser)
 {
-	self->index = self->top_idx = 0;
-	self->seek(self, 0, SEEK_SET);
+	browser->index = browser->top_idx = 0;
+	browser->seek(browser, 0, SEEK_SET);
 }
 
 void __ui_browser__show_title(struct ui_browser *browser, const char *title)
@@ -245,26 +245,26 @@ void ui_browser__show_title(struct ui_browser *browser, const char *title)
 	pthread_mutex_unlock(&ui__lock);
 }
 
-int ui_browser__show(struct ui_browser *self, const char *title,
+int ui_browser__show(struct ui_browser *browser, const char *title,
 		     const char *helpline, ...)
 {
 	int err;
 	va_list ap;
 
-	ui_browser__refresh_dimensions(self);
+	ui_browser__refresh_dimensions(browser);
 
 	pthread_mutex_lock(&ui__lock);
-	__ui_browser__show_title(self, title);
+	__ui_browser__show_title(browser, title);
 
-	self->title = title;
-	free(self->helpline);
-	self->helpline = NULL;
+	browser->title = title;
+	free(browser->helpline);
+	browser->helpline = NULL;
 
 	va_start(ap, helpline);
-	err = vasprintf(&self->helpline, helpline, ap);
+	err = vasprintf(&browser->helpline, helpline, ap);
 	va_end(ap);
 	if (err > 0)
-		ui_helpline__push(self->helpline);
+		ui_helpline__push(browser->helpline);
 	pthread_mutex_unlock(&ui__lock);
 	return err ? 0 : -1;
 }
@@ -350,7 +350,7 @@ void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries)
 	browser->seek(browser, browser->top_idx, SEEK_SET);
 }
 
-int ui_browser__run(struct ui_browser *self, int delay_secs)
+int ui_browser__run(struct ui_browser *browser, int delay_secs)
 {
 	int err, key;
 
@@ -358,7 +358,7 @@ int ui_browser__run(struct ui_browser *self, int delay_secs)
 		off_t offset;
 
 		pthread_mutex_lock(&ui__lock);
-		err = __ui_browser__refresh(self);
+		err = __ui_browser__refresh(browser);
 		SLsmg_refresh();
 		pthread_mutex_unlock(&ui__lock);
 		if (err < 0)
@@ -368,18 +368,18 @@ int ui_browser__run(struct ui_browser *self, int delay_secs)
 
 		if (key == K_RESIZE) {
 			ui__refresh_dimensions(false);
-			ui_browser__refresh_dimensions(self);
-			__ui_browser__show_title(self, self->title);
-			ui_helpline__puts(self->helpline);
+			ui_browser__refresh_dimensions(browser);
+			__ui_browser__show_title(browser, browser->title);
+			ui_helpline__puts(browser->helpline);
 			continue;
 		}
 
-		if (self->use_navkeypressed && !self->navkeypressed) {
+		if (browser->use_navkeypressed && !browser->navkeypressed) {
 			if (key == K_DOWN || key == K_UP ||
 			    key == K_PGDN || key == K_PGUP ||
 			    key == K_HOME || key == K_END ||
 			    key == ' ') {
-				self->navkeypressed = true;
+				browser->navkeypressed = true;
 				continue;
 			} else
 				return key;
@@ -387,59 +387,59 @@ int ui_browser__run(struct ui_browser *self, int delay_secs)
 
 		switch (key) {
 		case K_DOWN:
-			if (self->index == self->nr_entries - 1)
+			if (browser->index == browser->nr_entries - 1)
 				break;
-			++self->index;
-			if (self->index == self->top_idx + self->height) {
-				++self->top_idx;
-				self->seek(self, +1, SEEK_CUR);
+			++browser->index;
+			if (browser->index == browser->top_idx + browser->height) {
+				++browser->top_idx;
+				browser->seek(browser, +1, SEEK_CUR);
 			}
 			break;
 		case K_UP:
-			if (self->index == 0)
+			if (browser->index == 0)
 				break;
-			--self->index;
-			if (self->index < self->top_idx) {
-				--self->top_idx;
-				self->seek(self, -1, SEEK_CUR);
+			--browser->index;
+			if (browser->index < browser->top_idx) {
+				--browser->top_idx;
+				browser->seek(browser, -1, SEEK_CUR);
 			}
 			break;
 		case K_PGDN:
 		case ' ':
-			if (self->top_idx + self->height > self->nr_entries - 1)
+			if (browser->top_idx + browser->height > browser->nr_entries - 1)
 				break;
 
-			offset = self->height;
-			if (self->index + offset > self->nr_entries - 1)
-				offset = self->nr_entries - 1 - self->index;
-			self->index += offset;
-			self->top_idx += offset;
-			self->seek(self, +offset, SEEK_CUR);
+			offset = browser->height;
+			if (browser->index + offset > browser->nr_entries - 1)
+				offset = browser->nr_entries - 1 - browser->index;
+			browser->index += offset;
+			browser->top_idx += offset;
+			browser->seek(browser, +offset, SEEK_CUR);
 			break;
 		case K_PGUP:
-			if (self->top_idx == 0)
+			if (browser->top_idx == 0)
 				break;
 
-			if (self->top_idx < self->height)
-				offset = self->top_idx;
+			if (browser->top_idx < browser->height)
+				offset = browser->top_idx;
 			else
-				offset = self->height;
+				offset = browser->height;
 
-			self->index -= offset;
-			self->top_idx -= offset;
-			self->seek(self, -offset, SEEK_CUR);
+			browser->index -= offset;
+			browser->top_idx -= offset;
+			browser->seek(browser, -offset, SEEK_CUR);
 			break;
 		case K_HOME:
-			ui_browser__reset_index(self);
+			ui_browser__reset_index(browser);
 			break;
 		case K_END:
-			offset = self->height - 1;
-			if (offset >= self->nr_entries)
-				offset = self->nr_entries - 1;
+			offset = browser->height - 1;
+			if (offset >= browser->nr_entries)
+				offset = browser->nr_entries - 1;
 
-			self->index = self->nr_entries - 1;
-			self->top_idx = self->index - offset;
-			self->seek(self, -offset, SEEK_END);
+			browser->index = browser->nr_entries - 1;
+			browser->top_idx = browser->index - offset;
+			browser->seek(browser, -offset, SEEK_END);
 			break;
 		default:
 			return key;
@@ -448,22 +448,22 @@ int ui_browser__run(struct ui_browser *self, int delay_secs)
 	return -1;
 }
 
-unsigned int ui_browser__list_head_refresh(struct ui_browser *self)
+unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)
 {
 	struct list_head *pos;
-	struct list_head *head = self->entries;
+	struct list_head *head = browser->entries;
 	int row = 0;
 
-	if (self->top == NULL || self->top == self->entries)
-                self->top = ui_browser__list_head_filter_entries(self, head->next);
+	if (browser->top == NULL || browser->top == browser->entries)
+                browser->top = ui_browser__list_head_filter_entries(browser, head->next);
 
-	pos = self->top;
+	pos = browser->top;
 
 	list_for_each_from(pos, head) {
-		if (!self->filter || !self->filter(self, pos)) {
-			ui_browser__gotorc(self, row, 0);
-			self->write(self, pos, row);
-			if (++row == self->height)
+		if (!browser->filter || !browser->filter(browser, pos)) {
+			ui_browser__gotorc(browser, row, 0);
+			browser->write(browser, pos, row);
+			if (++row == browser->height)
 				break;
 		}
 	}
@@ -708,4 +708,6 @@ void ui_browser__init(void)
 		struct ui_browser__colorset *c = &ui_browser__colorsets[i++];
 		sltt_set_color(c->colorset, c->name, c->fg, c->bg);
 	}
+
+	annotate_browser__init();
 }
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index dd96d82..af70314 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -69,4 +69,5 @@ void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whenc
 unsigned int ui_browser__list_head_refresh(struct ui_browser *self);
 
 void ui_browser__init(void);
+void annotate_browser__init(void);
 #endif /* _PERF_UI_BROWSER_H_ */
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 6e0ef79..4deea6a 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -19,6 +19,16 @@ struct browser_disasm_line {
 	int		jump_sources;
 };
 
+static struct annotate_browser_opt {
+	bool hide_src_code,
+	     use_offset,
+	     jump_arrows,
+	     show_nr_jumps;
+} annotate_browser__opts = {
+	.use_offset	= true,
+	.jump_arrows	= true,
+};
+
 struct annotate_browser {
 	struct ui_browser b;
 	struct rb_root	  entries;
@@ -30,10 +40,6 @@ struct annotate_browser {
 	int		    nr_entries;
 	int		    max_jump_sources;
 	int		    nr_jumps;
-	bool		    hide_src_code;
-	bool		    use_offset;
-	bool		    jump_arrows;
-	bool		    show_nr_jumps;
 	bool		    searching_backwards;
 	u8		    addr_width;
 	u8		    jumps_width;
@@ -48,11 +54,9 @@ static inline struct browser_disasm_line *disasm_line__browser(struct disasm_lin
 	return (struct browser_disasm_line *)(dl + 1);
 }
 
-static bool disasm_line__filter(struct ui_browser *browser, void *entry)
+static bool disasm_line__filter(struct ui_browser *browser __used, void *entry)
 {
-	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
-
-	if (ab->hide_src_code) {
+	if (annotate_browser__opts.hide_src_code) {
 		struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
 		return dl->offset == -1;
 	}
@@ -79,30 +83,30 @@ static int annotate_browser__set_jumps_percent_color(struct annotate_browser *br
 	 return ui_browser__set_color(&browser->b, color);
 }
 
-static void annotate_browser__write(struct ui_browser *self, void *entry, int row)
+static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
 {
-	struct annotate_browser *ab = container_of(self, struct annotate_browser, b);
+	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
 	struct browser_disasm_line *bdl = disasm_line__browser(dl);
-	bool current_entry = ui_browser__is_current_entry(self, row);
-	bool change_color = (!ab->hide_src_code &&
-			     (!current_entry || (self->use_navkeypressed &&
-					         !self->navkeypressed)));
-	int width = self->width, printed;
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	bool change_color = (!annotate_browser__opts.hide_src_code &&
+			     (!current_entry || (browser->use_navkeypressed &&
+					         !browser->navkeypressed)));
+	int width = browser->width, printed;
 	char bf[256];
 
 	if (dl->offset != -1 && bdl->percent != 0.0) {
-		ui_browser__set_percent_color(self, bdl->percent, current_entry);
+		ui_browser__set_percent_color(browser, bdl->percent, current_entry);
 		slsmg_printf("%6.2f ", bdl->percent);
 	} else {
-		ui_browser__set_percent_color(self, 0, current_entry);
+		ui_browser__set_percent_color(browser, 0, current_entry);
 		slsmg_write_nstring(" ", 7);
 	}
 
 	SLsmg_write_char(' ');
 
 	/* The scroll bar isn't being used */
-	if (!self->navkeypressed)
+	if (!browser->navkeypressed)
 		width += 1;
 
 	if (!*dl->line)
@@ -116,14 +120,14 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 		u64 addr = dl->offset;
 		int color = -1;
 
-		if (!ab->use_offset)
+		if (!annotate_browser__opts.use_offset)
 			addr += ab->start;
 
-		if (!ab->use_offset) {
+		if (!annotate_browser__opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
 			if (bdl->jump_sources) {
-				if (ab->show_nr_jumps) {
+				if (annotate_browser__opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
 							    ab->jumps_width,
@@ -131,7 +135,7 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 					prev = annotate_browser__set_jumps_percent_color(ab, bdl->jump_sources,
 											 current_entry);
 					slsmg_write_nstring(bf, printed);
-					ui_browser__set_color(self, prev);
+					ui_browser__set_color(browser, prev);
 				}
 
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
@@ -143,19 +147,19 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 		}
 
 		if (change_color)
-			color = ui_browser__set_color(self, HE_COLORSET_ADDR);
+			color = ui_browser__set_color(browser, HE_COLORSET_ADDR);
 		slsmg_write_nstring(bf, printed);
 		if (change_color)
-			ui_browser__set_color(self, color);
+			ui_browser__set_color(browser, color);
 		if (dl->ins && dl->ins->ops->scnprintf) {
 			if (ins__is_jump(dl->ins)) {
 				bool fwd = dl->ops.target.offset > (u64)dl->offset;
 
-				ui_browser__write_graph(self, fwd ? SLSMG_DARROW_CHAR :
+				ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
 								    SLSMG_UARROW_CHAR);
 				SLsmg_write_char(' ');
 			} else if (ins__is_call(dl->ins)) {
-				ui_browser__write_graph(self, SLSMG_RARROW_CHAR);
+				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
 				SLsmg_write_char(' ');
 			} else {
 				slsmg_write_nstring(" ", 2);
@@ -164,12 +168,12 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 			if (strcmp(dl->name, "retq")) {
 				slsmg_write_nstring(" ", 2);
 			} else {
-				ui_browser__write_graph(self, SLSMG_LARROW_CHAR);
+				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
 				SLsmg_write_char(' ');
 			}
 		}
 
-		disasm_line__scnprintf(dl, bf, sizeof(bf), !ab->use_offset);
+		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
 		slsmg_write_nstring(bf, width - 10 - printed);
 	}
 
@@ -184,7 +188,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	struct browser_disasm_line *btarget, *bcursor;
 	unsigned int from, to;
 
-	if (!cursor->ins || !ins__is_jump(cursor->ins) ||
+	if (!cursor || !cursor->ins || !ins__is_jump(cursor->ins) ||
 	    !disasm_line__has_offset(cursor))
 		return;
 
@@ -195,7 +199,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	bcursor = disasm_line__browser(cursor);
 	btarget = disasm_line__browser(target);
 
-	if (ab->hide_src_code) {
+	if (annotate_browser__opts.hide_src_code) {
 		from = bcursor->idx_asm;
 		to = btarget->idx_asm;
 	} else {
@@ -209,10 +213,9 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 
 static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 {
-	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	int ret = ui_browser__list_head_refresh(browser);
 
-	if (ab->jump_arrows)
+	if (annotate_browser__opts.jump_arrows)
 		annotate_browser__draw_current_jump(browser);
 
 	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
@@ -272,27 +275,27 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_l
 	rb_insert_color(&bdl->rb_node, root);
 }
 
-static void annotate_browser__set_top(struct annotate_browser *self,
+static void annotate_browser__set_top(struct annotate_browser *browser,
 				      struct disasm_line *pos, u32 idx)
 {
 	unsigned back;
 
-	ui_browser__refresh_dimensions(&self->b);
-	back = self->b.height / 2;
-	self->b.top_idx = self->b.index = idx;
+	ui_browser__refresh_dimensions(&browser->b);
+	back = browser->b.height / 2;
+	browser->b.top_idx = browser->b.index = idx;
 
-	while (self->b.top_idx != 0 && back != 0) {
+	while (browser->b.top_idx != 0 && back != 0) {
 		pos = list_entry(pos->node.prev, struct disasm_line, node);
 
-		if (disasm_line__filter(&self->b, &pos->node))
+		if (disasm_line__filter(&browser->b, &pos->node))
 			continue;
 
-		--self->b.top_idx;
+		--browser->b.top_idx;
 		--back;
 	}
 
-	self->b.top = pos;
-	self->b.navkeypressed = true;
+	browser->b.top = pos;
+	browser->b.navkeypressed = true;
 }
 
 static void annotate_browser__set_rb_top(struct annotate_browser *browser,
@@ -300,10 +303,14 @@ static void annotate_browser__set_rb_top(struct annotate_browser *browser,
 {
 	struct browser_disasm_line *bpos;
 	struct disasm_line *pos;
+	u32 idx;
 
 	bpos = rb_entry(nd, struct browser_disasm_line, rb_node);
 	pos = ((struct disasm_line *)bpos) - 1;
-	annotate_browser__set_top(browser, pos, bpos->idx);
+	idx = bpos->idx;
+	if (annotate_browser__opts.hide_src_code)
+		idx = bpos->idx_asm;
+	annotate_browser__set_top(browser, pos, idx);
 	browser->curr_hot = nd;
 }
 
@@ -343,12 +350,12 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 	dl = list_entry(browser->b.top, struct disasm_line, node);
 	bdl = disasm_line__browser(dl);
 
-	if (browser->hide_src_code) {
+	if (annotate_browser__opts.hide_src_code) {
 		if (bdl->idx_asm < offset)
 			offset = bdl->idx;
 
 		browser->b.nr_entries = browser->nr_entries;
-		browser->hide_src_code = false;
+		annotate_browser__opts.hide_src_code = false;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = bdl->idx - offset;
 		browser->b.index = bdl->idx;
@@ -363,7 +370,7 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 			offset = bdl->idx_asm;
 
 		browser->b.nr_entries = browser->nr_asm_entries;
-		browser->hide_src_code = true;
+		annotate_browser__opts.hide_src_code = true;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = bdl->idx_asm - offset;
 		browser->b.index = bdl->idx_asm;
@@ -372,6 +379,12 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 	return true;
 }
 
+static void annotate_browser__init_asm_mode(struct annotate_browser *browser)
+{
+	ui_browser__reset_index(&browser->b);
+	browser->b.nr_entries = browser->nr_asm_entries;
+}
+
 static bool annotate_browser__callq(struct annotate_browser *browser,
 				    int evidx, void (*timer)(void *arg),
 				    void *arg, int delay_secs)
@@ -574,33 +587,46 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
 	return __annotate_browser__search_reverse(browser);
 }
 
-static int annotate_browser__run(struct annotate_browser *self, int evidx,
+static void annotate_browser__update_addr_width(struct annotate_browser *browser)
+{
+	if (annotate_browser__opts.use_offset)
+		browser->target_width = browser->min_addr_width;
+	else
+		browser->target_width = browser->max_addr_width;
+
+	browser->addr_width = browser->target_width;
+
+	if (annotate_browser__opts.show_nr_jumps)
+		browser->addr_width += browser->jumps_width + 1;
+}
+
+static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 				 void(*timer)(void *arg),
 				 void *arg, int delay_secs)
 {
 	struct rb_node *nd = NULL;
-	struct map_symbol *ms = self->b.priv;
+	struct map_symbol *ms = browser->b.priv;
 	struct symbol *sym = ms->sym;
 	const char *help = "Press 'h' for help on key bindings";
 	int key;
 
-	if (ui_browser__show(&self->b, sym->name, help) < 0)
+	if (ui_browser__show(&browser->b, sym->name, help) < 0)
 		return -1;
 
-	annotate_browser__calc_percent(self, evidx);
+	annotate_browser__calc_percent(browser, evidx);
 
-	if (self->curr_hot) {
-		annotate_browser__set_rb_top(self, self->curr_hot);
-		self->b.navkeypressed = false;
+	if (browser->curr_hot) {
+		annotate_browser__set_rb_top(browser, browser->curr_hot);
+		browser->b.navkeypressed = false;
 	}
 
-	nd = self->curr_hot;
+	nd = browser->curr_hot;
 
 	while (1) {
-		key = ui_browser__run(&self->b, delay_secs);
+		key = ui_browser__run(&browser->b, delay_secs);
 
 		if (delay_secs != 0) {
-			annotate_browser__calc_percent(self, evidx);
+			annotate_browser__calc_percent(browser, evidx);
 			/*
 			 * Current line focus got out of the list of most active
 			 * lines, NULL it so that if TAB|UNTAB is pressed, we
@@ -622,21 +648,21 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx,
 			if (nd != NULL) {
 				nd = rb_prev(nd);
 				if (nd == NULL)
-					nd = rb_last(&self->entries);
+					nd = rb_last(&browser->entries);
 			} else
-				nd = self->curr_hot;
+				nd = browser->curr_hot;
 			break;
 		case K_UNTAB:
 			if (nd != NULL)
 				nd = rb_next(nd);
 				if (nd == NULL)
-					nd = rb_first(&self->entries);
+					nd = rb_first(&browser->entries);
 			else
-				nd = self->curr_hot;
+				nd = browser->curr_hot;
 			break;
 		case K_F1:
 		case 'h':
-			ui_browser__help_window(&self->b,
+			ui_browser__help_window(&browser->b,
 		"UP/DOWN/PGUP\n"
 		"PGDN/SPACE    Navigate\n"
 		"q/ESC/CTRL+C  Exit\n\n"
@@ -652,57 +678,62 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx,
 		"?             Search previous string\n");
 			continue;
 		case 'H':
-			nd = self->curr_hot;
+			nd = browser->curr_hot;
 			break;
 		case 's':
-			if (annotate_browser__toggle_source(self))
+			if (annotate_browser__toggle_source(browser))
 				ui_helpline__puts(help);
 			continue;
 		case 'o':
-			self->use_offset = !self->use_offset;
-			if (self->use_offset)
-				self->target_width = self->min_addr_width;
-			else
-				self->target_width = self->max_addr_width;
-update_addr_width:
-			self->addr_width = self->target_width;
-			if (self->show_nr_jumps)
-				self->addr_width += self->jumps_width + 1;
+			annotate_browser__opts.use_offset = !annotate_browser__opts.use_offset;
+			annotate_browser__update_addr_width(browser);
 			continue;
 		case 'j':
-			self->jump_arrows = !self->jump_arrows;
+			annotate_browser__opts.jump_arrows = !annotate_browser__opts.jump_arrows;
 			continue;
 		case 'J':
-			self->show_nr_jumps = !self->show_nr_jumps;
-			goto update_addr_width;
+			annotate_browser__opts.show_nr_jumps = !annotate_browser__opts.show_nr_jumps;
+			annotate_browser__update_addr_width(browser);
+			continue;
 		case '/':
-			if (annotate_browser__search(self, delay_secs)) {
+			if (annotate_browser__search(browser, delay_secs)) {
 show_help:
 				ui_helpline__puts(help);
 			}
 			continue;
 		case 'n':
-			if (self->searching_backwards ?
-			    annotate_browser__continue_search_reverse(self, delay_secs) :
-			    annotate_browser__continue_search(self, delay_secs))
+			if (browser->searching_backwards ?
+			    annotate_browser__continue_search_reverse(browser, delay_secs) :
+			    annotate_browser__continue_search(browser, delay_secs))
 				goto show_help;
 			continue;
 		case '?':
-			if (annotate_browser__search_reverse(self, delay_secs))
+			if (annotate_browser__search_reverse(browser, delay_secs))
 				goto show_help;
 			continue;
+		case 'D': {
+			static int seq;
+			ui_helpline__pop();
+			ui_helpline__fpush("%d: nr_ent=%d, height=%d, idx=%d, top_idx=%d, nr_asm_entries=%d",
+					   seq++, browser->b.nr_entries,
+					   browser->b.height,
+					   browser->b.index,
+					   browser->b.top_idx,
+					   browser->nr_asm_entries);
+		}
+			continue;
 		case K_ENTER:
 		case K_RIGHT:
-			if (self->selection == NULL)
+			if (browser->selection == NULL)
 				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
-			else if (self->selection->offset == -1)
+			else if (browser->selection->offset == -1)
 				ui_helpline__puts("Actions are only available for assembly lines.");
-			else if (!self->selection->ins) {
-				if (strcmp(self->selection->name, "retq"))
+			else if (!browser->selection->ins) {
+				if (strcmp(browser->selection->name, "retq"))
 					goto show_sup_ins;
 				goto out;
-			} else if (!(annotate_browser__jump(self) ||
-				     annotate_browser__callq(self, evidx, timer, arg, delay_secs))) {
+			} else if (!(annotate_browser__jump(browser) ||
+				     annotate_browser__callq(browser, evidx, timer, arg, delay_secs))) {
 show_sup_ins:
 				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
 			}
@@ -717,10 +748,10 @@ show_sup_ins:
 		}
 
 		if (nd != NULL)
-			annotate_browser__set_rb_top(self, nd);
+			annotate_browser__set_rb_top(browser, nd);
 	}
 out:
-	ui_browser__hide(&self->b);
+	ui_browser__hide(&browser->b);
 	return key;
 }
 
@@ -797,8 +828,6 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 			.priv	 = &ms,
 			.use_navkeypressed = true,
 		},
-		.use_offset = true,
-		.jump_arrows = true,
 	};
 	int ret = -1;
 
@@ -855,6 +884,12 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 	browser.b.nr_entries = browser.nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
+
+	if (annotate_browser__opts.hide_src_code)
+		annotate_browser__init_asm_mode(&browser);
+
+	annotate_browser__update_addr_width(&browser);
+
 	ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs);
 	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
 		list_del(&pos->node);
@@ -865,3 +900,52 @@ out_free_offsets:
 	free(browser.offsets);
 	return ret;
 }
+
+#define ANNOTATE_CFG(n) \
+	{ .name = #n, .value = &annotate_browser__opts.n, }
+	
+/*
+ * Keep the entries sorted, they are bsearch'ed
+ */
+static struct annotate__config {
+	const char *name;
+	bool *value;
+} annotate__configs[] = {
+	ANNOTATE_CFG(hide_src_code),
+	ANNOTATE_CFG(jump_arrows),
+	ANNOTATE_CFG(show_nr_jumps),
+	ANNOTATE_CFG(use_offset),
+};
+
+#undef ANNOTATE_CFG
+
+static int annotate_config__cmp(const void *name, const void *cfgp)
+{
+	const struct annotate__config *cfg = cfgp;
+
+	return strcmp(name, cfg->name);
+}
+
+static int annotate__config(const char *var, const char *value, void *data __used)
+{
+	struct annotate__config *cfg;
+	const char *name;
+
+	if (prefixcmp(var, "annotate.") != 0)
+		return 0;
+
+	name = var + 9;
+	cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs),
+		      sizeof(struct annotate__config), annotate_config__cmp);
+
+	if (cfg == NULL)
+		return -1;
+
+	*cfg->value = perf_config_bool(name, value);
+	return 0;
+}
+
+void annotate_browser__init(void)
+{
+	perf_config(annotate__config, NULL);
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a372a4b..53f6697 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -26,21 +26,21 @@ struct hist_browser {
 	bool		     has_symbols;
 };
 
-static int hists__browser_title(struct hists *self, char *bf, size_t size,
+static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 				const char *ev_name);
 
-static void hist_browser__refresh_dimensions(struct hist_browser *self)
+static void hist_browser__refresh_dimensions(struct hist_browser *browser)
 {
 	/* 3 == +/- toggle symbol before actual hist_entry rendering */
-	self->b.width = 3 + (hists__sort_list_width(self->hists) +
+	browser->b.width = 3 + (hists__sort_list_width(browser->hists) +
 			     sizeof("[k]"));
 }
 
-static void hist_browser__reset(struct hist_browser *self)
+static void hist_browser__reset(struct hist_browser *browser)
 {
-	self->b.nr_entries = self->hists->nr_entries;
-	hist_browser__refresh_dimensions(self);
-	ui_browser__reset_index(&self->b);
+	browser->b.nr_entries = browser->hists->nr_entries;
+	hist_browser__refresh_dimensions(browser);
+	ui_browser__reset_index(&browser->b);
 }
 
 static char tree__folded_sign(bool unfolded)
@@ -48,32 +48,32 @@ static char tree__folded_sign(bool unfolded)
 	return unfolded ? '-' : '+';
 }
 
-static char map_symbol__folded(const struct map_symbol *self)
+static char map_symbol__folded(const struct map_symbol *ms)
 {
-	return self->has_children ? tree__folded_sign(self->unfolded) : ' ';
+	return ms->has_children ? tree__folded_sign(ms->unfolded) : ' ';
 }
 
-static char hist_entry__folded(const struct hist_entry *self)
+static char hist_entry__folded(const struct hist_entry *he)
 {
-	return map_symbol__folded(&self->ms);
+	return map_symbol__folded(&he->ms);
 }
 
-static char callchain_list__folded(const struct callchain_list *self)
+static char callchain_list__folded(const struct callchain_list *cl)
 {
-	return map_symbol__folded(&self->ms);
+	return map_symbol__folded(&cl->ms);
 }
 
-static void map_symbol__set_folding(struct map_symbol *self, bool unfold)
+static void map_symbol__set_folding(struct map_symbol *ms, bool unfold)
 {
-	self->unfolded = unfold ? self->has_children : false;
+	ms->unfolded = unfold ? ms->has_children : false;
 }
 
-static int callchain_node__count_rows_rb_tree(struct callchain_node *self)
+static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
 	int n = 0;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
 		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
 		struct callchain_list *chain;
 		char folded_sign = ' '; /* No children */
@@ -123,23 +123,23 @@ static int callchain__count_rows(struct rb_root *chain)
 	return n;
 }
 
-static bool map_symbol__toggle_fold(struct map_symbol *self)
+static bool map_symbol__toggle_fold(struct map_symbol *ms)
 {
-	if (!self)
+	if (!ms)
 		return false;
 
-	if (!self->has_children)
+	if (!ms->has_children)
 		return false;
 
-	self->unfolded = !self->unfolded;
+	ms->unfolded = !ms->unfolded;
 	return true;
 }
 
-static void callchain_node__init_have_children_rb_tree(struct callchain_node *self)
+static void callchain_node__init_have_children_rb_tree(struct callchain_node *node)
 {
-	struct rb_node *nd = rb_first(&self->rb_root);
+	struct rb_node *nd = rb_first(&node->rb_root);
 
-	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
 		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
 		struct callchain_list *chain;
 		bool first = true;
@@ -158,49 +158,49 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *se
 	}
 }
 
-static void callchain_node__init_have_children(struct callchain_node *self)
+static void callchain_node__init_have_children(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 
-	list_for_each_entry(chain, &self->val, list)
-		chain->ms.has_children = !RB_EMPTY_ROOT(&self->rb_root);
+	list_for_each_entry(chain, &node->val, list)
+		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
 
-	callchain_node__init_have_children_rb_tree(self);
+	callchain_node__init_have_children_rb_tree(node);
 }
 
-static void callchain__init_have_children(struct rb_root *self)
+static void callchain__init_have_children(struct rb_root *root)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
 		callchain_node__init_have_children(node);
 	}
 }
 
-static void hist_entry__init_have_children(struct hist_entry *self)
+static void hist_entry__init_have_children(struct hist_entry *he)
 {
-	if (!self->init_have_children) {
-		self->ms.has_children = !RB_EMPTY_ROOT(&self->sorted_chain);
-		callchain__init_have_children(&self->sorted_chain);
-		self->init_have_children = true;
+	if (!he->init_have_children) {
+		he->ms.has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
+		callchain__init_have_children(&he->sorted_chain);
+		he->init_have_children = true;
 	}
 }
 
-static bool hist_browser__toggle_fold(struct hist_browser *self)
+static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
-	if (map_symbol__toggle_fold(self->selection)) {
-		struct hist_entry *he = self->he_selection;
+	if (map_symbol__toggle_fold(browser->selection)) {
+		struct hist_entry *he = browser->he_selection;
 
 		hist_entry__init_have_children(he);
-		self->hists->nr_entries -= he->nr_rows;
+		browser->hists->nr_entries -= he->nr_rows;
 
 		if (he->ms.unfolded)
 			he->nr_rows = callchain__count_rows(&he->sorted_chain);
 		else
 			he->nr_rows = 0;
-		self->hists->nr_entries += he->nr_rows;
-		self->b.nr_entries = self->hists->nr_entries;
+		browser->hists->nr_entries += he->nr_rows;
+		browser->b.nr_entries = browser->hists->nr_entries;
 
 		return true;
 	}
@@ -209,12 +209,12 @@ static bool hist_browser__toggle_fold(struct hist_browser *self)
 	return false;
 }
 
-static int callchain_node__set_folding_rb_tree(struct callchain_node *self, bool unfold)
+static int callchain_node__set_folding_rb_tree(struct callchain_node *node, bool unfold)
 {
 	int n = 0;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
 		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
 		struct callchain_list *chain;
 		bool has_children = false;
@@ -263,37 +263,37 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
 	return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *self, bool unfold)
+static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
 {
-	hist_entry__init_have_children(self);
-	map_symbol__set_folding(&self->ms, unfold);
+	hist_entry__init_have_children(he);
+	map_symbol__set_folding(&he->ms, unfold);
 
-	if (self->ms.has_children) {
-		int n = callchain__set_folding(&self->sorted_chain, unfold);
-		self->nr_rows = unfold ? n : 0;
+	if (he->ms.has_children) {
+		int n = callchain__set_folding(&he->sorted_chain, unfold);
+		he->nr_rows = unfold ? n : 0;
 	} else
-		self->nr_rows = 0;
+		he->nr_rows = 0;
 }
 
-static void hists__set_folding(struct hists *self, bool unfold)
+static void hists__set_folding(struct hists *hists, bool unfold)
 {
 	struct rb_node *nd;
 
-	self->nr_entries = 0;
+	hists->nr_entries = 0;
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		hist_entry__set_folding(he, unfold);
-		self->nr_entries += 1 + he->nr_rows;
+		hists->nr_entries += 1 + he->nr_rows;
 	}
 }
 
-static void hist_browser__set_folding(struct hist_browser *self, bool unfold)
+static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
-	hists__set_folding(self->hists, unfold);
-	self->b.nr_entries = self->hists->nr_entries;
+	hists__set_folding(browser->hists, unfold);
+	browser->b.nr_entries = browser->hists->nr_entries;
 	/* Go to the start, we may be way after valid entries after a collapse */
-	ui_browser__reset_index(&self->b);
+	ui_browser__reset_index(&browser->b);
 }
 
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
@@ -305,64 +305,64 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *self, const char *ev_name,
+static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			     void(*timer)(void *arg), void *arg, int delay_secs)
 {
 	int key;
 	char title[160];
 
-	self->b.entries = &self->hists->entries;
-	self->b.nr_entries = self->hists->nr_entries;
+	browser->b.entries = &browser->hists->entries;
+	browser->b.nr_entries = browser->hists->nr_entries;
 
-	hist_browser__refresh_dimensions(self);
-	hists__browser_title(self->hists, title, sizeof(title), ev_name);
+	hist_browser__refresh_dimensions(browser);
+	hists__browser_title(browser->hists, title, sizeof(title), ev_name);
 
-	if (ui_browser__show(&self->b, title,
+	if (ui_browser__show(&browser->b, title,
 			     "Press '?' for help on key bindings") < 0)
 		return -1;
 
 	while (1) {
-		key = ui_browser__run(&self->b, delay_secs);
+		key = ui_browser__run(&browser->b, delay_secs);
 
 		switch (key) {
 		case K_TIMER:
 			timer(arg);
-			ui_browser__update_nr_entries(&self->b, self->hists->nr_entries);
+			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
 
-			if (self->hists->stats.nr_lost_warned !=
-			    self->hists->stats.nr_events[PERF_RECORD_LOST]) {
-				self->hists->stats.nr_lost_warned =
-					self->hists->stats.nr_events[PERF_RECORD_LOST];
-				ui_browser__warn_lost_events(&self->b);
+			if (browser->hists->stats.nr_lost_warned !=
+			    browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
+				browser->hists->stats.nr_lost_warned =
+					browser->hists->stats.nr_events[PERF_RECORD_LOST];
+				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(self->hists, title, sizeof(title), ev_name);
-			ui_browser__show_title(&self->b, title);
+			hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+			ui_browser__show_title(&browser->b, title);
 			continue;
 		case 'D': { /* Debug */
 			static int seq;
-			struct hist_entry *h = rb_entry(self->b.top,
+			struct hist_entry *h = rb_entry(browser->b.top,
 							struct hist_entry, rb_node);
 			ui_helpline__pop();
 			ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
-					   seq++, self->b.nr_entries,
-					   self->hists->nr_entries,
-					   self->b.height,
-					   self->b.index,
-					   self->b.top_idx,
+					   seq++, browser->b.nr_entries,
+					   browser->hists->nr_entries,
+					   browser->b.height,
+					   browser->b.index,
+					   browser->b.top_idx,
 					   h->row_offset, h->nr_rows);
 		}
 			break;
 		case 'C':
 			/* Collapse the whole world. */
-			hist_browser__set_folding(self, false);
+			hist_browser__set_folding(browser, false);
 			break;
 		case 'E':
 			/* Expand the whole world. */
-			hist_browser__set_folding(self, true);
+			hist_browser__set_folding(browser, true);
 			break;
 		case K_ENTER:
-			if (hist_browser__toggle_fold(self))
+			if (hist_browser__toggle_fold(browser))
 				break;
 			/* fall thru */
 		default:
@@ -370,23 +370,23 @@ static int hist_browser__run(struct hist_browser *self, const char *ev_name,
 		}
 	}
 out:
-	ui_browser__hide(&self->b);
+	ui_browser__hide(&browser->b);
 	return key;
 }
 
-static char *callchain_list__sym_name(struct callchain_list *self,
+static char *callchain_list__sym_name(struct callchain_list *cl,
 				      char *bf, size_t bfsize)
 {
-	if (self->ms.sym)
-		return self->ms.sym->name;
+	if (cl->ms.sym)
+		return cl->ms.sym->name;
 
-	snprintf(bf, bfsize, "%#" PRIx64, self->ip);
+	snprintf(bf, bfsize, "%#" PRIx64, cl->ip);
 	return bf;
 }
 
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
+static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser,
 						     struct callchain_node *chain_node,
 						     u64 total, int level,
 						     unsigned short row,
@@ -444,21 +444,21 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
 			}
 
 			color = HE_COLORSET_NORMAL;
-			width = self->b.width - (offset + extra_offset + 2);
-			if (ui_browser__is_current_entry(&self->b, row)) {
-				self->selection = &chain->ms;
+			width = browser->b.width - (offset + extra_offset + 2);
+			if (ui_browser__is_current_entry(&browser->b, row)) {
+				browser->selection = &chain->ms;
 				color = HE_COLORSET_SELECTED;
 				*is_current_entry = true;
 			}
 
-			ui_browser__set_color(&self->b, color);
-			ui_browser__gotorc(&self->b, row, 0);
+			ui_browser__set_color(&browser->b, color);
+			ui_browser__gotorc(&browser->b, row, 0);
 			slsmg_write_nstring(" ", offset + extra_offset);
 			slsmg_printf("%c ", folded_sign);
 			slsmg_write_nstring(str, width);
 			free(alloc_str);
 
-			if (++row == self->b.height)
+			if (++row == browser->b.height)
 				goto out;
 do_next:
 			if (folded_sign == '+')
@@ -467,11 +467,11 @@ do_next:
 
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
-			row += hist_browser__show_callchain_node_rb_tree(self, child, new_total,
+			row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total,
 									 new_level, row, row_offset,
 									 is_current_entry);
 		}
-		if (row == self->b.height)
+		if (row == browser->b.height)
 			goto out;
 		node = next;
 	}
@@ -479,7 +479,7 @@ out:
 	return row - first_row;
 }
 
-static int hist_browser__show_callchain_node(struct hist_browser *self,
+static int hist_browser__show_callchain_node(struct hist_browser *browser,
 					     struct callchain_node *node,
 					     int level, unsigned short row,
 					     off_t *row_offset,
@@ -488,7 +488,7 @@ static int hist_browser__show_callchain_node(struct hist_browser *self,
 	struct callchain_list *chain;
 	int first_row = row,
 	     offset = level * LEVEL_OFFSET_STEP,
-	     width = self->b.width - offset;
+	     width = browser->b.width - offset;
 	char folded_sign = ' ';
 
 	list_for_each_entry(chain, &node->val, list) {
@@ -503,26 +503,26 @@ static int hist_browser__show_callchain_node(struct hist_browser *self,
 		}
 
 		color = HE_COLORSET_NORMAL;
-		if (ui_browser__is_current_entry(&self->b, row)) {
-			self->selection = &chain->ms;
+		if (ui_browser__is_current_entry(&browser->b, row)) {
+			browser->selection = &chain->ms;
 			color = HE_COLORSET_SELECTED;
 			*is_current_entry = true;
 		}
 
 		s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
-		ui_browser__gotorc(&self->b, row, 0);
-		ui_browser__set_color(&self->b, color);
+		ui_browser__gotorc(&browser->b, row, 0);
+		ui_browser__set_color(&browser->b, color);
 		slsmg_write_nstring(" ", offset);
 		slsmg_printf("%c ", folded_sign);
 		slsmg_write_nstring(s, width - 2);
 
-		if (++row == self->b.height)
+		if (++row == browser->b.height)
 			goto out;
 	}
 
 	if (folded_sign == '-')
-		row += hist_browser__show_callchain_node_rb_tree(self, node,
-								 self->hists->stats.total_period,
+		row += hist_browser__show_callchain_node_rb_tree(browser, node,
+								 browser->hists->stats.total_period,
 								 level + 1, row,
 								 row_offset,
 								 is_current_entry);
@@ -530,7 +530,7 @@ out:
 	return row - first_row;
 }
 
-static int hist_browser__show_callchain(struct hist_browser *self,
+static int hist_browser__show_callchain(struct hist_browser *browser,
 					struct rb_root *chain,
 					int level, unsigned short row,
 					off_t *row_offset,
@@ -542,31 +542,31 @@ static int hist_browser__show_callchain(struct hist_browser *self,
 	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
 		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
 
-		row += hist_browser__show_callchain_node(self, node, level,
+		row += hist_browser__show_callchain_node(browser, node, level,
 							 row, row_offset,
 							 is_current_entry);
-		if (row == self->b.height)
+		if (row == browser->b.height)
 			break;
 	}
 
 	return row - first_row;
 }
 
-static int hist_browser__show_entry(struct hist_browser *self,
+static int hist_browser__show_entry(struct hist_browser *browser,
 				    struct hist_entry *entry,
 				    unsigned short row)
 {
 	char s[256];
 	double percent;
 	int printed = 0;
-	int width = self->b.width - 6; /* The percentage */
+	int width = browser->b.width - 6; /* The percentage */
 	char folded_sign = ' ';
-	bool current_entry = ui_browser__is_current_entry(&self->b, row);
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
 	off_t row_offset = entry->row_offset;
 
 	if (current_entry) {
-		self->he_selection = entry;
-		self->selection = &entry->ms;
+		browser->he_selection = entry;
+		browser->selection = &entry->ms;
 	}
 
 	if (symbol_conf.use_callchain) {
@@ -575,11 +575,11 @@ static int hist_browser__show_entry(struct hist_browser *self,
 	}
 
 	if (row_offset == 0) {
-		hist_entry__snprintf(entry, s, sizeof(s), self->hists);
-		percent = (entry->period * 100.0) / self->hists->stats.total_period;
+		hist_entry__snprintf(entry, s, sizeof(s), browser->hists);
+		percent = (entry->period * 100.0) / browser->hists->stats.total_period;
 
-		ui_browser__set_percent_color(&self->b, percent, current_entry);
-		ui_browser__gotorc(&self->b, row, 0);
+		ui_browser__set_percent_color(&browser->b, percent, current_entry);
+		ui_browser__gotorc(&browser->b, row, 0);
 		if (symbol_conf.use_callchain) {
 			slsmg_printf("%c ", folded_sign);
 			width -= 2;
@@ -588,11 +588,11 @@ static int hist_browser__show_entry(struct hist_browser *self,
 		slsmg_printf(" %5.2f%%", percent);
 
 		/* The scroll bar isn't being used */
-		if (!self->b.navkeypressed)
+		if (!browser->b.navkeypressed)
 			width += 1;
 
-		if (!current_entry || !self->b.navkeypressed)
-			ui_browser__set_color(&self->b, HE_COLORSET_NORMAL);
+		if (!current_entry || !browser->b.navkeypressed)
+			ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
 
 		if (symbol_conf.show_nr_samples) {
 			slsmg_printf(" %11u", entry->nr_events);
@@ -610,12 +610,12 @@ static int hist_browser__show_entry(struct hist_browser *self,
 	} else
 		--row_offset;
 
-	if (folded_sign == '-' && row != self->b.height) {
-		printed += hist_browser__show_callchain(self, &entry->sorted_chain,
+	if (folded_sign == '-' && row != browser->b.height) {
+		printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
 							1, row, &row_offset,
 							&current_entry);
 		if (current_entry)
-			self->he_selection = entry;
+			browser->he_selection = entry;
 	}
 
 	return printed;
@@ -631,22 +631,22 @@ static void ui_browser__hists_init_top(struct ui_browser *browser)
 	}
 }
 
-static unsigned int hist_browser__refresh(struct ui_browser *self)
+static unsigned int hist_browser__refresh(struct ui_browser *browser)
 {
 	unsigned row = 0;
 	struct rb_node *nd;
-	struct hist_browser *hb = container_of(self, struct hist_browser, b);
+	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
 
-	ui_browser__hists_init_top(self);
+	ui_browser__hists_init_top(browser);
 
-	for (nd = self->top; nd; nd = rb_next(nd)) {
+	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (h->filtered)
 			continue;
 
 		row += hist_browser__show_entry(hb, h, row);
-		if (row == self->height)
+		if (row == browser->height)
 			break;
 	}
 
@@ -679,27 +679,27 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd)
 	return NULL;
 }
 
-static void ui_browser__hists_seek(struct ui_browser *self,
+static void ui_browser__hists_seek(struct ui_browser *browser,
 				   off_t offset, int whence)
 {
 	struct hist_entry *h;
 	struct rb_node *nd;
 	bool first = true;
 
-	if (self->nr_entries == 0)
+	if (browser->nr_entries == 0)
 		return;
 
-	ui_browser__hists_init_top(self);
+	ui_browser__hists_init_top(browser);
 
 	switch (whence) {
 	case SEEK_SET:
-		nd = hists__filter_entries(rb_first(self->entries));
+		nd = hists__filter_entries(rb_first(browser->entries));
 		break;
 	case SEEK_CUR:
-		nd = self->top;
+		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
-		nd = hists__filter_prev_entries(rb_last(self->entries));
+		nd = hists__filter_prev_entries(rb_last(browser->entries));
 		first = false;
 		break;
 	default:
@@ -710,7 +710,7 @@ static void ui_browser__hists_seek(struct ui_browser *self,
 	 * Moves not relative to the first visible entry invalidates its
 	 * row_offset:
 	 */
-	h = rb_entry(self->top, struct hist_entry, rb_node);
+	h = rb_entry(browser->top, struct hist_entry, rb_node);
 	h->row_offset = 0;
 
 	/*
@@ -738,7 +738,7 @@ do_offset:
 				} else {
 					h->row_offset += offset;
 					offset = 0;
-					self->top = nd;
+					browser->top = nd;
 					break;
 				}
 			}
@@ -746,7 +746,7 @@ do_offset:
 			if (nd == NULL)
 				break;
 			--offset;
-			self->top = nd;
+			browser->top = nd;
 		} while (offset != 0);
 	} else if (offset < 0) {
 		while (1) {
@@ -759,7 +759,7 @@ do_offset:
 					} else {
 						h->row_offset += offset;
 						offset = 0;
-						self->top = nd;
+						browser->top = nd;
 						break;
 					}
 				} else {
@@ -769,7 +769,7 @@ do_offset:
 					} else {
 						h->row_offset = h->nr_rows + offset;
 						offset = 0;
-						self->top = nd;
+						browser->top = nd;
 						break;
 					}
 				}
@@ -779,7 +779,7 @@ do_offset:
 			if (nd == NULL)
 				break;
 			++offset;
-			self->top = nd;
+			browser->top = nd;
 			if (offset == 0) {
 				/*
 				 * Last unfiltered hist_entry, check if it is
@@ -794,7 +794,7 @@ do_offset:
 			first = false;
 		}
 	} else {
-		self->top = nd;
+		browser->top = nd;
 		h = rb_entry(nd, struct hist_entry, rb_node);
 		h->row_offset = 0;
 	}
@@ -802,46 +802,46 @@ do_offset:
 
 static struct hist_browser *hist_browser__new(struct hists *hists)
 {
-	struct hist_browser *self = zalloc(sizeof(*self));
+	struct hist_browser *browser = zalloc(sizeof(*browser));
 
-	if (self) {
-		self->hists = hists;
-		self->b.refresh = hist_browser__refresh;
-		self->b.seek = ui_browser__hists_seek;
-		self->b.use_navkeypressed = true;
+	if (browser) {
+		browser->hists = hists;
+		browser->b.refresh = hist_browser__refresh;
+		browser->b.seek = ui_browser__hists_seek;
+		browser->b.use_navkeypressed = true;
 		if (sort__branch_mode == 1)
-			self->has_symbols = sort_sym_from.list.next != NULL;
+			browser->has_symbols = sort_sym_from.list.next != NULL;
 		else
-			self->has_symbols = sort_sym.list.next != NULL;
+			browser->has_symbols = sort_sym.list.next != NULL;
 	}
 
-	return self;
+	return browser;
 }
 
-static void hist_browser__delete(struct hist_browser *self)
+static void hist_browser__delete(struct hist_browser *browser)
 {
-	free(self);
+	free(browser);
 }
 
-static struct hist_entry *hist_browser__selected_entry(struct hist_browser *self)
+static struct hist_entry *hist_browser__selected_entry(struct hist_browser *browser)
 {
-	return self->he_selection;
+	return browser->he_selection;
 }
 
-static struct thread *hist_browser__selected_thread(struct hist_browser *self)
+static struct thread *hist_browser__selected_thread(struct hist_browser *browser)
 {
-	return self->he_selection->thread;
+	return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *self, char *bf, size_t size,
+static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 				const char *ev_name)
 {
 	char unit;
 	int printed;
-	const struct dso *dso = self->dso_filter;
-	const struct thread *thread = self->thread_filter;
-	unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE];
-	u64 nr_events = self->stats.total_period;
+	const struct dso *dso = hists->dso_filter;
+	const struct thread *thread = hists->thread_filter;
+	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	u64 nr_events = hists->stats.total_period;
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
@@ -849,9 +849,9 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size,
 			   nr_samples, unit, ev_name, nr_events);
 
 
-	if (self->uid_filter_str)
+	if (hists->uid_filter_str)
 		printed += snprintf(bf + printed, size - printed,
-				    ", UID: %s", self->uid_filter_str);
+				    ", UID: %s", hists->uid_filter_str);
 	if (thread)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
@@ -879,8 +879,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    void(*timer)(void *arg), void *arg,
 				    int delay_secs)
 {
-	struct hists *self = &evsel->hists;
-	struct hist_browser *browser = hist_browser__new(self);
+	struct hists *hists = &evsel->hists;
+	struct hist_browser *browser = hist_browser__new(hists);
 	struct branch_info *bi;
 	struct pstack *fstack;
 	char *options[16];
@@ -946,8 +946,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					"Please enter the name of symbol you want to see",
 					buf, "ENTER: OK, ESC: Cancel",
 					delay_secs * 2) == K_ENTER) {
-				self->symbol_filter_str = *buf ? buf : NULL;
-				hists__filter_by_symbol(self);
+				hists->symbol_filter_str = *buf ? buf : NULL;
+				hists__filter_by_symbol(hists);
 				hist_browser__reset(browser);
 			}
 			continue;
@@ -1128,7 +1128,7 @@ zoom_out_dso:
 				sort_dso.elide = true;
 				pstack__push(fstack, &browser->hists->dso_filter);
 			}
-			hists__filter_by_dso(self);
+			hists__filter_by_dso(hists);
 			hist_browser__reset(browser);
 		} else if (choice == zoom_thread) {
 zoom_thread:
@@ -1146,7 +1146,7 @@ zoom_out_thread:
 				sort_thread.elide = true;
 				pstack__push(fstack, &browser->hists->thread_filter);
 			}
-			hists__filter_by_thread(self);
+			hists__filter_by_thread(hists);
 			hist_browser__reset(browser);
 		}
 	}
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 9f5f888..791fb15 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -22,6 +22,7 @@ void setup_browser(bool fallback_to_pager)
 			break;
 		/* fall through */
 	default:
+		use_browser = 0;
 		if (fallback_to_pager)
 			setup_pager();
 		break;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0deac6a..6faa3a1 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -120,7 +120,7 @@ static char *parse_value(void)
 
 static inline int iskeychar(int c)
 {
-	return isalnum(c) || c == '-';
+	return isalnum(c) || c == '-' || c == '_';
 }
 
 static int get_value(config_fn_t fn, void *data, char *name, unsigned int len)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 57e4ce5..91d1913 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,7 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
+#include "../../include/linux/perf_event.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
@@ -64,6 +65,95 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
+static const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
+	"cycles",
+	"instructions",
+	"cache-references",
+	"cache-misses",
+	"branches",
+	"branch-misses",
+	"bus-cycles",
+	"stalled-cycles-frontend",
+	"stalled-cycles-backend",
+	"ref-cycles",
+};
+
+const char *__perf_evsel__hw_name(u64 config)
+{
+	if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
+		return perf_evsel__hw_names[config];
+
+	return "unknown-hardware";
+}
+
+static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int colon = 0;
+	struct perf_event_attr *attr = &evsel->attr;
+	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(attr->config));
+	bool exclude_guest_default = false;
+
+#define MOD_PRINT(context, mod)	do {					\
+		if (!attr->exclude_##context) {				\
+			if (!colon) colon = r++;			\
+			r += scnprintf(bf + r, size - r, "%c", mod);	\
+		} } while(0)
+
+	if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) {
+		MOD_PRINT(kernel, 'k');
+		MOD_PRINT(user, 'u');
+		MOD_PRINT(hv, 'h');
+		exclude_guest_default = true;
+	}
+
+	if (attr->precise_ip) {
+		if (!colon)
+			colon = r++;
+		r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
+		exclude_guest_default = true;
+	}
+
+	if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) {
+		MOD_PRINT(host, 'H');
+		MOD_PRINT(guest, 'G');
+	}
+#undef MOD_PRINT
+	if (colon)
+		bf[colon] = ':';
+	return r;
+}
+
+int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int ret;
+
+	switch (evsel->attr.type) {
+	case PERF_TYPE_RAW:
+		ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+		break;
+
+	case PERF_TYPE_HARDWARE:
+		ret = perf_evsel__hw_name(evsel, bf, size);
+		break;
+	default:
+		/*
+		 * FIXME
+ 		 *
+		 * This is the minimal perf_evsel__name so that we can
+		 * reconstruct event names taking into account event modifiers.
+		 *
+		 * The old event_name uses it now for raw anr hw events, so that
+		 * we don't drag all the parsing stuff into the python binding.
+		 *
+		 * On the next devel cycle the rest of the event naming will be
+		 * brought here.
+ 		 */
+		return 0;
+	}
+
+	return ret;
+}
+
 void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
 			struct perf_evsel *first)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3d6b3e4..4ba8b56 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,6 +83,9 @@ void perf_evsel__config(struct perf_evsel *evsel,
 			struct perf_record_opts *opts,
 			struct perf_evsel *first);
 
+const char* __perf_evsel__hw_name(u64 config);
+int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size);
+
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index fac7d59..05dbc8b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -62,19 +62,6 @@ static struct event_symbol event_symbols[] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-static const char *hw_event_names[PERF_COUNT_HW_MAX] = {
-	"cycles",
-	"instructions",
-	"cache-references",
-	"cache-misses",
-	"branches",
-	"branch-misses",
-	"bus-cycles",
-	"stalled-cycles-frontend",
-	"stalled-cycles-backend",
-	"ref-cycles",
-};
-
 static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
 	"cpu-clock",
 	"task-clock",
@@ -300,6 +287,16 @@ const char *event_name(struct perf_evsel *evsel)
 	u64 config = evsel->attr.config;
 	int type = evsel->attr.type;
 
+	if (type == PERF_TYPE_RAW || type == PERF_TYPE_HARDWARE) {
+		/*
+ 		 * XXX minimal fix, see comment on perf_evsen__name, this static buffer
+ 		 * will go away together with event_name in the next devel cycle.
+ 		 */
+		static char bf[128];
+		perf_evsel__name(evsel, bf, sizeof(bf));
+		return bf;
+	}
+
 	if (evsel->name)
 		return evsel->name;
 
@@ -317,9 +314,7 @@ const char *__event_name(int type, u64 config)
 
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
-		if (config < PERF_COUNT_HW_MAX && hw_event_names[config])
-			return hw_event_names[config];
-		return "unknown-hardware";
+		return __perf_evsel__hw_name(config);
 
 	case PERF_TYPE_HW_CACHE: {
 		u8 cache_type, cache_op, cache_result;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 84d9bd78..9b5f856 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -188,28 +188,27 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 		nt = realloc(threads, (sizeof(*threads) +
 				       sizeof(pid_t) * total_tasks));
 		if (nt == NULL)
-			goto out_free_threads;
+			goto out_free_namelist;
 
 		threads = nt;
 
-		if (threads) {
-			for (i = 0; i < items; i++)
-				threads->map[j++] = atoi(namelist[i]->d_name);
-			threads->nr = total_tasks;
-		}
-
-		for (i = 0; i < items; i++)
+		for (i = 0; i < items; i++) {
+			threads->map[j++] = atoi(namelist[i]->d_name);
 			free(namelist[i]);
+		}
+		threads->nr = total_tasks;
 		free(namelist);
-
-		if (!threads)
-			break;
 	}
 
 out:
 	strlist__delete(slist);
 	return threads;
 
+out_free_namelist:
+	for (i = 0; i < items; i++)
+		free(namelist[i]);
+	free(namelist);
+
 out_free_threads:
 	free(threads);
 	threads = NULL;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-05-17  8:19 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-05-17  8:19 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 9b63776fa3ca96c4ecda76f6fa947b7b0add66ac tracing: Do not enable function event with enable

 Thanks,

	Ingo

------------------>
David Ahern (1):
      perf stat: handle ENXIO error for perf_event_open

Greg Kroah-Hartman (1):
      perf: Turn off compiler warnings for flex and bison generated files

Namhyung Kim (1):
      perf build-id: Fix filename size calculation

Stephane Eranian (1):
      perf stat: Fix case where guest/host monitoring is not supported by kernel

Steven Rostedt (1):
      tracing: Do not enable function event with enable


 include/linux/ftrace_event.h |    2 ++
 kernel/trace/trace_events.c  |    5 ++++-
 kernel/trace/trace_export.c  |    1 +
 tools/perf/Makefile          |    4 ++--
 tools/perf/builtin-stat.c    |   40 +++++++++++++++++++++++++++++++++++-----
 tools/perf/util/header.c     |    2 +-
 6 files changed, 45 insertions(+), 9 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 5f3f3be..176a939 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -179,6 +179,7 @@ enum {
 	TRACE_EVENT_FL_RECORDED_CMD_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
 	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
+	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
 };
 
 enum {
@@ -187,6 +188,7 @@ enum {
 	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
+	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
 };
 
 struct ftrace_event_call {
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 079a93a..29111da 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -294,6 +294,9 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
 		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
+		if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
+			continue;
+
 		if (match &&
 		    strcmp(match, call->name) != 0 &&
 		    strcmp(match, call->class->system) != 0)
@@ -1164,7 +1167,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		return -1;
 	}
 
-	if (call->class->reg)
+	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 		trace_create_file("enable", 0644, call->dir, call,
 				  enable);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 3dd15e8..e039906 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -180,6 +180,7 @@ struct ftrace_event_call __used event_##call = {			\
 	.event.type		= etype,				\
 	.class			= &event_class_ftrace_##call,		\
 	.print_fmt		= print,				\
+	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE,		\
 };									\
 struct ftrace_event_call __used						\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 9bf3fc7..92271d3 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -774,10 +774,10 @@ $(OUTPUT)perf.o perf.spec \
 # over the general rule for .o
 
 $(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Iutil/ -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Iutil/ -w $<
 
 $(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -Iutil/ -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -Iutil/ -w $<
 
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c941bb6..1e5e9b2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -283,6 +283,8 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	struct xyarray *group_fd = NULL;
+	bool exclude_guest_missing = false;
+	int ret;
 
 	if (group && evsel != first)
 		group_fd = first->fd;
@@ -293,16 +295,39 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 
 	attr->inherit = !no_inherit;
 
-	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
+retry:
+	if (exclude_guest_missing)
+		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+
+	if (system_wide) {
+		ret = perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
+		if (ret)
+			goto check_ret;
+		return 0;
+	}
+
 	if (!target_pid && !target_tid && (!group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads,
-					   group, group_fd);
+	ret = perf_evsel__open_per_thread(evsel, evsel_list->threads,
+					  group, group_fd);
+	if (!ret)
+		return 0;
+	/* fall through */
+check_ret:
+	if (ret && errno == EINVAL) {
+		if (!exclude_guest_missing &&
+		    (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+			pr_debug("Old kernel, cannot exclude "
+				 "guest or host samples.\n");
+			exclude_guest_missing = true;
+			goto retry;
+		}
+	}
+	return ret;
 }
 
 /*
@@ -463,8 +488,13 @@ static int run_perf_stat(int argc __used, const char **argv)
 
 	list_for_each_entry(counter, &evsel_list->entries, node) {
 		if (create_perf_stat_counter(counter, first) < 0) {
+			/*
+			 * PPC returns ENXIO for HW counters until 2.6.37
+			 * (behavior changed with commit b0a873e).
+			 */
 			if (errno == EINVAL || errno == ENOSYS ||
-			    errno == ENOENT || errno == EOPNOTSUPP) {
+			    errno == ENOENT || errno == EOPNOTSUPP ||
+			    errno == ENXIO) {
 				if (verbose)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    event_name(counter));
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4c7c2d7..c0b70c6 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -296,7 +296,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
-	snprintf(filename + len, sizeof(filename) - len, "/%s", sbuild_id);
+	snprintf(filename + len, size - len, "/%s", sbuild_id);
 
 	if (access(filename, F_OK)) {
 		if (is_kallsyms) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-04-27  6:32 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-04-27  6:32 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 724b6daa13e100067c30cfc4d1ad06629609dc4e perf: Fix perf_event_for_each() to use sibling

 Thanks,

	Ingo

------------------>
David Ahern (1):
      perf report: Fix crash showing warning related to kernel maps

Gleb Natapov (1):
      perf tools: Add 'G' and 'H' modifiers to event parsing

Jiri Olsa (1):
      perf symbols: Read plt symbols from proper symtab_type binary

Mark Brown (1):
      tracing: Fix build breakage without CONFIG_PERF_EVENTS (again)

Michael Ellerman (1):
      perf: Fix perf_event_for_each() to use sibling

Otavio Salvador (1):
      perf tools: Drop CROSS_COMPILE from flex and bison calls

Steven Rostedt (2):
      tracing: Fix regression with tracing_on
      tracing: Fix stacktrace of latency tracers (irqsoff and friends)


 kernel/events/core.c           |    2 +-
 kernel/trace/trace.c           |    8 +++++---
 kernel/trace/trace.h           |    4 ++--
 kernel/trace/trace_output.c    |    5 +++++
 tools/perf/Makefile            |    4 ++--
 tools/perf/builtin-report.c    |   17 ++++++++++++-----
 tools/perf/builtin-test.c      |   30 ++++++++++++++++++++++++++++++
 tools/perf/util/parse-events.l |    2 +-
 tools/perf/util/symbol.c       |   13 ++++++-------
 9 files changed, 64 insertions(+), 21 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6a9ec4..fd126f8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3183,7 +3183,7 @@ static void perf_event_for_each(struct perf_event *event,
 	perf_event_for_each_child(event, func);
 	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
-		perf_event_for_each_child(event, func);
+		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
 }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed7b5d1..2a22255 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4629,7 +4629,8 @@ static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
-	struct ring_buffer *buffer = filp->private_data;
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer *buffer = tr->buffer;
 	char buf[64];
 	int r;
 
@@ -4647,7 +4648,8 @@ static ssize_t
 rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
-	struct ring_buffer *buffer = filp->private_data;
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer *buffer = tr->buffer;
 	unsigned long val;
 	int ret;
 
@@ -4734,7 +4736,7 @@ static __init int tracer_init_debugfs(void)
 			  &trace_clock_fops);
 
 	trace_create_file("tracing_on", 0644, d_tracer,
-			    global_trace.buffer, &rb_simple_fops);
+			    &global_trace, &rb_simple_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 95059f0..f95d65d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -836,11 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
 		     filter)
 #include "trace_entries.h"
 
-#ifdef CONFIG_FUNCTION_TRACER
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
 int perf_ftrace_event_register(struct ftrace_event_call *call,
 			       enum trace_reg type, void *data);
 #else
 #define perf_ftrace_event_register NULL
-#endif /* CONFIG_FUNCTION_TRACER */
+#endif
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 859fae6..df611a0 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -652,6 +652,8 @@ int trace_print_lat_context(struct trace_iterator *iter)
 {
 	u64 next_ts;
 	int ret;
+	/* trace_find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent,
 			   *next_entry = trace_find_next_entry(iter, NULL,
@@ -660,6 +662,9 @@ int trace_print_lat_context(struct trace_iterator *iter)
 	unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
 	unsigned long rel_usecs;
 
+	/* Restore the original ent_size */
+	iter->ent_size = ent_size;
+
 	if (!next_entry)
 		next_ts = iter->ts;
 	rel_usecs = ns2usecs(next_ts - iter->ts);
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 03059e7..9bf3fc7 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -234,8 +234,8 @@ endif
 
 export PERL_PATH
 
-FLEX = $(CROSS_COMPILE)flex
-BISON= $(CROSS_COMPILE)bison
+FLEX = flex
+BISON= bison
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2e31743..cdae9b2 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -374,16 +374,23 @@ static int __cmd_report(struct perf_report *rep)
 	    (kernel_map->dso->hit &&
 	     (kernel_kmap->ref_reloc_sym == NULL ||
 	      kernel_kmap->ref_reloc_sym->addr == 0))) {
-		const struct dso *kdso = kernel_map->dso;
+		const char *desc =
+		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+		    "can't be resolved.";
+
+		if (kernel_map) {
+			const struct dso *kdso = kernel_map->dso;
+			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
+				desc = "If some relocation was applied (e.g. "
+				       "kexec) symbols may be misresolved.";
+			}
+		}
 
 		ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
 "Samples in kernel modules can't be resolved as well.\n\n",
-			    RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION]) ?
-"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
-"can't be resolved." :
-"If some relocation was applied (e.g. kexec) symbols may be misresolved.");
+		desc);
 	}
 
 	if (dump_trace) {
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1c5b980..223ffdc 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -851,6 +851,28 @@ static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist)
 	return test__checkevent_symbolic_name(evlist);
 }
 
+static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
 static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -1091,6 +1113,14 @@ static struct test__event_st {
 		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
 		.check = test__checkevent_list,
 	},
+	{
+		.name  = "instructions:G",
+		.check = test__checkevent_exclude_host_modifier,
+	},
+	{
+		.name  = "instructions:H",
+		.check = test__checkevent_exclude_guest_modifier,
+	},
 };
 
 #define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 05d766e..1fcf1bb 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -54,7 +54,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
-modifier_event	[ukhp]{1,5}
+modifier_event	[ukhpGH]{1,8}
 modifier_bp	[rwx]
 
 %%
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c0a028c..ab9867b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -977,8 +977,9 @@ static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-static int dso__synthesize_plt_symbols(struct  dso *dso, struct map *map,
-				       symbol_filter_t filter)
+static int
+dso__synthesize_plt_symbols(struct dso *dso, char *name, struct map *map,
+			    symbol_filter_t filter)
 {
 	uint32_t nr_rel_entries, idx;
 	GElf_Sym sym;
@@ -993,10 +994,7 @@ static int dso__synthesize_plt_symbols(struct  dso *dso, struct map *map,
 	char sympltname[1024];
 	Elf *elf;
 	int nr = 0, symidx, fd, err = 0;
-	char name[PATH_MAX];
 
-	snprintf(name, sizeof(name), "%s%s",
-		 symbol_conf.symfs, dso->long_name);
 	fd = open(name, O_RDONLY);
 	if (fd < 0)
 		goto out;
@@ -1703,8 +1701,9 @@ restart:
 			continue;
 
 		if (ret > 0) {
-			int nr_plt = dso__synthesize_plt_symbols(dso, map,
-								 filter);
+			int nr_plt;
+
+			nr_plt = dso__synthesize_plt_symbols(dso, name, map, filter);
 			if (nr_plt > 0)
 				ret += nr_plt;
 			break;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-04-16 17:48 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-04-16 17:48 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 6c7b8e82aab75a25581c4d446fc87f96634e9ef9 x86: Handle failures of parsing immediate operands in the instruction decoder

 Thanks,

	Ingo

------------------>
Chanho Park (1):
      perf archive: Correct cutting of symbolic link

Jiri Olsa (2):
      perf session: Skip event correctly for unknown id/machine
      perf tools: Fix parsers' rules to dependencies

Masami Hiramatsu (1):
      x86: Handle failures of parsing immediate operands in the instruction decoder

Namhyung Kim (1):
      perf tools: Ignore auto-generated bison/flex files

Stephane Eranian (1):
      perf tools: fix NO_GTK2 Makefile config error


 arch/x86/lib/insn.c        |   53 +++++++++++++++++++++++++++++--------------
 tools/perf/.gitignore      |    2 +
 tools/perf/Makefile        |   21 +++++++----------
 tools/perf/perf-archive.sh |    3 +-
 tools/perf/util/session.c  |    4 +-
 5 files changed, 51 insertions(+), 32 deletions(-)

diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 25feb1a..b1e6c4b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -379,8 +379,8 @@ err_out:
 	return;
 }
 
-/* Decode moffset16/32/64 */
-static void __get_moffset(struct insn *insn)
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
 {
 	switch (insn->addr_bytes) {
 	case 2:
@@ -397,15 +397,19 @@ static void __get_moffset(struct insn *insn)
 		insn->moffset2.value = get_next(int, insn);
 		insn->moffset2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->moffset1.got = insn->moffset2.got = 1;
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v32(Iz) */
-static void __get_immv32(struct insn *insn)
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -417,14 +421,18 @@ static void __get_immv32(struct insn *insn)
 		insn->immediate.value = get_next(int, insn);
 		insn->immediate.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v64(Iv/Ov) */
-static void __get_immv(struct insn *insn)
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -441,15 +449,18 @@ static void __get_immv(struct insn *insn)
 		insn->immediate2.value = get_next(int, insn);
 		insn->immediate2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /* Decode ptr16:16/32(Ap) */
-static void __get_immptr(struct insn *insn)
+static int __get_immptr(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -462,14 +473,17 @@ static void __get_immptr(struct insn *insn)
 		break;
 	case 8:
 		/* ptr16:64 is not exist (no segment) */
-		return;
+		return 0;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate2.value = get_next(unsigned short, insn);
 	insn->immediate2.nbytes = 2;
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /**
@@ -489,7 +503,8 @@ void insn_get_immediate(struct insn *insn)
 		insn_get_displacement(insn);
 
 	if (inat_has_moffset(insn->attr)) {
-		__get_moffset(insn);
+		if (!__get_moffset(insn))
+			goto err_out;
 		goto done;
 	}
 
@@ -517,16 +532,20 @@ void insn_get_immediate(struct insn *insn)
 		insn->immediate2.nbytes = 4;
 		break;
 	case INAT_IMM_PTR:
-		__get_immptr(insn);
+		if (!__get_immptr(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD32:
-		__get_immv32(insn);
+		if (!__get_immv32(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD:
-		__get_immv(insn);
+		if (!__get_immv(insn))
+			goto err_out;
 		break;
 	default:
-		break;
+		/* Here, insn must have an immediate, but failed */
+		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
 		insn->immediate2.value = get_next(char, insn);
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 416684b..26b823b 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -19,3 +19,5 @@ TAGS
 cscope*
 config.mak
 config.mak.autogen
+*-bison.*
+*-flex.*
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 820371f..03059e7 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -237,21 +237,20 @@ export PERL_PATH
 FLEX = $(CROSS_COMPILE)flex
 BISON= $(CROSS_COMPILE)bison
 
-event-parser:
-	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d -o $(OUTPUT)util/parse-events-bison.c
+$(OUTPUT)util/parse-events-flex.c: util/parse-events.l
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
 
-$(OUTPUT)util/parse-events-flex.c: event-parser
-$(OUTPUT)util/parse-events-bison.c: event-parser
+$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
+	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d -o $(OUTPUT)util/parse-events-bison.c
 
-pmu-parser:
-	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c
+$(OUTPUT)util/pmu-flex.c: util/pmu.l
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
 
-$(OUTPUT)util/pmu-flex.c: pmu-parser
-$(OUTPUT)util/pmu-bison.c: pmu-parser
+$(OUTPUT)util/pmu-bison.c: util/pmu.y
+	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c
 
-$(OUTPUT)util/parse-events.o: event-parser pmu-parser
+$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
+$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
 LIB_FILE=$(OUTPUT)libperf.a
 
@@ -527,7 +526,7 @@ else
 endif
 
 ifdef NO_GTK2
-	BASIC_CFLAGS += -DNO_GTK2
+	BASIC_CFLAGS += -DNO_GTK2_SUPPORT
 else
 	FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0)
 	ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y)
@@ -852,8 +851,6 @@ help:
 	@echo '  html		- make html documentation'
 	@echo '  info		- make GNU info documentation (access with info <foo>)'
 	@echo '  pdf		- make pdf documentation'
-	@echo '  event-parser	- make event parser code'
-	@echo '  pmu-parser	- make pmu format parser code'
 	@echo '  TAGS		- use etags to make tag information for source browsing'
 	@echo '  tags		- use ctags to make tag information for source browsing'
 	@echo '  cscope	- use cscope to make interactive browsing database'
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 677e59d..95b6f8b 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -29,13 +29,14 @@ if [ ! -s $BUILDIDS ] ; then
 fi
 
 MANIFEST=$(mktemp /tmp/perf-archive-manifest.XXXXXX)
+PERF_BUILDID_LINKDIR=$(readlink -f $PERF_BUILDID_DIR)/
 
 cut -d ' ' -f 1 $BUILDIDS | \
 while read build_id ; do
 	linkname=$PERF_BUILDID_DIR.build-id/${build_id:0:2}/${build_id:2}
 	filename=$(readlink -f $linkname)
 	echo ${linkname#$PERF_BUILDID_DIR} >> $MANIFEST
-	echo ${filename#$PERF_BUILDID_DIR} >> $MANIFEST
+	echo ${filename#$PERF_BUILDID_LINKDIR} >> $MANIFEST
 done
 
 tar cfj $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 00923cd..1efd3be 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -876,11 +876,11 @@ static int perf_session_deliver_event(struct perf_session *session,
 		dump_sample(session, event, sample);
 		if (evsel == NULL) {
 			++session->hists.stats.nr_unknown_id;
-			return -1;
+			return 0;
 		}
 		if (machine == NULL) {
 			++session->hists.stats.nr_unprocessable_samples;
-			return -1;
+			return 0;
 		}
 		return tool->sample(tool, event, sample, evsel, machine);
 	case PERF_RECORD_MMAP:

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-04-14 10:54 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-04-14 10:54 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: a7ca08038b990e2cbed324948664b2d8940fd782 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf top: Add intel_idle to the skip list
      perf annotate: Fix hist decay
      perf annotate: Validate addr in symbol__inc_addr_samples

David Miller (1):
      perf hists: Catch and handle out-of-date hist entry maps.

Jiri Olsa (1):
      perf hists browser: Fix NULL deref in hists browsing code

Nikunj A. Dadhania (1):
      perf kvm: Finding struct machine fails for PERF_RECORD_MMAP


 tools/perf/builtin-top.c            |   36 ++++++++++++++++++++++++++++++++++-
 tools/perf/util/annotate.c          |   16 +++++---------
 tools/perf/util/hist.c              |   12 +++++++++++
 tools/perf/util/map.c               |    1 +
 tools/perf/util/map.h               |    1 +
 tools/perf/util/session.c           |   12 +++++++++-
 tools/perf/util/ui/browsers/hists.c |    3 ++
 7 files changed, 68 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index e3c63ae..8ef59f8 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -42,6 +42,7 @@
 #include "util/debug.h"
 
 #include <assert.h>
+#include <elf.h>
 #include <fcntl.h>
 
 #include <stdio.h>
@@ -59,6 +60,7 @@
 #include <sys/prctl.h>
 #include <sys/wait.h>
 #include <sys/uio.h>
+#include <sys/utsname.h>
 #include <sys/mman.h>
 
 #include <linux/unistd.h>
@@ -162,12 +164,40 @@ static void __zero_source_counters(struct hist_entry *he)
 	symbol__annotate_zero_histograms(sym);
 }
 
+static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip)
+{
+	struct utsname uts;
+	int err = uname(&uts);
+
+	ui__warning("Out of bounds address found:\n\n"
+		    "Addr:   %" PRIx64 "\n"
+		    "DSO:    %s %c\n"
+		    "Map:    %" PRIx64 "-%" PRIx64 "\n"
+		    "Symbol: %" PRIx64 "-%" PRIx64 " %c %s\n"
+		    "Arch:   %s\n"
+		    "Kernel: %s\n"
+		    "Tools:  %s\n\n"
+		    "Not all samples will be on the annotation output.\n\n"
+		    "Please report to linux-kernel@vger.kernel.org\n",
+		    ip, map->dso->long_name, dso__symtab_origin(map->dso),
+		    map->start, map->end, sym->start, sym->end,
+		    sym->binding == STB_GLOBAL ? 'g' :
+		    sym->binding == STB_LOCAL  ? 'l' : 'w', sym->name,
+		    err ? "[unknown]" : uts.machine,
+		    err ? "[unknown]" : uts.release, perf_version_string);
+	if (use_browser <= 0)
+		sleep(5);
+	
+	map->erange_warned = true;
+}
+
 static void perf_top__record_precise_ip(struct perf_top *top,
 					struct hist_entry *he,
 					int counter, u64 ip)
 {
 	struct annotation *notes;
 	struct symbol *sym;
+	int err;
 
 	if (he == NULL || he->ms.sym == NULL ||
 	    ((top->sym_filter_entry == NULL ||
@@ -189,9 +219,12 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 	}
 
 	ip = he->ms.map->map_ip(he->ms.map, ip);
-	symbol__inc_addr_samples(sym, he->ms.map, counter, ip);
+	err = symbol__inc_addr_samples(sym, he->ms.map, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
+
+	if (err == -ERANGE && !he->ms.map->erange_warned)
+		ui__warn_map_erange(he->ms.map, sym, ip);
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -615,6 +648,7 @@ process_hotkey:
 
 /* Tag samples to be skipped. */
 static const char *skip_symbols[] = {
+	"intel_idle",
 	"default_idle",
 	"native_safe_halt",
 	"cpu_idle",
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 199f69e..08c6d13 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -64,8 +64,8 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr > sym->end)
-		return 0;
+	if (addr < sym->start || addr > sym->end)
+		return -ERANGE;
 
 	offset = addr - sym->start;
 	h = annotation__histogram(notes, evidx);
@@ -561,16 +561,12 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
-	struct objdump_line *pos;
-	int len = sym->end - sym->start;
+	int len = sym->end - sym->start, offset;
 
 	h->sum = 0;
-
-	list_for_each_entry(pos, &notes->src->source, node) {
-		if (pos->offset != -1 && pos->offset < len) {
-			h->addr[pos->offset] = h->addr[pos->offset] * 7 / 8;
-			h->sum += h->addr[pos->offset];
-		}
+	for (offset = 0; offset < len; ++offset) {
+		h->addr[offset] = h->addr[offset] * 7 / 8;
+		h->sum += h->addr[offset];
 	}
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2ec4b60..9f6d630 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -256,6 +256,18 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		if (!cmp) {
 			he->period += period;
 			++he->nr_events;
+
+			/* If the map of an existing hist_entry has
+			 * become out-of-date due to an exec() or
+			 * similar, update it.  Otherwise we will
+			 * mis-adjust symbol addresses when computing
+			 * the history counter to increment.
+			 */
+			if (he->ms.map != entry->ms.map) {
+				he->ms.map = entry->ms.map;
+				if (he->ms.map)
+					he->ms.map->referenced = true;
+			}
 			goto out;
 		}
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index dea6d1c..35ae568 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -38,6 +38,7 @@ void map__init(struct map *self, enum map_type type,
 	RB_CLEAR_NODE(&self->rb_node);
 	self->groups   = NULL;
 	self->referenced = false;
+	self->erange_warned = false;
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b100c20..81371ba 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -33,6 +33,7 @@ struct map {
 	u64			end;
 	u8 /* enum map_type */	type;
 	bool			referenced;
+	bool			erange_warned;
 	u32			priv;
 	u64			pgoff;
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 9412e3b..00923cd 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -826,8 +826,16 @@ static struct machine *
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest)
-		return perf_session__find_machine(session, event->ip.pid);
+	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+		u32 pid;
+
+		if (event->header.type == PERF_RECORD_MMAP)
+			pid = event->mmap.pid;
+		else
+			pid = event->ip.pid;
+
+		return perf_session__find_machine(session, pid);
+	}
 
 	return perf_session__find_host_machine(session);
 }
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index d7a1c4a..2f83e5d 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -125,6 +125,9 @@ static int callchain__count_rows(struct rb_root *chain)
 
 static bool map_symbol__toggle_fold(struct map_symbol *self)
 {
+	if (!self)
+		return false;
+
 	if (!self->has_children)
 		return false;
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-04-03 22:40 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-04-03 22:40 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 7b8e6da46b921d30ac1553cac56d8fb74f0b431d perf/x86/p4: Add format attributes

 Thanks,

	Ingo

------------------>
Oleg Nesterov (1):
      tracing, sched, vfs: Fix 'old_pid' usage in trace_sched_process_exec()

Peter Zijlstra (1):
      perf/x86/p4: Add format attributes


 arch/x86/kernel/cpu/perf_event_p4.c |   13 +++++++++++++
 fs/exec.c                           |    7 ++++---
 include/trace/events/sched.h        |    2 +-
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ef484d9..a2dfacf 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1271,6 +1271,17 @@ done:
 	return num ? -EINVAL : 0;
 }
 
+PMU_FORMAT_ATTR(cccr, "config:0-31" );
+PMU_FORMAT_ATTR(escr, "config:32-62");
+PMU_FORMAT_ATTR(ht,   "config:63"   );
+
+static struct attribute *intel_p4_formats_attr[] = {
+	&format_attr_cccr.attr,
+	&format_attr_escr.attr,
+	&format_attr_ht.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu p4_pmu = {
 	.name			= "Netburst P4/Xeon",
 	.handle_irq		= p4_pmu_handle_irq,
@@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * the former idea is taken from OProfile code
 	 */
 	.perfctr_second_write	= 1,
+
+	.format_attrs		= intel_p4_formats_attr,
 };
 
 __init int p4_pmu_init(void)
diff --git a/fs/exec.c b/fs/exec.c
index 23559c2..644f6c4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1370,7 +1370,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	unsigned int depth = bprm->recursion_depth;
 	int try,retval;
 	struct linux_binfmt *fmt;
-	pid_t old_pid;
+	pid_t old_pid, old_vpid;
 
 	retval = security_bprm_check(bprm);
 	if (retval)
@@ -1381,8 +1381,9 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 		return retval;
 
 	/* Need to fetch pid before load_binary changes it */
+	old_pid = current->pid;
 	rcu_read_lock();
-	old_pid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
+	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
 	rcu_read_unlock();
 
 	retval = -ENOENT;
@@ -1405,7 +1406,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			if (retval >= 0) {
 				if (depth == 0) {
 					trace_sched_process_exec(current, old_pid, bprm);
-					ptrace_event(PTRACE_EVENT_EXEC, old_pid);
+					ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
 				}
 				put_binfmt(fmt);
 				allow_write_access(bprm->file);
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fbc7b1a..ea7a203 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -295,7 +295,7 @@ TRACE_EVENT(sched_process_exec,
 	TP_fast_assign(
 		__assign_str(filename, bprm->filename);
 		__entry->pid		= p->pid;
-		__entry->old_pid	= p->pid;
+		__entry->old_pid	= old_pid;
 	),
 
 	TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename),

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-03-13 16:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-03-13 16:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Stephane Eranian, Andrew Morton, Thomas Gleixner

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 8aa8a7c80ccdfac2df5ee48a51a4a7bee2143d4f perf record: Fix buffer overrun bug in tracepoint_id_to_path()

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      perf/x86: Fix local vs remote memory events for NHM/WSM

Stephane Eranian (1):
      perf record: Fix buffer overrun bug in tracepoint_id_to_path()


 arch/x86/kernel/cpu/perf_event_intel.c |   17 +++++++++--------
 tools/perf/util/parse-events.c         |    2 +-
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3bd37bd..61d4f79 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -385,14 +385,15 @@ static __initconst const u64 westmere_hw_cache_event_ids
 #define NHM_LOCAL_DRAM		(1 << 14)
 #define NHM_NON_DRAM		(1 << 15)
 
-#define NHM_ALL_DRAM		(NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+#define NHM_LOCAL		(NHM_LOCAL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_REMOTE		(NHM_REMOTE_DRAM)
 
 #define NHM_DMND_READ		(NHM_DMND_DATA_RD)
 #define NHM_DMND_WRITE		(NHM_DMND_RFO|NHM_DMND_WB)
 #define NHM_DMND_PREFETCH	(NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
 
 #define NHM_L3_HIT	(NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
-#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_LOCAL_DRAM|NHM_REMOTE_DRAM|NHM_REMOTE_CACHE_FWD)
 #define NHM_L3_ACCESS	(NHM_L3_HIT|NHM_L3_MISS)
 
 static __initconst const u64 nehalem_hw_cache_extra_regs
@@ -416,16 +417,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
  },
  [ C(NODE) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM,
-		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_REMOTE_DRAM,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_LOCAL|NHM_REMOTE,
+		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_REMOTE,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM,
-		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_LOCAL|NHM_REMOTE,
+		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_REMOTE,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM,
-		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_LOCAL|NHM_REMOTE,
+		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_REMOTE,
 	},
  },
 };
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index b029296..c7a6f6f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -165,7 +165,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	struct tracepoint_path *path = NULL;
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
-	char id_buf[4];
+	char id_buf[24];
 	int fd;
 	u64 id;
 	char evt_path[MAXPATHLEN];

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-03-05  9:27 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-03-05  9:27 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: b7c924274c456499264d1cfa3d44063bb11eb5db Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

It contains three cherry-picked fixes from perf/core, which 
turned out to be more urgent than we originally thought.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf tools: Handle kernels that don't support attr.exclude_{guest,host}

David Ahern (1):
      perf record: No build id option fails

Joerg Roedel (1):
      perf tools: Change perf_guest default back to false


 tools/perf/builtin-record.c |   33 ++++++++++++++++++++++-----------
 tools/perf/builtin-top.c    |   23 +++++++++++++++++------
 tools/perf/perf.h           |    1 +
 tools/perf/util/top.h       |    1 +
 tools/perf/util/util.c      |    2 +-
 5 files changed, 42 insertions(+), 18 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0abfb18..227b6ae 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -204,6 +204,9 @@ static void perf_record__open(struct perf_record *rec)
 
 		if (opts->group && pos != first)
 			group_fd = first->fd;
+fallback_missing_features:
+		if (opts->exclude_guest_missing)
+			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
 		attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
 try_again:
@@ -217,15 +220,23 @@ try_again:
 			} else if (err ==  ENODEV && opts->cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
-			} else if (err == EINVAL && opts->sample_id_all_avail) {
-				/*
-				 * Old kernel, no attr->sample_id_type_all field
-				 */
-				opts->sample_id_all_avail = false;
-				if (!opts->sample_time && !opts->raw_samples && !time_needed)
-					attr->sample_type &= ~PERF_SAMPLE_TIME;
-
-				goto retry_sample_id;
+			} else if (err == EINVAL) {
+				if (!opts->exclude_guest_missing &&
+				    (attr->exclude_guest || attr->exclude_host)) {
+					pr_debug("Old kernel, cannot exclude "
+						 "guest or host samples.\n");
+					opts->exclude_guest_missing = true;
+					goto fallback_missing_features;
+				} else if (opts->sample_id_all_avail) {
+					/*
+					 * Old kernel, no attr->sample_id_type_all field
+					 */
+					opts->sample_id_all_avail = false;
+					if (!opts->sample_time && !opts->raw_samples && !time_needed)
+						attr->sample_type &= ~PERF_SAMPLE_TIME;
+
+					goto retry_sample_id;
+				}
 			}
 
 			/*
@@ -503,9 +514,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 			return err;
 	}
 
-	if (!!rec->no_buildid
+	if (!rec->no_buildid
 	    && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
-		pr_err("Couldn't generating buildids. "
+		pr_err("Couldn't generate buildids. "
 		       "Use --no-buildid to profile anyway.\n");
 		return -1;
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index dd162aa..ecff312 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -857,6 +857,9 @@ static void perf_top__start_counters(struct perf_top *top)
 		attr->mmap = 1;
 		attr->comm = 1;
 		attr->inherit = top->inherit;
+fallback_missing_features:
+		if (top->exclude_guest_missing)
+			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
 		attr->sample_id_all = top->sample_id_all_avail ? 1 : 0;
 try_again:
@@ -868,12 +871,20 @@ try_again:
 			if (err == EPERM || err == EACCES) {
 				ui__error_paranoid();
 				goto out_err;
-			} else if (err == EINVAL && top->sample_id_all_avail) {
-				/*
-				 * Old kernel, no attr->sample_id_type_all field
-				 */
-				top->sample_id_all_avail = false;
-				goto retry_sample_id;
+			} else if (err == EINVAL) {
+				if (!top->exclude_guest_missing &&
+				    (attr->exclude_guest || attr->exclude_host)) {
+					pr_debug("Old kernel, cannot exclude "
+						 "guest or host samples.\n");
+					top->exclude_guest_missing = true;
+					goto fallback_missing_features;
+				} else if (top->sample_id_all_avail) {
+					/*
+					 * Old kernel, no attr->sample_id_type_all field
+					 */
+					top->sample_id_all_avail = false;
+					goto retry_sample_id;
+				}
 			}
 			/*
 			 * If it's cycles then fall back to hrtimer
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 64f8bee..16e7d20 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -199,6 +199,7 @@ struct perf_record_opts {
 	bool	     sample_address;
 	bool	     sample_time;
 	bool	     sample_id_all_avail;
+	bool	     exclude_guest_missing;
 	bool	     system_wide;
 	bool	     period;
 	unsigned int freq;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index a248f3c..f2eab81 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -34,6 +34,7 @@ struct perf_top {
 	bool		   inherit;
 	bool		   group;
 	bool		   sample_id_all_avail;
+	bool		   exclude_guest_missing;
 	bool		   dump_symtab;
 	const char	   *cpu_list;
 	struct hist_entry  *sym_filter_entry;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 8131410..fb25d13 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -6,7 +6,7 @@
  * XXX We need to find a better place for these things...
  */
 bool perf_host  = true;
-bool perf_guest = true;
+bool perf_guest = false;
 
 void event_attr_init(struct perf_event_attr *attr)
 {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-03-02 10:47 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-03-02 10:47 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 5d85d97c9f6973ba854f35a2d5e80fe68272143e Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

 Thanks,

	Ingo

------------------>
David Ahern (1):
      perf tools: Ensure comm string is properly terminated

Namhyung Kim (2):
      perf/hwbp: Fix a possible memory leak
      perf evlist: Return first evsel for non-sample event on old kernel

Prashanth Nageshappa (2):
      perf probe: Ensure offset provided is not greater than function length
      perf probe: Ensure offset provided is not greater than function length without DWARF info too


 kernel/events/hw_breakpoint.c  |    4 ++--
 tools/perf/util/event.c        |    1 +
 tools/perf/util/evlist.c       |    4 ++++
 tools/perf/util/probe-event.c  |    6 ++++++
 tools/perf/util/probe-finder.c |   12 +++++++++++-
 5 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b7971d6..ee706ce 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -651,10 +651,10 @@ int __init init_hw_breakpoint(void)
 
  err_alloc:
 	for_each_possible_cpu(err_cpu) {
-		if (err_cpu == cpu)
-			break;
 		for (i = 0; i < TYPE_MAX; i++)
 			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+		if (err_cpu == cpu)
+			break;
 	}
 
 	return -ENOMEM;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2044324..2a6f33c 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -74,6 +74,7 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len)
 			if (size >= len)
 				size = len - 1;
 			memcpy(comm, name, size);
+			comm[size] = '\0';
 
 		} else if (memcmp(bf, "Tgid:", 5) == 0) {
 			char *tgids = bf + 5;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3f16e08..ea32a06 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -349,6 +349,10 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	hlist_for_each_entry(sid, pos, head, node)
 		if (sid->id == id)
 			return sid->evsel;
+
+	if (!perf_evlist__sample_id_all(evlist))
+		return list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	return NULL;
 }
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 29cb654..e33554a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1867,6 +1867,12 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 			   tev->point.symbol);
 		ret = -ENOENT;
 		goto error;
+	} else if (tev->point.offset > sym->end - sym->start) {
+		pr_warning("Offset specified is greater than size of %s\n",
+			   tev->point.symbol);
+		ret = -ENOENT;
+		goto error;
+
 	}
 
 	return 1;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 5d73262..74bd2e6 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -672,7 +672,7 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
 				  bool retprobe, struct probe_trace_point *tp)
 {
-	Dwarf_Addr eaddr;
+	Dwarf_Addr eaddr, highaddr;
 	const char *name;
 
 	/* Copy the name of probe point */
@@ -683,6 +683,16 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
 				   dwarf_diename(sp_die));
 			return -ENOENT;
 		}
+		if (dwarf_highpc(sp_die, &highaddr) != 0) {
+			pr_warning("Failed to get end address of %s\n",
+				   dwarf_diename(sp_die));
+			return -ENOENT;
+		}
+		if (paddr > highaddr) {
+			pr_warning("Offset specified is greater than size of %s\n",
+				   dwarf_diename(sp_die));
+			return -EINVAL;
+		}
 		tp->symbol = strdup(name);
 		if (tp->symbol == NULL)
 			return -ENOMEM;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-02-10 12:45 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-02-10 12:45 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: f39d47ff819ed52a2afbdbecbe35f23f7755f58d perf: Fix double start/stop in x86_pmu_start()

 Thanks,

	Ingo

------------------>
Jiri Olsa (2):
      perf tools: Fix perf stack to non executable on x86_64
      perf tools: Fix prefix matching for kernel maps

Naveen N. Rao (1):
      perf evsel: Fix an issue where perf report fails to show the proper percentage

Stephane Eranian (2):
      perf: Remove deprecated WARN_ON_ONCE()
      perf: Fix double start/stop in x86_pmu_start()


 arch/x86/kernel/cpu/perf_event_intel_ds.c  |    1 -
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |    2 --
 kernel/events/core.c                       |   19 ++++++++++++++-----
 tools/perf/bench/mem-memcpy-x86-64-asm.S   |    6 ++++++
 tools/perf/util/event.c                    |    2 +-
 tools/perf/util/evsel.c                    |    1 +
 6 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 73da6b6..d6bd49f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -439,7 +439,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
-	WARN_ON_ONCE(cpuc->enabled);
 
 	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
 		intel_pmu_lbr_enable(event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 3fab3de..47a7e63 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -72,8 +72,6 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	WARN_ON_ONCE(cpuc->enabled);
-
 	/*
 	 * Reset the LBR stack if we changed task context to
 	 * avoid data leaks.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ba36013..1b5c081 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2303,7 +2303,7 @@ do {					\
 static DEFINE_PER_CPU(int, perf_throttled_count);
 static DEFINE_PER_CPU(u64, perf_throttled_seq);
 
-static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
+static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bool disable)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	s64 period, sample_period;
@@ -2322,9 +2322,13 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 	hwc->sample_period = sample_period;
 
 	if (local64_read(&hwc->period_left) > 8*sample_period) {
-		event->pmu->stop(event, PERF_EF_UPDATE);
+		if (disable)
+			event->pmu->stop(event, PERF_EF_UPDATE);
+
 		local64_set(&hwc->period_left, 0);
-		event->pmu->start(event, PERF_EF_RELOAD);
+
+		if (disable)
+			event->pmu->start(event, PERF_EF_RELOAD);
 	}
 }
 
@@ -2350,6 +2354,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		return;
 
 	raw_spin_lock(&ctx->lock);
+	perf_pmu_disable(ctx->pmu);
 
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
@@ -2381,13 +2386,17 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		/*
 		 * restart the event
 		 * reload only if value has changed
+		 * we have stopped the event so tell that
+		 * to perf_adjust_period() to avoid stopping it
+		 * twice.
 		 */
 		if (delta > 0)
-			perf_adjust_period(event, period, delta);
+			perf_adjust_period(event, period, delta, false);
 
 		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
 	}
 
+	perf_pmu_enable(ctx->pmu);
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -4562,7 +4571,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		hwc->freq_time_stamp = now;
 
 		if (delta > 0 && delta < 2*TICK_NSEC)
-			perf_adjust_period(event, delta, hwc->last_period);
+			perf_adjust_period(event, delta, hwc->last_period, true);
 	}
 
 	/*
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index a57b66e..185a96d 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,2 +1,8 @@
 
 #include "../../../arch/x86/lib/memcpy_64.S"
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 73ddaf0..2044324 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -554,7 +554,7 @@ static int perf_event__process_kernel_mmap(struct perf_tool *tool __used,
 
 	is_kernel_mmap = memcmp(event->mmap.filename,
 				kmmap_prefix,
-				strlen(kmmap_prefix)) == 0;
+				strlen(kmmap_prefix) - 1) == 0;
 	if (event->mmap.filename[0] == '/' ||
 	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 667f3b7..7132ee8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -463,6 +463,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	memset(data, 0, sizeof(*data));
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
+	data->period = 1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!sample_id_all)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-02-02 10:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-02-02 10:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 45179fec946dd554f74e950d2278dabd5ad23fd3 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

 Thanks,

	Ingo

------------------>
Dan Carpenter (1):
      x86/dumpstack: Remove unneeded check in dump_trace()

David Daney (1):
      perf tools: Fix broken build by defining _GNU_SOURCE in Makefile

Stephane Eranian (3):
      perf: Fix broken interrupt rate throttling
      perf tools: Fix strlen() bug in perf_event__synthesize_event_type()
      perf top: Fix number of samples displayed


 arch/x86/kernel/dumpstack_64.c      |    2 +-
 include/linux/perf_event.h          |    1 +
 kernel/events/core.c                |  104 ++++++++++++++++++++++-------------
 tools/perf/Makefile                 |    7 +--
 tools/perf/builtin-probe.c          |    2 -
 tools/perf/builtin-top.c            |   13 +++-
 tools/perf/util/header.c            |    2 +-
 tools/perf/util/probe-event.c       |    2 -
 tools/perf/util/symbol.c            |    1 -
 tools/perf/util/trace-event-parse.c |    3 +-
 tools/perf/util/ui/browsers/hists.c |    2 -
 tools/perf/util/ui/helpline.c       |    1 -
 tools/perf/util/util.h              |    1 -
 13 files changed, 82 insertions(+), 59 deletions(-)

diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6d728d9..af7785f 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	if (!stack) {
 		if (regs)
 			stack = (unsigned long *)regs->sp;
-		else if (task && task != current)
+		else if (task != current)
 			stack = (unsigned long *)task->thread.sp;
 		else
 			stack = &dummy;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0885561..abb2776 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -587,6 +587,7 @@ struct hw_perf_event {
 	u64				sample_period;
 	u64				last_period;
 	local64_t			period_left;
+	u64                             interrupts_seq;
 	u64				interrupts;
 
 	u64				freq_time_stamp;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 32b48c8..ba36013 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2300,6 +2300,9 @@ do {					\
 	return div64_u64(dividend, divisor);
 }
 
+static DEFINE_PER_CPU(int, perf_throttled_count);
+static DEFINE_PER_CPU(u64, perf_throttled_seq);
+
 static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -2325,16 +2328,29 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 	}
 }
 
-static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
+/*
+ * combine freq adjustment with unthrottling to avoid two passes over the
+ * events. At the same time, make sure, having freq events does not change
+ * the rate of unthrottling as that would introduce bias.
+ */
+static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
+					   int needs_unthr)
 {
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
-	u64 interrupts, now;
+	u64 now, period = TICK_NSEC;
 	s64 delta;
 
-	if (!ctx->nr_freq)
+	/*
+	 * only need to iterate over all events iff:
+	 * - context have events in frequency mode (needs freq adjust)
+	 * - there are events to unthrottle on this cpu
+	 */
+	if (!(ctx->nr_freq || needs_unthr))
 		return;
 
+	raw_spin_lock(&ctx->lock);
+
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
@@ -2344,13 +2360,8 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 
 		hwc = &event->hw;
 
-		interrupts = hwc->interrupts;
-		hwc->interrupts = 0;
-
-		/*
-		 * unthrottle events on the tick
-		 */
-		if (interrupts == MAX_INTERRUPTS) {
+		if (needs_unthr && hwc->interrupts == MAX_INTERRUPTS) {
+			hwc->interrupts = 0;
 			perf_log_throttle(event, 1);
 			event->pmu->start(event, 0);
 		}
@@ -2358,14 +2369,26 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
-		event->pmu->read(event);
+		/*
+		 * stop the event and update event->count
+		 */
+		event->pmu->stop(event, PERF_EF_UPDATE);
+
 		now = local64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
 		hwc->freq_count_stamp = now;
 
+		/*
+		 * restart the event
+		 * reload only if value has changed
+		 */
 		if (delta > 0)
 			perf_adjust_period(event, period, delta);
+
+		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
 	}
+
+	raw_spin_unlock(&ctx->lock);
 }
 
 /*
@@ -2388,16 +2411,13 @@ static void rotate_ctx(struct perf_event_context *ctx)
  */
 static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
-	u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
 	struct perf_event_context *ctx = NULL;
-	int rotate = 0, remove = 1, freq = 0;
+	int rotate = 0, remove = 1;
 
 	if (cpuctx->ctx.nr_events) {
 		remove = 0;
 		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
 			rotate = 1;
-		if (cpuctx->ctx.nr_freq)
-			freq = 1;
 	}
 
 	ctx = cpuctx->task_ctx;
@@ -2405,37 +2425,26 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 		remove = 0;
 		if (ctx->nr_events != ctx->nr_active)
 			rotate = 1;
-		if (ctx->nr_freq)
-			freq = 1;
 	}
 
-	if (!rotate && !freq)
+	if (!rotate)
 		goto done;
 
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
-	if (freq) {
-		perf_ctx_adjust_freq(&cpuctx->ctx, interval);
-		if (ctx)
-			perf_ctx_adjust_freq(ctx, interval);
-	}
-
-	if (rotate) {
-		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-		if (ctx)
-			ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+	if (ctx)
+		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
 
-		rotate_ctx(&cpuctx->ctx);
-		if (ctx)
-			rotate_ctx(ctx);
+	rotate_ctx(&cpuctx->ctx);
+	if (ctx)
+		rotate_ctx(ctx);
 
-		perf_event_sched_in(cpuctx, ctx, current);
-	}
+	perf_event_sched_in(cpuctx, ctx, current);
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-
 done:
 	if (remove)
 		list_del_init(&cpuctx->rotation_list);
@@ -2445,10 +2454,22 @@ void perf_event_task_tick(void)
 {
 	struct list_head *head = &__get_cpu_var(rotation_list);
 	struct perf_cpu_context *cpuctx, *tmp;
+	struct perf_event_context *ctx;
+	int throttled;
 
 	WARN_ON(!irqs_disabled());
 
+	__this_cpu_inc(perf_throttled_seq);
+	throttled = __this_cpu_xchg(perf_throttled_count, 0);
+
 	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
+		ctx = &cpuctx->ctx;
+		perf_adjust_freq_unthr_context(ctx, throttled);
+
+		ctx = cpuctx->task_ctx;
+		if (ctx)
+			perf_adjust_freq_unthr_context(ctx, throttled);
+
 		if (cpuctx->jiffies_interval == 1 ||
 				!(jiffies % cpuctx->jiffies_interval))
 			perf_rotate_context(cpuctx);
@@ -4509,6 +4530,7 @@ static int __perf_event_overflow(struct perf_event *event,
 {
 	int events = atomic_read(&event->event_limit);
 	struct hw_perf_event *hwc = &event->hw;
+	u64 seq;
 	int ret = 0;
 
 	/*
@@ -4518,14 +4540,20 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (unlikely(!is_sampling_event(event)))
 		return 0;
 
-	if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
-		if (throttle) {
+	seq = __this_cpu_read(perf_throttled_seq);
+	if (seq != hwc->interrupts_seq) {
+		hwc->interrupts_seq = seq;
+		hwc->interrupts = 1;
+	} else {
+		hwc->interrupts++;
+		if (unlikely(throttle
+			     && hwc->interrupts >= max_samples_per_tick)) {
+			__this_cpu_inc(perf_throttled_count);
 			hwc->interrupts = MAX_INTERRUPTS;
 			perf_log_throttle(event, 0);
 			ret = 1;
 		}
-	} else
-		hwc->interrupts++;
+	}
 
 	if (event->attr.freq) {
 		u64 now = perf_clock();
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index ac86d67..7c12650 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -104,7 +104,7 @@ endif
 
 CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 ALL_LDFLAGS = $(LDFLAGS)
 STRIP ?= strip
 
@@ -168,10 +168,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-# Those must not be GNU-specific; they are shared with perl/ which may
-# be built by a different compiler. (Note that this is an artifact now
-# but it still might be nice to keep that distinction.)
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 59d43ab..fb85661 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -20,7 +20,6 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  */
-#define _GNU_SOURCE
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -31,7 +30,6 @@
 #include <stdlib.h>
 #include <string.h>
 
-#undef _GNU_SOURCE
 #include "perf.h"
 #include "builtin.h"
 #include "util/util.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8f80df8..dd162aa 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -89,8 +89,6 @@ void get_term_dimensions(struct winsize *ws)
 
 static void perf_top__update_print_entries(struct perf_top *top)
 {
-	top->print_entries = top->winsize.ws_row;
-
 	if (top->print_entries > 9)
 		top->print_entries -= 9;
 }
@@ -100,6 +98,13 @@ static void perf_top__sig_winch(int sig __used, siginfo_t *info __used, void *ar
 	struct perf_top *top = arg;
 
 	get_term_dimensions(&top->winsize);
+	if (!top->print_entries
+	    || (top->print_entries+4) > top->winsize.ws_row) {
+		top->print_entries = top->winsize.ws_row;
+	} else {
+		top->print_entries += 4;
+		top->winsize.ws_row = top->print_entries;
+	}
 	perf_top__update_print_entries(top);
 }
 
@@ -453,8 +458,10 @@ static void perf_top__handle_keypress(struct perf_top *top, int c)
 				};
 				perf_top__sig_winch(SIGWINCH, NULL, top);
 				sigaction(SIGWINCH, &act, NULL);
-			} else
+			} else {
+				perf_top__sig_winch(SIGWINCH, NULL, top);
 				signal(SIGWINCH, SIG_DFL);
+			}
 			break;
 		case 'E':
 			if (top->evlist->nr_entries > 1) {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3e7e0b0..ecd7f4d 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2105,7 +2105,7 @@ int perf_event__synthesize_event_type(struct perf_tool *tool,
 	strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
 
 	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
-	size = strlen(name);
+	size = strlen(ev.event_type.event_type.name);
 	size = ALIGN(size, sizeof(u64));
 	ev.event_type.header.size = sizeof(ev.event_type) -
 		(sizeof(ev.event_type.event_type.name) - size);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb25900..29cb654 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -19,7 +19,6 @@
  *
  */
 
-#define _GNU_SOURCE
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -33,7 +32,6 @@
 #include <limits.h>
 #include <elf.h>
 
-#undef _GNU_SOURCE
 #include "util.h"
 #include "event.h"
 #include "string.h"
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 215d50f..0975438 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,4 +1,3 @@
-#define _GNU_SOURCE
 #include <ctype.h>
 #include <dirent.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 6c164dc..1a8d4dc 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -21,14 +21,13 @@
  *  The parts for function graph printing was taken and modified from the
  *  Linux Kernel that were written by Frederic Weisbecker.
  */
-#define _GNU_SOURCE
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
 
-#undef _GNU_SOURCE
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 1212a38..e81aef1 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -1,6 +1,4 @@
-#define _GNU_SOURCE
 #include <stdio.h>
-#undef _GNU_SOURCE
 #include "../libslang.h"
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c
index 6ef3c56..4f48f59 100644
--- a/tools/perf/util/ui/helpline.c
+++ b/tools/perf/util/ui/helpline.c
@@ -1,4 +1,3 @@
-#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b9c530c..ecf9898 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -40,7 +40,6 @@
 #define decimal_length(x)	((int)(sizeof(x) * 2.56 + 0.5) + 1)
 
 #define _ALL_SOURCE 1
-#define _GNU_SOURCE 1
 #define _BSD_SOURCE 1
 #define HAS_BOOL
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2012-01-26 18:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2012-01-26 18:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   HEAD: 46cd6a7f680d14f6f80ede9f04aeb70fa83bd266 perf: Call perf_cgroup_event_time() directly

 Thanks,

	Ingo

------------------>
Namhyung Kim (2):
      perf: Don't call release_callchain_buffers() if allocation fails
      perf: Call perf_cgroup_event_time() directly


 kernel/events/callchain.c |    2 --
 kernel/events/core.c      |    2 +-
 2 files changed, 1 insertions(+), 3 deletions(-)

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 057e24b..6581a04 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -115,8 +115,6 @@ int get_callchain_buffers(void)
 	}
 
 	err = alloc_callchain_buffers();
-	if (err)
-		release_callchain_buffers();
 exit:
 	mutex_unlock(&callchain_mutex);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a8f4ac0..32b48c8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -815,7 +815,7 @@ static void update_event_times(struct perf_event *event)
 	 * here.
 	 */
 	if (is_cgroup_event(event))
-		run_end = perf_event_time(event);
+		run_end = perf_cgroup_event_time(event);
 	else if (ctx->is_active)
 		run_end = ctx->time;
 	else

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-12-29 21:02 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-12-29 21:02 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Robert Richter (1):
      perf/x86: Fix raw_spin_unlock_irqrestore() usage

Vladimir Zapolskiy (1):
      oprofile, arm/sh: Fix oprofile_arch_exit() linkage issue


 arch/arm/oprofile/common.c             |    2 +-
 arch/sh/oprofile/common.c              |    4 ++--
 arch/x86/kernel/cpu/perf_event_intel.c |    2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index c074e66..4e0a371 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -116,7 +116,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	return oprofile_perf_init(ops);
 }
 
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
 {
 	oprofile_perf_exit();
 }
diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c
index b4c2d2b..e4dd5d5 100644
--- a/arch/sh/oprofile/common.c
+++ b/arch/sh/oprofile/common.c
@@ -49,7 +49,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	return oprofile_perf_init(ops);
 }
 
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
 {
 	oprofile_perf_exit();
 	kfree(sh_pmu_op_name);
@@ -60,5 +60,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	ops->backtrace = sh_backtrace;
 	return -ENODEV;
 }
-void __exit oprofile_arch_exit(void) {}
+void oprofile_arch_exit(void) {}
 #endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8d601b1..121f1be 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1169,7 +1169,7 @@ again:
 		 */
 		c = &unconstrained;
 	} else if (intel_try_alt_er(event, orig_idx)) {
-		raw_spin_unlock(&era->lock);
+		raw_spin_unlock_irqrestore(&era->lock, flags);
 		goto again;
 	}
 	raw_spin_unlock_irqrestore(&era->lock, flags);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-12-09  6:16 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-12-09  6:16 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Andrew Vagin (1):
      perf header: Use event_name() to get an event name

Anton Blanchard (1):
      perf stat: Failure with "Operation not supported"

Gleb Natapov (1):
      perf: Do no try to schedule task events if there are none

Yong Zhang (1):
      lockdep, kmemcheck: Annotate ->lock in lockdep_init_map()


 kernel/events/core.c      |    4 ++--
 kernel/lockdep.c          |    8 +++++++-
 tools/perf/builtin-stat.c |    3 ++-
 tools/perf/util/header.c  |    2 +-
 4 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 600c162..d3b9df5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2174,11 +2174,11 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	perf_event_sched_in(cpuctx, ctx, task);
-
 	if (ctx->nr_events)
 		cpuctx->task_ctx = ctx;
 
+	perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
+
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index e69434b..b2e08c9 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -44,6 +44,7 @@
 #include <linux/stringify.h>
 #include <linux/bitops.h>
 #include <linux/gfp.h>
+#include <linux/kmemcheck.h>
 
 #include <asm/sections.h>
 
@@ -2948,7 +2949,12 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
-	memset(lock, 0, sizeof(*lock));
+	int i;
+
+	kmemcheck_mark_initialized(lock, sizeof(*lock));
+
+	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+		lock->class_cache[i] = NULL;
 
 #ifdef CONFIG_LOCK_STAT
 	lock->cpu = raw_smp_processor_id();
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7d98676..955930e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -463,7 +463,8 @@ static int run_perf_stat(int argc __used, const char **argv)
 
 	list_for_each_entry(counter, &evsel_list->entries, node) {
 		if (create_perf_stat_counter(counter, first) < 0) {
-			if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
+			if (errno == EINVAL || errno == ENOSYS ||
+			    errno == ENOENT || errno == EOPNOTSUPP) {
 				if (verbose)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    event_name(counter));
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index bcd05d0..33c17a2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -388,7 +388,7 @@ static int write_event_desc(int fd, struct perf_header *h __used,
 		/*
 		 * write event string as passed on cmdline
 		 */
-		ret = do_write_string(fd, attr->name);
+		ret = do_write_string(fd, event_name(attr));
 		if (ret < 0)
 			return ret;
 		/*

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-12-05 19:13 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-12-05 19:13 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf python: Fix undefined symbol problem

David Ahern (1):
      perf session: Fix crash with invalid CPU list

Gleb Natapov (1):
      perf: Do not set task_ctx pointer in cpuctx if there are no events in the context

Peter Zijlstra (5):
      perf/x86: Fix PEBS instruction unwind
      perf: Don't use -ENOSPC for out of PMU resources
      perf/x86: Enable raw event access to Intel offcore events
      perf, x86: Disable PEBS on SandyBridge chips
      perf: Fix loss of notification with multi-event

Robert Richter (3):
      oprofile: Fix crash when unloading module (hr timer mode)
      oprofile, x86: Fix crash when unloading module (nmi timer mode)
      perf, x86: Force IBS LVT offset assignment for family 10h

Tejun Heo (1):
      trace_events_filter: Use rcu_assign_pointer() when setting ftrace_event_call->filter


 arch/arm/kernel/perf_event.c              |    6 +-
 arch/mips/kernel/perf_event_mipsxx.c      |    8 +-
 arch/x86/kernel/cpu/perf_event.c          |   16 ++---
 arch/x86/kernel/cpu/perf_event_amd_ibs.c  |   29 ++++++----
 arch/x86/kernel/cpu/perf_event_intel.c    |    8 +++
 arch/x86/kernel/cpu/perf_event_intel_ds.c |    6 ++-
 arch/x86/kernel/cpu/perf_event_p4.c       |    2 +-
 arch/x86/oprofile/init.c                  |    7 ++-
 drivers/oprofile/oprof.c                  |   29 ++++++++--
 drivers/oprofile/timer_int.c              |    1 +
 include/linux/perf_event.h                |    1 +
 kernel/events/core.c                      |   89 ++++++++++++++++++++++++++++-
 kernel/events/internal.h                  |    3 +
 kernel/events/ring_buffer.c               |    3 +
 kernel/trace/trace_events_filter.c        |    6 +-
 tools/perf/util/evsel.c                   |   10 +++
 tools/perf/util/hist.c                    |   10 ---
 tools/perf/util/hist.h                    |    2 -
 tools/perf/util/session.c                 |    4 +
 19 files changed, 185 insertions(+), 55 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 24e2347..ff17b17 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -347,15 +347,15 @@ validate_group(struct perf_event *event)
 	memset(&fake_pmu, 0, sizeof(fake_pmu));
 
 	if (!validate_event(&fake_pmu, leader))
-		return -ENOSPC;
+		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
 		if (!validate_event(&fake_pmu, sibling))
-			return -ENOSPC;
+			return -EINVAL;
 	}
 
 	if (!validate_event(&fake_pmu, event))
-		return -ENOSPC;
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 4f2971b..315fc0b 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -623,7 +623,7 @@ static int mipspmu_event_init(struct perf_event *event)
 	if (!atomic_inc_not_zero(&active_events)) {
 		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
 			atomic_dec(&active_events);
-			return -ENOSPC;
+			return -EINVAL;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);
@@ -732,15 +732,15 @@ static int validate_group(struct perf_event *event)
 	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
 
 	if (!validate_event(&fake_cpuc, leader))
-		return -ENOSPC;
+		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
 		if (!validate_event(&fake_cpuc, sibling))
-			return -ENOSPC;
+			return -EINVAL;
 	}
 
 	if (!validate_event(&fake_cpuc, event))
-		return -ENOSPC;
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6408910..2bda212 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -312,12 +312,8 @@ int x86_setup_perfctr(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Do not allow config1 (extended registers) to propagate,
-	 * there's no sane user-space generalization yet:
-	 */
 	if (attr->type == PERF_TYPE_RAW)
-		return 0;
+		return x86_pmu_extra_regs(event->attr.config, event);
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, event);
@@ -588,7 +584,7 @@ done:
 				x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
 		}
 	}
-	return num ? -ENOSPC : 0;
+	return num ? -EINVAL : 0;
 }
 
 /*
@@ -607,7 +603,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 
 	if (is_x86_event(leader)) {
 		if (n >= max_count)
-			return -ENOSPC;
+			return -EINVAL;
 		cpuc->event_list[n] = leader;
 		n++;
 	}
@@ -620,7 +616,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 			continue;
 
 		if (n >= max_count)
-			return -ENOSPC;
+			return -EINVAL;
 
 		cpuc->event_list[n] = event;
 		n++;
@@ -1316,7 +1312,7 @@ static int validate_event(struct perf_event *event)
 	c = x86_pmu.get_event_constraints(fake_cpuc, event);
 
 	if (!c || !c->weight)
-		ret = -ENOSPC;
+		ret = -EINVAL;
 
 	if (x86_pmu.put_event_constraints)
 		x86_pmu.put_event_constraints(fake_cpuc, event);
@@ -1341,7 +1337,7 @@ static int validate_group(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
 	struct cpu_hw_events *fake_cpuc;
-	int ret = -ENOSPC, n;
+	int ret = -EINVAL, n;
 
 	fake_cpuc = allocate_fake_cpuc();
 	if (IS_ERR(fake_cpuc))
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index ab6343d..3b8a2d3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -199,8 +199,7 @@ static int force_ibs_eilvt_setup(void)
 		goto out;
 	}
 
-	pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
-	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+	pr_info("IBS: LVT offset %d assigned\n", offset);
 
 	return 0;
 out:
@@ -265,19 +264,23 @@ perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *h
 static __init int amd_ibs_init(void)
 {
 	u32 caps;
-	int ret;
+	int ret = -EINVAL;
 
 	caps = __get_ibs_caps();
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	if (!ibs_eilvt_valid()) {
-		ret = force_ibs_eilvt_setup();
-		if (ret) {
-			pr_err("Failed to setup IBS, %d\n", ret);
-			return ret;
-		}
-	}
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+
+	if (!ibs_eilvt_valid())
+		goto out;
 
 	get_online_cpus();
 	ibs_caps = caps;
@@ -287,7 +290,11 @@ static __init int amd_ibs_init(void)
 	smp_call_function(setup_APIC_ibs, NULL, 1);
 	put_online_cpus();
 
-	return perf_event_ibs_init();
+	ret = perf_event_ibs_init();
+out:
+	if (ret)
+		pr_err("Failed to setup IBS, %d\n", ret);
+	return ret;
 }
 
 /* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2be5ebe..8d601b1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1545,6 +1545,13 @@ static void intel_clovertown_quirks(void)
 	x86_pmu.pebs_constraints = NULL;
 }
 
+static void intel_sandybridge_quirks(void)
+{
+	printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+	x86_pmu.pebs = 0;
+	x86_pmu.pebs_constraints = NULL;
+}
+
 __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -1694,6 +1701,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
+		x86_pmu.quirks = intel_sandybridge_quirks;
 	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index c0d238f..73da6b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -493,6 +493,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
+	int is_64bit = 0;
 
 	/*
 	 * We don't need to fixup if the PEBS assist is fault like
@@ -544,7 +545,10 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		} else
 			kaddr = (void *)to;
 
-		kernel_insn_init(&insn, kaddr);
+#ifdef CONFIG_X86_64
+		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+#endif
+		insn_init(&insn, kaddr, is_64bit);
 		insn_get_length(&insn);
 		to += insn.length;
 	} while (to < ip);
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 492bf13..ef484d9 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1268,7 +1268,7 @@ reserve:
 	}
 
 done:
-	return num ? -ENOSPC : 0;
+	return num ? -EINVAL : 0;
 }
 
 static __initconst const struct x86_pmu p4_pmu = {
diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c
index cdfe4c5..f148cf6 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -21,6 +21,7 @@ extern int op_nmi_timer_init(struct oprofile_operations *ops);
 extern void op_nmi_exit(void);
 extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
 
+static int nmi_timer;
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
@@ -31,8 +32,9 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 #ifdef CONFIG_X86_LOCAL_APIC
 	ret = op_nmi_init(ops);
 #endif
+	nmi_timer = (ret != 0);
 #ifdef CONFIG_X86_IO_APIC
-	if (ret < 0)
+	if (nmi_timer)
 		ret = op_nmi_timer_init(ops);
 #endif
 	ops->backtrace = x86_backtrace;
@@ -44,6 +46,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 void oprofile_arch_exit(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	op_nmi_exit();
+	if (!nmi_timer)
+		op_nmi_exit();
 #endif
 }
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index dccd863..f8c752e 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -239,26 +239,45 @@ int oprofile_set_ulong(unsigned long *addr, unsigned long val)
 	return err;
 }
 
+static int timer_mode;
+
 static int __init oprofile_init(void)
 {
 	int err;
 
+	/* always init architecture to setup backtrace support */
 	err = oprofile_arch_init(&oprofile_ops);
-	if (err < 0 || timer) {
-		printk(KERN_INFO "oprofile: using timer interrupt.\n");
+
+	timer_mode = err || timer;	/* fall back to timer mode on errors */
+	if (timer_mode) {
+		if (!err)
+			oprofile_arch_exit();
 		err = oprofile_timer_init(&oprofile_ops);
 		if (err)
 			return err;
 	}
-	return oprofilefs_register();
+
+	err = oprofilefs_register();
+	if (!err)
+		return 0;
+
+	/* failed */
+	if (timer_mode)
+		oprofile_timer_exit();
+	else
+		oprofile_arch_exit();
+
+	return err;
 }
 
 
 static void __exit oprofile_exit(void)
 {
-	oprofile_timer_exit();
 	oprofilefs_unregister();
-	oprofile_arch_exit();
+	if (timer_mode)
+		oprofile_timer_exit();
+	else
+		oprofile_arch_exit();
 }
 
 
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 3ef4462..878fba1 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -110,6 +110,7 @@ int oprofile_timer_init(struct oprofile_operations *ops)
 	ops->start = oprofile_hrtimer_start;
 	ops->stop = oprofile_hrtimer_stop;
 	ops->cpu_type = "timer";
+	printk(KERN_INFO "oprofile: using timer interrupt.\n");
 	return 0;
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1e9ebe5..b1f8912 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -822,6 +822,7 @@ struct perf_event {
 	int				mmap_locked;
 	struct user_struct		*mmap_user;
 	struct ring_buffer		*rb;
+	struct list_head		rb_entry;
 
 	/* poll related */
 	wait_queue_head_t		waitq;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0e8457d..600c162 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -185,6 +185,9 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb);
+
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -2173,7 +2176,8 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 
 	perf_event_sched_in(cpuctx, ctx, task);
 
-	cpuctx->task_ctx = ctx;
+	if (ctx->nr_events)
+		cpuctx->task_ctx = ctx;
 
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
@@ -3190,12 +3194,33 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	struct ring_buffer *rb;
 	unsigned int events = POLL_HUP;
 
+	/*
+	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
+	 * grabs the rb reference but perf_event_set_output() overrides it.
+	 * Here is the timeline for two threads T1, T2:
+	 * t0: T1, rb = rcu_dereference(event->rb)
+	 * t1: T2, old_rb = event->rb
+	 * t2: T2, event->rb = new rb
+	 * t3: T2, ring_buffer_detach(old_rb)
+	 * t4: T1, ring_buffer_attach(rb1)
+	 * t5: T1, poll_wait(event->waitq)
+	 *
+	 * To avoid this problem, we grab mmap_mutex in perf_poll()
+	 * thereby ensuring that the assignment of the new ring buffer
+	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 */
+	mutex_lock(&event->mmap_mutex);
+
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (rb)
+	if (rb) {
+		ring_buffer_attach(event, rb);
 		events = atomic_xchg(&rb->poll, 0);
+	}
 	rcu_read_unlock();
 
+	mutex_unlock(&event->mmap_mutex);
+
 	poll_wait(file, &event->waitq, wait);
 
 	return events;
@@ -3496,6 +3521,49 @@ unlock:
 	return ret;
 }
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (!list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	if (!list_empty(&event->rb_entry))
+		goto unlock;
+
+	list_add(&event->rb_entry, &rb->event_list);
+unlock:
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_detach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_del_init(&event->rb_entry);
+	wake_up_all(&event->waitq);
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_wakeup(struct perf_event *event)
+{
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
+		wake_up_all(&event->waitq);
+	}
+	rcu_read_unlock();
+}
+
 static void rb_free_rcu(struct rcu_head *rcu_head)
 {
 	struct ring_buffer *rb;
@@ -3521,9 +3589,19 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
+	struct perf_event *event, *n;
+	unsigned long flags;
+
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
+		list_del_init(&event->rb_entry);
+		wake_up_all(&event->waitq);
+	}
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
@@ -3546,6 +3624,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
 		vma->vm_mm->pinned_vm -= event->mmap_locked;
 		rcu_assign_pointer(event->rb, NULL);
+		ring_buffer_detach(event, rb);
 		mutex_unlock(&event->mmap_mutex);
 
 		ring_buffer_put(rb);
@@ -3700,7 +3779,7 @@ static const struct file_operations perf_fops = {
 
 void perf_event_wakeup(struct perf_event *event)
 {
-	wake_up_all(&event->waitq);
+	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
 		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
@@ -5822,6 +5901,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->group_entry);
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
+	INIT_LIST_HEAD(&event->rb_entry);
+
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
 
@@ -6028,6 +6109,8 @@ set:
 
 	old_rb = event->rb;
 	rcu_assign_pointer(event->rb, rb);
+	if (old_rb)
+		ring_buffer_detach(event, old_rb);
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 09097dd..64568a6 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -22,6 +22,9 @@ struct ring_buffer {
 	local_t				lost;		/* nr records lost   */
 
 	long				watermark;	/* wakeup watermark  */
+	/* poll crap */
+	spinlock_t			event_lock;
+	struct list_head		event_list;
 
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a2a2920..7f3011c 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -209,6 +209,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->writable = 1;
 
 	atomic_set(&rb->refcount, 1);
+
+	INIT_LIST_HEAD(&rb->event_list);
+	spin_lock_init(&rb->event_lock);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 816d3d0..d6e7926 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1686,7 +1686,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		 * replace the filter for the call.
 		 */
 		filter = call->filter;
-		call->filter = filter_item->filter;
+		rcu_assign_pointer(call->filter, filter_item->filter);
 		filter_item->filter = filter;
 
 		fail = false;
@@ -1741,7 +1741,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		filter = call->filter;
 		if (!filter)
 			goto out_unlock;
-		call->filter = NULL;
+		RCU_INIT_POINTER(call->filter, NULL);
 		/* Make sure the filter is not being used */
 		synchronize_sched();
 		__free_filter(filter);
@@ -1782,7 +1782,7 @@ out:
 	 * string
 	 */
 	tmp = call->filter;
-	call->filter = filter;
+	rcu_assign_pointer(call->filter, filter);
 	if (tmp) {
 		/* Make sure the call is done with the filter */
 		synchronize_sched();
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e426264..d7915d4 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -34,6 +34,16 @@ int __perf_evsel__sample_size(u64 sample_type)
 	return size;
 }
 
+static void hists__init(struct hists *hists)
+{
+	memset(hists, 0, sizeof(*hists));
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in = &hists->entries_in_array[0];
+	hists->entries_collapsed = RB_ROOT;
+	hists->entries = RB_ROOT;
+	pthread_mutex_init(&hists->lock, NULL);
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index a36a3fa..abef270 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1211,13 +1211,3 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp)
 
 	return ret;
 }
-
-void hists__init(struct hists *hists)
-{
-	memset(hists, 0, sizeof(*hists));
-	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
-	hists->entries_in = &hists->entries_in_array[0];
-	hists->entries_collapsed = RB_ROOT;
-	hists->entries = RB_ROOT;
-	pthread_mutex_init(&hists->lock, NULL);
-}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index c86c1d2..89289c8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -63,8 +63,6 @@ struct hists {
 	struct callchain_cursor	callchain_cursor;
 };
 
-void hists__init(struct hists *hists);
-
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
 				      struct symbol *parent, u64 period);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 85c1e6b7..0f4555c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1333,6 +1333,10 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	}
 
 	map = cpu_map__new(cpu_list);
+	if (map == NULL) {
+		pr_err("Invalid cpu_list\n");
+		return -1;
+	}
 
 	for (i = 0; i < map->nr; i++) {
 		int cpu = map->map[i];

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-11-07 19:00 ` Linus Torvalds
@ 2011-11-07 19:50   ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-11-07 19:50 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Mon, Nov 7, 2011 at 10:49 AM, Ingo Molnar <mingo@elte.hu> wrote:
> >
> > Please pull the latest perf-urgent-for-linus git tree from:
> >
> >   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
> 
> I think you forgot to push. Or gave me the wrong branch name.

Oops, indeed, i forgot to push it properly. It's fixed now.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-11-07 18:49 Ingo Molnar
@ 2011-11-07 19:00 ` Linus Torvalds
  2011-11-07 19:50   ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2011-11-07 19:00 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

On Mon, Nov 7, 2011 at 10:49 AM, Ingo Molnar <mingo@elte.hu> wrote:
>
> Please pull the latest perf-urgent-for-linus git tree from:
>
>   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

I think you forgot to push. Or gave me the wrong branch name.

             Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-11-07 18:49 Ingo Molnar
  2011-11-07 19:00 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2011-11-07 18:49 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

This should finally solve the window resizing problem of the TUI: 
perf report and perf top will resize properly with xterm size 
changes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (16):
      perf evlist: Fix grouping of multiple events
      perf ui progress: Reimplement using slang
      perf ui: Improve handling sigwinch a bit
      perf ui: Reimplement ui_helpline using libslang
      perf ui: Reimplement ui__popup_menu using ui__browser
      perf ui: Reimplement the popup windows using libslang
      perf ui: Rename ui__warning_paranoid to ui__error_paranoid
      perf hists browser: Use K_TIMER
      perf ui browser: No need to switch char sets that often
      perf ui browser: Handle K_RESIZE in dialog windows
      perf header: Fix build on old systems
      perf hists: Fix recalculation of total_period when sorting entries
      perf hists browser: Warn about lost events
      perf report: Add progress bar when processing time ordered events
      perf top tui: Don't recalc column widths considering just the first page
      perf top: Fix live annotation in the --stdio interface

Masami Hiramatsu (1):
      perf tools: Fix a typo of command name as trace-cmd


 tools/perf/builtin-record.c            |   13 ++-
 tools/perf/builtin-stat.c              |   20 +++-
 tools/perf/builtin-test.c              |    6 +-
 tools/perf/builtin-top.c               |   54 +++++++---
 tools/perf/util/annotate.c             |    9 +-
 tools/perf/util/debug.c                |    7 +-
 tools/perf/util/debug.h                |   17 +--
 tools/perf/util/evlist.c               |   30 +++++
 tools/perf/util/evlist.h               |    2 +
 tools/perf/util/evsel.c                |   43 ++++++--
 tools/perf/util/evsel.h                |   10 ++-
 tools/perf/util/header.c               |    2 +-
 tools/perf/util/hist.c                 |    3 +-
 tools/perf/util/hist.h                 |    1 +
 tools/perf/util/python.c               |   31 +++++-
 tools/perf/util/session.c              |   46 ++++++--
 tools/perf/util/session.h              |    1 +
 tools/perf/util/top.h                  |    1 -
 tools/perf/util/trace-event-info.c     |    2 +-
 tools/perf/util/ui/browser.c           |  151 ++++++++++++++++++---------
 tools/perf/util/ui/browser.h           |    9 ++
 tools/perf/util/ui/browsers/annotate.c |   14 +--
 tools/perf/util/ui/browsers/hists.c    |   74 ++++++++++---
 tools/perf/util/ui/helpline.c          |   16 ++-
 tools/perf/util/ui/helpline.h          |    2 +
 tools/perf/util/ui/progress.c          |   65 +++---------
 tools/perf/util/ui/progress.h          |    7 +-
 tools/perf/util/ui/setup.c             |   83 ++++++++++++++-
 tools/perf/util/ui/ui.h                |    3 +
 tools/perf/util/ui/util.c              |  182 +++++++++++++++++++-------------
 tools/perf/util/ui/util.h              |    8 +-
 31 files changed, 624 insertions(+), 288 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f82480f..6ab58cc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -262,13 +262,16 @@ static bool perf_evlist__equal(struct perf_evlist *evlist,
 
 static void open_counters(struct perf_evlist *evlist)
 {
-	struct perf_evsel *pos;
+	struct perf_evsel *pos, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
+		struct xyarray *group_fd = NULL;
 		/*
 		 * Check if parse_single_tracepoint_event has already asked for
 		 * PERF_SAMPLE_TIME.
@@ -283,15 +286,19 @@ static void open_counters(struct perf_evlist *evlist)
 		 */
 		bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
 
+		if (group && pos != first)
+			group_fd = first->fd;
+
 		config_attr(pos, evlist);
 retry_sample_id:
 		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
+				     group_fd) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
-				ui__warning_paranoid();
+				ui__error_paranoid();
 				exit(EXIT_FAILURE);
 			} else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7ce65f5..7d98676 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -278,9 +278,14 @@ struct stats			runtime_itlb_cache_stats[MAX_NR_CPUS];
 struct stats			runtime_dtlb_cache_stats[MAX_NR_CPUS];
 struct stats			walltime_nsecs_stats;
 
-static int create_perf_stat_counter(struct perf_evsel *evsel)
+static int create_perf_stat_counter(struct perf_evsel *evsel,
+				    struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	struct xyarray *group_fd = NULL;
+
+	if (group && evsel != first)
+		group_fd = first->fd;
 
 	if (scale)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -289,14 +294,15 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	attr->inherit = !no_inherit;
 
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, group);
-
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
+						group, group_fd);
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, group);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads,
+					   group, group_fd);
 }
 
 /*
@@ -396,7 +402,7 @@ static int read_counter(struct perf_evsel *counter)
 static int run_perf_stat(int argc __used, const char **argv)
 {
 	unsigned long long t0, t1;
-	struct perf_evsel *counter;
+	struct perf_evsel *counter, *first;
 	int status = 0;
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
@@ -453,8 +459,10 @@ static int run_perf_stat(int argc __used, const char **argv)
 		close(child_ready_pipe[0]);
 	}
 
+	first = list_entry(evsel_list->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(counter, &evsel_list->entries, node) {
-		if (create_perf_stat_counter(counter) < 0) {
+		if (create_perf_stat_counter(counter, first) < 0) {
 			if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
 				if (verbose)
 					ui__warning("%s event is not supported by the kernel.\n",
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index efe696f..831d1ba 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -291,7 +291,7 @@ static int test__open_syscall_event(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false, NULL) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -366,7 +366,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false, NULL) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -531,7 +531,7 @@ static int test__basic_mmap(void)
 
 		perf_evlist__add(evlist, evsels[i]);
 
-		if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
+		if (perf_evsel__open(evsels[i], cpus, threads, false, NULL) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7a87171..c9cdedb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -89,6 +89,7 @@ static bool			vmlinux_warned;
 static bool			inherit				=  false;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
+static bool			sample_id_all_avail		=   true;
 static unsigned int		mmap_pages			=    128;
 
 static bool			dump_symtab                     =  false;
@@ -199,7 +200,8 @@ static void record_precise_ip(struct hist_entry *he, int counter, u64 ip)
 	struct symbol *sym;
 
 	if (he == NULL || he->ms.sym == NULL ||
-	    (he != top.sym_filter_entry && use_browser != 1))
+	    ((top.sym_filter_entry == NULL ||
+	      top.sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
 		return;
 
 	sym = he->ms.sym;
@@ -289,11 +291,13 @@ static void print_sym_table(void)
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (top.total_lost_warned != top.session->hists.stats.total_lost) {
-		top.total_lost_warned = top.session->hists.stats.total_lost;
-		color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
-		printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
-		       top.total_lost_warned);
+	if (top.sym_evsel->hists.stats.nr_lost_warned !=
+	    top.sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
+		top.sym_evsel->hists.stats.nr_lost_warned =
+			top.sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+		color_fprintf(stdout, PERF_COLOR_RED,
+			      "WARNING: LOST %d chunks, Check IO/CPU overload",
+			      top.sym_evsel->hists.stats.nr_lost_warned);
 		++printed;
 	}
 
@@ -561,7 +565,6 @@ static void perf_top__sort_new_samples(void *arg)
 	hists__decay_entries_threaded(&t->sym_evsel->hists,
 				      top.hide_user_symbols,
 				      top.hide_kernel_symbols);
-	hists__output_recalc_col_len(&t->sym_evsel->hists, winsize.ws_row - 3);
 }
 
 static void *display_thread_tui(void *arg __used)
@@ -671,6 +674,7 @@ static int symbol_filter(struct map *map __used, struct symbol *sym)
 }
 
 static void perf_event__process_sample(const union perf_event *event,
+				       struct perf_evsel *evsel,
 				       struct perf_sample *sample,
 				       struct perf_session *session)
 {
@@ -770,12 +774,8 @@ static void perf_event__process_sample(const union perf_event *event,
 	}
 
 	if (al.sym == NULL || !al.sym->ignore) {
-		struct perf_evsel *evsel;
 		struct hist_entry *he;
 
-		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
-		assert(evsel != NULL);
-
 		if ((sort__has_parent || symbol_conf.use_callchain) &&
 		    sample->callchain) {
 			err = perf_session__resolve_callchain(session, al.thread,
@@ -807,6 +807,7 @@ static void perf_event__process_sample(const union perf_event *event,
 static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
 	struct perf_sample sample;
+	struct perf_evsel *evsel;
 	union perf_event *event;
 	int ret;
 
@@ -817,10 +818,16 @@ static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 			continue;
 		}
 
+		evsel = perf_evlist__id2evsel(self->evlist, sample.id);
+		assert(evsel != NULL);
+
 		if (event->header.type == PERF_RECORD_SAMPLE)
-			perf_event__process_sample(event, &sample, self);
-		else
+			perf_event__process_sample(event, evsel, &sample, self);
+		else if (event->header.type < PERF_RECORD_MAX) {
+			hists__inc_nr_events(&evsel->hists, event->header.type);
 			perf_event__process(event, &sample, self);
+		} else
+			++self->hists.stats.nr_unknown_events;
 	}
 }
 
@@ -834,10 +841,16 @@ static void perf_session__mmap_read(struct perf_session *self)
 
 static void start_counters(struct perf_evlist *evlist)
 {
-	struct perf_evsel *counter;
+	struct perf_evsel *counter, *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
 
 	list_for_each_entry(counter, &evlist->entries, node) {
 		struct perf_event_attr *attr = &counter->attr;
+		struct xyarray *group_fd = NULL;
+
+		if (group && counter != first)
+			group_fd = first->fd;
 
 		attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
@@ -858,14 +871,23 @@ static void start_counters(struct perf_evlist *evlist)
 		attr->mmap = 1;
 		attr->comm = 1;
 		attr->inherit = inherit;
+retry_sample_id:
+		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
 		if (perf_evsel__open(counter, top.evlist->cpus,
-				     top.evlist->threads, group) < 0) {
+				     top.evlist->threads, group,
+				     group_fd) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
-				ui__warning_paranoid();
+				ui__error_paranoid();
 				goto out_err;
+			} else if (err == EINVAL && sample_id_all_avail) {
+				/*
+				 * Old kernel, no attr->sample_id_type_all field
+				 */
+				sample_id_all_avail = false;
+				goto retry_sample_id;
 			}
 			/*
 			 * If it's cycles then fall back to hrtimer
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index bc8f477..119e996 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -310,9 +310,12 @@ fallback:
 		}
 		err = -ENOENT;
 		dso->annotate_warned = 1;
-		pr_err("Can't annotate %s: No vmlinux file%s was found in the "
-		       "path.\nPlease use 'perf buildid-cache -av vmlinux' or "
-		       "--vmlinux vmlinux.\n",
+		pr_err("Can't annotate %s:\n\n"
+		       "No vmlinux file%s\nwas found in the path.\n\n"
+		       "Please use:\n\n"
+		       "  perf buildid-cache -av vmlinux\n\n"
+		       "or:\n\n"
+		       "  --vmlinux vmlinux",
 		       sym->name, build_id_msg ?: "");
 		goto out_free_filename;
 	}
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 155749d..26817da 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -47,19 +47,20 @@ int dump_printf(const char *fmt, ...)
 }
 
 #ifdef NO_NEWT_SUPPORT
-void ui__warning(const char *format, ...)
+int ui__warning(const char *format, ...)
 {
 	va_list args;
 
 	va_start(args, format);
 	vfprintf(stderr, format, args);
 	va_end(args);
+	return 0;
 }
 #endif
 
-void ui__warning_paranoid(void)
+int ui__error_paranoid(void)
 {
-	ui__warning("Permission error - are you root?\n"
+	return ui__error("Permission error - are you root?\n"
 		    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
 		    " -1 - Not paranoid at all\n"
 		    "  0 - Disallow raw tracepoint access for unpriv\n"
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index fd53db4..f2ce88d 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -19,23 +19,18 @@ static inline int ui_helpline__show_help(const char *format __used, va_list ap _
 	return 0;
 }
 
-static inline struct ui_progress *ui_progress__new(const char *title __used,
-						   u64 total __used)
-{
-	return (struct ui_progress *)1;
-}
-
-static inline void ui_progress__update(struct ui_progress *self __used,
-				       u64 curr __used) {}
+static inline void ui_progress__update(u64 curr __used, u64 total __used,
+				       const char *title __used) {}
 
-static inline void ui_progress__delete(struct ui_progress *self __used) {}
+#define ui__error(format, arg...) ui__warning(format, ##arg)
 #else
 extern char ui_helpline__last_msg[];
 int ui_helpline__show_help(const char *format, va_list ap);
 #include "ui/progress.h"
+int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
 #endif
 
-void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
-void ui__warning_paranoid(void);
+int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+int ui__error_paranoid(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 2f6bc89..fbb4b4a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -539,3 +539,33 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 {
 	evlist->selected = evsel;
 }
+
+int perf_evlist__open(struct perf_evlist *evlist, bool group)
+{
+	struct perf_evsel *evsel, *first;
+	int err, ncpus, nthreads;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		struct xyarray *group_fd = NULL;
+
+		if (group && evsel != first)
+			group_fd = first->fd;
+
+		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads,
+				       group, group_fd);
+		if (err < 0)
+			goto out_err;
+	}
+
+	return 0;
+out_err:
+	ncpus = evlist->cpus ? evlist->cpus->nr : 1;
+	nthreads = evlist->threads ? evlist->threads->nr : 1;
+
+	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+		perf_evsel__close(evsel, ncpus, nthreads);
+
+	return err;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6be71fc..1779ffe 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -50,6 +50,8 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
+int perf_evlist__open(struct perf_evlist *evlist, bool group);
+
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b46f6e4..e426264 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -16,6 +16,7 @@
 #include "thread_map.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
 int __perf_evsel__sample_size(u64 sample_type)
 {
@@ -204,15 +205,16 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group)
+			      struct thread_map *threads, bool group,
+			      struct xyarray *group_fds)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
-	int pid = -1;
+	int pid = -1, err;
 
 	if (evsel->fd == NULL &&
 	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
-		return -1;
+		return -ENOMEM;
 
 	if (evsel->cgrp) {
 		flags = PERF_FLAG_PID_CGROUP;
@@ -220,7 +222,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	}
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		int group_fd = -1;
+		int group_fd = group_fds ? GROUP_FD(group_fds, cpu) : -1;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -231,8 +233,10 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 								     pid,
 								     cpus->map[cpu],
 								     group_fd, flags);
-			if (FD(evsel, cpu, thread) < 0)
+			if (FD(evsel, cpu, thread) < 0) {
+				err = -errno;
 				goto out_close;
+			}
 
 			if (group && group_fd == -1)
 				group_fd = FD(evsel, cpu, thread);
@@ -249,7 +253,17 @@ out_close:
 		}
 		thread = threads->nr;
 	} while (--cpu >= 0);
-	return -1;
+	return err;
+}
+
+void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	if (evsel->fd == NULL)
+		return;
+
+	perf_evsel__close_fd(evsel, ncpus, nthreads);
+	perf_evsel__free_fd(evsel);
+	evsel->fd = NULL;
 }
 
 static struct {
@@ -269,7 +283,8 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group)
+		     struct thread_map *threads, bool group,
+		     struct xyarray *group_fd)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -279,19 +294,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group);
+	return __perf_evsel__open(evsel, cpus, threads, group, group_fd);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group)
+			     struct cpu_map *cpus, bool group,
+			     struct xyarray *group_fd)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group,
+				  group_fd);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group)
+				struct thread_map *threads, bool group,
+				struct xyarray *group_fd)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group,
+				  group_fd);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e9a3155..b1d15e6 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -82,11 +82,15 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group);
+			     struct cpu_map *cpus, bool group,
+			     struct xyarray *group_fds);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group);
+				struct thread_map *threads, bool group,
+				struct xyarray *group_fds);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group);
+		     struct thread_map *threads, bool group,
+		     struct xyarray *group_fds);
+void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 76c0b2c..bcd05d0 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,5 +1,6 @@
 #define _FILE_OFFSET_BITS 64
 
+#include "util.h"
 #include <sys/types.h>
 #include <byteswap.h>
 #include <unistd.h>
@@ -11,7 +12,6 @@
 
 #include "evlist.h"
 #include "evsel.h"
-#include "util.h"
 #include "header.h"
 #include "../perf.h"
 #include "trace-event.h"
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f6a9939..a36a3fa 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -365,7 +365,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
 
 	root = hists__get_rotate_entries_in(hists);
 	next = rb_first(root);
-	hists->stats.total_period = 0;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
@@ -379,7 +378,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
 			 * been set by, say, the hist_browser.
 			 */
 			hists__apply_filters(hists, n);
-			hists__inc_nr_entries(hists, n);
 		}
 	}
 }
@@ -442,6 +440,7 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
 	hists->entries = RB_ROOT;
 
 	hists->nr_entries = 0;
+	hists->stats.total_period = 0;
 	hists__reset_col_len(hists);
 
 	while (next) {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ff93ddc..c86c1d2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -28,6 +28,7 @@ struct events_stats {
 	u64 total_lost;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_lost_warned;
 	u32 nr_unknown_events;
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 7624324..9dd47a4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -623,7 +623,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
 	evsel->attr.inherit = inherit;
-	if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
+	/*
+	 * This will group just the fds for this single evsel, to group
+	 * multiple events, use evlist.open().
+	 */
+	if (perf_evsel__open(evsel, cpus, threads, group, NULL) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
@@ -814,6 +818,25 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	return Py_None;
 }
 
+static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	int group = 0;
+	static char *kwlist[] = { "group", NULL };
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group))
+		return NULL;
+
+	if (perf_evlist__open(evlist, group) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
 static PyMethodDef pyrf_evlist__methods[] = {
 	{
 		.ml_name  = "mmap",
@@ -822,6 +845,12 @@ static PyMethodDef pyrf_evlist__methods[] = {
 		.ml_doc	  = PyDoc_STR("mmap the file descriptor table.")
 	},
 	{
+		.ml_name  = "open",
+		.ml_meth  = (PyCFunction)pyrf_evlist__open,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("open the file descriptors.")
+	},
+	{
 		.ml_name  = "poll",
 		.ml_meth  = (PyCFunction)pyrf_evlist__poll,
 		.ml_flags = METH_VARARGS | METH_KEYWORDS,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 20e011c..85c1e6b7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -502,6 +502,7 @@ static void flush_sample_queue(struct perf_session *s,
 	struct perf_sample sample;
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
+	unsigned idx = 0, progress_next = os->nr_samples / 16;
 	int ret;
 
 	if (!ops->ordered_samples || !limit)
@@ -521,6 +522,11 @@ static void flush_sample_queue(struct perf_session *s,
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
 		list_add(&iter->list, &os->sample_cache);
+		if (++idx >= progress_next) {
+			progress_next += os->nr_samples / 16;
+			ui_progress__update(idx, os->nr_samples,
+					    "Processing time ordered events...");
+		}
 	}
 
 	if (list_empty(head)) {
@@ -529,6 +535,8 @@ static void flush_sample_queue(struct perf_session *s,
 		os->last_sample =
 			list_entry(head->prev, struct sample_queue, list);
 	}
+
+	os->nr_samples = 0;
 }
 
 /*
@@ -588,6 +596,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s)
 	u64 timestamp = new->timestamp;
 	struct list_head *p;
 
+	++os->nr_samples;
 	os->last_sample = new;
 
 	if (!sample) {
@@ -738,10 +747,27 @@ static int perf_session_deliver_event(struct perf_session *session,
 
 	dump_event(session, event, file_offset, sample);
 
+	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
+		/*
+		 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
+		 * because the tools right now may apply filters, discarding
+		 * some of the samples. For consistency, in the future we
+		 * should have something like nr_filtered_samples and remove
+		 * the sample->period from total_sample_period, etc, KISS for
+		 * now tho.
+		 *
+		 * Also testing against NULL allows us to handle files without
+		 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
+		 * future probably it'll be a good idea to restrict event
+		 * processing via perf_session to files with both set.
+		 */
+		hists__inc_nr_events(&evsel->hists, event->header.type);
+	}
+
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
 		dump_sample(session, event, sample);
-		evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 		if (evsel == NULL) {
 			++session->hists.stats.nr_unknown_id;
 			return -1;
@@ -874,11 +900,11 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 					    const struct perf_event_ops *ops)
 {
 	if (ops->lost == perf_event__process_lost &&
-	    session->hists.stats.total_lost != 0) {
-		ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64
-			    "!\n\nCheck IO/CPU overload!\n\n",
-			    session->hists.stats.total_period,
-			    session->hists.stats.total_lost);
+	    session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) {
+		ui__warning("Processed %d events and lost %d chunks!\n\n"
+			    "Check IO/CPU overload!\n\n",
+			    session->hists.stats.nr_events[0],
+			    session->hists.stats.nr_events[PERF_RECORD_LOST]);
 	}
 
 	if (session->hists.stats.nr_unknown_events != 0) {
@@ -1012,7 +1038,6 @@ int __perf_session__process_events(struct perf_session *session,
 {
 	u64 head, page_offset, file_offset, file_pos, progress_next;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
-	struct ui_progress *progress;
 	size_t	page_size, mmap_size;
 	char *buf, *mmaps[8];
 	union perf_event *event;
@@ -1030,9 +1055,6 @@ int __perf_session__process_events(struct perf_session *session,
 		file_size = data_offset + data_size;
 
 	progress_next = file_size / 16;
-	progress = ui_progress__new("Processing events...", file_size);
-	if (progress == NULL)
-		return -1;
 
 	mmap_size = session->mmap_window;
 	if (mmap_size > file_size)
@@ -1095,7 +1117,8 @@ more:
 
 	if (file_pos >= progress_next) {
 		progress_next += file_size / 16;
-		ui_progress__update(progress, file_pos);
+		ui_progress__update(file_pos, file_size,
+				    "Processing events...");
 	}
 
 	if (file_pos < file_size)
@@ -1106,7 +1129,6 @@ more:
 	session->ordered_samples.next_flush = ULLONG_MAX;
 	flush_sample_queue(session, ops);
 out_err:
-	ui_progress__delete(progress);
 	perf_session__warn_about_errors(session, ops);
 	perf_session_free_sample_buffers(session);
 	return err;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 514b06d..6e393c9 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -23,6 +23,7 @@ struct ordered_samples {
 	struct sample_queue	*sample_buffer;
 	struct sample_queue	*last_sample;
 	int			sample_buffer_idx;
+	unsigned int		nr_samples;
 };
 
 struct perf_session {
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 01d1057..3996509 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -19,7 +19,6 @@ struct perf_top {
 	u64		   kernel_samples, us_samples;
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
-	u64		   total_lost_warned;
 	int		   print_entries, count_filter, delay_secs;
 	int		   freq;
 	pid_t		   target_pid, target_tid;
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 2d530cf..d2655f0 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -80,7 +80,7 @@ static void die(const char *fmt, ...)
 	int ret = errno;
 
 	if (errno)
-		perror("trace-cmd");
+		perror("perf");
 	else
 		ret = -1;
 
diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c
index 5359f37..5568291 100644
--- a/tools/perf/util/ui/browser.c
+++ b/tools/perf/util/ui/browser.c
@@ -4,6 +4,7 @@
 #include "libslang.h"
 #include <newt.h>
 #include "ui.h"
+#include "util.h"
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
@@ -168,6 +169,59 @@ void ui_browser__refresh_dimensions(struct ui_browser *self)
 	self->x = 0;
 }
 
+void ui_browser__handle_resize(struct ui_browser *browser)
+{
+	ui__refresh_dimensions(false);
+	ui_browser__show(browser, browser->title, ui_helpline__current);
+	ui_browser__refresh(browser);
+}
+
+int ui_browser__warning(struct ui_browser *browser, int timeout,
+			const char *format, ...)
+{
+	va_list args;
+	char *text;
+	int key = 0, err;
+
+	va_start(args, format);
+	err = vasprintf(&text, format, args);
+	va_end(args);
+
+	if (err < 0) {
+		va_start(args, format);
+		ui_helpline__vpush(format, args);
+		va_end(args);
+	} else {
+		while ((key == ui__question_window("Warning!", text,
+						   "Press any key...",
+						   timeout)) == K_RESIZE)
+			ui_browser__handle_resize(browser);
+		free(text);
+	}
+
+	return key;
+}
+
+int ui_browser__help_window(struct ui_browser *browser, const char *text)
+{
+	int key;
+
+	while ((key = ui__help_window(text)) == K_RESIZE)
+		ui_browser__handle_resize(browser);
+
+	return key;
+}
+
+bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text)
+{
+	int key;
+
+	while ((key = ui__dialog_yesno(text)) == K_RESIZE)
+		ui_browser__handle_resize(browser);
+
+	return key == K_ENTER || toupper(key) == 'Y';
+}
+
 void ui_browser__reset_index(struct ui_browser *self)
 {
 	self->index = self->top_idx = 0;
@@ -230,13 +284,15 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser)
 		       (browser->nr_entries - 1));
 	}
 
+	SLsmg_set_char_set(1);
+
 	while (h < height) {
 	        ui_browser__gotorc(browser, row++, col);
-		SLsmg_set_char_set(1);
-		SLsmg_write_char(h == pct ? SLSMG_DIAMOND_CHAR : SLSMG_BOARD_CHAR);
-		SLsmg_set_char_set(0);
+		SLsmg_write_char(h == pct ? SLSMG_DIAMOND_CHAR : SLSMG_CKBRD_CHAR);
 		++h;
 	}
+
+	SLsmg_set_char_set(0);
 }
 
 static int __ui_browser__refresh(struct ui_browser *browser)
@@ -291,53 +347,10 @@ void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries)
 	browser->seek(browser, browser->top_idx, SEEK_SET);
 }
 
-static int ui__getch(int delay_secs)
-{
-	struct timeval timeout, *ptimeout = delay_secs ? &timeout : NULL;
-	fd_set read_set;
-	int err, key;
-
-	FD_ZERO(&read_set);
-	FD_SET(0, &read_set);
-
-	if (delay_secs) {
-		timeout.tv_sec = delay_secs;
-		timeout.tv_usec = 0;
-	}
-
-        err = select(1, &read_set, NULL, NULL, ptimeout);
-
-	if (err == 0)
-		return K_TIMER;
-
-	if (err == -1) {
-		if (errno == EINTR)
-			return K_RESIZE;
-		return K_ERROR;
-	}
-
-	key = SLang_getkey();
-	if (key != K_ESC)
-		return key;
-
-	FD_ZERO(&read_set);
-	FD_SET(0, &read_set);
-	timeout.tv_sec = 0;
-	timeout.tv_usec = 20;
-        err = select(1, &read_set, NULL, NULL, &timeout);
-	if (err == 0)
-		return K_ESC;
-
-	SLang_ungetkey(key);
-	return SLkp_getkey();
-}
-
 int ui_browser__run(struct ui_browser *self, int delay_secs)
 {
 	int err, key;
 
-	pthread__unblock_sigwinch();
-
 	while (1) {
 		off_t offset;
 
@@ -351,10 +364,7 @@ int ui_browser__run(struct ui_browser *self, int delay_secs)
 		key = ui__getch(delay_secs);
 
 		if (key == K_RESIZE) {
-			pthread_mutex_lock(&ui__lock);
-			SLtt_get_screen_size();
-			SLsmg_reinit_smg();
-			pthread_mutex_unlock(&ui__lock);
+			ui__refresh_dimensions(false);
 			ui_browser__refresh_dimensions(self);
 			__ui_browser__show_title(self, self->title);
 			ui_helpline__puts(self->helpline);
@@ -533,6 +543,47 @@ static int ui_browser__color_config(const char *var, const char *value,
 	return -1;
 }
 
+void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence)
+{
+	switch (whence) {
+	case SEEK_SET:
+		browser->top = browser->entries;
+		break;
+	case SEEK_CUR:
+		browser->top = browser->top + browser->top_idx + offset;
+		break;
+	case SEEK_END:
+		browser->top = browser->top + browser->nr_entries + offset;
+		break;
+	default:
+		return;
+	}
+}
+
+unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
+{
+	unsigned int row = 0, idx = browser->top_idx;
+	char **pos;
+
+	if (browser->top == NULL)
+		browser->top = browser->entries;
+
+	pos = (char **)browser->top;
+	while (idx < browser->nr_entries) {
+		if (!browser->filter || !browser->filter(browser, *pos)) {
+			ui_browser__gotorc(browser, row, 0);
+			browser->write(browser, pos, row);
+			if (++row == browser->height)
+				break;
+		}
+
+		++idx;
+		++pos;
+	}
+
+	return row;
+}
+
 void ui_browser__init(void)
 {
 	int i = 0;
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index a2c707d..84d761b 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -43,6 +43,15 @@ void ui_browser__hide(struct ui_browser *self);
 int ui_browser__refresh(struct ui_browser *self);
 int ui_browser__run(struct ui_browser *browser, int delay_secs);
 void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries);
+void ui_browser__handle_resize(struct ui_browser *browser);
+
+int ui_browser__warning(struct ui_browser *browser, int timeout,
+			const char *format, ...);
+int ui_browser__help_window(struct ui_browser *browser, const char *text);
+bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
+
+void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
+unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
 
 void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence);
 unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 4e0cb7fe..0575905 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -1,6 +1,9 @@
+#include "../../util.h"
 #include "../browser.h"
 #include "../helpline.h"
 #include "../libslang.h"
+#include "../ui.h"
+#include "../util.h"
 #include "../../annotate.h"
 #include "../../hist.h"
 #include "../../sort.h"
@@ -8,15 +11,6 @@
 #include <pthread.h>
 #include <newt.h>
 
-static void ui__error_window(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	newtWinMessagev((char *)"Error", (char *)"Ok", (char *)fmt, ap);
-	va_end(ap);
-}
-
 struct annotate_browser {
 	struct ui_browser b;
 	struct rb_root	  entries;
@@ -400,7 +394,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 		return -1;
 
 	if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) {
-		ui__error_window(ui_helpline__last_msg);
+		ui__error("%s", ui_helpline__last_msg);
 		return -1;
 	}
 
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 4663dcb..d0c94b4 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -17,6 +17,7 @@
 #include "../browser.h"
 #include "../helpline.h"
 #include "../util.h"
+#include "../ui.h"
 #include "map.h"
 
 struct hist_browser {
@@ -294,6 +295,15 @@ static void hist_browser__set_folding(struct hist_browser *self, bool unfold)
 	ui_browser__reset_index(&self->b);
 }
 
+static void ui_browser__warn_lost_events(struct ui_browser *browser)
+{
+	ui_browser__warning(browser, 4,
+		"Events are being lost, check IO/CPU overload!\n\n"
+		"You may want to run 'perf' using a RT scheduler policy:\n\n"
+		" perf top -r 80\n\n"
+		"Or reduce the sampling frequency.");
+}
+
 static int hist_browser__run(struct hist_browser *self, const char *ev_name,
 			     void(*timer)(void *arg), void *arg, int delay_secs)
 {
@@ -314,12 +324,18 @@ static int hist_browser__run(struct hist_browser *self, const char *ev_name,
 		key = ui_browser__run(&self->b, delay_secs);
 
 		switch (key) {
-		case -1:
-			/* FIXME we need to check if it was es.reason == NEWT_EXIT_TIMER */
+		case K_TIMER:
 			timer(arg);
 			ui_browser__update_nr_entries(&self->b, self->hists->nr_entries);
-			hists__browser_title(self->hists, title, sizeof(title),
-					     ev_name);
+
+			if (self->hists->stats.nr_lost_warned !=
+			    self->hists->stats.nr_events[PERF_RECORD_LOST]) {
+				self->hists->stats.nr_lost_warned =
+					self->hists->stats.nr_events[PERF_RECORD_LOST];
+				ui_browser__warn_lost_events(&self->b);
+			}
+
+			hists__browser_title(self->hists, title, sizeof(title), ev_name);
 			ui_browser__show_title(&self->b, title);
 			continue;
 		case 'D': { /* Debug */
@@ -883,7 +899,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			goto out_free_stack;
 		case 'a':
 			if (!browser->has_symbols) {
-				ui__warning(
+				ui_browser__warning(&browser->b, delay_secs * 2,
 			"Annotation is only available for symbolic views, "
 			"include \"sym\" in --sort to use it.");
 				continue;
@@ -901,7 +917,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case K_F1:
 		case 'h':
 		case '?':
-			ui__help_window("h/?/F1        Show this window\n"
+			ui_browser__help_window(&browser->b,
+					"h/?/F1        Show this window\n"
 					"UP/DOWN/PGUP\n"
 					"PGDN/SPACE    Navigate\n"
 					"q/ESC/CTRL+C  Exit browser\n\n"
@@ -914,7 +931,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					"C             Collapse all callchains\n"
 					"E             Expand all callchains\n"
 					"d             Zoom into current DSO\n"
-					"t             Zoom into current Thread\n");
+					"t             Zoom into current Thread");
 			continue;
 		case K_ENTER:
 		case K_RIGHT:
@@ -940,7 +957,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		}
 		case K_ESC:
 			if (!left_exits &&
-			    !ui__dialog_yesno("Do you really want to exit?"))
+			    !ui_browser__dialog_yesno(&browser->b,
+					       "Do you really want to exit?"))
 				continue;
 			/* Fall thru */
 		case 'q':
@@ -993,6 +1011,7 @@ add_exit_option:
 
 		if (choice == annotate) {
 			struct hist_entry *he;
+			int err;
 do_annotate:
 			he = hist_browser__selected_entry(browser);
 			if (he == NULL)
@@ -1001,10 +1020,12 @@ do_annotate:
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
 			he->used = true;
-			hist_entry__tui_annotate(he, evsel->idx, nr_events,
-						 timer, arg, delay_secs);
+			err = hist_entry__tui_annotate(he, evsel->idx, nr_events,
+						       timer, arg, delay_secs);
 			he->used = false;
 			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+			if (err)
+				ui_browser__handle_resize(&browser->b);
 		} else if (choice == browse_map)
 			map__browse(browser->selection->map);
 		else if (choice == zoom_dso) {
@@ -1056,6 +1077,7 @@ out:
 struct perf_evsel_menu {
 	struct ui_browser b;
 	struct perf_evsel *selection;
+	bool lost_events, lost_events_warned;
 };
 
 static void perf_evsel_menu__write(struct ui_browser *browser,
@@ -1068,14 +1090,29 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
 	const char *ev_name = event_name(evsel);
 	char bf[256], unit;
+	const char *warn = " ";
+	size_t printed;
 
 	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
 						       HE_COLORSET_NORMAL);
 
 	nr_events = convert_unit(nr_events, &unit);
-	snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
-		 unit, unit == ' ' ? "" : " ", ev_name);
-	slsmg_write_nstring(bf, browser->width);
+	printed = snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
+			   unit, unit == ' ' ? "" : " ", ev_name);
+	slsmg_printf("%s", bf);
+
+	nr_events = evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+	if (nr_events != 0) {
+		menu->lost_events = true;
+		if (!current_entry)
+			ui_browser__set_color(browser, HE_COLORSET_TOP);
+		nr_events = convert_unit(nr_events, &unit);
+		snprintf(bf, sizeof(bf), ": %ld%c%schunks LOST!", nr_events,
+			 unit, unit == ' ' ? "" : " ");
+		warn = bf;
+	}
+
+	slsmg_write_nstring(warn, browser->width - printed);
 
 	if (current_entry)
 		menu->selection = evsel;
@@ -1100,6 +1137,11 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 		switch (key) {
 		case K_TIMER:
 			timer(arg);
+
+			if (!menu->lost_events_warned && menu->lost_events) {
+				ui_browser__warn_lost_events(&menu->b);
+				menu->lost_events_warned = true;
+			}
 			continue;
 		case K_RIGHT:
 		case K_ENTER:
@@ -1133,7 +1175,8 @@ browse_hists:
 					pos = list_entry(pos->node.prev, struct perf_evsel, node);
 				goto browse_hists;
 			case K_ESC:
-				if (!ui__dialog_yesno("Do you really want to exit?"))
+				if (!ui_browser__dialog_yesno(&menu->b,
+						"Do you really want to exit?"))
 					continue;
 				/* Fall thru */
 			case 'q':
@@ -1145,7 +1188,8 @@ browse_hists:
 		case K_LEFT:
 			continue;
 		case K_ESC:
-			if (!ui__dialog_yesno("Do you really want to exit?"))
+			if (!ui_browser__dialog_yesno(&menu->b,
+					       "Do you really want to exit?"))
 				continue;
 			/* Fall thru */
 		case 'q':
diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c
index f36d2ff..6ef3c56 100644
--- a/tools/perf/util/ui/helpline.c
+++ b/tools/perf/util/ui/helpline.c
@@ -1,20 +1,28 @@
 #define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
-#include <newt.h>
+#include <string.h>
 
 #include "../debug.h"
 #include "helpline.h"
 #include "ui.h"
+#include "libslang.h"
 
 void ui_helpline__pop(void)
 {
-	newtPopHelpLine();
 }
 
+char ui_helpline__current[512];
+
 void ui_helpline__push(const char *msg)
 {
-	newtPushHelpLine(msg);
+	const size_t sz = sizeof(ui_helpline__current);
+
+	SLsmg_gotorc(SLtt_Screen_Rows - 1, 0);
+	SLsmg_set_color(0);
+	SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
+	SLsmg_refresh();
+	strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
 }
 
 void ui_helpline__vpush(const char *fmt, va_list ap)
@@ -63,7 +71,7 @@ int ui_helpline__show_help(const char *format, va_list ap)
 
 	if (ui_helpline__last_msg[backlog - 1] == '\n') {
 		ui_helpline__puts(ui_helpline__last_msg);
-		newtRefresh();
+		SLsmg_refresh();
 		backlog = 0;
 	}
 	pthread_mutex_unlock(&ui__lock);
diff --git a/tools/perf/util/ui/helpline.h b/tools/perf/util/ui/helpline.h
index fdcbc02..7bab6b3 100644
--- a/tools/perf/util/ui/helpline.h
+++ b/tools/perf/util/ui/helpline.h
@@ -11,4 +11,6 @@ void ui_helpline__vpush(const char *fmt, va_list ap);
 void ui_helpline__fpush(const char *fmt, ...);
 void ui_helpline__puts(const char *msg);
 
+extern char ui_helpline__current[];
+
 #endif /* _PERF_UI_HELPLINE_H_ */
diff --git a/tools/perf/util/ui/progress.c b/tools/perf/util/ui/progress.c
index d7fc399..295e366 100644
--- a/tools/perf/util/ui/progress.c
+++ b/tools/perf/util/ui/progress.c
@@ -1,60 +1,29 @@
-#include <stdlib.h>
-#include <newt.h>
 #include "../cache.h"
 #include "progress.h"
+#include "libslang.h"
+#include "ui.h"
+#include "browser.h"
 
-struct ui_progress {
-	newtComponent form, scale;
-};
-
-struct ui_progress *ui_progress__new(const char *title, u64 total)
-{
-	struct ui_progress *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		int cols;
-
-		if (use_browser <= 0)
-			return self;
-		newtGetScreenSize(&cols, NULL);
-		cols -= 4;
-		newtCenteredWindow(cols, 1, title);
-		self->form  = newtForm(NULL, NULL, 0);
-		if (self->form == NULL)
-			goto out_free_self;
-		self->scale = newtScale(0, 0, cols, total);
-		if (self->scale == NULL)
-			goto out_free_form;
-		newtFormAddComponent(self->form, self->scale);
-		newtRefresh();
-	}
-
-	return self;
-
-out_free_form:
-	newtFormDestroy(self->form);
-out_free_self:
-	free(self);
-	return NULL;
-}
-
-void ui_progress__update(struct ui_progress *self, u64 curr)
+void ui_progress__update(u64 curr, u64 total, const char *title)
 {
+	int bar, y;
 	/*
 	 * FIXME: We should have a per UI backend way of showing progress,
 	 * stdio will just show a percentage as NN%, etc.
 	 */
 	if (use_browser <= 0)
 		return;
-	newtScaleSet(self->scale, curr);
-	newtRefresh();
-}
 
-void ui_progress__delete(struct ui_progress *self)
-{
-	if (use_browser > 0) {
-		newtFormDestroy(self->form);
-		newtPopWindow();
-	}
-	free(self);
+	ui__refresh_dimensions(true);
+	pthread_mutex_lock(&ui__lock);
+	y = SLtt_Screen_Rows / 2 - 2;
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
+	SLsmg_gotorc(y++, 1);
+	SLsmg_write_string((char *)title);
+	SLsmg_set_color(HE_COLORSET_SELECTED);
+	bar = ((SLtt_Screen_Cols - 2) * curr) / total;
+	SLsmg_fill_region(y, 1, 1, bar, ' ');
+	SLsmg_refresh();
+	pthread_mutex_unlock(&ui__lock);
 }
diff --git a/tools/perf/util/ui/progress.h b/tools/perf/util/ui/progress.h
index a3820a0..d9c205b 100644
--- a/tools/perf/util/ui/progress.h
+++ b/tools/perf/util/ui/progress.h
@@ -1,11 +1,8 @@
 #ifndef _PERF_UI_PROGRESS_H_
 #define _PERF_UI_PROGRESS_H_ 1
 
-struct ui_progress;
+#include <../types.h>
 
-struct ui_progress *ui_progress__new(const char *title, u64 total);
-void ui_progress__delete(struct ui_progress *self);
-
-void ui_progress__update(struct ui_progress *self, u64 curr);
+void ui_progress__update(u64 curr, u64 total, const char *title);
 
 #endif
diff --git a/tools/perf/util/ui/setup.c b/tools/perf/util/ui/setup.c
index 1e6ba06..85a69fa 100644
--- a/tools/perf/util/ui/setup.c
+++ b/tools/perf/util/ui/setup.c
@@ -7,10 +7,85 @@
 #include "browser.h"
 #include "helpline.h"
 #include "ui.h"
+#include "util.h"
 #include "libslang.h"
+#include "keysyms.h"
 
 pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 
+static volatile int ui__need_resize;
+
+void ui__refresh_dimensions(bool force)
+{
+	if (force || ui__need_resize) {
+		ui__need_resize = 0;
+		pthread_mutex_lock(&ui__lock);
+		SLtt_get_screen_size();
+		SLsmg_reinit_smg();
+		pthread_mutex_unlock(&ui__lock);
+	}
+}
+
+static void ui__sigwinch(int sig __used)
+{
+	ui__need_resize = 1;
+}
+
+static void ui__setup_sigwinch(void)
+{
+	static bool done;
+
+	if (done)
+		return;
+
+	done = true;
+	pthread__unblock_sigwinch();
+	signal(SIGWINCH, ui__sigwinch);
+}
+
+int ui__getch(int delay_secs)
+{
+	struct timeval timeout, *ptimeout = delay_secs ? &timeout : NULL;
+	fd_set read_set;
+	int err, key;
+
+	ui__setup_sigwinch();
+
+	FD_ZERO(&read_set);
+	FD_SET(0, &read_set);
+
+	if (delay_secs) {
+		timeout.tv_sec = delay_secs;
+		timeout.tv_usec = 0;
+	}
+
+        err = select(1, &read_set, NULL, NULL, ptimeout);
+
+	if (err == 0)
+		return K_TIMER;
+
+	if (err == -1) {
+		if (errno == EINTR)
+			return K_RESIZE;
+		return K_ERROR;
+	}
+
+	key = SLang_getkey();
+	if (key != K_ESC)
+		return key;
+
+	FD_ZERO(&read_set);
+	FD_SET(0, &read_set);
+	timeout.tv_sec = 0;
+	timeout.tv_usec = 20;
+        err = select(1, &read_set, NULL, NULL, &timeout);
+	if (err == 0)
+		return K_ESC;
+
+	SLang_ungetkey(key);
+	return SLkp_getkey();
+}
+
 static void newt_suspend(void *d __used)
 {
 	newtSuspend();
@@ -71,10 +146,10 @@ void setup_browser(bool fallback_to_pager)
 void exit_browser(bool wait_for_ok)
 {
 	if (use_browser > 0) {
-		if (wait_for_ok) {
-			char title[] = "Fatal Error", ok[] = "Ok";
-			newtWinMessage(title, ok, ui_helpline__last_msg);
-		}
+		if (wait_for_ok)
+			ui__question_window("Fatal Error",
+					    ui_helpline__last_msg,
+					    "Press any key...", 0);
 		ui__exit();
 	}
 }
diff --git a/tools/perf/util/ui/ui.h b/tools/perf/util/ui/ui.h
index d264e05..7b67045 100644
--- a/tools/perf/util/ui/ui.h
+++ b/tools/perf/util/ui/ui.h
@@ -2,7 +2,10 @@
 #define _PERF_UI_H_ 1
 
 #include <pthread.h>
+#include <stdbool.h>
 
 extern pthread_mutex_t ui__lock;
 
+void ui__refresh_dimensions(bool force);
+
 #endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index fdf1fc8..45daa7c 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -1,6 +1,5 @@
-#include <newt.h>
+#include "../util.h"
 #include <signal.h>
-#include <stdio.h>
 #include <stdbool.h>
 #include <string.h>
 #include <sys/ttydefaults.h>
@@ -8,72 +7,75 @@
 #include "../cache.h"
 #include "../debug.h"
 #include "browser.h"
+#include "keysyms.h"
 #include "helpline.h"
 #include "ui.h"
 #include "util.h"
+#include "libslang.h"
 
-static void newt_form__set_exit_keys(newtComponent self)
+static void ui_browser__argv_write(struct ui_browser *browser,
+				   void *entry, int row)
 {
-	newtFormAddHotKey(self, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self, NEWT_KEY_ESCAPE);
-	newtFormAddHotKey(self, 'Q');
-	newtFormAddHotKey(self, 'q');
-	newtFormAddHotKey(self, CTRL('c'));
-}
+	char **arg = entry;
+	bool current_entry = ui_browser__is_current_entry(browser, row);
 
-static newtComponent newt_form__new(void)
-{
-	newtComponent self = newtForm(NULL, NULL, 0);
-	if (self)
-		newt_form__set_exit_keys(self);
-	return self;
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+	slsmg_write_nstring(*arg, browser->width);
 }
 
-int ui__popup_menu(int argc, char * const argv[])
+static int popup_menu__run(struct ui_browser *menu)
 {
-	struct newtExitStruct es;
-	int i, rc = -1, max_len = 5;
-	newtComponent listbox, form = newt_form__new();
+	int key;
 
-	if (form == NULL)
+	if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0)
 		return -1;
 
-	listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT);
-	if (listbox == NULL)
-		goto out_destroy_form;
+	while (1) {
+		key = ui_browser__run(menu, 0);
 
-	newtFormAddComponent(form, listbox);
+		switch (key) {
+		case K_RIGHT:
+		case K_ENTER:
+			key = menu->index;
+			break;
+		case K_LEFT:
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			key = -1;
+			break;
+		default:
+			continue;
+		}
 
-	for (i = 0; i < argc; ++i) {
-		int len = strlen(argv[i]);
-		if (len > max_len)
-			max_len = len;
-		if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i))
-			goto out_destroy_form;
+		break;
 	}
 
-	newtCenteredWindow(max_len, argc, NULL);
-	newtFormRun(form, &es);
-	rc = newtListboxGetCurrent(listbox) - NULL;
-	if (es.reason == NEWT_EXIT_HOTKEY)
-		rc = -1;
-	newtPopWindow();
-out_destroy_form:
-	newtFormDestroy(form);
-	return rc;
+	ui_browser__hide(menu);
+	return key;
 }
 
-int ui__help_window(const char *text)
+int ui__popup_menu(int argc, char * const argv[])
 {
-	struct newtExitStruct es;
-	newtComponent tb, form = newt_form__new();
-	int rc = -1;
+	struct ui_browser menu = {
+		.entries    = (void *)argv,
+		.refresh    = ui_browser__argv_refresh,
+		.seek	    = ui_browser__argv_seek,
+		.write	    = ui_browser__argv_write,
+		.nr_entries = argc,
+	};
+
+	return popup_menu__run(&menu);
+}
+
+int ui__question_window(const char *title, const char *text,
+			const char *exit_msg, int delay_secs)
+{
+	int x, y;
 	int max_len = 0, nr_lines = 0;
 	const char *t;
 
-	if (form == NULL)
-		return -1;
-
 	t = text;
 	while (1) {
 		const char *sep = strchr(t, '\n');
@@ -90,41 +92,77 @@ int ui__help_window(const char *text)
 		t = sep + 1;
 	}
 
-	tb = newtTextbox(0, 0, max_len, nr_lines, 0);
-	if (tb == NULL)
-		goto out_destroy_form;
-
-	newtTextboxSetText(tb, text);
-	newtFormAddComponent(form, tb);
-	newtCenteredWindow(max_len, nr_lines, NULL);
-	newtFormRun(form, &es);
-	newtPopWindow();
-	rc = 0;
-out_destroy_form:
-	newtFormDestroy(form);
-	return rc;
+	max_len += 2;
+	nr_lines += 4;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2,
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 2;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	SLsmg_gotorc(y + nr_lines - 2, x);
+	SLsmg_write_nstring((char *)" ", max_len);
+	SLsmg_gotorc(y + nr_lines - 1, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+	return ui__getch(delay_secs);
 }
 
-static const char yes[] = "Yes", no[] = "No",
-		  warning_str[] = "Warning!", ok[] = "Ok";
+int ui__help_window(const char *text)
+{
+	return ui__question_window("Help", text, "Press any key...", 0);
+}
 
-bool ui__dialog_yesno(const char *msg)
+int ui__dialog_yesno(const char *msg)
 {
-	/* newtWinChoice should really be accepting const char pointers... */
-	return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1;
+	return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0);
 }
 
-void ui__warning(const char *format, ...)
+int __ui__warning(const char *title, const char *format, va_list args)
 {
-	va_list args;
+	char *s;
+
+	if (use_browser > 0 && vasprintf(&s, format, args) > 0) {
+		int key;
 
-	va_start(args, format);
-	if (use_browser > 0) {
 		pthread_mutex_lock(&ui__lock);
-		newtWinMessagev((char *)warning_str, (char *)ok,
-				(char *)format, args);
+		key = ui__question_window(title, s, "Press any key...", 0);
 		pthread_mutex_unlock(&ui__lock);
-	} else
-		vfprintf(stderr, format, args);
+		free(s);
+		return key;
+	}
+
+	fprintf(stderr, "%s:\n", title);
+	vfprintf(stderr, format, args);
+	return K_ESC;
+}
+
+int ui__warning(const char *format, ...)
+{
+	int key;
+	va_list args;
+
+	va_start(args, format);
+	key = __ui__warning("Warning", format, args);
+	va_end(args);
+	return key;
+}
+
+int ui__error(const char *format, ...)
+{
+	int key;
+	va_list args;
+
+	va_start(args, format);
+	key = __ui__warning("Error", format, args);
 	va_end(args);
+	return key;
 }
diff --git a/tools/perf/util/ui/util.h b/tools/perf/util/ui/util.h
index afcbc1d..2d1738b 100644
--- a/tools/perf/util/ui/util.h
+++ b/tools/perf/util/ui/util.h
@@ -1,10 +1,14 @@
 #ifndef _PERF_UI_UTIL_H_
 #define _PERF_UI_UTIL_H_ 1
 
-#include <stdbool.h>
+#include <stdarg.h>
 
+int ui__getch(int delay_secs);
 int ui__popup_menu(int argc, char * const argv[]);
 int ui__help_window(const char *text);
-bool ui__dialog_yesno(const char *msg);
+int ui__dialog_yesno(const char *msg);
+int ui__question_window(const char *title, const char *text,
+			const char *exit_msg, int delay_secs);
+int __ui__warning(const char *title, const char *format, va_list args);
 
 #endif /* _PERF_UI_UTIL_H_ */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-08-22 17:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-08-22 17:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Geunsik Lim (1):
      MAINTAINERS: Fix list of perf events source files

Josh Boyer (1):
      perf tools: Fix build against newer glibc

Lin Ming (1):
      perf tools: Add group event scheduling option to perf record/stat

Stephane Eranian (3):
      perf list: Fix exit value
      perf evlist: Fix missing event name init for default event
      perf tools: Fix error handling of unknown events


 MAINTAINERS                              |    2 +-
 tools/perf/builtin-record.c              |    4 +++-
 tools/perf/builtin-stat.c                |    7 +++++--
 tools/perf/util/evlist.c                 |   11 ++++++++++-
 tools/perf/util/include/linux/compiler.h |    2 ++
 tools/perf/util/parse-events.c           |    8 +++++---
 6 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 1d445f5..069ee3b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4971,7 +4971,7 @@ M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 S:	Supported
-F:	kernel/perf_event*.c
+F:	kernel/events/*
 F:	include/linux/perf_event.h
 F:	arch/*/kernel/perf_event*.c
 F:	arch/*/kernel/*/perf_event*.c
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f6426b4..6b0519f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -45,7 +45,7 @@ static int			freq				=   1000;
 static int			output;
 static int			pipe_output			=      0;
 static const char		*output_name			= NULL;
-static int			group				=      0;
+static bool			group				=  false;
 static int			realtime_prio			=      0;
 static bool			nodelay				=  false;
 static bool			raw_samples			=  false;
@@ -753,6 +753,8 @@ const struct option record_options[] = {
 		    "child tasks do not inherit counters"),
 	OPT_UINTEGER('F', "freq", &user_freq, "profile at this frequency"),
 	OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
+	OPT_BOOLEAN(0, "group", &group,
+		    "put the counters into a counter group"),
 	OPT_BOOLEAN('g', "call-graph", &call_graph,
 		    "do call-graph (stack chain/backtrace) recording"),
 	OPT_INCR('v', "verbose", &verbose,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1ad04ce..5deb17d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -193,6 +193,7 @@ static int			big_num_opt			=  -1;
 static const char		*cpu_list;
 static const char		*csv_sep			= NULL;
 static bool			csv_output			= false;
+static bool			group				= false;
 
 static volatile int done = 0;
 
@@ -280,14 +281,14 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	attr->inherit = !no_inherit;
 
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, group);
 
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads, group);
 }
 
 /*
@@ -1043,6 +1044,8 @@ static const struct option options[] = {
 		    "stat events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
+	OPT_BOOLEAN('g', "group", &group,
+		    "put the counters into a counter group"),
 	OPT_BOOLEAN('c', "scale", &scale,
 		    "scale/normalize counters"),
 	OPT_INCR('v', "verbose", &verbose,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e03e7bc..c12bd47 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -85,10 +85,19 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
 	struct perf_evsel *evsel = perf_evsel__new(&attr, 0);
 
 	if (evsel == NULL)
-		return -ENOMEM;
+		goto error;
+
+	/* use strdup() because free(evsel) assumes name is allocated */
+	evsel->name = strdup("cycles");
+	if (!evsel->name)
+		goto error_free;
 
 	perf_evlist__add(evlist, evsel);
 	return 0;
+error_free:
+	perf_evsel__delete(evsel);
+error:
+	return -ENOMEM;
 }
 
 void perf_evlist__disable(struct perf_evlist *evlist)
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index 791f9dd..547628e 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -5,7 +5,9 @@
 #define __always_inline	inline
 #endif
 #define __user
+#ifndef __attribute_const__
 #define __attribute_const__
+#endif
 
 #define __used		__attribute__((__unused__))
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4ea7e19..928918b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -697,7 +697,11 @@ parse_raw_event(const char **strp, struct perf_event_attr *attr)
 		return EVT_FAILED;
 	n = hex2u64(str + 1, &config);
 	if (n > 0) {
-		*strp = str + n + 1;
+		const char *end = str + n + 1;
+		if (*end != '\0' && *end != ',' && *end != ':')
+			return EVT_FAILED;
+
+		*strp = end;
 		attr->type = PERF_TYPE_RAW;
 		attr->config = config;
 		return EVT_HANDLED;
@@ -1097,6 +1101,4 @@ void print_events(const char *event_glob)
 	printf("\n");
 
 	print_tracepoint_events(NULL, NULL);
-
-	exit(129);
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-08-11  8:17 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-08-11  8:17 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf evlist: Introduce 'disable' method
      perf python: Add PERF_RECORD_{LOST,READ,SAMPLE} routine tables
      perf report: Use ui__warning in some more places
      perf tools: Check $HOME/.perfconfig ownership

Han Pingtian (1):
      perf buildid-cache: Zero out buffer of filenames when adding/removing buildid

Jason Baron (1):
      jump label: Reduce the cycle count by changing the link order

Jesper Juhl (1):
      trace events: Update version number reference to new 3.x scheme for EVENT_POWER_TRACING_DEPRECATED

Jiri Olsa (3):
      perf tools: Add support to install perf python extension
      perf sched: Do not delete session object prematurely
      perf sched: Usage leftover from trace -> script rename

Jonathan Nieder (1):
      perf tools: do not look at ./config for configuration

Jovi Zhang (1):
      perf probe: Fix coredump introduced by probe module option

Kusanagi Kouichi (1):
      perf tools: Make clean leaves some files

Pekka Enberg (1):
      perf symbols: Check '/tmp/perf-' symbol file ownership

Youquan Song (1):
      perf, x86: Add model 45 SandyBridge support

Zhu Yanhai (1):
      perf lock: Dropping unsupported ':r' modifier


 arch/x86/kernel/cpu/perf_event_intel.c |    1 +
 kernel/Makefile                        |    3 +-
 kernel/trace/Kconfig                   |    2 +-
 tools/perf/Makefile                    |   21 ++++--
 tools/perf/builtin-lock.c              |    8 +-
 tools/perf/builtin-record.c            |   19 +-----
 tools/perf/builtin-report.c            |   15 ++--
 tools/perf/builtin-sched.c             |   24 +++++--
 tools/perf/util/config.c               |   32 ++++++---
 tools/perf/util/evlist.c               |   13 ++++
 tools/perf/util/evlist.h               |    2 +
 tools/perf/util/header.c               |    8 +-
 tools/perf/util/probe-event.c          |   12 ++-
 tools/perf/util/python.c               |  115 +++++++++++++++++++++++++++++++-
 tools/perf/util/setup.py               |   21 ++++++-
 tools/perf/util/symbol.c               |   11 +++
 16 files changed, 239 insertions(+), 68 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 45fbb8f..f88af2c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1590,6 +1590,7 @@ static __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
+	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/kernel/Makefile b/kernel/Makefile
index d06467f..eca595e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o jump_label.o
+	    async.o range.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -107,6 +107,7 @@ obj-$(CONFIG_PERF_EVENTS) += events/
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2ad39e5..cd31345 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -82,7 +82,7 @@ config EVENT_POWER_TRACING_DEPRECATED
 	  power:power_frequency
 	  This is for userspace compatibility
 	  and will vanish after 5 kernel iterations,
-	  namely 2.6.41.
+	  namely 3.1.
 
 config CONTEXT_SWITCH_TRACER
 	bool
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 56d62d3..3b8f7b8 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -181,9 +181,9 @@ strip-libs = $(filter-out -l%,$(1))
 
 $(OUTPUT)python/perf.so: $(PYRF_OBJS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
-	  --quiet build_ext \
-	  --build-lib='$(OUTPUT)python' \
-	  --build-temp='$(OUTPUT)python/temp'
+	  --quiet build_ext; \
+	mkdir -p $(OUTPUT)python && \
+	cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
 #
 # No Perl scripts right now:
 #
@@ -509,9 +509,13 @@ else
 
   PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
-  python-clean := $(PYTHON_WORD) util/setup.py clean \
-    --build-lib='$(OUTPUT)python' \
-    --build-temp='$(OUTPUT)python/temp'
+  # python extension build directories
+  PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
+  PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
+  PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
+  export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
+
+  python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
 
   ifdef NO_LIBPYTHON
     $(call disable-python)
@@ -868,6 +872,9 @@ install: all
 	$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
 	$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 
+install-python_ext:
+	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
+
 install-doc:
 	$(MAKE) -C Documentation install
 
@@ -895,7 +902,7 @@ quick-install-html:
 ### Cleaning rules
 
 clean:
-	$(RM) $(OUTPUT){*.o,*/*.o,*/*/*.o,*/*/*/*.o,$(LIB_FILE),perf-archive}
+	$(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS)
 	$(RM) $(ALL_PROGRAMS) perf
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 9ac05aa..899080a 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -942,10 +942,10 @@ static const char *record_args[] = {
 	"-f",
 	"-m", "1024",
 	"-c", "1",
-	"-e", "lock:lock_acquire:r",
-	"-e", "lock:lock_acquired:r",
-	"-e", "lock:lock_contended:r",
-	"-e", "lock:lock_release:r",
+	"-e", "lock:lock_acquire",
+	"-e", "lock:lock_acquired",
+	"-e", "lock:lock_contended",
+	"-e", "lock:lock_release",
 };
 
 static int __cmd_record(int argc, const char **argv)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 80dc5b7..f6426b4 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -30,8 +30,6 @@
 #include <sched.h>
 #include <sys/mman.h>
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
 enum write_mode_t {
 	WRITE_FORCE,
 	WRITE_APPEND
@@ -438,7 +436,6 @@ static void mmap_read_all(void)
 
 static int __cmd_record(int argc, const char **argv)
 {
-	int i;
 	struct stat st;
 	int flags;
 	int err;
@@ -682,7 +679,6 @@ static int __cmd_record(int argc, const char **argv)
 
 	for (;;) {
 		int hits = samples;
-		int thread;
 
 		mmap_read_all();
 
@@ -693,19 +689,8 @@ static int __cmd_record(int argc, const char **argv)
 			waking++;
 		}
 
-		if (done) {
-			for (i = 0; i < evsel_list->cpus->nr; i++) {
-				struct perf_evsel *pos;
-
-				list_for_each_entry(pos, &evsel_list->entries, node) {
-					for (thread = 0;
-						thread < evsel_list->threads->nr;
-						thread++)
-						ioctl(FD(pos, i, thread),
-							PERF_EVENT_IOC_DISABLE);
-				}
-			}
-		}
+		if (done)
+			perf_evlist__disable(evsel_list);
 	}
 
 	if (quiet || signr == SIGUSR1)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f854efd..d7ff277 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -162,23 +162,22 @@ static int perf_session__setup_sample_type(struct perf_session *self)
 {
 	if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
-			fprintf(stderr, "selected --sort parent, but no"
-					" callchain data. Did you call"
-					" perf record without -g?\n");
+			ui__warning("Selected --sort parent, but no "
+				    "callchain data. Did you call "
+				    "'perf record' without -g?\n");
 			return -EINVAL;
 		}
 		if (symbol_conf.use_callchain) {
-			fprintf(stderr, "selected -g but no callchain data."
-					" Did you call perf record without"
-					" -g?\n");
+			ui__warning("Selected -g but no callchain data. Did "
+				    "you call 'perf record' without -g?\n");
 			return -1;
 		}
 	} else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
 		   !symbol_conf.use_callchain) {
 			symbol_conf.use_callchain = true;
 			if (callchain_register_param(&callchain_param) < 0) {
-				fprintf(stderr, "Can't register callchain"
-						" params\n");
+				ui__warning("Can't register callchain "
+					    "params.\n");
 				return -EINVAL;
 			}
 	}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index dcfe887..5177964 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1637,23 +1637,29 @@ static struct perf_event_ops event_ops = {
 	.ordered_samples	= true,
 };
 
-static int read_events(void)
+static void read_events(bool destroy, struct perf_session **psession)
 {
 	int err = -EINVAL;
 	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
 							 0, false, &event_ops);
 	if (session == NULL)
-		return -ENOMEM;
+		die("No Memory");
 
 	if (perf_session__has_traces(session, "record -R")) {
 		err = perf_session__process_events(session, &event_ops);
+		if (err)
+			die("Failed to process events, error %d", err);
+
 		nr_events      = session->hists.stats.nr_events[0];
 		nr_lost_events = session->hists.stats.total_lost;
 		nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST];
 	}
 
-	perf_session__delete(session);
-	return err;
+	if (destroy)
+		perf_session__delete(session);
+
+	if (psession)
+		*psession = session;
 }
 
 static void print_bad_events(void)
@@ -1689,9 +1695,10 @@ static void print_bad_events(void)
 static void __cmd_lat(void)
 {
 	struct rb_node *next;
+	struct perf_session *session;
 
 	setup_pager();
-	read_events();
+	read_events(false, &session);
 	sort_lat();
 
 	printf("\n ---------------------------------------------------------------------------------------------------------------\n");
@@ -1717,6 +1724,7 @@ static void __cmd_lat(void)
 	print_bad_events();
 	printf("\n");
 
+	perf_session__delete(session);
 }
 
 static struct trace_sched_handler map_ops  = {
@@ -1731,7 +1739,7 @@ static void __cmd_map(void)
 	max_cpu = sysconf(_SC_NPROCESSORS_CONF);
 
 	setup_pager();
-	read_events();
+	read_events(true, NULL);
 	print_bad_events();
 }
 
@@ -1744,7 +1752,7 @@ static void __cmd_replay(void)
 
 	test_calibrations();
 
-	read_events();
+	read_events(true, NULL);
 
 	printf("nr_run_events:        %ld\n", nr_run_events);
 	printf("nr_sleep_events:      %ld\n", nr_sleep_events);
@@ -1769,7 +1777,7 @@ static void __cmd_replay(void)
 
 
 static const char * const sched_usage[] = {
-	"perf sched [<options>] {record|latency|map|replay|trace}",
+	"perf sched [<options>] {record|latency|map|replay|script}",
 	NULL
 };
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index e02d78c..fe02903 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -399,7 +399,6 @@ static int perf_config_global(void)
 int perf_config(config_fn_t fn, void *data)
 {
 	int ret = 0, found = 0;
-	char *repo_config = NULL;
 	const char *home = NULL;
 
 	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
@@ -414,19 +413,32 @@ int perf_config(config_fn_t fn, void *data)
 	home = getenv("HOME");
 	if (perf_config_global() && home) {
 		char *user_config = strdup(mkpath("%s/.perfconfig", home));
-		if (!access(user_config, R_OK)) {
-			ret += perf_config_from_file(fn, user_config, data);
-			found += 1;
+		struct stat st;
+
+		if (user_config == NULL) {
+			warning("Not enough memory to process %s/.perfconfig, "
+				"ignoring it.", home);
+			goto out;
 		}
-		free(user_config);
-	}
 
-	repo_config = perf_pathdup("config");
-	if (!access(repo_config, R_OK)) {
-		ret += perf_config_from_file(fn, repo_config, data);
+		if (stat(user_config, &st) < 0)
+			goto out_free;
+
+		if (st.st_uid && (st.st_uid != geteuid())) {
+			warning("File %s not owned by current user or root, "
+				"ignoring it.", user_config);
+			goto out_free;
+		}
+
+		if (!st.st_size)
+			goto out_free;
+
+		ret += perf_config_from_file(fn, user_config, data);
 		found += 1;
+out_free:
+		free(user_config);
 	}
-	free(repo_config);
+out:
 	if (found == 0)
 		return -1;
 	return ret;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b021ea9..e03e7bc 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -91,6 +91,19 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
 	return 0;
 }
 
+void perf_evlist__disable(struct perf_evlist *evlist)
+{
+	int cpu, thread;
+	struct perf_evsel *pos;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		list_for_each_entry(pos, &evlist->entries, node) {
+			for (thread = 0; thread < evlist->threads->nr; thread++)
+				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE);
+		}
+	}
+}
+
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b2b8623..ce85ae9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -53,6 +53,8 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
+void perf_evlist__disable(struct perf_evlist *evlist);
+
 static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 					 struct cpu_map *cpus,
 					 struct thread_map *threads)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index cb2959a..d4f3101 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -189,8 +189,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms)
 {
 	const size_t size = PATH_MAX;
-	char *realname, *filename = malloc(size),
-	     *linkname = malloc(size), *targetname;
+	char *realname, *filename = zalloc(size),
+	     *linkname = zalloc(size), *targetname;
 	int len, err = -1;
 
 	if (is_kallsyms) {
@@ -254,8 +254,8 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
 {
 	const size_t size = PATH_MAX;
-	char *filename = malloc(size),
-	     *linkname = malloc(size);
+	char *filename = zalloc(size),
+	     *linkname = zalloc(size);
 	int err = -1;
 
 	if (filename == NULL || linkname == NULL)
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b82d54f..1c7bfa5 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1820,11 +1820,15 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 		ret = -ENOMEM;
 		goto error;
 	}
-	tev->point.module = strdup(module);
-	if (tev->point.module == NULL) {
-		ret = -ENOMEM;
-		goto error;
+
+	if (module) {
+		tev->point.module = strdup(module);
+		if (tev->point.module == NULL) {
+			ret = -ENOMEM;
+			goto error;
+		}
 	}
+
 	tev->point.offset = pev->point.offset;
 	tev->point.retprobe = pev->point.retprobe;
 	tev->nargs = pev->nargs;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 8e0b5a3..cbc8f21 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -187,16 +187,119 @@ static PyTypeObject pyrf_throttle_event__type = {
 	.tp_repr	= (reprfunc)pyrf_throttle_event__repr,
 };
 
+static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object.");
+
+static PyMemberDef pyrf_lost_event__members[] = {
+	sample_members
+	member_def(lost_event, id, T_ULONGLONG, "event id"),
+	member_def(lost_event, lost, T_ULONGLONG, "number of lost events"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", "
+			 "lost: %#" PRIx64 " }",
+		     pevent->event.lost.id, pevent->event.lost.lost) < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_lost_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.lost_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_lost_event__doc,
+	.tp_members	= pyrf_lost_event__members,
+	.tp_repr	= (reprfunc)pyrf_lost_event__repr,
+};
+
+static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object.");
+
+static PyMemberDef pyrf_read_event__members[] = {
+	sample_members
+	member_def(read_event, pid, T_UINT, "event pid"),
+	member_def(read_event, tid, T_UINT, "event tid"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent)
+{
+	return PyString_FromFormat("{ type: read, pid: %u, tid: %u }",
+				   pevent->event.read.pid,
+				   pevent->event.read.tid);
+	/*
+ 	 * FIXME: return the array of read values,
+ 	 * making this method useful ;-)
+ 	 */
+}
+
+static PyTypeObject pyrf_read_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.read_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_read_event__doc,
+	.tp_members	= pyrf_read_event__members,
+	.tp_repr	= (reprfunc)pyrf_read_event__repr,
+};
+
+static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object.");
+
+static PyMemberDef pyrf_sample_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: sample }") < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_sample_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.sample_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_sample_event__doc,
+	.tp_members	= pyrf_sample_event__members,
+	.tp_repr	= (reprfunc)pyrf_sample_event__repr,
+};
+
 static int pyrf_event__setup_types(void)
 {
 	int err;
 	pyrf_mmap_event__type.tp_new =
 	pyrf_task_event__type.tp_new =
 	pyrf_comm_event__type.tp_new =
+	pyrf_lost_event__type.tp_new =
+	pyrf_read_event__type.tp_new =
+	pyrf_sample_event__type.tp_new =
 	pyrf_throttle_event__type.tp_new = PyType_GenericNew;
 	err = PyType_Ready(&pyrf_mmap_event__type);
 	if (err < 0)
 		goto out;
+	err = PyType_Ready(&pyrf_lost_event__type);
+	if (err < 0)
+		goto out;
 	err = PyType_Ready(&pyrf_task_event__type);
 	if (err < 0)
 		goto out;
@@ -206,20 +309,26 @@ static int pyrf_event__setup_types(void)
 	err = PyType_Ready(&pyrf_throttle_event__type);
 	if (err < 0)
 		goto out;
+	err = PyType_Ready(&pyrf_read_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_sample_event__type);
+	if (err < 0)
+		goto out;
 out:
 	return err;
 }
 
 static PyTypeObject *pyrf_event__type[] = {
 	[PERF_RECORD_MMAP]	 = &pyrf_mmap_event__type,
-	[PERF_RECORD_LOST]	 = &pyrf_mmap_event__type,
+	[PERF_RECORD_LOST]	 = &pyrf_lost_event__type,
 	[PERF_RECORD_COMM]	 = &pyrf_comm_event__type,
 	[PERF_RECORD_EXIT]	 = &pyrf_task_event__type,
 	[PERF_RECORD_THROTTLE]	 = &pyrf_throttle_event__type,
 	[PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type,
 	[PERF_RECORD_FORK]	 = &pyrf_task_event__type,
-	[PERF_RECORD_READ]	 = &pyrf_mmap_event__type,
-	[PERF_RECORD_SAMPLE]	 = &pyrf_mmap_event__type,
+	[PERF_RECORD_READ]	 = &pyrf_read_event__type,
+	[PERF_RECORD_SAMPLE]	 = &pyrf_sample_event__type,
 };
 
 static PyObject *pyrf_event__new(union perf_event *event)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index bbc982f..95d3700 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -3,9 +3,27 @@
 from distutils.core import setup, Extension
 from os import getenv
 
+from distutils.command.build_ext   import build_ext   as _build_ext
+from distutils.command.install_lib import install_lib as _install_lib
+
+class build_ext(_build_ext):
+    def finalize_options(self):
+        _build_ext.finalize_options(self)
+        self.build_lib  = build_lib
+        self.build_temp = build_tmp
+
+class install_lib(_install_lib):
+    def finalize_options(self):
+        _install_lib.finalize_options(self)
+        self.build_dir = build_lib
+
+
 cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
 cflags += getenv('CFLAGS', '').split()
 
+build_lib = getenv('PYTHON_EXTBUILD_LIB')
+build_tmp = getenv('PYTHON_EXTBUILD_TMP')
+
 perf = Extension('perf',
 		  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
 			     'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
@@ -21,4 +39,5 @@ setup(name='perf',
       author_email='acme@redhat.com',
       license='GPLv2',
       url='http://perf.wiki.kernel.org',
-      ext_modules=[perf])
+      ext_modules=[perf],
+      cmdclass={'build_ext': build_ext, 'install_lib': install_lib})
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index eec1963..a8b5371 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1504,6 +1504,17 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	dso->adjust_symbols = 0;
 
 	if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+		struct stat st;
+
+		if (stat(dso->name, &st) < 0)
+			return -1;
+
+		if (st.st_uid && (st.st_uid != geteuid())) {
+			pr_warning("File %s not owned by current user or root, "
+				"ignoring it.\n", dso->name);
+			return -1;
+		}
+
 		ret = dso__load_perf_map(dso, map, filter);
 		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
 					      SYMTAB__NOT_FOUND;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-07-07 18:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-07-07 18:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Frédéric Weisbecker, Steven Rostedt,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Robert Richter (1):
      oprofile, x86: Fix race in nmi handler while starting counters

Xiao Guangrong (1):
      jump_label: Fix jump_label update for modules


 arch/x86/oprofile/nmi_int.c |   14 ++++++++++----
 kernel/jump_label.c         |   14 +++++++++-----
 2 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cf97500..68894fd 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy)
 static int nmi_start(void)
 {
 	get_online_cpus();
-	on_each_cpu(nmi_cpu_start, NULL, 1);
 	ctr_running = 1;
+	/* make ctr_running visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_start, NULL, 1);
 	put_online_cpus();
 	return 0;
 }
@@ -504,15 +506,18 @@ static int nmi_setup(void)
 
 	nmi_enabled = 0;
 	ctr_running = 0;
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	err = register_die_notifier(&profile_exceptions_nb);
 	if (err)
 		goto fail;
 
 	get_online_cpus();
 	register_cpu_notifier(&oprofile_cpu_nb);
-	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	nmi_enabled = 1;
+	/* make nmi_enabled visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	put_online_cpus();
 
 	return 0;
@@ -531,7 +536,8 @@ static void nmi_shutdown(void)
 	nmi_enabled = 0;
 	ctr_running = 0;
 	put_online_cpus();
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	unregister_die_notifier(&profile_exceptions_nb);
 	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index fa27e75..a8ce450 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -375,15 +375,19 @@ int jump_label_text_reserved(void *start, void *end)
 
 static void jump_label_update(struct jump_label_key *key, int enable)
 {
-	struct jump_entry *entry = key->entries;
-
-	/* if there are no users, entry can be NULL */
-	if (entry)
-		__jump_label_update(key, entry, __stop___jump_table, enable);
+	struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
 
 #ifdef CONFIG_MODULES
+	struct module *mod = __module_address((jump_label_t)key);
+
 	__jump_label_mod_update(key, enable);
+
+	if (mod)
+		stop = mod->jump_entries + mod->num_jump_entries;
 #endif
+	/* if there are no users, entry can be NULL */
+	if (entry)
+		__jump_label_update(key, entry, stop, enable);
 }
 
 #endif

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-06-19  8:44 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-06-19  8:44 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Mathias Krause (1):
      tools/perf: Fix static build of perf tool

Steven Rostedt (1):
      tracing: Fix regression in printk_formats file


 kernel/trace/trace_printk.c |    5 +----
 tools/perf/Makefile         |    2 +-
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index dff763b..1f06468 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -240,13 +240,10 @@ static const char **find_next(void *v, loff_t *pos)
 	const char **fmt = v;
 	int start_index;
 
-	if (!fmt)
-		fmt = __start___trace_bprintk_fmt + *pos;
-
 	start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt;
 
 	if (*pos < start_index)
-		return fmt;
+		return __start___trace_bprintk_fmt + *pos;
 
 	return find_next_mod_format(start_index, v, fmt, pos);
 }
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 032ba63..940257b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -633,7 +633,7 @@ prefix_SQ = $(subst ','\'',$(prefix))
 
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
 
-LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS)
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
 ALL_CFLAGS += $(ARCH_CFLAGS)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-06-13  9:53 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-06-13  9:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
GuoWen Li (1):
      ftrace: Fix possible undefined return code

Robert Richter (4):
      oprofile, x86: Add comments to IBS LVT offset initialization
      oprofile: Free potentially owned tasks in case of errors
      oprofile: Fix locking dependency in sync_start()
      oprofile, dcookies: Fix possible circular locking dependency

Steven Rostedt (2):
      kprobes/trace: Fix kprobe selftest for gcc 4.6
      ftrace: Revert 8ab2b7efd ftrace: Remove unnecessary disabling of irqs


 arch/x86/kernel/apic/apic.c      |    3 ++-
 arch/x86/oprofile/op_model_amd.c |   13 +++++++++----
 drivers/oprofile/buffer_sync.c   |   21 +++++++++++----------
 fs/dcookies.c                    |    3 +++
 kernel/trace/ftrace.c            |    9 ++++++++-
 kernel/trace/trace_kprobe.c      |    8 ++++++--
 6 files changed, 39 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b961af8..b9338b8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -390,7 +390,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 
 /*
  * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * enables the vector. See also the BKDGs. Must be called with
+ * preemption disabled.
  */
 
 int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 9fd8a56..9cbb710 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -609,16 +609,21 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
 	return 0;
 }
 
+/*
+ * This runs only on the current cpu. We try to find an LVT offset and
+ * setup the local APIC. For this we must disable preemption. On
+ * success we initialize all nodes with this offset. This updates then
+ * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
+ * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_-
+ * amd_cpu_shutdown() using the new offset.
+ */
 static int force_ibs_eilvt_setup(void)
 {
 	int offset;
 	int ret;
 
-	/*
-	 * find the next free available EILVT entry, skip offset 0,
-	 * pin search to this cpu
-	 */
 	preempt_disable();
+	/* find the next free available EILVT entry, skip offset 0 */
 	for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
 		if (get_eilvt(offset))
 			break;
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index a3984f4..f34b5b2 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -141,6 +141,13 @@ static struct notifier_block module_load_nb = {
 	.notifier_call = module_load_notify,
 };
 
+static void free_all_tasks(void)
+{
+	/* make sure we don't leak task structs */
+	process_task_mortuary();
+	process_task_mortuary();
+}
+
 int sync_start(void)
 {
 	int err;
@@ -148,8 +155,6 @@ int sync_start(void)
 	if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL))
 		return -ENOMEM;
 
-	mutex_lock(&buffer_mutex);
-
 	err = task_handoff_register(&task_free_nb);
 	if (err)
 		goto out1;
@@ -166,7 +171,6 @@ int sync_start(void)
 	start_cpu_work();
 
 out:
-	mutex_unlock(&buffer_mutex);
 	return err;
 out4:
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
@@ -174,6 +178,7 @@ out3:
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 out2:
 	task_handoff_unregister(&task_free_nb);
+	free_all_tasks();
 out1:
 	free_cpumask_var(marked_cpus);
 	goto out;
@@ -182,20 +187,16 @@ out1:
 
 void sync_stop(void)
 {
-	/* flush buffers */
-	mutex_lock(&buffer_mutex);
 	end_cpu_work();
 	unregister_module_notifier(&module_load_nb);
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
-	mutex_unlock(&buffer_mutex);
-	flush_cpu_work();
+	barrier();			/* do all of the above first */
 
-	/* make sure we don't leak task structs */
-	process_task_mortuary();
-	process_task_mortuary();
+	flush_cpu_work();
 
+	free_all_tasks();
 	free_cpumask_var(marked_cpus);
 }
 
diff --git a/fs/dcookies.c b/fs/dcookies.c
index a21cabd..dda0dc7 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -178,6 +178,8 @@ SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len)
 	/* FIXME: (deleted) ? */
 	path = d_path(&dcs->path, kbuf, PAGE_SIZE);
 
+	mutex_unlock(&dcookie_mutex);
+
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
 		goto out_free;
@@ -194,6 +196,7 @@ SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len)
 
 out_free:
 	kfree(kbuf);
+	return err;
 out:
 	mutex_unlock(&dcookie_mutex);
 	return err;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1ee417f..908038f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2740,7 +2740,7 @@ static int ftrace_process_regex(struct ftrace_hash *hash,
 {
 	char *func, *command, *next = buff;
 	struct ftrace_func_command *p;
-	int ret;
+	int ret = -EINVAL;
 
 	func = strsep(&next, ":");
 
@@ -3330,6 +3330,7 @@ static int ftrace_process_locs(struct module *mod,
 {
 	unsigned long *p;
 	unsigned long addr;
+	unsigned long flags;
 
 	mutex_lock(&ftrace_lock);
 	p = start;
@@ -3346,7 +3347,13 @@ static int ftrace_process_locs(struct module *mod,
 		ftrace_record_ip(addr);
 	}
 
+	/*
+	 * Disable interrupts to prevent interrupts from executing
+	 * code that is being modified.
+	 */
+	local_irq_save(flags);
 	ftrace_update_code(mod);
+	local_irq_restore(flags);
 	mutex_unlock(&ftrace_lock);
 
 	return 0;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f925c45..27d13b3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1870,8 +1870,12 @@ fs_initcall(init_kprobe_trace);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 
-static int kprobe_trace_selftest_target(int a1, int a2, int a3,
-					int a4, int a5, int a6)
+/*
+ * The "__used" keeps gcc from removing the function symbol
+ * from the kallsyms table.
+ */
+static __used int kprobe_trace_selftest_target(int a1, int a2, int a3,
+					       int a4, int a5, int a6)
 {
 	return a1 + a2 + a3 + a4 + a5 + a6;
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-06-08 13:46 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-06-08 13:46 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf evlist: Remove dependency on debug routines
      perf python: Use exception to propagate errors
      perf evlist: Don't die if sample_{id_all|type} is invalid

Frederic Weisbecker (1):
      perf python: Fix argument name list of read_on_cpu()

Peter Zijlstra (1):
      perf, cgroups: Fix up for new API

Vince Weaver (2):
      perf: Comment /proc/sys/kernel/perf_event_paranoid to be part of user ABI
      perf: Fix comments in include/linux/perf_event.h


 include/linux/perf_event.h |    8 ++--
 kernel/events/core.c       |   22 ++-----------
 kernel/sysctl.c            |    6 ++++
 tools/perf/builtin-test.c  |    2 +-
 tools/perf/util/event.c    |   16 ----------
 tools/perf/util/event.h    |    2 -
 tools/perf/util/evlist.c   |   68 ++++++++++++++++++++++++-------------------
 tools/perf/util/evlist.h   |    6 ++-
 tools/perf/util/evsel.c    |   16 ++++++++++
 tools/perf/util/evsel.h    |    7 ++++
 tools/perf/util/python.c   |   14 ++++-----
 tools/perf/util/session.c  |   12 +++++++-
 12 files changed, 97 insertions(+), 82 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3412684..e0786e3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -137,14 +137,14 @@ enum perf_event_sample_format {
  *
  * struct read_format {
  *	{ u64		value;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
  *	  }		cntr[nr];
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d863b3c..9efe710 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7402,26 +7402,12 @@ static int __perf_cgroup_move(void *info)
 	return 0;
 }
 
-static void perf_cgroup_move(struct task_struct *task)
+static void
+perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task)
 {
 	task_function_call(task, __perf_cgroup_move, task);
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		struct cgroup *old_cgrp, struct task_struct *task,
-		bool threadgroup)
-{
-	perf_cgroup_move(task);
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			perf_cgroup_move(c);
-		}
-		rcu_read_unlock();
-	}
-}
-
 static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		struct cgroup *old_cgrp, struct task_struct *task)
 {
@@ -7433,7 +7419,7 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	if (!(task->flags & PF_EXITING))
 		return;
 
-	perf_cgroup_move(task);
+	perf_cgroup_attach_task(cgrp, task);
 }
 
 struct cgroup_subsys perf_subsys = {
@@ -7442,6 +7428,6 @@ struct cgroup_subsys perf_subsys = {
 	.create		= perf_cgroup_create,
 	.destroy	= perf_cgroup_destroy,
 	.exit		= perf_cgroup_exit,
-	.attach		= perf_cgroup_attach,
+	.attach_task	= perf_cgroup_attach_task,
 };
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4fc9244..f175d98 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -938,6 +938,12 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_PERF_EVENTS
+	/*
+	 * User-space scripts rely on the existence of this file
+	 * as a feature check for perf_events being enabled.
+	 *
+	 * So it's an ABI, do not remove!
+	 */
 	{
 		.procname	= "perf_event_paranoid",
 		.data		= &sysctl_perf_event_paranoid,
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index b671862..2da9162 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -474,7 +474,7 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = perf_sample_size(attr.sample_type);
+	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0fe9adf..3c1b8a6 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -35,22 +35,6 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-int perf_sample_size(u64 sample_type)
-{
-	u64 mask = sample_type & PERF_SAMPLE_MASK;
-	int size = 0;
-	int i;
-
-	for (i = 0; i < 64; i++) {
-		if (mask & (1ULL << i))
-			size++;
-	}
-
-	size *= sizeof(u64);
-
-	return size;
-}
-
 static struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c083328..1d7f664 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -82,8 +82,6 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 };
 
-int perf_sample_size(u64 sample_type);
-
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 50aa348..b021ea9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,7 +12,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
-#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -257,19 +256,15 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
 			       int idx, int prot, int mask, int fd)
 {
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[idx].base == MAP_FAILED) {
-		if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
-			ui__warning("Inherit is not allowed on per-task "
-				    "events using mmap.\n");
+	if (evlist->mmap[idx].base == MAP_FAILED)
 		return -1;
-	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
@@ -289,7 +284,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 
 				if (output == -1) {
 					output = fd;
-					if (__perf_evlist__mmap(evlist, evsel, cpu,
+					if (__perf_evlist__mmap(evlist, cpu,
 								prot, mask, output) < 0)
 						goto out_unmap;
 				} else {
@@ -329,7 +324,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 
 			if (output == -1) {
 				output = fd;
-				if (__perf_evlist__mmap(evlist, evsel, thread,
+				if (__perf_evlist__mmap(evlist, thread,
 							prot, mask, output) < 0)
 					goto out_unmap;
 			} else {
@@ -460,33 +455,46 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
 	return 0;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
 {
-	struct perf_evsel *pos;
-	u64 type = 0;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (!type)
-			type = pos->attr.sample_type;
-		else if (type != pos->attr.sample_type)
-			die("non matching sample_type");
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_type != pos->attr.sample_type)
+			return false;
 	}
 
-	return type;
+	return true;
 }
 
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_type;
+}
+
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
 {
-	bool value = false, first = true;
-	struct perf_evsel *pos;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (first) {
-			value = pos->attr.sample_id_all;
-			first = false;
-		} else if (value != pos->attr.sample_id_all)
-			die("non matching sample_id_all");
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_id_all != pos->attr.sample_id_all)
+			return false;
 	}
 
-	return value;
+	return true;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_id_all;
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0a1ef1f..b2b8623 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -66,7 +66,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cca29ed..0239eb8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,22 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+int __perf_evsel__sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1ULL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f79bb2c..7e9366e 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -149,4 +149,11 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
+int __perf_evsel__sample_size(u64 sample_type);
+
+static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
+{
+	return __perf_evsel__sample_size(evsel->attr.sample_type);
+}
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 69436b3..a9ac050 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -674,7 +674,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	struct perf_evlist *evlist = &pevlist->evlist;
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
-	static char *kwlist[] = {"sample_id_all", NULL, NULL};
+	static char *kwlist[] = {"cpu", "sample_id_all", NULL, NULL};
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -692,16 +692,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
 		err = perf_event__parse_sample(event, first->attr.sample_type,
-					       perf_sample_size(first->attr.sample_type),
+					       perf_evsel__sample_size(first),
 					       sample_id_all, &pevent->sample);
-		if (err) {
-			pr_err("Can't parse sample, err = %d\n", err);
-			goto end;
-		}
-
+		if (err)
+			return PyErr_Format(PyExc_OSError,
+					    "perf: can't parse sample, err=%d", err);
 		return pyevent;
 	}
-end:
+
 	Py_INCREF(Py_None);
 	return Py_None;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64500fc..f5a8fbd 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -58,6 +58,16 @@ static int perf_session__open(struct perf_session *self, bool force)
 		goto out_close;
 	}
 
+	if (!perf_evlist__valid_sample_type(self->evlist)) {
+		pr_err("non matching sample_type");
+		goto out_close;
+	}
+
+	if (!perf_evlist__valid_sample_id_all(self->evlist)) {
+		pr_err("non matching sample_id_all");
+		goto out_close;
+	}
+
 	self->size = input_stat.st_size;
 	return 0;
 
@@ -97,7 +107,7 @@ out:
 void perf_session__update_sample_type(struct perf_session *self)
 {
 	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = perf_sample_size(self->sample_type);
+	self->sample_size = __perf_evsel__sample_size(self->sample_type);
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	perf_session__id_header_size(self);
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-05-28 16:34 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-05-28 16:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      oprofile: Use linux/mutex.h

Arnaldo Carvalho de Melo (6):
      perf symbols: Handle /proc/sys/kernel/kptr_restrict
      perf tools: Fix build on older systems
      perf tools: Make sure kptr_restrict warnings fit 80 col terms
      perf top: Remove unused macro
      perf top: Handle kptr_restrict
      perf top: Don't stop if no kernel symtab is found

David Ahern (1):
      perf events: initialize fd array to -1 instead of 0

Eric B Munson (1):
      oprofile, powerpc: Handle events that raise an exception without overflowing

Ingo Molnar (1):
      watchdog: Fix non-standard prototype of get_softlockup_thresh()

Jesper Juhl (1):
      perf: Remove duplicate headers

Jiri Olsa (1):
      jump_label: Check entries limit in __jump_label_update

Peter Zijlstra (1):
      perf: Fix SIGIO handling

Rabin Vincent (1):
      ftrace/recordmcount: Avoid STT_FUNC symbols as base on ARM

Rakib Mullick (1):
      x86/ftrace: Fix compiler warning in ftrace.c

Robert Richter (1):
      oprofile, x86: Enable preemption during pci device setup in IBS init

Steven Rostedt (7):
      maccess,probe_kernel: Make write/read src const void *
      scripts/tags.sh: Fix ctags for DEFINE_EVENT()
      scripts/tags.sh: Add magic for trace-events for etags too
      ftrace: Have ftrace_startup() return failure code
      tracing: Have event with function tracer check error return
      ftrace: Set ops->flag to enabled even on static function tracing
      ftrace: Add internal recursive checks

liubo (2):
      tracing: Add __print_symbolic_u64 to avoid warnings on 32bit machine
      tracing: Update btrfs's tracepoints to use u64 interface


 arch/blackfin/mm/maccess.c              |    4 +-
 arch/powerpc/oprofile/op_model_power4.c |   24 ++++++++-
 arch/s390/mm/maccess.c                  |    4 +-
 arch/x86/kernel/ftrace.c                |   12 ++--
 arch/x86/oprofile/op_model_amd.c        |   95 +++++++++++++++++-------------
 drivers/oprofile/event_buffer.h         |    2 +-
 drivers/oprofile/oprof.c                |    2 +-
 include/linux/ftrace_event.h            |   12 ++++
 include/linux/sched.h                   |    2 +-
 include/linux/uaccess.h                 |    8 +-
 include/trace/events/btrfs.h            |    4 +-
 include/trace/ftrace.h                  |   13 ++++
 kernel/events/core.c                    |    8 +++
 kernel/jump_label.c                     |   18 ++++--
 kernel/trace/ftrace.c                   |   31 ++++++++--
 kernel/trace/ring_buffer.c              |   10 ++--
 kernel/trace/trace.h                    |   15 +++++
 kernel/trace/trace_events.c             |    7 ++-
 kernel/trace/trace_output.c             |   27 +++++++++
 kernel/watchdog.c                       |    9 +--
 mm/maccess.c                            |    8 +-
 scripts/recordmcount.h                  |    8 +++
 scripts/tags.sh                         |    6 +-
 tools/perf/Makefile                     |    2 +
 tools/perf/builtin-annotate.c           |    2 -
 tools/perf/builtin-record.c             |   10 +++
 tools/perf/builtin-report.c             |   23 ++++++++
 tools/perf/builtin-script.c             |    1 -
 tools/perf/builtin-top.c                |   37 ++++++++++--
 tools/perf/util/event.c                 |   15 ++++-
 tools/perf/util/evsel.c                 |   10 +++
 tools/perf/util/header.c                |    8 ++-
 tools/perf/util/include/linux/const.h   |    1 +
 tools/perf/util/symbol.c                |   48 ++++++++++++++++
 tools/perf/util/symbol.h                |    3 +-
 35 files changed, 382 insertions(+), 107 deletions(-)
 create mode 100644 tools/perf/util/include/linux/const.h

diff --git a/arch/blackfin/mm/maccess.c b/arch/blackfin/mm/maccess.c
index b71cebc..e253211 100644
--- a/arch/blackfin/mm/maccess.c
+++ b/arch/blackfin/mm/maccess.c
@@ -16,7 +16,7 @@ static int validate_memory_access_address(unsigned long addr, int size)
 	return bfin_mem_access_type(addr, size);
 }
 
-long probe_kernel_read(void *dst, void *src, size_t size)
+long probe_kernel_read(void *dst, const void *src, size_t size)
 {
 	unsigned long lsrc = (unsigned long)src;
 	int mem_type;
@@ -55,7 +55,7 @@ long probe_kernel_read(void *dst, void *src, size_t size)
 	return -EFAULT;
 }
 
-long probe_kernel_write(void *dst, void *src, size_t size)
+long probe_kernel_write(void *dst, const void *src, size_t size)
 {
 	unsigned long ldst = (unsigned long)dst;
 	int mem_type;
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 8ee51a2..e6bec74 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -261,6 +261,28 @@ static int get_kernel(unsigned long pc, unsigned long mmcra)
 	return is_kernel;
 }
 
+static bool pmc_overflow(unsigned long val)
+{
+	if ((int)val < 0)
+		return true;
+
+	/*
+	 * Events on POWER7 can roll back if a speculative event doesn't
+	 * eventually complete. Unfortunately in some rare cases they will
+	 * raise a performance monitor exception. We need to catch this to
+	 * ensure we reset the PMC. In all cases the PMC will be 256 or less
+	 * cycles from overflow.
+	 *
+	 * We only do this if the first pass fails to find any overflowing
+	 * PMCs because a user might set a period of less than 256 and we
+	 * don't want to mistakenly reset them.
+	 */
+	if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256))
+		return true;
+
+	return false;
+}
+
 static void power4_handle_interrupt(struct pt_regs *regs,
 				    struct op_counter_config *ctr)
 {
@@ -281,7 +303,7 @@ static void power4_handle_interrupt(struct pt_regs *regs,
 
 	for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
 		val = classic_ctr_read(i);
-		if (val < 0) {
+		if (pmc_overflow(val)) {
 			if (oprofile_running && ctr[i].enabled) {
 				oprofile_add_ext_sample(pc, regs, i, is_kernel);
 				classic_ctr_write(i, reset_value[i]);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 71a4b0d..51e5cd9 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -19,7 +19,7 @@
  * using the stura instruction.
  * Returns the number of bytes copied or -EFAULT.
  */
-static long probe_kernel_write_odd(void *dst, void *src, size_t size)
+static long probe_kernel_write_odd(void *dst, const void *src, size_t size)
 {
 	unsigned long count, aligned;
 	int offset, mask;
@@ -45,7 +45,7 @@ static long probe_kernel_write_odd(void *dst, void *src, size_t size)
 	return rc ? rc : count;
 }
 
-long probe_kernel_write(void *dst, void *src, size_t size)
+long probe_kernel_write(void *dst, const void *src, size_t size)
 {
 	long copied = 0;
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0ba15a6..c9a281f 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -123,7 +123,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;		/* holds return value of text write */
 static void *mod_code_ip;		/* holds the IP to write to */
-static void *mod_code_newcode;		/* holds the text to write to the IP */
+static const void *mod_code_newcode;	/* holds the text to write to the IP */
 
 static unsigned nmi_wait_count;
 static atomic_t nmi_update_count = ATOMIC_INIT(0);
@@ -225,7 +225,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 }
 
 static int
-do_ftrace_mod_code(unsigned long ip, void *new_code)
+do_ftrace_mod_code(unsigned long ip, const void *new_code)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -266,8 +266,8 @@ static const unsigned char *ftrace_nop_replace(void)
 }
 
 static int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-		   unsigned char *new_code)
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code)
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
@@ -301,7 +301,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_call_replace(ip, addr);
@@ -312,7 +312,7 @@ int ftrace_make_nop(struct module *mod,
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_nop_replace();
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index c3b8e24..9fd8a56 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -316,16 +316,23 @@ static void op_amd_stop_ibs(void)
 		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
-static inline int eilvt_is_available(int offset)
+static inline int get_eilvt(int offset)
 {
-	/* check if we may assign a vector */
 	return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
 }
 
+static inline int put_eilvt(int offset)
+{
+	return !setup_APIC_eilvt(offset, 0, 0, 1);
+}
+
 static inline int ibs_eilvt_valid(void)
 {
 	int offset;
 	u64 val;
+	int valid = 0;
+
+	preempt_disable();
 
 	rdmsrl(MSR_AMD64_IBSCTL, val);
 	offset = val & IBSCTL_LVT_OFFSET_MASK;
@@ -333,16 +340,20 @@ static inline int ibs_eilvt_valid(void)
 	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
 		pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
 		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
-		return 0;
+		goto out;
 	}
 
-	if (!eilvt_is_available(offset)) {
+	if (!get_eilvt(offset)) {
 		pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
 		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
-		return 0;
+		goto out;
 	}
 
-	return 1;
+	valid = 1;
+out:
+	preempt_enable();
+
+	return valid;
 }
 
 static inline int get_ibs_offset(void)
@@ -600,67 +611,69 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
 
 static int force_ibs_eilvt_setup(void)
 {
-	int i;
+	int offset;
 	int ret;
 
-	/* find the next free available EILVT entry */
-	for (i = 1; i < 4; i++) {
-		if (!eilvt_is_available(i))
-			continue;
-		ret = setup_ibs_ctl(i);
-		if (ret)
-			return ret;
-		pr_err(FW_BUG "using offset %d for IBS interrupts\n", i);
-		return 0;
+	/*
+	 * find the next free available EILVT entry, skip offset 0,
+	 * pin search to this cpu
+	 */
+	preempt_disable();
+	for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
+		if (get_eilvt(offset))
+			break;
 	}
+	preempt_enable();
 
-	printk(KERN_DEBUG "No EILVT entry available\n");
-
-	return -EBUSY;
-}
-
-static int __init_ibs_nmi(void)
-{
-	int ret;
-
-	if (ibs_eilvt_valid())
-		return 0;
+	if (offset == APIC_EILVT_NR_MAX) {
+		printk(KERN_DEBUG "No EILVT entry available\n");
+		return -EBUSY;
+	}
 
-	ret = force_ibs_eilvt_setup();
+	ret = setup_ibs_ctl(offset);
 	if (ret)
-		return ret;
+		goto out;
 
-	if (!ibs_eilvt_valid())
-		return -EFAULT;
+	if (!ibs_eilvt_valid()) {
+		ret = -EFAULT;
+		goto out;
+	}
 
+	pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
 	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
 
 	return 0;
+out:
+	preempt_disable();
+	put_eilvt(offset);
+	preempt_enable();
+	return ret;
 }
 
 /*
  * check and reserve APIC extended interrupt LVT offset for IBS if
  * available
- *
- * init_ibs() preforms implicitly cpu-local operations, so pin this
- * thread to its current CPU
  */
 
 static void init_ibs(void)
 {
-	preempt_disable();
-
 	ibs_caps = get_ibs_caps();
+
 	if (!ibs_caps)
+		return;
+
+	if (ibs_eilvt_valid())
 		goto out;
 
-	if (__init_ibs_nmi() < 0)
-		ibs_caps = 0;
-	else
-		printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
+	if (!force_ibs_eilvt_setup())
+		goto out;
+
+	/* Failed to setup ibs */
+	ibs_caps = 0;
+	return;
 
 out:
-	preempt_enable();
+	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 }
 
 static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
diff --git a/drivers/oprofile/event_buffer.h b/drivers/oprofile/event_buffer.h
index 4e70749..a8d5bb3 100644
--- a/drivers/oprofile/event_buffer.h
+++ b/drivers/oprofile/event_buffer.h
@@ -11,7 +11,7 @@
 #define EVENT_BUFFER_H
 
 #include <linux/types.h>
-#include <asm/mutex.h>
+#include <linux/mutex.h>
 
 int alloc_event_buffer(void);
 
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index f9bda64..dccd863 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -14,7 +14,7 @@
 #include <linux/moduleparam.h>
 #include <linux/workqueue.h>
 #include <linux/time.h>
-#include <asm/mutex.h>
+#include <linux/mutex.h>
 
 #include "oprof.h"
 #include "event_buffer.h"
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index b5a550a..59d3ef1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -16,6 +16,11 @@ struct trace_print_flags {
 	const char		*name;
 };
 
+struct trace_print_flags_u64 {
+	unsigned long long	mask;
+	const char		*name;
+};
+
 const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 				   unsigned long flags,
 				   const struct trace_print_flags *flag_array);
@@ -23,6 +28,13 @@ const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 				     const struct trace_print_flags *symbol_array);
 
+#if BITS_PER_LONG == 32
+const char *ftrace_print_symbols_seq_u64(struct trace_seq *p,
+					 unsigned long long val,
+					 const struct trace_print_flags_u64
+								 *symbol_array);
+#endif
+
 const char *ftrace_print_hex_seq(struct trace_seq *p,
 				 const unsigned char *buf, int len);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f18300e..106bd8a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1535,7 +1535,7 @@ struct task_struct {
 #ifdef CONFIG_TRACING
 	/* state flags for use by tracers */
 	unsigned long trace;
-	/* bitmask of trace recursion */
+	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d512d98..5ca0951 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -93,8 +93,8 @@ static inline unsigned long __copy_from_user_nocache(void *to,
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-extern long probe_kernel_read(void *dst, void *src, size_t size);
-extern long __probe_kernel_read(void *dst, void *src, size_t size);
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
  * probe_kernel_write(): safely attempt to write to a location
@@ -105,7 +105,7 @@ extern long __probe_kernel_read(void *dst, void *src, size_t size);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-extern long notrace probe_kernel_write(void *dst, void *src, size_t size);
-extern long notrace __probe_kernel_write(void *dst, void *src, size_t size);
+extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
+extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
 #endif		/* __LINUX_UACCESS_H__ */
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index f445cff..4114129 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -28,7 +28,7 @@ struct extent_buffer;
 		{ BTRFS_SHARED_DATA_REF_KEY, 	"SHARED_DATA_REF" })
 
 #define __show_root_type(obj)						\
-	__print_symbolic(obj,						\
+	__print_symbolic_u64(obj,					\
 		{ BTRFS_ROOT_TREE_OBJECTID, 	"ROOT_TREE"	},	\
 		{ BTRFS_EXTENT_TREE_OBJECTID, 	"EXTENT_TREE"	},	\
 		{ BTRFS_CHUNK_TREE_OBJECTID, 	"CHUNK_TREE"	},	\
@@ -125,7 +125,7 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 );
 
 #define __show_map_type(type)						\
-	__print_symbolic(type,						\
+	__print_symbolic_u64(type,					\
 		{ EXTENT_MAP_LAST_BYTE, "LAST_BYTE" 	},		\
 		{ EXTENT_MAP_HOLE, 	"HOLE" 		},		\
 		{ EXTENT_MAP_INLINE, 	"INLINE" 	},		\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3e68366..533c49f 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -205,6 +205,19 @@
 		ftrace_print_symbols_seq(p, value, symbols);		\
 	})
 
+#undef __print_symbolic_u64
+#if BITS_PER_LONG == 32
+#define __print_symbolic_u64(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags_u64 symbols[] =	\
+			{ symbol_array, { -1, NULL } };			\
+		ftrace_print_symbols_seq_u64(p, value, symbols);	\
+	})
+#else
+#define __print_symbolic_u64(value, symbol_array...)			\
+			__print_symbolic(value, symbol_array)
+#endif
+
 #undef __print_hex
 #define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c09767f..d863b3c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5028,6 +5028,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	else
 		perf_event_output(event, nmi, data, regs);
 
+	if (event->fasync && event->pending_kill) {
+		if (nmi) {
+			event->pending_wakeup = 1;
+			irq_work_queue(&event->pending);
+		} else
+			perf_event_wakeup(event);
+	}
+
 	return ret;
 }
 
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 74d1c09..fa27e75 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -105,9 +105,12 @@ static int __jump_label_text_reserved(struct jump_entry *iter_start,
 }
 
 static void __jump_label_update(struct jump_label_key *key,
-		struct jump_entry *entry, int enable)
+				struct jump_entry *entry,
+				struct jump_entry *stop, int enable)
 {
-	for (; entry->key == (jump_label_t)(unsigned long)key; entry++) {
+	for (; (entry < stop) &&
+	      (entry->key == (jump_label_t)(unsigned long)key);
+	      entry++) {
 		/*
 		 * entry->code set to 0 invalidates module init text sections
 		 * kernel_text_address() verifies we are not in core kernel
@@ -181,7 +184,11 @@ static void __jump_label_mod_update(struct jump_label_key *key, int enable)
 	struct jump_label_mod *mod = key->next;
 
 	while (mod) {
-		__jump_label_update(key, mod->entries, enable);
+		struct module *m = mod->mod;
+
+		__jump_label_update(key, mod->entries,
+				    m->jump_entries + m->num_jump_entries,
+				    enable);
 		mod = mod->next;
 	}
 }
@@ -245,7 +252,8 @@ static int jump_label_add_module(struct module *mod)
 		key->next = jlm;
 
 		if (jump_label_enabled(key))
-			__jump_label_update(key, iter, JUMP_LABEL_ENABLE);
+			__jump_label_update(key, iter, iter_stop,
+					    JUMP_LABEL_ENABLE);
 	}
 
 	return 0;
@@ -371,7 +379,7 @@ static void jump_label_update(struct jump_label_key *key, int enable)
 
 	/* if there are no users, entry can be NULL */
 	if (entry)
-		__jump_label_update(key, entry, enable);
+		__jump_label_update(key, entry, __stop___jump_table, enable);
 
 #ifdef CONFIG_MODULES
 	__jump_label_mod_update(key, enable);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d017c2c..1ee417f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -109,12 +109,18 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 static void ftrace_global_list_func(unsigned long ip,
 				    unsigned long parent_ip)
 {
-	struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/
+	struct ftrace_ops *op;
+
+	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
+		return;
 
+	trace_recursion_set(TRACE_GLOBAL_BIT);
+	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
 	while (op != &ftrace_list_end) {
 		op->func(ip, parent_ip);
 		op = rcu_dereference_raw(op->next); /*see above*/
 	};
+	trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
@@ -1638,12 +1644,12 @@ static void ftrace_startup_enable(int command)
 	ftrace_run_update_code(command);
 }
 
-static void ftrace_startup(struct ftrace_ops *ops, int command)
+static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	bool hash_enable = true;
 
 	if (unlikely(ftrace_disabled))
-		return;
+		return -ENODEV;
 
 	ftrace_start_up++;
 	command |= FTRACE_ENABLE_CALLS;
@@ -1662,6 +1668,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command)
 		ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
+
+	return 0;
 }
 
 static void ftrace_shutdown(struct ftrace_ops *ops, int command)
@@ -2501,7 +2509,7 @@ static void __enable_ftrace_function_probe(void)
 
 	ret = __register_ftrace_function(&trace_probe_ops);
 	if (!ret)
-		ftrace_startup(&trace_probe_ops, 0);
+		ret = ftrace_startup(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 1;
 }
@@ -3466,7 +3474,11 @@ device_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)	do { } while (0)
+# define ftrace_startup(ops, command)			\
+	({						\
+		(ops)->flags |= FTRACE_OPS_FL_ENABLED;	\
+		0;					\
+	})
 # define ftrace_shutdown(ops, command)	do { } while (0)
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
@@ -3484,6 +3496,10 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	struct ftrace_ops *op;
 
+	if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
+		return;
+
+	trace_recursion_set(TRACE_INTERNAL_BIT);
 	/*
 	 * Some of the ops may be dynamically allocated,
 	 * they must be freed after a synchronize_sched().
@@ -3496,6 +3512,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 		op = rcu_dereference_raw(op->next);
 	};
 	preempt_enable_notrace();
+	trace_recursion_clear(TRACE_INTERNAL_BIT);
 }
 
 static void clear_ftrace_swapper(void)
@@ -3799,7 +3816,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
 	ret = __register_ftrace_function(ops);
 	if (!ret)
-		ftrace_startup(ops, 0);
+		ret = ftrace_startup(ops, 0);
 
 
  out_unlock:
@@ -4045,7 +4062,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_return = retfunc;
 	ftrace_graph_entry = entryfunc;
 
-	ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0ef7b4b..b0c7aa4 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2216,7 +2216,7 @@ static noinline void trace_recursive_fail(void)
 
 	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
 		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-		    current->trace_recursion,
+		    trace_recursion_buffer(),
 		    hardirq_count() >> HARDIRQ_SHIFT,
 		    softirq_count() >> SOFTIRQ_SHIFT,
 		    in_nmi());
@@ -2226,9 +2226,9 @@ static noinline void trace_recursive_fail(void)
 
 static inline int trace_recursive_lock(void)
 {
-	current->trace_recursion++;
+	trace_recursion_inc();
 
-	if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+	if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
 		return 0;
 
 	trace_recursive_fail();
@@ -2238,9 +2238,9 @@ static inline int trace_recursive_lock(void)
 
 static inline void trace_recursive_unlock(void)
 {
-	WARN_ON_ONCE(!current->trace_recursion);
+	WARN_ON_ONCE(!trace_recursion_buffer());
 
-	current->trace_recursion--;
+	trace_recursion_dec();
 }
 
 #else
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b69c4b..229f859 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -784,4 +784,19 @@ extern const char *__stop___trace_bprintk_fmt[];
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT		(1<<11)
+#define TRACE_GLOBAL_BIT		(1<<12)
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 2fe1103..686ec39 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1657,7 +1657,12 @@ static struct ftrace_ops trace_ops __initdata  =
 
 static __init void event_trace_self_test_with_function(void)
 {
-	register_ftrace_function(&trace_ops);
+	int ret;
+	ret = register_ftrace_function(&trace_ops);
+	if (WARN_ON(ret < 0)) {
+		pr_info("Failed to enable function tracer for event tests\n");
+		return;
+	}
 	pr_info("Running tests again, along with the function tracer\n");
 	event_trace_self_tests();
 	unregister_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cf535cc..e37de49 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -353,6 +353,33 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
+#if BITS_PER_LONG == 32
+const char *
+ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
+			 const struct trace_print_flags_u64 *symbol_array)
+{
+	int i;
+	const char *ret = p->buffer + p->len;
+
+	for (i = 0;  symbol_array[i].name; i++) {
+
+		if (val != symbol_array[i].mask)
+			continue;
+
+		trace_seq_puts(p, symbol_array[i].name);
+		break;
+	}
+
+	if (!p->len)
+		trace_seq_printf(p, "0x%llx", val);
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq_u64);
+#endif
+
 const char *
 ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7daa4b0..3d0c56a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -415,15 +415,13 @@ static void watchdog_nmi_disable(int cpu) { return; }
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /* prepare/enable/disable routines */
-static int watchdog_prepare_cpu(int cpu)
+static void watchdog_prepare_cpu(int cpu)
 {
 	struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
 
 	WARN_ON(per_cpu(softlockup_watchdog, cpu));
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = watchdog_timer_fn;
-
-	return 0;
 }
 
 static int watchdog_enable(int cpu)
@@ -542,17 +540,16 @@ static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	int hotcpu = (unsigned long)hcpu;
-	int err = 0;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		err = watchdog_prepare_cpu(hotcpu);
+		watchdog_prepare_cpu(hotcpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		if (watchdog_enabled)
-			err = watchdog_enable(hotcpu);
+			watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
diff --git a/mm/maccess.c b/mm/maccess.c
index e2b6f56..4cee182 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -15,10 +15,10 @@
  * happens, handle that and return -EFAULT.
  */
 
-long __weak probe_kernel_read(void *dst, void *src, size_t size)
+long __weak probe_kernel_read(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_read")));
 
-long __probe_kernel_read(void *dst, void *src, size_t size)
+long __probe_kernel_read(void *dst, const void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
@@ -43,10 +43,10 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long __weak probe_kernel_write(void *dst, void *src, size_t size)
+long __weak probe_kernel_write(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_write")));
 
-long __probe_kernel_write(void *dst, void *src, size_t size)
+long __probe_kernel_write(void *dst, const void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 4be6036..f40a6af6 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -43,6 +43,7 @@
 #undef ELF_R_INFO
 #undef Elf_r_info
 #undef ELF_ST_BIND
+#undef ELF_ST_TYPE
 #undef fn_ELF_R_SYM
 #undef fn_ELF_R_INFO
 #undef uint_t
@@ -76,6 +77,7 @@
 # define ELF_R_INFO		ELF64_R_INFO
 # define Elf_r_info		Elf64_r_info
 # define ELF_ST_BIND		ELF64_ST_BIND
+# define ELF_ST_TYPE		ELF64_ST_TYPE
 # define fn_ELF_R_SYM		fn_ELF64_R_SYM
 # define fn_ELF_R_INFO		fn_ELF64_R_INFO
 # define uint_t			uint64_t
@@ -108,6 +110,7 @@
 # define ELF_R_INFO		ELF32_R_INFO
 # define Elf_r_info		Elf32_r_info
 # define ELF_ST_BIND		ELF32_ST_BIND
+# define ELF_ST_TYPE		ELF32_ST_TYPE
 # define fn_ELF_R_SYM		fn_ELF32_R_SYM
 # define fn_ELF_R_INFO		fn_ELF32_R_INFO
 # define uint_t			uint32_t
@@ -427,6 +430,11 @@ static unsigned find_secsym_ndx(unsigned const txtndx,
 		if (txtndx == w2(symp->st_shndx)
 			/* avoid STB_WEAK */
 		    && (STB_LOCAL == st_bind || STB_GLOBAL == st_bind)) {
+			/* function symbols on ARM have quirks, avoid them */
+			if (w2(ehdr->e_machine) == EM_ARM
+			    && ELF_ST_TYPE(symp->st_info) == STT_FUNC)
+				continue;
+
 			*recvalp = _w(symp->st_value);
 			return symp - sym0;
 		}
diff --git a/scripts/tags.sh b/scripts/tags.sh
index bd6185d..75c5d24 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -132,7 +132,7 @@ exuberant()
 	--regex-asm='/^ENTRY\(([^)]*)\).*/\1/'                  \
 	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
 	--regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'		\
-	--regex-c++='/^DEFINE_EVENT\(([^,)]*).*/trace_\1/'
+	--regex-c++='/^DEFINE_EVENT\([^,)]*, *([^,)]*).*/trace_\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--langdef=kconfig --language-force=kconfig              \
@@ -152,7 +152,9 @@ emacs()
 {
 	all_sources | xargs $1 -a                               \
 	--regex='/^ENTRY(\([^)]*\)).*/\1/'                      \
-	--regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'
+	--regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'   \
+	--regex='/^TRACE_EVENT(\([^,)]*\).*/trace_\1/'		\
+	--regex='/^DEFINE_EVENT([^,)]*, *\([^,)]*\).*/trace_\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1455413..032ba63 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -215,11 +215,13 @@ LIB_FILE=$(OUTPUT)libperf.a
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/linux/const.h
 LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
 LIB_H += util/include/linux/compiler.h
+LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e18eb7e..7b139e1 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,8 +8,6 @@
 #include "builtin.h"
 
 #include "util/util.h"
-
-#include "util/util.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0974f95..8e2c857 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -823,6 +823,16 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	symbol__init();
 
+	if (symbol_conf.kptr_restrict)
+		pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+
 	if (no_buildid_cache || no_buildid)
 		disable_buildid_cache();
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 498c6f7..287a173 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -116,6 +116,9 @@ static int process_sample_event(union perf_event *event,
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
 	if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
 		pr_debug("problem incrementing symbol period, skipping event\n");
 		return -1;
@@ -249,6 +252,8 @@ static int __cmd_report(void)
 	u64 nr_samples;
 	struct perf_session *session;
 	struct perf_evsel *pos;
+	struct map *kernel_map;
+	struct kmap *kernel_kmap;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
 	signal(SIGINT, sig_handler);
@@ -268,6 +273,24 @@ static int __cmd_report(void)
 	if (ret)
 		goto out_delete;
 
+	kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION];
+	kernel_kmap = map__kmap(kernel_map);
+	if (kernel_map == NULL ||
+	    (kernel_map->dso->hit &&
+	     (kernel_kmap->ref_reloc_sym == NULL ||
+	      kernel_kmap->ref_reloc_sym->addr == 0))) {
+		const struct dso *kdso = kernel_map->dso;
+
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+			    RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION]) ?
+"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+"can't be resolved." :
+"If some relocation was applied (e.g. kexec) symbols may be misresolved.");
+	}
+
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
 		goto out_delete;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 974f6d3..22747de 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -10,7 +10,6 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
-#include "util/parse-options.h"
 #include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2d7934e..f2f3f49 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -62,8 +62,6 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
 static struct perf_top top = {
 	.count_filter		= 5,
 	.delay_secs		= 2,
@@ -82,6 +80,8 @@ static bool			use_tui, use_stdio;
 
 static int			default_interval		=      0;
 
+static bool			kptr_restrict_warned;
+static bool			vmlinux_warned;
 static bool			inherit				=  false;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
@@ -740,7 +740,22 @@ static void perf_event__process_sample(const union perf_event *event,
 	    al.filtered)
 		return;
 
+	if (!kptr_restrict_warned &&
+	    symbol_conf.kptr_restrict &&
+	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Kernel%s samples will not be resolved.\n",
+			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  " modules" : "");
+		if (use_browser <= 0)
+			sleep(5);
+		kptr_restrict_warned = true;
+	}
+
 	if (al.sym == NULL) {
+		const char *msg = "Kernel samples will not be resolved.\n";
 		/*
 		 * As we do lazy loading of symtabs we only will know if the
 		 * specified vmlinux file is invalid when we actually have a
@@ -752,12 +767,20 @@ static void perf_event__process_sample(const union perf_event *event,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
+		if (!kptr_restrict_warned && !vmlinux_warned &&
+		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-			ui__warning("The %s file can't be used\n",
-				    symbol_conf.vmlinux_name);
-			exit_browser(0);
-			exit(1);
+			if (symbol_conf.vmlinux_name) {
+				ui__warning("The %s file can't be used.\n%s",
+					    symbol_conf.vmlinux_name, msg);
+			} else {
+				ui__warning("A vmlinux file was not found.\n%s",
+					    msg);
+			}
+
+			if (use_browser <= 0)
+				sleep(5);
+			vmlinux_warned = true;
 		}
 
 		return;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6635fcd..0fe9adf 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -553,9 +553,18 @@ static int perf_event__process_kernel_mmap(union perf_event *event,
 			goto out_problem;
 
 		perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 event->mmap.pgoff);
+
+		/*
+		 * Avoid using a zero address (kptr_restrict) for the ref reloc
+		 * symbol. Effectively having zero here means that at record
+		 * time /proc/sys/kernel/kptr_restrict was non zero.
+		 */
+		if (event->mmap.pgoff != 0) {
+			perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+								 symbol_name,
+								 event->mmap.pgoff);
+		}
+
 		if (machine__is_default_guest(machine)) {
 			/*
 			 * preload dso of guest kernel and modules
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ee0fe0d..cca29ed 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -35,7 +35,17 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	int cpu, thread;
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+	if (evsel->fd) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			for (thread = 0; thread < nthreads; thread++) {
+				FD(evsel, cpu, thread) = -1;
+			}
+		}
+	}
+
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0717beb..afb0849 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -193,9 +193,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
-	if (is_kallsyms)
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			return 0;
+		}
 		realname = (char *)name;
-	else
+	} else
 		realname = realpath(name, NULL);
 
 	if (realname == NULL || filename == NULL || linkname == NULL)
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 0000000..1b476c9
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 516876d..eec1963 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -676,9 +676,30 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	return count + moved;
 }
 
+static bool symbol__restricted_filename(const char *filename,
+					const char *restricted_filename)
+{
+	bool restricted = false;
+
+	if (symbol_conf.kptr_restrict) {
+		char *r = realpath(filename, NULL);
+
+		if (r != NULL) {
+			restricted = strcmp(r, restricted_filename) == 0;
+			free(r);
+			return restricted;
+		}
+	}
+
+	return restricted;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return -1;
+
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
@@ -1790,6 +1811,9 @@ static int machine__create_modules(struct machine *machine)
 		modules = path;
 	}
 
+	if (symbol__restricted_filename(path, "/proc/modules"))
+		return -1;
+
 	file = fopen(modules, "r");
 	if (file == NULL)
 		return -1;
@@ -2239,6 +2263,9 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
 		}
 	}
 
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
 	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
 		return 0;
 
@@ -2410,6 +2437,25 @@ static int setup_list(struct strlist **list, const char *list_str,
 	return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+	bool value = false;
+
+	if (geteuid() != 0) {
+		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+		if (fp != NULL) {
+			char line[8];
+
+			if (fgets(line, sizeof(line), fp) != NULL)
+				value = atoi(line) != 0;
+
+			fclose(fp);
+		}
+	}
+
+	return value;
+}
+
 int symbol__init(void)
 {
 	const char *symfs;
@@ -2456,6 +2502,8 @@ int symbol__init(void)
 	if (symfs != symbol_conf.symfs)
 		free((void *)symfs);
 
+	symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
 	symbol_conf.initialized = true;
 	return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 242de01..325ee36 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -75,7 +75,8 @@ struct symbol_conf {
 			use_callchain,
 			exclude_other,
 			show_cpu_utilization,
-			initialized;
+			initialized,
+			kptr_restrict;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-05-24  2:41 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-05-24  2:41 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (1):
      perf tools: Fix sample type size calculation in 32 bits archs

Jesper Juhl (1):
      profile: Use vzalloc() rather than vmalloc() & memset()


 kernel/profile.c        |    6 ++----
 tools/perf/util/event.c |    2 +-
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/kernel/profile.c b/kernel/profile.c
index 66f841b..14c9f87 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -126,11 +126,9 @@ int __ref profile_init(void)
 	if (prof_buffer)
 		return 0;
 
-	prof_buffer = vmalloc(buffer_bytes);
-	if (prof_buffer) {
-		memset(prof_buffer, 0, buffer_bytes);
+	prof_buffer = vzalloc(buffer_bytes);
+	if (prof_buffer)
 		return 0;
-	}
 
 	free_cpumask_var(prof_cpu_mask);
 	return -ENOMEM;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 252b72a..6635fcd 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -42,7 +42,7 @@ int perf_sample_size(u64 sample_type)
 	int i;
 
 	for (i = 0; i < 64; i++) {
-		if (mask & (1UL << i))
+		if (mask & (1ULL << i))
 			size++;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-05-23 22:19   ` Frederic Weisbecker
@ 2011-05-23 22:22     ` Eric Dumazet
  0 siblings, 0 replies; 376+ messages in thread
From: Eric Dumazet @ 2011-05-23 22:22 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Le mardi 24 mai 2011 à 00:19 +0200, Frederic Weisbecker a écrit :
> On Tue, May 24, 2011 at 12:10:48AM +0200, Eric Dumazet wrote:
> > Le lundi 23 mai 2011 à 15:41 +0200, Ingo Molnar a écrit :
> > > Linus,
> > > 
> > > Please pull the latest perf-urgent-for-linus git tree from:
> > > 
> > >    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus
> > > 
> > >  Thanks,
> > > 
> > 
> > Hi Ingo
> > 
> > I just tried latest "perf top" from linux-2.6 tree on my 32bit x86 host.
> > 
> > It outputs endless errors, I dont know if you guys already are aware of
> > this ?
> > 
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> > Can't parse sample, err = -14
> 
> Hi Eric,
> 
> Does that fix the issue?
> 
> diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
> index 252b72a..6635fcd 100644
> --- a/tools/perf/util/event.c
> +++ b/tools/perf/util/event.c
> @@ -42,7 +42,7 @@ int perf_sample_size(u64 sample_type)
>  	int i;
>  
>  	for (i = 0; i < 64; i++) {
> -		if (mask & (1UL << i))
> +		if (mask & (1ULL << i))
>  			size++;
>  	}
>  
> 

It does, thanks Frederic !



^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-05-23 22:10 ` Eric Dumazet
@ 2011-05-23 22:19   ` Frederic Weisbecker
  2011-05-23 22:22     ` Eric Dumazet
  0 siblings, 1 reply; 376+ messages in thread
From: Frederic Weisbecker @ 2011-05-23 22:19 UTC (permalink / raw)
  To: Eric Dumazet
  Cc: Ingo Molnar, Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

On Tue, May 24, 2011 at 12:10:48AM +0200, Eric Dumazet wrote:
> Le lundi 23 mai 2011 à 15:41 +0200, Ingo Molnar a écrit :
> > Linus,
> > 
> > Please pull the latest perf-urgent-for-linus git tree from:
> > 
> >    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus
> > 
> >  Thanks,
> > 
> 
> Hi Ingo
> 
> I just tried latest "perf top" from linux-2.6 tree on my 32bit x86 host.
> 
> It outputs endless errors, I dont know if you guys already are aware of
> this ?
> 
> Can't parse sample, err = -14
> Can't parse sample, err = -14
> Can't parse sample, err = -14
> Can't parse sample, err = -14
> Can't parse sample, err = -14
> Can't parse sample, err = -14
> Can't parse sample, err = -14
> Can't parse sample, err = -14

Hi Eric,

Does that fix the issue?

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 252b72a..6635fcd 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -42,7 +42,7 @@ int perf_sample_size(u64 sample_type)
 	int i;
 
 	for (i = 0; i < 64; i++) {
-		if (mask & (1UL << i))
+		if (mask & (1ULL << i))
 			size++;
 	}
 


^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-05-23 13:41 Ingo Molnar
@ 2011-05-23 22:10 ` Eric Dumazet
  2011-05-23 22:19   ` Frederic Weisbecker
  0 siblings, 1 reply; 376+ messages in thread
From: Eric Dumazet @ 2011-05-23 22:10 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Frédéric Weisbecker,
	Steven Rostedt, Thomas Gleixner, Andrew Morton

Le lundi 23 mai 2011 à 15:41 +0200, Ingo Molnar a écrit :
> Linus,
> 
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus
> 
>  Thanks,
> 

Hi Ingo

I just tried latest "perf top" from linux-2.6 tree on my 32bit x86 host.

It outputs endless errors, I dont know if you guys already are aware of
this ?

Can't parse sample, err = -14
Can't parse sample, err = -14
Can't parse sample, err = -14
Can't parse sample, err = -14
Can't parse sample, err = -14
Can't parse sample, err = -14
Can't parse sample, err = -14
Can't parse sample, err = -14

Thanks



^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-05-23 13:41 Ingo Molnar
  2011-05-23 22:10 ` Eric Dumazet
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2011-05-23 13:41 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (8):
      perf tools: Check we are able to read the event size on mmap
      perf tools: Remove junk code in mmap size handling
      perf tools: Move evlist sample helpers to evlist area
      perf tools: Pre-check sample size before parsing
      perf tools: Robustify dynamic sample content fetch
      perf tools: Propagate event parse error handling
      perf tools: Fix ommitted mmap data update on remap
      perf tools: Fix sample size bit operations

Mandeep Singh Baines (4):
      watchdog: Fix rounding bug in get_sample_period()
      watchdog: Only disable/enable watchdog if neccessary
      watchdog: Disable watchdog when thresh is zero
      watchdog: Change the default timeout and configure nmi watchdog period based on watchdog_thresh


 arch/x86/kernel/apic/hw_nmi.c        |    4 +-
 include/linux/nmi.h                  |    7 ++--
 include/linux/sched.h                |    1 -
 kernel/sysctl.c                      |   12 +++++--
 kernel/watchdog.c                    |   52 +++++++++++++++++++--------------
 tools/perf/builtin-test.c            |    9 +++++-
 tools/perf/builtin-top.c             |    7 ++++-
 tools/perf/util/event.c              |   46 ++++++++++++++++++++----------
 tools/perf/util/event.h              |   12 +++++++-
 tools/perf/util/evlist.c             |   31 ++++++++++++++++++++
 tools/perf/util/evlist.h             |    3 ++
 tools/perf/util/evsel.c              |   32 ++++++++++++++++++++-
 tools/perf/util/header.c             |   31 --------------------
 tools/perf/util/header.h             |    2 -
 tools/perf/util/include/linux/list.h |    2 +
 tools/perf/util/python.c             |   13 ++++++--
 tools/perf/util/session.c            |   50 ++++++++++++++++++++++++--------
 tools/perf/util/session.h            |    2 +
 18 files changed, 216 insertions(+), 100 deletions(-)

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 5260fe9..d5e57db0 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -19,9 +19,9 @@
 #include <linux/delay.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
-u64 hw_nmi_get_sample_period(void)
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
 {
-	return (u64)(cpu_khz) * 1000 * 60;
+	return (u64)(cpu_khz) * 1000 * watchdog_thresh;
 }
 #endif
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index c536f85..2d304ef 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -45,11 +45,12 @@ static inline bool trigger_all_cpu_backtrace(void)
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 int hw_nmi_is_cpu_stuck(struct pt_regs *);
-u64 hw_nmi_get_sample_period(void);
+u64 hw_nmi_get_sample_period(int watchdog_thresh);
 extern int watchdog_enabled;
+extern int watchdog_thresh;
 struct ctl_table;
-extern int proc_dowatchdog_enabled(struct ctl_table *, int ,
-			void __user *, size_t *, loff_t *);
+extern int proc_dowatchdog(struct ctl_table *, int ,
+			   void __user *, size_t *, loff_t *);
 #endif
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 12211e1..d8b2d0b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -315,7 +315,6 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
 				  void __user *buffer,
 				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
-extern int softlockup_thresh;
 void lockup_detector_init(void);
 #else
 static inline void touch_softlockup_watchdog(void)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c0bb324..3dd0c46 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -730,14 +730,16 @@ static struct ctl_table kern_table[] = {
 		.data           = &watchdog_enabled,
 		.maxlen         = sizeof (int),
 		.mode           = 0644,
-		.proc_handler   = proc_dowatchdog_enabled,
+		.proc_handler   = proc_dowatchdog,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 	{
 		.procname	= "watchdog_thresh",
-		.data		= &softlockup_thresh,
+		.data		= &watchdog_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dowatchdog_thresh,
+		.proc_handler	= proc_dowatchdog,
 		.extra1		= &neg_one,
 		.extra2		= &sixty,
 	},
@@ -755,7 +757,9 @@ static struct ctl_table kern_table[] = {
 		.data           = &watchdog_enabled,
 		.maxlen         = sizeof (int),
 		.mode           = 0644,
-		.proc_handler   = proc_dowatchdog_enabled,
+		.proc_handler   = proc_dowatchdog,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 14733d4..6e63097 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -28,7 +28,7 @@
 #include <linux/perf_event.h>
 
 int watchdog_enabled = 1;
-int __read_mostly softlockup_thresh = 60;
+int __read_mostly watchdog_thresh = 10;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
 static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
@@ -91,6 +91,17 @@ static int __init nosoftlockup_setup(char *str)
 __setup("nosoftlockup", nosoftlockup_setup);
 /*  */
 
+/*
+ * Hard-lockup warnings should be triggered after just a few seconds. Soft-
+ * lockups can have false positives under extreme conditions. So we generally
+ * want a higher threshold for soft lockups than for hard lockups. So we couple
+ * the thresholds with a factor: we make the soft threshold twice the amount of
+ * time the hard threshold is.
+ */
+static int get_softlockup_thresh()
+{
+	return watchdog_thresh * 2;
+}
 
 /*
  * Returns seconds, approximately.  We don't need nanosecond
@@ -105,12 +116,12 @@ static unsigned long get_timestamp(int this_cpu)
 static unsigned long get_sample_period(void)
 {
 	/*
-	 * convert softlockup_thresh from seconds to ns
+	 * convert watchdog_thresh from seconds to ns
 	 * the divide by 5 is to give hrtimer 5 chances to
 	 * increment before the hardlockup detector generates
 	 * a warning
 	 */
-	return softlockup_thresh / 5 * NSEC_PER_SEC;
+	return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
 }
 
 /* Commands for resetting the watchdog */
@@ -182,7 +193,7 @@ static int is_softlockup(unsigned long touch_ts)
 	unsigned long now = get_timestamp(smp_processor_id());
 
 	/* Warn about unreasonable delays: */
-	if (time_after(now, touch_ts + softlockup_thresh))
+	if (time_after(now, touch_ts + get_softlockup_thresh()))
 		return now - touch_ts;
 
 	return 0;
@@ -359,7 +370,7 @@ static int watchdog_nmi_enable(int cpu)
 
 	/* Try to register using hardware perf events */
 	wd_attr = &wd_hw_attr;
-	wd_attr->sample_period = hw_nmi_get_sample_period();
+	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
 	if (!IS_ERR(event)) {
 		printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
@@ -501,28 +512,25 @@ static void watchdog_disable_all_cpus(void)
 /* sysctl functions */
 #ifdef CONFIG_SYSCTL
 /*
- * proc handler for /proc/sys/kernel/nmi_watchdog
+ * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh
  */
 
-int proc_dowatchdog_enabled(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *length, loff_t *ppos)
+int proc_dowatchdog(struct ctl_table *table, int write,
+		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	proc_dointvec(table, write, buffer, length, ppos);
+	int ret;
 
-	if (write) {
-		if (watchdog_enabled)
-			watchdog_enable_all_cpus();
-		else
-			watchdog_disable_all_cpus();
-	}
-	return 0;
-}
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret || !write)
+		goto out;
 
-int proc_dowatchdog_thresh(struct ctl_table *table, int write,
-			     void __user *buffer,
-			     size_t *lenp, loff_t *ppos)
-{
-	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (watchdog_enabled && watchdog_thresh)
+		watchdog_enable_all_cpus();
+	else
+		watchdog_disable_all_cpus();
+
+out:
+	return ret;
 }
 #endif /* CONFIG_SYSCTL */
 
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 2f9a337..b671862 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -474,6 +474,7 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
+	int sample_size = perf_sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
@@ -558,7 +559,13 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		perf_event__parse_sample(event, attr.sample_type, false, &sample);
+		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
+					       false, &sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto out_munmap;
+		}
+
 		evsel = perf_evlist__id2evsel(evlist, sample.id);
 		if (evsel == NULL) {
 			pr_debug("event with id %" PRIu64
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ebfc7cf..2d7934e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -805,9 +805,14 @@ static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
 	struct perf_sample sample;
 	union perf_event *event;
+	int ret;
 
 	while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
-		perf_session__parse_sample(self, event, &sample);
+		ret = perf_session__parse_sample(self, event, &sample);
+		if (ret) {
+			pr_err("Can't parse sample, err = %d\n", ret);
+			continue;
+		}
 
 		if (event->header.type == PERF_RECORD_SAMPLE)
 			perf_event__process_sample(event, &sample, self);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1023f67..252b72a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -9,21 +9,21 @@
 #include "thread_map.h"
 
 static const char *perf_event__names[] = {
-	[0]			 = "TOTAL",
-	[PERF_RECORD_MMAP]	 = "MMAP",
-	[PERF_RECORD_LOST]	 = "LOST",
-	[PERF_RECORD_COMM]	 = "COMM",
-	[PERF_RECORD_EXIT]	 = "EXIT",
-	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
-	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-	[PERF_RECORD_FORK]	 = "FORK",
-	[PERF_RECORD_READ]	 = "READ",
-	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
-	[PERF_RECORD_HEADER_ATTR]	 = "ATTR",
-	[PERF_RECORD_HEADER_EVENT_TYPE]	 = "EVENT_TYPE",
-	[PERF_RECORD_HEADER_TRACING_DATA]	 = "TRACING_DATA",
-	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
-	[PERF_RECORD_FINISHED_ROUND]	 = "FINISHED_ROUND",
+	[0]					= "TOTAL",
+	[PERF_RECORD_MMAP]			= "MMAP",
+	[PERF_RECORD_LOST]			= "LOST",
+	[PERF_RECORD_COMM]			= "COMM",
+	[PERF_RECORD_EXIT]			= "EXIT",
+	[PERF_RECORD_THROTTLE]			= "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE]		= "UNTHROTTLE",
+	[PERF_RECORD_FORK]			= "FORK",
+	[PERF_RECORD_READ]			= "READ",
+	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
+	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
+	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
+	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
+	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -35,6 +35,22 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
+int perf_sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1UL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
 static struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 9c35170..c083328 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -56,6 +56,13 @@ struct read_event {
 	u64 id;
 };
 
+
+#define PERF_SAMPLE_MASK				\
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
+	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];
@@ -75,6 +82,8 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 };
 
+int perf_sample_size(u64 sample_type);
+
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
@@ -178,6 +187,7 @@ int perf_event__preprocess_sample(const union perf_event *self,
 const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     bool sample_id_all, struct perf_sample *sample);
+			     int sample_size, bool sample_id_all,
+			     struct perf_sample *sample);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 23eb22b..50aa348 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -459,3 +459,34 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos;
+	u64 type = 0;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (!type)
+			type = pos->attr.sample_type;
+		else if (type != pos->attr.sample_type)
+			die("non matching sample_type");
+	}
+
+	return type;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+	bool value = false, first = true;
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (first) {
+			value = pos->attr.sample_id_all;
+			first = false;
+		} else if (value != pos->attr.sample_id_all)
+			die("non matching sample_id_all");
+	}
+
+	return value;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7109d7a..0a1ef1f 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -66,4 +66,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
+u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d6fd59b..ee0fe0d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -303,8 +303,20 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
 	return 0;
 }
 
+static bool sample_overlap(const union perf_event *event,
+			   const void *offset, u64 size)
+{
+	const void *base = event;
+
+	if (offset + size > base + event->header.size)
+		return true;
+
+	return false;
+}
+
 int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     bool sample_id_all, struct perf_sample *data)
+			     int sample_size, bool sample_id_all,
+			     struct perf_sample *data)
 {
 	const u64 *array;
 
@@ -319,6 +331,9 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 
 	array = event->sample.array;
 
+	if (sample_size + sizeof(event->header) > event->header.size)
+		return -EFAULT;
+
 	if (type & PERF_SAMPLE_IP) {
 		data->ip = event->ip.ip;
 		array++;
@@ -369,14 +384,29 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CALLCHAIN) {
+		if (sample_overlap(event, array, sizeof(data->callchain->nr)))
+			return -EFAULT;
+
 		data->callchain = (struct ip_callchain *)array;
+
+		if (sample_overlap(event, array, data->callchain->nr))
+			return -EFAULT;
+
 		array += 1 + data->callchain->nr;
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
 		u32 *p = (u32 *)array;
+
+		if (sample_overlap(event, array, sizeof(u32)))
+			return -EFAULT;
+
 		data->raw_size = *p;
 		p++;
+
+		if (sample_overlap(event, p, data->raw_size))
+			return -EFAULT;
+
 		data->raw_data = p;
 	}
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 93862a8..0717beb 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -934,37 +934,6 @@ out_delete_evlist:
 	return -ENOMEM;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
-{
-	struct perf_evsel *pos;
-	u64 type = 0;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (!type)
-			type = pos->attr.sample_type;
-		else if (type != pos->attr.sample_type)
-			die("non matching sample_type");
-	}
-
-	return type;
-}
-
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
-{
-	bool value = false, first = true;
-	struct perf_evsel *pos;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (first) {
-			value = pos->attr.sample_id_all;
-			first = false;
-		} else if (value != pos->attr.sample_id_all)
-			die("non matching sample_id_all");
-	}
-
-	return value;
-}
-
 int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 				perf_event__handler_t process,
 				struct perf_session *session)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 456661d..1886256 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -64,8 +64,6 @@ int perf_header__write_pipe(int fd);
 int perf_header__push_event(u64 id, const char *name);
 char *perf_header__find_event(u64 id);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
 void perf_header__set_feat(struct perf_header *header, int feat);
 void perf_header__clear_feat(struct perf_header *header, int feat);
 bool perf_header__has_feat(const struct perf_header *header, int feat);
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 356c7e4..ed33609 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,4 +1,6 @@
 #include <linux/kernel.h>
+#include <linux/prefetch.h>
+
 #include "../../../../include/linux/list.h"
 
 #ifndef PERF_LIST_H
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index b5c7d81..69436b3 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -675,6 +675,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = {"sample_id_all", NULL, NULL};
+	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
 					 &cpu, &sample_id_all))
@@ -690,11 +691,17 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 			return PyErr_NoMemory();
 
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
-		perf_event__parse_sample(event, first->attr.sample_type, sample_id_all,
-					 &pevent->sample);
+		err = perf_event__parse_sample(event, first->attr.sample_type,
+					       perf_sample_size(first->attr.sample_type),
+					       sample_id_all, &pevent->sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto end;
+		}
+
 		return pyevent;
 	}
-
+end:
 	Py_INCREF(Py_None);
 	return Py_None;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fff6674..64500fc 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -97,6 +97,7 @@ out:
 void perf_session__update_sample_type(struct perf_session *self)
 {
 	self->sample_type = perf_evlist__sample_type(self->evlist);
+	self->sample_size = perf_sample_size(self->sample_type);
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	perf_session__id_header_size(self);
 }
@@ -479,6 +480,7 @@ static void flush_sample_queue(struct perf_session *s,
 	struct perf_sample sample;
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
+	int ret;
 
 	if (!ops->ordered_samples || !limit)
 		return;
@@ -487,9 +489,12 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		perf_session__parse_sample(s, iter->event, &sample);
-		perf_session_deliver_event(s, iter->event, &sample, ops,
-					   iter->file_offset);
+		ret = perf_session__parse_sample(s, iter->event, &sample);
+		if (ret)
+			pr_err("Can't parse sample, err = %d\n", ret);
+		else
+			perf_session_deliver_event(s, iter->event, &sample, ops,
+						   iter->file_offset);
 
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
@@ -805,7 +810,9 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	perf_session__parse_sample(session, event, &sample);
+	ret = perf_session__parse_sample(session, event, &sample);
+	if (ret)
+		return ret;
 
 	/* Preprocess sample records - precheck callchains */
 	if (perf_session__preprocess_sample(session, event, &sample))
@@ -953,6 +960,30 @@ out_err:
 	return err;
 }
 
+static union perf_event *
+fetch_mmaped_event(struct perf_session *session,
+		   u64 head, size_t mmap_size, char *buf)
+{
+	union perf_event *event;
+
+	/*
+	 * Ensure we have enough space remaining to read
+	 * the size of the event in the headers.
+	 */
+	if (head + sizeof(event->header) > mmap_size)
+		return NULL;
+
+	event = (union perf_event *)(buf + head);
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (head + event->header.size > mmap_size)
+		return NULL;
+
+	return event;
+}
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_event_ops *ops)
@@ -1007,15 +1038,8 @@ remap:
 	file_pos = file_offset + head;
 
 more:
-	event = (union perf_event *)(buf + head);
-
-	if (session->header.needs_swap)
-		perf_event_header__bswap(&event->header);
-	size = event->header.size;
-	if (size == 0)
-		size = 8;
-
-	if (head + event->header.size > mmap_size) {
+	event = fetch_mmaped_event(session, head, mmap_size, buf);
+	if (!event) {
 		if (mmaps[map_idx]) {
 			munmap(mmaps[map_idx], mmap_size);
 			mmaps[map_idx] = NULL;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 8daaa2d..66d4e14 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -43,6 +43,7 @@ struct perf_session {
 	 */
 	struct hists		hists;
 	u64			sample_type;
+	int			sample_size;
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
@@ -159,6 +160,7 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 					     struct perf_sample *sample)
 {
 	return perf_event__parse_sample(event, session->sample_type,
+					session->sample_size,
 					session->sample_id_all, sample);
 }
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-05-20 17:18 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-05-20 17:18 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Steven Rostedt, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Frédéric Weisbecker,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-urgent-for-linus

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      core_kernel_data(): Fix architectures that do not define _sdata

Steven Rostedt (1):
      extable, core_kernel_data(): Make sure all archs define _sdata


 arch/alpha/kernel/vmlinux.lds.S   |    1 +
 arch/m32r/kernel/vmlinux.lds.S    |    1 +
 arch/m68k/kernel/vmlinux-std.lds  |    2 ++
 arch/m68k/kernel/vmlinux-sun3.lds |    1 +
 arch/mips/kernel/vmlinux.lds.S    |    1 +
 arch/parisc/kernel/vmlinux.lds.S  |    3 +++
 kernel/extable.c                  |   10 ++++++++++
 7 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 433be2a..3d890a9 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -46,6 +46,7 @@ SECTIONS
 	__init_end = .;
 	/* Freed after init ends here */
 
+	_sdata = .;	/* Start of rw data section */
 	_data = .;
 	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index c194d64..cf95aec 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -44,6 +44,7 @@ SECTIONS
   EXCEPTION_TABLE(16)
   NOTES
 
+  _sdata = .;			/* Start of data section */
   RODATA
   RW_DATA_SECTION(32, PAGE_SIZE, THREAD_SIZE)
   _edata = .;			/* End of data section */
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 878be5f..d099359 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -25,6 +25,8 @@ SECTIONS
 
   EXCEPTION_TABLE(16)
 
+  _sdata = .;			/* Start of data section */
+
   RODATA
 
   RW_DATA_SECTION(16, PAGE_SIZE, THREAD_SIZE)
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index 1ad6b7a..8080469 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -25,6 +25,7 @@ SECTIONS
   _etext = .;			/* End of text section */
 
   EXCEPTION_TABLE(16) :data
+  _sdata = .;			/* Start of rw data section */
   RW_DATA_SECTION(16, PAGE_SIZE, THREAD_SIZE) :data
   /* End of data goes *here* so that freeing init code works properly. */
   _edata = .;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index cd2ca54..01af387 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -65,6 +65,7 @@ SECTIONS
 	NOTES :text :note
 	.dummy : { *(.dummy) } :text
 
+	_sdata = .;			/* Start of data section */
 	RODATA
 
 	/* writeable */
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 8f1e4ef..2d9a5c7 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -69,6 +69,9 @@ SECTIONS
 	/* End of text section */
 	_etext = .;
 
+	/* Start of data section */
+	_sdata = .;
+
 	RODATA
 
 	/* writeable */
diff --git a/kernel/extable.c b/kernel/extable.c
index c2d625f..5339705 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -72,6 +72,16 @@ int core_kernel_text(unsigned long addr)
 	return 0;
 }
 
+/**
+ * core_kernel_data - tell if addr points to kernel data
+ * @addr: address to test
+ *
+ * Returns true if @addr passed in is from the core kernel data
+ * section.
+ *
+ * Note: On some archs it may return true for core RODATA, and false
+ *  for others. But will always be true for core RW data.
+ */
 int core_kernel_data(unsigned long addr)
 {
 	if (addr >= (unsigned long)_sdata &&

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-05-17 22:07 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-05-17 22:07 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf tools: Honour the cpu list parameter when also monitoring a thread list
      perf evlist: Fix per thread mmap setup

Jiri Olsa (1):
      kprobes, x86: Disable irqs during optimized callback


 arch/x86/kernel/kprobes.c   |    5 +-
 tools/perf/builtin-record.c |    2 +-
 tools/perf/builtin-test.c   |    2 +-
 tools/perf/builtin-top.c    |    8 +-
 tools/perf/util/evlist.c    |  153 ++++++++++++++++++++++++++++++-------------
 tools/perf/util/evlist.h    |    3 +-
 tools/perf/util/python.c    |    2 +-
 7 files changed, 119 insertions(+), 56 deletions(-)

diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index c969fd9..f1a6244 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1183,12 +1183,13 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
 					 struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long flags;
 
 	/* This is possible if op is under delayed unoptimizing */
 	if (kprobe_disabled(&op->kp))
 		return;
 
-	preempt_disable();
+	local_irq_save(flags);
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(&op->kp);
 	} else {
@@ -1207,7 +1208,7 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
 		opt_pre_handler(&op->kp, regs);
 		__this_cpu_write(current_kprobe, NULL);
 	}
-	preempt_enable_no_resched();
+	local_irq_restore(flags);
 }
 
 static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4165382..0974f95 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -427,7 +427,7 @@ static void mmap_read_all(void)
 {
 	int i;
 
-	for (i = 0; i < evsel_list->cpus->nr; i++) {
+	for (i = 0; i < evsel_list->nr_mmaps; i++) {
 		if (evsel_list->mmap[i].base)
 			mmap_read(&evsel_list->mmap[i]);
 	}
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 11e3c84..2f9a337 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -549,7 +549,7 @@ static int test__basic_mmap(void)
 			++foo;
 		}
 
-	while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) {
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7e3d6e3..ebfc7cf 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -801,12 +801,12 @@ static void perf_event__process_sample(const union perf_event *event,
 	}
 }
 
-static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu)
+static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
 	struct perf_sample sample;
 	union perf_event *event;
 
-	while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) {
+	while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
 		perf_session__parse_sample(self, event, &sample);
 
 		if (event->header.type == PERF_RECORD_SAMPLE)
@@ -820,8 +820,8 @@ static void perf_session__mmap_read(struct perf_session *self)
 {
 	int i;
 
-	for (i = 0; i < top.evlist->cpus->nr; i++)
-		perf_session__mmap_read_cpu(self, i);
+	for (i = 0; i < top.evlist->nr_mmaps; i++)
+		perf_session__mmap_read_idx(self, i);
 }
 
 static void start_counters(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 45da8d1..23eb22b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -166,11 +166,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	/* XXX Move this to perf.c, making it generally available */
 	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-	struct perf_mmap *md = &evlist->mmap[cpu];
+	struct perf_mmap *md = &evlist->mmap[idx];
 	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
@@ -235,31 +235,37 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
-	int cpu;
+	int i;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		if (evlist->mmap[i].base != NULL) {
+			munmap(evlist->mmap[i].base, evlist->mmap_len);
+			evlist->mmap[i].base = NULL;
 		}
 	}
+
+	free(evlist->mmap);
+	evlist->mmap = NULL;
 }
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
-	evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+	evlist->nr_mmaps = evlist->cpus->nr;
+	if (evlist->cpus->map[0] == -1)
+		evlist->nr_mmaps = evlist->threads->nr;
+	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
 static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
-			       int cpu, int prot, int mask, int fd)
+			       int idx, int prot, int mask, int fd)
 {
-	evlist->mmap[cpu].prev = 0;
-	evlist->mmap[cpu].mask = mask;
-	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+	evlist->mmap[idx].prev = 0;
+	evlist->mmap[idx].mask = mask;
+	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[cpu].base == MAP_FAILED) {
-		if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit)
+	if (evlist->mmap[idx].base == MAP_FAILED) {
+		if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
 			ui__warning("Inherit is not allowed on per-task "
 				    "events using mmap.\n");
 		return -1;
@@ -269,6 +275,86 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *ev
 	return 0;
 }
 
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+{
+	struct perf_evsel *evsel;
+	int cpu, thread;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		int output = -1;
+
+		for (thread = 0; thread < evlist->threads->nr; thread++) {
+			list_for_each_entry(evsel, &evlist->entries, node) {
+				int fd = FD(evsel, cpu, thread);
+
+				if (output == -1) {
+					output = fd;
+					if (__perf_evlist__mmap(evlist, evsel, cpu,
+								prot, mask, output) < 0)
+						goto out_unmap;
+				} else {
+					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+						goto out_unmap;
+				}
+
+				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+					goto out_unmap;
+			}
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		if (evlist->mmap[cpu].base != NULL) {
+			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+			evlist->mmap[cpu].base = NULL;
+		}
+	}
+	return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+{
+	struct perf_evsel *evsel;
+	int thread;
+
+	for (thread = 0; thread < evlist->threads->nr; thread++) {
+		int output = -1;
+
+		list_for_each_entry(evsel, &evlist->entries, node) {
+			int fd = FD(evsel, 0, thread);
+
+			if (output == -1) {
+				output = fd;
+				if (__perf_evlist__mmap(evlist, evsel, thread,
+							prot, mask, output) < 0)
+					goto out_unmap;
+			} else {
+				if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+					goto out_unmap;
+			}
+
+			if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+			    perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
+				goto out_unmap;
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (thread = 0; thread < evlist->threads->nr; thread++) {
+		if (evlist->mmap[thread].base != NULL) {
+			munmap(evlist->mmap[thread].base, evlist->mmap_len);
+			evlist->mmap[thread].base = NULL;
+		}
+	}
+	return -1;
+}
+
 /** perf_evlist__mmap - Create per cpu maps to receive events
  *
  * @evlist - list of events
@@ -287,11 +373,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *ev
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 {
 	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-	int mask = pages * page_size - 1, cpu;
-	struct perf_evsel *first_evsel, *evsel;
+	int mask = pages * page_size - 1;
+	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
 
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
@@ -301,43 +387,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 
 	evlist->overwrite = overwrite;
 	evlist->mmap_len = (pages + 1) * page_size;
-	first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
 		    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
 			return -ENOMEM;
-
-		for (cpu = 0; cpu < cpus->nr; cpu++) {
-			for (thread = 0; thread < threads->nr; thread++) {
-				int fd = FD(evsel, cpu, thread);
-
-				if (evsel->idx || thread) {
-					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
-						  FD(first_evsel, cpu, 0)) != 0)
-						goto out_unmap;
-				} else if (__perf_evlist__mmap(evlist, evsel, cpu,
-							       prot, mask, fd) < 0)
-					goto out_unmap;
-
-				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-					goto out_unmap;
-			}
-		}
 	}
 
-	return 0;
+	if (evlist->cpus->map[0] == -1)
+		return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
-out_unmap:
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
-		}
-	}
-	return -1;
+	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
@@ -348,7 +409,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target_tid != -1)
+	if (cpu_list == NULL && target_tid != -1)
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(cpu_list);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8b1cb7a..7109d7a 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -17,6 +17,7 @@ struct perf_evlist {
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
 	int		 nr_fds;
+	int		 nr_mmaps;
 	int		 mmap_len;
 	bool		 overwrite;
 	union perf_event event_copy;
@@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index f5e3845..99c7226 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -680,7 +680,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 					 &cpu, &sample_id_all))
 		return NULL;
 
-	event = perf_evlist__read_on_cpu(evlist, cpu);
+	event = perf_evlist__mmap_read(evlist, cpu);
 	if (event != NULL) {
 		struct perf_evsel *first;
 		PyObject *pyevent = pyrf_event__new(event);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-05-07 18:20 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-05-07 18:20 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

This is larger than usual:

  - the breakpoints/ptrace fix is a bit late but fixes a crash

  - the cache-events regression fix is large due to the definitions added
    (which also document the PMU features) but is otherwise low risk.

Thanks,

	Ingo

------------------>
Frederic Weisbecker (6):
      ptrace: Prepare to fix racy accesses on task breakpoints
      x86, hw_breakpoints: Fix racy access to ptrace breakpoints
      powerpc, hw_breakpoints: Fix racy access to ptrace breakpoints
      arm, hw_breakpoints: Fix racy access to ptrace breakpoints
      sh, hw_breakpoints: Fix racy access to ptrace breakpoints
      hw_breakpoints, powerpc: Fix CONFIG_HAVE_HW_BREAKPOINT off-case in ptrace_set_debugreg()

Lin Ming (1):
      perf tools: Makefile: Use gcc to determine ARCH

Peter Zijlstra (1):
      perf events, x86: Fix Intel Nehalem and Westmere last level cache event definitions


 arch/arm/kernel/ptrace.c               |    8 +++
 arch/powerpc/kernel/ptrace.c           |   12 ++++-
 arch/sh/kernel/ptrace_32.c             |    4 ++
 arch/x86/kernel/cpu/perf_event_intel.c |   87 +++++++++++++++++++-------------
 arch/x86/kernel/ptrace.c               |   36 ++++++++++----
 include/linux/ptrace.h                 |   13 ++++-
 include/linux/sched.h                  |    3 +
 kernel/exit.c                          |    2 +-
 kernel/ptrace.c                        |   17 ++++++
 tools/perf/Makefile                    |   16 ++++--
 10 files changed, 144 insertions(+), 54 deletions(-)

diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 2bf27f3..8182f45 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -767,12 +767,20 @@ long arch_ptrace(struct task_struct *child, long request,
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		case PTRACE_GETHBPREGS:
+			if (ptrace_get_breakpoints(child) < 0)
+				return -ESRCH;
+
 			ret = ptrace_gethbpregs(child, addr,
 						(unsigned long __user *)data);
+			ptrace_put_breakpoints(child);
 			break;
 		case PTRACE_SETHBPREGS:
+			if (ptrace_get_breakpoints(child) < 0)
+				return -ESRCH;
+
 			ret = ptrace_sethbpregs(child, addr,
 						(unsigned long __user *)data);
+			ptrace_put_breakpoints(child);
 			break;
 #endif
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 55613e3..a6ae1cf 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -933,12 +933,16 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	if (data && !(data & DABR_TRANSLATION))
 		return -EIO;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
+	if (ptrace_get_breakpoints(task) < 0)
+		return -ESRCH;
+
 	bp = thread->ptrace_bps[0];
 	if ((!data) || !(data & (DABR_DATA_WRITE | DABR_DATA_READ))) {
 		if (bp) {
 			unregister_hw_breakpoint(bp);
 			thread->ptrace_bps[0] = NULL;
 		}
+		ptrace_put_breakpoints(task);
 		return 0;
 	}
 	if (bp) {
@@ -948,9 +952,12 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 					(DABR_DATA_WRITE | DABR_DATA_READ),
 							&attr.bp_type);
 		ret =  modify_user_hw_breakpoint(bp, &attr);
-		if (ret)
+		if (ret) {
+			ptrace_put_breakpoints(task);
 			return ret;
+		}
 		thread->ptrace_bps[0] = bp;
+		ptrace_put_breakpoints(task);
 		thread->dabr = data;
 		return 0;
 	}
@@ -965,9 +972,12 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 							ptrace_triggered, task);
 	if (IS_ERR(bp)) {
 		thread->ptrace_bps[0] = NULL;
+		ptrace_put_breakpoints(task);
 		return PTR_ERR(bp);
 	}
 
+	ptrace_put_breakpoints(task);
+
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
 	/* Move contents to the DABR register */
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 2130ca6..3d7b209 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -117,7 +117,11 @@ void user_enable_single_step(struct task_struct *child)
 
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 
+	if (ptrace_get_breakpoints(child) < 0)
+		return;
+
 	set_single_step(child, pc);
+	ptrace_put_breakpoints(child);
 }
 
 void user_disable_single_step(struct task_struct *child)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e61539b..447a28d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -184,26 +184,23 @@ static __initconst const u64 snb_hw_cache_event_ids
 	},
  },
  [ C(LL  ) ] = {
-	/*
-	 * TBD: Need Off-core Response Performance Monitoring support
-	 */
 	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_WRITE) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -285,26 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	/*
 	 * Use RFO, not WRITEBACK, because a write miss would typically occur
 	 * on RFO.
 	 */
 	[ C(OP_WRITE) ] = {
-		/* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
-		[ C(RESULT_ACCESS) ] = 0x01bb,
-		/* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
 		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -352,16 +349,36 @@ static __initconst const u64 westmere_hw_cache_event_ids
 };
 
 /*
- * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
  */
 
-#define DMND_DATA_RD     (1 << 0)
-#define DMND_RFO         (1 << 1)
-#define DMND_WB          (1 << 3)
-#define PF_DATA_RD       (1 << 4)
-#define PF_DATA_RFO      (1 << 5)
-#define RESP_UNCORE_HIT  (1 << 8)
-#define RESP_MISS        (0xf600) /* non uncore hit */
+#define NHM_DMND_DATA_RD	(1 << 0)
+#define NHM_DMND_RFO		(1 << 1)
+#define NHM_DMND_IFETCH		(1 << 2)
+#define NHM_DMND_WB		(1 << 3)
+#define NHM_PF_DATA_RD		(1 << 4)
+#define NHM_PF_DATA_RFO		(1 << 5)
+#define NHM_PF_IFETCH		(1 << 6)
+#define NHM_OFFCORE_OTHER	(1 << 7)
+#define NHM_UNCORE_HIT		(1 << 8)
+#define NHM_OTHER_CORE_HIT_SNP	(1 << 9)
+#define NHM_OTHER_CORE_HITM	(1 << 10)
+        			/* reserved */
+#define NHM_REMOTE_CACHE_FWD	(1 << 12)
+#define NHM_REMOTE_DRAM		(1 << 13)
+#define NHM_LOCAL_DRAM		(1 << 14)
+#define NHM_NON_DRAM		(1 << 15)
+
+#define NHM_ALL_DRAM		(NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+
+#define NHM_DMND_READ		(NHM_DMND_DATA_RD)
+#define NHM_DMND_WRITE		(NHM_DMND_RFO|NHM_DMND_WB)
+#define NHM_DMND_PREFETCH	(NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
+
+#define NHM_L3_HIT	(NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
+#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_ACCESS	(NHM_L3_HIT|NHM_L3_MISS)
 
 static __initconst const u64 nehalem_hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -370,16 +387,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
 {
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = DMND_DATA_RD|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_L3_MISS,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = DMND_RFO|DMND_WB|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_L3_MISS,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
 	},
  }
 };
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 45892dc..f65e5b5 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -608,6 +608,9 @@ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
 	unsigned len, type;
 	struct perf_event *bp;
 
+	if (ptrace_get_breakpoints(tsk) < 0)
+		return -ESRCH;
+
 	data &= ~DR_CONTROL_RESERVED;
 	old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
 restore:
@@ -655,6 +658,9 @@ restore:
 		}
 		goto restore;
 	}
+
+	ptrace_put_breakpoints(tsk);
+
 	return ((orig_ret < 0) ? orig_ret : rc);
 }
 
@@ -668,10 +674,17 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 
 	if (n < HBP_NUM) {
 		struct perf_event *bp;
+
+		if (ptrace_get_breakpoints(tsk) < 0)
+			return -ESRCH;
+
 		bp = thread->ptrace_bps[n];
 		if (!bp)
-			return 0;
-		val = bp->hw.info.address;
+			val = 0;
+		else
+			val = bp->hw.info.address;
+
+		ptrace_put_breakpoints(tsk);
 	} else if (n == 6) {
 		val = thread->debugreg6;
 	 } else if (n == 7) {
@@ -686,6 +699,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 	struct perf_event *bp;
 	struct thread_struct *t = &tsk->thread;
 	struct perf_event_attr attr;
+	int err = 0;
+
+	if (ptrace_get_breakpoints(tsk) < 0)
+		return -ESRCH;
 
 	if (!t->ptrace_bps[nr]) {
 		ptrace_breakpoint_init(&attr);
@@ -709,24 +726,23 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 		 * writing for the user. And anyway this is the previous
 		 * behaviour.
 		 */
-		if (IS_ERR(bp))
-			return PTR_ERR(bp);
+		if (IS_ERR(bp)) {
+			err = PTR_ERR(bp);
+			goto put;
+		}
 
 		t->ptrace_bps[nr] = bp;
 	} else {
-		int err;
-
 		bp = t->ptrace_bps[nr];
 
 		attr = bp->attr;
 		attr.bp_addr = addr;
 		err = modify_user_hw_breakpoint(bp, &attr);
-		if (err)
-			return err;
 	}
 
-
-	return 0;
+put:
+	ptrace_put_breakpoints(tsk);
+	return err;
 }
 
 /*
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index a1147e5..9178d5c 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -189,6 +189,10 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 		child->ptrace = current->ptrace;
 		__ptrace_link(child, current->parent);
 	}
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	atomic_set(&child->ptrace_bp_refcnt, 1);
+#endif
 }
 
 /**
@@ -350,6 +354,13 @@ extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
 
-#endif
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+extern int ptrace_get_breakpoints(struct task_struct *tsk);
+extern void ptrace_put_breakpoints(struct task_struct *tsk);
+#else
+static inline void ptrace_put_breakpoints(struct task_struct *tsk) { }
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+#endif /* __KERNEL */
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 18d63ce..781abd1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1537,6 +1537,9 @@ struct task_struct {
 		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
 	} memcg_batch;
 #endif
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	atomic_t ptrace_bp_refcnt;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
diff --git a/kernel/exit.c b/kernel/exit.c
index f5d2f63..8dd8741 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1016,7 +1016,7 @@ NORET_TYPE void do_exit(long code)
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
-	flush_ptrace_hw_breakpoint(tsk);
+	ptrace_put_breakpoints(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0fc1eed..dc7ab65 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
 
 
 /*
@@ -879,3 +880,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	return ret;
 }
 #endif	/* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+	if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+		return 0;
+
+	return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+	if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+		flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 207dee5..0c54256 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,15 +35,21 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
 				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
 				  -e s/sh[234].*/sh/ )
 
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
 # Additional ARCH settings for x86
 ifeq ($(ARCH),i386)
         ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
-	RAW_ARCH := x86_64
-        ARCH := x86
-	ARCH_CFLAGS := -DARCH_X86_64
-	ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+	ARCH := x86
+	IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1)
+	ifeq (${IS_X86_64}, 1)
+		RAW_ARCH := x86_64
+		ARCH_CFLAGS := -DARCH_X86_64
+		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+	endif
 endif
 
 #
@@ -119,8 +125,6 @@ lib = lib
 
 export prefix bindir sharedir sysconfdir
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
 RM = rm -f
 MKDIR = mkdir
 FIND = find

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-04-29 18:17 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-04-29 18:17 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Don Zickus (1):
      perf, x86, nmi: Move LVT un-masking into irq handlers

Ingo Molnar (1):
      perf events, x86: Work around the Nehalem AAJ80 erratum

Michal Simek (1):
      ftrace: Build without frame pointers on Microblaze

Peter Zijlstra (1):
      perf, x86: Fix BTS condition


 arch/x86/kernel/cpu/perf_event.c       |   16 ++++++++++++----
 arch/x86/kernel/cpu/perf_event_intel.c |   29 +++++++++++++++++++++++++++--
 arch/x86/kernel/cpu/perf_event_p4.c    |   17 +++++++++++++----
 kernel/trace/Kconfig                   |    2 +-
 4 files changed, 53 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 632e5dc..e638689 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -613,8 +613,8 @@ static int x86_setup_perfctr(struct perf_event *event)
 	/*
 	 * Branch tracing:
 	 */
-	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-	    (hwc->sample_period == 1)) {
+	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
+	    !attr->freq && hwc->sample_period == 1) {
 		/* BTS is not supported by this architecture. */
 		if (!x86_pmu.bts_active)
 			return -EOPNOTSUPP;
@@ -1288,6 +1288,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
+	/*
+	 * Some chipsets need to unmask the LVTPC in a particular spot
+	 * inside the nmi handler.  As a result, the unmasking was pushed
+	 * into all the nmi handlers.
+	 *
+	 * This generic handler doesn't seem to have any issues where the
+	 * unmasking occurs so it was left at the top.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask)) {
 			/*
@@ -1374,8 +1384,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 		return NOTIFY_DONE;
 	}
 
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-
 	handled = x86_pmu.handle_irq(args->regs);
 	if (!handled)
 		return NOTIFY_DONE;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 43fa20b..e61539b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -25,7 +25,7 @@ struct intel_percore {
 /*
  * Intel PerfMon, used on Core and later.
  */
-static const u64 intel_perfmon_event_map[] =
+static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
 {
   [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
   [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
@@ -933,6 +933,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
+	/*
+	 * Some chipsets need to unmask the LVTPC in a particular spot
+	 * inside the nmi handler.  As a result, the unmasking was pushed
+	 * into all the nmi handlers.
+	 *
+	 * This handler doesn't seem to have any issues with the unmasking
+	 * so it was left at the top.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
@@ -998,6 +1008,9 @@ intel_bts_constraints(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
 
+	if (event->attr.freq)
+		return NULL;
+
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
@@ -1305,7 +1318,7 @@ static void intel_clovertown_quirks(void)
 	 * AJ106 could possibly be worked around by not allowing LBR
 	 *       usage from PEBS, including the fixup.
 	 * AJ68  could possibly be worked around by always programming
-	 * 	 a pebs_event_reset[0] value and coping with the lost events.
+	 *	 a pebs_event_reset[0] value and coping with the lost events.
 	 *
 	 * But taken together it might just make sense to not enable PEBS on
 	 * these chips.
@@ -1409,6 +1422,18 @@ static __init int intel_pmu_init(void)
 		x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
+
+		if (ebx & 0x40) {
+			/*
+			 * Erratum AAJ80 detected, we work it around by using
+			 * the BR_MISP_EXEC.ANY event. This will over-count
+			 * branch-misses, but it's still much better than the
+			 * architectural event which is often completely bogus:
+			 */
+			intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+
+			pr_cont("erratum AAJ80 worked around, ");
+		}
 		pr_cont("Nehalem events, ");
 		break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index d1f77e2..e93fcd5 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -950,11 +950,20 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 			x86_pmu_stop(event, 0);
 	}
 
-	if (handled) {
-		/* p4 quirk: unmask it again */
-		apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+	if (handled)
 		inc_irq_stat(apic_perf_irqs);
-	}
+
+	/*
+	 * When dealing with the unmasking of the LVTPC on P4 perf hw, it has
+	 * been observed that the OVF bit flag has to be cleared first _before_
+	 * the LVTPC can be unmasked.
+	 *
+	 * The reason is the NMI line will continue to be asserted while the OVF
+	 * bit is set.  This causes a second NMI to generate if the LVTPC is
+	 * unmasked before the OVF bit is cleared, leading to unknown NMI
+	 * messages.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	return handled;
 }
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61d7d59f..2ad39e5 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,7 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if !ARM_UNWIND && !S390
+	select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-04-22 13:42 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-04-22 13:42 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf: Support Xeon E7's via the Westmere PMU driver

Cyrill Gorcunov (1):
      perf, x86: P4 PMU - Don't forget to clear cpuc->active_mask on overflow

Ingo Molnar (1):
      x86, perf event: Turn off unstructured raw event access to offcore registers

Peter Zijlstra (1):
      perf, x86: Update/fix Intel Nehalem cache events


 arch/x86/kernel/cpu/perf_event.c       |    6 +++++-
 arch/x86/kernel/cpu/perf_event_intel.c |    9 +++++----
 arch/x86/kernel/cpu/perf_event_p4.c    |    2 +-
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index eed3673a..632e5dc 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -586,8 +586,12 @@ static int x86_setup_perfctr(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
+	/*
+	 * Do not allow config1 (extended registers) to propagate,
+	 * there's no sane user-space generalization yet:
+	 */
 	if (attr->type == PERF_TYPE_RAW)
-		return x86_pmu_extra_regs(event->attr.config, event);
+		return 0;
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8fc2b2c..43fa20b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -391,12 +391,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
 {
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+		[ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
 	},
 	[ C(OP_PREFETCH) ] = {
 		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
@@ -1425,6 +1425,7 @@ static __init int intel_pmu_init(void)
 
 	case 37: /* 32 nm nehalem, "Clarkdale" */
 	case 44: /* 32 nm nehalem, "Gulftown" */
+	case 47: /* 32 nm Xeon E7 */
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index c2520e1..d1f77e2 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -947,7 +947,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 		if (perf_event_overflow(event, 1, &data, regs))
-			p4_pmu_disable_event(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	if (handled) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-04-19 15:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-04-19 15:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Andre Przywara (1):
      perf, x86: Fix pre-defined cache-misses event for AMD family 15h cpus

Arnaldo Carvalho de Melo (1):
      perf evsel: Fix use of inherit

Lin Ming (1):
      perf hists browser: Fix seg fault when annotate null symbol

Robert Richter (1):
      perf, x86: Fix AMD family 15h FPU event constraints


 arch/x86/kernel/cpu/perf_event_amd.c   |   22 ++++++++++++++++++----
 tools/perf/builtin-record.c            |    7 +++++--
 tools/perf/builtin-stat.c              |    7 ++++---
 tools/perf/builtin-test.c              |   10 +++++-----
 tools/perf/builtin-top.c               |    3 ++-
 tools/perf/util/evlist.c               |   14 ++++++++++----
 tools/perf/util/evsel.c                |   27 +++++++--------------------
 tools/perf/util/evsel.h                |    6 +++---
 tools/perf/util/python.c               |    9 +++++----
 tools/perf/util/ui/browsers/annotate.c |    6 ++++--
 tools/perf/util/ui/browsers/hists.c    |    2 +-
 11 files changed, 64 insertions(+), 49 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62b..cf4e369 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
+		[ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@ static __initconst const struct x86_pmu amd_pmu = {
  *
  * Exceptions:
  *
+ * 0x000	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x003	FP	PERF_CTL[3]
+ * 0x004	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x00B	FP	PERF_CTL[3]
  * 0x00D	FP	PERF_CTL[3]
  * 0x023	DE	PERF_CTL[2:0]
@@ -448,6 +450,8 @@ static __initconst const struct x86_pmu amd_pmu = {
  * 0x0DF	LS	PERF_CTL[5:0]
  * 0x1D6	EX	PERF_CTL[5:0]
  * 0x1D8	EX	PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
  */
 
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@ static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
-	unsigned int event_code = amd_get_event_code(&event->hw);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int event_code = amd_get_event_code(hwc);
 
 	switch (event_code & AMD_EVENT_TYPE_MASK) {
 	case AMD_EVENT_FP:
 		switch (event_code) {
+		case 0x000:
+			if (!(hwc->config & 0x0000F000ULL))
+				break;
+			if (!(hwc->config & 0x00000F00ULL))
+				break;
+			return &amd_f15_PMC3;
+		case 0x004:
+			if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+				break;
+			return &amd_f15_PMC3;
 		case 0x003:
 		case 0x00B:
 		case 0x00D:
 			return &amd_f15_PMC3;
-		default:
-			return &amd_f15_PMC53;
 		}
+		return &amd_f15_PMC53;
 	case AMD_EVENT_LS:
 	case AMD_EVENT_DC:
 	case AMD_EVENT_EX_LS:
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 17d1dcb..4165382 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -163,6 +163,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
 				  PERF_FORMAT_ID;
@@ -251,6 +252,9 @@ static void open_counters(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
+	if (evlist->cpus->map[0] < 0)
+		no_inherit = true;
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
 		/*
@@ -271,8 +275,7 @@ static void open_counters(struct perf_evlist *evlist)
 retry_sample_id:
 		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
-				     !no_inherit) < 0) {
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e2109f9..03f0e45 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -167,16 +167,17 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
+	attr->inherit = !no_inherit;
+
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
 
-	attr->inherit = !no_inherit;
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
 }
 
 /*
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1b2106c..11e3c84 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -290,7 +290,7 @@ static int test__open_syscall_event(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -303,7 +303,7 @@ static int test__open_syscall_event(void)
 	}
 
 	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
-		pr_debug("perf_evsel__open_read_on_cpu\n");
+		pr_debug("perf_evsel__read_on_cpu\n");
 		goto out_close_fd;
 	}
 
@@ -365,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -418,7 +418,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 			continue;
 
 		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
-			pr_debug("perf_evsel__open_read_on_cpu\n");
+			pr_debug("perf_evsel__read_on_cpu\n");
 			err = -1;
 			break;
 		}
@@ -529,7 +529,7 @@ static int test__basic_mmap(void)
 
 		perf_evlist__add(evlist, evsels[i]);
 
-		if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+		if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fc1273e..7e3d6e3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -845,9 +845,10 @@ static void start_counters(struct perf_evlist *evlist)
 		}
 
 		attr->mmap = 1;
+		attr->inherit = inherit;
 try_again:
 		if (perf_evsel__open(counter, top.evlist->cpus,
-				     top.evlist->threads, group, inherit) < 0) {
+				     top.evlist->threads, group) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cef..45da8d1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,6 +12,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
+#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -250,15 +251,19 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
-			       int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			       int cpu, int prot, int mask, int fd)
 {
 	evlist->mmap[cpu].prev = 0;
 	evlist->mmap[cpu].mask = mask;
 	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[cpu].base == MAP_FAILED)
+	if (evlist->mmap[cpu].base == MAP_FAILED) {
+		if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit)
+			ui__warning("Inherit is not allowed on per-task "
+				    "events using mmap.\n");
 		return -1;
+	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
@@ -312,7 +317,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
 						  FD(first_evsel, cpu, 0)) != 0)
 						goto out_unmap;
-				} else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
+				} else if (__perf_evlist__mmap(evlist, evsel, cpu,
+							       prot, mask, fd) < 0)
 					goto out_unmap;
 
 				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596a..d6fd59b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -175,7 +175,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group, bool inherit)
+			      struct thread_map *threads, bool group)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
@@ -192,19 +192,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		int group_fd = -1;
-		/*
-		 * Don't allow mmap() of inherited per-task counters. This
-		 * would create a performance issue due to all children writing
-		 * to the same buffer.
-		 *
-		 * FIXME:
-		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-		 * but a 'flags' parameter, with 'group' folded there as well,
-		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-		 * set. Lets go for the minimal fix first tho.
-		 */
-		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -253,7 +240,7 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit)
+		     struct thread_map *threads, bool group)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -263,19 +250,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+	return __perf_evsel__open(evsel, cpus, threads, group);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit)
+			     struct cpu_map *cpus, bool group)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit)
+				struct thread_map *threads, bool group)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab5..f79bb2c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit);
+			     struct cpu_map *cpus, bool group);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit);
+				struct thread_map *threads, bool group);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit);
+		     struct thread_map *threads, bool group);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a9f2d7e..f5e3845 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -498,11 +498,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	struct cpu_map *cpus = NULL;
 	struct thread_map *threads = NULL;
 	PyObject *pcpus = NULL, *pthreads = NULL;
-	int group = 0, overwrite = 0;
-	static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+	int group = 0, inherit = 0;
+	static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
-					 &pcpus, &pthreads, &group, &overwrite))
+					 &pcpus, &pthreads, &group, &inherit))
 		return NULL;
 
 	if (pthreads != NULL)
@@ -511,7 +511,8 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	if (pcpus != NULL)
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
-	if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+	evsel->attr.inherit = inherit;
+	if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a87..15633d6 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -256,10 +256,9 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 			 int refresh)
 {
 	struct objdump_line *pos, *n;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes;
 	struct annotate_browser browser = {
 		.b = {
-			.entries = &notes->src->source,
 			.refresh = ui_browser__list_head_refresh,
 			.seek	 = ui_browser__list_head_seek,
 			.write	 = annotate_browser__write,
@@ -281,6 +280,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 
 	ui_helpline__push("Press <- or ESC to exit");
 
+	notes = symbol__annotation(sym);
+
 	list_for_each_entry(pos, &notes->src->source, node) {
 		struct objdump_line_rb_node *rbpos;
 		size_t line_len = strlen(pos->line);
@@ -291,6 +292,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 		rbpos->idx = browser.b.nr_entries++;
 	}
 
+	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 	ret = annotate_browser__run(&browser, evidx, refresh);
 	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 798efdc..5d767c6 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -851,7 +851,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel,
 			goto out_free_stack;
 		case 'a':
 			if (browser->selection == NULL ||
-			    browser->selection->map == NULL ||
+			    browser->selection->sym == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 			goto do_annotate;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-04-16 10:03 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-04-16 10:03 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Eric Dumazet (1):
      perf: Fix a build error with some GCC versions

Stephane Eranian (1):
      perf_event: Fix cgrp event scheduling bug in perf_enable_on_exec()


 kernel/perf_event.c      |   12 ++++++++++++
 tools/perf/util/cgroup.c |    2 +-
 2 files changed, 13 insertions(+), 1 deletions(-)

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 27960f1..8e81a98 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 			}
 
 			if (mode & PERF_CGROUP_SWIN) {
+				WARN_ON_ONCE(cpuctx->cgrp);
 				/* set cgrp before ctxsw in to
 				 * allow event_filter_match() to not
 				 * have to pass task around
@@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 	if (!ctx || !ctx->nr_events)
 		goto out;
 
+	/*
+	 * We must ctxsw out cgroup events to avoid conflict
+	 * when invoking perf_task_event_sched_in() later on
+	 * in this function. Otherwise we end up trying to
+	 * ctxswin cgroup events which are already scheduled
+	 * in.
+	 */
+	perf_cgroup_sched_out(current);
 	task_ctx_sched_out(ctx, EVENT_ALL);
 
 	raw_spin_lock(&ctx->lock);
@@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
 	raw_spin_unlock(&ctx->lock);
 
+	/*
+	 * Also calls ctxswin for cgroup events, if any:
+	 */
 	perf_event_context_sched_in(ctx, ctx->task);
 out:
 	local_irq_restore(flags);
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 9fea755..96bee5c 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -13,7 +13,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 {
 	FILE *fp;
 	char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
-	char *token, *saved_ptr;
+	char *token, *saved_ptr = NULL;
 	int found = 0;
 
 	fp = fopen("/proc/mounts", "r");

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-04-07 17:48 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-04-07 17:48 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Masami Hiramatsu (5):
      perf probe: Fix to ensure function declared file
      perf probe: Fix to remove redundant close
      perf probe: Fix multiple --vars options behavior
      perf probe: Fix to find recursively inlined function
      perf probe: Fix listing incorrect line number with inline function


 tools/perf/util/probe-event.c  |   19 ++---
 tools/perf/util/probe-finder.c |  159 ++++++++++++++++++++++++++--------------
 2 files changed, 113 insertions(+), 65 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5ddee66..f022316 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -234,7 +234,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	/* Searching trace events corresponding to probe event */
 	ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs);
-	close(fd);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("find %d probe_trace_events.\n", ntevs);
@@ -388,7 +387,6 @@ int show_line_range(struct line_range *lr, const char *module)
 	}
 
 	ret = find_line_range(fd, lr);
-	close(fd);
 	if (ret == 0) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
@@ -512,19 +510,18 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	fd = open_vmlinux(module);
-	if (fd < 0) {
-		pr_warning("Failed to open debug information file.\n");
-		return fd;
-	}
-
 	setup_pager();
 
-	for (i = 0; i < npevs && ret >= 0; i++)
+	for (i = 0; i < npevs && ret >= 0; i++) {
+		fd = open_vmlinux(module);
+		if (fd < 0) {
+			pr_warning("Failed to open debug information file.\n");
+			ret = fd;
+			break;
+		}
 		ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
 					     externs);
-
-	close(fd);
+	}
 	return ret;
 }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 194f9e2..b7c85ce 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -273,6 +273,25 @@ static const char *cu_get_comp_dir(Dwarf_Die *cu_die)
 	return dwarf_formstring(&attr);
 }
 
+/* Get a line number and file name for given address */
+static int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+			    const char **fname, int *lineno)
+{
+	Dwarf_Line *line;
+	Dwarf_Addr laddr;
+
+	line = dwarf_getsrc_die(cudie, (Dwarf_Addr)addr);
+	if (line && dwarf_lineaddr(line, &laddr) == 0 &&
+	    addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) {
+		*fname = dwarf_linesrc(line, NULL, NULL);
+		if (!*fname)
+			/* line number is useless without filename */
+			*lineno = 0;
+	}
+
+	return *lineno ?: -ENOENT;
+}
+
 /* Compare diename and tname */
 static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
@@ -497,7 +516,20 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 				      Dwarf_Die *die_mem)
 {
-	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+	Dwarf_Die tmp_die;
+
+	sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die);
+	if (!sp_die)
+		return NULL;
+
+	/* Inlined function could be recursive. Trace it until fail */
+	while (sp_die) {
+		memcpy(die_mem, sp_die, sizeof(Dwarf_Die));
+		sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr,
+					&tmp_die);
+	}
+
+	return die_mem;
 }
 
 /* Walker on lines (Note: line number will not be sorted) */
@@ -1395,6 +1427,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	    !die_compare_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
+	/* Check declared file */
+	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -1451,6 +1487,7 @@ static int find_probes(int fd, struct probe_finder *pf)
 	if (!dbg) {
 		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		close(fd);	/* Without dwfl_end(), fd isn't closed. */
 		return -EBADF;
 	}
 
@@ -1686,11 +1723,9 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 	Dwarf_Die cudie, spdie, indie;
 	Dwarf *dbg = NULL;
 	Dwfl *dwfl = NULL;
-	Dwarf_Line *line;
-	Dwarf_Addr laddr, eaddr, bias = 0;
-	const char *tmp;
-	int lineno, ret = 0;
-	bool found = false;
+	Dwarf_Addr _addr, baseaddr, bias = 0;
+	const char *fname = NULL, *func = NULL, *tmp;
+	int baseline = 0, lineno = 0, ret = 0;
 
 	/* Open the live linux kernel */
 	dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias);
@@ -1711,68 +1746,79 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 		goto end;
 	}
 
-	/* Find a corresponding line */
-	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
-	if (line) {
-		if (dwarf_lineaddr(line, &laddr) == 0 &&
-		    (Dwarf_Addr)addr == laddr &&
-		    dwarf_lineno(line, &lineno) == 0) {
-			tmp = dwarf_linesrc(line, NULL, NULL);
-			if (tmp) {
-				ppt->line = lineno;
-				ppt->file = strdup(tmp);
-				if (ppt->file == NULL) {
-					ret = -ENOMEM;
-					goto end;
-				}
-				found = true;
-			}
-		}
-	}
+	/* Find a corresponding line (filename and lineno) */
+	cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+	/* Don't care whether it failed or not */
 
-	/* Find a corresponding function */
+	/* Find a corresponding function (name, baseline and baseaddr) */
 	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		/* Get function entry information */
 		tmp = dwarf_diename(&spdie);
-		if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
-			goto end;
-
-		if (ppt->line) {
-			if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-						&indie)) {
-				/* addr in an inline function */
+		if (!tmp ||
+		    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
+		    dwarf_decl_line(&spdie, &baseline) != 0)
+			goto post;
+		func = tmp;
+
+		if (addr == (unsigned long)baseaddr)
+			/* Function entry - Relative line number is 0 */
+			lineno = baseline;
+		else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+					     &indie)) {
+			if (dwarf_entrypc(&indie, &_addr) == 0 &&
+			    _addr == addr)
+				/*
+				 * addr is at an inline function entry.
+				 * In this case, lineno should be the call-site
+				 * line number.
+				 */
+				lineno = die_get_call_lineno(&indie);
+			else {
+				/*
+				 * addr is in an inline function body.
+				 * Since lineno points one of the lines
+				 * of the inline function, baseline should
+				 * be the entry line of the inline function.
+				 */
 				tmp = dwarf_diename(&indie);
-				if (!tmp)
-					goto end;
-				ret = dwarf_decl_line(&indie, &lineno);
-			} else {
-				if (eaddr == addr) {	/* Function entry */
-					lineno = ppt->line;
-					ret = 0;
-				} else
-					ret = dwarf_decl_line(&spdie, &lineno);
-			}
-			if (ret == 0) {
-				/* Make a relative line number */
-				ppt->line -= lineno;
-				goto found;
+				if (tmp &&
+				    dwarf_decl_line(&spdie, &baseline) == 0)
+					func = tmp;
 			}
 		}
-		/* We don't have a line number, let's use offset */
-		ppt->offset = addr - (unsigned long)eaddr;
-found:
-		ppt->function = strdup(tmp);
+	}
+
+post:
+	/* Make a relative line number or an offset */
+	if (lineno)
+		ppt->line = lineno - baseline;
+	else if (func)
+		ppt->offset = addr - (unsigned long)baseaddr;
+
+	/* Duplicate strings */
+	if (func) {
+		ppt->function = strdup(func);
 		if (ppt->function == NULL) {
 			ret = -ENOMEM;
 			goto end;
 		}
-		found = true;
 	}
-
+	if (fname) {
+		ppt->file = strdup(fname);
+		if (ppt->file == NULL) {
+			if (ppt->function) {
+				free(ppt->function);
+				ppt->function = NULL;
+			}
+			ret = -ENOMEM;
+			goto end;
+		}
+	}
 end:
 	if (dwfl)
 		dwfl_end(dwfl);
-	if (ret >= 0)
-		ret = found ? 1 : 0;
+	if (ret == 0 && (fname || func))
+		ret = 1;	/* Found a point */
 	return ret;
 }
 
@@ -1840,6 +1886,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
+	/* Check declared file */
+	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
 	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
 	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
@@ -1892,6 +1942,7 @@ int find_line_range(int fd, struct line_range *lr)
 	if (!dbg) {
 		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		close(fd);	/* Without dwfl_end(), fd isn't closed. */
 		return -EBADF;
 	}
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-04-02 10:25 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-04-02 10:25 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      oprofile, x86: Allow setting EDGE/INV/CMASK for counter events

Andrew Lutomirski (1):
      perf symbols: Fix vsyscall symbol lookup

Arnaldo Carvalho de Melo (1):
      perf tools: Fixup exit path when not able to open events

David Ahern (1):
      perf tools: Emit clearer message for sys_perf_event_open ENOENT return

David S. Miller (1):
      perf symbols: Properly align symbol_conf.priv_size

Frederic Weisbecker (2):
      perf: Rebase max unprivileged mlock threshold on top of page size
      perf: mmap 512 kiB by default

Peter Zijlstra (2):
      perf: Fix task context scheduling
      perf: Fix task_struct reference leak

Robert Richter (1):
      perf tools: Fix NO_NEWT=1 python build error


 arch/x86/oprofile/nmi_int.c    |    5 ++++
 arch/x86/oprofile/op_counter.h |    1 +
 include/linux/perf_event.h     |    2 +-
 kernel/perf_event.c            |    9 ++++++-
 tools/perf/Makefile            |    8 +++++-
 tools/perf/builtin-record.c    |   25 ++++++++++++++++------
 tools/perf/builtin-top.c       |   44 +++++++++++++++++++++++++++------------
 tools/perf/util/debug.c        |   10 +++++++++
 tools/perf/util/debug.h        |    1 +
 tools/perf/util/event.c        |    2 +-
 tools/perf/util/setup.py       |    7 +++++-
 tools/perf/util/symbol.c       |    5 ++++
 12 files changed, 91 insertions(+), 28 deletions(-)

diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 8dace18..cf97500 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -49,6 +49,10 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 	val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0;
 	val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0;
 	val |= (counter_config->unit_mask & 0xFF) << 8;
+	counter_config->extra &= (ARCH_PERFMON_EVENTSEL_INV |
+				  ARCH_PERFMON_EVENTSEL_EDGE |
+				  ARCH_PERFMON_EVENTSEL_CMASK);
+	val |= counter_config->extra;
 	event &= model->event_mask ? model->event_mask : 0xFF;
 	val |= event & 0xFF;
 	val |= (event & 0x0F00) << 24;
@@ -440,6 +444,7 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
 		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
 		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
 		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+		oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
 	}
 
 	return 0;
diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h
index e28398d..0b7b7b1 100644
--- a/arch/x86/oprofile/op_counter.h
+++ b/arch/x86/oprofile/op_counter.h
@@ -22,6 +22,7 @@ struct op_counter_config {
 	unsigned long kernel;
 	unsigned long user;
 	unsigned long unit_mask;
+	unsigned long extra;
 };
 
 extern struct op_counter_config counter_config[];
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 311b4dc..04d75a8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1086,7 +1086,7 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
-	COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
+	__perf_event_task_sched_out(task, next);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index c75925c..27960f1 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -145,8 +145,8 @@ static struct srcu_struct pmus_srcu;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-/* Minimum for 128 pages + 1 for the user control page */
-int sysctl_perf_event_mlock __read_mostly = 516; /* 'free' kb per user */
+/* Minimum for 512 kiB + 1 user control page */
+int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
 
 /*
  * max perf event sample rate
@@ -6531,6 +6531,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_alloc;
 	}
 
+	if (task) {
+		put_task_struct(task);
+		task = NULL;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 158c30e..207dee5 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -165,8 +165,12 @@ grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
 $(OUTPUT)python/perf.so: $(PYRF_OBJS)
-	$(QUIET_GEN)python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
-						--build-temp='$(OUTPUT)python/temp'
+	$(QUIET_GEN)( \
+		export CFLAGS="$(BASIC_CFLAGS)"; \
+		python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
+			--build-temp='$(OUTPUT)python/temp' \
+	)
+
 #
 # No Perl scripts right now:
 #
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6febcc1..17d1dcb 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,7 +41,7 @@ static u64			user_interval			= ULLONG_MAX;
 static u64			default_interval		=      0;
 
 static unsigned int		page_size;
-static unsigned int		mmap_pages			=    128;
+static unsigned int		mmap_pages			= UINT_MAX;
 static unsigned int		user_freq 			= UINT_MAX;
 static int			freq				=   1000;
 static int			output;
@@ -275,11 +275,10 @@ try_again:
 				     !no_inherit) < 0) {
 			int err = errno;
 
-			if (err == EPERM || err == EACCES)
-				die("Permission error - are you root?\n"
-					"\t Consider tweaking"
-					" /proc/sys/kernel/perf_event_paranoid.\n");
-			else if (err ==  ENODEV && cpu_list) {
+			if (err == EPERM || err == EACCES) {
+				ui__warning_paranoid();
+				exit(EXIT_FAILURE);
+			} else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
 			} else if (err == EINVAL && sample_id_all_avail) {
@@ -302,11 +301,19 @@ try_again:
 					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
 
 				if (verbose)
-					warning(" ... trying to fall back to cpu-clock-ticks\n");
+					ui__warning("The cycles event is not supported, "
+						    "trying to fall back to cpu-clock-ticks\n");
 				attr->type = PERF_TYPE_SOFTWARE;
 				attr->config = PERF_COUNT_SW_CPU_CLOCK;
 				goto try_again;
 			}
+
+			if (err == ENOENT) {
+				ui__warning("The %s event is not supported.\n",
+					    event_name(pos));
+				exit(EXIT_FAILURE);
+			}
+
 			printf("\n");
 			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
 			      err, strerror(err));
@@ -506,6 +513,10 @@ static int __cmd_record(int argc, const char **argv)
 	if (have_tracepoints(&evsel_list->entries))
 		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
+	/* 512 kiB: default amount of unprivileged mlocked memory */
+	if (mmap_pages == UINT_MAX)
+		mmap_pages = (512 * 1024) / page_size;
+
 	if (forks) {
 		child_pid = fork();
 		if (child_pid < 0) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 676b4fb..fc1273e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -850,10 +850,10 @@ try_again:
 				     top.evlist->threads, group, inherit) < 0) {
 			int err = errno;
 
-			if (err == EPERM || err == EACCES)
-				die("Permission error - are you root?\n"
-					"\t Consider tweaking"
-					" /proc/sys/kernel/perf_event_paranoid.\n");
+			if (err == EPERM || err == EACCES) {
+				ui__warning_paranoid();
+				goto out_err;
+			}
 			/*
 			 * If it's cycles then fall back to hrtimer
 			 * based cpu-clock-tick sw counter, which
@@ -861,25 +861,41 @@ try_again:
 			 */
 			if (attr->type == PERF_TYPE_HARDWARE &&
 			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
 				if (verbose)
-					warning(" ... trying to fall back to cpu-clock-ticks\n");
+					ui__warning("Cycles event not supported,\n"
+						    "trying to fall back to cpu-clock-ticks\n");
 
 				attr->type = PERF_TYPE_SOFTWARE;
 				attr->config = PERF_COUNT_SW_CPU_CLOCK;
 				goto try_again;
 			}
-			printf("\n");
-			error("sys_perf_event_open() syscall returned with %d "
-			      "(%s).  /bin/dmesg may provide additional information.\n",
-			      err, strerror(err));
-			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-			exit(-1);
+
+			if (err == ENOENT) {
+				ui__warning("The %s event is not supported.\n",
+					    event_name(counter));
+				goto out_err;
+			}
+
+			ui__warning("The sys_perf_event_open() syscall "
+				    "returned with %d (%s).  /bin/dmesg "
+				    "may provide additional information.\n"
+				    "No CONFIG_PERF_EVENTS=y kernel support "
+				    "configured?\n", err, strerror(err));
+			goto out_err;
 		}
 	}
 
-	if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
-		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+	if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) {
+		ui__warning("Failed to mmap with %d (%s)\n",
+			    errno, strerror(errno));
+		goto out_err;
+	}
+
+	return;
+
+out_err:
+	exit_browser(0);
+	exit(0);
 }
 
 static int __cmd_top(void)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index d4536a9..155749d 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -57,6 +57,16 @@ void ui__warning(const char *format, ...)
 }
 #endif
 
+void ui__warning_paranoid(void)
+{
+	ui__warning("Permission error - are you root?\n"
+		    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
+		    " -1 - Not paranoid at all\n"
+		    "  0 - Disallow raw tracepoint access for unpriv\n"
+		    "  1 - Disallow cpu events for unpriv\n"
+		    "  2 - Disallow kernel profiling for unpriv\n");
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 93516cf4..fd53db4 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -36,5 +36,6 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #endif
 
 void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+void ui__warning_paranoid(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2b15c36..1023f67 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -710,7 +710,7 @@ try_again:
 		 * in the whole kernel symbol list.
 		 */
 		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_KERNEL &&
+		    cpumode == PERF_RECORD_MISC_USER &&
 		    machine && mg != &machine->kmaps) {
 			mg = &machine->kmaps;
 			goto try_again;
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index e24ffad..bbc982f 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,13 +1,18 @@
 #!/usr/bin/python2
 
 from distutils.core import setup, Extension
+from os import getenv
+
+cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
+cflags += getenv('CFLAGS', '').split()
 
 perf = Extension('perf',
 		  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
 			     'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
 			     'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
 		  include_dirs = ['util/include'],
-		  extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings'])
+		  extra_compile_args = cflags,
+                 )
 
 setup(name='perf',
       version='0.1',
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 17df793..f06c10f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1196,6 +1196,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				if (curr_dso == NULL)
 					goto out_elf_end;
 				curr_dso->kernel = self->kernel;
+				curr_dso->long_name = self->long_name;
+				curr_dso->long_name_len = self->long_name_len;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
@@ -1842,6 +1844,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	if (fd < 0)
 		return -1;
 
+	dso__set_long_name(self, (char *)vmlinux);
 	dso__set_loaded(self, map->type);
 	err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
 	close(fd);
@@ -2403,6 +2406,8 @@ int symbol__init(void)
 	if (symbol_conf.initialized)
 		return 0;
 
+	symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
+
 	elf_version(EV_CURRENT);
 	if (symbol_conf.sort_by_name)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-03-25 13:11 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-03-25 13:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Akihiro Nagai (1):
      perf top: Fix uninitialized 'counter' variable

Arnaldo Carvalho de Melo (3):
      perf session: Pass evsel in event_ops->sample()
      perf build-id: Add quirk to deal with perf.data file format breakage
      perf symbols: Look at .dynsym again if .symtab not found

Don Zickus (1):
      perf, x86: P4 PMU - Read proper MSR register to catch unflagged overflows

Frederic Weisbecker (1):
      perf: Better fit max unprivileged mlock pages for tools needs

Ingo Molnar (1):
      perf, x86: Complain louder about BIOSen corrupting CPU/PMU state and continue

Jiri Olsa (1):
      tracing: Fix set_ftrace_filter probe function display

Stephane Eranian (2):
      perf, x86: Fix Intel fixed counters base initialization
      perf_events: Fix stale ->cgrp pointer in update_cgrp_time_from_cpuctx()


 arch/x86/kernel/cpu/perf_event.c                   |   11 +++-
 arch/x86/kernel/cpu/perf_event_p4.c                |    1 +
 include/linux/perf_event.h                         |    2 -
 kernel/perf_event.c                                |   15 +++++-
 kernel/trace/ftrace.c                              |    3 +-
 tools/perf/builtin-annotate.c                      |   18 ++-----
 tools/perf/builtin-diff.c                          |    1 +
 tools/perf/builtin-inject.c                        |   11 ++++-
 tools/perf/builtin-kmem.c                          |    1 +
 tools/perf/builtin-lock.c                          |    4 +-
 tools/perf/builtin-report.c                        |   19 ++-----
 tools/perf/builtin-sched.c                         |    1 +
 tools/perf/builtin-script.c                        |   15 ++----
 tools/perf/builtin-timechart.c                     |   11 ++++
 tools/perf/builtin-top.c                           |    4 +-
 tools/perf/util/build-id.c                         |    1 +
 tools/perf/util/header.c                           |   57 +++++++++++++++++++-
 tools/perf/util/hist.h                             |    1 +
 .../perf/util/scripting-engines/trace-event-perl.c |    1 +
 .../util/scripting-engines/trace-event-python.c    |    1 +
 tools/perf/util/session.c                          |   25 ++++++++-
 tools/perf/util/session.h                          |    7 ++-
 tools/perf/util/symbol.c                           |   25 +++++----
 tools/perf/util/trace-event-scripting.c            |    1 +
 tools/perf/util/trace-event.h                      |    1 +
 25 files changed, 168 insertions(+), 69 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e8dbe17..eb00677 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -500,12 +500,17 @@ static bool check_hw_exists(void)
 	return true;
 
 bios_fail:
-	printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+	/*
+	 * We still allow the PMU driver to operate:
+	 */
+	printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
 	printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
-	return false;
+
+	return true;
 
 msr_fail:
 	printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+
 	return false;
 }
 
@@ -912,7 +917,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 		hwc->event_base	= 0;
 	} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0;
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED);
 	} else {
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 3769ac8..d3d7b59 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -777,6 +777,7 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 	 * the counter has reached zero value and continued counting before
 	 * real NMI signal was received:
 	 */
+	rdmsrl(hwc->event_base, v);
 	if (!(v & ARCH_P4_UNFLAGGED_BIT))
 		return 1;
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f495c01..311b4dc 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -938,9 +938,7 @@ struct perf_cpu_context {
 	struct list_head		rotation_list;
 	int				jiffies_interval;
 	struct pmu			*active_pmu;
-#ifdef CONFIG_CGROUP_PERF
 	struct perf_cgroup		*cgrp;
-#endif
 };
 
 struct perf_output_handle {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 3472bb1..c75925c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -145,7 +145,8 @@ static struct srcu_struct pmus_srcu;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
+/* Minimum for 128 pages + 1 for the user control page */
+int sysctl_perf_event_mlock __read_mostly = 516; /* 'free' kb per user */
 
 /*
  * max perf event sample rate
@@ -941,6 +942,7 @@ static void perf_group_attach(struct perf_event *event)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
+	struct perf_cpu_context *cpuctx;
 	/*
 	 * We can have double detach due to exit/hot-unplug + close.
 	 */
@@ -949,8 +951,17 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
-	if (is_cgroup_event(event))
+	if (is_cgroup_event(event)) {
 		ctx->nr_cgroups--;
+		cpuctx = __get_cpu_context(ctx);
+		/*
+		 * if there are no more cgroup events
+		 * then cler cgrp to avoid stale pointer
+		 * in update_cgrp_time_from_cpuctx()
+		 */
+		if (!ctx->nr_cgroups)
+			cpuctx->cgrp = NULL;
+	}
 
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 888b611..c075f4e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1467,7 +1467,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		return t_hash_next(m, pos);
 
 	(*pos)++;
-	iter->pos = *pos;
+	iter->pos = iter->func_pos = *pos;
 
 	if (iter->flags & FTRACE_ITER_PRINTALL)
 		return t_hash_start(m, pos);
@@ -1502,7 +1502,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 	if (!rec)
 		return t_hash_start(m, pos);
 
-	iter->func_pos = *pos;
 	iter->func = rec;
 
 	return iter;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 695de4b..e18eb7e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -42,9 +42,9 @@ static const char *sym_hist_filter;
 
 static int perf_evlist__add_sample(struct perf_evlist *evlist,
 				   struct perf_sample *sample,
+				   struct perf_evsel *evsel,
 				   struct addr_location *al)
 {
-	struct perf_evsel *evsel;
 	struct hist_entry *he;
 	int ret;
 
@@ -59,18 +59,6 @@ static int perf_evlist__add_sample(struct perf_evlist *evlist,
 		return 0;
 	}
 
-	evsel = perf_evlist__id2evsel(evlist, sample->id);
-	if (evsel == NULL) {
-		/*
-		 * FIXME: Propagate this back, but at least we're in a builtin,
-		 * where exit() is allowed. ;-)
-		 */
-		ui__warning("Invalid %s file, contains samples with id not in "
-			    "its header!\n", input_name);
-		exit_browser(0);
-		exit(1);
-	}
-
 	he = __hists__add_entry(&evsel->hists, al, NULL, 1);
 	if (he == NULL)
 		return -ENOMEM;
@@ -92,6 +80,7 @@ static int perf_evlist__add_sample(struct perf_evlist *evlist,
 
 static int process_sample_event(union perf_event *event,
 				struct perf_sample *sample,
+				struct perf_evsel *evsel,
 				struct perf_session *session)
 {
 	struct addr_location al;
@@ -103,7 +92,8 @@ static int process_sample_event(union perf_event *event,
 		return -1;
 	}
 
-	if (!al.filtered && perf_evlist__add_sample(session->evlist, sample, &al)) {
+	if (!al.filtered &&
+	    perf_evlist__add_sample(session->evlist, sample, evsel, &al)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		return -1;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 6b7d911..e821999 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -32,6 +32,7 @@ static int hists__add_entry(struct hists *self,
 
 static int diff__process_sample_event(union perf_event *event,
 				      struct perf_sample *sample,
+				      struct perf_evsel *evsel __used,
 				      struct perf_session *session)
 {
 	struct addr_location al;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index e29f04e..8dfc12b 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -43,6 +43,14 @@ static int perf_event__repipe(union perf_event *event,
 	return perf_event__repipe_synth(event, session);
 }
 
+static int perf_event__repipe_sample(union perf_event *event,
+			      struct perf_sample *sample __used,
+			      struct perf_evsel *evsel __used,
+			      struct perf_session *session)
+{
+	return perf_event__repipe_synth(event, session);
+}
+
 static int perf_event__repipe_mmap(union perf_event *event,
 				   struct perf_sample *sample,
 				   struct perf_session *session)
@@ -124,6 +132,7 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session)
 
 static int perf_event__inject_buildid(union perf_event *event,
 				      struct perf_sample *sample,
+				      struct perf_evsel *evsel __used,
 				      struct perf_session *session)
 {
 	struct addr_location al;
@@ -164,7 +173,7 @@ repipe:
 }
 
 struct perf_event_ops inject_ops = {
-	.sample		= perf_event__repipe,
+	.sample		= perf_event__repipe_sample,
 	.mmap		= perf_event__repipe,
 	.comm		= perf_event__repipe,
 	.fork		= perf_event__repipe,
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 7f618f4..225e963 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -305,6 +305,7 @@ static void process_raw_event(union perf_event *raw_event __used, void *data,
 
 static int process_sample_event(union perf_event *event,
 				struct perf_sample *sample,
+				struct perf_evsel *evsel __used,
 				struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, event->ip.pid);
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 7a2a79d..9ac05aa 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -845,7 +845,9 @@ static void dump_info(void)
 		die("Unknown type of information\n");
 }
 
-static int process_sample_event(union perf_event *event, struct perf_sample *sample,
+static int process_sample_event(union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel __used,
 				struct perf_session *s)
 {
 	struct thread *thread = perf_session__findnew(s, sample->tid);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b1b8200..498c6f7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -50,12 +50,12 @@ static symbol_filter_t	annotate_init;
 
 static int perf_session__add_hist_entry(struct perf_session *session,
 					struct addr_location *al,
-					struct perf_sample *sample)
+					struct perf_sample *sample,
+					struct perf_evsel *evsel)
 {
 	struct symbol *parent = NULL;
 	int err = 0;
 	struct hist_entry *he;
-	struct perf_evsel *evsel;
 
 	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
 		err = perf_session__resolve_callchain(session, al->thread,
@@ -64,18 +64,6 @@ static int perf_session__add_hist_entry(struct perf_session *session,
 			return err;
 	}
 
-	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	if (evsel == NULL) {
-		/*
-		 * FIXME: Propagate this back, but at least we're in a builtin,
-		 * where exit() is allowed. ;-)
-		 */
-		ui__warning("Invalid %s file, contains samples with id %" PRIu64 " not in "
-			    "its header!\n", input_name, sample->id);
-		exit_browser(0);
-		exit(1);
-	}
-
 	he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
 	if (he == NULL)
 		return -ENOMEM;
@@ -113,6 +101,7 @@ out:
 
 static int process_sample_event(union perf_event *event,
 				struct perf_sample *sample,
+				struct perf_evsel *evsel,
 				struct perf_session *session)
 {
 	struct addr_location al;
@@ -127,7 +116,7 @@ static int process_sample_event(union perf_event *event,
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
-	if (perf_session__add_hist_entry(session, &al, sample)) {
+	if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
 		pr_debug("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index a32f411..dcfe887 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1603,6 +1603,7 @@ static void process_raw_event(union perf_event *raw_event __used,
 
 static int process_sample_event(union perf_event *event,
 				struct perf_sample *sample,
+				struct perf_evsel *evsel __used,
 				struct perf_session *session)
 {
 	struct thread *thread;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9f5fc54..ac574ea 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -162,19 +162,11 @@ static void print_sample_start(struct perf_sample *sample,
 
 static void process_event(union perf_event *event __unused,
 			  struct perf_sample *sample,
+			  struct perf_evsel *evsel,
 			  struct perf_session *session,
 			  struct thread *thread)
 {
-	struct perf_event_attr *attr;
-	struct perf_evsel *evsel;
-
-	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	if (evsel == NULL) {
-		pr_err("Invalid data. Contains samples with id not in "
-		       "its header!\n");
-		return;
-	}
-	attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->attr;
 
 	if (output_fields[attr->type] == 0)
 		return;
@@ -244,6 +236,7 @@ static char const		*input_name = "perf.data";
 
 static int process_sample_event(union perf_event *event,
 				struct perf_sample *sample,
+				struct perf_evsel *evsel,
 				struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, event->ip.pid);
@@ -264,7 +257,7 @@ static int process_sample_event(union perf_event *event,
 		last_timestamp = sample->time;
 		return 0;
 	}
-	scripting_ops->process_event(event, sample, session, thread);
+	scripting_ops->process_event(event, sample, evsel, session, thread);
 
 	session->hists.stats.total_period += sample->period;
 	return 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 67c0459..aa26f4d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -488,6 +488,7 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 
 static int process_sample_event(union perf_event *event __used,
 				struct perf_sample *sample,
+				struct perf_evsel *evsel __used,
 				struct perf_session *session)
 {
 	struct trace_entry *te;
@@ -506,6 +507,16 @@ static int process_sample_event(union perf_event *event __used,
 		struct power_entry_old *peo;
 		peo = (void *)te;
 #endif
+		/*
+		 * FIXME: use evsel, its already mapped from id to perf_evsel,
+		 * remove perf_header__find_event infrastructure bits.
+		 * Mapping all these "power:cpu_idle" strings to the tracepoint
+		 * ID and then just comparing against evsel->attr.config.
+		 *
+		 * e.g.:
+		 *
+		 * if (evsel->attr.config == power_cpu_idle_id)
+		 */
 		event_str = perf_header__find_event(te->type);
 
 		if (!event_str)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 70f1075..676b4fb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -515,7 +515,9 @@ static void handle_keypress(struct perf_session *session, int c)
 			break;
 		case 'E':
 			if (top.evlist->nr_entries > 1) {
-				int counter;
+				/* Select 0 as the default event: */
+				int counter = 0;
+
 				fprintf(stderr, "\nAvailable events:");
 
 				list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 31f934a..a91cd99 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -16,6 +16,7 @@
 
 static int build_id__mark_dso_hit(union perf_event *event,
 				  struct perf_sample *sample __used,
+				  struct perf_evsel *evsel __used,
 				  struct perf_session *session)
 {
 	struct addr_location al;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e5230c0..93862a8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -695,13 +695,50 @@ out:
 	return err;
 }
 
+static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
+						 int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct {
+		struct perf_event_header   header;
+		u8			   build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+		char			   filename[0];
+	} old_bev;
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+			return -1;
+
+		if (header->needs_swap)
+			perf_event_header__bswap(&old_bev.header);
+
+		len = old_bev.header.size - sizeof(old_bev);
+		if (read(input, filename, len) != len)
+			return -1;
+
+		bev.header = old_bev.header;
+		bev.pid	   = 0;
+		memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+
+	return 0;
+}
+
 static int perf_header__read_build_ids(struct perf_header *header,
 				       int input, u64 offset, u64 size)
 {
 	struct perf_session *session = container_of(header, struct perf_session, header);
 	struct build_id_event bev;
 	char filename[PATH_MAX];
-	u64 limit = offset + size;
+	u64 limit = offset + size, orig_offset = offset;
 	int err = -1;
 
 	while (offset < limit) {
@@ -716,6 +753,24 @@ static int perf_header__read_build_ids(struct perf_header *header,
 		len = bev.header.size - sizeof(bev);
 		if (read(input, filename, len) != len)
 			goto out;
+		/*
+		 * The a1645ce1 changeset:
+		 *
+		 * "perf: 'perf kvm' tool for monitoring guest performance from host"
+		 *
+		 * Added a field to struct build_id_event that broke the file
+		 * format.
+		 *
+		 * Since the kernel build-id is the first entry, process the
+		 * table using the old format if the well known
+		 * '[kernel.kallsyms]' string for the kernel build-id has the
+		 * first 4 characters chopped off (where the pid_t sits).
+		 */
+		if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
+			if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
+				return -1;
+			return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
+		}
 
 		__event_process_build_id(&bev, filename, session);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index cb6858a..3beb97c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -29,6 +29,7 @@ struct events_stats {
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_unknown_events;
 	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
 };
 
 enum hist_column {
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 6214272..74350ff 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -247,6 +247,7 @@ static inline struct event *find_cache_event(int type)
 
 static void perl_process_event(union perf_event *pevent __unused,
 			       struct perf_sample *sample,
+			       struct perf_evsel *evsel,
 			       struct perf_session *session __unused,
 			       struct thread *thread)
 {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 1b85d60..6ccf70e 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -206,6 +206,7 @@ static inline struct event *find_cache_event(int type)
 
 static void python_process_event(union perf_event *pevent __unused,
 				 struct perf_sample *sample,
+				 struct perf_evsel *evsel __unused,
 				 struct perf_session *session __unused,
 				 struct thread *thread)
 {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c68cf40..caa2245 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -280,6 +280,15 @@ static int process_event_synth_stub(union perf_event *event __used,
 	return 0;
 }
 
+static int process_event_sample_stub(union perf_event *event __used,
+				     struct perf_sample *sample __used,
+				     struct perf_evsel *evsel __used,
+				     struct perf_session *session __used)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_event_stub(union perf_event *event __used,
 			      struct perf_sample *sample __used,
 			      struct perf_session *session __used)
@@ -303,7 +312,7 @@ static int process_finished_round(union perf_event *event,
 static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 {
 	if (handler->sample == NULL)
-		handler->sample = process_event_stub;
+		handler->sample = process_event_sample_stub;
 	if (handler->mmap == NULL)
 		handler->mmap = process_event_stub;
 	if (handler->comm == NULL)
@@ -698,12 +707,19 @@ static int perf_session_deliver_event(struct perf_session *session,
 				      struct perf_event_ops *ops,
 				      u64 file_offset)
 {
+	struct perf_evsel *evsel;
+
 	dump_event(session, event, file_offset, sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
 		dump_sample(session, event, sample);
-		return ops->sample(event, sample, session);
+		evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+		if (evsel == NULL) {
+			++session->hists.stats.nr_unknown_id;
+			return -1;
+		}
+		return ops->sample(event, sample, evsel, session);
 	case PERF_RECORD_MMAP:
 		return ops->mmap(event, sample, session);
 	case PERF_RECORD_COMM:
@@ -845,6 +861,11 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 			    session->hists.stats.nr_unknown_events);
 	}
 
+	if (session->hists.stats.nr_unknown_id != 0) {
+		ui__warning("%u samples with id not present in the header\n",
+			    session->hists.stats.nr_unknown_id);
+	}
+
  	if (session->hists.stats.nr_invalid_chains != 0) {
  		ui__warning("Found invalid callchains!\n\n"
  			    "%u out of %u events were discarded for this reason.\n\n"
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0b3c9af..1ac481f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -55,8 +55,11 @@ struct perf_session {
 	char			filename[0];
 };
 
+struct perf_evsel;
 struct perf_event_ops;
 
+typedef int (*event_sample)(union perf_event *event, struct perf_sample *sample,
+			    struct perf_evsel *evsel, struct perf_session *session);
 typedef int (*event_op)(union perf_event *self, struct perf_sample *sample,
 			struct perf_session *session);
 typedef int (*event_synth_op)(union perf_event *self,
@@ -65,8 +68,8 @@ typedef int (*event_op2)(union perf_event *self, struct perf_session *session,
 			 struct perf_event_ops *ops);
 
 struct perf_event_ops {
-	event_op	sample,
-			mmap,
+	event_sample	sample;
+	event_op	mmap,
 			comm,
 			fork,
 			exit,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 651dbfe..17df793 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1486,7 +1486,9 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
-	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE, want_symtab = 1;
+	want_symtab = 1;
+restart:
+	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE;
 	     self->symtab_type != SYMTAB__NOT_FOUND;
 	     self->symtab_type++) {
 		switch (self->symtab_type) {
@@ -1536,17 +1538,7 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 			snprintf(name, size, "%s%s", symbol_conf.symfs,
 				 self->long_name);
 			break;
-
-		default:
-			/*
-			 * If we wanted a full symtab but no image had one,
-			 * relax our requirements and repeat the search.
-			 */
-			if (want_symtab) {
-				want_symtab = 0;
-				self->symtab_type = SYMTAB__BUILD_ID_CACHE;
-			} else
-				continue;
+		default:;
 		}
 
 		/* Name is now the name of the next image to try */
@@ -1573,6 +1565,15 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 		}
 	}
 
+	/*
+	 * If we wanted a full symtab but no image had one,
+	 * relax our requirements and repeat the search.
+	 */
+	if (ret <= 0 && want_symtab) {
+		want_symtab = 0;
+		goto restart;
+	}
+
 	free(name);
 	if (ret < 0 && strstr(self->name, " (deleted)") != NULL)
 		return 0;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 66f4b78..c9dcbec 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -38,6 +38,7 @@ static int stop_script_unsupported(void)
 
 static void process_event_unsupported(union perf_event *event __unused,
 				      struct perf_sample *sample __unused,
+				      struct perf_evsel *evsel __unused,
 				      struct perf_session *session __unused,
 				      struct thread *thread __unused)
 {
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b04da57..f674dda 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -280,6 +280,7 @@ struct scripting_ops {
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
+			       struct perf_evsel *evsel,
 			       struct perf_session *session,
 			       struct thread *thread);
 	int (*generate_script) (const char *outfile);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-03-10  7:53 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-03-10  7:53 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/urgent

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf symbols: Fix vmlinux path when not using --symfs

Lin Ming (1):
      perf symbols: Avoid resolving [kernel.kallsyms] to real path for buildid cache


 tools/perf/util/header.c |   11 ++++++++---
 tools/perf/util/symbol.c |    2 +-
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f6a929e7..0866bcd 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -270,11 +270,15 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms)
 {
 	const size_t size = PATH_MAX;
-	char *realname = realpath(name, NULL),
-	     *filename = malloc(size),
+	char *realname, *filename = malloc(size),
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
+	if (is_kallsyms)
+		realname = (char *)name;
+	else
+		realname = realpath(name, NULL);
+
 	if (realname == NULL || filename == NULL || linkname == NULL)
 		goto out_free;
 
@@ -306,7 +310,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (symlink(targetname, linkname) == 0)
 		err = 0;
 out_free:
-	free(realname);
+	if (!is_kallsyms)
+		free(realname);
 	free(filename);
 	free(linkname);
 	return err;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7821d0e..b1bf490 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1836,7 +1836,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	int err = -1, fd;
 	char symfs_vmlinux[PATH_MAX];
 
-	snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s/%s",
+	snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
 		 symbol_conf.symfs, vmlinux);
 	fd = open(symfs_vmlinux, O_RDONLY);
 	if (fd < 0)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-02-28 17:34 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-02-28 17:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf hists: Print number of samples, not the period sum

Thomas Renninger (2):
      perf timechart: Fix black idle boxes in the title
      perf timechart: Fix max number of cpus


 tools/perf/builtin-timechart.c |    6 +++---
 tools/perf/util/hist.c         |    7 +++++--
 tools/perf/util/svghelper.c    |    6 +++---
 3 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 746cf03..0ace786 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -264,9 +264,6 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
 		c->start_time = start;
 	if (p->start_time == 0 || p->start_time > start)
 		p->start_time = start;
-
-	if (cpu > numcpus)
-		numcpus = cpu;
 }
 
 #define MAX_CPUS 4096
@@ -511,6 +508,9 @@ static int process_sample_event(event_t *event __used,
 		if (!event_str)
 			return 0;
 
+		if (sample->cpu > numcpus)
+			numcpus = sample->cpu;
+
 		if (strcmp(event_str, "power:cpu_idle") == 0) {
 			struct power_processor_entry *ppe = (void *)te;
 			if (ppe->state == (u32)PWR_EVENT_EXIT)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 32f4f1f..df51560 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -585,6 +585,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 {
 	struct sort_entry *se;
 	u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
+	u64 nr_events;
 	const char *sep = symbol_conf.field_sep;
 	int ret;
 
@@ -593,6 +594,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 
 	if (pair_hists) {
 		period = self->pair ? self->pair->period : 0;
+		nr_events = self->pair ? self->pair->nr_events : 0;
 		total = pair_hists->stats.total_period;
 		period_sys = self->pair ? self->pair->period_sys : 0;
 		period_us = self->pair ? self->pair->period_us : 0;
@@ -600,6 +602,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 		period_guest_us = self->pair ? self->pair->period_guest_us : 0;
 	} else {
 		period = self->period;
+		nr_events = self->nr_events;
 		total = session_total;
 		period_sys = self->period_sys;
 		period_us = self->period_us;
@@ -640,9 +643,9 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 
 	if (symbol_conf.show_nr_samples) {
 		if (sep)
-			ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period);
+			ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events);
 		else
-			ret += snprintf(s + ret, size - ret, "%11" PRIu64, period);
+			ret += snprintf(s + ret, size - ret, "%11" PRIu64, nr_events);
 	}
 
 	if (pair_hists) {
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index fb737fe..96c8660 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -456,9 +456,9 @@ void svg_legenda(void)
 		return;
 
 	svg_legenda_box(0,	"Running", "sample");
-	svg_legenda_box(100,	"Idle","rect.c1");
-	svg_legenda_box(200,	"Deeper Idle", "rect.c3");
-	svg_legenda_box(350,	"Deepest Idle", "rect.c6");
+	svg_legenda_box(100,	"Idle","c1");
+	svg_legenda_box(200,	"Deeper Idle", "c3");
+	svg_legenda_box(350,	"Deepest Idle", "c6");
 	svg_legenda_box(550,	"Sleeping", "process2");
 	svg_legenda_box(650,	"Waiting for cpu", "waiting");
 	svg_legenda_box(800,	"Blocked on IO", "blocked");

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-02-22 16:03 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-02-22 16:03 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Cyrill Gorcunov (1):
      perf, x86: P4 PMU: Fix spurious NMI messages

Peter Zijlstra (1):
      perf: Fix throttle logic


 arch/x86/include/asm/perf_event_p4.h |    1 +
 arch/x86/kernel/cpu/perf_event_p4.c  |   11 ++++++++---
 kernel/perf_event.c                  |   19 +++++++++++++++----
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index e2f6a99..cc29086 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -22,6 +22,7 @@
 
 #define ARCH_P4_CNTRVAL_BITS	(40)
 #define ARCH_P4_CNTRVAL_MASK	((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
+#define ARCH_P4_UNFLAGGED_BIT	((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1))
 
 #define P4_ESCR_EVENT_MASK	0x7e000000U
 #define P4_ESCR_EVENT_SHIFT	25
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index f7a0993..ff751a9 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -770,9 +770,14 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 		return 1;
 	}
 
-	/* it might be unflagged overflow */
-	rdmsrl(hwc->event_base + hwc->idx, v);
-	if (!(v & ARCH_P4_CNTRVAL_MASK))
+	/*
+	 * In some circumstances the overflow might issue an NMI but did
+	 * not set P4_CCCR_OVF bit. Because a counter holds a negative value
+	 * we simply check for high bit being set, if it's cleared it means
+	 * the counter has reached zero value and continued counting before
+	 * real NMI signal was received:
+	 */
+	if (!(v & ARCH_P4_UNFLAGGED_BIT))
 		return 1;
 
 	return 0;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 999835b..656222f 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -782,6 +782,10 @@ retry:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
 static int
 event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
@@ -794,6 +798,17 @@ event_sched_in(struct perf_event *event,
 
 	event->state = PERF_EVENT_STATE_ACTIVE;
 	event->oncpu = smp_processor_id();
+
+	/*
+	 * Unthrottle events, since we scheduled we might have missed several
+	 * ticks already, also for a heavily scheduling task there is little
+	 * guarantee it'll get a tick in a timely manner.
+	 */
+	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+		perf_log_throttle(event, 1);
+		event->hw.interrupts = 0;
+	}
+
 	/*
 	 * The new state must be visible before we turn it on in the hardware:
 	 */
@@ -1596,10 +1611,6 @@ void __perf_event_task_sched_in(struct task_struct *task)
 	}
 }
 
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	u64 frequency = event->attr.sample_freq;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-02-15 16:58 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-02-15 16:58 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Ari Kauppi (2):
      oprofile: Fix usage of CONFIG_HW_PERF_EVENTS for oprofile_perf_init and friends
      ARM: oprofile: Fix backtraces in timer mode

Arnaldo Carvalho de Melo (1):
      perf tools: Fix thread_map event synthesizing in top and record

Don Zickus (1):
      watchdog, nmi: Lower the severity of error messages

Peter Zijlstra (1):
      x86: Fix text_poke_smp_batch() deadlock


 arch/arm/oprofile/common.c    |   12 ++----------
 arch/x86/kernel/alternative.c |    2 +-
 include/linux/oprofile.h      |   13 +++++++++++--
 kernel/watchdog.c             |   10 ++++++++--
 tools/perf/builtin-record.c   |    4 ++--
 tools/perf/builtin-top.c      |    2 +-
 tools/perf/util/event.c       |   18 +++++++++++++-----
 tools/perf/util/event.h       |    6 ++++--
 8 files changed, 42 insertions(+), 25 deletions(-)

diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 8aa9744..2b66391 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -10,8 +10,6 @@
  */
 
 #include <linux/cpumask.h>
-#include <linux/err.h>
-#include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/oprofile.h>
@@ -46,6 +44,7 @@ char *op_name_from_perf_id(void)
 		return NULL;
 	}
 }
+#endif
 
 static int report_trace(struct stackframe *frame, void *d)
 {
@@ -111,6 +110,7 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth)
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
+	/* provide backtrace support also in timer mode: */
 	ops->backtrace		= arm_backtrace;
 
 	return oprofile_perf_init(ops);
@@ -120,11 +120,3 @@ void __exit oprofile_arch_exit(void)
 {
 	oprofile_perf_exit();
 }
-#else
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
-	pr_info("oprofile: hardware counters not available\n");
-	return -ENODEV;
-}
-void __exit oprofile_arch_exit(void) {}
-#endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 1236085..7038b95 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -671,7 +671,7 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 
 	atomic_set(&stop_machine_first, 1);
 	wrote_text = 0;
-	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 }
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 32fb812..1ca6411 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/printk.h>
 #include <asm/atomic.h>
  
 /* Each escaped entry is prefixed by ESCAPE_CODE
@@ -186,10 +188,17 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val);
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_HW_PERF_EVENTS
 int __init oprofile_perf_init(struct oprofile_operations *ops);
 void oprofile_perf_exit(void);
 char *op_name_from_perf_id(void);
-#endif /* CONFIG_PERF_EVENTS */
+#else
+static inline int __init oprofile_perf_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
+}
+static inline void oprofile_perf_exit(void) { }
+#endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* OPROFILE_H */
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f37f974..18bb157 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -363,8 +363,14 @@ static int watchdog_nmi_enable(int cpu)
 		goto out_save;
 	}
 
-	printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
-	       cpu, PTR_ERR(event));
+
+	/* vary the KERN level based on the returned errno */
+	if (PTR_ERR(event) == -EOPNOTSUPP)
+		printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+	else if (PTR_ERR(event) == -ENOENT)
+		printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu);
+	else
+		printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event));
 	return PTR_ERR(event);
 
 	/* success path */
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b2f729f..60cac6f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -759,8 +759,8 @@ static int __cmd_record(int argc, const char **argv)
 		perf_session__process_machines(session, event__synthesize_guest_os);
 
 	if (!system_wide)
-		event__synthesize_thread(target_tid, process_synthesized_event,
-					 session);
+		event__synthesize_thread_map(threads, process_synthesized_event,
+					     session);
 	else
 		event__synthesize_threads(process_synthesized_event, session);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b6998e0..5a29d9c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1306,7 +1306,7 @@ static int __cmd_top(void)
 		return -ENOMEM;
 
 	if (target_tid != -1)
-		event__synthesize_thread(target_tid, event__process, session);
+		event__synthesize_thread_map(threads, event__process, session);
 	else
 		event__synthesize_threads(event__process, session);
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1478ab4..50d0a93 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -263,11 +263,12 @@ static int __event__synthesize_thread(event_t *comm_event, event_t *mmap_event,
 					     process, session);
 }
 
-int event__synthesize_thread(pid_t pid, event__handler_t process,
-			     struct perf_session *session)
+int event__synthesize_thread_map(struct thread_map *threads,
+				 event__handler_t process,
+				 struct perf_session *session)
 {
 	event_t *comm_event, *mmap_event;
-	int err = -1;
+	int err = -1, thread;
 
 	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
 	if (comm_event == NULL)
@@ -277,8 +278,15 @@ int event__synthesize_thread(pid_t pid, event__handler_t process,
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
-	err = __event__synthesize_thread(comm_event, mmap_event, pid,
-					 process, session);
+	err = 0;
+	for (thread = 0; thread < threads->nr; ++thread) {
+		if (__event__synthesize_thread(comm_event, mmap_event,
+					       threads->map[thread],
+					       process, session)) {
+			err = -1;
+			break;
+		}
+	}
 	free(mmap_event);
 out_free_comm:
 	free(comm_event);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 2b7e919..cc7b52f 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -135,14 +135,16 @@ typedef union event_union {
 void event__print_totals(void);
 
 struct perf_session;
+struct thread_map;
 
 typedef int (*event__handler_synth_t)(event_t *event, 
 				      struct perf_session *session);
 typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
 				struct perf_session *session);
 
-int event__synthesize_thread(pid_t pid, event__handler_t process,
-			     struct perf_session *session);
+int event__synthesize_thread_map(struct thread_map *threads,
+				 event__handler_t process,
+				 struct perf_session *session);
 int event__synthesize_threads(event__handler_t process,
 			      struct perf_session *session);
 int event__synthesize_kernel_mmap(event__handler_t process,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-02-06 11:27 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-02-06 11:27 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf stat: Fix aggreate counter reading accounting

Mathieu Desnoyers (1):
      tracepoints: Fix section alignment using pointer array

Steven Rostedt (2):
      tracing: Replace trace_event struct array with pointer array
      tracing: Replace syscall_meta_data struct array with pointer array


 include/asm-generic/vmlinux.lds.h |   24 ++++++++++++------------
 include/linux/module.h            |    4 ++--
 include/linux/syscalls.h          |   28 +++++++++++++++-------------
 include/linux/tracepoint.h        |   35 ++++++++++++++++++++---------------
 include/trace/ftrace.h            |   24 +++++++++++++-----------
 kernel/module.c                   |   16 ++++++++--------
 kernel/trace/trace_events.c       |   12 ++++++------
 kernel/trace/trace_export.c       |    6 +++---
 kernel/trace/trace_syscalls.c     |   19 ++++++++++---------
 kernel/tracepoint.c               |   31 ++++++++++++++++---------------
 tools/perf/util/evsel.c           |    2 +-
 11 files changed, 106 insertions(+), 95 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 6ebb810..fe77e33 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -124,7 +124,8 @@
 #endif
 
 #ifdef CONFIG_EVENT_TRACING
-#define FTRACE_EVENTS()	VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
+#define FTRACE_EVENTS()	. = ALIGN(8);					\
+			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
 			*(_ftrace_events)				\
 			VMLINUX_SYMBOL(__stop_ftrace_events) = .;
 #else
@@ -140,7 +141,8 @@
 #endif
 
 #ifdef CONFIG_FTRACE_SYSCALLS
-#define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .;	\
+#define TRACE_SYSCALLS() . = ALIGN(8);					\
+			 VMLINUX_SYMBOL(__start_syscalls_metadata) = .;	\
 			 *(__syscalls_metadata)				\
 			 VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
 #else
@@ -165,10 +167,8 @@
 	CPU_KEEP(exit.data)						\
 	MEM_KEEP(init.data)						\
 	MEM_KEEP(exit.data)						\
-	. = ALIGN(32);							\
-	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
+	STRUCT_ALIGN();							\
 	*(__tracepoints)						\
-	VMLINUX_SYMBOL(__stop___tracepoints) = .;			\
 	/* implement dynamic printk debug */				\
 	. = ALIGN(8);							\
 	VMLINUX_SYMBOL(__start___verbose) = .;                          \
@@ -176,13 +176,7 @@
 	VMLINUX_SYMBOL(__stop___verbose) = .;				\
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
-	TRACE_PRINTKS()							\
-									\
-	STRUCT_ALIGN();							\
-	FTRACE_EVENTS()							\
-									\
-	STRUCT_ALIGN();							\
-	TRACE_SYSCALLS()
+	TRACE_PRINTKS()
 
 /*
  * Data section helpers
@@ -220,6 +214,10 @@
 		VMLINUX_SYMBOL(__start_rodata) = .;			\
 		*(.rodata) *(.rodata.*)					\
 		*(__vermagic)		/* Kernel version magic */	\
+		. = ALIGN(8);						\
+		VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .;		\
+		*(__tracepoints_ptrs)	/* Tracepoints: pointer array */\
+		VMLINUX_SYMBOL(__stop___tracepoints_ptrs) = .;		\
 		*(__markers_strings)	/* Markers: strings */		\
 		*(__tracepoints_strings)/* Tracepoints: strings */	\
 	}								\
@@ -482,6 +480,8 @@
 	KERNEL_CTORS()							\
 	*(.init.rodata)							\
 	MCOUNT_REC()							\
+	FTRACE_EVENTS()							\
+	TRACE_SYSCALLS()						\
 	DEV_DISCARD(init.rodata)					\
 	CPU_DISCARD(init.rodata)					\
 	MEM_DISCARD(init.rodata)					\
diff --git a/include/linux/module.h b/include/linux/module.h
index e7c6385..9bdf27c 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -377,7 +377,7 @@ struct module
 	   keeping pointers to this stuff */
 	char *args;
 #ifdef CONFIG_TRACEPOINTS
-	struct tracepoint *tracepoints;
+	struct tracepoint * const *tracepoints_ptrs;
 	unsigned int num_tracepoints;
 #endif
 #ifdef HAVE_JUMP_LABEL
@@ -389,7 +389,7 @@ struct module
 	unsigned int num_trace_bprintk_fmt;
 #endif
 #ifdef CONFIG_EVENT_TRACING
-	struct ftrace_event_call *trace_events;
+	struct ftrace_event_call **trace_events;
 	unsigned int num_trace_events;
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 18cd068..98664db 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -125,39 +125,37 @@ extern struct trace_event_functions enter_syscall_print_funcs;
 extern struct trace_event_functions exit_syscall_print_funcs;
 
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
-	static struct syscall_metadata					\
-	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
+	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call __used				\
-	  __attribute__((__aligned__(4)))				\
-	  __attribute__((section("_ftrace_events")))			\
 	  event_enter_##sname = {					\
 		.name                   = "sys_enter"#sname,		\
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
 	};								\
+	static struct ftrace_event_call __used				\
+	  __attribute__((section("_ftrace_events")))			\
+	 *__event_enter_##sname = &event_enter_##sname;			\
 	__TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
-	static struct syscall_metadata					\
-	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
+	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call __used				\
-	  __attribute__((__aligned__(4)))				\
-	  __attribute__((section("_ftrace_events")))			\
 	  event_exit_##sname = {					\
 		.name                   = "sys_exit"#sname,		\
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
 	};								\
+	static struct ftrace_event_call __used				\
+	  __attribute__((section("_ftrace_events")))			\
+	*__event_exit_##sname = &event_exit_##sname;			\
 	__TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\
 	SYSCALL_TRACE_EXIT_EVENT(sname);			\
 	static struct syscall_metadata __used			\
-	  __attribute__((__aligned__(4)))			\
-	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta_##sname = {				\
 		.name 		= "sys"#sname,			\
 		.nb_args 	= nb,				\
@@ -166,14 +164,15 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.enter_event	= &event_enter_##sname,		\
 		.exit_event	= &event_exit_##sname,		\
 		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
-	};
+	};							\
+	static struct syscall_metadata __used			\
+	  __attribute__((section("__syscalls_metadata")))	\
+	 *__p_syscall_meta_##sname = &__syscall_meta_##sname;
 
 #define SYSCALL_DEFINE0(sname)					\
 	SYSCALL_TRACE_ENTER_EVENT(_##sname);			\
 	SYSCALL_TRACE_EXIT_EVENT(_##sname);			\
 	static struct syscall_metadata __used			\
-	  __attribute__((__aligned__(4)))			\
-	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta__##sname = {				\
 		.name 		= "sys_"#sname,			\
 		.nb_args 	= 0,				\
@@ -181,6 +180,9 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.exit_event	= &event_exit__##sname,		\
 		.enter_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \
 	};							\
+	static struct syscall_metadata __used			\
+	  __attribute__((section("__syscalls_metadata")))	\
+	 *__p_syscall_meta_##sname = &__syscall_meta__##sname;	\
 	asmlinkage long sys_##sname(void)
 #else
 #define SYSCALL_DEFINE0(name)	   asmlinkage long sys_##name(void)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index c681461..97c84a5 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -33,12 +33,7 @@ struct tracepoint {
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
-} __attribute__((aligned(32)));		/*
-					 * Aligned on 32 bytes because it is
-					 * globally visible and gcc happily
-					 * align these on the structure size.
-					 * Keep in sync with vmlinux.lds.h.
-					 */
+};
 
 /*
  * Connect a probe to a tracepoint.
@@ -61,15 +56,15 @@ extern void tracepoint_probe_update_all(void);
 
 struct tracepoint_iter {
 	struct module *module;
-	struct tracepoint *tracepoint;
+	struct tracepoint * const *tracepoint;
 };
 
 extern void tracepoint_iter_start(struct tracepoint_iter *iter);
 extern void tracepoint_iter_next(struct tracepoint_iter *iter);
 extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
 extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
-extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
-	struct tracepoint *begin, struct tracepoint *end);
+extern int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
+	struct tracepoint * const *begin, struct tracepoint * const *end);
 
 /*
  * tracepoint_synchronize_unregister must be called between the last tracepoint
@@ -84,11 +79,13 @@ static inline void tracepoint_synchronize_unregister(void)
 #define PARAMS(args...) args
 
 #ifdef CONFIG_TRACEPOINTS
-extern void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end);
+extern
+void tracepoint_update_probe_range(struct tracepoint * const *begin,
+	struct tracepoint * const *end);
 #else
-static inline void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end)
+static inline
+void tracepoint_update_probe_range(struct tracepoint * const *begin,
+	struct tracepoint * const *end)
 { }
 #endif /* CONFIG_TRACEPOINTS */
 
@@ -174,12 +171,20 @@ do_trace:								\
 	{								\
 	}
 
+/*
+ * We have no guarantee that gcc and the linker won't up-align the tracepoint
+ * structures, so we create an array of pointers that will be used for iteration
+ * on the tracepoints.
+ */
 #define DEFINE_TRACE_FN(name, reg, unreg)				\
 	static const char __tpstrtab_##name[]				\
 	__attribute__((section("__tracepoints_strings"))) = #name;	\
 	struct tracepoint __tracepoint_##name				\
-	__attribute__((section("__tracepoints"), aligned(32))) =	\
-		{ __tpstrtab_##name, 0, reg, unreg, NULL }
+	__attribute__((section("__tracepoints"))) =			\
+		{ __tpstrtab_##name, 0, reg, unreg, NULL };		\
+	static struct tracepoint * const __tracepoint_ptr_##name __used	\
+	__attribute__((section("__tracepoints_ptrs"))) =		\
+		&__tracepoint_##name;
 
 #define DEFINE_TRACE(name)						\
 	DEFINE_TRACE_FN(name, NULL, NULL);
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index e16610c..3e68366 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -446,14 +446,16 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *	.reg			= ftrace_event_reg,
  * };
  *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
+ * static struct ftrace_event_call event_<call> = {
  *	.name			= "<call>",
  *	.class			= event_class_<template>,
  *	.event			= &ftrace_event_type_<call>,
  *	.print_fmt		= print_fmt_<call>,
  * };
+ * // its only safe to use pointers when doing linker tricks to
+ * // create an array.
+ * static struct ftrace_event_call __used
+ * __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
  *
  */
 
@@ -579,28 +581,28 @@ static struct ftrace_event_class __used event_class_##call = {		\
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
 									\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
+static struct ftrace_event_call __used event_##call = {			\
 	.name			= #call,				\
 	.class			= &event_class_##template,		\
 	.event.funcs		= &ftrace_event_type_funcs_##template,	\
 	.print_fmt		= print_fmt_##template,			\
-};
+};									\
+static struct ftrace_event_call __used					\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
 									\
 static const char print_fmt_##call[] = print;				\
 									\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
+static struct ftrace_event_call __used event_##call = {			\
 	.name			= #call,				\
 	.class			= &event_class_##template,		\
 	.event.funcs		= &ftrace_event_type_funcs_##call,	\
 	.print_fmt		= print_fmt_##call,			\
-}
+};									\
+static struct ftrace_event_call __used					\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
diff --git a/kernel/module.c b/kernel/module.c
index 34e00b7..efa290e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2460,9 +2460,9 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 #endif
 
 #ifdef CONFIG_TRACEPOINTS
-	mod->tracepoints = section_objs(info, "__tracepoints",
-					sizeof(*mod->tracepoints),
-					&mod->num_tracepoints);
+	mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs",
+					     sizeof(*mod->tracepoints_ptrs),
+					     &mod->num_tracepoints);
 #endif
 #ifdef HAVE_JUMP_LABEL
 	mod->jump_entries = section_objs(info, "__jump_table",
@@ -3393,7 +3393,7 @@ void module_layout(struct module *mod,
 		   struct modversion_info *ver,
 		   struct kernel_param *kp,
 		   struct kernel_symbol *ks,
-		   struct tracepoint *tp)
+		   struct tracepoint * const *tp)
 {
 }
 EXPORT_SYMBOL(module_layout);
@@ -3407,8 +3407,8 @@ void module_update_tracepoints(void)
 	mutex_lock(&module_mutex);
 	list_for_each_entry(mod, &modules, list)
 		if (!mod->taints)
-			tracepoint_update_probe_range(mod->tracepoints,
-				mod->tracepoints + mod->num_tracepoints);
+			tracepoint_update_probe_range(mod->tracepoints_ptrs,
+				mod->tracepoints_ptrs + mod->num_tracepoints);
 	mutex_unlock(&module_mutex);
 }
 
@@ -3432,8 +3432,8 @@ int module_get_iter_tracepoints(struct tracepoint_iter *iter)
 			else if (iter_mod > iter->module)
 				iter->tracepoint = NULL;
 			found = tracepoint_get_iter_range(&iter->tracepoint,
-				iter_mod->tracepoints,
-				iter_mod->tracepoints
+				iter_mod->tracepoints_ptrs,
+				iter_mod->tracepoints_ptrs
 					+ iter_mod->num_tracepoints);
 			if (found) {
 				iter->module = iter_mod;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 35fde09..5f499e0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1284,7 +1284,7 @@ trace_create_file_ops(struct module *mod)
 static void trace_module_add_events(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops = NULL;
-	struct ftrace_event_call *call, *start, *end;
+	struct ftrace_event_call **call, **start, **end;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -1297,7 +1297,7 @@ static void trace_module_add_events(struct module *mod)
 		return;
 
 	for_each_event(call, start, end) {
-		__trace_add_event_call(call, mod,
+		__trace_add_event_call(*call, mod,
 				       &file_ops->id, &file_ops->enable,
 				       &file_ops->filter, &file_ops->format);
 	}
@@ -1367,8 +1367,8 @@ static struct notifier_block trace_module_nb = {
 	.priority = 0,
 };
 
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
+extern struct ftrace_event_call *__start_ftrace_events[];
+extern struct ftrace_event_call *__stop_ftrace_events[];
 
 static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
 
@@ -1384,7 +1384,7 @@ __setup("trace_event=", setup_trace_event);
 
 static __init int event_trace_init(void)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_call **call;
 	struct dentry *d_tracer;
 	struct dentry *entry;
 	struct dentry *d_events;
@@ -1430,7 +1430,7 @@ static __init int event_trace_init(void)
 		pr_warning("tracing: Failed to allocate common fields");
 
 	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
-		__trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+		__trace_add_event_call(*call, NULL, &ftrace_event_id_fops,
 				       &ftrace_enable_fops,
 				       &ftrace_event_filter_fops,
 				       &ftrace_event_format_fops);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4b74d71..bbeec31 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -161,13 +161,13 @@ struct ftrace_event_class event_class_ftrace_##call = {			\
 	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
 };									\
 									\
-struct ftrace_event_call __used						\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
+struct ftrace_event_call __used event_##call = {			\
 	.name			= #call,				\
 	.event.type		= etype,				\
 	.class			= &event_class_ftrace_##call,		\
 	.print_fmt		= print,				\
 };									\
+struct ftrace_event_call __used						\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 
 #include "trace_entries.h"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index b706529..5c9fe08 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -55,20 +55,21 @@ struct ftrace_event_class event_class_syscall_exit = {
 	.raw_init	= init_syscall_trace,
 };
 
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
+extern struct syscall_metadata *__start_syscalls_metadata[];
+extern struct syscall_metadata *__stop_syscalls_metadata[];
 
 static struct syscall_metadata **syscalls_metadata;
 
-static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+static __init struct syscall_metadata *
+find_syscall_meta(unsigned long syscall)
 {
-	struct syscall_metadata *start;
-	struct syscall_metadata *stop;
+	struct syscall_metadata **start;
+	struct syscall_metadata **stop;
 	char str[KSYM_SYMBOL_LEN];
 
 
-	start = (struct syscall_metadata *)__start_syscalls_metadata;
-	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	start = __start_syscalls_metadata;
+	stop = __stop_syscalls_metadata;
 	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
 
 	for ( ; start < stop; start++) {
@@ -78,8 +79,8 @@ static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
 		 * with "SyS" instead of "sys", leading to an unwanted
 		 * mismatch.
 		 */
-		if (start->name && !strcmp(start->name + 3, str + 3))
-			return start;
+		if ((*start)->name && !strcmp((*start)->name + 3, str + 3))
+			return *start;
 	}
 	return NULL;
 }
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index e95ee7f..68187af 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -27,8 +27,8 @@
 #include <linux/sched.h>
 #include <linux/jump_label.h>
 
-extern struct tracepoint __start___tracepoints[];
-extern struct tracepoint __stop___tracepoints[];
+extern struct tracepoint * const __start___tracepoints_ptrs[];
+extern struct tracepoint * const __stop___tracepoints_ptrs[];
 
 /* Set to 1 to enable tracepoint debug output */
 static const int tracepoint_debug;
@@ -298,10 +298,10 @@ static void disable_tracepoint(struct tracepoint *elem)
  *
  * Updates the probe callback corresponding to a range of tracepoints.
  */
-void
-tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
+void tracepoint_update_probe_range(struct tracepoint * const *begin,
+				   struct tracepoint * const *end)
 {
-	struct tracepoint *iter;
+	struct tracepoint * const *iter;
 	struct tracepoint_entry *mark_entry;
 
 	if (!begin)
@@ -309,12 +309,12 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
 
 	mutex_lock(&tracepoints_mutex);
 	for (iter = begin; iter < end; iter++) {
-		mark_entry = get_tracepoint(iter->name);
+		mark_entry = get_tracepoint((*iter)->name);
 		if (mark_entry) {
-			set_tracepoint(&mark_entry, iter,
+			set_tracepoint(&mark_entry, *iter,
 					!!mark_entry->refcount);
 		} else {
-			disable_tracepoint(iter);
+			disable_tracepoint(*iter);
 		}
 	}
 	mutex_unlock(&tracepoints_mutex);
@@ -326,8 +326,8 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
 static void tracepoint_update_probes(void)
 {
 	/* Core kernel tracepoints */
-	tracepoint_update_probe_range(__start___tracepoints,
-		__stop___tracepoints);
+	tracepoint_update_probe_range(__start___tracepoints_ptrs,
+		__stop___tracepoints_ptrs);
 	/* tracepoints in modules. */
 	module_update_tracepoints();
 }
@@ -514,8 +514,8 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
  * Will return the first tracepoint in the range if the input tracepoint is
  * NULL.
  */
-int tracepoint_get_iter_range(struct tracepoint **tracepoint,
-	struct tracepoint *begin, struct tracepoint *end)
+int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
+	struct tracepoint * const *begin, struct tracepoint * const *end)
 {
 	if (!*tracepoint && begin != end) {
 		*tracepoint = begin;
@@ -534,7 +534,8 @@ static void tracepoint_get_iter(struct tracepoint_iter *iter)
 	/* Core kernel tracepoints */
 	if (!iter->module) {
 		found = tracepoint_get_iter_range(&iter->tracepoint,
-				__start___tracepoints, __stop___tracepoints);
+				__start___tracepoints_ptrs,
+				__stop___tracepoints_ptrs);
 		if (found)
 			goto end;
 	}
@@ -585,8 +586,8 @@ int tracepoint_module_notify(struct notifier_block *self,
 	switch (val) {
 	case MODULE_STATE_COMING:
 	case MODULE_STATE_GOING:
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
+		tracepoint_update_probe_range(mod->tracepoints_ptrs,
+			mod->tracepoints_ptrs + mod->num_tracepoints);
 		break;
 	}
 	return 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f5cfed6..d8575d3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -90,7 +90,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	int cpu, thread;
 	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
 
-	aggr->val = 0;
+	aggr->val = aggr->ena = aggr->run = 0;
 
 	for (cpu = 0; cpu < ncpus; cpu++) {
 		for (thread = 0; thread < nthreads; thread++) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-02-03 15:47 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-02-03 15:47 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Steven Rostedt, Frédéric Weisbecker,
	Andrew Morton


Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Eric Dumazet (1):
      perf: Fix alloc_callchain_buffers()

Marcin Slusarz (3):
      watchdog: Fix broken nowatchdog logic
      watchdog: Fix sysctl consistency
      watchdog: Don't change watchdog state on read of sysctl

Peter Zijlstra (1):
      perf: Fix reading in perf_event_read()

Stephane Eranian (1):
      perf: Fix Pentium4 raw event validation


 arch/x86/kernel/cpu/perf_event_p4.c |   12 ++++++++-
 kernel/perf_event.c                 |   10 ++++----
 kernel/watchdog.c                   |   43 +++++++++++++++-------------------
 3 files changed, 34 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index e56b9bf..f7a0993 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -682,7 +682,7 @@ static int p4_validate_raw_event(struct perf_event *event)
 	 * if an event is shared accross the logical threads
 	 * the user needs special permissions to be able to use it
 	 */
-	if (p4_event_bind_map[v].shared) {
+	if (p4_ht_active() && p4_event_bind_map[v].shared) {
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return -EACCES;
 	}
@@ -727,7 +727,8 @@ static int p4_hw_config(struct perf_event *event)
 		event->hw.config = p4_set_ht_bit(event->hw.config);
 
 	if (event->attr.type == PERF_TYPE_RAW) {
-
+		struct p4_event_bind *bind;
+		unsigned int esel;
 		/*
 		 * Clear bits we reserve to be managed by kernel itself
 		 * and never allowed from a user space
@@ -743,6 +744,13 @@ static int p4_hw_config(struct perf_event *event)
 		 * bits since we keep additional info here (for cache events and etc)
 		 */
 		event->hw.config |= event->attr.config;
+		bind = p4_config_get_bind(event->attr.config);
+		if (!bind) {
+			rc = -EINVAL;
+			goto out;
+		}
+		esel = P4_OPCODE_ESEL(bind->opcode);
+		event->hw.config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel));
 	}
 
 	rc = x86_setup_perfctr(event);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 126a302..999835b 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1901,11 +1901,12 @@ static void __perf_event_read(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	update_context_time(ctx);
+	if (ctx->is_active)
+		update_context_time(ctx);
 	update_event_times(event);
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		event->pmu->read(event);
 	raw_spin_unlock(&ctx->lock);
-
-	event->pmu->read(event);
 }
 
 static inline u64 perf_event_count(struct perf_event *event)
@@ -1999,8 +2000,7 @@ static int alloc_callchain_buffers(void)
 	 * accessed from NMI. Use a temporary manual per cpu allocation
 	 * until that gets sorted out.
 	 */
-	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
-		num_possible_cpus();
+	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
 
 	entries = kzalloc(size, GFP_KERNEL);
 	if (!entries)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d7ebdf4..f37f974 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -27,7 +27,7 @@
 #include <asm/irq_regs.h>
 #include <linux/perf_event.h>
 
-int watchdog_enabled;
+int watchdog_enabled = 1;
 int __read_mostly softlockup_thresh = 60;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 
-static int no_watchdog;
-
-
 /* boot commands */
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
@@ -58,7 +55,7 @@ static int __init hardlockup_panic_setup(char *str)
 	if (!strncmp(str, "panic", 5))
 		hardlockup_panic = 1;
 	else if (!strncmp(str, "0", 1))
-		no_watchdog = 1;
+		watchdog_enabled = 0;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -77,7 +74,7 @@ __setup("softlockup_panic=", softlockup_panic_setup);
 
 static int __init nowatchdog_setup(char *str)
 {
-	no_watchdog = 1;
+	watchdog_enabled = 0;
 	return 1;
 }
 __setup("nowatchdog", nowatchdog_setup);
@@ -85,7 +82,7 @@ __setup("nowatchdog", nowatchdog_setup);
 /* deprecated */
 static int __init nosoftlockup_setup(char *str)
 {
-	no_watchdog = 1;
+	watchdog_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
@@ -432,9 +429,6 @@ static int watchdog_enable(int cpu)
 		wake_up_process(p);
 	}
 
-	/* if any cpu succeeds, watchdog is considered enabled for the system */
-	watchdog_enabled = 1;
-
 	return 0;
 }
 
@@ -462,12 +456,16 @@ static void watchdog_disable(int cpu)
 static void watchdog_enable_all_cpus(void)
 {
 	int cpu;
-	int result = 0;
+
+	watchdog_enabled = 0;
 
 	for_each_online_cpu(cpu)
-		result += watchdog_enable(cpu);
+		if (!watchdog_enable(cpu))
+			/* if any cpu succeeds, watchdog is considered
+			   enabled for the system */
+			watchdog_enabled = 1;
 
-	if (result)
+	if (!watchdog_enabled)
 		printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n");
 
 }
@@ -476,9 +474,6 @@ static void watchdog_disable_all_cpus(void)
 {
 	int cpu;
 
-	if (no_watchdog)
-		return;
-
 	for_each_online_cpu(cpu)
 		watchdog_disable(cpu);
 
@@ -498,10 +493,12 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write,
 {
 	proc_dointvec(table, write, buffer, length, ppos);
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
+	if (write) {
+		if (watchdog_enabled)
+			watchdog_enable_all_cpus();
+		else
+			watchdog_disable_all_cpus();
+	}
 	return 0;
 }
 
@@ -530,7 +527,8 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		err = watchdog_enable(hotcpu);
+		if (watchdog_enabled)
+			err = watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
@@ -555,9 +553,6 @@ void __init lockup_detector_init(void)
 	void *cpu = (void *)(long)smp_processor_id();
 	int err;
 
-	if (no_watchdog)
-		return;
-
 	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
 	WARN_ON(notifier_to_errno(err));
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 22:00             ` Arnaldo Carvalho de Melo
@ 2011-01-25  0:16               ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-25  0:16 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton


* Arnaldo Carvalho de Melo <acme@redhat.com> wrote:

> Em Mon, Jan 24, 2011 at 10:25:26PM +0100, Ingo Molnar escreveu:
> > * Arnaldo Carvalho de Melo <acme@redhat.com> wrote:
> > > Was this on a freshly installed machine? Or on a freshly updated one?
> > > 
> > > Probably its the build-id collecting at the end of a session, on the
> > > first run you had a cold cache and it had to figure out which binaries
> > > to cache on ~/.debug, second time it was already cached so it was fast.
> > 
> > Hm, it would be nice to not surprise users with an unlimited-timeout, up to half a 
> > minute 'frozen' app. Can we possibly display a more finegrained progress indicator?
> 
> Definetely, adding this to the todo list.
> 
> In fact perf_session__process_events already has an ui_progress stuff,
> its just that it works only on report/TUI. Need to make it work with
> some /-|/- spinning text progress indicator after a "collecting
> build-ids:" string, something like that.

Yeah, something like that would awesome!

No need for it to be particularly pretty or complex - just _some_ minimal feedback 
to the user gives us most of the bang for the buck already.

( And, of course, the best solution is to make it all run even faster. When it comes
  to debuginfo data structures i can not prevent myself from thinking 'bloat!' ;-)

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 21:25           ` Ingo Molnar
@ 2011-01-24 22:00             ` Arnaldo Carvalho de Melo
  2011-01-25  0:16               ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-01-24 22:00 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Em Mon, Jan 24, 2011 at 10:25:26PM +0100, Ingo Molnar escreveu:
> * Arnaldo Carvalho de Melo <acme@redhat.com> wrote:
> > Was this on a freshly installed machine? Or on a freshly updated one?
> > 
> > Probably its the build-id collecting at the end of a session, on the
> > first run you had a cold cache and it had to figure out which binaries
> > to cache on ~/.debug, second time it was already cached so it was fast.
> 
> Hm, it would be nice to not surprise users with an unlimited-timeout, up to half a 
> minute 'frozen' app. Can we possibly display a more finegrained progress indicator?

Definetely, adding this to the todo list.

In fact perf_session__process_events already has an ui_progress stuff,
its just that it works only on report/TUI. Need to make it work with
some /-|/- spinning text progress indicator after a "collecting
build-ids:" string, something like that.

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:38         ` Arnaldo Carvalho de Melo
  2011-01-24 21:13           ` Linus Torvalds
@ 2011-01-24 21:25           ` Ingo Molnar
  2011-01-24 22:00             ` Arnaldo Carvalho de Melo
  1 sibling, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2011-01-24 21:25 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Linus Torvalds, linux-kernel, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton


* Arnaldo Carvalho de Melo <acme@redhat.com> wrote:

> Em Tue, Jan 25, 2011 at 06:27:31AM +1000, Linus Torvalds escreveu:
> > On Tue, Jan 25, 2011 at 6:17 AM, Linus Torvalds
> > <torvalds@linux-foundation.org> wrote:
> > >
> > > It only happens for me with "g". With "perf record -af sleep 10" it worked.
> > 
> > Actually, it's something subtler than that. It must depend on the
> > actual data, because now when I tried it again, it worked with 'g'
> > too. I hadn't saved the old perf.data that caused the lockup (it got
> > overwritten by the non-g test), and now when I try to re-create it it
> > doesn't hang on the result.
> > 
> > So it's probably some very specific data pattern that causes it.
> > 
> > (And I don't know if it's a hard hang - it could just be something
> > _very_ slow. But we're talking half a minute kind of slow).
> 
> Was this on a freshly installed machine? Or on a freshly updated one?
> 
> Probably its the build-id collecting at the end of a session, on the
> first run you had a cold cache and it had to figure out which binaries
> to cache on ~/.debug, second time it was already cached so it was fast.

Hm, it would be nice to not surprise users with an unlimited-timeout, up to half a 
minute 'frozen' app. Can we possibly display a more finegrained progress indicator?

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:38         ` Arnaldo Carvalho de Melo
@ 2011-01-24 21:13           ` Linus Torvalds
  2011-01-24 21:25           ` Ingo Molnar
  1 sibling, 0 replies; 376+ messages in thread
From: Linus Torvalds @ 2011-01-24 21:13 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: Ingo Molnar, linux-kernel, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

On Tue, Jan 25, 2011 at 6:38 AM, Arnaldo Carvalho de Melo
<acme@redhat.com> wrote:
>
> Was this on a freshly installed machine? Or on a freshly updated one?

It is. And the machine is slow too.

> Probably its the build-id collecting at the end of a session, on the
> first run you had a cold cache and it had to figure out which binaries
> to cache on ~/.debug, second time it was already cached so it was fast.

That sounds like a reasonable explanation.

So just ignore this report,

             Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:27       ` Linus Torvalds
@ 2011-01-24 20:38         ` Arnaldo Carvalho de Melo
  2011-01-24 21:13           ` Linus Torvalds
  2011-01-24 21:25           ` Ingo Molnar
  0 siblings, 2 replies; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-01-24 20:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, linux-kernel, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Em Tue, Jan 25, 2011 at 06:27:31AM +1000, Linus Torvalds escreveu:
> On Tue, Jan 25, 2011 at 6:17 AM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
> >
> > It only happens for me with "g". With "perf record -af sleep 10" it worked.
> 
> Actually, it's something subtler than that. It must depend on the
> actual data, because now when I tried it again, it worked with 'g'
> too. I hadn't saved the old perf.data that caused the lockup (it got
> overwritten by the non-g test), and now when I try to re-create it it
> doesn't hang on the result.
> 
> So it's probably some very specific data pattern that causes it.
> 
> (And I don't know if it's a hard hang - it could just be something
> _very_ slow. But we're talking half a minute kind of slow).

Was this on a freshly installed machine? Or on a freshly updated one?

Probably its the build-id collecting at the end of a session, on the
first run you had a cold cache and it had to figure out which binaries
to cache on ~/.debug, second time it was already cached so it was fast.

So one way to try to reproduce would be to:

rm -rf ~/.debug

and then try it again.

To double check, you can try to disable the build-id cache with:

--no-buildid-cache or -N

i.e.:

perf record -afN sleep 10

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:17     ` Linus Torvalds
  2011-01-24 20:27       ` Linus Torvalds
@ 2011-01-24 20:37       ` Davidlohr Bueso
  1 sibling, 0 replies; 376+ messages in thread
From: Davidlohr Bueso @ 2011-01-24 20:37 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, linux-kernel, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Frédéric Weisbecker,
	Steven Rostedt, Thomas Gleixner, Andrew Morton

On Tue, 2011-01-25 at 06:17 +1000, Linus Torvalds wrote:
> On Tue, Jan 25, 2011 at 6:07 AM, Ingo Molnar <mingo@elte.hu> wrote:
> >>
> >>     perf report -agf sleep 10
> >
> > (that's perf record i guess?)
> 
> Eh. Yes,
> 
> >> Is it just me?
> >
> > We used to have such bugs recently so i'm quite sure what you see is real.
> >
> > The above test is almost the same what i did before sending you the pull request, so
> > it's not occuring all the time and on all boxes.
> 
> It only happens for me with "g". With "perf record -af sleep 10" it worked.
> 
> > The distro version on that box you are using would be helpful, plus the build output
> > you get when you build 'tools/perf'. (I.e. which libraries are there. If it comes up
> > empty with no complaints you have all the devel libraries.)
> 
> It's up-to-date Fedora 14 on x86-32.
> 
> And there's no build output at all, except for the trivial:
> 
>   [torvalds@eeepc perf]$ make
>   PERF_VERSION = 2.6.38.rc2.62.gec30f3.dirty
>       GEN common-cmds.h
>       * new build flags or prefix
>       CC perf.o
>       CC builtin-annotate.o
>       CC builtin-bench.o
>       ...
> 

For what it's worth I cant reproduce this either, at least on x86_64
using 2.6.38.rc2.37.g9320a7.

> so I have everything installed.
> 
>                     Linus
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 



^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:17     ` Linus Torvalds
@ 2011-01-24 20:27       ` Linus Torvalds
  2011-01-24 20:38         ` Arnaldo Carvalho de Melo
  2011-01-24 20:37       ` Davidlohr Bueso
  1 sibling, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2011-01-24 20:27 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

On Tue, Jan 25, 2011 at 6:17 AM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> It only happens for me with "g". With "perf record -af sleep 10" it worked.

Actually, it's something subtler than that. It must depend on the
actual data, because now when I tried it again, it worked with 'g'
too. I hadn't saved the old perf.data that caused the lockup (it got
overwritten by the non-g test), and now when I try to re-create it it
doesn't hang on the result.

So it's probably some very specific data pattern that causes it.

(And I don't know if it's a hard hang - it could just be something
_very_ slow. But we're talking half a minute kind of slow).

                     Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:11     ` Ingo Molnar
@ 2011-01-24 20:17       ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-24 20:17 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton


* Ingo Molnar <mingo@elte.hu> wrote:

> 
> * Ingo Molnar <mingo@elte.hu> wrote:
> 
> > The distro version on that box you are using would be helpful, plus the build 
> > output you get when you build 'tools/perf'. (I.e. which libraries are there. If it 
> > comes up empty with no complaints you have all the devel libraries.)
> 
> and a gdb backtrace of the perf report lockup site would be helpful too i suspect.

There's two areas that would be prime suspects: the ELF symbol lookup code, or the 
call-chain code.

Neither is expected to lock up, on arbitrary input of perf.data.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:07   ` Ingo Molnar
  2011-01-24 20:11     ` Ingo Molnar
@ 2011-01-24 20:17     ` Linus Torvalds
  2011-01-24 20:27       ` Linus Torvalds
  2011-01-24 20:37       ` Davidlohr Bueso
  1 sibling, 2 replies; 376+ messages in thread
From: Linus Torvalds @ 2011-01-24 20:17 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

On Tue, Jan 25, 2011 at 6:07 AM, Ingo Molnar <mingo@elte.hu> wrote:
>>
>>     perf report -agf sleep 10
>
> (that's perf record i guess?)

Eh. Yes,

>> Is it just me?
>
> We used to have such bugs recently so i'm quite sure what you see is real.
>
> The above test is almost the same what i did before sending you the pull request, so
> it's not occuring all the time and on all boxes.

It only happens for me with "g". With "perf record -af sleep 10" it worked.

> The distro version on that box you are using would be helpful, plus the build output
> you get when you build 'tools/perf'. (I.e. which libraries are there. If it comes up
> empty with no complaints you have all the devel libraries.)

It's up-to-date Fedora 14 on x86-32.

And there's no build output at all, except for the trivial:

  [torvalds@eeepc perf]$ make
  PERF_VERSION = 2.6.38.rc2.62.gec30f3.dirty
      GEN common-cmds.h
      * new build flags or prefix
      CC perf.o
      CC builtin-annotate.o
      CC builtin-bench.o
      ...

so I have everything installed.

                    Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 19:48 ` Linus Torvalds
  2011-01-24 20:07   ` Ingo Molnar
@ 2011-01-24 20:14   ` Arnaldo Carvalho de Melo
  1 sibling, 0 replies; 376+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-01-24 20:14 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, linux-kernel, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Em Tue, Jan 25, 2011 at 05:48:01AM +1000, Linus Torvalds escreveu:
> On Mon, Jan 24, 2011 at 11:34 PM, Ingo Molnar <mingo@elte.hu> wrote:
> >
> > Please pull the latest perf-fixes-for-linus git tree from:
> >
> >   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus
> 
> I'm not sure if this was true before too, but when I do
> 
>     perf report -agf sleep 10
> 
> while compiling the kernel to get a system profile on x86-32, the
> resulting pef.data file will cause "perf report" to just hang.
> 
> Is it just me?

s/report/record/ :-)

I'm building perf/urgent tooling then kernel on my Acer netbook with a:

model name	: Intel(R) Atom(TM) CPU N270   @ 1.60GHz

To check. It now has 2.6.38-rc1 with my perf/core branch tool/kernel
combo, where I couldn't reproduce the problem.

- Arnaldo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 20:07   ` Ingo Molnar
@ 2011-01-24 20:11     ` Ingo Molnar
  2011-01-24 20:17       ` Ingo Molnar
  2011-01-24 20:17     ` Linus Torvalds
  1 sibling, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2011-01-24 20:11 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton


* Ingo Molnar <mingo@elte.hu> wrote:

> The distro version on that box you are using would be helpful, plus the build 
> output you get when you build 'tools/perf'. (I.e. which libraries are there. If it 
> comes up empty with no complaints you have all the devel libraries.)

and a gdb backtrace of the perf report lockup site would be helpful too i suspect.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 19:48 ` Linus Torvalds
@ 2011-01-24 20:07   ` Ingo Molnar
  2011-01-24 20:11     ` Ingo Molnar
  2011-01-24 20:17     ` Linus Torvalds
  2011-01-24 20:14   ` Arnaldo Carvalho de Melo
  1 sibling, 2 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-24 20:07 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Mon, Jan 24, 2011 at 11:34 PM, Ingo Molnar <mingo@elte.hu> wrote:
> >
> > Please pull the latest perf-fixes-for-linus git tree from:
> >
> >   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus
> 
> I'm not sure if this was true before too, but when I do
> 
>     perf report -agf sleep 10

(that's perf record i guess?)

> 
> while compiling the kernel to get a system profile on x86-32, the
> resulting pef.data file will cause "perf report" to just hang.
> 
> Is it just me?

We used to have such bugs recently so i'm quite sure what you see is real.

The above test is almost the same what i did before sending you the pull request, so 
it's not occuring all the time and on all boxes.

The distro version on that box you are using would be helpful, plus the build output 
you get when you build 'tools/perf'. (I.e. which libraries are there. If it comes up 
empty with no complaints you have all the devel libraries.)

We'll try to reproduce it locally before asking more debug data from you, 
perf.data's can be pretty large to send via email :)

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2011-01-24 13:34 Ingo Molnar
@ 2011-01-24 19:48 ` Linus Torvalds
  2011-01-24 20:07   ` Ingo Molnar
  2011-01-24 20:14   ` Arnaldo Carvalho de Melo
  0 siblings, 2 replies; 376+ messages in thread
From: Linus Torvalds @ 2011-01-24 19:48 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

On Mon, Jan 24, 2011 at 11:34 PM, Ingo Molnar <mingo@elte.hu> wrote:
>
> Please pull the latest perf-fixes-for-linus git tree from:
>
>   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

I'm not sure if this was true before too, but when I do

    perf report -agf sleep 10

while compiling the kernel to get a system profile on x86-32, the
resulting pef.data file will cause "perf report" to just hang.

Is it just me?

                Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-01-24 13:34 Ingo Molnar
  2011-01-24 19:48 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2011-01-24 13:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

The diffstat is larger than usual - in good part due to the PRIx64 format string 
fixes to tools/perf/.

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      powerpc, perf: Fix frequency calculation for overflowing counters (FSL version)

Arnaldo Carvalho de Melo (5):
      perf test: Fix build on older glibcs
      perf tools: Fix 64 bit integer format strings
      perf tools: Add missing header, fixes build
      perf tools: Fix build when using gcc 3.4.6
      perf tools: Fix build by checking if extra warnings are supported

Dr. David Alan Gilbert (1):
      perf symbols: Fix annotation of thumb code

Han Pingtian (1):
      perf test: Use cpu_map->[cpu] when setting affinity

Oleg Nesterov (3):
      perf: Fix find_get_context() vs perf_event_exit_task() race
      perf: Fix perf_event_init_task()/perf_event_free_task() interaction
      perf: perf_event_exit_task_context: s/rcu_dereference/rcu_dereference_raw/

Peter Zijlstra (1):
      perf: Annotate cpuctx->ctx.mutex to avoid a lockdep splat

Thomas Renninger (1):
      perf tools: Fix time function double declaration with glibc


 arch/powerpc/kernel/perf_event_fsl_emb.c |    1 +
 kernel/perf_event.c                      |   46 +++++++++++++++----------
 tools/perf/Makefile                      |    9 ++++-
 tools/perf/builtin-annotate.c            |    6 ++--
 tools/perf/builtin-kmem.c                |    4 +-
 tools/perf/builtin-lock.c                |    6 ++--
 tools/perf/builtin-record.c              |    2 +-
 tools/perf/builtin-report.c              |    2 +-
 tools/perf/builtin-sched.c               |   20 +++++-----
 tools/perf/builtin-script.c              |    6 ++--
 tools/perf/builtin-stat.c                |    4 +-
 tools/perf/builtin-test.c                |   54 +++++++++++++++++------------
 tools/perf/builtin-top.c                 |    9 +++--
 tools/perf/util/event.c                  |    5 ++-
 tools/perf/util/header.c                 |    4 +-
 tools/perf/util/hist.c                   |   17 +++++----
 tools/perf/util/include/linux/bitops.h   |    1 +
 tools/perf/util/map.c                    |    3 +-
 tools/perf/util/parse-events.c           |    2 +-
 tools/perf/util/parse-events.h           |    2 +-
 tools/perf/util/probe-event.c            |    2 +-
 tools/perf/util/session.c                |   28 ++++++++-------
 tools/perf/util/svghelper.c              |    9 +++--
 tools/perf/util/symbol.c                 |   16 +++++++--
 tools/perf/util/types.h                  |   10 +++--
 tools/perf/util/ui/browsers/hists.c      |    2 +-
 tools/perf/util/ui/browsers/map.c        |    5 ++-
 tools/perf/util/values.c                 |   10 +++---
 28 files changed, 164 insertions(+), 121 deletions(-)

diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
index 4dcf5f8..b0dc8f7 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -596,6 +596,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			if (left <= 0)
 				left = period;
 			record = 1;
+			event->hw.last_period = event->hw.sample_period;
 		}
 		if (left < 0x80000000LL)
 			val = 0x80000000LL - left;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 84522c7..126a302 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2201,13 +2201,6 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/*
-	 * Can't attach events to a dying task.
-	 */
-	err = -ESRCH;
-	if (task->flags & PF_EXITING)
-		goto errout;
-
 	/* Reuse ptrace permission checks for now. */
 	err = -EACCES;
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
@@ -2268,14 +2261,27 @@ retry:
 
 		get_ctx(ctx);
 
-		if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
-			/*
-			 * We raced with some other task; use
-			 * the context they set.
-			 */
+		err = 0;
+		mutex_lock(&task->perf_event_mutex);
+		/*
+		 * If it has already passed perf_event_exit_task().
+		 * we must see PF_EXITING, it takes this mutex too.
+		 */
+		if (task->flags & PF_EXITING)
+			err = -ESRCH;
+		else if (task->perf_event_ctxp[ctxn])
+			err = -EAGAIN;
+		else
+			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+		mutex_unlock(&task->perf_event_mutex);
+
+		if (unlikely(err)) {
 			put_task_struct(task);
 			kfree(ctx);
-			goto retry;
+
+			if (err == -EAGAIN)
+				goto retry;
+			goto errout;
 		}
 	}
 
@@ -5374,6 +5380,8 @@ free_dev:
 	goto out;
 }
 
+static struct lock_class_key cpuctx_mutex;
+
 int perf_pmu_register(struct pmu *pmu, char *name, int type)
 {
 	int cpu, ret;
@@ -5422,6 +5430,7 @@ skip_type:
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		__perf_event_init_context(&cpuctx->ctx);
+		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
@@ -6127,7 +6136,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 * scheduled, so we are now safe from rescheduling changing
 	 * our context.
 	 */
-	child_ctx = child->perf_event_ctxp[ctxn];
+	child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
 	task_ctx_sched_out(child_ctx, EVENT_ALL);
 
 	/*
@@ -6440,11 +6449,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	unsigned long flags;
 	int ret = 0;
 
-	child->perf_event_ctxp[ctxn] = NULL;
-
-	mutex_init(&child->perf_event_mutex);
-	INIT_LIST_HEAD(&child->perf_event_list);
-
 	if (likely(!parent->perf_event_ctxp[ctxn]))
 		return 0;
 
@@ -6533,6 +6537,10 @@ int perf_event_init_task(struct task_struct *child)
 {
 	int ctxn, ret;
 
+	memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp));
+	mutex_init(&child->perf_event_mutex);
+	INIT_LIST_HEAD(&child->perf_event_list);
+
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
 		if (ret)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 2b5387d..7141c42 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -204,13 +204,11 @@ EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wshadow
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Winit-self
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wpacked
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wredundant-decls
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstack-protector
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-aliasing=3
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-default
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-enum
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wno-system-headers
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wundef
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wvolatile-register-var
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wwrite-strings
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wbad-function-cast
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-declarations
@@ -294,6 +292,13 @@ ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
 	CFLAGS := $(CFLAGS) -fstack-protector-all
 endif
 
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wstack-protector),y)
+       CFLAGS := $(CFLAGS) -Wstack-protector
+endif
+
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wvolatile-register-var),y)
+       CFLAGS := $(CFLAGS) -Wvolatile-register-var
+endif
 
 ### --- END CONFIGURATION SECTION ---
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index c056cdc..8879463 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -212,7 +212,7 @@ get_source_line(struct hist_entry *he, int len, const char *filename)
 			continue;
 
 		offset = start + i;
-		sprintf(cmd, "addr2line -e %s %016llx", filename, offset);
+		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
 		fp = popen(cmd, "r");
 		if (!fp)
 			continue;
@@ -270,9 +270,9 @@ static void hist_entry__print_hits(struct hist_entry *self)
 
 	for (offset = 0; offset < len; ++offset)
 		if (h->ip[offset] != 0)
-			printf("%*Lx: %Lu\n", BITS_PER_LONG / 2,
+			printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
 			       sym->start + offset, h->ip[offset]);
-	printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
 }
 
 static int hist_entry__tty_annotate(struct hist_entry *he)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index def7ddc..d97256d 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -371,10 +371,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			addr = data->ptr;
 
 		if (sym != NULL)
-			snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
+			snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name,
 				 addr - map->unmap_ip(map, sym->start));
 		else
-			snprintf(buf, sizeof(buf), "%#Lx", addr);
+			snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
 		printf(" %-34s |", buf);
 
 		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index b9c6e54..2b36def 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -782,9 +782,9 @@ static void print_result(void)
 		pr_info("%10u ", st->nr_acquired);
 		pr_info("%10u ", st->nr_contended);
 
-		pr_info("%15llu ", st->wait_time_total);
-		pr_info("%15llu ", st->wait_time_max);
-		pr_info("%15llu ", st->wait_time_min == ULLONG_MAX ?
+		pr_info("%15" PRIu64 " ", st->wait_time_total);
+		pr_info("%15" PRIu64 " ", st->wait_time_max);
+		pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ?
 		       0 : st->wait_time_min);
 		pr_info("\n");
 	}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fcd29e8..b2f729f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -817,7 +817,7 @@ static int __cmd_record(int argc, const char **argv)
 	 * Approximate RIP event size: 24 bytes.
 	 */
 	fprintf(stderr,
-		"[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n",
+		"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
 		(double)bytes_written / 1024.0 / 1024.0,
 		output_name,
 		bytes_written / 24);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 75183a4..c27e31f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -197,7 +197,7 @@ static int process_read_event(event_t *event, struct sample_data *sample __used,
 					   event->read.value);
 	}
 
-	dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid,
+	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
 		    attr ? __event_name(attr->type, attr->config) : "FAIL",
 		    event->read.value);
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 29e7ffd..29acb89 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -193,7 +193,7 @@ static void calibrate_run_measurement_overhead(void)
 	}
 	run_measurement_overhead = min_delta;
 
-	printf("run measurement overhead: %Ld nsecs\n", min_delta);
+	printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static void calibrate_sleep_measurement_overhead(void)
@@ -211,7 +211,7 @@ static void calibrate_sleep_measurement_overhead(void)
 	min_delta -= 10000;
 	sleep_measurement_overhead = min_delta;
 
-	printf("sleep measurement overhead: %Ld nsecs\n", min_delta);
+	printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static struct sched_atom *
@@ -617,13 +617,13 @@ static void test_calibrations(void)
 	burn_nsecs(1e6);
 	T1 = get_nsecs();
 
-	printf("the run test took %Ld nsecs\n", T1-T0);
+	printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
 
 	T0 = get_nsecs();
 	sleep_nsecs(1e6);
 	T1 = get_nsecs();
 
-	printf("the sleep test took %Ld nsecs\n", T1-T0);
+	printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
 }
 
 #define FILL_FIELD(ptr, field, event, data)	\
@@ -816,10 +816,10 @@ replay_switch_event(struct trace_switch_event *switch_event,
 		delta = 0;
 
 	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
+		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 	if (verbose) {
-		printf(" ... switch from %s/%d to %s/%d [ran %Ld nsecs]\n",
+		printf(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
 			switch_event->prev_comm, switch_event->prev_pid,
 			switch_event->next_comm, switch_event->next_pid,
 			delta);
@@ -1048,7 +1048,7 @@ latency_switch_event(struct trace_switch_event *switch_event,
 		delta = 0;
 
 	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
+		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 
 	sched_out = perf_session__findnew(session, switch_event->prev_pid);
@@ -1221,7 +1221,7 @@ static void output_lat_thread(struct work_atoms *work_list)
 
 	avg = work_list->total_lat / work_list->nb_atoms;
 
-	printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
+	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
 	      (double)work_list->total_runtime / 1e6,
 		 work_list->nb_atoms, (double)avg / 1e6,
 		 (double)work_list->max_lat / 1e6,
@@ -1423,7 +1423,7 @@ map_switch_event(struct trace_switch_event *switch_event,
 		delta = 0;
 
 	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
+		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 
 	sched_out = perf_session__findnew(session, switch_event->prev_pid);
@@ -1713,7 +1713,7 @@ static void __cmd_lat(void)
 	}
 
 	printf(" -----------------------------------------------------------------------------------------\n");
-	printf("  TOTAL:                |%11.3f ms |%9Ld |\n",
+	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
 		(double)all_runtime/1e6, all_count);
 
 	printf(" ---------------------------------------------------\n");
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 150a606..b766c2a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -77,8 +77,8 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 	if (session->sample_type & PERF_SAMPLE_RAW) {
 		if (debug_mode) {
 			if (sample->time < last_timestamp) {
-				pr_err("Samples misordered, previous: %llu "
-					"this: %llu\n", last_timestamp,
+				pr_err("Samples misordered, previous: %" PRIu64
+					" this: %" PRIu64 "\n", last_timestamp,
 					sample->time);
 				nr_unordered++;
 			}
@@ -126,7 +126,7 @@ static int __cmd_script(struct perf_session *session)
 	ret = perf_session__process_events(session, &event_ops);
 
 	if (debug_mode)
-		pr_err("Misordered timestamps: %llu\n", nr_unordered);
+		pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
 
 	return ret;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0ff11d9..a482a19 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -206,8 +206,8 @@ static int read_counter_aggr(struct perf_evsel *counter)
 		update_stats(&ps->res_stats[i], count[i]);
 
 	if (verbose) {
-		fprintf(stderr, "%s: %Ld %Ld %Ld\n", event_name(counter),
-				count[0], count[1], count[2]);
+		fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+			event_name(counter), count[0], count[1], count[2]);
 	}
 
 	/*
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index ed56961..5dcdba6 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -146,7 +146,7 @@ next_pair:
 				if (llabs(skew) < page_size)
 					continue;
 
-				pr_debug("%#Lx: diff end addr for %s v: %#Lx k: %#Lx\n",
+				pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
 					 sym->start, sym->name, sym->end, pair->end);
 			} else {
 				struct rb_node *nnd;
@@ -168,11 +168,11 @@ detour:
 					goto detour;
 				}
 
-				pr_debug("%#Lx: diff name v: %s k: %s\n",
+				pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
 					 sym->start, sym->name, pair->name);
 			}
 		} else
-			pr_debug("%#Lx: %s not on kallsyms\n", sym->start, sym->name);
+			pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name);
 
 		err = -1;
 	}
@@ -211,10 +211,10 @@ detour:
 
 		if (pair->start == pos->start) {
 			pair->priv = 1;
-			pr_info(" %Lx-%Lx %Lx %s in kallsyms as",
+			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
 				pos->start, pos->end, pos->pgoff, pos->dso->name);
 			if (pos->pgoff != pair->pgoff || pos->end != pair->end)
-				pr_info(": \n*%Lx-%Lx %Lx",
+				pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "",
 					pair->start, pair->end, pair->pgoff);
 			pr_info(" %s\n", pair->dso->name);
 			pair->priv = 1;
@@ -307,7 +307,7 @@ static int test__open_syscall_event(void)
 	}
 
 	if (evsel->counts->cpu[0].val != nr_open_calls) {
-		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %Ld\n",
+		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
 			 nr_open_calls, evsel->counts->cpu[0].val);
 		goto out_close_fd;
 	}
@@ -332,8 +332,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 	struct perf_evsel *evsel;
 	struct perf_event_attr attr;
 	unsigned int nr_open_calls = 111, i;
-	cpu_set_t *cpu_set;
-	size_t cpu_set_size;
+	cpu_set_t cpu_set;
 	int id = trace_event__id("sys_enter_open");
 
 	if (id < 0) {
@@ -353,13 +352,8 @@ static int test__open_syscall_event_on_all_cpus(void)
 		return -1;
 	}
 
-	cpu_set = CPU_ALLOC(cpus->nr);
 
-	if (cpu_set == NULL)
-		goto out_thread_map_delete;
-
-	cpu_set_size = CPU_ALLOC_SIZE(cpus->nr);
-	CPU_ZERO_S(cpu_set_size, cpu_set);
+	CPU_ZERO(&cpu_set);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.type = PERF_TYPE_TRACEPOINT;
@@ -367,7 +361,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 	evsel = perf_evsel__new(&attr, 0);
 	if (evsel == NULL) {
 		pr_debug("perf_evsel__new\n");
-		goto out_cpu_free;
+		goto out_thread_map_delete;
 	}
 
 	if (perf_evsel__open(evsel, cpus, threads) < 0) {
@@ -379,14 +373,29 @@ static int test__open_syscall_event_on_all_cpus(void)
 
 	for (cpu = 0; cpu < cpus->nr; ++cpu) {
 		unsigned int ncalls = nr_open_calls + cpu;
+		/*
+		 * XXX eventually lift this restriction in a way that
+		 * keeps perf building on older glibc installations
+		 * without CPU_ALLOC. 1024 cpus in 2010 still seems
+		 * a reasonable upper limit tho :-)
+		 */
+		if (cpus->map[cpu] >= CPU_SETSIZE) {
+			pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+			continue;
+		}
 
-		CPU_SET(cpu, cpu_set);
-		sched_setaffinity(0, cpu_set_size, cpu_set);
+		CPU_SET(cpus->map[cpu], &cpu_set);
+		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+				 cpus->map[cpu],
+				 strerror(errno));
+			goto out_close_fd;
+		}
 		for (i = 0; i < ncalls; ++i) {
 			fd = open("/etc/passwd", O_RDONLY);
 			close(fd);
 		}
-		CPU_CLR(cpu, cpu_set);
+		CPU_CLR(cpus->map[cpu], &cpu_set);
 	}
 
 	/*
@@ -402,6 +411,9 @@ static int test__open_syscall_event_on_all_cpus(void)
 	for (cpu = 0; cpu < cpus->nr; ++cpu) {
 		unsigned int expected;
 
+		if (cpus->map[cpu] >= CPU_SETSIZE)
+			continue;
+
 		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
 			pr_debug("perf_evsel__open_read_on_cpu\n");
 			goto out_close_fd;
@@ -409,8 +421,8 @@ static int test__open_syscall_event_on_all_cpus(void)
 
 		expected = nr_open_calls + cpu;
 		if (evsel->counts->cpu[cpu].val != expected) {
-			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %Ld\n",
-				 expected, cpu, evsel->counts->cpu[cpu].val);
+			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
+				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
 			goto out_close_fd;
 		}
 	}
@@ -420,8 +432,6 @@ out_close_fd:
 	perf_evsel__close_fd(evsel, 1, threads->nr);
 out_evsel_delete:
 	perf_evsel__delete(evsel);
-out_cpu_free:
-	CPU_FREE(cpu_set);
 out_thread_map_delete:
 	thread_map__delete(threads);
 	return err;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 05344c6..b6998e0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -40,6 +40,7 @@
 #include <stdio.h>
 #include <termios.h>
 #include <unistd.h>
+#include <inttypes.h>
 
 #include <errno.h>
 #include <time.h>
@@ -214,7 +215,7 @@ static int parse_source(struct sym_entry *syme)
 	len = sym->end - sym->start;
 
 	sprintf(command,
-		"objdump --start-address=%#0*Lx --stop-address=%#0*Lx -dS %s",
+		"objdump --start-address=%#0*" PRIx64 " --stop-address=%#0*" PRIx64 " -dS %s",
 		BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
 		BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
 
@@ -308,7 +309,7 @@ static void lookup_sym_source(struct sym_entry *syme)
 	struct source_line *line;
 	char pattern[PATTERN_LEN + 1];
 
-	sprintf(pattern, "%0*Lx <", BITS_PER_LONG / 4,
+	sprintf(pattern, "%0*" PRIx64 " <", BITS_PER_LONG / 4,
 		map__rip_2objdump(syme->map, symbol->start));
 
 	pthread_mutex_lock(&syme->src->lock);
@@ -537,7 +538,7 @@ static void print_sym_table(void)
 	if (nr_counters == 1 || !display_weighted) {
 		struct perf_evsel *first;
 		first = list_entry(evsel_list.next, struct perf_evsel, node);
-		printf("%Ld", first->attr.sample_period);
+		printf("%" PRIu64, (uint64_t)first->attr.sample_period);
 		if (freq)
 			printf("Hz ");
 		else
@@ -640,7 +641,7 @@ static void print_sym_table(void)
 
 		percent_color_fprintf(stdout, "%4.1f%%", pcnt);
 		if (verbose)
-			printf(" %016llx", sym->start);
+			printf(" %016" PRIx64, sym->start);
 		printf(" %-*.*s", sym_width, sym_width, sym->name);
 		printf(" %-*.*s\n", dso_width, dso_width,
 		       dso_width >= syme->map->dso->long_name_len ?
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2302ec0..1478ab4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -459,7 +459,8 @@ int event__process_comm(event_t *self, struct sample_data *sample __used,
 int event__process_lost(event_t *self, struct sample_data *sample __used,
 			struct perf_session *session)
 {
-	dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
+	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+		    self->lost.id, self->lost.lost);
 	session->hists.stats.total_lost += self->lost.lost;
 	return 0;
 }
@@ -575,7 +576,7 @@ int event__process_mmap(event_t *self, struct sample_data *sample __used,
 	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	int ret = 0;
 
-	dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
+	dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
 			self->mmap.pid, self->mmap.tid, self->mmap.start,
 			self->mmap.len, self->mmap.pgoff, self->mmap.filename);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 989fa2d..f6a929e7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -798,8 +798,8 @@ static int perf_file_section__process(struct perf_file_section *self,
 				      int feat, int fd)
 {
 	if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) {
-		pr_debug("Failed to lseek to %Ld offset for feature %d, "
-			 "continuing...\n", self->offset, feat);
+		pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
+			  "%d, continuing...\n", self->offset, feat);
 		return 0;
 	}
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index c749ba6..32f4f1f 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -636,13 +636,13 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 			}
 		}
 	} else
-		ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period);
+		ret = snprintf(s, size, sep ? "%" PRIu64 : "%12" PRIu64 " ", period);
 
 	if (symbol_conf.show_nr_samples) {
 		if (sep)
-			ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period);
+			ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period);
 		else
-			ret += snprintf(s + ret, size - ret, "%11lld", period);
+			ret += snprintf(s + ret, size - ret, "%11" PRIu64, period);
 	}
 
 	if (pair_hists) {
@@ -971,7 +971,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
 	sym_size = sym->end - sym->start;
 	offset = ip - sym->start;
 
-	pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
+	pr_debug3("%s: ip=%#" PRIx64 "\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
 
 	if (offset >= sym_size)
 		return 0;
@@ -980,8 +980,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
 	h->sum++;
 	h->ip[offset]++;
 
-	pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start,
-		  self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]);
+	pr_debug3("%#" PRIx64 " %s: period++ [ip: %#" PRIx64 ", %#" PRIx64
+		  "] => %" PRIu64 "\n", self->ms.sym->start, self->ms.sym->name,
+		  ip, ip - self->ms.sym->start, h->ip[offset]);
 	return 0;
 }
 
@@ -1132,7 +1133,7 @@ fallback:
 		goto out_free_filename;
 	}
 
-	pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
+	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
 		 filename, sym->name, map->unmap_ip(map, sym->start),
 		 map->unmap_ip(map, sym->end));
 
@@ -1142,7 +1143,7 @@ fallback:
 		 dso, dso->long_name, sym, sym->name);
 
 	snprintf(command, sizeof(command),
-		 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand",
+		 "objdump --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 symfs_filename, filename);
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 8be0b96..305c848 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -2,6 +2,7 @@
 #define _PERF_LINUX_BITOPS_H_
 
 #include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <asm/hweight.h>
 
 #define BITS_PER_LONG __WORDSIZE
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 3a7eb6e..a16ecab 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 #include "symbol.h"
 #include <errno.h>
+#include <inttypes.h>
 #include <limits.h>
 #include <stdlib.h>
 #include <string.h>
@@ -195,7 +196,7 @@ int map__overlap(struct map *l, struct map *r)
 
 size_t map__fprintf(struct map *self, FILE *fp)
 {
-	return fprintf(fp, " %Lx-%Lx %Lx %s\n",
+	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
 		       self->start, self->end, self->pgoff, self->dso->name);
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bc2732e..135f69b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -279,7 +279,7 @@ const char *__event_name(int type, u64 config)
 	static char buf[32];
 
 	if (type == PERF_TYPE_RAW) {
-		sprintf(buf, "raw 0x%llx", config);
+		sprintf(buf, "raw 0x%" PRIx64, config);
 		return buf;
 	}
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b82cafb..458e3ec 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -23,7 +23,7 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
-extern bool have_tracepoints(struct list_head *evsel_list);
+extern bool have_tracepoints(struct list_head *evlist);
 
 extern int			nr_counters;
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 128aaab..6e29d9c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -172,7 +172,7 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 	sym = __find_kernel_function_by_name(tp->symbol, &map);
 	if (sym) {
 		addr = map->unmap_ip(map, sym->start + tp->offset);
-		pr_debug("try to find %s+%ld@%llx\n", tp->symbol,
+		pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol,
 			 tp->offset, addr);
 		ret = find_perf_probe_point((unsigned long)addr, pp);
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 313dac2..105f00b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -652,10 +652,11 @@ static void callchain__printf(struct sample_data *sample)
 {
 	unsigned int i;
 
-	printf("... chain: nr:%Lu\n", sample->callchain->nr);
+	printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr);
 
 	for (i = 0; i < sample->callchain->nr; i++)
-		printf("..... %2d: %016Lx\n", i, sample->callchain->ips[i]);
+		printf("..... %2d: %016" PRIx64 "\n",
+		       i, sample->callchain->ips[i]);
 }
 
 static void perf_session__print_tstamp(struct perf_session *session,
@@ -672,7 +673,7 @@ static void perf_session__print_tstamp(struct perf_session *session,
 		printf("%u ", sample->cpu);
 
 	if (session->sample_type & PERF_SAMPLE_TIME)
-		printf("%Lu ", sample->time);
+		printf("%" PRIu64 " ", sample->time);
 }
 
 static void dump_event(struct perf_session *session, event_t *event,
@@ -681,16 +682,16 @@ static void dump_event(struct perf_session *session, event_t *event,
 	if (!dump_trace)
 		return;
 
-	printf("\n%#Lx [%#x]: event: %d\n", file_offset, event->header.size,
-	       event->header.type);
+	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
+	       file_offset, event->header.size, event->header.type);
 
 	trace_event(event);
 
 	if (sample)
 		perf_session__print_tstamp(session, event, sample);
 
-	printf("%#Lx [%#x]: PERF_RECORD_%s", file_offset, event->header.size,
-	       event__get_event_name(event->header.type));
+	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
+	       event->header.size, event__get_event_name(event->header.type));
 }
 
 static void dump_sample(struct perf_session *session, event_t *event,
@@ -699,8 +700,9 @@ static void dump_sample(struct perf_session *session, event_t *event,
 	if (!dump_trace)
 		return;
 
-	printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-	       sample->pid, sample->tid, sample->ip, sample->period);
+	printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 "\n",
+	       event->header.misc, sample->pid, sample->tid, sample->ip,
+	       sample->period);
 
 	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
@@ -843,8 +845,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 {
 	if (ops->lost == event__process_lost &&
 	    session->hists.stats.total_lost != 0) {
-		ui__warning("Processed %Lu events and LOST %Lu!\n\n"
-			    "Check IO/CPU overload!\n\n",
+		ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64
+			    "!\n\nCheck IO/CPU overload!\n\n",
 			    session->hists.stats.total_period,
 			    session->hists.stats.total_lost);
 	}
@@ -918,7 +920,7 @@ more:
 
 	if (size == 0 ||
 	    (skip = perf_session__process_event(self, &event, ops, head)) < 0) {
-		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+		dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n",
 			    head, event.header.size, event.header.type);
 		/*
 		 * assume we lost track of the stream, check alignment, and
@@ -1023,7 +1025,7 @@ more:
 
 	if (size == 0 ||
 	    perf_session__process_event(session, event, ops, file_pos) < 0) {
-		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+		dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n",
 			    file_offset + head, event->header.size,
 			    event->header.type);
 		/*
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index b3637db..fb737fe 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -12,6 +12,7 @@
  * of the License.
  */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -43,11 +44,11 @@ static double cpu2y(int cpu)
 	return cpu2slot(cpu) * SLOT_MULT;
 }
 
-static double time2pixels(u64 time)
+static double time2pixels(u64 __time)
 {
 	double X;
 
-	X = 1.0 * svg_page_width * (time - first_time) / (last_time - first_time);
+	X = 1.0 * svg_page_width * (__time - first_time) / (last_time - first_time);
 	return X;
 }
 
@@ -94,7 +95,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
 	total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
 	fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
-	fprintf(svgfile, "<svg width=\"%i\" height=\"%llu\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
+	fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
 	fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
 
@@ -483,7 +484,7 @@ void svg_time_grid(void)
 			color = 128;
 		}
 
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%llu\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
+		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
 			time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness);
 
 		i += 10000000;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 15ccfba..7821d0e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -11,6 +11,7 @@
 #include <sys/param.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <inttypes.h>
 #include "build-id.h"
 #include "debug.h"
 #include "symbol.h"
@@ -153,7 +154,7 @@ static struct symbol *symbol__new(u64 start, u64 len, u8 binding,
 	self->binding = binding;
 	self->namelen = namelen - 1;
 
-	pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
+	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n", __func__, name, start, self->end);
 
 	memcpy(self->name, name, namelen);
 
@@ -167,7 +168,7 @@ void symbol__delete(struct symbol *self)
 
 static size_t symbol__fprintf(struct symbol *self, FILE *fp)
 {
-	return fprintf(fp, " %llx-%llx %c %s\n",
+	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
 		       self->start, self->end,
 		       self->binding == STB_GLOBAL ? 'g' :
 		       self->binding == STB_LOCAL  ? 'l' : 'w',
@@ -1161,6 +1162,13 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 
 		section_name = elf_sec__name(&shdr, secstrs);
 
+		/* On ARM, symbols for thumb functions have 1 added to
+		 * the symbol address as a flag - remove it */
+		if ((ehdr.e_machine == EM_ARM) &&
+		    (map->type == MAP__FUNCTION) &&
+		    (sym.st_value & 1))
+			--sym.st_value;
+
 		if (self->kernel != DSO_TYPE_USER || kmodule) {
 			char dso_name[PATH_MAX];
 
@@ -1208,8 +1216,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 		}
 
 		if (curr_dso->adjust_symbols) {
-			pr_debug4("%s: adjusting symbol: st_value: %#Lx "
-				  "sh_addr: %#Lx sh_offset: %#Lx\n", __func__,
+			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
 				  (u64)sym.st_value, (u64)shdr.sh_addr,
 				  (u64)shdr.sh_offset);
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h
index 7d6b833..5f3689a 100644
--- a/tools/perf/util/types.h
+++ b/tools/perf/util/types.h
@@ -1,12 +1,14 @@
 #ifndef __PERF_TYPES_H
 #define __PERF_TYPES_H
 
+#include <stdint.h>
+
 /*
- * We define u64 as unsigned long long for every architecture
- * so that we can print it with %Lx without getting warnings.
+ * We define u64 as uint64_t for every architecture
+ * so that we can print it with "%"PRIx64 without getting warnings.
  */
-typedef unsigned long long u64;
-typedef signed long long   s64;
+typedef uint64_t	   u64;
+typedef int64_t		   s64;
 typedef unsigned int	   u32;
 typedef signed int	   s32;
 typedef unsigned short	   u16;
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index ebda8c3..60c463c 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -350,7 +350,7 @@ static char *callchain_list__sym_name(struct callchain_list *self,
 	if (self->ms.sym)
 		return self->ms.sym->name;
 
-	snprintf(bf, bfsize, "%#Lx", self->ip);
+	snprintf(bf, bfsize, "%#" PRIx64, self->ip);
 	return bf;
 }
 
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index e35437d..e515836 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -1,5 +1,6 @@
 #include "../libslang.h"
 #include <elf.h>
+#include <inttypes.h>
 #include <sys/ttydefaults.h>
 #include <ctype.h>
 #include <string.h>
@@ -57,7 +58,7 @@ static void map_browser__write(struct ui_browser *self, void *nd, int row)
 	int width;
 
 	ui_browser__set_percent_color(self, 0, current_entry);
-	slsmg_printf("%*llx %*llx %c ",
+	slsmg_printf("%*" PRIx64 " %*" PRIx64 " %c ",
 		     mb->addrlen, sym->start, mb->addrlen, sym->end,
 		     sym->binding == STB_GLOBAL ? 'g' :
 		     sym->binding == STB_LOCAL  ? 'l' : 'w');
@@ -150,6 +151,6 @@ int map__browse(struct map *self)
 		++mb.b.nr_entries;
 	}
 
-	mb.addrlen = snprintf(tmp, sizeof(tmp), "%llx", maxaddr);
+	mb.addrlen = snprintf(tmp, sizeof(tmp), "%" PRIx64, maxaddr);
 	return map_browser__run(&mb);
 }
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index cfa55d6..bdd3347 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -150,7 +150,7 @@ static void perf_read_values__display_pretty(FILE *fp,
 		if (width > tidwidth)
 			tidwidth = width;
 		for (j = 0; j < values->counters; j++) {
-			width = snprintf(NULL, 0, "%Lu", values->value[i][j]);
+			width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
 			if (width > counterwidth[j])
 				counterwidth[j] = width;
 		}
@@ -165,7 +165,7 @@ static void perf_read_values__display_pretty(FILE *fp,
 		fprintf(fp, "  %*d  %*d", pidwidth, values->pid[i],
 			tidwidth, values->tid[i]);
 		for (j = 0; j < values->counters; j++)
-			fprintf(fp, "  %*Lu",
+			fprintf(fp, "  %*" PRIu64,
 				counterwidth[j], values->value[i][j]);
 		fprintf(fp, "\n");
 	}
@@ -196,13 +196,13 @@ static void perf_read_values__display_raw(FILE *fp,
 		width = strlen(values->countername[j]);
 		if (width > namewidth)
 			namewidth = width;
-		width = snprintf(NULL, 0, "%llx", values->counterrawid[j]);
+		width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]);
 		if (width > rawwidth)
 			rawwidth = width;
 	}
 	for (i = 0; i < values->threads; i++) {
 		for (j = 0; j < values->counters; j++) {
-			width = snprintf(NULL, 0, "%Lu", values->value[i][j]);
+			width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
 			if (width > countwidth)
 				countwidth = width;
 		}
@@ -214,7 +214,7 @@ static void perf_read_values__display_raw(FILE *fp,
 		countwidth, "Count");
 	for (i = 0; i < values->threads; i++)
 		for (j = 0; j < values->counters; j++)
-			fprintf(fp, "  %*d  %*d  %*s  %*llx  %*Lu\n",
+			fprintf(fp, "  %*d  %*d  %*s  %*" PRIx64 "  %*" PRIu64,
 				pidwidth, values->pid[i],
 				tidwidth, values->tid[i],
 				namewidth, values->countername[j],

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-01-18 18:59 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-18 18:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Steven Rostedt, Frédéric Weisbecker,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Oleg Nesterov (2):
      perf: Find_get_context: fix the per-cpu-counter check
      perf: Validate cpu early in perf_event_alloc()

Peter Zijlstra (1):
      perf: Fix contexted inheritance


 kernel/perf_event.c |   23 ++++++++++++-----------
 1 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index b782b7a..67d9bd7 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2228,14 +2228,11 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 	unsigned long flags;
 	int ctxn, err;
 
-	if (!task && cpu != -1) {
+	if (!task) {
 		/* Must be root to operate on a CPU event: */
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
-		if (cpu < 0 || cpu >= nr_cpumask_bits)
-			return ERR_PTR(-EINVAL);
-
 		/*
 		 * We could be clever and allow to attach a event to an
 		 * offline CPU and activate it when the CPU comes up, but
@@ -5541,6 +5538,11 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	struct hw_perf_event *hwc;
 	long err;
 
+	if ((unsigned)cpu >= nr_cpu_ids) {
+		if (!task || cpu != -1)
+			return ERR_PTR(-EINVAL);
+	}
+
 	event = kzalloc(sizeof(*event), GFP_KERNEL);
 	if (!event)
 		return ERR_PTR(-ENOMEM);
@@ -5589,7 +5591,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	if (!overflow_handler && parent_event)
 		overflow_handler = parent_event->overflow_handler;
-	
+
 	event->overflow_handler	= overflow_handler;
 
 	if (attr->disabled)
@@ -6494,7 +6496,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
 	parent_ctx->rotate_disable = 0;
-	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
 
 	child_ctx = child->perf_event_ctxp[ctxn];
 
@@ -6502,12 +6503,11 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 		/*
 		 * Mark the child context as a clone of the parent
 		 * context, or of whatever the parent is a clone of.
-		 * Note that if the parent is a clone, it could get
-		 * uncloned at any point, but that doesn't matter
-		 * because the list of events and the generation
-		 * count can't have changed since we took the mutex.
+		 *
+		 * Note that if the parent is a clone, the holding of
+		 * parent_ctx->lock avoids it from being uncloned.
 		 */
-		cloned_ctx = rcu_dereference(parent_ctx->parent_ctx);
+		cloned_ctx = parent_ctx->parent_ctx;
 		if (cloned_ctx) {
 			child_ctx->parent_ctx = cloned_ctx;
 			child_ctx->parent_gen = parent_ctx->parent_gen;
@@ -6518,6 +6518,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 		get_ctx(child_ctx->parent_ctx);
 	}
 
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-01-18  9:42 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-18  9:42 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      powerpc: perf: Fix frequency calculation for overflowing counters

Arnaldo Carvalho de Melo (2):
      perf tools: Fix handling of wildcards in tracepoint event selectors
      perf tools: Fix tracepoint id to string perf.data header table


 arch/powerpc/kernel/perf_event.c |    1 +
 tools/perf/builtin-record.c      |    2 ++
 tools/perf/util/parse-events.c   |   31 +------------------------------
 3 files changed, 4 insertions(+), 30 deletions(-)

diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 5674807..ab6f6be 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1212,6 +1212,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			if (left <= 0)
 				left = period;
 			record = 1;
+			event->hw.last_period = event->hw.sample_period;
 		}
 		if (left < 0x80000000LL)
 			val = 0x80000000LL - left;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index df6064a..fcd29e8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -936,6 +936,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	list_for_each_entry(pos, &evsel_list, node) {
 		if (perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
 			goto out_free_fd;
+		if (perf_header__push_event(pos->attr.config, event_name(pos)))
+			goto out_free_fd;
 	}
 	event_array = malloc((sizeof(struct pollfd) * MAX_NR_CPUS *
 			      MAX_COUNTERS * threads->nr));
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5cb6f4b..bc2732e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -490,32 +490,6 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
 	return EVT_HANDLED_ALL;
 }
 
-static int store_event_type(const char *orgname)
-{
-	char filename[PATH_MAX], *c;
-	FILE *file;
-	int id, n;
-
-	sprintf(filename, "%s/", debugfs_path);
-	strncat(filename, orgname, strlen(orgname));
-	strcat(filename, "/id");
-
-	c = strchr(filename, ':');
-	if (c)
-		*c = '/';
-
-	file = fopen(filename, "r");
-	if (!file)
-		return 0;
-	n = fscanf(file, "%i", &id);
-	fclose(file);
-	if (n < 1) {
-		pr_err("cannot store event ID\n");
-		return -EINVAL;
-	}
-	return perf_header__push_event(id, orgname);
-}
-
 static enum event_result parse_tracepoint_event(const char **strp,
 				    struct perf_event_attr *attr)
 {
@@ -555,13 +529,10 @@ static enum event_result parse_tracepoint_event(const char **strp,
 	if (evt_length >= MAX_EVENT_LENGTH)
 		return EVT_FAILED;
 	if (strpbrk(evt_name, "*?")) {
-		*strp += strlen(sys_name) + evt_length;
+		*strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
 		return parse_multiple_tracepoint_event(sys_name, evt_name,
 						       flags);
 	} else {
-		if (store_event_type(evt_name) < 0)
-			return EVT_FAILED;
-
 		return parse_single_tracepoint_event(sys_name, evt_name,
 						     evt_length, attr, strp);
 	}

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-01-15 15:24 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-15 15:24 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf evsel: Fix order of event list deletion
      perf top: Fix annotate segv
      Revert "perf tools: Emit clearer message for sys_perf_event_open ENOENT return"

Kirill Smelkov (1):
      perf record: Add "nodelay" mode, disabled by default

Lai Jiangshan (1):
      tracing: Remove syscall_exit_fields

Stephane Eranian (1):
      perf sched: Fix list of events, dropping unsupported ':r' modifier

Steven Rostedt (1):
      tracing: Only process module tracepoints once


 include/trace/events/module.h            |   10 +++++++++
 kernel/trace/trace_syscalls.c            |   33 ++++++++++-------------------
 tools/perf/Documentation/perf-record.txt |    3 ++
 tools/perf/builtin-record.c              |   12 ++++++++--
 tools/perf/builtin-sched.c               |   18 ++++++++--------
 tools/perf/builtin-stat.c                |    1 +
 tools/perf/builtin-top.c                 |    5 ++-
 tools/perf/perf.c                        |    2 -
 8 files changed, 47 insertions(+), 37 deletions(-)

diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c7bb2f0..c6bae36 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -1,5 +1,15 @@
+/*
+ * Because linux/module.h has tracepoints in the header, and ftrace.h
+ * eventually includes this file, define_trace.h includes linux/module.h
+ * But we do not want the module.h to override the TRACE_SYSTEM macro
+ * variable that define_trace.h is processing, so we only set it
+ * when module events are being processed, which would happen when
+ * CREATE_TRACE_POINTS is defined.
+ */
+#ifdef CREATE_TRACE_POINTS
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM module
+#endif
 
 #if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_MODULE_H
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index bac752f..b706529 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -23,9 +23,6 @@ static int syscall_exit_register(struct ftrace_event_call *event,
 static int syscall_enter_define_fields(struct ftrace_event_call *call);
 static int syscall_exit_define_fields(struct ftrace_event_call *call);
 
-/* All syscall exit events have the same fields */
-static LIST_HEAD(syscall_exit_fields);
-
 static struct list_head *
 syscall_get_enter_fields(struct ftrace_event_call *call)
 {
@@ -34,34 +31,28 @@ syscall_get_enter_fields(struct ftrace_event_call *call)
 	return &entry->enter_fields;
 }
 
-static struct list_head *
-syscall_get_exit_fields(struct ftrace_event_call *call)
-{
-	return &syscall_exit_fields;
-}
-
 struct trace_event_functions enter_syscall_print_funcs = {
-	.trace                  = print_syscall_enter,
+	.trace		= print_syscall_enter,
 };
 
 struct trace_event_functions exit_syscall_print_funcs = {
-	.trace                  = print_syscall_exit,
+	.trace		= print_syscall_exit,
 };
 
 struct ftrace_event_class event_class_syscall_enter = {
-	.system			= "syscalls",
-	.reg			= syscall_enter_register,
-	.define_fields		= syscall_enter_define_fields,
-	.get_fields		= syscall_get_enter_fields,
-	.raw_init		= init_syscall_trace,
+	.system		= "syscalls",
+	.reg		= syscall_enter_register,
+	.define_fields	= syscall_enter_define_fields,
+	.get_fields	= syscall_get_enter_fields,
+	.raw_init	= init_syscall_trace,
 };
 
 struct ftrace_event_class event_class_syscall_exit = {
-	.system			= "syscalls",
-	.reg			= syscall_exit_register,
-	.define_fields		= syscall_exit_define_fields,
-	.get_fields		= syscall_get_exit_fields,
-	.raw_init		= init_syscall_trace,
+	.system		= "syscalls",
+	.reg		= syscall_exit_register,
+	.define_fields	= syscall_exit_define_fields,
+	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
+	.raw_init	= init_syscall_trace,
 };
 
 extern unsigned long __start_syscalls_metadata[];
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 52462ae..e032716 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -61,6 +61,9 @@ OPTIONS
 -r::
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.
+-D::
+--no-delay::
+	Collect data without buffering.
 -A::
 --append::
 	Append to the output file to do incremental profiling.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7069bd3..df6064a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,6 +49,7 @@ static int			pipe_output			=      0;
 static const char		*output_name			= "perf.data";
 static int			group				=      0;
 static int			realtime_prio			=      0;
+static bool			nodelay				=  false;
 static bool			raw_samples			=  false;
 static bool			sample_id_all_avail		=   true;
 static bool			system_wide			=  false;
@@ -307,6 +308,11 @@ static void create_counter(struct perf_evsel *evsel, int cpu)
 		attr->sample_type	|= PERF_SAMPLE_CPU;
 	}
 
+	if (nodelay) {
+		attr->watermark = 0;
+		attr->wakeup_events = 1;
+	}
+
 	attr->mmap		= track;
 	attr->comm		= track;
 	attr->inherit		= !no_inherit;
@@ -331,9 +337,6 @@ try_again:
 			else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
-			} else if (err == ENOENT) {
-				die("%s event is not supported. ",
-				     event_name(evsel));
 			} else if (err == EINVAL && sample_id_all_avail) {
 				/*
 				 * Old kernel, no attr->sample_id_type_all field
@@ -480,6 +483,7 @@ static void atexit_header(void)
 			process_buildids();
 		perf_header__write(&session->header, output, true);
 		perf_session__delete(session);
+		perf_evsel_list__delete();
 		symbol__exit();
 	}
 }
@@ -845,6 +849,8 @@ const struct option record_options[] = {
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
+	OPT_BOOLEAN('D', "no-delay", &nodelay,
+		    "collect data without buffering"),
 	OPT_BOOLEAN('R', "raw-samples", &raw_samples,
 		    "collect raw sample records from all opened counters"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index abd4b84..29e7ffd 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1843,15 +1843,15 @@ static const char *record_args[] = {
 	"-f",
 	"-m", "1024",
 	"-c", "1",
-	"-e", "sched:sched_switch:r",
-	"-e", "sched:sched_stat_wait:r",
-	"-e", "sched:sched_stat_sleep:r",
-	"-e", "sched:sched_stat_iowait:r",
-	"-e", "sched:sched_stat_runtime:r",
-	"-e", "sched:sched_process_exit:r",
-	"-e", "sched:sched_process_fork:r",
-	"-e", "sched:sched_wakeup:r",
-	"-e", "sched:sched_migrate_task:r",
+	"-e", "sched:sched_switch",
+	"-e", "sched:sched_stat_wait",
+	"-e", "sched:sched_stat_sleep",
+	"-e", "sched:sched_stat_iowait",
+	"-e", "sched:sched_stat_runtime",
+	"-e", "sched:sched_process_exit",
+	"-e", "sched:sched_process_fork",
+	"-e", "sched:sched_wakeup",
+	"-e", "sched:sched_migrate_task",
 };
 
 static int __cmd_record(int argc, const char **argv)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c385a63..0ff11d9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -743,6 +743,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 out_free_fd:
 	list_for_each_entry(pos, &evsel_list, node)
 		perf_evsel__free_stat_priv(pos);
+	perf_evsel_list__delete();
 out:
 	thread_map__delete(threads);
 	threads = NULL;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6ce4042..05344c6 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1247,8 +1247,6 @@ try_again:
 				die("Permission error - are you root?\n"
 					"\t Consider tweaking"
 					" /proc/sys/kernel/perf_event_paranoid.\n");
-			if (err == ENOENT)
-				die("%s event is not supported. ", event_name(evsel));
 			/*
 			 * If it's cycles then fall back to hrtimer
 			 * based cpu-clock-tick sw counter, which
@@ -1473,6 +1471,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		pos->attr.sample_period = default_interval;
 	}
 
+	sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
+
 	symbol_conf.priv_size = (sizeof(struct sym_entry) +
 				 (nr_counters + 1) * sizeof(unsigned long));
 
@@ -1490,6 +1490,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 out_free_fd:
 	list_for_each_entry(pos, &evsel_list, node)
 		perf_evsel__free_mmap(pos);
+	perf_evsel_list__delete();
 
 	return status;
 }
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 5b1ecd6..595d0f4 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -286,8 +286,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	status = p->fn(argc, argv, prefix);
 	exit_browser(status);
 
-	perf_evsel_list__delete();
-
 	if (status)
 		return status & 0xff;
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-01-11 11:32 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-11 11:32 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Steven Rostedt, Frédéric Weisbecker,
	H. Peter Anvin, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

A few late coming items plus fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf sched: Fix allocation result check
      perf tools: Emit clearer message for sys_perf_event_open ENOENT return
      perf evsel: Support perf_evsel__open(cpus > 1 && threads > 1)
      perf session: Fix infinite loop in __perf_session__process_events

Cyrill Gorcunov (1):
      perf, x86: P4 PMU - Fix unflagged overflows handling

David Ahern (1):
      perf stat: better error message for unsupported events

Don Zickus (5):
      x86: Convert some devices to use DIE_NMIUNKNOWN
      x86, NMI: Add priorities to handlers
      x86, NMI: Remove DIE_NMI_IPI
      x86, NMI: Allow NMI reason io port (0x61) to be processed on any CPU
      x86, NMI: Clean-up default_do_nmi()

Frederic Weisbecker (2):
      perf tools: Build with frame pointer
      x86: Save rbp in pt_regs on irq entry

Han Pingtian (1):
      perf tools: Fix buffer overflow error when specifying all tracepoints

Huang Ying (1):
      x86, NMI: Add NMI symbol constants and rename memory parity to PCI SERR

Jason Baron (1):
      dynamic debug: Fix build issue with older gcc

Jiri Pirko (1):
      perf sched: Use PTHREAD_STACK_MIN to avoid pthread_attr_setstacksize() fail

Lai Jiangshan (1):
      tracepoint: Add __rcu annotation

Li Zefan (1):
      tracing: Fix preempt count leak

Lin Ming (1):
      perf tools: Pass whole attr to event selectors

Mathieu Desnoyers (3):
      tracing/trivial: Add missing comma in TRACE_EVENT comment
      tracing: remove duplicate null-pointer check in skb tracepoint
      tracing: Fix TRACE_EVENT power tracepoint creation

Rakib Mullick (1):
      x86, dumpstack: Fix unused variable warning

Stephane Eranian (3):
      perf_events: Move code around to prepare for cgroup
      perf_events: Generalize use of event_filter_match()
      perf_events: Add perf_event_time()

Steven Rostedt (1):
      tracing: Include module.h in define_trace.h


 arch/x86/include/asm/kdebug.h           |    1 -
 arch/x86/include/asm/mach_traps.h       |   12 +++-
 arch/x86/include/asm/nmi.h              |   20 +++++
 arch/x86/include/asm/perf_event_p4.h    |    3 +
 arch/x86/kernel/apic/hw_nmi.c           |    3 +-
 arch/x86/kernel/apic/x2apic_uv_x.c      |    2 +-
 arch/x86/kernel/cpu/mcheck/mce-inject.c |    5 +-
 arch/x86/kernel/cpu/perf_event.c        |    3 +-
 arch/x86/kernel/cpu/perf_event_p4.c     |   28 ++++----
 arch/x86/kernel/dumpstack.c             |    6 --
 arch/x86/kernel/entry_64.S              |   36 ++++++----
 arch/x86/kernel/kgdb.c                  |    7 +--
 arch/x86/kernel/reboot.c                |    5 +-
 arch/x86/kernel/traps.c                 |  102 ++++++++++++++--------------
 arch/x86/oprofile/nmi_int.c             |    3 +-
 arch/x86/oprofile/nmi_timer_int.c       |    2 +-
 drivers/char/ipmi/ipmi_watchdog.c       |    2 +-
 drivers/watchdog/hpwdt.c                |    2 +-
 include/linux/dynamic_debug.h           |   18 +----
 include/linux/tracepoint.h              |    4 +-
 include/trace/define_trace.h            |   10 +++
 include/trace/events/skb.h              |    4 +-
 kernel/Makefile                         |    1 +
 kernel/exit.c                           |   14 +++--
 kernel/perf_event.c                     |   82 +++++++++++++---------
 kernel/trace/Makefile                   |    2 +-
 kernel/trace/trace.c                    |    6 +-
 lib/dynamic_debug.c                     |    9 +--
 tools/perf/Makefile                     |    2 +-
 tools/perf/builtin-record.c             |    3 +
 tools/perf/builtin-sched.c              |    5 +-
 tools/perf/builtin-stat.c               |    5 +-
 tools/perf/builtin-test.c               |  116 ++++++++++++++++++++++++++++++-
 tools/perf/builtin-top.c                |    2 +
 tools/perf/util/evsel.c                 |   87 ++++++++++++++----------
 tools/perf/util/evsel.h                 |    2 +-
 tools/perf/util/parse-events.c          |   74 +++++++++++---------
 tools/perf/util/session.c               |    2 +-
 38 files changed, 442 insertions(+), 248 deletions(-)

diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index f23eb25..ca242d3 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -18,7 +18,6 @@ enum die_val {
 	DIE_TRAP,
 	DIE_GPF,
 	DIE_CALL,
-	DIE_NMI_IPI,
 	DIE_PAGE_FAULT,
 	DIE_NMIUNKNOWN,
 };
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index f792060..72a8b52 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -7,9 +7,19 @@
 
 #include <asm/mc146818rtc.h>
 
+#define NMI_REASON_PORT		0x61
+
+#define NMI_REASON_SERR		0x80
+#define NMI_REASON_IOCHK	0x40
+#define NMI_REASON_MASK		(NMI_REASON_SERR | NMI_REASON_IOCHK)
+
+#define NMI_REASON_CLEAR_SERR	0x04
+#define NMI_REASON_CLEAR_IOCHK	0x08
+#define NMI_REASON_CLEAR_MASK	0x0f
+
 static inline unsigned char get_nmi_reason(void)
 {
-	return inb(0x61);
+	return inb(NMI_REASON_PORT);
 }
 
 static inline void reassert_nmi(void)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c4021b9..c76f5b9 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -23,6 +23,26 @@ void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 
+/*
+ * Define some priorities for the nmi notifier call chain.
+ *
+ * Create a local nmi bit that has a higher priority than
+ * external nmis, because the local ones are more frequent.
+ *
+ * Also setup some default high/normal/low settings for
+ * subsystems to registers with.  Using 4 bits to seperate
+ * the priorities.  This can go alot higher if needed be.
+ */
+
+#define NMI_LOCAL_SHIFT		16	/* randomly picked */
+#define NMI_LOCAL_BIT		(1ULL << NMI_LOCAL_SHIFT)
+#define NMI_HIGH_PRIOR		(1ULL << 8)
+#define NMI_NORMAL_PRIOR	(1ULL << 4)
+#define NMI_LOW_PRIOR		(1ULL << 0)
+#define NMI_LOCAL_HIGH_PRIOR	(NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
+#define NMI_LOCAL_NORMAL_PRIOR	(NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
+#define NMI_LOCAL_LOW_PRIOR	(NMI_LOCAL_BIT | NMI_LOW_PRIOR)
+
 void stop_nmi(void);
 void restart_nmi(void);
 
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 295e2ff..e2f6a99 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -20,6 +20,9 @@
 #define ARCH_P4_MAX_ESCR	(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
 #define ARCH_P4_MAX_CCCR	(18)
 
+#define ARCH_P4_CNTRVAL_BITS	(40)
+#define ARCH_P4_CNTRVAL_MASK	((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
+
 #define P4_ESCR_EVENT_MASK	0x7e000000U
 #define P4_ESCR_EVENT_SHIFT	25
 #define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 72ec29e..79fd43c 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -68,7 +68,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 
 	switch (cmd) {
 	case DIE_NMI:
-	case DIE_NMI_IPI:
 		break;
 
 	default:
@@ -96,7 +95,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block backtrace_notifier = {
 	.notifier_call          = arch_trigger_all_cpu_backtrace_handler,
 	.next                   = NULL,
-	.priority               = 1
+	.priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static int __init register_trigger_all_cpu_backtrace(void)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 2a3f2a7..936613e 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -641,7 +641,7 @@ void __cpuinit uv_cpu_init(void)
  */
 int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 {
-	if (reason != DIE_NMI_IPI)
+	if (reason != DIE_NMIUNKNOWN)
 		return NOTIFY_OK;
 
 	if (in_crash_kexec)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7..a779719 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
 #include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
 	struct die_args *args = (struct die_args *)data;
 	int cpu = smp_processor_id();
 	struct mce *m = &__get_cpu_var(injectm);
-	if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+	if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
 		return NOTIFY_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
 	if (m->inject_flags & MCJ_EXCEPTION)
@@ -95,7 +96,7 @@ static int mce_raise_notify(struct notifier_block *self,
 
 static struct notifier_block mce_raise_nb = {
 	.notifier_call = mce_raise_notify,
-	.priority = 1000,
+	.priority = NMI_LOCAL_NORMAL_PRIOR,
 };
 
 /* Inject mce on current CPU */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 0a360d1..c71bae4 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1268,7 +1268,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 
 	switch (cmd) {
 	case DIE_NMI:
-	case DIE_NMI_IPI:
 		break;
 	case DIE_NMIUNKNOWN:
 		this_nmi = percpu_read(irq_stat.__nmi_count);
@@ -1318,7 +1317,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block perf_event_nmi_notifier = {
 	.notifier_call		= perf_event_nmi_handler,
 	.next			= NULL,
-	.priority		= 1
+	.priority		= NMI_LOCAL_LOW_PRIOR,
 };
 
 static struct event_constraint unconstrained;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 81400b9..e56b9bf 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -753,19 +753,21 @@ out:
 
 static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-	int overflow = 0;
-	u32 low, high;
+	u64 v;
 
-	rdmsr(hwc->config_base + hwc->idx, low, high);
-
-	/* we need to check high bit for unflagged overflows */
-	if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
-		overflow = 1;
-		(void)checking_wrmsrl(hwc->config_base + hwc->idx,
-			((u64)low) & ~P4_CCCR_OVF);
+	/* an official way for overflow indication */
+	rdmsrl(hwc->config_base + hwc->idx, v);
+	if (v & P4_CCCR_OVF) {
+		wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+		return 1;
 	}
 
-	return overflow;
+	/* it might be unflagged overflow */
+	rdmsrl(hwc->event_base + hwc->idx, v);
+	if (!(v & ARCH_P4_CNTRVAL_MASK))
+		return 1;
+
+	return 0;
 }
 
 static void p4_pmu_disable_pebs(void)
@@ -1152,9 +1154,9 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 */
 	.num_counters		= ARCH_P4_MAX_CCCR,
 	.apic			= 1,
-	.cntval_bits		= 40,
-	.cntval_mask		= (1ULL << 40) - 1,
-	.max_period		= (1ULL << 39) - 1,
+	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
+	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
+	.max_period		= (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
 	.hw_config		= p4_hw_config,
 	.schedule_events	= p4_pmu_schedule_events,
 	/*
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 8474c99..d6fb146 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -197,14 +197,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
  */
 void dump_stack(void)
 {
-	unsigned long bp = 0;
 	unsigned long stack;
 
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp)
-		get_bp(bp);
-#endif
-
 	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
 		current->pid, current->comm, print_tainted(),
 		init_utsname()->release,
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e3ba417..d3b895f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -299,17 +299,21 @@ ENDPROC(native_usergs_sysret64)
 ENTRY(save_args)
 	XCPT_FRAME
 	cld
-	movq_cfi rdi, RDI+16-ARGOFFSET
-	movq_cfi rsi, RSI+16-ARGOFFSET
-	movq_cfi rdx, RDX+16-ARGOFFSET
-	movq_cfi rcx, RCX+16-ARGOFFSET
-	movq_cfi rax, RAX+16-ARGOFFSET
-	movq_cfi  r8,  R8+16-ARGOFFSET
-	movq_cfi  r9,  R9+16-ARGOFFSET
-	movq_cfi r10, R10+16-ARGOFFSET
-	movq_cfi r11, R11+16-ARGOFFSET
-
-	leaq -ARGOFFSET+16(%rsp),%rdi	/* arg1 for handler */
+	/*
+	 * start from rbp in pt_regs and jump over
+	 * return address.
+	 */
+	movq_cfi rdi, RDI+8-RBP
+	movq_cfi rsi, RSI+8-RBP
+	movq_cfi rdx, RDX+8-RBP
+	movq_cfi rcx, RCX+8-RBP
+	movq_cfi rax, RAX+8-RBP
+	movq_cfi  r8,  R8+8-RBP
+	movq_cfi  r9,  R9+8-RBP
+	movq_cfi r10, R10+8-RBP
+	movq_cfi r11, R11+8-RBP
+
+	leaq -RBP+8(%rsp),%rdi	/* arg1 for handler */
 	movq_cfi rbp, 8		/* push %rbp */
 	leaq 8(%rsp), %rbp		/* mov %rsp, %ebp */
 	testl $3, CS(%rdi)
@@ -782,8 +786,9 @@ END(interrupt)
 
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
-	subq $ORIG_RAX-ARGOFFSET+8, %rsp
-	CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
+	/* reserve pt_regs for scratch regs and rbp */
+	subq $ORIG_RAX-RBP, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
 	call save_args
 	PARTIAL_FRAME 0
 	call \func
@@ -808,9 +813,14 @@ ret_from_intr:
 	TRACE_IRQS_OFF
 	decl PER_CPU_VAR(irq_count)
 	leaveq
+
 	CFI_RESTORE		rbp
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET	-8
+
+	/* we did not save rbx, restore only from ARGOFFSET */
+	addq $8, %rsp
+	CFI_ADJUST_CFA_OFFSET	-8
 exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index cd21b65..a413000 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -48,6 +48,7 @@
 #include <asm/apicdef.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
 {
@@ -525,10 +526,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 		}
 		return NOTIFY_DONE;
 
-	case DIE_NMI_IPI:
-		/* Just ignore, we will handle the roundup on DIE_NMI. */
-		return NOTIFY_DONE;
-
 	case DIE_NMIUNKNOWN:
 		if (was_in_debug_nmi[raw_smp_processor_id()]) {
 			was_in_debug_nmi[raw_smp_processor_id()] = 0;
@@ -606,7 +603,7 @@ static struct notifier_block kgdb_notifier = {
 	/*
 	 * Lowest-prio notifier priority, we want to be notified last:
 	 */
-	.priority	= -INT_MAX,
+	.priority	= NMI_LOCAL_LOW_PRIOR,
 };
 
 /**
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c495aa8..fc7aae1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -18,6 +18,7 @@
 #include <asm/pci_x86.h>
 #include <asm/virtext.h>
 #include <asm/cpu.h>
+#include <asm/nmi.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/ctype.h>
@@ -747,7 +748,7 @@ static int crash_nmi_callback(struct notifier_block *self,
 {
 	int cpu;
 
-	if (val != DIE_NMI_IPI)
+	if (val != DIE_NMI)
 		return NOTIFY_OK;
 
 	cpu = raw_smp_processor_id();
@@ -778,6 +779,8 @@ static void smp_send_nmi_allbutself(void)
 
 static struct notifier_block crash_nmi_nb = {
 	.notifier_call = crash_nmi_callback,
+	/* we want to be the first one called */
+	.priority = NMI_LOCAL_HIGH_PRIOR+1,
 };
 
 /* Halt all other CPUs, calling the specified function on each of them
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c76aaca..b9b6716 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -84,6 +84,11 @@ EXPORT_SYMBOL_GPL(used_vectors);
 static int ignore_nmis;
 
 int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
 
 static inline void conditional_sti(struct pt_regs *regs)
 {
@@ -310,15 +315,15 @@ static int __init setup_unknown_nmi_panic(char *str)
 __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 static notrace __kprobes void
-mem_parity_error(unsigned char reason, struct pt_regs *regs)
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
-	printk(KERN_EMERG
-		"Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-			reason, smp_processor_id());
-
-	printk(KERN_EMERG
-		"You have some hardware problem, likely on the PCI bus.\n");
+	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
 
+	/*
+	 * On some machines, PCI SERR line is used to report memory
+	 * errors. EDAC makes use of it.
+	 */
 #if defined(CONFIG_EDAC)
 	if (edac_handler_set()) {
 		edac_atomic_assert_error();
@@ -329,11 +334,11 @@ mem_parity_error(unsigned char reason, struct pt_regs *regs)
 	if (panic_on_unrecovered_nmi)
 		panic("NMI: Not continuing");
 
-	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+	pr_emerg("Dazed and confused, but trying to continue\n");
 
-	/* Clear and disable the memory parity error line. */
-	reason = (reason & 0xf) | 4;
-	outb(reason, 0x61);
+	/* Clear and disable the PCI SERR error line. */
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+	outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -341,15 +346,17 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 {
 	unsigned long i;
 
-	printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
+	pr_emerg(
+	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
 	show_registers(regs);
 
 	if (panic_on_io_nmi)
 		panic("NMI IOCK error: Not continuing");
 
 	/* Re-enable the IOCK line, wait for a few seconds */
-	reason = (reason & 0xf) | 8;
-	outb(reason, 0x61);
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
 
 	i = 20000;
 	while (--i) {
@@ -357,8 +364,8 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 		udelay(100);
 	}
 
-	reason &= ~8;
-	outb(reason, 0x61);
+	reason &= ~NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -377,57 +384,50 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 		return;
 	}
 #endif
-	printk(KERN_EMERG
-		"Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-			reason, smp_processor_id());
+	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
 
-	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
+	pr_emerg("Do you have a strange power saving mode enabled?\n");
 	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
 		panic("NMI: Not continuing");
 
-	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+	pr_emerg("Dazed and confused, but trying to continue\n");
 }
 
 static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 {
 	unsigned char reason = 0;
-	int cpu;
 
-	cpu = smp_processor_id();
-
-	/* Only the BSP gets external NMIs from the system. */
-	if (!cpu)
-		reason = get_nmi_reason();
+	/*
+	 * CPU-specific NMI must be processed before non-CPU-specific
+	 * NMI, otherwise we may lose it, because the CPU-specific
+	 * NMI can not be detected/processed on other CPUs.
+	 */
+	if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
+		return;
 
-	if (!(reason & 0xc0)) {
-		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
-								== NOTIFY_STOP)
-			return;
+	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+	raw_spin_lock(&nmi_reason_lock);
+	reason = get_nmi_reason();
 
-#ifdef CONFIG_X86_LOCAL_APIC
-		if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-							== NOTIFY_STOP)
-			return;
+	if (reason & NMI_REASON_MASK) {
+		if (reason & NMI_REASON_SERR)
+			pci_serr_error(reason, regs);
+		else if (reason & NMI_REASON_IOCHK)
+			io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
+		/*
+		 * Reassert NMI in case it became active
+		 * meanwhile as it's edge-triggered:
+		 */
+		reassert_nmi();
 #endif
-		unknown_nmi_error(reason, regs);
-
+		raw_spin_unlock(&nmi_reason_lock);
 		return;
 	}
-	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
-		return;
+	raw_spin_unlock(&nmi_reason_lock);
 
-	/* AK: following checks seem to be broken on modern chipsets. FIXME */
-	if (reason & 0x80)
-		mem_parity_error(reason, regs);
-	if (reason & 0x40)
-		io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
-	/*
-	 * Reassert NMI in case it became active meanwhile
-	 * as it's edge-triggered:
-	 */
-	reassert_nmi();
-#endif
+	unknown_nmi_error(reason, regs);
 }
 
 dotraplinkage notrace __kprobes void
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 358c8b9..e77ea0b 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -65,7 +65,6 @@ static int profile_exceptions_notify(struct notifier_block *self,
 
 	switch (val) {
 	case DIE_NMI:
-	case DIE_NMI_IPI:
 		if (ctr_running)
 			model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
 		else if (!nmi_enabled)
@@ -361,7 +360,7 @@ static void nmi_cpu_setup(void *dummy)
 static struct notifier_block profile_exceptions_nb = {
 	.notifier_call = profile_exceptions_notify,
 	.next = NULL,
-	.priority = 2
+	.priority = NMI_LOCAL_LOW_PRIOR,
 };
 
 static void nmi_cpu_restore_registers(struct op_msrs *msrs)
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index 0636dd9..720bf5a 100644
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ b/arch/x86/oprofile/nmi_timer_int.c
@@ -38,7 +38,7 @@ static int profile_timer_exceptions_notify(struct notifier_block *self,
 static struct notifier_block profile_timer_exceptions_nb = {
 	.notifier_call = profile_timer_exceptions_notify,
 	.next = NULL,
-	.priority = 0
+	.priority = NMI_LOW_PRIOR,
 };
 
 static int timer_start(void)
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index f4d334f..320668f 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -1081,7 +1081,7 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct die_args *args = data;
 
-	if (val != DIE_NMI)
+	if (val != DIE_NMIUNKNOWN)
 		return NOTIFY_OK;
 
 	/* Hack, if it's a memory or I/O error, ignore it. */
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index dea7b5b..24b966d 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -469,7 +469,7 @@ static int hpwdt_pretimeout(struct notifier_block *nb, unsigned long ulReason,
 	unsigned long rom_pl;
 	static int die_nmi_called;
 
-	if (ulReason != DIE_NMI && ulReason != DIE_NMI_IPI)
+	if (ulReason != DIE_NMIUNKNOWN)
 		goto out;
 
 	if (!hpwdt_nmi_decoding)
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index a90b389..1c70028 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -44,34 +44,24 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 extern int ddebug_remove_module(const char *mod_name);
 
 #define dynamic_pr_debug(fmt, ...) do {					\
-	__label__ do_printk;						\
-	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
 	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
 		_DPRINTK_FLAGS_DEFAULT };				\
-	JUMP_LABEL(&descriptor.enabled, do_printk);			\
-	goto out;							\
-do_printk:								\
-	printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);			\
-out:	;								\
+	if (unlikely(descriptor.enabled))				\
+		printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);		\
 	} while (0)
 
 
 #define dynamic_dev_dbg(dev, fmt, ...) do {				\
-	__label__ do_printk;						\
-	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
 	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
 		_DPRINTK_FLAGS_DEFAULT };				\
-	JUMP_LABEL(&descriptor.enabled, do_printk);			\
-	goto out;							\
-do_printk:								\
-	dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);		\
-out:	;								\
+	if (unlikely(descriptor.enabled))				\
+		dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);	\
 	} while (0)
 
 #else
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index d3e4f87..c681461 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -32,7 +32,7 @@ struct tracepoint {
 	int state;			/* State. */
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
-	struct tracepoint_func *funcs;
+	struct tracepoint_func __rcu *funcs;
 } __attribute__((aligned(32)));		/*
 					 * Aligned on 32 bytes because it is
 					 * globally visible and gcc happily
@@ -326,7 +326,7 @@ do_trace:								\
  *		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
  *		__entry->next_pid	= next->pid;
  *		__entry->next_prio	= next->prio;
- *	)
+ *	),
  *
  *	*
  *	* Formatted output of a trace record via TP_printk().
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index b0b4eb2..da39b22 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -21,6 +21,16 @@
 #undef CREATE_TRACE_POINTS
 
 #include <linux/stringify.h>
+/*
+ * module.h includes tracepoints, and because ftrace.h
+ * pulls in module.h:
+ *  trace/ftrace.h -> linux/ftrace_event.h -> linux/perf_event.h ->
+ *  linux/ftrace.h -> linux/module.h
+ * we must include module.h here before we play with any of
+ * the TRACE_EVENT() macros, otherwise the tracepoints included
+ * by module.h may break the build.
+ */
+#include <linux/module.h>
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 75ce9d5..f10293c 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -25,9 +25,7 @@ TRACE_EVENT(kfree_skb,
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		if (skb) {
-			__entry->protocol = ntohs(skb->protocol);
-		}
+		__entry->protocol = ntohs(skb->protocol);
 		__entry->location = location;
 	),
 
diff --git a/kernel/Makefile b/kernel/Makefile
index 0b5ff08..e0f2831 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -100,6 +100,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
+obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
diff --git a/kernel/exit.c b/kernel/exit.c
index 676149a..8cb8904 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -994,6 +994,15 @@ NORET_TYPE void do_exit(long code)
 	exit_fs(tsk);
 	check_stack_usage();
 	exit_thread();
+
+	/*
+	 * Flush inherited counters to the parent - before the parent
+	 * gets woken up by child-exit notifications.
+	 *
+	 * because of cgroup mode, must be called before cgroup_exit()
+	 */
+	perf_event_exit_task(tsk);
+
 	cgroup_exit(tsk, 1);
 
 	if (group_dead)
@@ -1007,11 +1016,6 @@ NORET_TYPE void do_exit(long code)
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
-	/*
-	 * Flush inherited counters to the parent - before the parent
-	 * gets woken up by child-exit notifications.
-	 */
-	perf_event_exit_task(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 11847bf..b782b7a 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,6 +38,12 @@
 
 #include <asm/irq_regs.h>
 
+enum event_type_t {
+	EVENT_FLEXIBLE = 0x1,
+	EVENT_PINNED = 0x2,
+	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
+};
+
 atomic_t perf_task_events __read_mostly;
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -65,6 +71,12 @@ int sysctl_perf_event_sample_rate __read_mostly = 100000;
 
 static atomic64_t perf_event_id;
 
+static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			      enum event_type_t event_type);
+
+static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
+			     enum event_type_t event_type);
+
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -72,6 +84,11 @@ extern __weak const char *perf_pmu_name(void)
 	return "pmu";
 }
 
+static inline u64 perf_clock(void)
+{
+	return local_clock();
+}
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -240,11 +257,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 	put_ctx(ctx);
 }
 
-static inline u64 perf_clock(void)
-{
-	return local_clock();
-}
-
 /*
  * Update the record of the current time in a context.
  */
@@ -256,6 +268,12 @@ static void update_context_time(struct perf_event_context *ctx)
 	ctx->timestamp = now;
 }
 
+static u64 perf_event_time(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	return ctx ? ctx->time : 0;
+}
+
 /*
  * Update the total_time_enabled and total_time_running fields for a event.
  */
@@ -269,7 +287,7 @@ static void update_event_times(struct perf_event *event)
 		return;
 
 	if (ctx->is_active)
-		run_end = ctx->time;
+		run_end = perf_event_time(event);
 	else
 		run_end = event->tstamp_stopped;
 
@@ -278,7 +296,7 @@ static void update_event_times(struct perf_event *event)
 	if (event->state == PERF_EVENT_STATE_INACTIVE)
 		run_end = event->tstamp_stopped;
 	else
-		run_end = ctx->time;
+		run_end = perf_event_time(event);
 
 	event->total_time_running = run_end - event->tstamp_running;
 }
@@ -534,6 +552,7 @@ event_sched_out(struct perf_event *event,
 		  struct perf_cpu_context *cpuctx,
 		  struct perf_event_context *ctx)
 {
+	u64 tstamp = perf_event_time(event);
 	u64 delta;
 	/*
 	 * An event which could not be activated because of
@@ -545,7 +564,7 @@ event_sched_out(struct perf_event *event,
 	    && !event_filter_match(event)) {
 		delta = ctx->time - event->tstamp_stopped;
 		event->tstamp_running += delta;
-		event->tstamp_stopped = ctx->time;
+		event->tstamp_stopped = tstamp;
 	}
 
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
@@ -556,7 +575,7 @@ event_sched_out(struct perf_event *event,
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = ctx->time;
+	event->tstamp_stopped = tstamp;
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
@@ -768,6 +787,8 @@ event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
 		 struct perf_event_context *ctx)
 {
+	u64 tstamp = perf_event_time(event);
+
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
 
@@ -784,9 +805,9 @@ event_sched_in(struct perf_event *event,
 		return -EAGAIN;
 	}
 
-	event->tstamp_running += ctx->time - event->tstamp_stopped;
+	event->tstamp_running += tstamp - event->tstamp_stopped;
 
-	event->shadow_ctx_time = ctx->time - ctx->timestamp;
+	event->shadow_ctx_time = tstamp - ctx->timestamp;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
@@ -898,11 +919,13 @@ static int group_can_go_on(struct perf_event *event,
 static void add_event_to_ctx(struct perf_event *event,
 			       struct perf_event_context *ctx)
 {
+	u64 tstamp = perf_event_time(event);
+
 	list_add_event(event, ctx);
 	perf_group_attach(event);
-	event->tstamp_enabled = ctx->time;
-	event->tstamp_running = ctx->time;
-	event->tstamp_stopped = ctx->time;
+	event->tstamp_enabled = tstamp;
+	event->tstamp_running = tstamp;
+	event->tstamp_stopped = tstamp;
 }
 
 /*
@@ -937,7 +960,7 @@ static void __perf_install_in_context(void *info)
 
 	add_event_to_ctx(event, ctx);
 
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
+	if (!event_filter_match(event))
 		goto unlock;
 
 	/*
@@ -1042,14 +1065,13 @@ static void __perf_event_mark_enabled(struct perf_event *event,
 					struct perf_event_context *ctx)
 {
 	struct perf_event *sub;
+	u64 tstamp = perf_event_time(event);
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
-	event->tstamp_enabled = ctx->time - event->total_time_enabled;
+	event->tstamp_enabled = tstamp - event->total_time_enabled;
 	list_for_each_entry(sub, &event->sibling_list, group_entry) {
-		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
-			sub->tstamp_enabled =
-				ctx->time - sub->total_time_enabled;
-		}
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
+			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
 	}
 }
 
@@ -1082,7 +1104,7 @@ static void __perf_event_enable(void *info)
 		goto unlock;
 	__perf_event_mark_enabled(event, ctx);
 
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
+	if (!event_filter_match(event))
 		goto unlock;
 
 	/*
@@ -1193,12 +1215,6 @@ static int perf_event_refresh(struct perf_event *event, int refresh)
 	return 0;
 }
 
-enum event_type_t {
-	EVENT_FLEXIBLE = 0x1,
-	EVENT_PINNED = 0x2,
-	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
-};
-
 static void ctx_sched_out(struct perf_event_context *ctx,
 			  struct perf_cpu_context *cpuctx,
 			  enum event_type_t event_type)
@@ -1435,7 +1451,7 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
 	list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
 		if (event->state <= PERF_EVENT_STATE_OFF)
 			continue;
-		if (event->cpu != -1 && event->cpu != smp_processor_id())
+		if (!event_filter_match(event))
 			continue;
 
 		if (group_can_go_on(event, cpuctx, 1))
@@ -1467,7 +1483,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 		 * Listen to the 'cpu' scheduling filter constraint
 		 * of events:
 		 */
-		if (event->cpu != -1 && event->cpu != smp_processor_id())
+		if (!event_filter_match(event))
 			continue;
 
 		if (group_can_go_on(event, cpuctx, can_add_hw)) {
@@ -1694,7 +1710,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
 
-		if (event->cpu != -1 && event->cpu != smp_processor_id())
+		if (!event_filter_match(event))
 			continue;
 
 		hwc = &event->hw;
@@ -3893,7 +3909,7 @@ static int perf_event_task_match(struct perf_event *event)
 	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
+	if (!event_filter_match(event))
 		return 0;
 
 	if (event->attr.comm || event->attr.mmap ||
@@ -4030,7 +4046,7 @@ static int perf_event_comm_match(struct perf_event *event)
 	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
+	if (!event_filter_match(event))
 		return 0;
 
 	if (event->attr.comm)
@@ -4178,7 +4194,7 @@ static int perf_event_mmap_match(struct perf_event *event,
 	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
+	if (!event_filter_match(event))
 		return 0;
 
 	if ((!executable && event->attr.mmap_data) ||
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 53f3381..761c510 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
-obj-$(CONFIG_EVENT_TRACING) += power-traces.o
+obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f8cf959..dc53ecb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1313,12 +1313,10 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 
 	__this_cpu_inc(user_stack_count);
 
-
-
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
-		return;
+		goto out_drop_count;
 	entry	= ring_buffer_event_data(event);
 
 	entry->tgid		= current->tgid;
@@ -1333,8 +1331,8 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
 
+ out_drop_count:
 	__this_cpu_dec(user_stack_count);
-
  out:
 	preempt_enable();
 }
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 3094318..b335acb 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -141,11 +141,10 @@ static void ddebug_change(const struct ddebug_query *query,
 			else if (!dp->flags)
 				dt->num_enabled++;
 			dp->flags = newflags;
-			if (newflags) {
-				jump_label_enable(&dp->enabled);
-			} else {
-				jump_label_disable(&dp->enabled);
-			}
+			if (newflags)
+				dp->enabled = 1;
+			else
+				dp->enabled = 0;
 			if (verbose)
 				printk(KERN_INFO
 					"ddebug: changed %s:%d [%s]%s %s\n",
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1b9b13e..2b5387d 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -227,7 +227,7 @@ ifndef PERF_DEBUG
   CFLAGS_OPTIMIZE = -O6
 endif
 
-CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7bc0490..7069bd3 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -331,6 +331,9 @@ try_again:
 			else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
+			} else if (err == ENOENT) {
+				die("%s event is not supported. ",
+				     event_name(evsel));
 			} else if (err == EINVAL && sample_id_all_avail) {
 				/*
 				 * Old kernel, no attr->sample_id_type_all field
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 7a4ebeb..abd4b84 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -489,7 +489,8 @@ static void create_tasks(void)
 
 	err = pthread_attr_init(&attr);
 	BUG_ON(err);
-	err = pthread_attr_setstacksize(&attr, (size_t)(16*1024));
+	err = pthread_attr_setstacksize(&attr,
+			(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
 	BUG_ON(err);
 	err = pthread_mutex_lock(&start_work_mutex);
 	BUG_ON(err);
@@ -1861,7 +1862,7 @@ static int __cmd_record(int argc, const char **argv)
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
-	if (rec_argv)
+	if (rec_argv == NULL)
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 02b2d80..c385a63 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -316,6 +316,8 @@ static int run_perf_stat(int argc __used, const char **argv)
 				      "\t Consider tweaking"
 				      " /proc/sys/kernel/perf_event_paranoid or running as root.",
 				      system_wide ? "system-wide " : "");
+			} else if (errno == ENOENT) {
+				error("%s event is not supported. ", event_name(counter));
 			} else {
 				error("open_counter returned with %d (%s). "
 				      "/bin/dmesg may provide additional information.\n",
@@ -683,8 +685,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		nr_counters = ARRAY_SIZE(default_attrs);
 
 		for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
-			pos = perf_evsel__new(default_attrs[c].type,
-					      default_attrs[c].config,
+			pos = perf_evsel__new(&default_attrs[c],
 					      nr_counters);
 			if (pos == NULL)
 				goto out;
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1c98434..ed56961 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -234,6 +234,7 @@ out:
 	return err;
 }
 
+#include "util/cpumap.h"
 #include "util/evsel.h"
 #include <sys/types.h>
 
@@ -264,6 +265,7 @@ static int test__open_syscall_event(void)
 	int err = -1, fd;
 	struct thread_map *threads;
 	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
 	unsigned int nr_open_calls = 111, i;
 	int id = trace_event__id("sys_enter_open");
 
@@ -278,7 +280,10 @@ static int test__open_syscall_event(void)
 		return -1;
 	}
 
-	evsel = perf_evsel__new(PERF_TYPE_TRACEPOINT, id, 0);
+	memset(&attr, 0, sizeof(attr));
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.config = id;
+	evsel = perf_evsel__new(&attr, 0);
 	if (evsel == NULL) {
 		pr_debug("perf_evsel__new\n");
 		goto out_thread_map_delete;
@@ -317,6 +322,111 @@ out_thread_map_delete:
 	return err;
 }
 
+#include <sched.h>
+
+static int test__open_syscall_event_on_all_cpus(void)
+{
+	int err = -1, fd, cpu;
+	struct thread_map *threads;
+	struct cpu_map *cpus;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	unsigned int nr_open_calls = 111, i;
+	cpu_set_t *cpu_set;
+	size_t cpu_set_size;
+	int id = trace_event__id("sys_enter_open");
+
+	if (id < 0) {
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		return -1;
+	}
+
+	threads = thread_map__new(-1, getpid());
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpu_set = CPU_ALLOC(cpus->nr);
+
+	if (cpu_set == NULL)
+		goto out_thread_map_delete;
+
+	cpu_set_size = CPU_ALLOC_SIZE(cpus->nr);
+	CPU_ZERO_S(cpu_set_size, cpu_set);
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.config = id;
+	evsel = perf_evsel__new(&attr, 0);
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		goto out_cpu_free;
+	}
+
+	if (perf_evsel__open(evsel, cpus, threads) < 0) {
+		pr_debug("failed to open counter: %s, "
+			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+			 strerror(errno));
+		goto out_evsel_delete;
+	}
+
+	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+		unsigned int ncalls = nr_open_calls + cpu;
+
+		CPU_SET(cpu, cpu_set);
+		sched_setaffinity(0, cpu_set_size, cpu_set);
+		for (i = 0; i < ncalls; ++i) {
+			fd = open("/etc/passwd", O_RDONLY);
+			close(fd);
+		}
+		CPU_CLR(cpu, cpu_set);
+	}
+
+	/*
+	 * Here we need to explicitely preallocate the counts, as if
+	 * we use the auto allocation it will allocate just for 1 cpu,
+	 * as we start by cpu 0.
+	 */
+	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
+		goto out_close_fd;
+	}
+
+	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+		unsigned int expected;
+
+		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+			pr_debug("perf_evsel__open_read_on_cpu\n");
+			goto out_close_fd;
+		}
+
+		expected = nr_open_calls + cpu;
+		if (evsel->counts->cpu[cpu].val != expected) {
+			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %Ld\n",
+				 expected, cpu, evsel->counts->cpu[cpu].val);
+			goto out_close_fd;
+		}
+	}
+
+	err = 0;
+out_close_fd:
+	perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+	perf_evsel__delete(evsel);
+out_cpu_free:
+	CPU_FREE(cpu_set);
+out_thread_map_delete:
+	thread_map__delete(threads);
+	return err;
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -330,6 +440,10 @@ static struct test {
 		.func = test__open_syscall_event,
 	},
 	{
+		.desc = "detect open syscall event on all cpus",
+		.func = test__open_syscall_event_on_all_cpus,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1e67ab9..6ce4042 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1247,6 +1247,8 @@ try_again:
 				die("Permission error - are you root?\n"
 					"\t Consider tweaking"
 					" /proc/sys/kernel/perf_event_paranoid.\n");
+			if (err == ENOENT)
+				die("%s event is not supported. ", event_name(evsel));
 			/*
 			 * If it's cycles then fall back to hrtimer
 			 * based cpu-clock-tick sw counter, which
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c95267e..f5cfed6 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -6,14 +6,13 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
-struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx)
+struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 {
 	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
 
 	if (evsel != NULL) {
 		evsel->idx	   = idx;
-		evsel->attr.type   = type;
-		evsel->attr.config = config;
+		evsel->attr	   = *attr;
 		INIT_LIST_HEAD(&evsel->node);
 	}
 
@@ -128,59 +127,75 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	return 0;
 }
 
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
+static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+			      struct thread_map *threads)
 {
-	int cpu;
+	int cpu, thread;
 
-	if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, 1) < 0)
+	if (evsel->fd == NULL &&
+	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
 		return -1;
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		FD(evsel, cpu, 0) = sys_perf_event_open(&evsel->attr, -1,
-							cpus->map[cpu], -1, 0);
-		if (FD(evsel, cpu, 0) < 0)
-			goto out_close;
+		for (thread = 0; thread < threads->nr; thread++) {
+			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
+								     threads->map[thread],
+								     cpus->map[cpu], -1, 0);
+			if (FD(evsel, cpu, thread) < 0)
+				goto out_close;
+		}
 	}
 
 	return 0;
 
 out_close:
-	while (--cpu >= 0) {
-		close(FD(evsel, cpu, 0));
-		FD(evsel, cpu, 0) = -1;
-	}
+	do {
+		while (--thread >= 0) {
+			close(FD(evsel, cpu, thread));
+			FD(evsel, cpu, thread) = -1;
+		}
+		thread = threads->nr;
+	} while (--cpu >= 0);
 	return -1;
 }
 
-int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
+static struct {
+	struct cpu_map map;
+	int cpus[1];
+} empty_cpu_map = {
+	.map.nr	= 1,
+	.cpus	= { -1, },
+};
+
+static struct {
+	struct thread_map map;
+	int threads[1];
+} empty_thread_map = {
+	.map.nr	 = 1,
+	.threads = { -1, },
+};
+
+int perf_evsel__open(struct perf_evsel *evsel,
+		     struct cpu_map *cpus, struct thread_map *threads)
 {
-	int thread;
-
-	if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, 1, threads->nr))
-		return -1;
 
-	for (thread = 0; thread < threads->nr; thread++) {
-		FD(evsel, 0, thread) = sys_perf_event_open(&evsel->attr,
-							   threads->map[thread], -1, -1, 0);
-		if (FD(evsel, 0, thread) < 0)
-			goto out_close;
+	if (cpus == NULL) {
+		/* Work around old compiler warnings about strict aliasing */
+		cpus = &empty_cpu_map.map;
 	}
 
-	return 0;
+	if (threads == NULL)
+		threads = &empty_thread_map.map;
 
-out_close:
-	while (--thread >= 0) {
-		close(FD(evsel, 0, thread));
-		FD(evsel, 0, thread) = -1;
-	}
-	return -1;
+	return __perf_evsel__open(evsel, cpus, threads);
 }
 
-int perf_evsel__open(struct perf_evsel *evsel, 
-		     struct cpu_map *cpus, struct thread_map *threads)
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
 {
-	if (threads == NULL)
-		return perf_evsel__open_per_cpu(evsel, cpus);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+}
 
-	return perf_evsel__open_per_thread(evsel, threads);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
+{
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a0ccd69..b2d755f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -37,7 +37,7 @@ struct perf_evsel {
 struct cpu_map;
 struct thread_map;
 
-struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx);
+struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 649083f..5cb6f4b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -490,6 +490,31 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
 	return EVT_HANDLED_ALL;
 }
 
+static int store_event_type(const char *orgname)
+{
+	char filename[PATH_MAX], *c;
+	FILE *file;
+	int id, n;
+
+	sprintf(filename, "%s/", debugfs_path);
+	strncat(filename, orgname, strlen(orgname));
+	strcat(filename, "/id");
+
+	c = strchr(filename, ':');
+	if (c)
+		*c = '/';
+
+	file = fopen(filename, "r");
+	if (!file)
+		return 0;
+	n = fscanf(file, "%i", &id);
+	fclose(file);
+	if (n < 1) {
+		pr_err("cannot store event ID\n");
+		return -EINVAL;
+	}
+	return perf_header__push_event(id, orgname);
+}
 
 static enum event_result parse_tracepoint_event(const char **strp,
 				    struct perf_event_attr *attr)
@@ -533,9 +558,13 @@ static enum event_result parse_tracepoint_event(const char **strp,
 		*strp += strlen(sys_name) + evt_length;
 		return parse_multiple_tracepoint_event(sys_name, evt_name,
 						       flags);
-	} else
+	} else {
+		if (store_event_type(evt_name) < 0)
+			return EVT_FAILED;
+
 		return parse_single_tracepoint_event(sys_name, evt_name,
 						     evt_length, attr, strp);
+	}
 }
 
 static enum event_result
@@ -778,41 +807,11 @@ modifier:
 	return ret;
 }
 
-static int store_event_type(const char *orgname)
-{
-	char filename[PATH_MAX], *c;
-	FILE *file;
-	int id, n;
-
-	sprintf(filename, "%s/", debugfs_path);
-	strncat(filename, orgname, strlen(orgname));
-	strcat(filename, "/id");
-
-	c = strchr(filename, ':');
-	if (c)
-		*c = '/';
-
-	file = fopen(filename, "r");
-	if (!file)
-		return 0;
-	n = fscanf(file, "%i", &id);
-	fclose(file);
-	if (n < 1) {
-		pr_err("cannot store event ID\n");
-		return -EINVAL;
-	}
-	return perf_header__push_event(id, orgname);
-}
-
 int parse_events(const struct option *opt __used, const char *str, int unset __used)
 {
 	struct perf_event_attr attr;
 	enum event_result ret;
 
-	if (strchr(str, ':'))
-		if (store_event_type(str) < 0)
-			return -1;
-
 	for (;;) {
 		memset(&attr, 0, sizeof(attr));
 		ret = parse_event_symbols(&str, &attr);
@@ -824,7 +823,7 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 
 		if (ret != EVT_HANDLED_ALL) {
 			struct perf_evsel *evsel;
-			evsel = perf_evsel__new(attr.type, attr.config,
+			evsel = perf_evsel__new(&attr,
 						nr_counters);
 			if (evsel == NULL)
 				return -1;
@@ -1014,8 +1013,15 @@ void print_events(void)
 
 int perf_evsel_list__create_default(void)
 {
-	struct perf_evsel *evsel = perf_evsel__new(PERF_TYPE_HARDWARE,
-						   PERF_COUNT_HW_CPU_CYCLES, 0);
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.config = PERF_COUNT_HW_CPU_CYCLES;
+
+	evsel = perf_evsel__new(&attr, 0);
+
 	if (evsel == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6fb4694..313dac2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1007,7 +1007,7 @@ more:
 	if (size == 0)
 		size = 8;
 
-	if (head + event->header.size >= mmap_size) {
+	if (head + event->header.size > mmap_size) {
 		if (mmaps[map_idx]) {
 			munmap(mmaps[map_idx], mmap_size);
 			mmaps[map_idx] = NULL;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2011-01-03 19:04 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2011-01-03 19:04 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Ben Hutchings (1):
      watchdog: Improve initialisation error message and documentation

Frederic Weisbecker (1):
      perf: Fix callchain hit bad cast on ascii display

Robert Richter (1):
      arch/x86/oprofile/op_model_amd.c: Perform initialisation on a single CPU


 Documentation/kernel-parameters.txt |    2 +-
 arch/x86/oprofile/op_model_amd.c    |   24 ++++++++++++++++--------
 kernel/watchdog.c                   |    3 ++-
 tools/perf/util/hist.c              |    2 +-
 4 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8b61c93..01ece1b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1759,7 +1759,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nousb		[USB] Disable the USB subsystem
 
-	nowatchdog	[KNL] Disable the lockup detector.
+	nowatchdog	[KNL] Disable the lockup detector (NMI watchdog).
 
 	nowb		[ARM]
 
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index a011bcc..7d90d47 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -630,21 +630,29 @@ static int __init_ibs_nmi(void)
 	return 0;
 }
 
-/* initialize the APIC for the IBS interrupts if available */
+/*
+ * check and reserve APIC extended interrupt LVT offset for IBS if
+ * available
+ *
+ * init_ibs() preforms implicitly cpu-local operations, so pin this
+ * thread to its current CPU
+ */
+
 static void init_ibs(void)
 {
-	ibs_caps = get_ibs_caps();
+	preempt_disable();
 
+	ibs_caps = get_ibs_caps();
 	if (!ibs_caps)
-		return;
+		goto out;
 
-	if (__init_ibs_nmi()) {
+	if (__init_ibs_nmi() < 0)
 		ibs_caps = 0;
-		return;
-	}
+	else
+		printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 
-	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n",
-	       (unsigned)ibs_caps);
+out:
+	preempt_enable();
 }
 
 static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6e3c41a..5b08215 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -364,7 +364,8 @@ static int watchdog_nmi_enable(int cpu)
 		goto out_save;
 	}
 
-	printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
+	printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
+	       cpu, PTR_ERR(event));
 	return PTR_ERR(event);
 
 	/* success path */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2022e87..76bcc35 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -356,7 +356,7 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 
 static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 				     int depth, int depth_mask, int period,
-				     u64 total_samples, int hits,
+				     u64 total_samples, u64 hits,
 				     int left_margin)
 {
 	int i;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-12-23 12:56 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-12-23 12:56 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf buildid-list: Fix error return for success

Franck Bui-Huu (3):
      perf probe: Fix use of kernel image path given by 'k' option
      perf symbols: Stop using vmlinux files with no symbols
      perf buildid-cache: Fix symbolic link handling

Masami Hiramatsu (2):
      perf tools: Fix lazy wildcard matching
      perf probe: Fix to support libdwfl older than 0.148


 tools/perf/builtin-buildid-list.c |    3 +-
 tools/perf/builtin-probe.c        |    5 ++
 tools/perf/util/header.c          |   10 +++--
 tools/perf/util/probe-event.c     |   15 +++++-
 tools/perf/util/probe-finder.c    |   85 ++++++++++++++++++++++++-------------
 tools/perf/util/string.c          |    2 +-
 tools/perf/util/symbol.c          |    4 +-
 tools/perf/util/symbol.h          |    2 +
 8 files changed, 84 insertions(+), 42 deletions(-)

diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 44a47e1..c49837d 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -36,7 +36,6 @@ static const struct option options[] = {
 
 static int __cmd_buildid_list(void)
 {
-	int err = -1;
 	struct perf_session *session;
 
 	session = perf_session__new(input_name, O_RDONLY, force, false);
@@ -49,7 +48,7 @@ static int __cmd_buildid_list(void)
 	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 
 	perf_session__delete(session);
-	return err;
+	return 0;
 }
 
 int cmd_buildid_list(int argc, const char **argv, const char *prefix __used)
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 2e000c0..add163c 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -249,6 +249,11 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 	     !params.show_lines))
 		usage_with_options(probe_usage, options);
 
+	/*
+	 * Only consider the user's kernel image path if given.
+	 */
+	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+
 	if (params.list_events) {
 		if (params.mod_events) {
 			pr_err("  Error: Don't use --list with --add/--del.\n");
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 64a85ba..7cba055 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -265,15 +265,16 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms)
 {
 	const size_t size = PATH_MAX;
-	char *filename = malloc(size),
+	char *realname = realpath(name, NULL),
+	     *filename = malloc(size),
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
-	if (filename == NULL || linkname == NULL)
+	if (realname == NULL || filename == NULL || linkname == NULL)
 		goto out_free;
 
 	len = snprintf(filename, size, "%s%s%s",
-		       debugdir, is_kallsyms ? "/" : "", name);
+		       debugdir, is_kallsyms ? "/" : "", realname);
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
@@ -283,7 +284,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 		if (is_kallsyms) {
 			 if (copyfile("/proc/kallsyms", filename))
 				goto out_free;
-		} else if (link(name, filename) && copyfile(name, filename))
+		} else if (link(realname, filename) && copyfile(name, filename))
 			goto out_free;
 	}
 
@@ -300,6 +301,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (symlink(targetname, linkname) == 0)
 		err = 0;
 out_free:
+	free(realname);
 	free(filename);
 	free(linkname);
 	return err;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 3b6a529..61191c6 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -114,6 +114,8 @@ static struct symbol *__find_kernel_function_by_name(const char *name,
 const char *kernel_get_module_path(const char *module)
 {
 	struct dso *dso;
+	struct map *map;
+	const char *vmlinux_name;
 
 	if (module) {
 		list_for_each_entry(dso, &machine.kernel_dsos, node) {
@@ -123,10 +125,17 @@ const char *kernel_get_module_path(const char *module)
 		}
 		pr_debug("Failed to find module %s.\n", module);
 		return NULL;
+	}
+
+	map = machine.vmlinux_maps[MAP__FUNCTION];
+	dso = map->dso;
+
+	vmlinux_name = symbol_conf.vmlinux_name;
+	if (vmlinux_name) {
+		if (dso__load_vmlinux(dso, map, vmlinux_name, NULL) <= 0)
+			return NULL;
 	} else {
-		dso = machine.vmlinux_maps[MAP__FUNCTION]->dso;
-		if (dso__load_vmlinux_path(dso,
-			 machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
+		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
 			pr_debug("Failed to load kernel map.\n");
 			return NULL;
 		}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 3991d73..ddf4d45 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -117,28 +117,6 @@ static void line_list__free(struct list_head *head)
 }
 
 /* Dwarf FL wrappers */
-
-static int __linux_kernel_find_elf(Dwfl_Module *mod,
-				   void **userdata,
-				   const char *module_name,
-				   Dwarf_Addr base,
-				   char **file_name, Elf **elfp)
-{
-	int fd;
-	const char *path = kernel_get_module_path(module_name);
-
-	if (path) {
-		fd = open(path, O_RDONLY);
-		if (fd >= 0) {
-			*file_name = strdup(path);
-			return fd;
-		}
-	}
-	/* If failed, try to call standard method */
-	return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
-					  file_name, elfp);
-}
-
 static char *debuginfo_path;	/* Currently dummy */
 
 static const Dwfl_Callbacks offline_callbacks = {
@@ -151,14 +129,6 @@ static const Dwfl_Callbacks offline_callbacks = {
 	.find_elf = dwfl_build_id_find_elf,
 };
 
-static const Dwfl_Callbacks kernel_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.find_elf = __linux_kernel_find_elf,
-	.section_address = dwfl_linux_kernel_module_section_address,
-};
-
 /* Get a Dwarf from offline image */
 static Dwarf *dwfl_init_offline_dwarf(int fd, Dwfl **dwflp, Dwarf_Addr *bias)
 {
@@ -185,6 +155,38 @@ error:
 	return dbg;
 }
 
+#if _ELFUTILS_PREREQ(0, 148)
+/* This method is buggy if elfutils is older than 0.148 */
+static int __linux_kernel_find_elf(Dwfl_Module *mod,
+				   void **userdata,
+				   const char *module_name,
+				   Dwarf_Addr base,
+				   char **file_name, Elf **elfp)
+{
+	int fd;
+	const char *path = kernel_get_module_path(module_name);
+
+	pr_debug2("Use file %s for %s\n", path, module_name);
+	if (path) {
+		fd = open(path, O_RDONLY);
+		if (fd >= 0) {
+			*file_name = strdup(path);
+			return fd;
+		}
+	}
+	/* If failed, try to call standard method */
+	return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
+					  file_name, elfp);
+}
+
+static const Dwfl_Callbacks kernel_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
+
+	.find_elf = __linux_kernel_find_elf,
+	.section_address = dwfl_linux_kernel_module_section_address,
+};
+
 /* Get a Dwarf from live kernel image */
 static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **dwflp,
 					  Dwarf_Addr *bias)
@@ -205,11 +207,34 @@ static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **dwflp,
 	dbg = dwfl_addrdwarf(*dwflp, addr, bias);
 	/* Here, check whether we could get a real dwarf */
 	if (!dbg) {
+		pr_debug("Failed to find kernel dwarf at %lx\n",
+			 (unsigned long)addr);
 		dwfl_end(*dwflp);
 		*dwflp = NULL;
 	}
 	return dbg;
 }
+#else
+/* With older elfutils, this just support kernel module... */
+static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr __used, Dwfl **dwflp,
+					  Dwarf_Addr *bias)
+{
+	int fd;
+	const char *path = kernel_get_module_path("kernel");
+
+	if (!path) {
+		pr_err("Failed to find vmlinux path\n");
+		return NULL;
+	}
+
+	pr_debug2("Use file %s for debuginfo\n", path);
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return NULL;
+
+	return dwfl_init_offline_dwarf(fd, dwflp, bias);
+}
+#endif
 
 /* Dwarf wrappers */
 
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 0409fc7..8fc0bd3 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -259,7 +259,7 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space)
 		if (!*pat)	/* Tail wild card matches all */
 			return true;
 		while (*str)
-			if (strglobmatch(str++, pat))
+			if (__match_glob(str++, pat, ignore_space))
 				return true;
 	}
 	return !*str && !*pat;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index d628c8d..439ab94 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1780,8 +1780,8 @@ out_failure:
 	return -1;
 }
 
-static int dso__load_vmlinux(struct dso *self, struct map *map,
-			     const char *vmlinux, symbol_filter_t filter)
+int dso__load_vmlinux(struct dso *self, struct map *map,
+		      const char *vmlinux, symbol_filter_t filter)
 {
 	int err = -1, fd;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 038f220..6c6eafd 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -166,6 +166,8 @@ void dso__sort_by_name(struct dso *self, enum map_type type);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
 int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
+int dso__load_vmlinux(struct dso *self, struct map *map,
+		      const char *vmlinux, symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *self, struct map *map,
 			   symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-12-19 15:34 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-12-19 15:34 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Dan Carpenter (1):
      perf: Fix off by one in perf_swevent_init()

John Reiser (1):
      ftrace: Have recordmcount honor endianness in fn_ELF_R_INFO

Peter Zijlstra (2):
      scripts/tags.sh: Add magic for trace-events
      perf: Fix duplicate events with multiple-pmu vs software events

Slava Pestov (1):
      tracing: Fix panic when lseek() called on "trace" opened for writing


 include/linux/perf_event.h |    1 +
 kernel/perf_event.c        |   37 ++++++++++++++++++++++++++++++-------
 kernel/trace/trace.c       |   10 +++++++++-
 scripts/recordmcount.h     |    2 +-
 scripts/tags.sh            |    4 +++-
 5 files changed, 44 insertions(+), 10 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index de2c417..4f1279e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -887,6 +887,7 @@ struct perf_cpu_context {
 	int				exclusive;
 	struct list_head		rotation_list;
 	int				jiffies_interval;
+	struct pmu			*active_pmu;
 };
 
 struct perf_output_handle {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index eac7e33..2870fee 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3824,6 +3824,8 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_task_ctx(&cpuctx->ctx, task_event);
 
 		ctx = task_event->task_ctx;
@@ -3959,6 +3961,8 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
 		ctxn = pmu->task_ctx_nr;
@@ -4144,6 +4148,8 @@ got_name:
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
 					vma->vm_flags & VM_EXEC);
 
@@ -4713,7 +4719,7 @@ static int perf_swevent_init(struct perf_event *event)
 		break;
 	}
 
-	if (event_id > PERF_COUNT_SW_MAX)
+	if (event_id >= PERF_COUNT_SW_MAX)
 		return -ENOENT;
 
 	if (!event->parent) {
@@ -5145,20 +5151,36 @@ static void *find_pmu_context(int ctxn)
 	return NULL;
 }
 
-static void free_pmu_context(void * __percpu cpu_context)
+static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
 {
-	struct pmu *pmu;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct perf_cpu_context *cpuctx;
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+
+		if (cpuctx->active_pmu == old_pmu)
+			cpuctx->active_pmu = pmu;
+	}
+}
+
+static void free_pmu_context(struct pmu *pmu)
+{
+	struct pmu *i;
 
 	mutex_lock(&pmus_lock);
 	/*
 	 * Like a real lame refcount.
 	 */
-	list_for_each_entry(pmu, &pmus, entry) {
-		if (pmu->pmu_cpu_context == cpu_context)
+	list_for_each_entry(i, &pmus, entry) {
+		if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
+			update_pmu_context(i, pmu);
 			goto out;
+		}
 	}
 
-	free_percpu(cpu_context);
+	free_percpu(pmu->pmu_cpu_context);
 out:
 	mutex_unlock(&pmus_lock);
 }
@@ -5190,6 +5212,7 @@ int perf_pmu_register(struct pmu *pmu)
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
 		INIT_LIST_HEAD(&cpuctx->rotation_list);
+		cpuctx->active_pmu = pmu;
 	}
 
 got_cpu_context:
@@ -5241,7 +5264,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	free_pmu_context(pmu->pmu_cpu_context);
+	free_pmu_context(pmu);
 }
 
 struct pmu *perf_init_event(struct perf_event *event)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c380612..f8cf959 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2338,11 +2338,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
 	return count;
 }
 
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+	if (file->f_mode & FMODE_READ)
+		return seq_lseek(file, offset, origin);
+	else
+		return 0;
+}
+
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
 	.write		= tracing_write_stub,
-	.llseek		= seq_lseek,
+	.llseek		= tracing_seek,
 	.release	= tracing_release,
 };
 
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 58e933a..3966717 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -119,7 +119,7 @@ static uint_t (*Elf_r_sym)(Elf_Rel const *rp) = fn_ELF_R_SYM;
 
 static void fn_ELF_R_INFO(Elf_Rel *const rp, unsigned sym, unsigned type)
 {
-	rp->r_info = ELF_R_INFO(sym, type);
+	rp->r_info = _w(ELF_R_INFO(sym, type));
 }
 static void (*Elf_r_info)(Elf_Rel *const rp, unsigned sym, unsigned type) = fn_ELF_R_INFO;
 
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 8509bb5..bbbe584 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -125,7 +125,9 @@ exuberant()
 	-I DEFINE_TRACE,EXPORT_TRACEPOINT_SYMBOL,EXPORT_TRACEPOINT_SYMBOL_GPL \
 	--extra=+f --c-kinds=-px                                \
 	--regex-asm='/^ENTRY\(([^)]*)\).*/\1/'                  \
-	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/'
+	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
+	--regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'		\
+	--regex-c++='/^DEFINE_EVENT\(([^,)]*).*/trace_\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--langdef=kconfig --language-force=kconfig              \

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-12-08  7:55 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-12-08  7:55 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf symbols: Fix kallsyms kernel/module map splitting
      perf record: Fix eternal wait for stillborn child

Franck Bui-Huu (1):
      perf header: Don't assume there's no attr info if no sample ids is provided

Ming Lei (1):
      perf symbols: Figure out start address of kernel map from kallsyms


 tools/perf/builtin-record.c |    6 +++-
 tools/perf/util/header.c    |   11 ++++++--
 tools/perf/util/symbol.c    |   59 ++++++++++++++++++++++++++++++++++++++----
 3 files changed, 65 insertions(+), 11 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e2c2de2..564491f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -197,7 +197,7 @@ static void sig_atexit(void)
 	if (child_pid > 0)
 		kill(child_pid, SIGTERM);
 
-	if (signr == -1)
+	if (signr == -1 || signr == SIGUSR1)
 		return;
 
 	signal(signr, SIG_DFL);
@@ -515,6 +515,7 @@ static int __cmd_record(int argc, const char **argv)
 	atexit(sig_atexit);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
+	signal(SIGUSR1, sig_handler);
 
 	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
 		perror("failed to create pipes");
@@ -606,6 +607,7 @@ static int __cmd_record(int argc, const char **argv)
 			execvp(argv[0], (char **)argv);
 
 			perror(argv[0]);
+			kill(getppid(), SIGUSR1);
 			exit(-1);
 		}
 
@@ -762,7 +764,7 @@ static int __cmd_record(int argc, const char **argv)
 		}
 	}
 
-	if (quiet)
+	if (quiet || signr == SIGUSR1)
 		return 0;
 
 	fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d7e67b1..64a85ba 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -946,11 +946,16 @@ perf_header__find_attr(u64 id, struct perf_header *header)
 
 	/*
 	 * We set id to -1 if the data file doesn't contain sample
-	 * ids. Check for this and avoid walking through the entire
-	 * list of ids which may be large.
+	 * ids. This can happen when the data file contains one type
+	 * of event and in that case, the header can still store the
+	 * event attribute information. Check for this and avoid
+	 * walking through the entire list of ids which may be large.
 	 */
-	if (id == -1ULL)
+	if (id == -1ULL) {
+		if (header->attrs > 0)
+			return &header->attr[0]->attr;
 		return NULL;
+	}
 
 	for (i = 0; i < header->attrs; i++) {
 		struct perf_header_attr *attr = header->attr[i];
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 0500895..d628c8d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -532,7 +532,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 	struct machine *machine = kmaps->machine;
 	struct map *curr_map = map;
 	struct symbol *pos;
-	int count = 0;
+	int count = 0, moved = 0;	
 	struct rb_root *root = &self->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
@@ -590,6 +590,11 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			char dso_name[PATH_MAX];
 			struct dso *dso;
 
+			if (count == 0) {
+				curr_map = map;
+				goto filter_symbol;
+			}
+
 			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
@@ -615,7 +620,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			map_groups__insert(kmaps, curr_map);
 			++kernel_range;
 		}
-
+filter_symbol:
 		if (filter && filter(curr_map, pos)) {
 discard_symbol:		rb_erase(&pos->rb_node, root);
 			symbol__delete(pos);
@@ -623,8 +628,9 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 			if (curr_map != map) {
 				rb_erase(&pos->rb_node, root);
 				symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
-			}
-			count++;
+				++moved;
+			} else
+				++count;
 		}
 	}
 
@@ -634,7 +640,7 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 		dso__set_loaded(curr_map->dso, curr_map->type);
 	}
 
-	return count;
+	return count + moved;
 }
 
 int dso__load_kallsyms(struct dso *self, const char *filename,
@@ -2125,14 +2131,55 @@ static struct dso *machine__create_kernel(struct machine *self)
 	return kernel;
 }
 
+struct process_args {
+	u64 start;
+};
+
+static int symbol__in_kernel(void *arg, const char *name,
+			     char type __used, u64 start)
+{
+	struct process_args *args = arg;
+
+	if (strchr(name, '['))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
+/* Figure out the start address of kernel map from /proc/kallsyms */
+static u64 machine__get_kernel_start_addr(struct machine *machine)
+{
+	const char *filename;
+	char path[PATH_MAX];
+	struct process_args args;
+
+	if (machine__is_host(machine)) {
+		filename = "/proc/kallsyms";
+	} else {
+		if (machine__is_default_guest(machine))
+			filename = (char *)symbol_conf.default_guest_kallsyms;
+		else {
+			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+			filename = path;
+		}
+	}
+
+	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
+		return 0;
+
+	return args.start;
+}
+
 int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
 {
 	enum map_type type;
+	u64 start = machine__get_kernel_start_addr(self);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		self->vmlinux_maps[type] = map__new2(0, kernel, type);
+		self->vmlinux_maps[type] = map__new2(start, kernel, type);
 		if (self->vmlinux_maps[type] == NULL)
 			return -1;
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-11-28 17:36 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-11-28 17:36 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Frédéric Weisbecker, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Don Zickus (1):
      x86, perf, nmi: Disable perf if counters are not accessible

Peter Zijlstra (2):
      perf, x86: Fixup Kconfig deps
      perf: Fix the software context switch counter

Thomas Gleixner (1):
      perf: Fix inherit vs. context rotation bug


 arch/x86/Kconfig                 |    2 +-
 arch/x86/kernel/cpu/perf_event.c |   20 ++++++++++++++++++++
 include/linux/perf_event.h       |   30 ++++++++++++++++--------------
 kernel/perf_event.c              |   24 ++++++++++++++++++++----
 4 files changed, 57 insertions(+), 19 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e832768..e330da2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,7 +21,7 @@ config X86
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
-	select HAVE_PERF_EVENTS if (!M386 && !M486)
+	select HAVE_PERF_EVENTS
 	select HAVE_IRQ_WORK
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index ed63101..6d75b91 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -381,6 +381,20 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
+static bool check_hw_exists(void)
+{
+	u64 val, val_new = 0;
+	int ret = 0;
+
+	val = 0xabcdUL;
+	ret |= checking_wrmsrl(x86_pmu.perfctr, val);
+	ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+	if (ret || val != val_new)
+		return false;
+
+	return true;
+}
+
 static void reserve_ds_buffers(void);
 static void release_ds_buffers(void);
 
@@ -1372,6 +1386,12 @@ void __init init_hw_perf_events(void)
 
 	pmu_check_apic();
 
+	/* sanity check that the hardware exists or is emulated */
+	if (!check_hw_exists()) {
+		pr_cont("Broken PMU hardware detected, software events only.\n");
+		return;
+	}
+
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
 	if (x86_pmu.quirks)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 40150f3..de2c417 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -850,6 +850,7 @@ struct perf_event_context {
 	int				nr_active;
 	int				is_active;
 	int				nr_stat;
+	int				rotate_disable;
 	atomic_t			refcount;
 	struct task_struct		*task;
 
@@ -908,20 +909,6 @@ extern int perf_num_counters(void);
 extern const char *perf_pmu_name(void);
 extern void __perf_event_task_sched_in(struct task_struct *task);
 extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
-
-extern atomic_t perf_task_events;
-
-static inline void perf_event_task_sched_in(struct task_struct *task)
-{
-	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
-}
-
-static inline
-void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
-{
-	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
-}
-
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
@@ -1030,6 +1017,21 @@ have_event:
 	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern atomic_t perf_task_events;
+
+static inline void perf_event_task_sched_in(struct task_struct *task)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+}
+
+static inline
+void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+{
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+
+	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
+
 extern void perf_event_mmap(struct vm_area_struct *vma);
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 671f6c8..eac7e33 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1287,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 }
@@ -1622,8 +1620,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
 {
 	raw_spin_lock(&ctx->lock);
 
-	/* Rotate the first entry last of non-pinned groups */
-	list_rotate_left(&ctx->flexible_groups);
+	/*
+	 * Rotate the first entry last of non-pinned groups. Rotation might be
+	 * disabled by the inheritance code.
+	 */
+	if (!ctx->rotate_disable)
+		list_rotate_left(&ctx->flexible_groups);
 
 	raw_spin_unlock(&ctx->lock);
 }
@@ -6162,6 +6164,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	struct perf_event *event;
 	struct task_struct *parent = current;
 	int inherited_all = 1;
+	unsigned long flags;
 	int ret = 0;
 
 	child->perf_event_ctxp[ctxn] = NULL;
@@ -6202,6 +6205,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 			break;
 	}
 
+	/*
+	 * We can't hold ctx->lock when iterating the ->flexible_group list due
+	 * to allocations, but we need to prevent rotation because
+	 * rotate_ctx() will change the list from interrupt context.
+	 */
+	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+	parent_ctx->rotate_disable = 1;
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
 	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
@@ -6209,6 +6221,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 			break;
 	}
 
+	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+	parent_ctx->rotate_disable = 0;
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
 	child_ctx = child->perf_event_ctxp[ctxn];
 
 	if (child_ctx && inherited_all) {

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-11-26 13:20 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-11-26 13:20 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf record: Handle restrictive permissions in /proc/{kallsyms,modules}

Frederic Weisbecker (1):
      x86: Ignore trap bits on single step exceptions

Jason Wessel (1):
      perf,hw_breakpoint: Initialize hardware api earlier

Masami Hiramatsu (1):
      x86/kprobes: Prevent kprobes to probe on save_args()

Peter Zijlstra (1):
      perf: Fix owner-list vs exit

Rabin Vincent (1):
      perf symbols: Remove incorrect open-coded container_of()

Rakib Mullick (1):
      x86, hw_nmi: Move backtrace_mask declaration under ARCH_HAS_NMI_WATCHDOG

Sergio Aguirre (1):
      irq_work: Drop cmpxchg() result

Steven Rostedt (3):
      tracing: Fix module use of trace_bprintk()
      tracing: Force arch_local_irq_* notrace for paravirt
      tracing: Fix recursive user stack trace


 arch/x86/include/asm/paravirt.h |   10 +++---
 arch/x86/kernel/apic/hw_nmi.c   |    7 ++--
 arch/x86/kernel/entry_64.S      |    2 +
 arch/x86/kernel/hw_breakpoint.c |    4 ++
 include/linux/hw_breakpoint.h   |    4 ++
 kernel/hw_breakpoint.c          |    3 +-
 kernel/irq_work.c               |    4 ++-
 kernel/module.c                 |   12 +++++++
 kernel/perf_event.c             |   69 ++++++++++++++++++++++++++++++++-------
 kernel/trace/trace.c            |   19 +++++++++++
 tools/perf/builtin-record.c     |   17 +++++----
 tools/perf/util/symbol.c        |    4 ++-
 12 files changed, 123 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 18e3b8a..ef99758 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -824,27 +824,27 @@ static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
 #define __PV_IS_CALLEE_SAVE(func)			\
 	((struct paravirt_callee_save) { func })
 
-static inline unsigned long arch_local_save_flags(void)
+static inline notrace unsigned long arch_local_save_flags(void)
 {
 	return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
-static inline void arch_local_irq_restore(unsigned long f)
+static inline notrace void arch_local_irq_restore(unsigned long f)
 {
 	PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
-static inline void arch_local_irq_disable(void)
+static inline notrace void arch_local_irq_disable(void)
 {
 	PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
-static inline void arch_local_irq_enable(void)
+static inline notrace void arch_local_irq_enable(void)
 {
 	PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
-static inline unsigned long arch_local_irq_save(void)
+static inline notrace unsigned long arch_local_irq_save(void)
 {
 	unsigned long f;
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index cefd694..62f6e1e 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,15 +17,16 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
 u64 hw_nmi_get_sample_period(void)
 {
 	return (u64)(cpu_khz) * 1000 * 60;
 }
 
 #ifdef ARCH_HAS_NMI_WATCHDOG
+
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
 void arch_trigger_all_cpu_backtrace(void)
 {
 	int i;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index fe2690d..e3ba417 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -295,6 +295,7 @@ ENDPROC(native_usergs_sysret64)
 	.endm
 
 /* save partial stack frame */
+	.pushsection .kprobes.text, "ax"
 ENTRY(save_args)
 	XCPT_FRAME
 	cld
@@ -334,6 +335,7 @@ ENTRY(save_args)
 	ret
 	CFI_ENDPROC
 END(save_args)
+	.popsection
 
 ENTRY(save_rest)
 	PARTIAL_FRAME 1 REST_SKIP+8
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index ff15c9d..42c5942 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -433,6 +433,10 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 	dr6_p = (unsigned long *)ERR_PTR(args->err);
 	dr6 = *dr6_p;
 
+	/* If it's a single step, TRAP bits are random */
+	if (dr6 & DR_STEP)
+		return NOTIFY_DONE;
+
 	/* Do an early return if no trap bits are set in DR6 */
 	if ((dr6 & DR_TRAP_BITS) == 0)
 		return NOTIFY_DONE;
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index a2d6ea4..d1e55fe 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -33,6 +33,8 @@ enum bp_type_idx {
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 
+extern int __init init_hw_breakpoint(void);
+
 static inline void hw_breakpoint_init(struct perf_event_attr *attr)
 {
 	memset(attr, 0, sizeof(*attr));
@@ -108,6 +110,8 @@ static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
 
 #else /* !CONFIG_HAVE_HW_BREAKPOINT */
 
+static inline int __init init_hw_breakpoint(void) { return 0; }
+
 static inline struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 2c9120f..e532582 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -620,7 +620,7 @@ static struct pmu perf_breakpoint = {
 	.read		= hw_breakpoint_pmu_read,
 };
 
-static int __init init_hw_breakpoint(void)
+int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;
 	int cpu, err_cpu;
@@ -655,6 +655,5 @@ static int __init init_hw_breakpoint(void)
 
 	return -ENOMEM;
 }
-core_initcall(init_hw_breakpoint);
 
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f16763f..90f8819 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -145,7 +145,9 @@ void irq_work_run(void)
 		 * Clear the BUSY bit and return to the free state if
 		 * no-one else claimed it meanwhile.
 		 */
-		cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+		(void)cmpxchg(&entry->next,
+			      next_flags(NULL, IRQ_WORK_BUSY),
+			      NULL);
 	}
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
diff --git a/kernel/module.c b/kernel/module.c
index 437a74a..d190664 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2326,6 +2326,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 	kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
 			   mod->num_trace_events, GFP_KERNEL);
 #endif
+#ifdef CONFIG_TRACING
+	mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
+					 sizeof(*mod->trace_bprintk_fmt_start),
+					 &mod->num_trace_bprintk_fmt);
+	/*
+	 * This section contains pointers to allocated objects in the trace
+	 * code and not scanning it leads to false positives.
+	 */
+	kmemleak_scan_area(mod->trace_bprintk_fmt_start,
+			   sizeof(*mod->trace_bprintk_fmt_start) *
+			   mod->num_trace_bprintk_fmt, GFP_KERNEL);
+#endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	/* sechdrs[0].sh_size is always zero */
 	mod->ftrace_callsites = section_objs(info, "__mcount_loc",
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index cb6c0d2..671f6c8 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -31,6 +31,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
@@ -2234,11 +2235,6 @@ int perf_event_release_kernel(struct perf_event *event)
 	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
-	mutex_lock(&event->owner->perf_event_mutex);
-	list_del_init(&event->owner_entry);
-	mutex_unlock(&event->owner->perf_event_mutex);
-	put_task_struct(event->owner);
-
 	free_event(event);
 
 	return 0;
@@ -2251,9 +2247,43 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 static int perf_release(struct inode *inode, struct file *file)
 {
 	struct perf_event *event = file->private_data;
+	struct task_struct *owner;
 
 	file->private_data = NULL;
 
+	rcu_read_lock();
+	owner = ACCESS_ONCE(event->owner);
+	/*
+	 * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+	 * !owner it means the list deletion is complete and we can indeed
+	 * free this event, otherwise we need to serialize on
+	 * owner->perf_event_mutex.
+	 */
+	smp_read_barrier_depends();
+	if (owner) {
+		/*
+		 * Since delayed_put_task_struct() also drops the last
+		 * task reference we can safely take a new reference
+		 * while holding the rcu_read_lock().
+		 */
+		get_task_struct(owner);
+	}
+	rcu_read_unlock();
+
+	if (owner) {
+		mutex_lock(&owner->perf_event_mutex);
+		/*
+		 * We have to re-check the event->owner field, if it is cleared
+		 * we raced with perf_event_exit_task(), acquiring the mutex
+		 * ensured they're done, and we can proceed with freeing the
+		 * event.
+		 */
+		if (event->owner)
+			list_del_init(&event->owner_entry);
+		mutex_unlock(&owner->perf_event_mutex);
+		put_task_struct(owner);
+	}
+
 	return perf_event_release_kernel(event);
 }
 
@@ -5677,7 +5707,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
-	get_task_struct(current);
+
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -5745,12 +5775,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	++ctx->generation;
 	mutex_unlock(&ctx->mutex);
 
-	event->owner = current;
-	get_task_struct(current);
-	mutex_lock(&current->perf_event_mutex);
-	list_add_tail(&event->owner_entry, &current->perf_event_list);
-	mutex_unlock(&current->perf_event_mutex);
-
 	return event;
 
 err_free:
@@ -5901,8 +5925,24 @@ again:
  */
 void perf_event_exit_task(struct task_struct *child)
 {
+	struct perf_event *event, *tmp;
 	int ctxn;
 
+	mutex_lock(&child->perf_event_mutex);
+	list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+				 owner_entry) {
+		list_del_init(&event->owner_entry);
+
+		/*
+		 * Ensure the list deletion is visible before we clear
+		 * the owner, closes a race against perf_release() where
+		 * we need to serialize on the owner->perf_event_mutex.
+		 */
+		smp_wmb();
+		event->owner = NULL;
+	}
+	mutex_unlock(&child->perf_event_mutex);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_exit_task_context(child, ctxn);
 }
@@ -6321,6 +6361,8 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 
 void __init perf_event_init(void)
 {
+	int ret;
+
 	perf_event_init_all_cpus();
 	init_srcu_struct(&pmus_srcu);
 	perf_pmu_register(&perf_swevent);
@@ -6328,4 +6370,7 @@ void __init perf_event_init(void)
 	perf_pmu_register(&perf_task_clock);
 	perf_tp_register();
 	perf_cpu_notifier(perf_cpu_notify);
+
+	ret = init_hw_breakpoint();
+	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b81..ee6a733 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1284,6 +1284,8 @@ void trace_dump_stack(void)
 	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
 }
 
+static DEFINE_PER_CPU(int, user_stack_count);
+
 void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
@@ -1302,6 +1304,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (unlikely(in_nmi()))
 		return;
 
+	/*
+	 * prevent recursion, since the user stack tracing may
+	 * trigger other kernel events.
+	 */
+	preempt_disable();
+	if (__this_cpu_read(user_stack_count))
+		goto out;
+
+	__this_cpu_inc(user_stack_count);
+
+
+
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -1319,6 +1333,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	save_stack_trace_user(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+	__this_cpu_dec(user_stack_count);
+
+ out:
+	preempt_enable();
 }
 
 #ifdef UNUSED
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 93bd2ff..e2c2de2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -697,17 +697,18 @@ static int __cmd_record(int argc, const char **argv)
 	if (err < 0)
 		err = event__synthesize_kernel_mmap(process_synthesized_event,
 						    session, machine, "_stext");
-	if (err < 0) {
-		pr_err("Couldn't record kernel reference relocation symbol.\n");
-		return err;
-	}
+	if (err < 0)
+		pr_err("Couldn't record kernel reference relocation symbol\n"
+		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+		       "Check /proc/kallsyms permission or run as root.\n");
 
 	err = event__synthesize_modules(process_synthesized_event,
 					session, machine);
-	if (err < 0) {
-		pr_err("Couldn't record kernel reference relocation symbol.\n");
-		return err;
-	}
+	if (err < 0)
+		pr_err("Couldn't record kernel module information.\n"
+		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+		       "Check /proc/modules permission or run as root.\n");
+
 	if (perf_guest)
 		perf_session__process_machines(session, event__synthesize_guest_os);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b39f499..0500895 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -295,7 +295,9 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 {
 	struct rb_node **p = &self->rb_node;
 	struct rb_node *parent = NULL;
-	struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s;
+	struct symbol_name_rb_node *symn, *s;
+
+	symn = container_of(sym, struct symbol_name_rb_node, sym);
 
 	while (*p != NULL) {
 		parent = *p;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-11-11 10:38 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-11-11 10:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Corey Ashford (1):
      perf: Fix usages of profile_cpu in builtin-top.c to use cpu_list

Cyrill Gorcunov (1):
      perf, ui: Eliminate stack-smashing protection compiler complaint

Peter Zijlstra (1):
      perf, amd: Use kmalloc_node(,__GFP_ZERO) for northbridge structure allocation

Stephane Eranian (1):
      perf_events: Fix time tracking in samples

Tom Zanussi (7):
      perf trace scripting: fix some small memory leaks and missing error checks
      perf trace scripting: remove system-wide param from shell scripts
      perf record: make the record options available outside perf record
      perf trace record: handle commands correctly
      perf trace: live-mode command-line cleanup
      perf trace: update Documentation with new perf trace variants
      perf trace: update usage


 arch/x86/kernel/cpu/perf_event_amd.c               |    4 +-
 include/linux/perf_event.h                         |   10 +
 kernel/perf_event.c                                |   42 ++++-
 tools/perf/Documentation/perf-trace.txt            |   57 +++++-
 tools/perf/builtin-record.c                        |   10 +-
 tools/perf/builtin-top.c                           |   12 +-
 tools/perf/builtin-trace.c                         |  209 ++++++++++++++------
 tools/perf/scripts/perl/bin/failed-syscalls-record |    2 +-
 tools/perf/scripts/perl/bin/rw-by-file-record      |    2 +-
 tools/perf/scripts/perl/bin/rw-by-pid-record       |    2 +-
 tools/perf/scripts/perl/bin/rwtop-record           |    2 +-
 tools/perf/scripts/perl/bin/wakeup-latency-record  |    2 +-
 tools/perf/scripts/perl/bin/workqueue-stats-record |    2 +-
 .../python/bin/failed-syscalls-by-pid-record       |    2 +-
 .../scripts/python/bin/futex-contention-record     |    2 +-
 tools/perf/scripts/python/bin/netdev-times-record  |    2 +-
 .../perf/scripts/python/bin/sched-migration-record |    2 +-
 tools/perf/scripts/python/bin/sctop-record         |    2 +-
 .../python/bin/syscall-counts-by-pid-record        |    2 +-
 .../perf/scripts/python/bin/syscall-counts-record  |    2 +-
 tools/perf/util/ui/util.c                          |    5 +-
 21 files changed, 271 insertions(+), 104 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 46d5844..e421b8c 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -280,11 +280,11 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	struct amd_nb *nb;
 	int i;
 
-	nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+	nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
+			  cpu_to_node(cpu));
 	if (!nb)
 		return NULL;
 
-	memset(nb, 0, sizeof(*nb));
 	nb->nb_id = nb_id;
 
 	/*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 057bf22..40150f3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -747,6 +747,16 @@ struct perf_event {
 	u64				tstamp_running;
 	u64				tstamp_stopped;
 
+	/*
+	 * timestamp shadows the actual context timing but it can
+	 * be safely used in NMI interrupt context. It reflects the
+	 * context time as it was when the event was last scheduled in.
+	 *
+	 * ctx_time already accounts for ctx->timestamp. Therefore to
+	 * compute ctx_time for a sample, simply add perf_clock().
+	 */
+	u64				shadow_ctx_time;
+
 	struct perf_event_attr		attr;
 	struct hw_perf_event		hw;
 
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 517d827..cb6c0d2 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -674,6 +674,8 @@ event_sched_in(struct perf_event *event,
 
 	event->tstamp_running += ctx->time - event->tstamp_stopped;
 
+	event->shadow_ctx_time = ctx->time - ctx->timestamp;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	ctx->nr_active++;
@@ -3396,7 +3398,8 @@ static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
 }
 
 static void perf_output_read_one(struct perf_output_handle *handle,
-				 struct perf_event *event)
+				 struct perf_event *event,
+				 u64 enabled, u64 running)
 {
 	u64 read_format = event->attr.read_format;
 	u64 values[4];
@@ -3404,11 +3407,11 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 
 	values[n++] = perf_event_count(event);
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = event->total_time_enabled +
+		values[n++] = enabled +
 			atomic64_read(&event->child_total_time_enabled);
 	}
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = event->total_time_running +
+		values[n++] = running +
 			atomic64_read(&event->child_total_time_running);
 	}
 	if (read_format & PERF_FORMAT_ID)
@@ -3421,7 +3424,8 @@ static void perf_output_read_one(struct perf_output_handle *handle,
  * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
  */
 static void perf_output_read_group(struct perf_output_handle *handle,
-			    struct perf_event *event)
+			    struct perf_event *event,
+			    u64 enabled, u64 running)
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
@@ -3431,10 +3435,10 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		values[n++] = leader->total_time_enabled;
+		values[n++] = enabled;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		values[n++] = leader->total_time_running;
+		values[n++] = running;
 
 	if (leader != event)
 		leader->pmu->read(leader);
@@ -3459,13 +3463,35 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	}
 }
 
+#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
+				 PERF_FORMAT_TOTAL_TIME_RUNNING)
+
 static void perf_output_read(struct perf_output_handle *handle,
 			     struct perf_event *event)
 {
+	u64 enabled = 0, running = 0, now, ctx_time;
+	u64 read_format = event->attr.read_format;
+
+	/*
+	 * compute total_time_enabled, total_time_running
+	 * based on snapshot values taken when the event
+	 * was last scheduled in.
+	 *
+	 * we cannot simply called update_context_time()
+	 * because of locking issue as we are called in
+	 * NMI context
+	 */
+	if (read_format & PERF_FORMAT_TOTAL_TIMES) {
+		now = perf_clock();
+		ctx_time = event->shadow_ctx_time + now;
+		enabled = ctx_time - event->tstamp_enabled;
+		running = ctx_time - event->tstamp_running;
+	}
+
 	if (event->attr.read_format & PERF_FORMAT_GROUP)
-		perf_output_read_group(handle, event);
+		perf_output_read_group(handle, event, enabled, running);
 	else
-		perf_output_read_one(handle, event);
+		perf_output_read_one(handle, event, enabled, running);
 }
 
 void perf_output_sample(struct perf_output_handle *handle,
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 122ec9d..26aff6b 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -8,7 +8,11 @@ perf-trace - Read perf.data (created by perf record) and display trace output
 SYNOPSIS
 --------
 [verse]
-'perf trace' {record <script> | report <script> [args] }
+'perf trace' [<options>]
+'perf trace' [<options>] record <script> [<record-options>] <command>
+'perf trace' [<options>] report <script> [script-args]
+'perf trace' [<options>] <script> <required-script-args> [<record-options>] <command>
+'perf trace' [<options>] <top-script> [script-args]
 
 DESCRIPTION
 -----------
@@ -24,23 +28,53 @@ There are several variants of perf trace:
   available via 'perf trace -l').  The following variants allow you to
   record and run those scripts:
 
-  'perf trace record <script>' to record the events required for 'perf
-  trace report'.  <script> is the name displayed in the output of
-  'perf trace --list' i.e. the actual script name minus any language
-  extension.
+  'perf trace record <script> <command>' to record the events required
+  for 'perf trace report'.  <script> is the name displayed in the
+  output of 'perf trace --list' i.e. the actual script name minus any
+  language extension.  If <command> is not specified, the events are
+  recorded using the -a (system-wide) 'perf record' option.
 
-  'perf trace report <script>' to run and display the results of
-  <script>.  <script> is the name displayed in the output of 'perf
+  'perf trace report <script> [args]' to run and display the results
+  of <script>.  <script> is the name displayed in the output of 'perf
   trace --list' i.e. the actual script name minus any language
   extension.  The perf.data output from a previous run of 'perf trace
   record <script>' is used and should be present for this command to
-  succeed.
+  succeed.  [args] refers to the (mainly optional) args expected by
+  the script.
+
+  'perf trace <script> <required-script-args> <command>' to both
+  record the events required for <script> and to run the <script>
+  using 'live-mode' i.e. without writing anything to disk.  <script>
+  is the name displayed in the output of 'perf trace --list' i.e. the
+  actual script name minus any language extension.  If <command> is
+  not specified, the events are recorded using the -a (system-wide)
+  'perf record' option.  If <script> has any required args, they
+  should be specified before <command>.  This mode doesn't allow for
+  optional script args to be specified; if optional script args are
+  desired, they can be specified using separate 'perf trace record'
+  and 'perf trace report' commands, with the stdout of the record step
+  piped to the stdin of the report script, using the '-o -' and '-i -'
+  options of the corresponding commands.
+
+  'perf trace <top-script>' to both record the events required for
+  <top-script> and to run the <top-script> using 'live-mode'
+  i.e. without writing anything to disk.  <top-script> is the name
+  displayed in the output of 'perf trace --list' i.e. the actual
+  script name minus any language extension; a <top-script> is defined
+  as any script name ending with the string 'top'.
+
+  [<record-options>] can be passed to the record steps of 'perf trace
+  record' and 'live-mode' variants; this isn't possible however for
+  <top-script> 'live-mode' or 'perf trace report' variants.
 
   See the 'SEE ALSO' section for links to language-specific
   information on how to write and run your own trace scripts.
 
 OPTIONS
 -------
+<command>...::
+	Any command you can specify in a shell.
+
 -D::
 --dump-raw-trace=::
         Display verbose dump of the trace data.
@@ -64,6 +98,13 @@ OPTIONS
         Generate perf-trace.[ext] starter script for given language,
         using current perf.data.
 
+-a::
+        Force system-wide collection.  Scripts run without a <command>
+        normally use -a by default, while scripts run with a <command>
+        normally don't - this option allows the latter to be run in
+        system-wide mode.
+
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-trace-perl[1],
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e75583..93bd2ff 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -790,7 +790,7 @@ static const char * const record_usage[] = {
 
 static bool force, append_file;
 
-static const struct option options[] = {
+const struct option record_options[] = {
 	OPT_CALLBACK('e', "event", NULL, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events),
@@ -839,16 +839,16 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 {
 	int i, j, err = -ENOMEM;
 
-	argc = parse_options(argc, argv, options, record_usage,
+	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc && target_pid == -1 && target_tid == -1 &&
 		!system_wide && !cpu_list)
-		usage_with_options(record_usage, options);
+		usage_with_options(record_usage, record_options);
 
 	if (force && append_file) {
 		fprintf(stderr, "Can't overwrite and append at the same time."
 				" You need to choose between -f and -A");
-		usage_with_options(record_usage, options);
+		usage_with_options(record_usage, record_options);
 	} else if (append_file) {
 		write_mode = WRITE_APPEND;
 	} else {
@@ -871,7 +871,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		if (thread_num <= 0) {
 			fprintf(stderr, "Can't find all threads of pid %d\n",
 					target_pid);
-			usage_with_options(record_usage, options);
+			usage_with_options(record_usage, record_options);
 		}
 	} else {
 		all_tids=malloc(sizeof(pid_t));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b513e40..dd62580 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -69,7 +69,6 @@ static int			target_tid			=     -1;
 static pid_t			*all_tids			=      NULL;
 static int			thread_num			=      0;
 static bool			inherit				=  false;
-static int			profile_cpu			=     -1;
 static int			nr_cpus				=      0;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
@@ -558,13 +557,13 @@ static void print_sym_table(void)
 	else
 		printf(" (all");
 
-	if (profile_cpu != -1)
-		printf(", cpu: %d)\n", profile_cpu);
+	if (cpu_list)
+		printf(", CPU%s: %s)\n", nr_cpus > 1 ? "s" : "", cpu_list);
 	else {
 		if (target_tid != -1)
 			printf(")\n");
 		else
-			printf(", %d CPUs)\n", nr_cpus);
+			printf(", %d CPU%s)\n", nr_cpus, nr_cpus > 1 ? "s" : "");
 	}
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
@@ -1187,11 +1186,10 @@ int group_fd;
 static void start_counter(int i, int counter)
 {
 	struct perf_event_attr *attr;
-	int cpu;
+	int cpu = -1;
 	int thread_index;
 
-	cpu = profile_cpu;
-	if (target_tid == -1 && profile_cpu == -1)
+	if (target_tid == -1)
 		cpu = cpumap[i];
 
 	attr = attrs + counter;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 2f8df45..86cfe38 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -10,6 +10,7 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
+#include "util/parse-options.h"
 #include "util/util.h"
 
 static char const		*script_name;
@@ -17,6 +18,7 @@ static char const		*generate_script_lang;
 static bool			debug_mode;
 static u64			last_timestamp;
 static u64			nr_unordered;
+extern const struct option	record_options[];
 
 static int default_start_script(const char *script __unused,
 				int argc __unused,
@@ -328,7 +330,7 @@ static struct script_desc *script_desc__new(const char *name)
 {
 	struct script_desc *s = zalloc(sizeof(*s));
 
-	if (s != NULL)
+	if (s != NULL && name)
 		s->name = strdup(name);
 
 	return s;
@@ -337,6 +339,8 @@ static struct script_desc *script_desc__new(const char *name)
 static void script_desc__delete(struct script_desc *s)
 {
 	free(s->name);
+	free(s->half_liner);
+	free(s->args);
 	free(s);
 }
 
@@ -537,8 +541,40 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	return path;
 }
 
+static bool is_top_script(const char *script_path)
+{
+	return ends_with((char *)script_path, "top") == NULL ? false : true;
+}
+
+static int has_required_arg(char *script_path)
+{
+	struct script_desc *desc;
+	int n_args = 0;
+	char *p;
+
+	desc = script_desc__new(NULL);
+
+	if (read_script_info(desc, script_path))
+		goto out;
+
+	if (!desc->args)
+		goto out;
+
+	for (p = desc->args; *p; p++)
+		if (*p == '<')
+			n_args++;
+out:
+	script_desc__delete(desc);
+
+	return n_args;
+}
+
 static const char * const trace_usage[] = {
-	"perf trace [<options>] <command>",
+	"perf trace [<options>]",
+	"perf trace [<options>] record <script> [<record-options>] <command>",
+	"perf trace [<options>] report <script> [script-args]",
+	"perf trace [<options>] <script> [<record-options>] <command>",
+	"perf trace [<options>] <top-script> [script-args]",
 	NULL
 };
 
@@ -564,50 +600,81 @@ static const struct option options[] = {
 	OPT_END()
 };
 
+static bool have_cmd(int argc, const char **argv)
+{
+	char **__argv = malloc(sizeof(const char *) * argc);
+
+	if (!__argv)
+		die("malloc");
+	memcpy(__argv, argv, sizeof(const char *) * argc);
+	argc = parse_options(argc, (const char **)__argv, record_options,
+			     NULL, PARSE_OPT_STOP_AT_NON_OPTION);
+	free(__argv);
+
+	return argc != 0;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __used)
 {
+	char *rec_script_path = NULL;
+	char *rep_script_path = NULL;
 	struct perf_session *session;
-	const char *suffix = NULL;
+	char *script_path = NULL;
 	const char **__argv;
-	char *script_path;
-	int i, err;
+	bool system_wide;
+	int i, j, err;
 
-	if (argc >= 2 && strncmp(argv[1], "rec", strlen("rec")) == 0) {
-		if (argc < 3) {
-			fprintf(stderr,
-				"Please specify a record script\n");
-			return -1;
-		}
-		suffix = RECORD_SUFFIX;
+	setup_scripting();
+
+	argc = parse_options(argc, argv, options, trace_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
+		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+		if (!rec_script_path)
+			return cmd_record(argc, argv, NULL);
 	}
 
-	if (argc >= 2 && strncmp(argv[1], "rep", strlen("rep")) == 0) {
-		if (argc < 3) {
+	if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
+		rep_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+		if (!rep_script_path) {
 			fprintf(stderr,
-				"Please specify a report script\n");
+				"Please specify a valid report script"
+				"(see 'perf trace -l' for listing)\n");
 			return -1;
 		}
-		suffix = REPORT_SUFFIX;
 	}
 
 	/* make sure PERF_EXEC_PATH is set for scripts */
 	perf_set_argv_exec_path(perf_exec_path());
 
-	if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
-		char *record_script_path, *report_script_path;
+	if (argc && !script_name && !rec_script_path && !rep_script_path) {
 		int live_pipe[2];
+		int rep_args;
 		pid_t pid;
 
-		record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
-		if (!record_script_path) {
-			fprintf(stderr, "record script not found\n");
-			return -1;
+		rec_script_path = get_script_path(argv[0], RECORD_SUFFIX);
+		rep_script_path = get_script_path(argv[0], REPORT_SUFFIX);
+
+		if (!rec_script_path && !rep_script_path) {
+			fprintf(stderr, " Couldn't find script %s\n\n See perf"
+				" trace -l for available scripts.\n", argv[0]);
+			usage_with_options(trace_usage, options);
 		}
 
-		report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
-		if (!report_script_path) {
-			fprintf(stderr, "report script not found\n");
-			return -1;
+		if (is_top_script(argv[0])) {
+			rep_args = argc - 1;
+		} else {
+			int rec_args;
+
+			rep_args = has_required_arg(rep_script_path);
+			rec_args = (argc - 1) - rep_args;
+			if (rec_args < 0) {
+				fprintf(stderr, " %s script requires options."
+					"\n\n See perf trace -l for available "
+					"scripts and options.\n", argv[0]);
+				usage_with_options(trace_usage, options);
+			}
 		}
 
 		if (pipe(live_pipe) < 0) {
@@ -622,60 +689,84 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 		}
 
 		if (!pid) {
+			system_wide = true;
+			j = 0;
+
 			dup2(live_pipe[1], 1);
 			close(live_pipe[0]);
 
-			__argv = malloc(6 * sizeof(const char *));
-			__argv[0] = "/bin/sh";
-			__argv[1] = record_script_path;
-			__argv[2] = "-q";
-			__argv[3] = "-o";
-			__argv[4] = "-";
-			__argv[5] = NULL;
+			if (!is_top_script(argv[0]))
+				system_wide = !have_cmd(argc - rep_args,
+							&argv[rep_args]);
+
+			__argv = malloc((argc + 6) * sizeof(const char *));
+			if (!__argv)
+				die("malloc");
+
+			__argv[j++] = "/bin/sh";
+			__argv[j++] = rec_script_path;
+			if (system_wide)
+				__argv[j++] = "-a";
+			__argv[j++] = "-q";
+			__argv[j++] = "-o";
+			__argv[j++] = "-";
+			for (i = rep_args + 1; i < argc; i++)
+				__argv[j++] = argv[i];
+			__argv[j++] = NULL;
 
 			execvp("/bin/sh", (char **)__argv);
+			free(__argv);
 			exit(-1);
 		}
 
 		dup2(live_pipe[0], 0);
 		close(live_pipe[1]);
 
-		__argv = malloc((argc + 3) * sizeof(const char *));
-		__argv[0] = "/bin/sh";
-		__argv[1] = report_script_path;
-		for (i = 2; i < argc; i++)
-			__argv[i] = argv[i];
-		__argv[i++] = "-i";
-		__argv[i++] = "-";
-		__argv[i++] = NULL;
+		__argv = malloc((argc + 4) * sizeof(const char *));
+		if (!__argv)
+			die("malloc");
+		j = 0;
+		__argv[j++] = "/bin/sh";
+		__argv[j++] = rep_script_path;
+		for (i = 1; i < rep_args + 1; i++)
+			__argv[j++] = argv[i];
+		__argv[j++] = "-i";
+		__argv[j++] = "-";
+		__argv[j++] = NULL;
 
 		execvp("/bin/sh", (char **)__argv);
+		free(__argv);
 		exit(-1);
 	}
 
-	if (suffix) {
-		script_path = get_script_path(argv[2], suffix);
-		if (!script_path) {
-			fprintf(stderr, "script not found\n");
-			return -1;
-		}
-
-		__argv = malloc((argc + 1) * sizeof(const char *));
-		__argv[0] = "/bin/sh";
-		__argv[1] = script_path;
-		for (i = 3; i < argc; i++)
-			__argv[i - 1] = argv[i];
-		__argv[argc - 1] = NULL;
+	if (rec_script_path)
+		script_path = rec_script_path;
+	if (rep_script_path)
+		script_path = rep_script_path;
+
+	if (script_path) {
+		system_wide = false;
+		j = 0;
+
+		if (rec_script_path)
+			system_wide = !have_cmd(argc - 1, &argv[1]);
+
+		__argv = malloc((argc + 2) * sizeof(const char *));
+		if (!__argv)
+			die("malloc");
+		__argv[j++] = "/bin/sh";
+		__argv[j++] = script_path;
+		if (system_wide)
+			__argv[j++] = "-a";
+		for (i = 2; i < argc; i++)
+			__argv[j++] = argv[i];
+		__argv[j++] = NULL;
 
 		execvp("/bin/sh", (char **)__argv);
+		free(__argv);
 		exit(-1);
 	}
 
-	setup_scripting();
-
-	argc = parse_options(argc, argv, options, trace_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
-
 	if (symbol__init() < 0)
 		return -1;
 	if (!script_name)
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index eb5846b..8104895 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record
index 5bfaae5..33efc86 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-record
+++ b/tools/perf/scripts/perl/bin/rw-by-file-record
@@ -1,3 +1,3 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
 
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record
index 6e0b2f7..7cb9db2 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-record
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
index 6e0b2f7..7cb9db2 100644
--- a/tools/perf/scripts/perl/bin/rwtop-record
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record
index 9f2acaa..464251a 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-record
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-record
@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -a -e sched:sched_switch -e sched:sched_wakeup $@
+perf record -e sched:sched_switch -e sched:sched_wakeup $@
 
 
 
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
index 85301f2..8edda90 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
+perf record -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index eb5846b..8104895 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/python/bin/futex-contention-record b/tools/perf/scripts/python/bin/futex-contention-record
index 5ecbb43..b1495c9 100644
--- a/tools/perf/scripts/python/bin/futex-contention-record
+++ b/tools/perf/scripts/python/bin/futex-contention-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
+perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
diff --git a/tools/perf/scripts/python/bin/netdev-times-record b/tools/perf/scripts/python/bin/netdev-times-record
index d931a82..558754b 100644
--- a/tools/perf/scripts/python/bin/netdev-times-record
+++ b/tools/perf/scripts/python/bin/netdev-times-record
@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -a -e net:net_dev_xmit -e net:net_dev_queue		\
+perf record -e net:net_dev_xmit -e net:net_dev_queue		\
 		-e net:netif_receive_skb -e net:netif_rx		\
 		-e skb:consume_skb -e skb:kfree_skb			\
 		-e skb:skb_copy_datagram_iovec -e napi:napi_poll	\
diff --git a/tools/perf/scripts/python/bin/sched-migration-record b/tools/perf/scripts/python/bin/sched-migration-record
index 17a3e9b..7493fdd 100644
--- a/tools/perf/scripts/python/bin/sched-migration-record
+++ b/tools/perf/scripts/python/bin/sched-migration-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -m 16384 -a -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
+perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
index 1fc5998..4efbfaa 100644
--- a/tools/perf/scripts/python/bin/sctop-record
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 1fc5998..4efbfaa 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 1fc5998..4efbfaa 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 9706d9d..056c695 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -104,9 +104,10 @@ out_destroy_form:
 	return rc;
 }
 
+static const char yes[] = "Yes", no[] = "No";
+
 bool ui__dialog_yesno(const char *msg)
 {
 	/* newtWinChoice should really be accepting const char pointers... */
-	char yes[] = "Yes", no[] = "No";
-	return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
+	return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1;
 }

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-10-30 18:21 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-10-30 18:21 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

One of the fixes works around a compiler bug in the jump label optimization on 
x86-32 - and while this fixes the bug it reduced our confidence in GCC getting jump 
labels right, so we also made the optimization Kconfig optional (and it defaults to 
off).

 Thanks,

	Ingo

------------------>
David Miller (1):
      jump_label: Fix unaligned traps on sparc.

H. Peter Anvin (1):
      x86, ftrace: Use safe noops, drop trap test

Jason Baron (2):
      jump label: Fix module __init section race
      jump label: Fix deadlock b/w jump_label_mutex vs. text_mutex

Santosh Shilimkar (1):
      oprofile: Fix the hang while taking the cpu offline

Steven Rostedt (3):
      jump label: Fix error with preempt disable holding mutex
      jump label: Make arch_jump_label_text_poke_early() optional
      jump label: Add work around to i386 gcc asm goto bug

Tejun Heo (1):
      oprofile: Remove deprecated use of flush_scheduled_work()


 arch/Kconfig                        |   14 ++++++
 arch/sparc/include/asm/jump_label.h |    1 +
 arch/x86/Makefile_32.cpu            |   13 +++++-
 arch/x86/kernel/alternative.c       |   69 +++++++------------------------
 drivers/oprofile/buffer_sync.c      |    2 +-
 drivers/oprofile/cpu_buffer.c       |   10 +++-
 drivers/oprofile/cpu_buffer.h       |    1 +
 drivers/oprofile/timer_int.c        |   13 ++++++
 include/linux/jump_label.h          |    7 +++-
 kernel/jump_label.c                 |   77 ++++++++++++++++++++++++++++++-----
 kernel/kprobes.c                    |   26 +++++++-----
 11 files changed, 152 insertions(+), 81 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 53d7f61..8bf0fa65 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -42,6 +42,20 @@ config KPROBES
 	  for kernel debugging, non-intrusive instrumentation and testing.
 	  If in doubt, say "N".
 
+config JUMP_LABEL
+       bool "Optimize trace point call sites"
+       depends on HAVE_ARCH_JUMP_LABEL
+       help
+         If it is detected that the compiler has support for "asm goto",
+	 the kernel will compile trace point locations with just a
+	 nop instruction. When trace points are enabled, the nop will
+	 be converted to a jump to the trace function. This technique
+	 lowers overhead and stress on the branch prediction of the
+	 processor.
+
+	 On i386, options added to the compiler flags may increase
+	 the size of the kernel slightly.
+
 config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 62e66d7..d95cf44 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -14,6 +14,7 @@
 			 "nop\n\t"				\
 			 "nop\n\t"				\
 			 ".pushsection __jump_table,  \"a\"\n\t"\
+			 ".align 4\n\t"				\
 			 ".word 1b, %l[" #label "], %c0\n\t"	\
 			 ".popsection \n\t"			\
 			 : :  "i" (key) :  : label);\
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 1255d95..f2ee1ab 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -51,7 +51,18 @@ cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 # prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
 # tracer assumptions. For i686, generic, core2 this is set by the
 # compiler anyway
-cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args)
+ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+# Work around to a bug with asm goto with first implementations of it
+# in gcc causing gcc to mess up the push and pop of the stack in some
+# uses of asm goto.
+ifeq ($(CONFIG_JUMP_LABEL), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
 
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a36bb90..0b30214 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -644,65 +644,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 
-unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+#ifdef CONFIG_X86_64
+unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
+#else
+unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+#endif
 
 void __init arch_init_ideal_nop5(void)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
-
 	/*
-	 * There is no good nop for all x86 archs.
-	 * We will default to using the P6_NOP5, but first we
-	 * will test to make sure that the nop will actually
-	 * work on this CPU. If it faults, we will then
-	 * go to a lesser efficient 5 byte nop. If that fails
-	 * we then just use a jmp as our nop. This isn't the most
-	 * efficient nop, but we can not use a multi part nop
-	 * since we would then risk being preempted in the middle
-	 * of that nop, and if we enabled tracing then, it might
-	 * cause a system crash.
+	 * There is no good nop for all x86 archs.  This selection
+	 * algorithm should be unified with the one in find_nop_table(),
+	 * but this should be good enough for now.
 	 *
-	 * TODO: check the cpuid to determine the best nop.
+	 * For cases other than the ones below, use the safe (as in
+	 * always functional) defaults above.
 	 */
-	asm volatile (
-		"ftrace_test_jmp:"
-		"jmp ftrace_test_p6nop\n"
-		"nop\n"
-		"nop\n"
-		"nop\n"  /* 2 byte jmp + 3 bytes */
-		"ftrace_test_p6nop:"
-		P6_NOP5
-		"jmp 1f\n"
-		"ftrace_test_nop5:"
-		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"1:"
-		".section .fixup, \"ax\"\n"
-		"2:	movl $1, %0\n"
-		"	jmp ftrace_test_nop5\n"
-		"3:	movl $2, %0\n"
-		"	jmp 1b\n"
-		".previous\n"
-		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
-		_ASM_EXTABLE(ftrace_test_nop5, 3b)
-		: "=r"(faulted) : "0" (faulted));
-
-	switch (faulted) {
-	case 0:
-		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
-		memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
-		break;
-	case 1:
-		pr_info("converting mcount calls to 66 66 66 66 90\n");
-		memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
-		break;
-	case 2:
-		pr_info("converting mcount calls to jmp . + 5\n");
-		memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
-		break;
-	}
-
+#ifdef CONFIG_X86_64
+	/* Don't use these on 32 bits due to broken virtualizers */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		memcpy(ideal_nop5, p6_nops[5], 5);
+#endif
 }
 #endif
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index b7e755f..a3984f4 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -190,7 +190,7 @@ void sync_stop(void)
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
 	mutex_unlock(&buffer_mutex);
-	flush_scheduled_work();
+	flush_cpu_work();
 
 	/* make sure we don't leak task structs */
 	process_task_mortuary();
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index f179ac2..59f5544 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -111,14 +111,18 @@ void start_cpu_work(void)
 
 void end_cpu_work(void)
 {
-	int i;
-
 	work_enabled = 0;
+}
+
+void flush_cpu_work(void)
+{
+	int i;
 
 	for_each_online_cpu(i) {
 		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
-		cancel_delayed_work(&b->work);
+		/* these works are per-cpu, no need for flush_sync */
+		flush_delayed_work(&b->work);
 	}
 }
 
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index 68ea16a..e1d097e 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -25,6 +25,7 @@ void free_cpu_buffers(void);
 
 void start_cpu_work(void);
 void end_cpu_work(void);
+void flush_cpu_work(void);
 
 /* CPU buffer is composed of such entries (which are
  * also used for context switch notes)
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index dc0ae4d..0107251 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -21,6 +21,7 @@
 #include "oprof.h"
 
 static DEFINE_PER_CPU(struct hrtimer, oprofile_hrtimer);
+static int ctr_running;
 
 static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
 {
@@ -33,6 +34,9 @@ static void __oprofile_hrtimer_start(void *unused)
 {
 	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
 
+	if (!ctr_running)
+		return;
+
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = oprofile_hrtimer_notify;
 
@@ -42,7 +46,10 @@ static void __oprofile_hrtimer_start(void *unused)
 
 static int oprofile_hrtimer_start(void)
 {
+	get_online_cpus();
+	ctr_running = 1;
 	on_each_cpu(__oprofile_hrtimer_start, NULL, 1);
+	put_online_cpus();
 	return 0;
 }
 
@@ -50,6 +57,9 @@ static void __oprofile_hrtimer_stop(int cpu)
 {
 	struct hrtimer *hrtimer = &per_cpu(oprofile_hrtimer, cpu);
 
+	if (!ctr_running)
+		return;
+
 	hrtimer_cancel(hrtimer);
 }
 
@@ -57,8 +67,11 @@ static void oprofile_hrtimer_stop(void)
 {
 	int cpu;
 
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		__oprofile_hrtimer_stop(cpu);
+	ctr_running = 0;
+	put_online_cpus();
 }
 
 static int __cpuinit oprofile_cpu_notify(struct notifier_block *self,
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index b67cb18..7880f18 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif
@@ -18,6 +18,8 @@ struct module;
 extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
+extern void jump_label_lock(void);
+extern void jump_label_unlock(void);
 extern void arch_jump_label_transform(struct jump_entry *entry,
 				 enum jump_label_type type);
 extern void arch_jump_label_text_poke_early(jump_label_t addr);
@@ -59,6 +61,9 @@ static inline int jump_label_text_reserved(void *start, void *end)
 	return 0;
 }
 
+static inline void jump_label_lock(void) {}
+static inline void jump_label_unlock(void) {}
+
 #endif
 
 #define COND_STMT(key, stmt)					\
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 7be868b..3b79bd9 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -39,6 +39,16 @@ struct jump_label_module_entry {
 	struct module *mod;
 };
 
+void jump_label_lock(void)
+{
+	mutex_lock(&jump_label_mutex);
+}
+
+void jump_label_unlock(void)
+{
+	mutex_unlock(&jump_label_mutex);
+}
+
 static int jump_label_cmp(const void *a, const void *b)
 {
 	const struct jump_entry *jea = a;
@@ -152,7 +162,7 @@ void jump_label_update(unsigned long key, enum jump_label_type type)
 	struct jump_label_module_entry *e_module;
 	int count;
 
-	mutex_lock(&jump_label_mutex);
+	jump_label_lock();
 	entry = get_jump_label_entry((jump_label_t)key);
 	if (entry) {
 		count = entry->nr_entries;
@@ -168,13 +178,14 @@ void jump_label_update(unsigned long key, enum jump_label_type type)
 			count = e_module->nr_entries;
 			iter = e_module->table;
 			while (count--) {
-				if (kernel_text_address(iter->code))
+				if (iter->key &&
+						kernel_text_address(iter->code))
 					arch_jump_label_transform(iter, type);
 				iter++;
 			}
 		}
 	}
-	mutex_unlock(&jump_label_mutex);
+	jump_label_unlock();
 }
 
 static int addr_conflict(struct jump_entry *entry, void *start, void *end)
@@ -231,6 +242,7 @@ out:
  * overlaps with any of the jump label patch addresses. Code
  * that wants to modify kernel text should first verify that
  * it does not overlap with any of the jump label addresses.
+ * Caller must hold jump_label_mutex.
  *
  * returns 1 if there is an overlap, 0 otherwise
  */
@@ -241,7 +253,6 @@ int jump_label_text_reserved(void *start, void *end)
 	struct jump_entry *iter_stop = __start___jump_table;
 	int conflict = 0;
 
-	mutex_lock(&jump_label_mutex);
 	iter = iter_start;
 	while (iter < iter_stop) {
 		if (addr_conflict(iter, start, end)) {
@@ -256,10 +267,16 @@ int jump_label_text_reserved(void *start, void *end)
 	conflict = module_conflict(start, end);
 #endif
 out:
-	mutex_unlock(&jump_label_mutex);
 	return conflict;
 }
 
+/*
+ * Not all archs need this.
+ */
+void __weak arch_jump_label_text_poke_early(jump_label_t addr)
+{
+}
+
 static __init int init_jump_label(void)
 {
 	int ret;
@@ -267,7 +284,7 @@ static __init int init_jump_label(void)
 	struct jump_entry *iter_stop = __stop___jump_table;
 	struct jump_entry *iter;
 
-	mutex_lock(&jump_label_mutex);
+	jump_label_lock();
 	ret = build_jump_label_hashtable(__start___jump_table,
 					 __stop___jump_table);
 	iter = iter_start;
@@ -275,7 +292,7 @@ static __init int init_jump_label(void)
 		arch_jump_label_text_poke_early(iter->code);
 		iter++;
 	}
-	mutex_unlock(&jump_label_mutex);
+	jump_label_unlock();
 	return ret;
 }
 early_initcall(init_jump_label);
@@ -366,6 +383,39 @@ static void remove_jump_label_module(struct module *mod)
 	}
 }
 
+static void remove_jump_label_module_init(struct module *mod)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	struct jump_entry *iter;
+	int i, count;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+						  module_node_next,
+						  &(e->modules), hlist) {
+				if (e_module->mod != mod)
+					continue;
+				count = e_module->nr_entries;
+				iter = e_module->table;
+				while (count--) {
+					if (within_module_init(iter->code, mod))
+						iter->key = 0;
+					iter++;
+				}
+			}
+		}
+	}
+}
+
 static int
 jump_label_module_notify(struct notifier_block *self, unsigned long val,
 			 void *data)
@@ -375,16 +425,21 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 
 	switch (val) {
 	case MODULE_STATE_COMING:
-		mutex_lock(&jump_label_mutex);
+		jump_label_lock();
 		ret = add_jump_label_module(mod);
 		if (ret)
 			remove_jump_label_module(mod);
-		mutex_unlock(&jump_label_mutex);
+		jump_label_unlock();
 		break;
 	case MODULE_STATE_GOING:
-		mutex_lock(&jump_label_mutex);
+		jump_label_lock();
 		remove_jump_label_module(mod);
-		mutex_unlock(&jump_label_mutex);
+		jump_label_unlock();
+		break;
+	case MODULE_STATE_LIVE:
+		jump_label_lock();
+		remove_jump_label_module_init(mod);
+		jump_label_unlock();
 		break;
 	}
 	return ret;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 99865c3..9737a76 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1145,14 +1145,13 @@ int __kprobes register_kprobe(struct kprobe *p)
 	if (ret)
 		return ret;
 
+	jump_label_lock();
 	preempt_disable();
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr) ||
 	    ftrace_text_reserved(p->addr, p->addr) ||
-	    jump_label_text_reserved(p->addr, p->addr)) {
-		preempt_enable();
-		return -EINVAL;
-	}
+	    jump_label_text_reserved(p->addr, p->addr))
+		goto fail_with_jump_label;
 
 	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
 	p->flags &= KPROBE_FLAG_DISABLED;
@@ -1166,10 +1165,9 @@ int __kprobes register_kprobe(struct kprobe *p)
 		 * We must hold a refcount of the probed module while updating
 		 * its code to prohibit unexpected unloading.
 		 */
-		if (unlikely(!try_module_get(probed_mod))) {
-			preempt_enable();
-			return -EINVAL;
-		}
+		if (unlikely(!try_module_get(probed_mod)))
+			goto fail_with_jump_label;
+
 		/*
 		 * If the module freed .init.text, we couldn't insert
 		 * kprobes in there.
@@ -1177,16 +1175,18 @@ int __kprobes register_kprobe(struct kprobe *p)
 		if (within_module_init((unsigned long)p->addr, probed_mod) &&
 		    probed_mod->state != MODULE_STATE_COMING) {
 			module_put(probed_mod);
-			preempt_enable();
-			return -EINVAL;
+			goto fail_with_jump_label;
 		}
 	}
 	preempt_enable();
+	jump_label_unlock();
 
 	p->nmissed = 0;
 	INIT_LIST_HEAD(&p->list);
 	mutex_lock(&kprobe_mutex);
 
+	jump_label_lock(); /* needed to call jump_label_text_reserved() */
+
 	get_online_cpus();	/* For avoiding text_mutex deadlock. */
 	mutex_lock(&text_mutex);
 
@@ -1214,12 +1214,18 @@ int __kprobes register_kprobe(struct kprobe *p)
 out:
 	mutex_unlock(&text_mutex);
 	put_online_cpus();
+	jump_label_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	if (probed_mod)
 		module_put(probed_mod);
 
 	return ret;
+
+fail_with_jump_label:
+	preempt_enable();
+	jump_label_unlock();
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(register_kprobe);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-10-13 15:21 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-10-13 15:21 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Deng-Cheng Zhu (1):
      perf, MIPS: Support cross compiling of tools/perf for MIPS

John Blackwood (1):
      perf: Fix incorrect copy_from_user() usage

Steven Rostedt (1):
      ring-buffer: Fix typo of time extends per page


 kernel/perf_event.c        |    4 +---
 kernel/trace/ring_buffer.c |    2 +-
 tools/perf/perf.h          |   12 ++++++++++++
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index db5b560..b98bed3 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2202,15 +2202,13 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	unsigned long size;
 	int ret = 0;
 	u64 value;
 
 	if (!event->attr.sample_period)
 		return -EINVAL;
 
-	size = copy_from_user(&value, arg, sizeof(value));
-	if (size != sizeof(value))
+	if (copy_from_user(&value, arg, sizeof(value)))
 		return -EFAULT;
 
 	if (!value)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 492197e..bca9637 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -405,7 +405,7 @@ static inline int test_time_stamp(u64 delta)
 #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
 
 /* Max number of timestamps that can fit on a page */
-#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_EXTEND)
 
 int ring_buffer_print_page_header(struct trace_seq *s)
 {
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index ef7aa0a..95aaf56 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -73,6 +73,18 @@ void get_term_dimensions(struct winsize *ws);
 #define cpu_relax()	asm volatile("":::"memory")
 #endif
 
+#ifdef __mips__
+#include "../../arch/mips/include/asm/unistd.h"
+#define rmb()		asm volatile(					\
+				".set	mips2\n\t"			\
+				"sync\n\t"				\
+				".set	mips0"				\
+				: /* no output */			\
+				: /* no input */			\
+				: "memory")
+#define cpu_relax()	asm volatile("" ::: "memory")
+#endif
+
 #include <time.h>
 #include <unistd.h>
 #include <sys/types.h>

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-10-05 14:49 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-10-05 14:49 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Cyrill Gorcunov (1):
      perf, x86: Handle in flight NMIs on P4 platform

Frederik Deweerdt (1):
      perf ui hist browser: Fix segfault on 'a' for annotate

Jiri Olsa (1):
      oprofile: Add Support for Intel CPU Family 6 / Model 29

Kusanagi Kouichi (1):
      perf tools: Fix build breakage

Robert Richter (1):
      oprofile, ARM: Release resources on failure

Stephane Eranian (1):
      perf trace scripting: Fix extern struct definitions


 arch/arm/oprofile/common.c              |    7 +++++--
 arch/x86/kernel/cpu/perf_event_p4.c     |    6 +++++-
 arch/x86/oprofile/nmi_int.c             |    1 +
 tools/perf/Makefile                     |    2 +-
 tools/perf/util/trace-event-scripting.c |    4 ++--
 tools/perf/util/ui/browsers/hists.c     |    2 +-
 6 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 0691176..72e09eb 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -102,6 +102,7 @@ static int op_create_counter(int cpu, int event)
 	if (IS_ERR(pevent)) {
 		ret = PTR_ERR(pevent);
 	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		perf_event_release_kernel(pevent);
 		pr_warning("oprofile: failed to enable event %d "
 				"on CPU %d\n", event, cpu);
 		ret = -EBUSY;
@@ -365,6 +366,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	ret = init_driverfs();
 	if (ret) {
 		kfree(counter_config);
+		counter_config = NULL;
 		return ret;
 	}
 
@@ -402,7 +404,6 @@ void oprofile_arch_exit(void)
 	struct perf_event *event;
 
 	if (*perf_events) {
-		exit_driverfs();
 		for_each_possible_cpu(cpu) {
 			for (id = 0; id < perf_num_counters; ++id) {
 				event = perf_events[cpu][id];
@@ -413,8 +414,10 @@ void oprofile_arch_exit(void)
 		}
 	}
 
-	if (counter_config)
+	if (counter_config) {
 		kfree(counter_config);
+		exit_driverfs();
+	}
 }
 #else
 int __init oprofile_arch_init(struct oprofile_operations *ops)
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index b560db3..2490151 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -660,8 +660,12 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		int overflow;
 
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!test_bit(idx, cpuc->active_mask)) {
+			/* catch in-flight IRQs */
+			if (__test_and_clear_bit(idx, cpuc->running))
+				handled++;
 			continue;
+		}
 
 		event = cpuc->events[idx];
 		hwc = &event->hw;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 009b819..f1575c9 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -674,6 +674,7 @@ static int __init ppro_init(char **cpu_type)
 	case 0x0f:
 	case 0x16:
 	case 0x17:
+	case 0x1d:
 		*cpu_type = "i386/core_2";
 		break;
 	case 0x1a:
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4f1fa77..1950e19 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1017,7 +1017,7 @@ builtin-revert.o wt-status.o: wt-status.h
 # we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
 # we depend the various files onto their directories.
 DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
-$(DIRECTORY_DEPS): $(sort $(dir $(DIRECTORY_DEPS)))
+$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
 # In the second step, we make a rule to actually create these directories
 $(sort $(dir $(DIRECTORY_DEPS))):
 	$(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 7ea983a..f7af2fc 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -97,7 +97,7 @@ void setup_python_scripting(void)
 	register_python_scripting(&python_scripting_unsupported_ops);
 }
 #else
-struct scripting_ops python_scripting_ops;
+extern struct scripting_ops python_scripting_ops;
 
 void setup_python_scripting(void)
 {
@@ -158,7 +158,7 @@ void setup_perl_scripting(void)
 	register_perl_scripting(&perl_scripting_unsupported_ops);
 }
 #else
-struct scripting_ops perl_scripting_ops;
+extern struct scripting_ops perl_scripting_ops;
 
 void setup_perl_scripting(void)
 {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index dafdf67..6866aa4 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -773,7 +773,7 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 
 			switch (key) {
 			case 'a':
-				if (browser->selection->map == NULL &&
+				if (browser->selection->map == NULL ||
 				    browser->selection->map->dso->annotate_warned)
 					continue;
 				goto do_annotate;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-09-26  8:38 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-09-26  8:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Jeremy Fitzhardinge (1):
      tracing/x86: Don't use mcount in pvclock.c

Robert Richter (1):
      perf, x86: Catch spurious interrupts after disabling counters

Steven Rostedt (1):
      tracing/x86: Don't use mcount in kvmclock.c


 arch/x86/kernel/Makefile         |    2 ++
 arch/x86/kernel/cpu/perf_event.c |   12 +++++++++++-
 2 files changed, 13 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0925676..fedf32a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -11,6 +11,8 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
+CFLAGS_REMOVE_pvclock.o = -pg
+CFLAGS_REMOVE_kvmclock.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3efdf28..03a5b03 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -102,6 +102,7 @@ struct cpu_hw_events {
 	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
 	int			n_events;
@@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event)
 	x86_perf_event_set_period(event);
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
+	__set_bit(idx, cpuc->running);
 	x86_pmu.enable(event);
 	perf_event_update_userpage(event);
 
@@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!test_bit(idx, cpuc->active_mask)) {
+			/*
+			 * Though we deactivated the counter some cpus
+			 * might still deliver spurious interrupts still
+			 * in flight. Catch them:
+			 */
+			if (__test_and_clear_bit(idx, cpuc->running))
+				handled++;
 			continue;
+		}
 
 		event = cpuc->events[idx];
 		hwc = &event->hw;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-09-21 19:39 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-09-21 19:39 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (1):
      x86: Fix instruction breakpoint encoding

Masami Hiramatsu (1):
      kprobes: Fix Kconfig dependency

Matt Helsley (1):
      hw breakpoints: Fix pid namespace bug

Patrick Simmons (1):
      oprofile: Add Support for Intel CPU Family 6 / Model 22 (Intel Celeron 540)


 arch/Kconfig                         |    4 +-
 arch/x86/include/asm/hw_breakpoint.h |    2 +-
 arch/x86/kernel/hw_breakpoint.c      |   40 ++++++++++++++++-----------------
 arch/x86/oprofile/nmi_int.c          |    4 ++-
 kernel/hw_breakpoint.c               |    3 +-
 5 files changed, 27 insertions(+), 26 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 4877a8c..fe48fc7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -32,8 +32,9 @@ config HAVE_OPROFILE
 
 config KPROBES
 	bool "Kprobes"
-	depends on KALLSYMS && MODULES
+	depends on MODULES
 	depends on HAVE_KPROBES
+	select KALLSYMS
 	help
 	  Kprobes allows you to trap at almost any kernel address and
 	  execute a callback function.  register_kprobe() establishes
@@ -45,7 +46,6 @@ config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
-	select KALLSYMS_ALL
 
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 528a11e..824ca07 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -20,7 +20,7 @@ struct arch_hw_breakpoint {
 #include <linux/list.h>
 
 /* Available HW breakpoint length encodings */
-#define X86_BREAKPOINT_LEN_X		0x00
+#define X86_BREAKPOINT_LEN_X		0x40
 #define X86_BREAKPOINT_LEN_1		0x40
 #define X86_BREAKPOINT_LEN_2		0x44
 #define X86_BREAKPOINT_LEN_4		0x4c
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index a474ec3..ff15c9d 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -206,11 +206,27 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
-	/* Len */
-	switch (x86_len) {
-	case X86_BREAKPOINT_LEN_X:
+	/* Type */
+	switch (x86_type) {
+	case X86_BREAKPOINT_EXECUTE:
+		if (x86_len != X86_BREAKPOINT_LEN_X)
+			return -EINVAL;
+
+		*gen_type = HW_BREAKPOINT_X;
 		*gen_len = sizeof(long);
+		return 0;
+	case X86_BREAKPOINT_WRITE:
+		*gen_type = HW_BREAKPOINT_W;
 		break;
+	case X86_BREAKPOINT_RW:
+		*gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Len */
+	switch (x86_len) {
 	case X86_BREAKPOINT_LEN_1:
 		*gen_len = HW_BREAKPOINT_LEN_1;
 		break;
@@ -229,21 +245,6 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 		return -EINVAL;
 	}
 
-	/* Type */
-	switch (x86_type) {
-	case X86_BREAKPOINT_EXECUTE:
-		*gen_type = HW_BREAKPOINT_X;
-		break;
-	case X86_BREAKPOINT_WRITE:
-		*gen_type = HW_BREAKPOINT_W;
-		break;
-	case X86_BREAKPOINT_RW:
-		*gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	return 0;
 }
 
@@ -316,9 +317,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	ret = -EINVAL;
 
 	switch (info->len) {
-	case X86_BREAKPOINT_LEN_X:
-		align = sizeof(long) -1;
-		break;
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
 		break;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cfe4faa..009b819 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -671,7 +671,9 @@ static int __init ppro_init(char **cpu_type)
 	case 14:
 		*cpu_type = "i386/core";
 		break;
-	case 15: case 23:
+	case 0x0f:
+	case 0x16:
+	case 0x17:
 		*cpu_type = "i386/core_2";
 		break;
 	case 0x1a:
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index d71a987..c7c2aed 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -433,7 +433,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
+						triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-09-10 14:26 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-09-10 14:26 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Chris Wright (1):
      tracing: t_start: reset FTRACE_ITER_HASH in case of seek/pread

Jovi Zhang (1):
      perf symbols: Fix multiple initialization of symbol system

Li Zefan (1):
      perf, trace: Fix module leak

Masami Hiramatsu (5):
      tracing/kprobe: Fix a memory leak in error case
      perf probe: Fix return probe support
      perf probe: Fix handling of arguments names
      tracing/kprobes: Fix handling of argument names
      tracing/kprobe: Fix handling of C-unlike argument names

Peter Zijlstra (1):
      perf: Fix CPU hotplug

Steven Rostedt (1):
      tracing: Do not allow llseek to set_ftrace_filter


 kernel/perf_event.c             |    6 ++--
 kernel/trace/ftrace.c           |    4 ++-
 kernel/trace/trace_event_perf.c |    3 ++
 kernel/trace/trace_kprobe.c     |   43 ++++++++++++++++++++++----------------
 tools/perf/util/probe-event.c   |    1 +
 tools/perf/util/probe-finder.c  |   42 ++++++++++++++++++++++++++-----------
 tools/perf/util/symbol.c        |    7 ++++++
 tools/perf/util/symbol.h        |    3 +-
 8 files changed, 73 insertions(+), 36 deletions(-)

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 657555a..db5b560 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -5761,15 +5761,15 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		perf_event_exit_cpu(cpu);
 		break;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7cb1f45..fa7ece6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1510,6 +1510,8 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
+		/* reset in case of seek/pread */
+		iter->flags &= ~FTRACE_ITER_HASH;
 		return iter;
 	}
 
@@ -2416,7 +2418,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = no_llseek,
 	.release = ftrace_filter_release,
 };
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 000e6e8..31cc4cb 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -91,6 +91,8 @@ int perf_trace_init(struct perf_event *p_event)
 		    tp_event->class && tp_event->class->reg &&
 		    try_module_get(tp_event->mod)) {
 			ret = perf_trace_event_init(tp_event, p_event);
+			if (ret)
+				module_put(tp_event->mod);
 			break;
 		}
 	}
@@ -146,6 +148,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 		}
 	}
 out:
+	module_put(tp_event->mod);
 	mutex_unlock(&event_mutex);
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8b27c98..544301d 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -514,8 +514,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
 				struct pt_regs *regs);
 
-/* Check the name is good for event/group */
-static int check_event_name(const char *name)
+/* Check the name is good for event/group/fields */
+static int is_good_name(const char *name)
 {
 	if (!isalpha(*name) && *name != '_')
 		return 0;
@@ -557,7 +557,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	else
 		tp->rp.kp.pre_handler = kprobe_dispatcher;
 
-	if (!event || !check_event_name(event)) {
+	if (!event || !is_good_name(event)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -567,7 +567,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	if (!tp->call.name)
 		goto error;
 
-	if (!group || !check_event_name(group)) {
+	if (!group || !is_good_name(group)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -883,7 +883,7 @@ static int create_trace_probe(int argc, char **argv)
 	int i, ret = 0;
 	int is_return = 0, is_delete = 0;
 	char *symbol = NULL, *event = NULL, *group = NULL;
-	char *arg, *tmp;
+	char *arg;
 	unsigned long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
@@ -992,26 +992,36 @@ static int create_trace_probe(int argc, char **argv)
 	/* parse arguments */
 	ret = 0;
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+		/* Increment count for freeing args in error case */
+		tp->nr_args++;
+
 		/* Parse argument name */
 		arg = strchr(argv[i], '=');
-		if (arg)
+		if (arg) {
 			*arg++ = '\0';
-		else
+			tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+		} else {
 			arg = argv[i];
+			/* If argument name is omitted, set "argN" */
+			snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
+			tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+		}
 
-		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
 		if (!tp->args[i].name) {
-			pr_info("Failed to allocate argument%d name '%s'.\n",
-				i, argv[i]);
+			pr_info("Failed to allocate argument[%d] name.\n", i);
 			ret = -ENOMEM;
 			goto error;
 		}
-		tmp = strchr(tp->args[i].name, ':');
-		if (tmp)
-			*tmp = '_';	/* convert : to _ */
+
+		if (!is_good_name(tp->args[i].name)) {
+			pr_info("Invalid argument[%d] name: %s\n",
+				i, tp->args[i].name);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		if (conflict_field_name(tp->args[i].name, tp->args, i)) {
-			pr_info("Argument%d name '%s' conflicts with "
+			pr_info("Argument[%d] name '%s' conflicts with "
 				"another field.\n", i, argv[i]);
 			ret = -EINVAL;
 			goto error;
@@ -1020,12 +1030,9 @@ static int create_trace_probe(int argc, char **argv)
 		/* Parse fetch argument */
 		ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
 		if (ret) {
-			pr_info("Parse error at argument%d. (%d)\n", i, ret);
-			kfree(tp->args[i].name);
+			pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
 			goto error;
 		}
-
-		tp->nr_args++;
 	}
 
 	ret = register_trace_probe(tp);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e72f05c..fcc16e4 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1539,6 +1539,7 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 		goto error;
 	}
 	tev->point.offset = pev->point.offset;
+	tev->point.retprobe = pev->point.retprobe;
 	tev->nargs = pev->nargs;
 	if (tev->nargs) {
 		tev->args = zalloc(sizeof(struct probe_trace_arg)
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 5251366..32b81f7 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -686,6 +686,25 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 	char buf[32], *ptr;
 	int ret, nscopes;
 
+	if (!is_c_varname(pf->pvar->var)) {
+		/* Copy raw parameters */
+		pf->tvar->value = strdup(pf->pvar->var);
+		if (pf->tvar->value == NULL)
+			return -ENOMEM;
+		if (pf->pvar->type) {
+			pf->tvar->type = strdup(pf->pvar->type);
+			if (pf->tvar->type == NULL)
+				return -ENOMEM;
+		}
+		if (pf->pvar->name) {
+			pf->tvar->name = strdup(pf->pvar->name);
+			if (pf->tvar->name == NULL)
+				return -ENOMEM;
+		} else
+			pf->tvar->name = NULL;
+		return 0;
+	}
+
 	if (pf->pvar->name)
 		pf->tvar->name = strdup(pf->pvar->name);
 	else {
@@ -700,19 +719,6 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 	if (pf->tvar->name == NULL)
 		return -ENOMEM;
 
-	if (!is_c_varname(pf->pvar->var)) {
-		/* Copy raw parameters */
-		pf->tvar->value = strdup(pf->pvar->var);
-		if (pf->tvar->value == NULL)
-			return -ENOMEM;
-		if (pf->pvar->type) {
-			pf->tvar->type = strdup(pf->pvar->type);
-			if (pf->tvar->type == NULL)
-				return -ENOMEM;
-		}
-		return 0;
-	}
-
 	pr_debug("Searching '%s' variable in context.\n",
 		 pf->pvar->var);
 	/* Search child die for local variables and parameters. */
@@ -783,6 +789,16 @@ static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 		/* This function has no name. */
 		tev->point.offset = (unsigned long)pf->addr;
 
+	/* Return probe must be on the head of a subprogram */
+	if (pf->pev->point.retprobe) {
+		if (tev->point.offset != 0) {
+			pr_warning("Return probe must be on the head of"
+				   " a real function\n");
+			return -EINVAL;
+		}
+		tev->point.retprobe = true;
+	}
+
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1a36773..b2f5ae9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2268,6 +2268,9 @@ static int setup_list(struct strlist **list, const char *list_str,
 
 int symbol__init(void)
 {
+	if (symbol_conf.initialized)
+		return 0;
+
 	elf_version(EV_CURRENT);
 	if (symbol_conf.sort_by_name)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
@@ -2293,6 +2296,7 @@ int symbol__init(void)
 		       symbol_conf.sym_list_str, "symbol") < 0)
 		goto out_free_comm_list;
 
+	symbol_conf.initialized = true;
 	return 0;
 
 out_free_dso_list:
@@ -2304,11 +2308,14 @@ out_free_comm_list:
 
 void symbol__exit(void)
 {
+	if (!symbol_conf.initialized)
+		return;
 	strlist__delete(symbol_conf.sym_list);
 	strlist__delete(symbol_conf.dso_list);
 	strlist__delete(symbol_conf.comm_list);
 	vmlinux_path__exit();
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
+	symbol_conf.initialized = false;
 }
 
 int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index b7a8da4..ea95c27 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -69,7 +69,8 @@ struct symbol_conf {
 			show_nr_samples,
 			use_callchain,
 			exclude_other,
-			show_cpu_utilization;
+			show_cpu_utilization,
+			initialized;
 	const char	*vmlinux_name,
 			*source_prefix,
 			*field_sep;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-08-25 17:44 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-08-25 17:44 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Paul Mackerras, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      tracing/trace_stack: Fix stack trace on ppc64

Lin Ming (1):
      perf, x86, Pentium4: Clear the P4_CCCR_FORCE_OVF flag


 arch/x86/kernel/cpu/perf_event_p4.c |    2 ++
 kernel/trace/trace_stack.c          |    2 +-
 2 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index febb12c..7e578e9 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -497,6 +497,8 @@ static int p4_hw_config(struct perf_event *event)
 		event->hw.config |= event->attr.config &
 			(p4_config_pack_escr(P4_ESCR_MASK_HT) |
 			 p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED));
+
+		event->hw.config &= ~P4_CCCR_FORCE_OVF;
 	}
 
 	rc = x86_setup_perfctr(event);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 056468e..a6b7e0e 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -249,7 +249,7 @@ static int trace_lookup_stack(struct seq_file *m, long i)
 {
 	unsigned long addr = stack_dump_trace[i];
 
-	return seq_printf(m, "%pF\n", (void *)addr);
+	return seq_printf(m, "%pS\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-08-24 19:06 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-08-24 19:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Steven Rostedt, Thomas Gleixner,
	Arjan van de Ven, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arjan van de Ven (1):
      tracing: Fix timer tracing

Peter Zijlstra (1):
      watchdog: Don't throttle the watchdog


 include/trace/events/timer.h |    8 ++++++--
 kernel/watchdog.c            |    3 +++
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index c624126..425bcfe 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -81,14 +81,16 @@ TRACE_EVENT(timer_expire_entry,
 	TP_STRUCT__entry(
 		__field( void *,	timer	)
 		__field( unsigned long,	now	)
+		__field( void *,	function)
 	),
 
 	TP_fast_assign(
 		__entry->timer		= timer;
 		__entry->now		= jiffies;
+		__entry->function	= timer->function;
 	),
 
-	TP_printk("timer=%p now=%lu", __entry->timer, __entry->now)
+	TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now)
 );
 
 /**
@@ -200,14 +202,16 @@ TRACE_EVENT(hrtimer_expire_entry,
 	TP_STRUCT__entry(
 		__field( void *,	hrtimer	)
 		__field( s64,		now	)
+		__field( void *,	function)
 	),
 
 	TP_fast_assign(
 		__entry->hrtimer	= hrtimer;
 		__entry->now		= now->tv64;
+		__entry->function	= hrtimer->function;
 	),
 
-	TP_printk("hrtimer=%p now=%llu", __entry->hrtimer,
+	TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
 		  (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now }))
  );
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 613bc1f..0d53c8e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -206,6 +206,9 @@ void watchdog_overflow_callback(struct perf_event *event, int nmi,
 		 struct perf_sample_data *data,
 		 struct pt_regs *regs)
 {
+	/* Ensure the watchdog never gets throttled */
+	event->hw.interrupts = 0;
+
 	if (__get_cpu_var(watchdog_nmi_touch) == true) {
 		__get_cpu_var(watchdog_nmi_touch) = false;
 		return;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-08-19 14:55 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-08-19 14:55 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Steven Rostedt, Frédéric Weisbecker, Thomas Gleixner

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
KUMANO Syuhei (1):
      kprobes/x86: Fix the return address of multiple kretprobes

Kusanagi Kouichi (1):
      perf tools: Fix build error on read only source.

Zhang, Yanmin (1):
      perf, x86: Fix Intel-nhm PMU programming errata workaround


 arch/x86/kernel/cpu/perf_event_intel.c |   81 +++++++++++++++++++++++++-------
 arch/x86/kernel/kprobes.c              |   25 +++++++++-
 tools/perf/Makefile                    |   14 ++++--
 tools/perf/feature-tests.mak           |    2 +-
 4 files changed, 96 insertions(+), 26 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 214ac86..d8d86d0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -491,33 +491,78 @@ static void intel_pmu_enable_all(int added)
  *   Intel Errata AAP53  (model 30)
  *   Intel Errata BD53   (model 44)
  *
- * These chips need to be 'reset' when adding counters by programming
- * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5
- * either in sequence on the same PMC or on different PMCs.
+ * The official story:
+ *   These chips need to be 'reset' when adding counters by programming the
+ *   magic three (non-counting) events 0x4300B5, 0x4300D2, and 0x4300B1 either
+ *   in sequence on the same PMC or on different PMCs.
+ *
+ * In practise it appears some of these events do in fact count, and
+ * we need to programm all 4 events.
  */
-static void intel_pmu_nhm_enable_all(int added)
+static void intel_pmu_nhm_workaround(void)
 {
-	if (added) {
-		struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-		int i;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	static const unsigned long nhm_magic[4] = {
+		0x4300B5,
+		0x4300D2,
+		0x4300B1,
+		0x4300B1
+	};
+	struct perf_event *event;
+	int i;
+
+	/*
+	 * The Errata requires below steps:
+	 * 1) Clear MSR_IA32_PEBS_ENABLE and MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 2) Configure 4 PERFEVTSELx with the magic events and clear
+	 *    the corresponding PMCx;
+	 * 3) set bit0~bit3 of MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 4) Clear MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 5) Clear 4 pairs of ERFEVTSELx and PMCx;
+	 */
+
+	/*
+	 * The real steps we choose are a little different from above.
+	 * A) To reduce MSR operations, we don't run step 1) as they
+	 *    are already cleared before this function is called;
+	 * B) Call x86_perf_event_update to save PMCx before configuring
+	 *    PERFEVTSELx with magic number;
+	 * C) With step 5), we do clear only when the PERFEVTSELx is
+	 *    not used currently.
+	 * D) Call x86_perf_event_set_period to restore PMCx;
+	 */
 
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2);
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
+	/* We always operate 4 pairs of PERF Counters */
+	for (i = 0; i < 4; i++) {
+		event = cpuc->events[i];
+		if (event)
+			x86_perf_event_update(event);
+	}
 
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+	for (i = 0; i < 4; i++) {
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
+		wrmsrl(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
+	}
 
-		for (i = 0; i < 3; i++) {
-			struct perf_event *event = cpuc->events[i];
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
 
-			if (!event)
-				continue;
+	for (i = 0; i < 4; i++) {
+		event = cpuc->events[i];
 
+		if (event) {
+			x86_perf_event_set_period(event);
 			__x86_pmu_enable_event(&event->hw,
-					       ARCH_PERFMON_EVENTSEL_ENABLE);
-		}
+					ARCH_PERFMON_EVENTSEL_ENABLE);
+		} else
+			wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
 	}
+}
+
+static void intel_pmu_nhm_enable_all(int added)
+{
+	if (added)
+		intel_pmu_nhm_workaround();
 	intel_pmu_enable_all(added);
 }
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1bfb6cf..770ebfb 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -709,6 +709,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	struct hlist_node *node, *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -740,14 +741,34 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			/* another task is sharing our hash bucket */
 			continue;
 
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__get_cpu_var(current_kprobe) = &ri->rp->kp;
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
 			__get_cpu_var(current_kprobe) = NULL;
 		}
 
-		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)
@@ -759,8 +780,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			break;
 	}
 
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcb9700..4f1fa77 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -5,6 +5,12 @@ endif
 # The default target of this Makefile is...
 all::
 
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
+
 # Define V=1 to have a more verbose compile.
 # Define V=2 to have an even more verbose compile.
 #
@@ -931,15 +937,15 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
 $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
-	$(QUIET_GEN)$(RM) $@ $@+ && \
+	$(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \
 	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
 	    -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
 	    -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
 	    -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
 	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
-	    $@.sh >$@+ && \
-	chmod +x $@+ && \
-	mv $@+ $(OUTPUT)$@
+	    $@.sh > $(OUTPUT)$@+ && \
+	chmod +x $(OUTPUT)$@+ && \
+	mv $(OUTPUT)$@+ $(OUTPUT)$@
 
 configure: configure.ac
 	$(QUIET_GEN)$(RM) $@ $<+ && \
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
index ddb68e6..7a7b608 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/feature-tests.mak
@@ -113,7 +113,7 @@ endef
 # try-cc
 # Usage: option = $(call try-cc, source-to-build, cc-options)
 try-cc = $(shell sh -c						  \
-	'TMP="$(TMPOUT).$$$$";			 		  \
+	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
 	 echo "$(1)" |						  \
 	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
 	 rm -f "$$TMP"')

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-08-18  8:14 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-08-18  8:14 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Steven Rostedt, Frédéric Weisbecker, Paul Mackerras,
	Andrew Morton, Thomas Gleixner


Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

The trace_events.c seqfile conversion makes up for the bulk of the diffstat - 
this was needed for a fix.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf annotate tui: Fix exit and RIGHT keys handling

Bernd Petrovitsch (1):
      perf tools: Fix build on POSIX shells

Huang Ying (1):
      tracing: Fix ring_buffer_read_page reading out of page boundary

Marcin Slusarz (1):
      tracing: Sanitize value returned from write(trace_marker, "...", len)

Mike Frysinger (1):
      tracing: Extend recordmcount to better support Blackfin mcount

Randy Dunlap (1):
      latencytop: Fix kconfig dependency warnings

Shaohua Li (1):
      tracing: Fix an unallocated memory access in function_graph

Steven Rostedt (1):
      tracing/events: Convert format output to seq_file


 kernel/trace/ring_buffer.c             |    3 +
 kernel/trace/trace.c                   |   11 ++-
 kernel/trace/trace_events.c            |  207 ++++++++++++++++++++++----------
 kernel/trace/trace_functions_graph.c   |   10 ++-
 lib/Kconfig.debug                      |    5 +-
 scripts/recordmcount.pl                |    7 +-
 tools/perf/Makefile                    |   16 ++-
 tools/perf/util/ui/browsers/annotate.c |    3 +-
 8 files changed, 185 insertions(+), 77 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3632ce8..19cccc3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3846,6 +3846,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 			rpos = reader->read;
 			pos += size;
 
+			if (rpos >= commit)
+				break;
+
 			event = rb_reader_event(cpu_buffer);
 			size = rb_event_length(event);
 		} while (len > size);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ba14a22..9ec59f5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3463,6 +3463,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
 	char *buf;
+	size_t written;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -3484,11 +3485,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	} else
 		buf[cnt] = '\0';
 
-	cnt = mark_printk("%s", buf);
+	written = mark_printk("%s", buf);
 	kfree(buf);
-	*fpos += cnt;
+	*fpos += written;
 
-	return cnt;
+	/* don't tell userspace we wrote more - it might confuse them */
+	if (written > cnt)
+		written = cnt;
+
+	return written;
 }
 
 static int tracing_clock_show(struct seq_file *m, void *v)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 09b4fa6..4c758f1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -598,88 +598,165 @@ out:
 	return ret;
 }
 
-static void print_event_fields(struct trace_seq *s, struct list_head *head)
+enum {
+	FORMAT_HEADER		= 1,
+	FORMAT_PRINTFMT		= 2,
+};
+
+static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	struct ftrace_event_call *call = m->private;
 	struct ftrace_event_field *field;
+	struct list_head *head;
 
-	list_for_each_entry_reverse(field, head, link) {
-		/*
-		 * Smartly shows the array type(except dynamic array).
-		 * Normal:
-		 *	field:TYPE VAR
-		 * If TYPE := TYPE[LEN], it is shown:
-		 *	field:TYPE VAR[LEN]
-		 */
-		const char *array_descriptor = strchr(field->type, '[');
+	(*pos)++;
 
-		if (!strncmp(field->type, "__data_loc", 10))
-			array_descriptor = NULL;
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		head = &ftrace_common_fields;
 
-		if (!array_descriptor) {
-			trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					field->type, field->name, field->offset,
-					field->size, !!field->is_signed);
-		} else {
-			trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					(int)(array_descriptor - field->type),
-					field->type, field->name,
-					array_descriptor, field->offset,
-					field->size, !!field->is_signed);
-		}
+		if (unlikely(list_empty(head)))
+			return NULL;
+
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		return field;
+
+	case FORMAT_PRINTFMT:
+		/* all done */
+		return NULL;
+	}
+
+	head = trace_get_fields(call);
+
+	/*
+	 * To separate common fields from event fields, the
+	 * LSB is set on the first event field. Clear it in case.
+	 */
+	v = (void *)((unsigned long)v & ~1L);
+
+	field = v;
+	/*
+	 * If this is a common field, and at the end of the list, then
+	 * continue with main list.
+	 */
+	if (field->link.prev == &ftrace_common_fields) {
+		if (unlikely(list_empty(head)))
+			return NULL;
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		/* Set the LSB to notify f_show to print an extra newline */
+		field = (struct ftrace_event_field *)
+			((unsigned long)field | 1);
+		return field;
 	}
+
+	/* If we are done tell f_show to print the format */
+	if (field->link.prev == head)
+		return (void *)FORMAT_PRINTFMT;
+
+	field = list_entry(field->link.prev, struct ftrace_event_field, link);
+
+	return field;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-		  loff_t *ppos)
+static void *f_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call = filp->private_data;
-	struct list_head *head;
-	struct trace_seq *s;
-	char *buf;
-	int r;
+	loff_t l = 0;
+	void *p;
 
-	if (*ppos)
+	/* Start by showing the header */
+	if (!*pos)
+		return (void *)FORMAT_HEADER;
+
+	p = (void *)FORMAT_HEADER;
+	do {
+		p = f_next(m, p, &l);
+	} while (p && l < *pos);
+
+	return p;
+}
+
+static int f_show(struct seq_file *m, void *v)
+{
+	struct ftrace_event_call *call = m->private;
+	struct ftrace_event_field *field;
+	const char *array_descriptor;
+
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		seq_printf(m, "name: %s\n", call->name);
+		seq_printf(m, "ID: %d\n", call->event.type);
+		seq_printf(m, "format:\n");
 		return 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
+	case FORMAT_PRINTFMT:
+		seq_printf(m, "\nprint fmt: %s\n",
+			   call->print_fmt);
+		return 0;
+	}
 
-	trace_seq_init(s);
+	/*
+	 * To separate common fields from event fields, the
+	 * LSB is set on the first event field. Clear it and
+	 * print a newline if it is set.
+	 */
+	if ((unsigned long)v & 1) {
+		seq_putc(m, '\n');
+		v = (void *)((unsigned long)v & ~1L);
+	}
 
-	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->event.type);
-	trace_seq_printf(s, "format:\n");
+	field = v;
 
-	/* print common fields */
-	print_event_fields(s, &ftrace_common_fields);
+	/*
+	 * Smartly shows the array type(except dynamic array).
+	 * Normal:
+	 *	field:TYPE VAR
+	 * If TYPE := TYPE[LEN], it is shown:
+	 *	field:TYPE VAR[LEN]
+	 */
+	array_descriptor = strchr(field->type, '[');
 
-	trace_seq_putc(s, '\n');
+	if (!strncmp(field->type, "__data_loc", 10))
+		array_descriptor = NULL;
 
-	/* print event specific fields */
-	head = trace_get_fields(call);
-	print_event_fields(s, head);
+	if (!array_descriptor)
+		seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   field->type, field->name, field->offset,
+			   field->size, !!field->is_signed);
+	else
+		seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   (int)(array_descriptor - field->type),
+			   field->type, field->name,
+			   array_descriptor, field->offset,
+			   field->size, !!field->is_signed);
 
-	r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
+	return 0;
+}
 
-	if (!r) {
-		/*
-		 * ug!  The format output is bigger than a PAGE!!
-		 */
-		buf = "FORMAT TOO BIG\n";
-		r = simple_read_from_buffer(ubuf, cnt, ppos,
-					      buf, strlen(buf));
-		goto out;
-	}
+static void f_stop(struct seq_file *m, void *p)
+{
+}
 
-	r = simple_read_from_buffer(ubuf, cnt, ppos,
-				    s->buffer, s->len);
- out:
-	kfree(s);
-	return r;
+static const struct seq_operations trace_format_seq_ops = {
+	.start		= f_start,
+	.next		= f_next,
+	.stop		= f_stop,
+	.show		= f_show,
+};
+
+static int trace_format_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_event_call *call = inode->i_private;
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &trace_format_seq_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = call;
+
+	return 0;
 }
 
 static ssize_t
@@ -877,8 +954,10 @@ static const struct file_operations ftrace_enable_fops = {
 };
 
 static const struct file_operations ftrace_event_format_fops = {
-	.open = tracing_open_generic,
-	.read = event_format_read,
+	.open = trace_format_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
 };
 
 static const struct file_operations ftrace_event_id_fops = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6bff236..6f23369 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * if the output fails.
 			 */
 			data->ent = *curr;
-			data->ret = *next;
+			/*
+			 * If the next event is not a return type, then
+			 * we only care about what type it is. Otherwise we can
+			 * safely copy the entire event.
+			 */
+			if (next->ent.type == TRACE_GRAPH_RET)
+				data->ret = *next;
+			else
+				data->ret.ent.type = next->ent.type;
 		}
 	}
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9e06b7f..1b4afd2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -994,13 +994,16 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 
 config LATENCYTOP
 	bool "Latency measuring infrastructure"
+	depends on HAVE_LATENCYTOP_SUPPORT
+	depends on DEBUG_KERNEL
+	depends on STACKTRACE_SUPPORT
+	depends on PROC_FS
 	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select KALLSYMS_ALL
 	select STACKTRACE
 	select SCHEDSTATS
 	select SCHED_DEBUG
-	depends on HAVE_LATENCYTOP_SUPPORT
 	help
 	  Enable this option if you want to use the LatencyTOP tool
 	  to find out which userspace is blocking on what kernel operations.
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 0171060..e67f054 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -159,6 +159,7 @@ my $section_regex;	# Find the start of a section
 my $function_regex;	# Find the name of a function
 			#    (return offset and func name)
 my $mcount_regex;	# Find the call site to mcount (return offset)
+my $mcount_adjust;	# Address adjustment to mcount offset
 my $alignment;		# The .align value to use for $mcount_section
 my $section_type;	# Section header plus possible alignment command
 my $can_use_local = 0; 	# If we can use local function references
@@ -213,6 +214,7 @@ $section_regex = "Disassembly of section\\s+(\\S+):";
 $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
 $section_type = '@progbits';
+$mcount_adjust = 0;
 $type = ".long";
 
 if ($arch eq "x86_64") {
@@ -351,6 +353,9 @@ if ($arch eq "x86_64") {
 } elsif ($arch eq "microblaze") {
     # Microblaze calls '_mcount' instead of plain 'mcount'.
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
+} elsif ($arch eq "blackfin") {
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s__mcount\$";
+    $mcount_adjust = -4;
 } else {
     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 }
@@ -511,7 +516,7 @@ while (<IN>) {
     }
     # is this a call site to mcount? If so, record it to print later
     if ($text_found && /$mcount_regex/) {
-	push(@offsets, hex $1);
+	push(@offsets, (hex $1) + $mcount_adjust);
     }
 }
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 41abb90..dcb9700 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -157,10 +157,6 @@ all::
 #
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
 
-$(shell sh -c 'mkdir -p $(OUTPUT)scripts/{perl,python}/Perf-Trace-Util/' 2> /dev/null)
-$(shell sh -c 'mkdir -p $(OUTPUT)util/{ui/browsers,scripting-engines}/' 2> /dev/null)
-$(shell sh -c 'mkdir $(OUTPUT)bench' 2> /dev/null)
-
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 -include $(OUTPUT)PERF-VERSION-FILE
@@ -186,8 +182,6 @@ ifeq ($(ARCH),x86_64)
         ARCH := x86
 endif
 
-$(shell sh -c 'mkdir -p $(OUTPUT)arch/$(ARCH)/util/' 2> /dev/null)
-
 # CFLAGS and LDFLAGS are for the users to override from the command line.
 
 #
@@ -268,6 +262,7 @@ export prefix bindir sharedir sysconfdir
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
 RM = rm -f
+MKDIR = mkdir
 TAR = tar
 FIND = find
 INSTALL = install
@@ -838,6 +833,7 @@ ifndef V
 	QUIET_CC       = @echo '   ' CC $@;
 	QUIET_AR       = @echo '   ' AR $@;
 	QUIET_LINK     = @echo '   ' LINK $@;
+	QUIET_MKDIR    = @echo '   ' MKDIR $@;
 	QUIET_BUILT_IN = @echo '   ' BUILTIN $@;
 	QUIET_GEN      = @echo '   ' GEN $@;
 	QUIET_SUBDIR0  = +@subdir=
@@ -1012,6 +1008,14 @@ $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
 builtin-revert.o wt-status.o: wt-status.h
 
+# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
+# we depend the various files onto their directories.
+DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
+$(DIRECTORY_DEPS): $(sort $(dir $(DIRECTORY_DEPS)))
+# In the second step, we make a rule to actually create these directories
+$(sort $(dir $(DIRECTORY_DEPS))):
+	$(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
+
 $(LIB_FILE): $(LIB_OBJS)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
 
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 55ff792..a90273e 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -146,6 +146,7 @@ static int annotate_browser__run(struct annotate_browser *self,
 		return -1;
 
 	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
+	newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
 
 	nd = self->curr_hot;
 	if (nd) {
@@ -178,7 +179,7 @@ static int annotate_browser__run(struct annotate_browser *self,
 	}
 out:
 	ui_browser__hide(&self->b);
-	return 0;
+	return es->u.key;
 }
 
 int hist_entry__tui_annotate(struct hist_entry *self)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-07-23 19:41 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-07-23 19:41 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Fr??d??ric Weisbecker,
	Peter Zijlstra, Paul Mackerras, Thomas Gleixner, Andrew Morton,
	Steven Rostedt

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf annotate: Fix handling of goto labels that are valid hex numbers

Conny Seidel (1):
      perf tools: Fix fallback to cplus_demangle() when bfd_demangle() is not available

Frederic Weisbecker (1):
      perf: Fix various display bugs with parent filtering

Gui Jianfeng (1):
      perf symbols: Fix directory descriptor leaking

Sam Ravnborg (1):
      tracing: Properly align linker defined symbols


 include/asm-generic/vmlinux.lds.h |   10 +++++++++
 tools/perf/Makefile               |   40 +++++++++++++++++++-----------------
 tools/perf/util/hist.c            |   29 ++++++++++++++++++++------
 tools/perf/util/symbol.c          |   17 +++++++++------
 4 files changed, 63 insertions(+), 33 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 48c5299..4b5902a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -63,6 +63,12 @@
 /* Align . to a 8 byte boundary equals to maximum function alignment. */
 #define ALIGN_FUNCTION()  . = ALIGN(8)
 
+/*
+ * Align to a 32 byte boundary equal to the
+ * alignment gcc 4.5 uses for a struct
+ */
+#define STRUCT_ALIGN() . = ALIGN(32)
+
 /* The actual configuration determine if the init/exit sections
  * are handled as text/data or they can be discarded (which
  * often happens at runtime)
@@ -166,7 +172,11 @@
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
+									\
+	STRUCT_ALIGN();							\
 	FTRACE_EVENTS()							\
+									\
+	STRUCT_ALIGN();							\
 	TRACE_SYSCALLS()
 
 /*
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3d8f31e..d75c28a 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -600,30 +600,32 @@ endif
 
 ifdef NO_DEMANGLE
 	BASIC_CFLAGS += -DNO_DEMANGLE
-else ifdef HAVE_CPLUS_DEMANGLE
-	EXTLIBS += -liberty
-	BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
 else
-	has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
-
-	ifeq ($(has_bfd),y)
-		EXTLIBS += -lbfd
+	ifdef HAVE_CPLUS_DEMANGLE
+		EXTLIBS += -liberty
+		BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
 	else
-		has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
-		ifeq ($(has_bfd_iberty),y)
-			EXTLIBS += -lbfd -liberty
+		has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
+
+		ifeq ($(has_bfd),y)
+			EXTLIBS += -lbfd
 		else
-			has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
-			ifeq ($(has_bfd_iberty_z),y)
-				EXTLIBS += -lbfd -liberty -lz
+			has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
+			ifeq ($(has_bfd_iberty),y)
+				EXTLIBS += -lbfd -liberty
 			else
-				has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
-				ifeq ($(has_cplus_demangle),y)
-					EXTLIBS += -liberty
-					BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
+				has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
+				ifeq ($(has_bfd_iberty_z),y)
+					EXTLIBS += -lbfd -liberty -lz
 				else
-					msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
-					BASIC_CFLAGS += -DNO_DEMANGLE
+					has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
+					ifeq ($(has_cplus_demangle),y)
+						EXTLIBS += -liberty
+						BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
+					else
+						msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
+						BASIC_CFLAGS += -DNO_DEMANGLE
+					endif
 				endif
 			endif
 		endif
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 07f89b6..784ee0b 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -631,9 +631,14 @@ int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
 			u64 session_total)
 {
 	char bf[512];
-	hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
-			     show_displacement, displacement,
-			     true, session_total);
+	int ret;
+
+	ret = hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
+				   show_displacement, displacement,
+				   true, session_total);
+	if (!ret)
+		return 0;
+
 	return fprintf(fp, "%s\n", bf);
 }
 
@@ -762,6 +767,7 @@ size_t hists__fprintf(struct hists *self, struct hists *pair,
 print_entries:
 	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int cnt;
 
 		if (show_displacement) {
 			if (h->pair != NULL)
@@ -771,8 +777,13 @@ print_entries:
 				displacement = 0;
 			++position;
 		}
-		ret += hist_entry__fprintf(h, pair, show_displacement,
-					   displacement, fp, self->stats.total_period);
+		cnt = hist_entry__fprintf(h, pair, show_displacement,
+					  displacement, fp, self->stats.total_period);
+		/* Ignore those that didn't match the parent filter */
+		if (!cnt)
+			continue;
+
+		ret += cnt;
 
 		if (symbol_conf.use_callchain)
 			ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period);
@@ -965,13 +976,17 @@ static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
 		 * Parse hexa addresses followed by ':'
 		 */
 		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':' || tmp == tmp2)
+		if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
 			line_ip = -1;
 	}
 
 	if (line_ip != -1) {
-		u64 start = map__rip_2objdump(self->ms.map, sym->start);
+		u64 start = map__rip_2objdump(self->ms.map, sym->start),
+		    end = map__rip_2objdump(self->ms.map, sym->end);
+
 		offset = line_ip - start;
+		if (offset < 0 || (u64)line_ip > end)
+			offset = -1;
 	}
 
 	objdump_line = objdump_line__new(offset, line);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b63e571..5b27683 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1443,6 +1443,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 {
 	struct dirent *dent;
 	DIR *dir = opendir(dir_name);
+	int ret = 0;
 
 	if (!dir) {
 		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
@@ -1465,8 +1466,9 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 
 			snprintf(path, sizeof(path), "%s/%s",
 				 dir_name, dent->d_name);
-			if (map_groups__set_modules_path_dir(self, path) < 0)
-				goto failure;
+			ret = map_groups__set_modules_path_dir(self, path);
+			if (ret < 0)
+				goto out;
 		} else {
 			char *dot = strrchr(dent->d_name, '.'),
 			     dso_name[PATH_MAX];
@@ -1487,17 +1489,18 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 				 dir_name, dent->d_name);
 
 			long_name = strdup(path);
-			if (long_name == NULL)
-				goto failure;
+			if (long_name == NULL) {
+				ret = -1;
+				goto out;
+			}
 			dso__set_long_name(map->dso, long_name);
 			dso__kernel_module_get_build_id(map->dso, "");
 		}
 	}
 
-	return 0;
-failure:
+out:
 	closedir(dir);
-	return -1;
+	return ret;
 }
 
 static char *get_kernel_version(const char *root_dir)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-07-16 17:30 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-07-16 17:30 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Peter Zijlstra,
	Andrew Morton, Thomas Gleixner, Fr??d??ric Weisbecker,
	Steven Rostedt

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

Note, we included the version fixes because external tools started to rely on 
perf command output and we got a request to have more precise versioning 
available.

This tree also includes the simpler fix from Steve for syscalls.h. There was a 
second patch being worked on as well - this one fixes the crash for the time 
being.

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (2):
      perf: Resurrect flat callchains
      perf: Sync callchains with period based hits

Steven Rostedt (1):
      tracing: Add alignment to syscall metadata declarations

Thavidu Ranatunga (2):
      perf: Version String fix, using kernel version
      perf: Version String fix, for fallback if not from git


 include/linux/syscalls.h         |    6 ++++--
 tools/perf/builtin-report.c      |    2 +-
 tools/perf/util/PERF-VERSION-GEN |   17 +++++++++--------
 tools/perf/util/callchain.c      |   35 ++++++++++++++++++-----------------
 tools/perf/util/callchain.h      |    5 ++++-
 5 files changed, 36 insertions(+), 29 deletions(-)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7f614ce..13ebb54 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -124,7 +124,8 @@ extern struct trace_event_functions enter_syscall_print_funcs;
 extern struct trace_event_functions exit_syscall_print_funcs;
 
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
-	static struct syscall_metadata __syscall_meta_##sname;		\
+	static struct syscall_metadata					\
+	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_enter_##sname;		\
 	static struct ftrace_event_call __used				\
@@ -138,7 +139,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
-	static struct syscall_metadata __syscall_meta_##sname;		\
+	static struct syscall_metadata					\
+	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_exit_##sname;		\
 	static struct ftrace_event_call __used				\
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3592057..fd7407c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -107,7 +107,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 		goto out_free_syms;
 	err = 0;
 	if (symbol_conf.use_callchain) {
-		err = append_chain(he->callchain, data->callchain, syms);
+		err = append_chain(he->callchain, data->callchain, syms, data->period);
 		if (err)
 			goto out_free_syms;
 	}
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 49ece79..97d7656 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -5,17 +5,13 @@ if [ $# -eq 1 ]  ; then
 fi
 
 GVF=${OUTPUT}PERF-VERSION-FILE
-DEF_VER=v0.0.2.PERF
 
 LF='
 '
 
-# First see if there is a version file (included in release tarballs),
-# then try git-describe, then default.
-if test -f version
-then
-	VN=$(cat version) || VN="$DEF_VER"
-elif test -d .git -o -f .git &&
+# First check if there is a .git to get the version from git describe
+# otherwise try to get the version from the kernel makefile
+if test -d ../../.git -o -f ../../.git &&
 	VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
 	case "$VN" in
 	*$LF*) (exit 1) ;;
@@ -27,7 +23,12 @@ elif test -d .git -o -f .git &&
 then
 	VN=$(echo "$VN" | sed -e 's/-/./g');
 else
-	VN="$DEF_VER"
+	eval `grep '^VERSION\s*=' ../../Makefile|tr -d ' '`
+	eval `grep '^PATCHLEVEL\s*=' ../../Makefile|tr -d ' '`
+	eval `grep '^SUBLEVEL\s*=' ../../Makefile|tr -d ' '`
+	eval `grep '^EXTRAVERSION\s*=' ../../Makefile|tr -d ' '`
+
+	VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}"
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 62b69ad..52c777e 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -230,7 +230,7 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 
 static void
 add_child(struct callchain_node *parent, struct resolved_chain *chain,
-	  int start)
+	  int start, u64 period)
 {
 	struct callchain_node *new;
 
@@ -238,7 +238,7 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
 	fill_node(new, chain, start);
 
 	new->children_hit = 0;
-	new->hit = 1;
+	new->hit = period;
 }
 
 /*
@@ -248,7 +248,8 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
  */
 static void
 split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local)
+		struct callchain_list *to_split, int idx_parents, int idx_local,
+		u64 period)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -275,41 +276,41 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
 	/* create a new child for the new branch if any */
 	if (idx_total < chain->nr) {
 		parent->hit = 0;
-		add_child(parent, chain, idx_total);
-		parent->children_hit++;
+		add_child(parent, chain, idx_total, period);
+		parent->children_hit += period;
 	} else {
-		parent->hit = 1;
+		parent->hit = period;
 	}
 }
 
 static int
 __append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start);
+	       unsigned int start, u64 period);
 
 static void
 __append_chain_children(struct callchain_node *root,
 			struct resolved_chain *chain,
-			unsigned int start)
+			unsigned int start, u64 period)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start);
+		unsigned int ret = __append_chain(rnode, chain, start, period);
 
 		if (!ret)
 			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start);
+	add_child(root, chain, start, period);
 
 inc_children_hit:
-	root->children_hit++;
+	root->children_hit += period;
 }
 
 static int
 __append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start)
+	       unsigned int start, u64 period)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -345,18 +346,18 @@ __append_chain(struct callchain_node *root, struct resolved_chain *chain,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start);
+		split_add_child(root, chain, cnode, start, i - start, period);
 		return 0;
 	}
 
 	/* we match 100% of the path, increment the hit */
 	if (i - start == root->val_nr && i == chain->nr) {
-		root->hit++;
+		root->hit += period;
 		return 0;
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, i);
+	__append_chain_children(root, chain, i, period);
 
 	return 0;
 }
@@ -380,7 +381,7 @@ static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
 
 
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms)
+		 struct map_symbol *syms, u64 period)
 {
 	struct resolved_chain *filtered;
 
@@ -397,7 +398,7 @@ int append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	if (!filtered->nr)
 		goto end;
 
-	__append_chain_children(root, filtered, 0);
+	__append_chain_children(root, filtered, 0, period);
 end:
 	free(filtered);
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1ca73e4..f2e9ee1 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -49,6 +49,9 @@ static inline void callchain_init(struct callchain_node *node)
 	INIT_LIST_HEAD(&node->brothers);
 	INIT_LIST_HEAD(&node->children);
 	INIT_LIST_HEAD(&node->val);
+
+	node->parent = NULL;
+	node->hit = 0;
 }
 
 static inline u64 cumul_hits(struct callchain_node *node)
@@ -58,7 +61,7 @@ static inline u64 cumul_hits(struct callchain_node *node)
 
 int register_callchain_param(struct callchain_param *param);
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms);
+		 struct map_symbol *syms, u64 period);
 
 bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
 #endif	/* __PERF_CALLCHAIN_H */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-07-08  4:36 Frederic Weisbecker
  2010-07-08  4:40 ` Frederic Weisbecker
@ 2010-07-08  6:36 ` Ingo Molnar
  1 sibling, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-07-08  6:36 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: LKML, Peter Zijlstra, Arnaldo Carvalho de Melo, Paul Mackerras,
	2 . 6 . 31 . x-2 . 6 . 34 . x


* Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Ingo,
> 
> Please pull the perf/urgent branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/urgent
> 
> This resurrects flat and graph (absolute fractals) callchains.
> All tested with and without newt.
> 
> As you know there are still things to fix: filtering by parents (probably a
> regression) and dso multiple callchains (not a regression).
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (2):
>       perf: Resurrect flat callchains
>       perf: Sync callchains with period based hits
> 
> 
>  tools/perf/builtin-report.c |    2 +-
>  tools/perf/util/callchain.c |   35 ++++++++++++++++++-----------------
>  tools/perf/util/callchain.h |    5 ++++-
>  3 files changed, 23 insertions(+), 19 deletions(-)

Pulled, thanks Frederic!

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-07-08  4:36 Frederic Weisbecker
@ 2010-07-08  4:40 ` Frederic Weisbecker
  2010-07-08  6:36 ` Ingo Molnar
  1 sibling, 0 replies; 376+ messages in thread
From: Frederic Weisbecker @ 2010-07-08  4:40 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: LKML, Peter Zijlstra, Arnaldo Carvalho de Melo, Paul Mackerras,
	2 . 6 . 31 . x-2 . 6 . 34 . x

On Thu, Jul 08, 2010 at 06:36:49AM +0200, Frederic Weisbecker wrote:
> Ingo,
> 
> Please pull the perf/urgent branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/urgent
> 
> This resurrects flat and graph (absolute fractals) callchains.
> All tested with and without newt.
> 
> As you know there are still things to fix: filtering by parents (probably a
> regression) and dso multiple callchains (not a regression).
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (2):
>       perf: Resurrect flat callchains
>       perf: Sync callchains with period based hits



BTW, the second is not that small for a regression fix. If that's a problem,
tell me and I will move this one to perf/core.


^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-07-08  4:36 Frederic Weisbecker
  2010-07-08  4:40 ` Frederic Weisbecker
  2010-07-08  6:36 ` Ingo Molnar
  0 siblings, 2 replies; 376+ messages in thread
From: Frederic Weisbecker @ 2010-07-08  4:36 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: LKML, Frederic Weisbecker, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Paul Mackerras,
	2 . 6 . 31 . x-2 . 6 . 34 . x

Ingo,

Please pull the perf/urgent branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
	perf/urgent

This resurrects flat and graph (absolute fractals) callchains.
All tested with and without newt.

As you know there are still things to fix: filtering by parents (probably a
regression) and dso multiple callchains (not a regression).

Thanks,
	Frederic
---

Frederic Weisbecker (2):
      perf: Resurrect flat callchains
      perf: Sync callchains with period based hits


 tools/perf/builtin-report.c |    2 +-
 tools/perf/util/callchain.c |   35 ++++++++++++++++++-----------------
 tools/perf/util/callchain.h |    5 ++++-
 3 files changed, 23 insertions(+), 19 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-07-04 20:24 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-07-04 20:24 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Thomas Gleixner, Fr??d??ric Weisbecker, Steven Rostedt,
	Paul Mackerras, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (1):
      x86: Send a SIGTRAP for user icebp traps

Gui Jianfeng (1):
      perf tools: Fix find tids routine by excluding "." and ".."

Vince Weaver (1):
      perf, x86: Fix incorrect branches event on AMD CPUs


 arch/x86/kernel/cpu/perf_event_amd.c |    4 ++--
 arch/x86/kernel/traps.c              |   11 ++++++++++-
 tools/perf/util/thread.c             |   11 ++++++++++-
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 611df11..c2897b7 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -102,8 +102,8 @@ static const u64 amd_perfmon_event_map[] =
   [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
   [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0080,
   [PERF_COUNT_HW_CACHE_MISSES]		= 0x0081,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 };
 
 static u64 amd_pmu_event_map(int hw_event)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 142d70c..725ef4d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -526,6 +526,7 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
+	int user_icebp = 0;
 	unsigned long dr6;
 	int si_code;
 
@@ -534,6 +535,14 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	/* Filter out all the reserved bits which are preset to 1 */
 	dr6 &= ~DR6_RESERVED;
 
+	/*
+	 * If dr6 has no reason to give us about the origin of this trap,
+	 * then it's very likely the result of an icebp/int01 trap.
+	 * User wants a sigtrap for that.
+	 */
+	if (!dr6 && user_mode(regs))
+		user_icebp = 1;
+
 	/* Catch kmemcheck conditions first of all! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		return;
@@ -575,7 +584,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 		regs->flags &= ~X86_EFLAGS_TF;
 	}
 	si_code = get_si_code(tsk->thread.debugreg6);
-	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
+	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
 	preempt_conditional_cli(regs);
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1f7ecd4..9a448b4 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,15 @@
 #include "util.h"
 #include "debug.h"
 
+/* Skip "." and ".." directories */
+static int filter(const struct dirent *dir)
+{
+	if (dir->d_name[0] == '.')
+		return 0;
+	else
+		return 1;
+}
+
 int find_all_tid(int pid, pid_t ** all_tid)
 {
 	char name[256];
@@ -16,7 +25,7 @@ int find_all_tid(int pid, pid_t ** all_tid)
 	int i;
 
 	sprintf(name, "/proc/%d/task", pid);
-	items = scandir(name, &namelist, NULL, NULL);
+	items = scandir(name, &namelist, filter, NULL);
 	if (items <= 0)
                 return -ENOENT;
 	*all_tid = malloc(sizeof(pid_t) * items);


^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-06-10 10:25 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-06-10 10:25 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Paul Mackerras, Fr??d??ric Weisbecker, Steven Rostedt,
	Robert Richter, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf symbols: Set the DSO long name when using symbol_conf.vmlinux_name

Denis Kirjanov (1):
      powerpc/oprofile: fix potential buffer overrun in op_model_cell.c

Oleg Nesterov (1):
      tracing: Fix null pointer deref with SEND_SIG_FORCED

Peter Zijlstra (1):
      perf: Fix signed comparison in perf_adjust_period()


 arch/powerpc/oprofile/op_model_cell.c |    2 +-
 include/trace/events/signal.h         |    3 ++-
 kernel/perf_event.c                   |    5 ++++-
 tools/perf/util/symbol.c              |    8 ++++++--
 4 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index 2c9e522..7fd90d0 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -1077,7 +1077,7 @@ static int calculate_lfsr(int n)
 		index = ENTRIES-1;
 
 	/* make sure index is valid */
-	if ((index > ENTRIES) || (index < 0))
+	if ((index >= ENTRIES) || (index < 0))
 		index = ENTRIES-1;
 
 	return initial_lfsr[index];
diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index 814566c..17df434 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -10,7 +10,8 @@
 
 #define TP_STORE_SIGINFO(__entry, info)				\
 	do {							\
-		if (info == SEND_SIG_NOINFO) {			\
+		if (info == SEND_SIG_NOINFO ||			\
+		    info == SEND_SIG_FORCED) {			\
 			__entry->errno	= 0;			\
 			__entry->code	= SI_USER;		\
 		} else if (info == SEND_SIG_PRIV) {		\
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 31d6afe..ff86c55 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1507,6 +1507,9 @@ do {					\
 		divisor = nsec * frequency;
 	}
 
+	if (!divisor)
+		return dividend;
+
 	return div64_u64(dividend, divisor);
 }
 
@@ -1529,7 +1532,7 @@ static int perf_event_start(struct perf_event *event)
 static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	u64 period, sample_period;
+	s64 period, sample_period;
 	s64 delta;
 
 	period = perf_calculate_period(event, nsec, count);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7fd6b15..b63e571 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1745,7 +1745,12 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	if (symbol_conf.vmlinux_name != NULL) {
 		err = dso__load_vmlinux(self, map,
 					symbol_conf.vmlinux_name, filter);
-		goto out_try_fixup;
+		if (err > 0) {
+			dso__set_long_name(self,
+					   strdup(symbol_conf.vmlinux_name));
+			goto out_fixup;
+		}
+		return err;
 	}
 
 	if (vmlinux_path != NULL) {
@@ -1806,7 +1811,6 @@ do_kallsyms:
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	free(kallsyms_allocated_filename);
 
-out_try_fixup:
 	if (err > 0) {
 out_fixup:
 		if (kallsyms_filename != NULL)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-06-02 12:28 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-06-02 12:28 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Fr??d??ric Weisbecker, Thomas Gleixner, Steven Rostedt,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf buildid-list: Fix --with-hits event processing

Borislav Petkov (1):
      perf-record: Check correct pid when forking

Frederic Weisbecker (4):
      perf_events: Fix unincremented buffer base on partial copy
      perf: Process comm events by tid
      perf: Use event__process_task from perf sched
      perf: Do the comm inheritance per thread in event__process_task

Konstantin Stepanyuk (1):
      perf hist: fix objdump output parsing

Peter Zijlstra (4):
      perf_events: Fix races and clean up perf_event and perf_mmap_data interaction
      perf_events: Fix races in group composition
      perf_events, trace: Fix probe unregister race
      perf_events, trace: Fix perf_trace_destroy(), mutex went missing

Pierre Tardy (1):
      perf scripts python: Give field dict to unhandled callback

Randy Dunlap (1):
      blktrace: Fix new kernel-doc warnings

Stephane Eranian (1):
      perf_events: Fix event scheduling issues introduced by transactional API


 arch/x86/kernel/cpu/perf_event.c                   |   22 ++
 include/linux/perf_event.h                         |    9 +-
 include/trace/ftrace.h                             |    2 +-
 kernel/perf_event.c                                |  327 ++++++++++++--------
 kernel/trace/blktrace.c                            |    2 +
 kernel/trace/trace_event_perf.c                    |   15 +-
 kernel/trace/trace_kprobe.c                        |    4 +-
 kernel/trace/trace_syscalls.c                      |    4 +-
 tools/perf/builtin-buildid-list.c                  |    4 +-
 tools/perf/builtin-record.c                        |    3 +-
 tools/perf/builtin-sched.c                         |    1 +
 tools/perf/scripts/python/check-perf-trace.py      |    3 +-
 tools/perf/util/event.c                            |   13 +-
 tools/perf/util/hist.c                             |    2 +-
 .../util/scripting-engines/trace-event-python.c    |   50 ++-
 15 files changed, 294 insertions(+), 167 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c775860..5db5b7d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -106,6 +106,7 @@ struct cpu_hw_events {
 
 	int			n_events;
 	int			n_added;
+	int			n_txn;
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
@@ -983,6 +984,7 @@ static int x86_pmu_enable(struct perf_event *event)
 out:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
+	cpuc->n_txn += n - n0;
 
 	return 0;
 }
@@ -1089,6 +1091,14 @@ static void x86_pmu_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int i;
 
+	/*
+	 * If we're called during a txn, we don't need to do anything.
+	 * The events never got scheduled and ->cancel_txn will truncate
+	 * the event_list.
+	 */
+	if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+		return;
+
 	x86_pmu_stop(event);
 
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1379,6 +1389,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+	cpuc->n_txn = 0;
 }
 
 /*
@@ -1391,6 +1402,11 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+	/*
+	 * Truncate the collected events.
+	 */
+	cpuc->n_added -= cpuc->n_txn;
+	cpuc->n_events -= cpuc->n_txn;
 }
 
 /*
@@ -1419,6 +1435,12 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
+	/*
+	 * Clear out the txn count so that ->cancel_txn() which gets
+	 * run after ->commit_txn() doesn't undo things.
+	 */
+	cpuc->n_txn = 0;
+
 	return 0;
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fb6c91e..5d0266d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -585,6 +585,7 @@ enum perf_event_active_state {
 struct file;
 
 struct perf_mmap_data {
+	atomic_t			refcount;
 	struct rcu_head			rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
@@ -592,7 +593,6 @@ struct perf_mmap_data {
 #endif
 	int				nr_pages;	/* nr of data pages  */
 	int				writable;	/* are we writable   */
-	int				nr_locked;	/* nr pages mlocked  */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
 
@@ -631,6 +631,9 @@ struct swevent_hlist {
 	struct rcu_head		rcu_head;
 };
 
+#define PERF_ATTACH_CONTEXT	0x01
+#define PERF_ATTACH_GROUP	0x02
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -643,10 +646,10 @@ struct perf_event {
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	struct perf_event		*output;
 	const struct pmu		*pmu;
 
 	enum perf_event_active_state	state;
+	unsigned int			attach_state;
 	atomic64_t			count;
 
 	/*
@@ -704,6 +707,8 @@ struct perf_event {
 	/* mmap bits */
 	struct mutex			mmap_mutex;
 	atomic_t			mmap_count;
+	int				mmap_locked;
+	struct user_struct		*mmap_user;
 	struct perf_mmap_data		*data;
 
 	/* poll related */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3d685d1..5a64905 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -725,7 +725,7 @@ perf_trace_##call(void *__data, proto)					\
 									\
 	{ assign; }							\
 									\
-	head = per_cpu_ptr(event_call->perf_events, smp_processor_id());\
+	head = this_cpu_ptr(event_call->perf_events);			\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 		__count, &__regs, head);				\
 }
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index bd7ce8c..858f56f 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -283,14 +283,15 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-	struct perf_event *group_leader = event->group_leader;
+	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+	event->attach_state |= PERF_ATTACH_CONTEXT;
 
 	/*
-	 * Depending on whether it is a standalone or sibling event,
-	 * add it straight to the context's event list, or to the group
-	 * leader's sibling list:
+	 * If we're a stand alone event or group leader, we go to the context
+	 * list, group events are kept attached to the group so that
+	 * perf_group_detach can, at all times, locate all siblings.
 	 */
-	if (group_leader == event) {
+	if (event->group_leader == event) {
 		struct list_head *list;
 
 		if (is_software_event(event))
@@ -298,13 +299,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 
 		list = ctx_group_list(event, ctx);
 		list_add_tail(&event->group_entry, list);
-	} else {
-		if (group_leader->group_flags & PERF_GROUP_SOFTWARE &&
-		    !is_software_event(event))
-			group_leader->group_flags &= ~PERF_GROUP_SOFTWARE;
-
-		list_add_tail(&event->group_entry, &group_leader->sibling_list);
-		group_leader->nr_siblings++;
 	}
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
@@ -313,6 +307,24 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		ctx->nr_stat++;
 }
 
+static void perf_group_attach(struct perf_event *event)
+{
+	struct perf_event *group_leader = event->group_leader;
+
+	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_GROUP);
+	event->attach_state |= PERF_ATTACH_GROUP;
+
+	if (group_leader == event)
+		return;
+
+	if (group_leader->group_flags & PERF_GROUP_SOFTWARE &&
+			!is_software_event(event))
+		group_leader->group_flags &= ~PERF_GROUP_SOFTWARE;
+
+	list_add_tail(&event->group_entry, &group_leader->sibling_list);
+	group_leader->nr_siblings++;
+}
+
 /*
  * Remove a event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
@@ -320,17 +332,22 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-	if (list_empty(&event->group_entry))
+	/*
+	 * We can have double detach due to exit/hot-unplug + close.
+	 */
+	if (!(event->attach_state & PERF_ATTACH_CONTEXT))
 		return;
+
+	event->attach_state &= ~PERF_ATTACH_CONTEXT;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
 
-	list_del_init(&event->group_entry);
 	list_del_rcu(&event->event_entry);
 
-	if (event->group_leader != event)
-		event->group_leader->nr_siblings--;
+	if (event->group_leader == event)
+		list_del_init(&event->group_entry);
 
 	update_group_times(event);
 
@@ -345,21 +362,39 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 		event->state = PERF_EVENT_STATE_OFF;
 }
 
-static void
-perf_destroy_group(struct perf_event *event, struct perf_event_context *ctx)
+static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *sibling, *tmp;
+	struct list_head *list = NULL;
+
+	/*
+	 * We can have double detach due to exit/hot-unplug + close.
+	 */
+	if (!(event->attach_state & PERF_ATTACH_GROUP))
+		return;
+
+	event->attach_state &= ~PERF_ATTACH_GROUP;
+
+	/*
+	 * If this is a sibling, remove it from its group.
+	 */
+	if (event->group_leader != event) {
+		list_del_init(&event->group_entry);
+		event->group_leader->nr_siblings--;
+		return;
+	}
+
+	if (!list_empty(&event->group_entry))
+		list = &event->group_entry;
 
 	/*
 	 * If this was a group event with sibling events then
 	 * upgrade the siblings to singleton events by adding them
-	 * to the context list directly:
+	 * to whatever list we are on.
 	 */
 	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, group_entry) {
-		struct list_head *list;
-
-		list = ctx_group_list(event, ctx);
-		list_move_tail(&sibling->group_entry, list);
+		if (list)
+			list_move_tail(&sibling->group_entry, list);
 		sibling->group_leader = sibling;
 
 		/* Inherit group flags from the previous leader */
@@ -652,8 +687,11 @@ group_sched_in(struct perf_event *group_event,
 	if (txn)
 		pmu->start_txn(pmu);
 
-	if (event_sched_in(group_event, cpuctx, ctx))
+	if (event_sched_in(group_event, cpuctx, ctx)) {
+		if (txn)
+			pmu->cancel_txn(pmu);
 		return -EAGAIN;
+	}
 
 	/*
 	 * Schedule in siblings as one group (if any):
@@ -675,9 +713,6 @@ group_sched_in(struct perf_event *group_event,
 	}
 
 group_error:
-	if (txn)
-		pmu->cancel_txn(pmu);
-
 	/*
 	 * Groups can be scheduled in as one unit only, so undo any
 	 * partial group before returning:
@@ -689,6 +724,9 @@ group_error:
 	}
 	event_sched_out(group_event, cpuctx, ctx);
 
+	if (txn)
+		pmu->cancel_txn(pmu);
+
 	return -EAGAIN;
 }
 
@@ -727,6 +765,7 @@ static void add_event_to_ctx(struct perf_event *event,
 			       struct perf_event_context *ctx)
 {
 	list_add_event(event, ctx);
+	perf_group_attach(event);
 	event->tstamp_enabled = ctx->time;
 	event->tstamp_running = ctx->time;
 	event->tstamp_stopped = ctx->time;
@@ -1841,6 +1880,7 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void perf_pending_sync(struct perf_event *event);
+static void perf_mmap_data_put(struct perf_mmap_data *data);
 
 static void free_event(struct perf_event *event)
 {
@@ -1856,9 +1896,9 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&nr_task_events);
 	}
 
-	if (event->output) {
-		fput(event->output->filp);
-		event->output = NULL;
+	if (event->data) {
+		perf_mmap_data_put(event->data);
+		event->data = NULL;
 	}
 
 	if (event->destroy)
@@ -1893,8 +1933,8 @@ int perf_event_release_kernel(struct perf_event *event)
 	 */
 	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
 	raw_spin_lock_irq(&ctx->lock);
+	perf_group_detach(event);
 	list_del_event(event, ctx);
-	perf_destroy_group(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
@@ -2175,7 +2215,27 @@ unlock:
 	return ret;
 }
 
-static int perf_event_set_output(struct perf_event *event, int output_fd);
+static const struct file_operations perf_fops;
+
+static struct perf_event *perf_fget_light(int fd, int *fput_needed)
+{
+	struct file *file;
+
+	file = fget_light(fd, fput_needed);
+	if (!file)
+		return ERR_PTR(-EBADF);
+
+	if (file->f_op != &perf_fops) {
+		fput_light(file, *fput_needed);
+		*fput_needed = 0;
+		return ERR_PTR(-EBADF);
+	}
+
+	return file->private_data;
+}
+
+static int perf_event_set_output(struct perf_event *event,
+				 struct perf_event *output_event);
 static int perf_event_set_filter(struct perf_event *event, void __user *arg);
 
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -2202,7 +2262,23 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return perf_event_period(event, (u64 __user *)arg);
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
-		return perf_event_set_output(event, arg);
+	{
+		struct perf_event *output_event = NULL;
+		int fput_needed = 0;
+		int ret;
+
+		if (arg != -1) {
+			output_event = perf_fget_light(arg, &fput_needed);
+			if (IS_ERR(output_event))
+				return PTR_ERR(output_event);
+		}
+
+		ret = perf_event_set_output(event, output_event);
+		if (output_event)
+			fput_light(output_event->filp, fput_needed);
+
+		return ret;
+	}
 
 	case PERF_EVENT_IOC_SET_FILTER:
 		return perf_event_set_filter(event, (void __user *)arg);
@@ -2335,8 +2411,6 @@ perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
 	unsigned long size;
 	int i;
 
-	WARN_ON(atomic_read(&event->mmap_count));
-
 	size = sizeof(struct perf_mmap_data);
 	size += nr_pages * sizeof(void *);
 
@@ -2452,8 +2526,6 @@ perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
 	unsigned long size;
 	void *all_buf;
 
-	WARN_ON(atomic_read(&event->mmap_count));
-
 	size = sizeof(struct perf_mmap_data);
 	size += sizeof(void *);
 
@@ -2536,7 +2608,7 @@ perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
 	if (!data->watermark)
 		data->watermark = max_size / 2;
 
-
+	atomic_set(&data->refcount, 1);
 	rcu_assign_pointer(event->data, data);
 }
 
@@ -2548,13 +2620,26 @@ static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head)
 	perf_mmap_data_free(data);
 }
 
-static void perf_mmap_data_release(struct perf_event *event)
+static struct perf_mmap_data *perf_mmap_data_get(struct perf_event *event)
 {
-	struct perf_mmap_data *data = event->data;
+	struct perf_mmap_data *data;
 
-	WARN_ON(atomic_read(&event->mmap_count));
+	rcu_read_lock();
+	data = rcu_dereference(event->data);
+	if (data) {
+		if (!atomic_inc_not_zero(&data->refcount))
+			data = NULL;
+	}
+	rcu_read_unlock();
+
+	return data;
+}
+
+static void perf_mmap_data_put(struct perf_mmap_data *data)
+{
+	if (!atomic_dec_and_test(&data->refcount))
+		return;
 
-	rcu_assign_pointer(event->data, NULL);
 	call_rcu(&data->rcu_head, perf_mmap_data_free_rcu);
 }
 
@@ -2569,15 +2654,18 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	WARN_ON_ONCE(event->ctx->parent_ctx);
 	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
 		unsigned long size = perf_data_size(event->data);
-		struct user_struct *user = current_user();
+		struct user_struct *user = event->mmap_user;
+		struct perf_mmap_data *data = event->data;
 
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->locked_vm -= event->data->nr_locked;
-		perf_mmap_data_release(event);
+		vma->vm_mm->locked_vm -= event->mmap_locked;
+		rcu_assign_pointer(event->data, NULL);
 		mutex_unlock(&event->mmap_mutex);
+
+		perf_mmap_data_put(data);
+		free_uid(user);
 	}
 }
 
@@ -2629,13 +2717,10 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
 	mutex_lock(&event->mmap_mutex);
-	if (event->output) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	if (atomic_inc_not_zero(&event->mmap_count)) {
-		if (nr_pages != event->data->nr_pages)
+	if (event->data) {
+		if (event->data->nr_pages == nr_pages)
+			atomic_inc(&event->data->refcount);
+		else
 			ret = -EINVAL;
 		goto unlock;
 	}
@@ -2667,21 +2752,23 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	WARN_ON(event->data);
 
 	data = perf_mmap_data_alloc(event, nr_pages);
-	ret = -ENOMEM;
-	if (!data)
+	if (!data) {
+		ret = -ENOMEM;
 		goto unlock;
+	}
 
-	ret = 0;
 	perf_mmap_data_init(event, data);
-
-	atomic_set(&event->mmap_count, 1);
-	atomic_long_add(user_extra, &user->locked_vm);
-	vma->vm_mm->locked_vm += extra;
-	event->data->nr_locked = extra;
 	if (vma->vm_flags & VM_WRITE)
 		event->data->writable = 1;
 
+	atomic_long_add(user_extra, &user->locked_vm);
+	event->mmap_locked = extra;
+	event->mmap_user = get_current_user();
+	vma->vm_mm->locked_vm += event->mmap_locked;
+
 unlock:
+	if (!ret)
+		atomic_inc(&event->mmap_count);
 	mutex_unlock(&event->mmap_mutex);
 
 	vma->vm_flags |= VM_RESERVED;
@@ -2977,6 +3064,7 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle,
 
 		len -= size;
 		handle->addr += size;
+		buf += size;
 		handle->size -= size;
 		if (!handle->size) {
 			struct perf_mmap_data *data = handle->data;
@@ -2993,7 +3081,6 @@ int perf_output_begin(struct perf_output_handle *handle,
 		      struct perf_event *event, unsigned int size,
 		      int nmi, int sample)
 {
-	struct perf_event *output_event;
 	struct perf_mmap_data *data;
 	unsigned long tail, offset, head;
 	int have_lost;
@@ -3010,10 +3097,6 @@ int perf_output_begin(struct perf_output_handle *handle,
 	if (event->parent)
 		event = event->parent;
 
-	output_event = rcu_dereference(event->output);
-	if (output_event)
-		event = output_event;
-
 	data = rcu_dereference(event->data);
 	if (!data)
 		goto out;
@@ -4912,39 +4995,17 @@ err_size:
 	goto out;
 }
 
-static int perf_event_set_output(struct perf_event *event, int output_fd)
+static int
+perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
-	struct perf_event *output_event = NULL;
-	struct file *output_file = NULL;
-	struct perf_event *old_output;
-	int fput_needed = 0;
+	struct perf_mmap_data *data = NULL, *old_data = NULL;
 	int ret = -EINVAL;
 
-	/*
-	 * Don't allow output of inherited per-task events. This would
-	 * create performance issues due to cross cpu access.
-	 */
-	if (event->cpu == -1 && event->attr.inherit)
-		return -EINVAL;
-
-	if (!output_fd)
+	if (!output_event)
 		goto set;
 
-	output_file = fget_light(output_fd, &fput_needed);
-	if (!output_file)
-		return -EBADF;
-
-	if (output_file->f_op != &perf_fops)
-		goto out;
-
-	output_event = output_file->private_data;
-
-	/* Don't chain output fds */
-	if (output_event->output)
-		goto out;
-
-	/* Don't set an output fd when we already have an output channel */
-	if (event->data)
+	/* don't allow circular references */
+	if (event == output_event)
 		goto out;
 
 	/*
@@ -4959,26 +5020,28 @@ static int perf_event_set_output(struct perf_event *event, int output_fd)
 	if (output_event->cpu == -1 && output_event->ctx != event->ctx)
 		goto out;
 
-	atomic_long_inc(&output_file->f_count);
-
 set:
 	mutex_lock(&event->mmap_mutex);
-	old_output = event->output;
-	rcu_assign_pointer(event->output, output_event);
-	mutex_unlock(&event->mmap_mutex);
+	/* Can't redirect output if we've got an active mmap() */
+	if (atomic_read(&event->mmap_count))
+		goto unlock;
 
-	if (old_output) {
-		/*
-		 * we need to make sure no existing perf_output_*()
-		 * is still referencing this event.
-		 */
-		synchronize_rcu();
-		fput(old_output->filp);
+	if (output_event) {
+		/* get the buffer we want to redirect to */
+		data = perf_mmap_data_get(output_event);
+		if (!data)
+			goto unlock;
 	}
 
+	old_data = event->data;
+	rcu_assign_pointer(event->data, data);
 	ret = 0;
+unlock:
+	mutex_unlock(&event->mmap_mutex);
+
+	if (old_data)
+		perf_mmap_data_put(old_data);
 out:
-	fput_light(output_file, fput_needed);
 	return ret;
 }
 
@@ -4994,7 +5057,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_attr __user *, attr_uptr,
 		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
 {
-	struct perf_event *event, *group_leader;
+	struct perf_event *event, *group_leader = NULL, *output_event = NULL;
 	struct perf_event_attr attr;
 	struct perf_event_context *ctx;
 	struct file *event_file = NULL;
@@ -5034,19 +5097,25 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_fd;
 	}
 
+	if (group_fd != -1) {
+		group_leader = perf_fget_light(group_fd, &fput_needed);
+		if (IS_ERR(group_leader)) {
+			err = PTR_ERR(group_leader);
+			goto err_put_context;
+		}
+		group_file = group_leader->filp;
+		if (flags & PERF_FLAG_FD_OUTPUT)
+			output_event = group_leader;
+		if (flags & PERF_FLAG_FD_NO_GROUP)
+			group_leader = NULL;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
-	group_leader = NULL;
-	if (group_fd != -1 && !(flags & PERF_FLAG_FD_NO_GROUP)) {
+	if (group_leader) {
 		err = -EINVAL;
-		group_file = fget_light(group_fd, &fput_needed);
-		if (!group_file)
-			goto err_put_context;
-		if (group_file->f_op != &perf_fops)
-			goto err_put_context;
 
-		group_leader = group_file->private_data;
 		/*
 		 * Do not allow a recursive hierarchy (this new sibling
 		 * becoming part of another group-sibling):
@@ -5068,9 +5137,16 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	event = perf_event_alloc(&attr, cpu, ctx, group_leader,
 				     NULL, NULL, GFP_KERNEL);
-	err = PTR_ERR(event);
-	if (IS_ERR(event))
+	if (IS_ERR(event)) {
+		err = PTR_ERR(event);
 		goto err_put_context;
+	}
+
+	if (output_event) {
+		err = perf_event_set_output(event, output_event);
+		if (err)
+			goto err_free_put_context;
+	}
 
 	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
 	if (IS_ERR(event_file)) {
@@ -5078,12 +5154,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_free_put_context;
 	}
 
-	if (flags & PERF_FLAG_FD_OUTPUT) {
-		err = perf_event_set_output(event, group_fd);
-		if (err)
-			goto err_fput_free_put_context;
-	}
-
 	event->filp = event_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
@@ -5097,12 +5167,16 @@ SYSCALL_DEFINE5(perf_event_open,
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
 
+	/*
+	 * Drop the reference on the group_event after placing the
+	 * new event on the sibling_list. This ensures destruction
+	 * of the group leader will find the pointer to itself in
+	 * perf_group_detach().
+	 */
 	fput_light(group_file, fput_needed);
 	fd_install(event_fd, event_file);
 	return event_fd;
 
-err_fput_free_put_context:
-	fput(event_file);
 err_free_put_context:
 	free_event(event);
 err_put_context:
@@ -5420,6 +5494,7 @@ static void perf_free_event(struct perf_event *event,
 
 	fput(parent->filp);
 
+	perf_group_detach(event);
 	list_del_event(event, ctx);
 	free_event(event);
 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 36ea2b6..638711c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -842,6 +842,7 @@ static void blk_add_trace_split(void *ignore,
 
 /**
  * blk_add_trace_remap - Add a trace for a remap operation
+ * @ignore:	trace callback data parameter (not used)
  * @q:		queue the io is for
  * @bio:	the source bio
  * @dev:	target device
@@ -873,6 +874,7 @@ static void blk_add_trace_remap(void *ignore,
 
 /**
  * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @ignore:	trace callback data parameter (not used)
  * @q:		queue the io is for
  * @rq:		the source request
  * @dev:	target device
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index cb6f365..e6f6588 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -116,7 +116,7 @@ int perf_trace_enable(struct perf_event *p_event)
 	if (WARN_ON_ONCE(!list))
 		return -EINVAL;
 
-	list = per_cpu_ptr(list, smp_processor_id());
+	list = this_cpu_ptr(list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
 	return 0;
@@ -132,8 +132,9 @@ void perf_trace_destroy(struct perf_event *p_event)
 	struct ftrace_event_call *tp_event = p_event->tp_event;
 	int i;
 
+	mutex_lock(&event_mutex);
 	if (--tp_event->perf_refcount > 0)
-		return;
+		goto out;
 
 	if (tp_event->class->reg)
 		tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
@@ -142,6 +143,12 @@ void perf_trace_destroy(struct perf_event *p_event)
 					    tp_event->class->perf_probe,
 					    tp_event);
 
+	/*
+	 * Ensure our callback won't be called anymore. See
+	 * tracepoint_probe_unregister() and __DO_TRACE().
+	 */
+	synchronize_sched();
+
 	free_percpu(tp_event->perf_events);
 	tp_event->perf_events = NULL;
 
@@ -151,6 +158,8 @@ void perf_trace_destroy(struct perf_event *p_event)
 			perf_trace_buf[i] = NULL;
 		}
 	}
+out:
+	mutex_unlock(&event_mutex);
 }
 
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
@@ -169,7 +178,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	if (*rctxp < 0)
 		return NULL;
 
-	raw_data = per_cpu_ptr(perf_trace_buf[*rctxp], smp_processor_id());
+	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
 
 	/* zero the dead bytes from align to not leak stack to user */
 	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index faf7cef..f52b5f5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1359,7 +1359,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	for (i = 0; i < tp->nr_args; i++)
 		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-	head = per_cpu_ptr(call->perf_events, smp_processor_id());
+	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
 }
 
@@ -1392,7 +1392,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	for (i = 0; i < tp->nr_args; i++)
 		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-	head = per_cpu_ptr(call->perf_events, smp_processor_id());
+	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index d2c859c..34e3580 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -519,7 +519,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
 
-	head = per_cpu_ptr(sys_data->enter_event->perf_events, smp_processor_id());
+	head = this_cpu_ptr(sys_data->enter_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
 }
 
@@ -595,7 +595,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	head = per_cpu_ptr(sys_data->exit_event->perf_events, smp_processor_id());
+	head = this_cpu_ptr(sys_data->exit_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
 }
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 44a47e1..9989072 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -43,8 +43,10 @@ static int __cmd_buildid_list(void)
 	if (session == NULL)
 		return -1;
 
-	if (with_hits)
+	if (with_hits) {
+		symbol_conf.full_paths = true;
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
+	}
 
 	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9bc8905..dc3435e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -503,7 +503,6 @@ static int __cmd_record(int argc, const char **argv)
 {
 	int i, counter;
 	struct stat st;
-	pid_t pid = 0;
 	int flags;
 	int err;
 	unsigned long waking = 0;
@@ -572,7 +571,7 @@ static int __cmd_record(int argc, const char **argv)
 
 	if (forks) {
 		child_pid = fork();
-		if (pid < 0) {
+		if (child_pid < 0) {
 			perror("failed to fork");
 			exit(-1);
 		}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f67bce2..55f3b5d 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1645,6 +1645,7 @@ static struct perf_event_ops event_ops = {
 	.sample			= process_sample_event,
 	.comm			= event__process_comm,
 	.lost			= event__process_lost,
+	.fork			= event__process_task,
 	.ordered_samples	= true,
 };
 
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index 964d934..d9f7893 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -51,8 +51,7 @@ def kmem__kmalloc(event_name, context, common_cpu,
 
 		flag_str("kmem__kmalloc", "gfp_flags", gfp_flags)),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     try:
         unhandled[event_name] += 1
     except TypeError:
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 50771b5..1f08f00 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -370,9 +370,9 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm)
 
 int event__process_comm(event_t *self, struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, self->comm.pid);
+	struct thread *thread = perf_session__findnew(session, self->comm.tid);
 
-	dump_printf(": %s:%d\n", self->comm.comm, self->comm.pid);
+	dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
 
 	if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
@@ -532,16 +532,11 @@ out_problem:
 
 int event__process_task(event_t *self, struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, self->fork.pid);
-	struct thread *parent = perf_session__findnew(session, self->fork.ppid);
+	struct thread *thread = perf_session__findnew(session, self->fork.tid);
+	struct thread *parent = perf_session__findnew(session, self->fork.ptid);
 
 	dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
 		    self->fork.ppid, self->fork.ptid);
-	/*
-	 * A thread clone will have the same PID for both parent and child.
-	 */
-	if (thread == parent)
-		return 0;
 
 	if (self->header.type == PERF_RECORD_EXIT)
 		return 0;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cbf7eae..07f89b6 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -965,7 +965,7 @@ static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
 		 * Parse hexa addresses followed by ':'
 		 */
 		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':')
+		if (*tmp2 != ':' || tmp == tmp2)
 			line_ip = -1;
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 81f39ca..33a6325 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -208,7 +208,7 @@ static void python_process_event(int cpu, void *data,
 				 int size __unused,
 				 unsigned long long nsecs, char *comm)
 {
-	PyObject *handler, *retval, *context, *t, *obj;
+	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long long val;
@@ -232,6 +232,14 @@ static void python_process_event(int cpu, void *data,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (handler && !PyCallable_Check(handler))
+		handler = NULL;
+	if (!handler) {
+		dict = PyDict_New();
+		if (!dict)
+			Py_FatalError("couldn't create Python dict");
+	}
 	s = nsecs / NSECS_PER_SEC;
 	ns = nsecs - s * NSECS_PER_SEC;
 
@@ -242,12 +250,20 @@ static void python_process_event(int cpu, void *data,
 	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
 	PyTuple_SetItem(t, n++,
 			PyCObject_FromVoidPtr(scripting_context, NULL));
-	PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
-	PyTuple_SetItem(t, n++, PyInt_FromLong(s));
-	PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
-	PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
-	PyTuple_SetItem(t, n++, PyString_FromString(comm));
 
+	if (handler) {
+		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+		PyTuple_SetItem(t, n++, PyInt_FromLong(s));
+		PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
+		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
+		PyTuple_SetItem(t, n++, PyString_FromString(comm));
+	} else {
+		PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
+		PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
+		PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
+		PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
+		PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
 			int offset;
@@ -272,27 +288,31 @@ static void python_process_event(int cpu, void *data,
 					obj = PyLong_FromUnsignedLongLong(val);
 			}
 		}
-		PyTuple_SetItem(t, n++, obj);
+		if (handler)
+			PyTuple_SetItem(t, n++, obj);
+		else
+			PyDict_SetItemString(dict, field->name, obj);
+
 	}
+	if (!handler)
+		PyTuple_SetItem(t, n++, dict);
 
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
+	if (handler) {
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
 	} else {
 		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
 		if (handler && PyCallable_Check(handler)) {
-			if (_PyTuple_Resize(&t, N_COMMON_FIELDS) == -1)
-				Py_FatalError("error resizing Python tuple");
 
 			retval = PyObject_CallObject(handler, t);
 			if (retval == NULL)
 				handler_call_die("trace_unhandled");
 		}
+		Py_DECREF(dict);
 	}
 
 	Py_DECREF(t);
@@ -548,12 +568,10 @@ static int python_generate_script(const char *outfile)
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
-		"common_cpu, common_secs, common_nsecs,\n\t\t"
-		"common_pid, common_comm):\n");
+		"event_fields_dict):\n");
 
-	fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
-		"common_secs, common_nsecs,\n\t\tcommon_pid, "
-		"common_comm)\n\n");
+	fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))"
+		"for k,v in sorted(event_fields_dict.items())])\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-05-31 23:02 Frederic Weisbecker
@ 2010-06-01  6:59 ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-06-01  6:59 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: LKML, Borislav Petkov, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Paul Mackerras, Thomas Gleixner


* Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Ingo,
> 
> Please pull the perf/urgent branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/urgent
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (3):
>       perf: Process comm events by tid
>       perf: Use event__process_task from perf sched
>       perf: Do the comm inheritance per thread in event__process_task
> 
> Borislav Petkov (1):
>       perf-record: Check correct pid when forking
> 
> 
>  tools/perf/builtin-record.c |    3 +--
>  tools/perf/builtin-sched.c  |    1 +
>  tools/perf/util/event.c     |   13 ++++---------
>  3 files changed, 6 insertions(+), 11 deletions(-)

Pulled, thanks a lot Frederic!

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-05-31 23:02 Frederic Weisbecker
  2010-06-01  6:59 ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Frederic Weisbecker @ 2010-05-31 23:02 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: LKML, Frederic Weisbecker, Borislav Petkov, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Paul Mackerras

Ingo,

Please pull the perf/urgent branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
	perf/urgent

Thanks,
	Frederic
---

Frederic Weisbecker (3):
      perf: Process comm events by tid
      perf: Use event__process_task from perf sched
      perf: Do the comm inheritance per thread in event__process_task

Borislav Petkov (1):
      perf-record: Check correct pid when forking


 tools/perf/builtin-record.c |    3 +--
 tools/perf/builtin-sched.c  |    1 +
 tools/perf/util/event.c     |   13 ++++---------
 3 files changed, 6 insertions(+), 11 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-05-30 19:27 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-05-30 19:27 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Paul Mackerras, Fr??d??ric Weisbecker, Steven Rostedt,
	Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf tui: Reset use_browser if stdout is not a tty
      perf symbols: Add the build id cache to the vmlinux path
      perf tui: Fix last use_browser problem related to .perfconfig

Steven Rostedt (2):
      ring-buffer: Reset "real_end" when page is filled
      ring-buffer: Move zeroing out excess in page to ring buffer code


 kernel/trace/ring_buffer.c    |   19 +++++++++++++++++--
 kernel/trace/trace.c          |    6 ------
 tools/perf/builtin-annotate.c |    2 +-
 tools/perf/builtin-top.c      |    2 +-
 tools/perf/util/debug.c       |    2 +-
 tools/perf/util/newt.c        |    1 +
 tools/perf/util/symbol.c      |   27 +++++++++++++++++++++++----
 tools/perf/util/symbol.h      |    2 +-
 8 files changed, 45 insertions(+), 16 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7f6059c..1da7b6e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1768,6 +1768,14 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * must fill the old tail_page with padding.
 	 */
 	if (tail >= BUF_PAGE_SIZE) {
+		/*
+		 * If the page was filled, then we still need
+		 * to update the real_end. Reset it to zero
+		 * and the reader will ignore it.
+		 */
+		if (tail == BUF_PAGE_SIZE)
+			tail_page->real_end = 0;
+
 		local_sub(length, &tail_page->write);
 		return;
 	}
@@ -3894,12 +3902,12 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	ret = read;
 
 	cpu_buffer->lost_events = 0;
+
+	commit = local_read(&bpage->commit);
 	/*
 	 * Set a flag in the commit field if we lost events
 	 */
 	if (missed_events) {
-		commit = local_read(&bpage->commit);
-
 		/* If there is room at the end of the page to save the
 		 * missed events, then record it there.
 		 */
@@ -3907,10 +3915,17 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 			memcpy(&bpage->data[commit], &missed_events,
 			       sizeof(missed_events));
 			local_add(RB_MISSED_STORED, &bpage->commit);
+			commit += sizeof(missed_events);
 		}
 		local_add(RB_MISSED_EVENTS, &bpage->commit);
 	}
 
+	/*
+	 * This page may be off to user land. Zero it out here.
+	 */
+	if (commit < BUF_PAGE_SIZE)
+		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+
  out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ba0ec81..95d0b1a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3661,7 +3661,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
 	struct ftrace_buffer_info *info = filp->private_data;
-	unsigned int pos;
 	ssize_t ret;
 	size_t size;
 
@@ -3688,11 +3687,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (ret < 0)
 		return 0;
 
-	pos = ring_buffer_page_len(info->spare);
-
-	if (pos < PAGE_SIZE)
-		memset(info->spare + pos, 0, PAGE_SIZE - pos);
-
 read:
 	size = PAGE_SIZE - info->read;
 	if (size > count)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 08278ed..96db524 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -343,7 +343,7 @@ find_next:
 			continue;
 		}
 
-		if (use_browser) {
+		if (use_browser > 0) {
 			key = hist_entry__tui_annotate(he);
 			if (is_exit_key(key))
 				break;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 397290a..a66f427 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1060,7 +1060,7 @@ static void event__process_sample(const event_t *self,
 			pr_err("Can't annotate %s", sym->name);
 			if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
 				pr_err(": No vmlinux file was found in the path:\n");
-				vmlinux_path__fprintf(stderr);
+				machine__fprintf_vmlinux_path(machine, stderr);
 			} else
 				pr_err(".\n");
 			exit(1);
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index dd824cf..6cddff2 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -22,7 +22,7 @@ int eprintf(int level, const char *fmt, ...)
 
 	if (verbose >= level) {
 		va_start(args, fmt);
-		if (use_browser)
+		if (use_browser > 0)
 			ret = browser__show_help(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
index d54c540..cf182ca 100644
--- a/tools/perf/util/newt.c
+++ b/tools/perf/util/newt.c
@@ -1139,6 +1139,7 @@ void setup_browser(void)
 	struct newtPercentTreeColors *c = &defaultPercentTreeColors;
 
 	if (!isatty(1) || !use_browser || dump_trace) {
+		use_browser = 0;
 		setup_pager();
 		return;
 	}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index aaa51ba..7fd6b15 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1695,9 +1695,20 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
 			   symbol_filter_t filter)
 {
 	int i, err = 0;
+	char *filename;
 
 	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-		 vmlinux_path__nr_entries);
+		 vmlinux_path__nr_entries + 1);
+
+	filename = dso__build_id_filename(self, NULL, 0);
+	if (filename != NULL) {
+		err = dso__load_vmlinux(self, map, filename, filter);
+		if (err > 0) {
+			dso__set_long_name(self, filename);
+			goto out;
+		}
+		free(filename);
+	}
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
 		err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
@@ -1706,7 +1717,7 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
 			break;
 		}
 	}
-
+out:
 	return err;
 }
 
@@ -2102,13 +2113,21 @@ out_fail:
 	return -1;
 }
 
-size_t vmlinux_path__fprintf(FILE *fp)
+size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp)
 {
 	int i;
 	size_t printed = 0;
+	struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso;
+
+	if (kdso->has_build_id) {
+		char filename[PATH_MAX];
+		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+			printed += fprintf(fp, "[0] %s\n", filename);
+	}
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i)
-		printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]);
+		printed += fprintf(fp, "[%d] %s\n",
+				   i + kdso->has_build_id, vmlinux_path[i]);
 
 	return printed;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5d25b5e..5e02d2c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -216,6 +216,6 @@ int machines__create_guest_kernel_maps(struct rb_root *self);
 int symbol__init(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-size_t vmlinux_path__fprintf(FILE *fp);
+size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp);
 
 #endif /* __PERF_SYMBOL */

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-05-20  9:44 Frederic Weisbecker
@ 2010-05-20 12:40 ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-05-20 12:40 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: LKML, Peter Zijlstra, Arnaldo Carvalho de Melo, Paul Mackerras


* Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Ingo,
> 
> Please pull the perf/urgent branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/urgent
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (2):
>       perf: Comply with new rcu checks API
>       perf: Fix unaligned accesses while fetching trace values
> 
> Tom Zanussi (1):
>       perf: Use read() instead of lseek() in trace_event_read.c:skip()
> 
> 
>  kernel/perf_event.c                |   58 ++++++++++++++++++++++++++++-------
>  tools/perf/util/trace-event-read.c |   19 ++++++++----
>  tools/perf/util/trace-event.h      |    7 ++++-
>  3 files changed, 65 insertions(+), 19 deletions(-)

Pulled, thanks Frederic!

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-05-20  9:44 Frederic Weisbecker
  2010-05-20 12:40 ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Frederic Weisbecker @ 2010-05-20  9:44 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: LKML, Frederic Weisbecker, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Paul Mackerras

Ingo,

Please pull the perf/urgent branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
	perf/urgent

Thanks,
	Frederic
---

Frederic Weisbecker (2):
      perf: Comply with new rcu checks API
      perf: Fix unaligned accesses while fetching trace values

Tom Zanussi (1):
      perf: Use read() instead of lseek() in trace_event_read.c:skip()


 kernel/perf_event.c                |   58 ++++++++++++++++++++++++++++-------
 tools/perf/util/trace-event-read.c |   19 ++++++++----
 tools/perf/util/trace-event.h      |    7 ++++-
 3 files changed, 65 insertions(+), 19 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-05-11 19:18 Ingo Molnar
@ 2010-05-12  0:39 ` Linus Torvalds
  0 siblings, 0 replies; 376+ messages in thread
From: Linus Torvalds @ 2010-05-12  0:39 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Paul Mackerras, Fr??d??ric Weisbecker, Thomas Gleixner,
	Andrew Morton



On Tue, 11 May 2010, Ingo Molnar wrote:
>
> Frederic Weisbecker (1):
>       perf: Fix static strings treated like dynamic ones

Grr. This one doesn't have a proper sign-off chain.

I pulled it, but please be more careful.

		Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-05-11 19:18 Ingo Molnar
  2010-05-12  0:39 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2010-05-11 19:18 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Paul Mackerras, Fr??d??ric Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (1):
      perf: Fix static strings treated like dynamic ones

Masami Hiramatsu (1):
      kprobes/x86: Fix removed int3 checking order


 arch/x86/kernel/kprobes.c           |   27 +++++++++++++--------------
 tools/perf/util/trace-event-parse.c |    2 +-
 2 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index b43bbae..1658efd 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -534,20 +534,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	struct kprobe_ctlblk *kcb;
 
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
-	if (*addr != BREAKPOINT_INSTRUCTION) {
-		/*
-		 * The breakpoint instruction was removed right
-		 * after we hit it.  Another cpu has removed
-		 * either a probepoint or a debugger breakpoint
-		 * at this address.  In either case, no further
-		 * handling of this interrupt is appropriate.
-		 * Back up over the (now missing) int3 and run
-		 * the original instruction.
-		 */
-		regs->ip = (unsigned long)addr;
-		return 1;
-	}
-
 	/*
 	 * We don't want to be preempted for the entire
 	 * duration of kprobe processing. We conditionally
@@ -579,6 +565,19 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
+	} else if (*addr != BREAKPOINT_INSTRUCTION) {
+		/*
+		 * The breakpoint instruction was removed right
+		 * after we hit it.  Another cpu has removed
+		 * either a probepoint or a debugger breakpoint
+		 * at this address.  In either case, no further
+		 * handling of this interrupt is appropriate.
+		 * Back up over the (now missing) int3 and run
+		 * the original instruction.
+		 */
+		regs->ip = (unsigned long)addr;
+		preempt_enable_no_resched();
+		return 1;
 	} else if (kprobe_running()) {
 		p = __get_cpu_var(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 9b3c20f..613c9cc 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1925,7 +1925,7 @@ void *raw_field_ptr(struct event *event, const char *name, void *data)
 	if (!field)
 		return NULL;
 
-	if (field->flags & FIELD_IS_STRING) {
+	if (field->flags & FIELD_IS_DYNAMIC) {
 		int offset;
 
 		offset = *(int *)(data + field->offset);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-04-06 17:49 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-04-06 17:49 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	=?unknown-8bit?B?RnLDqWTDqXJpYw==?= Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf kmem: Fix breakage introduced by 5a0e3ad slab.h script

Vince Weaver (1):
      perf, x86: Enable Nehalem-EX support


 arch/x86/kernel/cpu/perf_event_intel.c |    1 +
 tools/perf/builtin-kmem.c              |    1 -
 2 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 84bfde6..9c794ac 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -936,6 +936,7 @@ static __init int intel_pmu_init(void)
 
 	case 26: /* 45 nm nehalem, "Bloomfield" */
 	case 30: /* 45 nm nehalem, "Lynnfield" */
+	case 46: /* 45 nm nehalem-ex, "Beckton" */
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 7d9e3a7..924a951 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -14,7 +14,6 @@
 #include "util/debug.h"
 
 #include <linux/rbtree.h>
-#include <linux/slab.h>
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-04-04 10:15 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-04-04 10:15 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Frédéric Weisbecker, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Borislav Petkov (1):
      perf, probe-finder: Build fix on Debian

Frederic Weisbecker (4):
      perf: Correctly align perf event tracing buffer
      perf: Use hot regs with software sched switch/migrate events
      perf: Always build the stub perf_arch_fetch_caller_regs version
      perf: Always build the powerpc perf_arch_fetch_caller_regs version

Jason Wessel (1):
      x86,kgdb: Always initialize the hw breakpoint attribute

Mike Galbraith (1):
      perf: Fix 'perf sched record' deadlock

Peter Zijlstra (2):
      x86: Move notify_cpu_starting() callback to a later stage
      perf, x86: Fix AMD hotplug & constraint initialization

Tom Zanussi (1):
      perf/scripts: Tuple was set from long in both branches in python_process_event()

Torok Edwin (1):
      perf, x86: Fix callgraphs of 32-bit processes on 64-bit kernels


 arch/powerpc/kernel/misc.S                         |    2 -
 arch/x86/kernel/cpu/perf_event.c                   |   54 +++++++++++---
 arch/x86/kernel/cpu/perf_event_amd.c               |   80 ++++++++++++--------
 arch/x86/kernel/dumpstack.h                        |    5 +
 arch/x86/kernel/kgdb.c                             |    2 +-
 arch/x86/kernel/smpboot.c                          |    4 +-
 include/linux/perf_event.h                         |   21 ++++--
 kernel/perf_event.c                                |   22 ++++--
 kernel/trace/trace_event_perf.c                    |   11 ++-
 tools/perf/Makefile                                |   10 +-
 .../util/scripting-engines/trace-event-python.c    |   17 +++-
 11 files changed, 153 insertions(+), 75 deletions(-)

diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index b485a87..22e507c 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -128,7 +128,6 @@ _GLOBAL(__restore_cpu_power7)
 	/* place holder */
 	blr
 
-#ifdef CONFIG_EVENT_TRACING
 /*
  * Get a minimal set of registers for our caller's nth caller.
  * r3 = regs pointer, r5 = n.
@@ -154,4 +153,3 @@ _GLOBAL(perf_arch_fetch_caller_regs)
 	PPC_STL	r4,_NIP-STACK_FRAME_OVERHEAD(r3)
 	PPC_STL	r7,_LINK-STACK_FRAME_OVERHEAD(r3)
 	blr
-#endif /* CONFIG_EVENT_TRACING */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 60398a0..53ea4cf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -28,6 +28,7 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
+#include <asm/compat.h>
 
 static u64 perf_event_mask __read_mostly;
 
@@ -158,7 +159,7 @@ struct x86_pmu {
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
 
-	void		(*cpu_prepare)(int cpu);
+	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
@@ -1333,11 +1334,12 @@ static int __cpuinit
 x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
+	int ret = NOTIFY_OK;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
 		if (x86_pmu.cpu_prepare)
-			x86_pmu.cpu_prepare(cpu);
+			ret = x86_pmu.cpu_prepare(cpu);
 		break;
 
 	case CPU_STARTING:
@@ -1350,6 +1352,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 			x86_pmu.cpu_dying(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DEAD:
 		if (x86_pmu.cpu_dead)
 			x86_pmu.cpu_dead(cpu);
@@ -1359,7 +1362,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 	}
 
-	return NOTIFY_OK;
+	return ret;
 }
 
 static void __init pmu_check_apic(void)
@@ -1628,14 +1631,42 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+#ifdef CONFIG_COMPAT
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	unsigned long bytes;
+	/* 32-bit process in 64-bit kernel. */
+	struct stack_frame_ia32 frame;
+	const void __user *fp;
 
-	bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
+	if (!test_thread_flag(TIF_IA32))
+		return 0;
+
+	fp = compat_ptr(regs->bp);
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
+		frame.next_frame     = 0;
+		frame.return_address = 0;
+
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
+			break;
+
+		if (fp < compat_ptr(regs->sp))
+			break;
 
-	return bytes == sizeof(*frame);
+		callchain_store(entry, frame.return_address);
+		fp = compat_ptr(frame.next_frame);
+	}
+	return 1;
+}
+#else
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+    return 0;
 }
+#endif
 
 static void
 perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1651,11 +1682,16 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->ip);
 
+	if (perf_callchain_user32(regs, entry))
+		return;
+
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!copy_stack_frame(fp, &frame))
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
 			break;
 
 		if ((unsigned long)fp < regs->sp)
@@ -1702,7 +1738,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 	regs->ip = ip;
@@ -1714,4 +1749,3 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
 	regs->cs = __KERNEL_CS;
 	local_save_flags(regs->flags);
 }
-#endif
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index b87e0b6..db6f7d4 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -137,6 +137,13 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_has_nb(struct cpu_hw_events *cpuc)
+{
+	struct amd_nb *nb = cpuc->amd_nb;
+
+	return nb && nb->nb_id != -1;
+}
+
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 				      struct perf_event *event)
 {
@@ -147,7 +154,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	/*
 	 * only care about NB events
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return;
 
 	/*
@@ -214,7 +221,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	/*
 	 * if not NB event or no NB, then no constraints
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return &unconstrained;
 
 	/*
@@ -293,51 +300,55 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	return nb;
 }
 
-static void amd_pmu_cpu_online(int cpu)
+static int amd_pmu_cpu_prepare(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	WARN_ON_ONCE(cpuc->amd_nb);
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return NOTIFY_OK;
+
+	cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+	if (!cpuc->amd_nb)
+		return NOTIFY_BAD;
+
+	return NOTIFY_OK;
+}
+
+static void amd_pmu_cpu_starting(int cpu)
 {
-	struct cpu_hw_events *cpu1, *cpu2;
-	struct amd_nb *nb = NULL;
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct amd_nb *nb;
 	int i, nb_id;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
 
-	/*
-	 * function may be called too early in the
-	 * boot process, in which case nb_id is bogus
-	 */
 	nb_id = amd_get_nb_id(cpu);
-	if (nb_id == BAD_APICID)
-		return;
-
-	cpu1 = &per_cpu(cpu_hw_events, cpu);
-	cpu1->amd_nb = NULL;
+	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	raw_spin_lock(&amd_nb_lock);
 
 	for_each_online_cpu(i) {
-		cpu2 = &per_cpu(cpu_hw_events, i);
-		nb = cpu2->amd_nb;
-		if (!nb)
+		nb = per_cpu(cpu_hw_events, i).amd_nb;
+		if (WARN_ON_ONCE(!nb))
 			continue;
-		if (nb->nb_id == nb_id)
-			goto found;
-	}
 
-	nb = amd_alloc_nb(cpu, nb_id);
-	if (!nb) {
-		pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
-		raw_spin_unlock(&amd_nb_lock);
-		return;
+		if (nb->nb_id == nb_id) {
+			kfree(cpuc->amd_nb);
+			cpuc->amd_nb = nb;
+			break;
+		}
 	}
-found:
-	nb->refcnt++;
-	cpu1->amd_nb = nb;
+
+	cpuc->amd_nb->nb_id = nb_id;
+	cpuc->amd_nb->refcnt++;
 
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static void amd_pmu_cpu_offline(int cpu)
+static void amd_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuhw;
 
@@ -349,8 +360,10 @@ static void amd_pmu_cpu_offline(int cpu)
 	raw_spin_lock(&amd_nb_lock);
 
 	if (cpuhw->amd_nb) {
-		if (--cpuhw->amd_nb->refcnt == 0)
-			kfree(cpuhw->amd_nb);
+		struct amd_nb *nb = cpuhw->amd_nb;
+
+		if (nb->nb_id == -1 || --nb->refcnt == 0)
+			kfree(nb);
 
 		cpuhw->amd_nb = NULL;
 	}
@@ -379,8 +392,9 @@ static __initconst struct x86_pmu amd_pmu = {
 	.get_event_constraints	= amd_get_event_constraints,
 	.put_event_constraints	= amd_put_event_constraints,
 
-	.cpu_prepare		= amd_pmu_cpu_online,
-	.cpu_dead		= amd_pmu_cpu_offline,
+	.cpu_prepare		= amd_pmu_cpu_prepare,
+	.cpu_starting		= amd_pmu_cpu_starting,
+	.cpu_dead		= amd_pmu_cpu_dead,
 };
 
 static __init int amd_pmu_init(void)
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 29e5f7c..e39e771 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -30,6 +30,11 @@ struct stack_frame {
 	unsigned long return_address;
 };
 
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
 static inline unsigned long rewind_frame_pointer(int n)
 {
 	struct stack_frame *frame;
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index bfba601..b2258ca 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -618,8 +618,8 @@ int kgdb_arch_init(void)
 	 * portion of kgdb because this operation requires mutexs to
 	 * complete.
 	 */
+	hw_breakpoint_init(&attr);
 	attr.bp_addr = (unsigned long)kgdb_arch_init;
-	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.bp_len = HW_BREAKPOINT_LEN_1;
 	attr.bp_type = HW_BREAKPOINT_W;
 	attr.disabled = 1;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 06d98ae..6808b93 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -242,8 +242,6 @@ static void __cpuinit smp_callin(void)
 	end_local_APIC_setup();
 	map_cpu_to_logical_apicid();
 
-	notify_cpu_starting(cpuid);
-
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
@@ -264,6 +262,8 @@ static void __cpuinit smp_callin(void)
 	 */
 	smp_store_cpu_info(cpuid);
 
+	notify_cpu_starting(cpuid);
+
 	/*
 	 * Allow the master to continue.
 	 */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9547703..c8e3754 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -842,13 +842,6 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
-static inline void
-perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
-{
-	if (atomic_read(&perf_swevent_enabled[event_id]))
-		__perf_sw_event(event_id, nr, nmi, regs, addr);
-}
-
 extern void
 perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
 
@@ -887,6 +880,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
 	return perf_arch_fetch_caller_regs(regs, ip, skip);
 }
 
+static inline void
+perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+{
+	if (atomic_read(&perf_swevent_enabled[event_id])) {
+		struct pt_regs hot_regs;
+
+		if (!regs) {
+			perf_fetch_caller_regs(&hot_regs, 1);
+			regs = &hot_regs;
+		}
+		__perf_sw_event(event_id, nr, nmi, regs, addr);
+	}
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 574ee58..681af80 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1164,11 +1164,9 @@ void perf_event_task_sched_out(struct task_struct *task,
 	struct perf_event_context *ctx = task->perf_event_ctxp;
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
-	struct pt_regs *regs;
 	int do_switch = 1;
 
-	regs = task_pt_regs(task);
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
 	if (likely(!ctx || !cpuctx->task_ctx))
 		return;
@@ -2786,12 +2784,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 __weak
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 }
-#endif
+
 
 /*
  * Output
@@ -3378,15 +3375,23 @@ static void perf_event_task_output(struct perf_event *event,
 				     struct perf_task_event *task_event)
 {
 	struct perf_output_handle handle;
-	int size;
 	struct task_struct *task = task_event->task;
-	int ret;
+	unsigned long flags;
+	int size, ret;
+
+	/*
+	 * If this CPU attempts to acquire an rq lock held by a CPU spinning
+	 * in perf_output_lock() from interrupt context, it's game over.
+	 */
+	local_irq_save(flags);
 
 	size  = task_event->event_id.header.size;
 	ret = perf_output_begin(&handle, event, size, 0, 0);
 
-	if (ret)
+	if (ret) {
+		local_irq_restore(flags);
 		return;
+	}
 
 	task_event->event_id.pid = perf_event_pid(event, task);
 	task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3397,6 +3402,7 @@ static void perf_event_task_output(struct perf_event *event,
 	perf_output_put(&handle, task_event->event_id);
 
 	perf_output_end(&handle);
+	local_irq_restore(flags);
 }
 
 static int perf_event_task_match(struct perf_event *event)
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 81f691e..0565bb4 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -17,7 +17,12 @@ EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
 static char *perf_trace_buf;
 static char *perf_trace_buf_nmi;
 
-typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+	perf_trace_t;
 
 /* Count the events in use (per event id, not per instance) */
 static int	total_ref_count;
@@ -130,6 +135,8 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	char *trace_buf, *raw_data;
 	int pc, cpu;
 
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
 	pc = preempt_count();
 
 	/* Protect the per cpu buffer, begin the rcu read side */
@@ -152,7 +159,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	raw_data = per_cpu_ptr(trace_buf, cpu);
 
 	/* zero the dead bytes from align to not leak stack to user */
-	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
 
 	entry = (struct trace_entry *)raw_data;
 	tracing_generic_entry_update(entry, *irq_flags, pc);
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 8a8f52d..bc0f670 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -200,7 +200,7 @@ endif
 
 CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS)
+ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
 STRIP ?= strip
 
@@ -492,19 +492,19 @@ ifeq ($(uname_S),Darwin)
 	PTHREAD_LIBS =
 endif
 
-ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 	msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
 endif
 
-	ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+	ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 		BASIC_CFLAGS += -DLIBELF_NO_MMAP
 	endif
 else
 	msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 	msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev);
 	BASIC_CFLAGS += -DNO_DWARF_SUPPORT
 else
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 33a414b..6a72f14 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -208,7 +208,7 @@ static void python_process_event(int cpu, void *data,
 				 int size __unused,
 				 unsigned long long nsecs, char *comm)
 {
-	PyObject *handler, *retval, *context, *t;
+	PyObject *handler, *retval, *context, *t, *obj;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long long val;
@@ -256,16 +256,23 @@ static void python_process_event(int cpu, void *data,
 				offset &= 0xffff;
 			} else
 				offset = field->offset;
-			PyTuple_SetItem(t, n++,
-				PyString_FromString((char *)data + offset));
+			obj = PyString_FromString((char *)data + offset);
 		} else { /* FIELD_IS_NUMERIC */
 			val = read_size(data + field->offset, field->size);
 			if (field->flags & FIELD_IS_SIGNED) {
-				PyTuple_SetItem(t, n++, PyInt_FromLong(val));
+				if ((long long)val >= LONG_MIN &&
+				    (long long)val <= LONG_MAX)
+					obj = PyInt_FromLong(val);
+				else
+					obj = PyLong_FromLongLong(val);
 			} else {
-				PyTuple_SetItem(t, n++, PyInt_FromLong(val));
+				if (val <= LONG_MAX)
+					obj = PyInt_FromLong(val);
+				else
+					obj = PyLong_FromUnsignedLongLong(val);
 			}
 		}
+		PyTuple_SetItem(t, n++, obj);
 	}
 
 	if (_PyTuple_Resize(&t, n) == -1)

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-04-03 10:47 Frederic Weisbecker
  0 siblings, 0 replies; 376+ messages in thread
From: Frederic Weisbecker @ 2010-04-03 10:47 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: LKML, Frederic Weisbecker, Michael Ellerman, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Paul Mackerras

Ingo,

Please pull the perf/urgent branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
	perf/urgent

Thanks,
	Frederic
---

Frederic Weisbecker (2):
      perf: Always build the stub perf_arch_fetch_caller_regs version
      perf: Always build the powerpc perf_arch_fetch_caller_regs version


 arch/powerpc/kernel/misc.S |    2 --
 kernel/perf_event.c        |    3 +--
 2 files changed, 1 insertions(+), 4 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-03-28  5:11 Frederic Weisbecker
@ 2010-03-29  3:33 ` Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-03-29  3:33 UTC (permalink / raw)
  To: Frederic Weisbecker
  Cc: LKML, Peter Zijlstra, Arnaldo Carvalho de Melo, Paul Mackerras,
	David Miller, Steven Rostedt


* Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Ingo,
> 
> Please pull the perf/urgent branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/urgent
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (2):
>       perf: Correctly align perf event tracing buffer
>       perf: Use hot regs with software sched switch/migrate events
> 
> 
>  include/linux/perf_event.h      |   21 ++++++++++++++-------
>  kernel/perf_event.c             |    4 +---
>  kernel/trace/trace_event_perf.c |   11 +++++++++--
>  3 files changed, 24 insertions(+), 12 deletions(-)

Pulled, thanks a lot Frederic!

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-03-28  5:11 Frederic Weisbecker
  2010-03-29  3:33 ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Frederic Weisbecker @ 2010-03-28  5:11 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: LKML, Frederic Weisbecker, Peter Zijlstra,
	Arnaldo Carvalho de Melo, Paul Mackerras, David Miller,
	Steven Rostedt

Ingo,

Please pull the perf/urgent branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
	perf/urgent

Thanks,
	Frederic
---

Frederic Weisbecker (2):
      perf: Correctly align perf event tracing buffer
      perf: Use hot regs with software sched switch/migrate events


 include/linux/perf_event.h      |   21 ++++++++++++++-------
 kernel/perf_event.c             |    4 +---
 kernel/trace/trace_event_perf.c |   11 +++++++++--
 3 files changed, 24 insertions(+), 12 deletions(-)

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-03-26 15:16 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-03-26 15:16 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras,
	Arnaldo Carvalho de Melo,
	=?unknown-8bit?B?RnLDqWTDqXJpYw==?= Weisbecker, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (2):
      perf top: Improve the autosizing of column lenghts
      perf top: Add missing initialization to zero

Masami Hiramatsu (4):
      perf probe: Fix probe_point buffer overrun
      perf probe: Fix need_dwarf flag if lazy matching is used
      perf probe: Fix offset to allow signed value
      perf probe: Use original address instead of CU-based address

Paul Mackerras (1):
      powerpc/perf_events: Fix call-graph recording, add perf_arch_fetch_caller_regs


 arch/powerpc/include/asm/asm-compat.h |    2 ++
 arch/powerpc/kernel/misc.S            |   28 ++++++++++++++++++++++++++++
 tools/perf/builtin-probe.c            |    1 -
 tools/perf/builtin-top.c              |   13 +++++++++----
 tools/perf/util/probe-event.c         |    2 +-
 tools/perf/util/probe-finder.c        |   18 +++++++-----------
 tools/perf/util/probe-finder.h        |    1 -
 tools/perf/util/symbol.c              |   18 +++++++++++++-----
 tools/perf/util/symbol.h              |    3 ++-
 9 files changed, 62 insertions(+), 24 deletions(-)

diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index c1b475a..a9b91ed 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -28,6 +28,7 @@
 #define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
+#define PPC_LR_STKOFF	16
 
 /* Move to CR, single-entry optimized version. Only available
  * on POWER4 and later.
@@ -51,6 +52,7 @@
 #define PPC_STLCX	stringify_in_c(stwcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzw)
 #define PPC_MTOCRF	stringify_in_c(mtcrf)
+#define PPC_LR_STKOFF	4
 
 #endif
 
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 2d29752..b485a87 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -127,3 +127,31 @@ _GLOBAL(__setup_cpu_power7)
 _GLOBAL(__restore_cpu_power7)
 	/* place holder */
 	blr
+
+#ifdef CONFIG_EVENT_TRACING
+/*
+ * Get a minimal set of registers for our caller's nth caller.
+ * r3 = regs pointer, r5 = n.
+ *
+ * We only get R1 (stack pointer), NIP (next instruction pointer)
+ * and LR (link register).  These are all we can get in the
+ * general case without doing complicated stack unwinding, but
+ * fortunately they are enough to do a stack backtrace, which
+ * is all we need them for.
+ */
+_GLOBAL(perf_arch_fetch_caller_regs)
+	mr	r6,r1
+	cmpwi	r5,0
+	mflr	r4
+	ble	2f
+	mtctr	r5
+1:	PPC_LL	r6,0(r6)
+	bdnz	1b
+	PPC_LL	r4,PPC_LR_STKOFF(r6)
+2:	PPC_LL	r7,0(r6)
+	PPC_LL	r7,PPC_LR_STKOFF(r7)
+	PPC_STL	r6,GPR1-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r4,_NIP-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r7,_LINK-STACK_FRAME_OVERHEAD(r3)
+	blr
+#endif /* CONFIG_EVENT_TRACING */
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c30a335..152d6c9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -47,7 +47,6 @@
 #include "util/probe-event.h"
 
 #define MAX_PATH_LEN 256
-#define MAX_PROBES 128
 
 /* Session management structure */
 static struct {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0b719e3..1f52932 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -455,7 +455,7 @@ static void print_sym_table(void)
 	struct sym_entry *syme, *n;
 	struct rb_root tmp = RB_ROOT;
 	struct rb_node *nd;
-	int sym_width = 0, dso_width = 0, max_dso_width;
+	int sym_width = 0, dso_width = 0, dso_short_width = 0;
 	const int win_width = winsize.ws_col - 1;
 
 	samples = userspace_samples = 0;
@@ -545,15 +545,20 @@ static void print_sym_table(void)
 		if (syme->map->dso->long_name_len > dso_width)
 			dso_width = syme->map->dso->long_name_len;
 
+		if (syme->map->dso->short_name_len > dso_short_width)
+			dso_short_width = syme->map->dso->short_name_len;
+
 		if (syme->name_len > sym_width)
 			sym_width = syme->name_len;
 	}
 
 	printed = 0;
 
-	max_dso_width = winsize.ws_col - sym_width - 29;
-	if (dso_width > max_dso_width)
-		dso_width = max_dso_width;
+	if (sym_width + dso_width > winsize.ws_col - 29) {
+		dso_width = dso_short_width;
+		if (sym_width + dso_width > winsize.ws_col - 29)
+			sym_width = winsize.ws_col - dso_width - 29;
+	}
 	putchar('\n');
 	if (nr_counters == 1)
 		printf("             samples  pcnt");
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 53181db..7c004b6 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -242,7 +242,7 @@ void parse_perf_probe_event(const char *str, struct probe_point *pp,
 
 	/* Parse probe point */
 	parse_perf_probe_probepoint(argv[0], pp);
-	if (pp->file || pp->line)
+	if (pp->file || pp->line || pp->lazy_line)
 		*need_dwarf = true;
 
 	/* Copy arguments and ensure return probe has no C argument */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1e6c65e..c171a24 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -333,8 +333,8 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 		die("%u exceeds max register number.", regn);
 
 	if (deref)
-		ret = snprintf(pf->buf, pf->len, " %s=+%ju(%s)",
-			       pf->var, (uintmax_t)offs, regs);
+		ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)",
+			       pf->var, (intmax_t)offs, regs);
 	else
 		ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
 	DIE_IF(ret < 0);
@@ -352,8 +352,7 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
 		goto error;
 	/* TODO: handle more than 1 exprs */
-	ret = dwarf_getlocation_addr(&attr, (pf->addr - pf->cu_base),
-				     &expr, &nexpr, 1);
+	ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1);
 	if (ret <= 0 || nexpr == 0)
 		goto error;
 
@@ -437,8 +436,7 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 
 	/* Get the frame base attribute/ops */
 	dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
-	ret = dwarf_getlocation_addr(&fb_attr, (pf->addr - pf->cu_base),
-				     &pf->fb_ops, &nops, 1);
+	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0)
 		pf->fb_ops = NULL;
 
@@ -455,6 +453,9 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 	/* *pf->fb_ops will be cached in libdw. Don't free it. */
 	pf->fb_ops = NULL;
 
+	if (pp->found == MAX_PROBES)
+		die("Too many( > %d) probe point found.\n", MAX_PROBES);
+
 	pp->probes[pp->found] = strdup(tmp);
 	pp->found++;
 }
@@ -641,7 +642,6 @@ static void find_probe_point_by_func(struct probe_finder *pf)
 int find_probe_point(int fd, struct probe_point *pp)
 {
 	struct probe_finder pf = {.pp = pp};
-	int ret;
 	Dwarf_Off off, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
@@ -668,10 +668,6 @@ int find_probe_point(int fd, struct probe_point *pp)
 			pf.fname = NULL;
 
 		if (!pp->file || pf.fname) {
-			/* Save CU base address (for frame_base) */
-			ret = dwarf_lowpc(&pf.cu_die, &pf.cu_base);
-			if (ret != 0)
-				pf.cu_base = 0;
 			if (pp->function)
 				find_probe_point_by_func(&pf);
 			else if (pp->lazy_line)
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index d1a6517..21f7354 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -71,7 +71,6 @@ struct probe_finder {
 
 	/* For variable searching */
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
-	Dwarf_Addr		cu_base;	/* Current CU base address */
 	const char		*var;		/* Current variable name */
 	char			*buf;		/* Current output buffer */
 	int			len;		/* Length of output buffer */
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 323c0ae..c458c4a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -163,9 +163,17 @@ void dso__set_long_name(struct dso *self, char *name)
 	self->long_name_len = strlen(name);
 }
 
+static void dso__set_short_name(struct dso *self, const char *name)
+{
+	if (name == NULL)
+		return;
+	self->short_name = name;
+	self->short_name_len = strlen(name);
+}
+
 static void dso__set_basename(struct dso *self)
 {
-	self->short_name = basename(self->long_name);
+	dso__set_short_name(self, basename(self->long_name));
 }
 
 struct dso *dso__new(const char *name)
@@ -176,7 +184,7 @@ struct dso *dso__new(const char *name)
 		int i;
 		strcpy(self->name, name);
 		dso__set_long_name(self, self->name);
-		self->short_name = self->name;
+		dso__set_short_name(self, self->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
 		self->slen_calculated = 0;
@@ -897,7 +905,6 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
 	struct map *curr_map = map;
 	struct dso *curr_dso = self;
-	size_t dso_name_len = strlen(self->short_name);
 	Elf_Data *symstrs, *secstrs;
 	uint32_t nr_syms;
 	int err = -1;
@@ -987,7 +994,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 			char dso_name[PATH_MAX];
 
 			if (strcmp(section_name,
-				   curr_dso->short_name + dso_name_len) == 0)
+				   (curr_dso->short_name +
+				    self->short_name_len)) == 0)
 				goto new_symbol;
 
 			if (strcmp(section_name, ".text") == 0) {
@@ -1782,7 +1790,7 @@ struct dso *dso__new_kernel(const char *name)
 	struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
 
 	if (self != NULL) {
-		self->short_name = "[kernel]";
+		dso__set_short_name(self, "[kernel]");
 		self->kernel	 = 1;
 	}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 280dadd..f30a374 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -110,9 +110,10 @@ struct dso {
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
-	u16		 long_name_len;
 	const char	 *short_name;
 	char	 	 *long_name;
+	u16		 long_name_len;
+	u16		 short_name_len;
 	char		 name[0];
 };
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-03-16 16:06 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-03-16 16:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras,
	Arnaldo Carvalho de Melo, Thomas Gleixner, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

Now that i look at the combo diff, it seems uncomfortably big to me :-/ A good 
chunk of that is due to three categories of fixes:

 - the hotplug cpu notifier fixes (kernel side)
 - the cpumap fix for hotplugged cpu enumeration (tools side)
 - the multi-event displaying fixes for perf report (tools side)

In hindsight, i could/should have pushed the last one to .35 and we could have 
saved ~200 lines of diffs. If you think it's not acceptable i'll rebase these 
bits and provide a more compact tree. (The rest of the cycle should be pretty 
quiet, we dont have any other pending regressions at the moment.)

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf tools: Don't trow away old map slices not overlapped by new maps
      perf probe: Add missing variable initialization
      perf report: Print the map table just after samples for which no map was found
      perf record: Don't try to find buildids in a zero sized file

Eric B Munson (5):
      perf record: Add ID and to recorded event data when recording multiple events
      perf session: Change add_hist_entry to take the tree root instead of session
      perf session: Add storage for seperating event types in report
      perf session: Change perf_session post processing functions to take histogram tree
      perf report: Add multiple event support

Frederic Weisbecker (5):
      lockdep: Move lock events under lockdep recursion protection
      perf/x86-64: Use frame pointer to walk on irq and process stacks
      perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot
      perf: Take a hot regs snapshot for trace events
      perf: Drop the obsolete profile naming for trace events

John Kacur (1):
      perf: Make the install relative to DESTDIR if specified

Masami Hiramatsu (1):
      kprobes: Calculate the index correctly when freeing the out-of-line execution slot

Paul Mackerras (2):
      perf_event: Fix oops triggered by cpu offline/online
      perf tools: Fix sparse CPU numbering related bugs

Peter Zijlstra (15):
      perf: Rework and fix the arch CPU-hotplug hooks
      perf: Optimize perf_disable
      perf, x86, Do not user perf_disable from NMI context
      perf, x86: Remove superfluous arguments to x86_perf_event_set_period()
      perf, x86: Remove superfluous arguments to x86_perf_event_update()
      perf, x86: Change x86_pmu.{enable,disable} calling convention
      perf, x86: Use unlocked bitops
      perf, x86: Fix x86_pmu_start
      perf, x86: Avoid double disable on throttle vs ioctl(PERF_IOC_DISABLE)
      perf, x86: Properly account n_added
      perf, x86: Fix double disable calls
      perf, x86: Fix double enable calls
      perf: Provide better condition for event rotation
      perf, ppc: Fix compile error due to new cpu notifiers
      perf, x86: Fix hw_perf_enable() event assignment

Xiao Guangrong (1):
      perf: export perf_trace_regs and perf_arch_fetch_caller_regs


 arch/powerpc/kernel/perf_event.c                   |   21 ++-
 arch/sh/kernel/perf_event.c                        |   20 ++-
 arch/x86/kernel/cpu/perf_event.c                   |  182 +++++++++++---------
 arch/x86/kernel/cpu/perf_event_amd.c               |   62 +++----
 arch/x86/kernel/cpu/perf_event_intel.c             |   57 +++---
 arch/x86/kernel/cpu/perf_event_p6.c                |   10 +-
 arch/x86/kernel/dumpstack.h                        |   15 ++
 arch/x86/kernel/dumpstack_64.c                     |    4 +-
 include/linux/ftrace_event.h                       |   23 ++-
 include/linux/perf_event.h                         |   59 ++++++-
 include/linux/syscalls.h                           |   24 ++--
 include/trace/ftrace.h                             |   44 +++--
 include/trace/syscall.h                            |    8 +-
 kernel/kprobes.c                                   |    3 +-
 kernel/lockdep.c                                   |    9 +-
 kernel/perf_event.c                                |   82 ++++-----
 kernel/trace/Makefile                              |    2 +-
 .../{trace_event_profile.c => trace_event_perf.c}  |   48 +++---
 kernel/trace/trace_events.c                        |    2 +-
 kernel/trace/trace_kprobe.c                        |   29 ++--
 kernel/trace/trace_syscalls.c                      |   72 ++++----
 tools/perf/Documentation/Makefile                  |    4 +-
 tools/perf/Makefile                                |    6 +-
 tools/perf/builtin-annotate.c                      |    6 +-
 tools/perf/builtin-diff.c                          |   13 +-
 tools/perf/builtin-record.c                        |   13 +-
 tools/perf/builtin-report.c                        |  112 +++++++++++--
 tools/perf/builtin-stat.c                          |   10 +-
 tools/perf/builtin-top.c                           |    9 +-
 tools/perf/util/cpumap.c                           |   59 +++++++
 tools/perf/util/cpumap.h                           |    7 +
 tools/perf/util/event.h                            |    9 +
 tools/perf/util/hist.c                             |   50 +++---
 tools/perf/util/hist.h                             |   12 +-
 tools/perf/util/probe-finder.c                     |    2 +-
 tools/perf/util/session.c                          |    1 +
 tools/perf/util/session.h                          |    1 +
 tools/perf/util/thread.c                           |   41 ++++-
 tools/perf/util/thread.h                           |    3 +
 39 files changed, 736 insertions(+), 398 deletions(-)
 rename kernel/trace/{trace_event_profile.c => trace_event_perf.c} (69%)
 create mode 100644 tools/perf/util/cpumap.c
 create mode 100644 tools/perf/util/cpumap.h

diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 5120bd4..08460a2 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1287,7 +1287,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 		irq_exit();
 }
 
-void hw_perf_event_setup(int cpu)
+static void power_pmu_setup(int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
@@ -1297,6 +1297,23 @@ void hw_perf_event_setup(int cpu)
 	cpuhw->mmcr[0] = MMCR0_FC;
 }
 
+static int __cpuinit
+power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		power_pmu_setup(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
 int register_power_pmu(struct power_pmu *pmu)
 {
 	if (ppmu)
@@ -1314,5 +1331,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
+	perf_cpu_notifier(power_pmu_notifier);
+
 	return 0;
 }
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7ff0943..9f253e9 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -275,13 +275,30 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	return &pmu;
 }
 
-void hw_perf_event_setup(int cpu)
+static void sh_pmu_setup(int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
 	memset(cpuhw, 0, sizeof(struct cpu_hw_events));
 }
 
+static int __cpuinit
+sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		sh_pmu_setup(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
 void hw_perf_enable(void)
 {
 	if (!sh_pmu_initialized())
@@ -308,5 +325,6 @@ int register_sh_pmu(struct sh_pmu *pmu)
 
 	WARN_ON(pmu->num_events > MAX_HWEVENTS);
 
+	perf_cpu_notifier(sh_pmu_notifier);
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 42aafd1..7645fae 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -133,8 +133,8 @@ struct x86_pmu {
 	int		(*handle_irq)(struct pt_regs *);
 	void		(*disable_all)(void);
 	void		(*enable_all)(void);
-	void		(*enable)(struct hw_perf_event *, int);
-	void		(*disable)(struct hw_perf_event *, int);
+	void		(*enable)(struct perf_event *);
+	void		(*disable)(struct perf_event *);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	u64		(*event_map)(int);
@@ -157,6 +157,11 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+
+	void		(*cpu_prepare)(int cpu);
+	void		(*cpu_starting)(int cpu);
+	void		(*cpu_dying)(int cpu);
+	void		(*cpu_dead)(int cpu);
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -165,8 +170,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
-static int x86_perf_event_set_period(struct perf_event *event,
-			     struct hw_perf_event *hwc, int idx);
+static int x86_perf_event_set_period(struct perf_event *event);
 
 /*
  * Generalized hw caching related hw_event table, filled
@@ -189,11 +193,12 @@ static u64 __read_mostly hw_cache_event_ids
  * Returns the delta events processed.
  */
 static u64
-x86_perf_event_update(struct perf_event *event,
-			struct hw_perf_event *hwc, int idx)
+x86_perf_event_update(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.event_bits;
 	u64 prev_raw_count, new_raw_count;
+	int idx = hwc->idx;
 	s64 delta;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
@@ -293,7 +298,7 @@ static inline bool bts_available(void)
 	return x86_pmu.enable_bts != NULL;
 }
 
-static inline void init_debug_store_on_cpu(int cpu)
+static void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 
@@ -305,7 +310,7 @@ static inline void init_debug_store_on_cpu(int cpu)
 		     (u32)((u64)(unsigned long)ds >> 32));
 }
 
-static inline void fini_debug_store_on_cpu(int cpu)
+static void fini_debug_store_on_cpu(int cpu)
 {
 	if (!per_cpu(cpu_hw_events, cpu).ds)
 		return;
@@ -638,7 +643,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		if (test_bit(hwc->idx, used_mask))
 			break;
 
-		set_bit(hwc->idx, used_mask);
+		__set_bit(hwc->idx, used_mask);
 		if (assign)
 			assign[i] = hwc->idx;
 	}
@@ -687,7 +692,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			if (j == X86_PMC_IDX_MAX)
 				break;
 
-			set_bit(j, used_mask);
+			__set_bit(j, used_mask);
 
 			if (assign)
 				assign[i] = j;
@@ -780,6 +785,7 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc,
 		hwc->last_tag == cpuc->tags[i];
 }
 
+static int x86_pmu_start(struct perf_event *event);
 static void x86_pmu_stop(struct perf_event *event);
 
 void hw_perf_enable(void)
@@ -796,6 +802,7 @@ void hw_perf_enable(void)
 		return;
 
 	if (cpuc->n_added) {
+		int n_running = cpuc->n_events - cpuc->n_added;
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -803,8 +810,7 @@ void hw_perf_enable(void)
 		 * step1: save events moving to new counters
 		 * step2: reprogram moved events into new counters
 		 */
-		for (i = 0; i < cpuc->n_events; i++) {
-
+		for (i = 0; i < n_running; i++) {
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
@@ -819,29 +825,18 @@ void hw_perf_enable(void)
 				continue;
 
 			x86_pmu_stop(event);
-
-			hwc->idx = -1;
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {
-
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
-			if (hwc->idx == -1) {
+			if (!match_prev_assignment(hwc, cpuc, i))
 				x86_assign_hw_event(event, cpuc, i);
-				x86_perf_event_set_period(event, hwc, hwc->idx);
-			}
-			/*
-			 * need to mark as active because x86_pmu_disable()
-			 * clear active_mask and events[] yet it preserves
-			 * idx
-			 */
-			set_bit(hwc->idx, cpuc->active_mask);
-			cpuc->events[hwc->idx] = event;
+			else if (i < n_running)
+				continue;
 
-			x86_pmu.enable(hwc, hwc->idx);
-			perf_event_update_userpage(event);
+			x86_pmu_start(event);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();
@@ -853,15 +848,16 @@ void hw_perf_enable(void)
 	x86_pmu.enable_all();
 }
 
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx,
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
 			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
-static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static inline void x86_pmu_disable_event(struct perf_event *event)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
+	struct hw_perf_event *hwc = &event->hw;
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -871,12 +867,12 @@ static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
  * To be called with the event disabled in hw:
  */
 static int
-x86_perf_event_set_period(struct perf_event *event,
-			     struct hw_perf_event *hwc, int idx)
+x86_perf_event_set_period(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	s64 left = atomic64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
-	int err, ret = 0;
+	int err, ret = 0, idx = hwc->idx;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
 		return 0;
@@ -922,11 +918,11 @@ x86_perf_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void x86_pmu_enable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	if (cpuc->enabled)
-		__x86_pmu_enable_event(hwc, idx);
+		__x86_pmu_enable_event(&event->hw);
 }
 
 /*
@@ -962,34 +958,32 @@ static int x86_pmu_enable(struct perf_event *event)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->n_events = n;
-	cpuc->n_added  = n - n0;
+	cpuc->n_added += n - n0;
 
 	return 0;
 }
 
 static int x86_pmu_start(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = event->hw.idx;
 
-	if (hwc->idx == -1)
+	if (idx == -1)
 		return -EAGAIN;
 
-	x86_perf_event_set_period(event, hwc, hwc->idx);
-	x86_pmu.enable(hwc, hwc->idx);
+	x86_perf_event_set_period(event);
+	cpuc->events[idx] = event;
+	__set_bit(idx, cpuc->active_mask);
+	x86_pmu.enable(event);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
 
 static void x86_pmu_unthrottle(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (WARN_ON_ONCE(hwc->idx >= X86_PMC_IDX_MAX ||
-				cpuc->events[hwc->idx] != event))
-		return;
-
-	x86_pmu.enable(hwc, hwc->idx);
+	int ret = x86_pmu_start(event);
+	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)
@@ -1049,18 +1043,16 @@ static void x86_pmu_stop(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	/*
-	 * Must be done before we disable, otherwise the nmi handler
-	 * could reenable again:
-	 */
-	clear_bit(idx, cpuc->active_mask);
-	x86_pmu.disable(hwc, idx);
+	if (!__test_and_clear_bit(idx, cpuc->active_mask))
+		return;
+
+	x86_pmu.disable(event);
 
 	/*
 	 * Drain the remaining delta count out of a event
 	 * that we are disabling:
 	 */
-	x86_perf_event_update(event, hwc, idx);
+	x86_perf_event_update(event);
 
 	cpuc->events[idx] = NULL;
 }
@@ -1108,7 +1100,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		event = cpuc->events[idx];
 		hwc = &event->hw;
 
-		val = x86_perf_event_update(event, hwc, idx);
+		val = x86_perf_event_update(event);
 		if (val & (1ULL << (x86_pmu.event_bits - 1)))
 			continue;
 
@@ -1118,11 +1110,11 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		handled		= 1;
 		data.period	= event->hw.last_period;
 
-		if (!x86_perf_event_set_period(event, hwc, idx))
+		if (!x86_perf_event_set_period(event))
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu.disable(hwc, idx);
+			x86_pmu_stop(event);
 	}
 
 	if (handled)
@@ -1309,7 +1301,7 @@ int hw_perf_group_sched_in(struct perf_event *leader,
 	memcpy(cpuc->assign, assign, n0*sizeof(int));
 
 	cpuc->n_events  = n0;
-	cpuc->n_added   = n1;
+	cpuc->n_added  += n1;
 	ctx->nr_active += n1;
 
 	/*
@@ -1337,6 +1329,39 @@ undo:
 #include "perf_event_p6.c"
 #include "perf_event_intel.c"
 
+static int __cpuinit
+x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		if (x86_pmu.cpu_prepare)
+			x86_pmu.cpu_prepare(cpu);
+		break;
+
+	case CPU_STARTING:
+		if (x86_pmu.cpu_starting)
+			x86_pmu.cpu_starting(cpu);
+		break;
+
+	case CPU_DYING:
+		if (x86_pmu.cpu_dying)
+			x86_pmu.cpu_dying(cpu);
+		break;
+
+	case CPU_DEAD:
+		if (x86_pmu.cpu_dead)
+			x86_pmu.cpu_dead(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
 static void __init pmu_check_apic(void)
 {
 	if (cpu_has_apic)
@@ -1415,11 +1440,13 @@ void __init init_hw_perf_events(void)
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_events_fixed);
 	pr_info("... event mask:             %016Lx\n", perf_event_mask);
+
+	perf_cpu_notifier(x86_pmu_notifier);
 }
 
 static inline void x86_pmu_read(struct perf_event *event)
 {
-	x86_perf_event_update(event, &event->hw, event->hw.idx);
+	x86_perf_event_update(event);
 }
 
 static const struct pmu pmu = {
@@ -1675,28 +1702,15 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-void hw_perf_event_setup_online(int cpu)
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
-	init_debug_store_on_cpu(cpu);
-
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		amd_pmu_cpu_online(cpu);
-		break;
-	default:
-		return;
-	}
-}
-
-void hw_perf_event_setup_offline(int cpu)
-{
-	init_debug_store_on_cpu(cpu);
-
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		amd_pmu_cpu_offline(cpu);
-		break;
-	default:
-		return;
-	}
+	regs->ip = ip;
+	/*
+	 * perf_arch_fetch_caller_regs adds another call, we need to increment
+	 * the skip level
+	 */
+	regs->bp = rewind_frame_pointer(skip + 1);
+	regs->cs = __KERNEL_CS;
+	local_save_flags(regs->flags);
 }
+EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 8f3dbfd..573458f 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -271,28 +271,6 @@ done:
 	return &emptyconstraint;
 }
 
-static __initconst struct x86_pmu amd_pmu = {
-	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= x86_pmu_enable_all,
-	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.eventsel		= MSR_K7_EVNTSEL0,
-	.perfctr		= MSR_K7_PERFCTR0,
-	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
-	.apic			= 1,
-	/* use highest bit to detect overflow */
-	.max_period		= (1ULL << 47) - 1,
-	.get_event_constraints	= amd_get_event_constraints,
-	.put_event_constraints	= amd_put_event_constraints
-};
-
 static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 {
 	struct amd_nb *nb;
@@ -309,7 +287,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	 * initialize all possible NB constraints
 	 */
 	for (i = 0; i < x86_pmu.num_events; i++) {
-		set_bit(i, nb->event_constraints[i].idxmsk);
+		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
 	return nb;
@@ -378,6 +356,31 @@ static void amd_pmu_cpu_offline(int cpu)
 	raw_spin_unlock(&amd_nb_lock);
 }
 
+static __initconst struct x86_pmu amd_pmu = {
+	.name			= "AMD",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= x86_pmu_enable_all,
+	.enable			= x86_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.eventsel		= MSR_K7_EVNTSEL0,
+	.perfctr		= MSR_K7_PERFCTR0,
+	.event_map		= amd_pmu_event_map,
+	.raw_event		= amd_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
+	.num_events		= 4,
+	.event_bits		= 48,
+	.event_mask		= (1ULL << 48) - 1,
+	.apic			= 1,
+	/* use highest bit to detect overflow */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= amd_get_event_constraints,
+	.put_event_constraints	= amd_put_event_constraints,
+
+	.cpu_prepare		= amd_pmu_cpu_online,
+	.cpu_dead		= amd_pmu_cpu_offline,
+};
+
 static __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
@@ -390,11 +393,6 @@ static __init int amd_pmu_init(void)
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
 	       sizeof(hw_cache_event_ids));
 
-	/*
-	 * explicitly initialize the boot cpu, other cpus will get
-	 * the cpu hotplug callbacks from smp_init()
-	 */
-	amd_pmu_cpu_online(smp_processor_id());
 	return 0;
 }
 
@@ -405,12 +403,4 @@ static int amd_pmu_init(void)
 	return 0;
 }
 
-static void amd_pmu_cpu_online(int cpu)
-{
-}
-
-static void amd_pmu_cpu_offline(int cpu)
-{
-}
-
 #endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 44b60c8..84bfde6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -548,9 +548,9 @@ static inline void intel_pmu_ack_status(u64 ack)
 }
 
 static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 {
-	int idx = __idx - X86_PMC_IDX_FIXED;
+	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
 	mask = 0xfULL << (idx * 4);
@@ -621,26 +621,28 @@ static void intel_pmu_drain_bts_buffer(void)
 }
 
 static inline void
-intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+intel_pmu_disable_event(struct perf_event *event)
 {
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
 		return;
 	}
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_disable_fixed(hwc, idx);
+		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
-	x86_pmu_disable_event(hwc, idx);
+	x86_pmu_disable_event(event);
 }
 
 static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
-	int idx = __idx - X86_PMC_IDX_FIXED;
+	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, bits, mask;
 	int err;
 
@@ -670,9 +672,11 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
 	err = checking_wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void intel_pmu_enable_event(struct perf_event *event)
 {
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		if (!__get_cpu_var(cpu_hw_events).enabled)
 			return;
 
@@ -681,11 +685,11 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 	}
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc, idx);
+		intel_pmu_enable_fixed(hwc);
 		return;
 	}
 
-	__x86_pmu_enable_event(hwc, idx);
+	__x86_pmu_enable_event(hwc);
 }
 
 /*
@@ -694,14 +698,8 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
  */
 static int intel_pmu_save_and_restart(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-	int ret;
-
-	x86_perf_event_update(event, hwc, idx);
-	ret = x86_perf_event_set_period(event, hwc, idx);
-
-	return ret;
+	x86_perf_event_update(event);
+	return x86_perf_event_set_period(event);
 }
 
 static void intel_pmu_reset(void)
@@ -745,11 +743,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
-	perf_disable();
+	intel_pmu_disable_all();
 	intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
-		perf_enable();
+		intel_pmu_enable_all();
 		return 0;
 	}
 
@@ -759,8 +757,7 @@ again:
 		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
 		perf_event_print_debug();
 		intel_pmu_reset();
-		perf_enable();
-		return 1;
+		goto done;
 	}
 
 	inc_irq_stat(apic_perf_irqs);
@@ -768,7 +765,6 @@ again:
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
 
-		clear_bit(bit, (unsigned long *) &status);
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
@@ -778,7 +774,7 @@ again:
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			intel_pmu_disable_event(&event->hw, bit);
+			x86_pmu_stop(event);
 	}
 
 	intel_pmu_ack_status(ack);
@@ -790,8 +786,8 @@ again:
 	if (status)
 		goto again;
 
-	perf_enable();
-
+done:
+	intel_pmu_enable_all();
 	return 1;
 }
 
@@ -870,7 +866,10 @@ static __initconst struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.enable_bts		= intel_pmu_enable_bts,
 	.disable_bts		= intel_pmu_disable_bts,
-	.get_event_constraints	= intel_get_event_constraints
+	.get_event_constraints	= intel_get_event_constraints,
+
+	.cpu_starting		= init_debug_store_on_cpu,
+	.cpu_dying		= fini_debug_store_on_cpu,
 };
 
 static __init int intel_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index a4e67b9..a330485 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -77,27 +77,29 @@ static void p6_pmu_enable_all(void)
 }
 
 static inline void
-p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+p6_pmu_disable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 val = P6_NOP_EVENT;
 
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
-static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void p6_pmu_enable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
 static __initconst struct x86_pmu p6_pmu = {
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 4fd1420..29e5f7c 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,4 +29,19 @@ struct stack_frame {
 	struct stack_frame *next_frame;
 	unsigned long return_address;
 };
+
+static inline unsigned long rewind_frame_pointer(int n)
+{
+	struct stack_frame *frame;
+
+	get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+	while (n--)
+		frame = frame->next_frame;
 #endif
+
+	return (unsigned long)frame;
+}
+
+#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d5e2a2e..272c9f1 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -208,7 +208,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
 				if (ops->stack(data, "IRQ") < 0)
 					break;
-				bp = print_context_stack(tinfo, stack, bp,
+				bp = ops->walk_stack(tinfo, stack, bp,
 					ops, data, irq_stack_end, &graph);
 				/*
 				 * We link to the next stack (which would be
@@ -229,7 +229,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	/*
 	 * This handles the process stack:
 	 */
-	bp = print_context_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
 	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6b7c444..c0f4b36 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -131,12 +131,12 @@ struct ftrace_event_call {
 	void			*mod;
 	void			*data;
 
-	int			profile_count;
-	int			(*profile_enable)(struct ftrace_event_call *);
-	void			(*profile_disable)(struct ftrace_event_call *);
+	int			perf_refcount;
+	int			(*perf_event_enable)(struct ftrace_event_call *);
+	void			(*perf_event_disable)(struct ftrace_event_call *);
 };
 
-#define FTRACE_MAX_PROFILE_SIZE	2048
+#define PERF_MAX_TRACE_SIZE	2048
 
 #define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
@@ -187,22 +187,25 @@ do {									\
 
 #ifdef CONFIG_PERF_EVENTS
 struct perf_event;
-extern int ftrace_profile_enable(int event_id);
-extern void ftrace_profile_disable(int event_id);
+
+DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+
+extern int perf_trace_enable(int event_id);
+extern void perf_trace_disable(int event_id);
 extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
 extern void *
-ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
+perf_trace_buf_prepare(int size, unsigned short type, int *rctxp,
 			 unsigned long *irq_flags);
 
 static inline void
-ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-		       u64 count, unsigned long irq_flags)
+perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+		       u64 count, unsigned long irq_flags, struct pt_regs *regs)
 {
 	struct trace_entry *entry = raw_data;
 
-	perf_tp_event(entry->type, addr, count, raw_data, size);
+	perf_tp_event(entry->type, addr, count, raw_data, size, regs);
 	perf_swevent_put_recursion_context(rctx);
 	local_irq_restore(irq_flags);
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6f8cd7d..9547703 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -452,6 +452,8 @@ enum perf_callchain_context {
 #include <linux/fs.h>
 #include <linux/pid_namespace.h>
 #include <linux/workqueue.h>
+#include <linux/ftrace.h>
+#include <linux/cpu.h>
 #include <asm/atomic.h>
 
 #define PERF_MAX_STACK_DEPTH		255
@@ -847,6 +849,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 		__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+/*
+ * Take a snapshot of the regs. Skip ip and frame pointer to
+ * the nth caller. We only need a few of the regs:
+ * - ip for PERF_SAMPLE_IP
+ * - cs for user_mode() tests
+ * - bp for callchains
+ * - eflags, for future purposes, just in case
+ */
+static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+{
+	unsigned long ip;
+
+	memset(regs, 0, sizeof(*regs));
+
+	switch (skip) {
+	case 1 :
+		ip = CALLER_ADDR0;
+		break;
+	case 2 :
+		ip = CALLER_ADDR1;
+		break;
+	case 3 :
+		ip = CALLER_ADDR2;
+		break;
+	case 4:
+		ip = CALLER_ADDR3;
+		break;
+	/* No need to support further for now */
+	default:
+		ip = 0;
+	}
+
+	return perf_arch_fetch_caller_regs(regs, ip, skip);
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
@@ -880,7 +920,8 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size, struct pt_regs *regs);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
@@ -936,5 +977,21 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 #define perf_output_put(handle, x) \
 	perf_output_copy((handle), &(x), sizeof(x))
 
+/*
+ * This has to have a higher priority than migration_notifier in sched.c.
+ */
+#define perf_cpu_notifier(fn)					\
+do {								\
+	static struct notifier_block fn##_nb __cpuinitdata =	\
+		{ .notifier_call = fn, .priority = 20 };	\
+	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
+		(void *)(unsigned long)smp_processor_id());	\
+	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\
+		(void *)(unsigned long)smp_processor_id());	\
+	fn(&fn##_nb, (unsigned long)CPU_ONLINE,			\
+		(void *)(unsigned long)smp_processor_id());	\
+	register_cpu_notifier(&fn##_nb);			\
+} while (0)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8126f23..51435bc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -101,18 +101,18 @@ struct perf_event_attr;
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
-	.profile_enable = prof_sysenter_enable,				       \
-	.profile_disable = prof_sysenter_disable,
+#define TRACE_SYS_ENTER_PERF_INIT(sname)				       \
+	.perf_event_enable = perf_sysenter_enable,			       \
+	.perf_event_disable = perf_sysenter_disable,
 
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)				       \
-	.profile_enable = prof_sysexit_enable,				       \
-	.profile_disable = prof_sysexit_disable,
+#define TRACE_SYS_EXIT_PERF_INIT(sname)					       \
+	.perf_event_enable = perf_sysexit_enable,			       \
+	.perf_event_disable = perf_sysexit_disable,
 #else
-#define TRACE_SYS_ENTER_PROFILE(sname)
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
-#define TRACE_SYS_EXIT_PROFILE(sname)
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#define TRACE_SYS_ENTER_PERF(sname)
+#define TRACE_SYS_ENTER_PERF_INIT(sname)
+#define TRACE_SYS_EXIT_PERF(sname)
+#define TRACE_SYS_EXIT_PERF_INIT(sname)
 #endif /* CONFIG_PERF_EVENTS */
 
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -149,7 +149,7 @@ struct perf_event_attr;
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_ENTER_PROFILE_INIT(sname)			\
+		TRACE_SYS_ENTER_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
@@ -171,7 +171,7 @@ struct perf_event_attr;
 		.regfunc		= reg_event_syscall_exit,	\
 		.unregfunc		= unreg_event_syscall_exit,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_EXIT_PROFILE_INIT(sname)			\
+		TRACE_SYS_EXIT_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_METADATA(sname, nb)				\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 0804cd5..25ab56f 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -401,18 +401,18 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args)			\
 									\
-static void ftrace_profile_##name(proto);				\
+static void perf_trace_##name(proto);					\
 									\
 static notrace int							\
-ftrace_profile_enable_##name(struct ftrace_event_call *unused)		\
+perf_trace_enable_##name(struct ftrace_event_call *unused)		\
 {									\
-	return register_trace_##name(ftrace_profile_##name);		\
+	return register_trace_##name(perf_trace_##name);		\
 }									\
 									\
 static notrace void							\
-ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
+perf_trace_disable_##name(struct ftrace_event_call *unused)		\
 {									\
-	unregister_trace_##name(ftrace_profile_##name);			\
+	unregister_trace_##name(perf_trace_##name);			\
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -507,12 +507,12 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define _TRACE_PROFILE_INIT(call)					\
-	.profile_enable = ftrace_profile_enable_##call,			\
-	.profile_disable = ftrace_profile_disable_##call,
+#define _TRACE_PERF_INIT(call)						\
+	.perf_event_enable = perf_trace_enable_##call,			\
+	.perf_event_disable = perf_trace_disable_##call,
 
 #else
-#define _TRACE_PROFILE_INIT(call)
+#define _TRACE_PERF_INIT(call)
 #endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
@@ -638,7 +638,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.print_fmt		= print_fmt_##template,			\
 	.define_fields		= ftrace_define_fields_##template,	\
-	_TRACE_PROFILE_INIT(call)					\
+	_TRACE_PERF_INIT(call)					\
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -657,18 +657,18 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.print_fmt		= print_fmt_##call,			\
 	.define_fields		= ftrace_define_fields_##template,	\
-	_TRACE_PROFILE_INIT(call)					\
+	_TRACE_PERF_INIT(call)					\
 }
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
- * Define the insertion callback to profile events
+ * Define the insertion callback to perf events
  *
  * The job is very similar to ftrace_raw_event_<call> except that we don't
  * insert in the ring buffer but in a perf counter.
  *
- * static void ftrace_profile_<call>(proto)
+ * static void ftrace_perf_<call>(proto)
  * {
  *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ftrace_event_call *event_call = &event_<call>;
@@ -757,13 +757,14 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace void							\
-ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
+perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
 			    proto)					\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
+	struct pt_regs *__regs;						\
 	int __entry_size;						\
 	int __data_size;						\
 	int rctx;							\
@@ -773,10 +774,10 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,		\
+	if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,		\
 		      "profile buffer not large enough"))		\
 		return;							\
-	entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare(	\
+	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
 		__entry_size, event_call->id, &rctx, &irq_flags);	\
 	if (!entry)							\
 		return;							\
@@ -784,17 +785,20 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 									\
 	{ assign; }							\
 									\
-	ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr,	\
-			       __count, irq_flags);			\
+	__regs = &__get_cpu_var(perf_trace_regs);			\
+	perf_fetch_caller_regs(__regs, 2);				\
+									\
+	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
+			       __count, irq_flags, __regs);		\
 }
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)		\
-static notrace void ftrace_profile_##call(proto)		\
+static notrace void perf_trace_##call(proto)			\
 {								\
 	struct ftrace_event_call *event_call = &event_##call;	\
 								\
-	ftrace_profile_templ_##template(event_call, args);	\
+	perf_trace_templ_##template(event_call, args);		\
 }
 
 #undef DEFINE_EVENT_PRINT
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 0387100..e5e5f48 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -47,10 +47,10 @@ enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
 
 #ifdef CONFIG_PERF_EVENTS
-int prof_sysenter_enable(struct ftrace_event_call *call);
-void prof_sysenter_disable(struct ftrace_event_call *call);
-int prof_sysexit_enable(struct ftrace_event_call *call);
-void prof_sysexit_disable(struct ftrace_event_call *call);
+int perf_sysenter_enable(struct ftrace_event_call *call);
+void perf_sysenter_disable(struct ftrace_event_call *call);
+int perf_sysexit_enable(struct ftrace_event_call *call);
+void perf_sysexit_disable(struct ftrace_event_call *call);
 #endif
 
 #endif /* _TRACE_SYSCALL_H */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index fa034d2..0ed46f3 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -259,7 +259,8 @@ static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
 	struct kprobe_insn_page *kip;
 
 	list_for_each_entry(kip, &c->pages, list) {
-		long idx = ((long)slot - (long)kip->insns) / c->insn_size;
+		long idx = ((long)slot - (long)kip->insns) /
+				(c->insn_size * sizeof(kprobe_opcode_t));
 		if (idx >= 0 && idx < slots_per_page(c)) {
 			WARN_ON(kip->slot_used[idx] != SLOT_USED);
 			if (dirty) {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 0c30d04..65b5f5b 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3211,8 +3211,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;
 
-	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
-
 	if (unlikely(current->lockdep_recursion))
 		return;
 
@@ -3220,6 +3218,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	check_flags(flags);
 
 	current->lockdep_recursion = 1;
+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0);
 	current->lockdep_recursion = 0;
@@ -3232,14 +3231,13 @@ void lock_release(struct lockdep_map *lock, int nested,
 {
 	unsigned long flags;
 
-	trace_lock_release(lock, nested, ip);
-
 	if (unlikely(current->lockdep_recursion))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
+	trace_lock_release(lock, nested, ip);
 	__lock_release(lock, nested, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -3413,8 +3411,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	trace_lock_contended(lock, ip);
-
 	if (unlikely(!lock_stat))
 		return;
 
@@ -3424,6 +3420,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
+	trace_lock_contended(lock, ip);
 	__lock_contended(lock, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 4393b9e..fb3031c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -81,10 +81,6 @@ extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
 void __weak hw_perf_disable(void)		{ barrier(); }
 void __weak hw_perf_enable(void)		{ barrier(); }
 
-void __weak hw_perf_event_setup(int cpu)	{ barrier(); }
-void __weak hw_perf_event_setup_online(int cpu)	{ barrier(); }
-void __weak hw_perf_event_setup_offline(int cpu)	{ barrier(); }
-
 int __weak
 hw_perf_group_sched_in(struct perf_event *group_leader,
 	       struct perf_cpu_context *cpuctx,
@@ -97,25 +93,15 @@ void __weak perf_event_print_debug(void)	{ }
 
 static DEFINE_PER_CPU(int, perf_disable_count);
 
-void __perf_disable(void)
-{
-	__get_cpu_var(perf_disable_count)++;
-}
-
-bool __perf_enable(void)
-{
-	return !--__get_cpu_var(perf_disable_count);
-}
-
 void perf_disable(void)
 {
-	__perf_disable();
-	hw_perf_disable();
+	if (!__get_cpu_var(perf_disable_count)++)
+		hw_perf_disable();
 }
 
 void perf_enable(void)
 {
-	if (__perf_enable())
+	if (!--__get_cpu_var(perf_disable_count))
 		hw_perf_enable();
 }
 
@@ -1538,12 +1524,15 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 		 */
 		if (interrupts == MAX_INTERRUPTS) {
 			perf_log_throttle(event, 1);
+			perf_disable();
 			event->pmu->unthrottle(event);
+			perf_enable();
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
+		perf_disable();
 		event->pmu->read(event);
 		now = atomic64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
@@ -1551,6 +1540,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 
 		if (delta > 0)
 			perf_adjust_period(event, TICK_NSEC, delta);
+		perf_enable();
 	}
 	raw_spin_unlock(&ctx->lock);
 }
@@ -1560,9 +1550,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
  */
 static void rotate_ctx(struct perf_event_context *ctx)
 {
-	if (!ctx->nr_events)
-		return;
-
 	raw_spin_lock(&ctx->lock);
 
 	/* Rotate the first entry last of non-pinned groups */
@@ -1575,19 +1562,28 @@ void perf_event_task_tick(struct task_struct *curr)
 {
 	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
+	int rotate = 0;
 
 	if (!atomic_read(&nr_events))
 		return;
 
 	cpuctx = &__get_cpu_var(perf_cpu_context);
-	ctx = curr->perf_event_ctxp;
+	if (cpuctx->ctx.nr_events &&
+	    cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
+		rotate = 1;
 
-	perf_disable();
+	ctx = curr->perf_event_ctxp;
+	if (ctx && ctx->nr_events && ctx->nr_events != ctx->nr_active)
+		rotate = 1;
 
 	perf_ctx_adjust_freq(&cpuctx->ctx);
 	if (ctx)
 		perf_ctx_adjust_freq(ctx);
 
+	if (!rotate)
+		return;
+
+	perf_disable();
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_out(ctx, EVENT_FLEXIBLE);
@@ -1599,7 +1595,6 @@ void perf_event_task_tick(struct task_struct *curr)
 	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-
 	perf_enable();
 }
 
@@ -2791,6 +2786,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
+__weak
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
+{
+}
+
 /*
  * Output
  */
@@ -4318,9 +4318,8 @@ static const struct pmu perf_ops_task_clock = {
 #ifdef CONFIG_EVENT_TRACING
 
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
-			  int entry_size)
+		   int entry_size, struct pt_regs *regs)
 {
-	struct pt_regs *regs = get_irq_regs();
 	struct perf_sample_data data;
 	struct perf_raw_record raw = {
 		.size = entry_size,
@@ -4330,12 +4329,9 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
 	perf_sample_data_init(&data, addr);
 	data.raw = &raw;
 
-	if (!regs)
-		regs = task_pt_regs(current);
-
 	/* Trace events already protected against recursion */
 	do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
-				&data, regs);
+			 &data, regs);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
@@ -4351,7 +4347,7 @@ static int perf_tp_event_match(struct perf_event *event,
 
 static void tp_perf_event_destroy(struct perf_event *event)
 {
-	ftrace_profile_disable(event->attr.config);
+	perf_trace_disable(event->attr.config);
 }
 
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
@@ -4365,7 +4361,7 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
 			!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	if (ftrace_profile_enable(event->attr.config))
+	if (perf_trace_enable(event->attr.config))
 		return NULL;
 
 	event->destroy = tp_perf_event_destroy;
@@ -5372,18 +5368,26 @@ int perf_event_init_task(struct task_struct *child)
 	return ret;
 }
 
+static void __init perf_event_init_all_cpus(void)
+{
+	int cpu;
+	struct perf_cpu_context *cpuctx;
+
+	for_each_possible_cpu(cpu) {
+		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		__perf_event_init_context(&cpuctx->ctx, NULL);
+	}
+}
+
 static void __cpuinit perf_event_init_cpu(int cpu)
 {
 	struct perf_cpu_context *cpuctx;
 
 	cpuctx = &per_cpu(perf_cpu_context, cpu);
-	__perf_event_init_context(&cpuctx->ctx, NULL);
 
 	spin_lock(&perf_resource_lock);
 	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
 	spin_unlock(&perf_resource_lock);
-
-	hw_perf_event_setup(cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -5423,20 +5427,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 		perf_event_init_cpu(cpu);
 		break;
 
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		hw_perf_event_setup_online(cpu);
-		break;
-
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		perf_event_exit_cpu(cpu);
 		break;
 
-	case CPU_DEAD:
-		hw_perf_event_setup_offline(cpu);
-		break;
-
 	default:
 		break;
 	}
@@ -5454,6 +5449,7 @@ static struct notifier_block __cpuinitdata perf_cpu_nb = {
 
 void __init perf_event_init(void)
 {
+	perf_event_init_all_cpus();
 	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
 			(void *)(long)smp_processor_id());
 	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d00c6fe..78edc64 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events.o
 obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 ifeq ($(CONFIG_PERF_EVENTS),y)
-obj-$(CONFIG_EVENT_TRACING) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_perf.c
similarity index 69%
rename from kernel/trace/trace_event_profile.c
rename to kernel/trace/trace_event_perf.c
index f0d6930..0709e4f 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,32 +1,34 @@
 /*
- * trace event based perf counter profiling
+ * trace event based perf event profiling/tracing
  *
  * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include "trace.h"
 
+DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
+EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
 
 static char *perf_trace_buf;
 static char *perf_trace_buf_nmi;
 
-typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
+typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
 
 /* Count the events in use (per event id, not per instance) */
-static int	total_profile_count;
+static int	total_ref_count;
 
-static int ftrace_profile_enable_event(struct ftrace_event_call *event)
+static int perf_trace_event_enable(struct ftrace_event_call *event)
 {
 	char *buf;
 	int ret = -ENOMEM;
 
-	if (event->profile_count++ > 0)
+	if (event->perf_refcount++ > 0)
 		return 0;
 
-	if (!total_profile_count) {
+	if (!total_ref_count) {
 		buf = (char *)alloc_percpu(perf_trace_t);
 		if (!buf)
 			goto fail_buf;
@@ -40,35 +42,35 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 		rcu_assign_pointer(perf_trace_buf_nmi, buf);
 	}
 
-	ret = event->profile_enable(event);
+	ret = event->perf_event_enable(event);
 	if (!ret) {
-		total_profile_count++;
+		total_ref_count++;
 		return 0;
 	}
 
 fail_buf_nmi:
-	if (!total_profile_count) {
+	if (!total_ref_count) {
 		free_percpu(perf_trace_buf_nmi);
 		free_percpu(perf_trace_buf);
 		perf_trace_buf_nmi = NULL;
 		perf_trace_buf = NULL;
 	}
 fail_buf:
-	event->profile_count--;
+	event->perf_refcount--;
 
 	return ret;
 }
 
-int ftrace_profile_enable(int event_id)
+int perf_trace_enable(int event_id)
 {
 	struct ftrace_event_call *event;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id && event->profile_enable &&
+		if (event->id == event_id && event->perf_event_enable &&
 		    try_module_get(event->mod)) {
-			ret = ftrace_profile_enable_event(event);
+			ret = perf_trace_event_enable(event);
 			break;
 		}
 	}
@@ -77,16 +79,16 @@ int ftrace_profile_enable(int event_id)
 	return ret;
 }
 
-static void ftrace_profile_disable_event(struct ftrace_event_call *event)
+static void perf_trace_event_disable(struct ftrace_event_call *event)
 {
 	char *buf, *nmi_buf;
 
-	if (--event->profile_count > 0)
+	if (--event->perf_refcount > 0)
 		return;
 
-	event->profile_disable(event);
+	event->perf_event_disable(event);
 
-	if (!--total_profile_count) {
+	if (!--total_ref_count) {
 		buf = perf_trace_buf;
 		rcu_assign_pointer(perf_trace_buf, NULL);
 
@@ -104,14 +106,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
 	}
 }
 
-void ftrace_profile_disable(int event_id)
+void perf_trace_disable(int event_id)
 {
 	struct ftrace_event_call *event;
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
 		if (event->id == event_id) {
-			ftrace_profile_disable_event(event);
+			perf_trace_event_disable(event);
 			module_put(event->mod);
 			break;
 		}
@@ -119,8 +121,8 @@ void ftrace_profile_disable(int event_id)
 	mutex_unlock(&event_mutex);
 }
 
-__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
-					int *rctxp, unsigned long *irq_flags)
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+				       int *rctxp, unsigned long *irq_flags)
 {
 	struct trace_entry *entry;
 	char *trace_buf, *raw_data;
@@ -161,4 +163,4 @@ err_recursion:
 	local_irq_restore(*irq_flags);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare);
+EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3f972ad..beab8bf 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -938,7 +938,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		trace_create_file("enable", 0644, call->dir, call,
 				  enable);
 
-	if (call->id && call->profile_enable)
+	if (call->id && call->perf_event_enable)
 		trace_create_file("id", 0444, call->dir, call,
 		 		  id);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 505c922..1251e36 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1214,7 +1214,7 @@ static int set_print_fmt(struct trace_probe *tp)
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
-static __kprobes void kprobe_profile_func(struct kprobe *kp,
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
 					 struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
@@ -1227,11 +1227,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
 	__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
 		     "profile buffer not large enough"))
 		return;
 
-	entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+	entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
 	if (!entry)
 		return;
 
@@ -1240,11 +1240,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
 	for (i = 0; i < tp->nr_args; i++)
 		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
 
-	ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags);
+	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
 }
 
 /* Kretprobe profile handler */
-static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 					    struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
@@ -1257,11 +1257,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
 	__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
 		     "profile buffer not large enough"))
 		return;
 
-	entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+	entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
 	if (!entry)
 		return;
 
@@ -1271,10 +1271,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
 	for (i = 0; i < tp->nr_args; i++)
 		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
 
-	ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags);
+	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
+			       irq_flags, regs);
 }
 
-static int probe_profile_enable(struct ftrace_event_call *call)
+static int probe_perf_enable(struct ftrace_event_call *call)
 {
 	struct trace_probe *tp = (struct trace_probe *)call->data;
 
@@ -1286,7 +1287,7 @@ static int probe_profile_enable(struct ftrace_event_call *call)
 		return enable_kprobe(&tp->rp.kp);
 }
 
-static void probe_profile_disable(struct ftrace_event_call *call)
+static void probe_perf_disable(struct ftrace_event_call *call)
 {
 	struct trace_probe *tp = (struct trace_probe *)call->data;
 
@@ -1311,7 +1312,7 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 		kprobe_trace_func(kp, regs);
 #ifdef CONFIG_PERF_EVENTS
 	if (tp->flags & TP_FLAG_PROFILE)
-		kprobe_profile_func(kp, regs);
+		kprobe_perf_func(kp, regs);
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
@@ -1325,7 +1326,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 		kretprobe_trace_func(ri, regs);
 #ifdef CONFIG_PERF_EVENTS
 	if (tp->flags & TP_FLAG_PROFILE)
-		kretprobe_profile_func(ri, regs);
+		kretprobe_perf_func(ri, regs);
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
@@ -1358,8 +1359,8 @@ static int register_probe_event(struct trace_probe *tp)
 	call->unregfunc = probe_event_disable;
 
 #ifdef CONFIG_PERF_EVENTS
-	call->profile_enable = probe_profile_enable;
-	call->profile_disable = probe_profile_disable;
+	call->perf_event_enable = probe_perf_enable;
+	call->perf_event_disable = probe_perf_disable;
 #endif
 	call->data = tp;
 	ret = trace_add_event_call(call);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index cba47d7..33c2a5b 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -428,12 +428,12 @@ core_initcall(init_ftrace_syscalls);
 
 #ifdef CONFIG_PERF_EVENTS
 
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
 
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(struct pt_regs *regs, long id)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
@@ -443,7 +443,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
-	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -455,11 +455,11 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-		      "profile buffer not large enough"))
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+		      "perf buffer not large enough"))
 		return;
 
-	rec = (struct syscall_trace_enter *)ftrace_perf_buf_prepare(size,
+	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
 				sys_data->enter_event->id, &rctx, &flags);
 	if (!rec)
 		return;
@@ -467,10 +467,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
-	ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+	perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int prof_sysenter_enable(struct ftrace_event_call *call)
+int perf_sysenter_enable(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -478,34 +478,34 @@ int prof_sysenter_enable(struct ftrace_event_call *call)
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_prof_refcount_enter)
-		ret = register_trace_sys_enter(prof_syscall_enter);
+	if (!sys_perf_refcount_enter)
+		ret = register_trace_sys_enter(perf_syscall_enter);
 	if (ret) {
 		pr_info("event trace: Could not activate"
 				"syscall entry trace point");
 	} else {
-		set_bit(num, enabled_prof_enter_syscalls);
-		sys_prof_refcount_enter++;
+		set_bit(num, enabled_perf_enter_syscalls);
+		sys_perf_refcount_enter++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-void prof_sysenter_disable(struct ftrace_event_call *call)
+void perf_sysenter_disable(struct ftrace_event_call *call)
 {
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	sys_prof_refcount_enter--;
-	clear_bit(num, enabled_prof_enter_syscalls);
-	if (!sys_prof_refcount_enter)
-		unregister_trace_sys_enter(prof_syscall_enter);
+	sys_perf_refcount_enter--;
+	clear_bit(num, enabled_perf_enter_syscalls);
+	if (!sys_perf_refcount_enter)
+		unregister_trace_sys_enter(perf_syscall_enter);
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(struct pt_regs *regs, long ret)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
@@ -515,7 +515,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
-	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -530,11 +530,11 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	 * Impossible, but be paranoid with the future
 	 * How to put this check outside runtime?
 	 */
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-		"exit event has grown above profile buffer size"))
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+		"exit event has grown above perf buffer size"))
 		return;
 
-	rec = (struct syscall_trace_exit *)ftrace_perf_buf_prepare(size,
+	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
 				sys_data->exit_event->id, &rctx, &flags);
 	if (!rec)
 		return;
@@ -542,10 +542,10 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+	perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int prof_sysexit_enable(struct ftrace_event_call *call)
+int perf_sysexit_enable(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -553,30 +553,30 @@ int prof_sysexit_enable(struct ftrace_event_call *call)
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_prof_refcount_exit)
-		ret = register_trace_sys_exit(prof_syscall_exit);
+	if (!sys_perf_refcount_exit)
+		ret = register_trace_sys_exit(perf_syscall_exit);
 	if (ret) {
 		pr_info("event trace: Could not activate"
 				"syscall exit trace point");
 	} else {
-		set_bit(num, enabled_prof_exit_syscalls);
-		sys_prof_refcount_exit++;
+		set_bit(num, enabled_perf_exit_syscalls);
+		sys_perf_refcount_exit++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-void prof_sysexit_disable(struct ftrace_event_call *call)
+void perf_sysexit_disable(struct ftrace_event_call *call)
 {
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	sys_prof_refcount_exit--;
-	clear_bit(num, enabled_prof_exit_syscalls);
-	if (!sys_prof_refcount_exit)
-		unregister_trace_sys_exit(prof_syscall_exit);
+	sys_perf_refcount_exit--;
+	clear_bit(num, enabled_perf_exit_syscalls);
+	if (!sys_perf_refcount_exit)
+		unregister_trace_sys_exit(perf_syscall_exit);
 	mutex_unlock(&syscall_trace_lock);
 }
 
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index bdd3b7e..bd498d4 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -24,7 +24,10 @@ DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
 DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
 DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
 
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
 prefix?=$(HOME)
+endif
 bindir?=$(prefix)/bin
 htmldir?=$(prefix)/share/doc/perf-doc
 pdfdir?=$(prefix)/share/doc/perf-doc
@@ -32,7 +35,6 @@ mandir?=$(prefix)/share/man
 man1dir=$(mandir)/man1
 man5dir=$(mandir)/man5
 man7dir=$(mandir)/man7
-# DESTDIR=
 
 ASCIIDOC=asciidoc
 ASCIIDOC_EXTRA = --unsafe
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 2d53738..8a8f52d 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -216,7 +216,10 @@ STRIP ?= strip
 # runtime figures out where they are based on the path to the executable.
 # This can help installing the suite in a relocatable way.
 
+# Make the path relative to DESTDIR, not to prefix
+ifndef DESTDIR
 prefix = $(HOME)
+endif
 bindir_relative = bin
 bindir = $(prefix)/$(bindir_relative)
 mandir = share/man
@@ -233,7 +236,6 @@ sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
 lib = lib
-# DESTDIR=
 
 export prefix bindir sharedir sysconfdir
 
@@ -387,6 +389,7 @@ LIB_H += util/thread.h
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
+LIB_H += util/cpumap.h
 
 LIB_OBJS += util/abspath.o
 LIB_OBJS += util/alias.o
@@ -433,6 +436,7 @@ LIB_OBJS += util/sort.o
 LIB_OBJS += util/hist.o
 LIB_OBJS += util/probe-event.o
 LIB_OBJS += util/util.o
+LIB_OBJS += util/cpumap.o
 
 BUILTIN_OBJS += builtin-annotate.o
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5ec5de9..6ad7148 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -116,7 +116,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 		return 0;
 	}
 
-	he = __perf_session__add_hist_entry(self, al, NULL, count, &hit);
+	he = __perf_session__add_hist_entry(&self->hists, al, NULL, count, &hit);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -564,8 +564,8 @@ static int __cmd_annotate(void)
 	if (verbose > 2)
 		dsos__fprintf(stdout);
 
-	perf_session__collapse_resort(session);
-	perf_session__output_resort(session, session->event_total[0]);
+	perf_session__collapse_resort(&session->hists);
+	perf_session__output_resort(&session->hists, session->event_total[0]);
 	perf_session__find_annotations(session);
 out_delete:
 	perf_session__delete(session);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 18b3f50..1ea15d8 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -26,7 +26,8 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 					struct addr_location *al, u64 count)
 {
 	bool hit;
-	struct hist_entry *he = __perf_session__add_hist_entry(self, al, NULL,
+	struct hist_entry *he = __perf_session__add_hist_entry(&self->hists,
+							       al, NULL,
 							       count, &hit);
 	if (he == NULL)
 		return -ENOMEM;
@@ -114,7 +115,7 @@ static void perf_session__resort_hist_entries(struct perf_session *self)
 
 static void perf_session__set_hist_entries_positions(struct perf_session *self)
 {
-	perf_session__output_resort(self, self->events_stats.total);
+	perf_session__output_resort(&self->hists, self->events_stats.total);
 	perf_session__resort_hist_entries(self);
 }
 
@@ -166,13 +167,15 @@ static int __cmd_diff(void)
 			goto out_delete;
 	}
 
-	perf_session__output_resort(session[1], session[1]->events_stats.total);
+	perf_session__output_resort(&session[1]->hists,
+				    session[1]->events_stats.total);
 	if (show_displacement)
 		perf_session__set_hist_entries_positions(session[0]);
 
 	perf_session__match_hists(session[0], session[1]);
-	perf_session__fprintf_hists(session[1], session[0],
-				    show_displacement, stdout);
+	perf_session__fprintf_hists(&session[1]->hists, session[0],
+				    show_displacement, stdout,
+				    session[1]->events_stats.total);
 out_delete:
 	for (i = 0; i < 2; ++i)
 		perf_session__delete(session[i]);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 771533c..3b8b638 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -22,6 +22,7 @@
 #include "util/debug.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/cpumap.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -244,6 +245,9 @@ static void create_counter(int counter, int cpu, pid_t pid)
 
 	attr->sample_type	|= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
+	if (nr_counters > 1)
+		attr->sample_type |= PERF_SAMPLE_ID;
+
 	if (freq) {
 		attr->sample_type	|= PERF_SAMPLE_PERIOD;
 		attr->freq		= 1;
@@ -391,6 +395,9 @@ static int process_buildids(void)
 {
 	u64 size = lseek(output, 0, SEEK_CUR);
 
+	if (size == 0)
+		return 0;
+
 	session->fd = output;
 	return __perf_session__process_events(session, post_processing_offset,
 					      size - post_processing_offset,
@@ -418,9 +425,6 @@ static int __cmd_record(int argc, const char **argv)
 	char buf;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
-	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	assert(nr_cpus <= MAX_NR_CPUS);
-	assert(nr_cpus >= 0);
 
 	atexit(sig_atexit);
 	signal(SIGCHLD, sig_handler);
@@ -544,8 +548,9 @@ static int __cmd_record(int argc, const char **argv)
 	if ((!system_wide && !inherit) || profile_cpu != -1) {
 		open_counters(profile_cpu, target_pid);
 	} else {
+		nr_cpus = read_cpu_map();
 		for (i = 0; i < nr_cpus; i++)
-			open_counters(i, target_pid);
+			open_counters(cpumap[i], target_pid);
 	}
 
 	if (file_new) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cfc655d..f815de2 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -45,28 +45,71 @@ static char		*pretty_printing_style = default_pretty_printing_style;
 
 static char		callchain_default_opt[] = "fractal,0.5";
 
+static struct event_stat_id *get_stats(struct perf_session *self,
+				       u64 event_stream, u32 type, u64 config)
+{
+	struct rb_node **p = &self->stats_by_id.rb_node;
+	struct rb_node *parent = NULL;
+	struct event_stat_id *iter, *new;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct event_stat_id, rb_node);
+		if (iter->config == config)
+			return iter;
+
+
+		if (config > iter->config)
+			p = &(*p)->rb_right;
+		else
+			p = &(*p)->rb_left;
+	}
+
+	new = malloc(sizeof(struct event_stat_id));
+	if (new == NULL)
+		return NULL;
+	memset(new, 0, sizeof(struct event_stat_id));
+	new->event_stream = event_stream;
+	new->config = config;
+	new->type = type;
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, &self->stats_by_id);
+	return new;
+}
+
 static int perf_session__add_hist_entry(struct perf_session *self,
 					struct addr_location *al,
-					struct ip_callchain *chain, u64 count)
+					struct sample_data *data)
 {
 	struct symbol **syms = NULL, *parent = NULL;
 	bool hit;
 	struct hist_entry *he;
+	struct event_stat_id *stats;
+	struct perf_event_attr *attr;
 
-	if ((sort__has_parent || symbol_conf.use_callchain) && chain)
+	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain)
 		syms = perf_session__resolve_callchain(self, al->thread,
-						       chain, &parent);
-	he = __perf_session__add_hist_entry(self, al, parent, count, &hit);
+						       data->callchain, &parent);
+
+	attr = perf_header__find_attr(data->id, &self->header);
+	if (attr)
+		stats = get_stats(self, data->id, attr->type, attr->config);
+	else
+		stats = get_stats(self, data->id, 0, 0);
+	if (stats == NULL)
+		return -ENOMEM;
+	he = __perf_session__add_hist_entry(&stats->hists, al, parent,
+					    data->period, &hit);
 	if (he == NULL)
 		return -ENOMEM;
 
 	if (hit)
-		he->count += count;
+		he->count += data->period;
 
 	if (symbol_conf.use_callchain) {
 		if (!hit)
 			callchain_init(&he->callchain);
-		append_chain(&he->callchain, chain, syms);
+		append_chain(&he->callchain, data->callchain, syms);
 		free(syms);
 	}
 
@@ -86,10 +129,30 @@ static int validate_chain(struct ip_callchain *chain, event_t *event)
 	return 0;
 }
 
+static int add_event_total(struct perf_session *session,
+			   struct sample_data *data,
+			   struct perf_event_attr *attr)
+{
+	struct event_stat_id *stats;
+
+	if (attr)
+		stats = get_stats(session, data->id, attr->type, attr->config);
+	else
+		stats = get_stats(session, data->id, 0, 0);
+
+	if (!stats)
+		return -ENOMEM;
+
+	stats->stats.total += data->period;
+	session->events_stats.total += data->period;
+	return 0;
+}
+
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
 	struct sample_data data = { .period = 1, };
 	struct addr_location al;
+	struct perf_event_attr *attr;
 
 	event__parse_sample(event, session->sample_type, &data);
 
@@ -123,12 +186,18 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
-	if (perf_session__add_hist_entry(session, &al, data.callchain, data.period)) {
+	if (perf_session__add_hist_entry(session, &al, &data)) {
 		pr_debug("problem incrementing symbol count, skipping event\n");
 		return -1;
 	}
 
-	session->events_stats.total += data.period;
+	attr = perf_header__find_attr(data.id, &session->header);
+
+	if (add_event_total(session, &data, attr)) {
+		pr_debug("problem adding event count\n");
+		return -1;
+	}
+
 	return 0;
 }
 
@@ -197,6 +266,7 @@ static int __cmd_report(void)
 {
 	int ret = -EINVAL;
 	struct perf_session *session;
+	struct rb_node *next;
 
 	session = perf_session__new(input_name, O_RDONLY, force);
 	if (session == NULL)
@@ -224,10 +294,28 @@ static int __cmd_report(void)
 	if (verbose > 2)
 		dsos__fprintf(stdout);
 
-	perf_session__collapse_resort(session);
-	perf_session__output_resort(session, session->events_stats.total);
-	fprintf(stdout, "# Samples: %Ld\n#\n", session->events_stats.total);
-	perf_session__fprintf_hists(session, NULL, false, stdout);
+	next = rb_first(&session->stats_by_id);
+	while (next) {
+		struct event_stat_id *stats;
+
+		stats = rb_entry(next, struct event_stat_id, rb_node);
+		perf_session__collapse_resort(&stats->hists);
+		perf_session__output_resort(&stats->hists, stats->stats.total);
+		if (rb_first(&session->stats_by_id) ==
+		    rb_last(&session->stats_by_id))
+			fprintf(stdout, "# Samples: %Ld\n#\n",
+				stats->stats.total);
+		else
+			fprintf(stdout, "# Samples: %Ld %s\n#\n",
+				stats->stats.total,
+				__event_name(stats->type, stats->config));
+
+		perf_session__fprintf_hists(&stats->hists, NULL, false, stdout,
+					    stats->stats.total);
+		fprintf(stdout, "\n\n");
+		next = rb_next(&stats->rb_node);
+	}
+
 	if (sort_order == default_sort_order &&
 	    parent_pattern == default_parent_pattern)
 		fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n");
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e8c85d5..95db31c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -45,6 +45,7 @@
 #include "util/event.h"
 #include "util/debug.h"
 #include "util/header.h"
+#include "util/cpumap.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -151,7 +152,7 @@ static void create_perf_stat_counter(int counter, int pid)
 		unsigned int cpu;
 
 		for (cpu = 0; cpu < nr_cpus; cpu++) {
-			fd[cpu][counter] = sys_perf_event_open(attr, -1, cpu, -1, 0);
+			fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
 			if (fd[cpu][counter] < 0 && verbose)
 				fprintf(stderr, ERR_PERF_OPEN, counter,
 					fd[cpu][counter], strerror(errno));
@@ -519,9 +520,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		nr_counters = ARRAY_SIZE(default_attrs);
 	}
 
-	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	assert(nr_cpus <= MAX_NR_CPUS);
-	assert((int)nr_cpus >= 0);
+	if (system_wide)
+		nr_cpus = read_cpu_map();
+	else
+		nr_cpus = 1;
 
 	/*
 	 * We dont want to block the signals - that would cause
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 31f2e59..0b719e3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -28,6 +28,7 @@
 #include <linux/rbtree.h>
 #include "util/parse-options.h"
 #include "util/parse-events.h"
+#include "util/cpumap.h"
 
 #include "util/debug.h"
 
@@ -1123,7 +1124,7 @@ static void start_counter(int i, int counter)
 
 	cpu = profile_cpu;
 	if (target_pid == -1 && profile_cpu == -1)
-		cpu = i;
+		cpu = cpumap[i];
 
 	attr = attrs + counter;
 
@@ -1347,12 +1348,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		attrs[counter].sample_period = default_interval;
 	}
 
-	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	assert(nr_cpus <= MAX_NR_CPUS);
-	assert(nr_cpus >= 0);
-
 	if (target_pid != -1 || profile_cpu != -1)
 		nr_cpus = 1;
+	else
+		nr_cpus = read_cpu_map();
 
 	get_term_dimensions(&winsize);
 	if (print_entries == 0) {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
new file mode 100644
index 0000000..4e01490
--- /dev/null
+++ b/tools/perf/util/cpumap.c
@@ -0,0 +1,59 @@
+#include "util.h"
+#include "../perf.h"
+#include "cpumap.h"
+#include <assert.h>
+#include <stdio.h>
+
+int cpumap[MAX_NR_CPUS];
+
+static int default_cpu_map(void)
+{
+	int nr_cpus, i;
+
+	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	assert(nr_cpus <= MAX_NR_CPUS);
+	assert((int)nr_cpus >= 0);
+
+	for (i = 0; i < nr_cpus; ++i)
+		cpumap[i] = i;
+
+	return nr_cpus;
+}
+
+int read_cpu_map(void)
+{
+	FILE *onlnf;
+	int nr_cpus = 0;
+	int n, cpu, prev;
+	char sep;
+
+	onlnf = fopen("/sys/devices/system/cpu/online", "r");
+	if (!onlnf)
+		return default_cpu_map();
+
+	sep = 0;
+	prev = -1;
+	for (;;) {
+		n = fscanf(onlnf, "%u%c", &cpu, &sep);
+		if (n <= 0)
+			break;
+		if (prev >= 0) {
+			assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+			while (++prev < cpu)
+				cpumap[nr_cpus++] = prev;
+		}
+		assert (nr_cpus < MAX_NR_CPUS);
+		cpumap[nr_cpus++] = cpu;
+		if (n == 2 && sep == '-')
+			prev = cpu;
+		else
+			prev = -1;
+		if (n == 1 || sep == '\n')
+			break;
+	}
+	fclose(onlnf);
+	if (nr_cpus > 0)
+		return nr_cpus;
+
+	return default_cpu_map();
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
new file mode 100644
index 0000000..86c78bb
--- /dev/null
+++ b/tools/perf/util/cpumap.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_CPUMAP_H
+#define __PERF_CPUMAP_H
+
+extern int read_cpu_map(void);
+extern int cpumap[];
+
+#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 50a7132..a33b949 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -99,6 +99,15 @@ struct events_stats {
 	u64 lost;
 };
 
+struct event_stat_id {
+	struct rb_node		rb_node;
+	struct rb_root		hists;
+	struct events_stats	stats;
+	u64			config;
+	u64			event_stream;
+	u32			type;
+};
+
 void event__print_totals(void);
 
 struct perf_session;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e8daf5c..bdcfd61 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -12,12 +12,12 @@ struct callchain_param	callchain_param = {
  * histogram, sorted on item, collects counts
  */
 
-struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
+struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 						  struct addr_location *al,
 						  struct symbol *sym_parent,
 						  u64 count, bool *hit)
 {
-	struct rb_node **p = &self->hists.rb_node;
+	struct rb_node **p = &hists->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	struct hist_entry entry = {
@@ -53,7 +53,7 @@ struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
 		return NULL;
 	*he = entry;
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, &self->hists);
+	rb_insert_color(&he->rb_node, hists);
 	*hit = false;
 	return he;
 }
@@ -130,7 +130,7 @@ static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 	rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__collapse_resort(struct perf_session *self)
+void perf_session__collapse_resort(struct rb_root *hists)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
@@ -140,17 +140,17 @@ void perf_session__collapse_resort(struct perf_session *self)
 		return;
 
 	tmp = RB_ROOT;
-	next = rb_first(&self->hists);
+	next = rb_first(hists);
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, &self->hists);
+		rb_erase(&n->rb_node, hists);
 		collapse__insert_entry(&tmp, n);
 	}
 
-	self->hists = tmp;
+	*hists = tmp;
 }
 
 /*
@@ -183,7 +183,7 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root,
 	rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__output_resort(struct perf_session *self, u64 total_samples)
+void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
@@ -194,18 +194,18 @@ void perf_session__output_resort(struct perf_session *self, u64 total_samples)
 		total_samples * (callchain_param.min_percent / 100);
 
 	tmp = RB_ROOT;
-	next = rb_first(&self->hists);
+	next = rb_first(hists);
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, &self->hists);
+		rb_erase(&n->rb_node, hists);
 		perf_session__insert_output_hist_entry(&tmp, n,
 						       min_callchain_hits);
 	}
 
-	self->hists = tmp;
+	*hists = tmp;
 }
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -456,10 +456,10 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 }
 
 static size_t hist_entry__fprintf(struct hist_entry *self,
-				  struct perf_session *session,
 				  struct perf_session *pair_session,
 				  bool show_displacement,
-				  long displacement, FILE *fp)
+				  long displacement, FILE *fp,
+				  u64 session_total)
 {
 	struct sort_entry *se;
 	u64 count, total;
@@ -474,7 +474,7 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 		total = pair_session->events_stats.total;
 	} else {
 		count = self->count;
-		total = session->events_stats.total;
+		total = session_total;
 	}
 
 	if (total)
@@ -496,8 +496,8 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 
 		if (total > 0)
 			old_percent = (count * 100.0) / total;
-		if (session->events_stats.total > 0)
-			new_percent = (self->count * 100.0) / session->events_stats.total;
+		if (session_total > 0)
+			new_percent = (self->count * 100.0) / session_total;
 
 		diff = new_percent - old_percent;
 
@@ -544,16 +544,17 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 			left_margin -= thread__comm_len(self->thread);
 		}
 
-		hist_entry_callchain__fprintf(fp, self, session->events_stats.total,
+		hist_entry_callchain__fprintf(fp, self, session_total,
 					      left_margin);
 	}
 
 	return ret;
 }
 
-size_t perf_session__fprintf_hists(struct perf_session *self,
+size_t perf_session__fprintf_hists(struct rb_root *hists,
 				   struct perf_session *pair,
-				   bool show_displacement, FILE *fp)
+				   bool show_displacement, FILE *fp,
+				   u64 session_total)
 {
 	struct sort_entry *se;
 	struct rb_node *nd;
@@ -641,7 +642,7 @@ size_t perf_session__fprintf_hists(struct perf_session *self,
 	fprintf(fp, "\n#\n");
 
 print_entries:
-	for (nd = rb_first(&self->hists); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (show_displacement) {
@@ -652,8 +653,13 @@ print_entries:
 				displacement = 0;
 			++position;
 		}
-		ret += hist_entry__fprintf(h, self, pair, show_displacement,
-					   displacement, fp);
+		ret += hist_entry__fprintf(h, pair, show_displacement,
+					   displacement, fp, session_total);
+		if (h->map == NULL && verbose > 1) {
+			__map_groups__fprintf_maps(&h->thread->mg,
+						   MAP__FUNCTION, fp);
+			fprintf(fp, "%.10s end\n", graph_dotted_line);
+		}
 	}
 
 	free(rem_sq_bracket);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index e5f99b2..16f360c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -10,8 +10,9 @@ struct perf_session;
 struct hist_entry;
 struct addr_location;
 struct symbol;
+struct rb_root;
 
-struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
+struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 						  struct addr_location *al,
 						  struct symbol *parent,
 						  u64 count, bool *hit);
@@ -19,9 +20,10 @@ extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
 void hist_entry__free(struct hist_entry *);
 
-void perf_session__output_resort(struct perf_session *self, u64 total_samples);
-void perf_session__collapse_resort(struct perf_session *self);
-size_t perf_session__fprintf_hists(struct perf_session *self,
+void perf_session__output_resort(struct rb_root *hists, u64 total_samples);
+void perf_session__collapse_resort(struct rb_root *hists);
+size_t perf_session__fprintf_hists(struct rb_root *hists,
 				   struct perf_session *pair,
-				   bool show_displacement, FILE *fp);
+				   bool show_displacement, FILE *fp,
+				   u64 session_total);
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index e77dc88..1e6c65e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -169,7 +169,7 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 {
 	Dwarf_Files *files;
 	size_t nfiles, i;
-	const char *src;
+	const char *src = NULL;
 	int ret;
 
 	if (!fname)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0de7258..eed1cb8 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -70,6 +70,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 
 	memcpy(self->filename, filename, len);
 	self->threads = RB_ROOT;
+	self->stats_by_id = RB_ROOT;
 	self->last_match = NULL;
 	self->mmap_window = 32;
 	self->cwd = NULL;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 31950fc..5c33417 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -20,6 +20,7 @@ struct perf_session {
 	struct thread		*last_match;
 	struct map		*vmlinux_maps[MAP__NR_TYPES];
 	struct events_stats	events_stats;
+	struct rb_root		stats_by_id;
 	unsigned long		event_total[PERF_RECORD_MAX];
 	unsigned long		unknown_events;
 	struct rb_root		hists;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 21b9216..fa96831 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -79,8 +79,8 @@ int thread__comm_len(struct thread *self)
 	return self->comm_len;
 }
 
-static size_t __map_groups__fprintf_maps(struct map_groups *self,
-					 enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, FILE *fp)
 {
 	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
 	struct rb_node *nd;
@@ -89,7 +89,7 @@ static size_t __map_groups__fprintf_maps(struct map_groups *self,
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
+		if (verbose > 2) {
 			printed += dso__fprintf(pos->dso, type, fp);
 			printed += fprintf(fp, "--\n");
 		}
@@ -183,8 +183,8 @@ struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
 	return th;
 }
 
-static void map_groups__remove_overlappings(struct map_groups *self,
-					    struct map *map)
+static int map_groups__fixup_overlappings(struct map_groups *self,
+					  struct map *map)
 {
 	struct rb_root *root = &self->maps[map->type];
 	struct rb_node *next = rb_first(root);
@@ -209,7 +209,36 @@ static void map_groups__remove_overlappings(struct map_groups *self,
 		 * list.
 		 */
 		list_add_tail(&pos->node, &self->removed_maps[map->type]);
+		/*
+		 * Now check if we need to create new maps for areas not
+		 * overlapped by the new map:
+		 */
+		if (map->start > pos->start) {
+			struct map *before = map__clone(pos);
+
+			if (before == NULL)
+				return -ENOMEM;
+
+			before->end = map->start - 1;
+			map_groups__insert(self, before);
+			if (verbose >= 2)
+				map__fprintf(before, stderr);
+		}
+
+		if (map->end < pos->end) {
+			struct map *after = map__clone(pos);
+
+			if (after == NULL)
+				return -ENOMEM;
+
+			after->start = map->end + 1;
+			map_groups__insert(self, after);
+			if (verbose >= 2)
+				map__fprintf(after, stderr);
+		}
 	}
+
+	return 0;
 }
 
 void maps__insert(struct rb_root *maps, struct map *map)
@@ -254,7 +283,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 
 void thread__insert_map(struct thread *self, struct map *map)
 {
-	map_groups__remove_overlappings(&self->mg, map);
+	map_groups__fixup_overlappings(&self->mg, map);
 	map_groups__insert(&self->mg, map);
 }
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 0a28f39..dcf7030 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -10,6 +10,9 @@ struct map_groups {
 	struct list_head	removed_maps[MAP__NR_TYPES];
 };
 
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, FILE *fp);
+
 struct thread {
 	struct rb_node		rb_node;
 	struct map_groups	mg;

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-03-11 19:12 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-03-11 19:12 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Arnaldo Carvalho de Melo,
	Paul Mackerras, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf archive: Don't try to collect files without a build-id

Frederic Weisbecker (5):
      perf lock: Drop the buffers multiplexing dependency
      perf: Remove pointless breakpoint union
      x86/hw-breakpoints: Remove the name field
      hw-breakpoints: Remove stub unthrottle callback
      x86/stacktrace: Don't dereference bad frame pointers

Hitoshi Mitake (1):
      perf lock: Fix and add misc documentally things

Ingo Molnar (1):
      MAINTAINERS: Add Arnaldo as tools/perf/ co-maintainer

Peter Zijlstra (3):
      perf, x86: Restrict the ANY flag
      perf_events, x86: Fixup fixed counter constraints
      perf: Provide generic perf_sample_data initialization

Robert Richter (3):
      perf, x86: make IBS macros available in perf_event.h
      perf, x86: add some IBS macros to perf_event.h
      perf, x86: rename macro in ARCH_PERFMON_EVENTSEL_ENABLE

Tejun Heo (1):
      percpu: Add __percpu sparse annotations to hw_breakpoint

Tom Zanussi (2):
      perf trace/scripting: Remove extraneous header read
      perf trace: Don't use pager if scripting

Will Deacon (1):
      perf, ARM: Modify kuser rmb() call to compile for Thumb-2


 MAINTAINERS                             |    1 +
 arch/arm/kernel/perf_event.c            |    4 +-
 arch/powerpc/kernel/perf_event.c        |    8 +-
 arch/sparc/kernel/perf_event.c          |    2 +-
 arch/x86/include/asm/hw_breakpoint.h    |    1 -
 arch/x86/include/asm/perf_event.h       |   16 +++-
 arch/x86/kernel/cpu/perf_event.c        |   39 ++++++---
 arch/x86/kernel/cpu/perf_event_intel.c  |   37 +++++---
 arch/x86/kernel/cpu/perf_event_p6.c     |    8 +-
 arch/x86/kernel/cpu/perfctr-watchdog.c  |    2 +-
 arch/x86/kernel/dumpstack_64.c          |   10 ++-
 arch/x86/kernel/hw_breakpoint.c         |   12 ---
 arch/x86/oprofile/op_model_amd.c        |   23 ++----
 arch/x86/oprofile/op_model_ppro.c       |    6 +-
 include/linux/hw_breakpoint.h           |    8 +-
 include/linux/perf_event.h              |   27 +++++-
 kernel/hw_breakpoint.c                  |   11 +--
 kernel/perf_event.c                     |   36 ++------
 lib/Kconfig.debug                       |    8 ++
 samples/hw_breakpoint/data_breakpoint.c |    6 +-
 tools/perf/Documentation/perf-lock.txt  |   29 ++++++
 tools/perf/builtin-lock.c               |  148 ++++++++++++++++++++++++++++++-
 tools/perf/builtin-trace.c              |    4 +-
 tools/perf/command-list.txt             |    1 +
 tools/perf/perf-archive.sh              |    3 +-
 tools/perf/perf.h                       |    4 +-
 tools/perf/util/probe-event.c           |    2 +-
 27 files changed, 327 insertions(+), 129 deletions(-)
 create mode 100644 tools/perf/Documentation/perf-lock.txt

diff --git a/MAINTAINERS b/MAINTAINERS
index c8a8b1f..14d5c4c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4293,6 +4293,7 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@elte.hu>
+M:	Arnaldo Carvalho de Melo <acme@redhat.com>
 S:	Supported
 F:	kernel/perf_event.c
 F:	include/linux/perf_event.h
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index c54ceb3..3875d99 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -965,7 +965,7 @@ armv6pmu_handle_irq(int irq_num,
 	 */
 	armv6_pmcr_write(pmcr);
 
-	data.addr = 0;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx <= armpmu->num_events; ++idx) {
@@ -1945,7 +1945,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	 */
 	regs = get_irq_regs();
 
-	data.addr = 0;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx <= armpmu->num_events; ++idx) {
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index b6cf8f1..5120bd4 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1164,10 +1164,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	 * Finally record data if requested.
 	 */
 	if (record) {
-		struct perf_sample_data data = {
-			.addr	= ~0ULL,
-			.period	= event->hw.last_period,
-		};
+		struct perf_sample_data data;
+
+		perf_sample_data_init(&data, ~0ULL);
+		data.period = event->hw.last_period;
 
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 9f2b2ba..6504208 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1189,7 +1189,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	data.addr = 0;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 0675a7c..2a1bd8f 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -10,7 +10,6 @@
  * (display/resolving)
  */
 struct arch_hw_breakpoint {
-	char		*name; /* Contains name of the symbol to set bkpt */
 	unsigned long	address;
 	u8		len;
 	u8		type;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index befd172..db6109a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -18,7 +18,7 @@
 #define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
-#define ARCH_PERFMON_EVENTSEL0_ENABLE			  (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_ENABLE			  (1 << 22)
 #define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
 #define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
 #define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
@@ -50,7 +50,7 @@
 	 INTEL_ARCH_INV_MASK| \
 	 INTEL_ARCH_EDGE_MASK|\
 	 INTEL_ARCH_UNIT_MASK|\
-	 INTEL_ARCH_EVTSEL_MASK)
+	 INTEL_ARCH_EVENT_MASK)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -117,6 +117,18 @@ union cpuid10_edx {
  */
 #define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
 
+/* IbsFetchCtl bits/masks */
+#define IBS_FETCH_RAND_EN		(1ULL<<57)
+#define IBS_FETCH_VAL			(1ULL<<49)
+#define IBS_FETCH_ENABLE		(1ULL<<48)
+#define IBS_FETCH_CNT			0xFFFF0000ULL
+#define IBS_FETCH_MAX_CNT		0x0000FFFFULL
+
+/* IbsOpCtl bits */
+#define IBS_OP_CNT_CTL			(1ULL<<19)
+#define IBS_OP_VAL			(1ULL<<18)
+#define IBS_OP_ENABLE			(1ULL<<17)
+#define IBS_OP_MAX_CNT			0x0000FFFFULL
 
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b1fbdee..42aafd1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -73,10 +73,10 @@ struct debug_store {
 struct event_constraint {
 	union {
 		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-		u64		idxmsk64[1];
+		u64		idxmsk64;
 	};
-	int	code;
-	int	cmask;
+	u64	code;
+	u64	cmask;
 	int	weight;
 };
 
@@ -103,7 +103,7 @@ struct cpu_hw_events {
 };
 
 #define __EVENT_CONSTRAINT(c, n, m, w) {\
-	{ .idxmsk64[0] = (n) },		\
+	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
 	.cmask = (m),			\
 	.weight = (w),			\
@@ -116,7 +116,7 @@ struct cpu_hw_events {
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
 
 #define FIXED_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK)
+	EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)
 
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
@@ -503,6 +503,9 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	if (attr->type == PERF_TYPE_RAW) {
 		hwc->config |= x86_pmu.raw_event(attr->config);
+		if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
+		    perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
 		return 0;
 	}
 
@@ -553,9 +556,9 @@ static void x86_pmu_disable_all(void)
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 		rdmsrl(x86_pmu.eventsel + idx, val);
-		if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
+		if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
 			continue;
-		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(x86_pmu.eventsel + idx, val);
 	}
 }
@@ -590,7 +593,7 @@ static void x86_pmu_enable_all(void)
 			continue;
 
 		val = event->hw.config;
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(x86_pmu.eventsel + idx, val);
 	}
 }
@@ -612,8 +615,8 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 
 	for (i = 0; i < n; i++) {
-		constraints[i] =
-		  x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+		c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+		constraints[i] = c;
 	}
 
 	/*
@@ -853,7 +856,7 @@ void hw_perf_enable(void)
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	(void)checking_wrmsrl(hwc->config_base + idx,
-			      hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
+			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
 static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
@@ -1094,8 +1097,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1347,6 +1349,7 @@ static void __init pmu_check_apic(void)
 
 void __init init_hw_perf_events(void)
 {
+	struct event_constraint *c;
 	int err;
 
 	pr_info("Performance Events: ");
@@ -1395,6 +1398,16 @@ void __init init_hw_perf_events(void)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
 				   0, x86_pmu.num_events);
 
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			if (c->cmask != INTEL_ARCH_FIXED_MASK)
+				continue;
+
+			c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
+			c->weight += x86_pmu.num_events;
+		}
+	}
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.event_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_events);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 977e754..44b60c8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1,7 +1,7 @@
 #ifdef CONFIG_CPU_SUP_INTEL
 
 /*
- * Intel PerfMon v3. Used on Core2 and later.
+ * Intel PerfMon, used on Core and later.
  */
 static const u64 intel_perfmon_event_map[] =
 {
@@ -27,8 +27,14 @@ static struct event_constraint intel_core_event_constraints[] =
 
 static struct event_constraint intel_core2_event_constraints[] =
 {
-	FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
-	FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	/*
+	 * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event
+	 * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed
+	 * ratio between these counters.
+	 */
+	/* FIXED_EVENT_CONSTRAINT(0x013c, 2),  CPU_CLK_UNHALTED.REF */
 	INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
 	INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
 	INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
@@ -37,14 +43,16 @@ static struct event_constraint intel_core2_event_constraints[] =
 	INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */
 	INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
 	INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */
+	INTEL_EVENT_CONSTRAINT(0xc9, 0x1), /* ITLB_MISS_RETIRED (T30-9) */
 	INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */
 	EVENT_CONSTRAINT_END
 };
 
 static struct event_constraint intel_nehalem_event_constraints[] =
 {
-	FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
-	FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
 	INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
 	INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
 	INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
@@ -58,8 +66,9 @@ static struct event_constraint intel_nehalem_event_constraints[] =
 
 static struct event_constraint intel_westmere_event_constraints[] =
 {
-	FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
-	FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
 	INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
 	INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
 	INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
@@ -68,8 +77,9 @@ static struct event_constraint intel_westmere_event_constraints[] =
 
 static struct event_constraint intel_gen_event_constraints[] =
 {
-	FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
-	FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
 	EVENT_CONSTRAINT_END
 };
 
@@ -580,10 +590,9 @@ static void intel_pmu_drain_bts_buffer(void)
 
 	ds->bts_index = ds->bts_buffer_base;
 
+	perf_sample_data_init(&data, 0);
 
 	data.period	= event->hw.last_period;
-	data.addr	= 0;
-	data.raw	= NULL;
 	regs.ip		= 0;
 
 	/*
@@ -732,8 +741,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	int bit, loops;
 	u64 ack, status;
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -935,7 +943,7 @@ static __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_nehalem_event_constraints;
 		pr_cont("Nehalem/Corei7 events, ");
 		break;
-	case 28:
+	case 28: /* Atom */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -951,6 +959,7 @@ static __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_westmere_event_constraints;
 		pr_cont("Westmere events, ");
 		break;
+
 	default:
 		/*
 		 * default constraints for v2 and up
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 1ca5ba0..a4e67b9 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -62,7 +62,7 @@ static void p6_pmu_disable_all(void)
 
 	/* p6 only has one enable register */
 	rdmsrl(MSR_P6_EVNTSEL0, val);
-	val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+	val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 	wrmsrl(MSR_P6_EVNTSEL0, val);
 }
 
@@ -72,7 +72,7 @@ static void p6_pmu_enable_all(void)
 
 	/* p6 only has one enable register */
 	rdmsrl(MSR_P6_EVNTSEL0, val);
-	val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 	wrmsrl(MSR_P6_EVNTSEL0, val);
 }
 
@@ -83,7 +83,7 @@ p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	u64 val = P6_NOP_EVENT;
 
 	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
 	(void)checking_wrmsrl(hwc->config_base + idx, val);
 }
@@ -95,7 +95,7 @@ static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 
 	val = hwc->config;
 	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
 	(void)checking_wrmsrl(hwc->config_base + idx, val);
 }
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 74f4e85..fb329e9 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -680,7 +680,7 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
 	cpu_nmi_set_wd_enabled();
 
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE;
 	wrmsr(evntsel_msr, evntsel, 0);
 	intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
 	return 1;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index dce99ab..d5e2a2e 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -120,9 +120,15 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
 {
 #ifdef CONFIG_FRAME_POINTER
 	struct stack_frame *frame = (struct stack_frame *)bp;
+	unsigned long next;
 
-	if (!in_irq_stack(stack, irq_stack, irq_stack_end))
-		return (unsigned long)frame->next_frame;
+	if (!in_irq_stack(stack, irq_stack, irq_stack_end)) {
+		if (!probe_kernel_address(&frame->next_frame, next))
+			return next;
+		else
+			WARN_ONCE(1, "Perf: bad frame pointer = %p in "
+				  "callchain\n", &frame->next_frame);
+	}
 #endif
 	return bp;
 }
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index dca2802..d6cc065 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -344,13 +344,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 	}
 
 	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)
-				kallsyms_lookup_name(info->name);
-	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
@@ -535,8 +528,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
-
-void hw_breakpoint_pmu_unthrottle(struct perf_event *bp)
-{
-	/* TODO */
-}
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 6a58256..090cbbe 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -46,17 +46,6 @@
 
 static unsigned long reset_value[NUM_VIRT_COUNTERS];
 
-/* IbsFetchCtl bits/masks */
-#define IBS_FETCH_RAND_EN		(1ULL<<57)
-#define IBS_FETCH_VAL			(1ULL<<49)
-#define IBS_FETCH_ENABLE		(1ULL<<48)
-#define IBS_FETCH_CNT_MASK		0xFFFF0000ULL
-
-/* IbsOpCtl bits */
-#define IBS_OP_CNT_CTL			(1ULL<<19)
-#define IBS_OP_VAL			(1ULL<<18)
-#define IBS_OP_ENABLE			(1ULL<<17)
-
 #define IBS_FETCH_SIZE			6
 #define IBS_OP_SIZE			12
 
@@ -182,7 +171,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
 			continue;
 		}
 		rdmsrl(msrs->controls[i].addr, val);
-		if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
 			op_x86_warn_in_use(i);
 		val &= model->reserved;
 		wrmsrl(msrs->controls[i].addr, val);
@@ -290,7 +279,7 @@ op_amd_handle_ibs(struct pt_regs * const regs,
 			oprofile_write_commit(&entry);
 
 			/* reenable the IRQ */
-			ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT_MASK);
+			ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT);
 			ctl |= IBS_FETCH_ENABLE;
 			wrmsrl(MSR_AMD64_IBSFETCHCTL, ctl);
 		}
@@ -330,7 +319,7 @@ static inline void op_amd_start_ibs(void)
 		return;
 
 	if (ibs_config.fetch_enabled) {
-		val = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
+		val = (ibs_config.max_cnt_fetch >> 4) & IBS_FETCH_MAX_CNT;
 		val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0;
 		val |= IBS_FETCH_ENABLE;
 		wrmsrl(MSR_AMD64_IBSFETCHCTL, val);
@@ -352,7 +341,7 @@ static inline void op_amd_start_ibs(void)
 			 * avoid underflows.
 			 */
 			ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET,
-					 0xFFFFULL);
+					 IBS_OP_MAX_CNT);
 		}
 		if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops)
 			ibs_op_ctl |= IBS_OP_CNT_CTL;
@@ -409,7 +398,7 @@ static void op_amd_start(struct op_msrs const * const msrs)
 		if (!reset_value[op_x86_phys_to_virt(i)])
 			continue;
 		rdmsrl(msrs->controls[i].addr, val);
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(msrs->controls[i].addr, val);
 	}
 
@@ -429,7 +418,7 @@ static void op_amd_stop(struct op_msrs const * const msrs)
 		if (!reset_value[op_x86_phys_to_virt(i)])
 			continue;
 		rdmsrl(msrs->controls[i].addr, val);
-		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(msrs->controls[i].addr, val);
 	}
 
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 5d1727b..2bf90fa 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -88,7 +88,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
 			continue;
 		}
 		rdmsrl(msrs->controls[i].addr, val);
-		if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
 			op_x86_warn_in_use(i);
 		val &= model->reserved;
 		wrmsrl(msrs->controls[i].addr, val);
@@ -166,7 +166,7 @@ static void ppro_start(struct op_msrs const * const msrs)
 	for (i = 0; i < num_counters; ++i) {
 		if (reset_value[i]) {
 			rdmsrl(msrs->controls[i].addr, val);
-			val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+			val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 			wrmsrl(msrs->controls[i].addr, val);
 		}
 	}
@@ -184,7 +184,7 @@ static void ppro_stop(struct op_msrs const * const msrs)
 		if (!reset_value[i])
 			continue;
 		rdmsrl(msrs->controls[i].addr, val);
-		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(msrs->controls[i].addr, val);
 	}
 }
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 5977b72..c70d27a 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -66,14 +66,14 @@ register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	triggered,
 				int cpu);
 
-extern struct perf_event **
+extern struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
 extern int __register_perf_hw_breakpoint(struct perf_event *bp);
 extern void unregister_hw_breakpoint(struct perf_event *bp);
-extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events);
+extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
 
 extern int dbg_reserve_bp_slot(struct perf_event *bp);
 extern int dbg_release_bp_slot(struct perf_event *bp);
@@ -100,7 +100,7 @@ static inline struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	 triggered,
 				int cpu)		{ return NULL; }
-static inline struct perf_event **
+static inline struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered)	{ return NULL; }
 static inline int
@@ -109,7 +109,7 @@ static inline int
 __register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
 static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
 static inline void
-unregister_wide_hw_breakpoint(struct perf_event **cpu_events)		{ }
+unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)	{ }
 static inline int
 reserve_bp_slot(struct perf_event *bp)			{return -ENOSYS; }
 static inline void release_bp_slot(struct perf_event *bp) 		{ }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7b18b4f..6f8cd7d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -487,9 +487,8 @@ struct hw_perf_event {
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-		union { /* breakpoint */
-			struct arch_hw_breakpoint	info;
-		};
+		/* breakpoint */
+		struct arch_hw_breakpoint	info;
 #endif
 	};
 	atomic64_t			prev_count;
@@ -802,6 +801,13 @@ struct perf_sample_data {
 	struct perf_raw_record		*raw;
 };
 
+static inline
+void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
+{
+	data->addr = addr;
+	data->raw  = NULL;
+}
+
 extern void perf_output_sample(struct perf_output_handle *handle,
 			       struct perf_event_header *header,
 			       struct perf_sample_data *data,
@@ -858,6 +864,21 @@ extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
 
+static inline bool perf_paranoid_tracepoint_raw(void)
+{
+	return sysctl_perf_event_paranoid > -1;
+}
+
+static inline bool perf_paranoid_cpu(void)
+{
+	return sysctl_perf_event_paranoid > 0;
+}
+
+static inline bool perf_paranoid_kernel(void)
+{
+	return sysctl_perf_event_paranoid > 1;
+}
+
 extern void perf_event_init(void);
 extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
 extern void perf_bp_event(struct perf_event *event, void *data);
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 967e661..03808ed 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -413,17 +413,17 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  *
  * @return a set of per_cpu pointers to perf events
  */
-struct perf_event **
+struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered)
 {
-	struct perf_event **cpu_events, **pevent, *bp;
+	struct perf_event * __percpu *cpu_events, **pevent, *bp;
 	long err;
 	int cpu;
 
 	cpu_events = alloc_percpu(typeof(*cpu_events));
 	if (!cpu_events)
-		return ERR_PTR(-ENOMEM);
+		return (void __percpu __force *)ERR_PTR(-ENOMEM);
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
@@ -451,7 +451,7 @@ fail:
 	put_online_cpus();
 
 	free_percpu(cpu_events);
-	return ERR_PTR(err);
+	return (void __percpu __force *)ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
 
@@ -459,7 +459,7 @@ EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
  * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
  * @cpu_events: the per cpu set of events to unregister
  */
-void unregister_wide_hw_breakpoint(struct perf_event **cpu_events)
+void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
 {
 	int cpu;
 	struct perf_event **pevent;
@@ -489,5 +489,4 @@ struct pmu perf_ops_bp = {
 	.enable		= arch_install_hw_breakpoint,
 	.disable	= arch_uninstall_hw_breakpoint,
 	.read		= hw_breakpoint_pmu_read,
-	.unthrottle	= hw_breakpoint_pmu_unthrottle
 };
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index f40560b..4393b9e 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -56,21 +56,6 @@ static atomic_t nr_task_events __read_mostly;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-static inline bool perf_paranoid_tracepoint_raw(void)
-{
-	return sysctl_perf_event_paranoid > -1;
-}
-
-static inline bool perf_paranoid_cpu(void)
-{
-	return sysctl_perf_event_paranoid > 0;
-}
-
-static inline bool perf_paranoid_kernel(void)
-{
-	return sysctl_perf_event_paranoid > 1;
-}
-
 int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 
 /*
@@ -4123,8 +4108,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 	if (rctx < 0)
 		return;
 
-	data.addr = addr;
-	data.raw  = NULL;
+	perf_sample_data_init(&data, addr);
 
 	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
 
@@ -4169,11 +4153,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	struct perf_event *event;
 	u64 period;
 
-	event	= container_of(hrtimer, struct perf_event, hw.hrtimer);
+	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
 	event->pmu->read(event);
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 	data.period = event->hw.last_period;
 	regs = get_irq_regs();
 	/*
@@ -4337,17 +4320,15 @@ static const struct pmu perf_ops_task_clock = {
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
 			  int entry_size)
 {
+	struct pt_regs *regs = get_irq_regs();
+	struct perf_sample_data data;
 	struct perf_raw_record raw = {
 		.size = entry_size,
 		.data = record,
 	};
 
-	struct perf_sample_data data = {
-		.addr = addr,
-		.raw = &raw,
-	};
-
-	struct pt_regs *regs = get_irq_regs();
+	perf_sample_data_init(&data, addr);
+	data.raw = &raw;
 
 	if (!regs)
 		regs = task_pt_regs(current);
@@ -4463,8 +4444,7 @@ void perf_bp_event(struct perf_event *bp, void *data)
 	struct perf_sample_data sample;
 	struct pt_regs *regs = data;
 
-	sample.raw = NULL;
-	sample.addr = bp->attr.bp_addr;
+	perf_sample_data_init(&sample, bp->attr.bp_addr);
 
 	if (!perf_exclude_event(bp, regs))
 		perf_swevent_add(bp, 1, 1, &sample, regs);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b520ec1..8e5ec5e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -532,6 +532,14 @@ config LOCK_STAT
 
 	 For more details, see Documentation/lockstat.txt
 
+	 This also enables lock events required by "perf lock",
+	 subcommand of perf.
+	 If you want to use "perf lock", you also need to turn on
+	 CONFIG_EVENT_TRACING.
+
+	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
+	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c
index c69cbe9..bd0f337 100644
--- a/samples/hw_breakpoint/data_breakpoint.c
+++ b/samples/hw_breakpoint/data_breakpoint.c
@@ -34,7 +34,7 @@
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 
-struct perf_event **sample_hbp;
+struct perf_event * __percpu *sample_hbp;
 
 static char ksym_name[KSYM_NAME_LEN] = "pid_max";
 module_param_string(ksym, ksym_name, KSYM_NAME_LEN, S_IRUGO);
@@ -61,8 +61,8 @@ static int __init hw_break_module_init(void)
 	attr.bp_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
 
 	sample_hbp = register_wide_hw_breakpoint(&attr, sample_hbp_handler);
-	if (IS_ERR(sample_hbp)) {
-		ret = PTR_ERR(sample_hbp);
+	if (IS_ERR((void __force *)sample_hbp)) {
+		ret = PTR_ERR((void __force *)sample_hbp);
 		goto fail;
 	}
 
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
new file mode 100644
index 0000000..b317102
--- /dev/null
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -0,0 +1,29 @@
+perf-lock(1)
+============
+
+NAME
+----
+perf-lock - Analyze lock events
+
+SYNOPSIS
+--------
+[verse]
+'perf lock' {record|report|trace}
+
+DESCRIPTION
+-----------
+You can analyze various lock behaviours
+and statistics with this 'perf lock' command.
+
+  'perf lock record <command>' records lock events
+  between start and end <command>. And this command
+  produces the file "perf.data" which contains tracing
+  results of lock events.
+
+  'perf lock trace' shows raw lock events.
+
+  'perf lock report' reports statistical data.
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index fb9ab2a..e12c844 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -460,6 +460,150 @@ process_raw_event(void *data, int cpu,
 		process_lock_release_event(data, event, cpu, timestamp, thread);
 }
 
+struct raw_event_queue {
+	u64			timestamp;
+	int			cpu;
+	void			*data;
+	struct thread		*thread;
+	struct list_head	list;
+};
+
+static LIST_HEAD(raw_event_head);
+
+#define FLUSH_PERIOD	(5 * NSEC_PER_SEC)
+
+static u64 flush_limit = ULLONG_MAX;
+static u64 last_flush = 0;
+struct raw_event_queue *last_inserted;
+
+static void flush_raw_event_queue(u64 limit)
+{
+	struct raw_event_queue *tmp, *iter;
+
+	list_for_each_entry_safe(iter, tmp, &raw_event_head, list) {
+		if (iter->timestamp > limit)
+			return;
+
+		if (iter == last_inserted)
+			last_inserted = NULL;
+
+		process_raw_event(iter->data, iter->cpu, iter->timestamp,
+				  iter->thread);
+
+		last_flush = iter->timestamp;
+		list_del(&iter->list);
+		free(iter->data);
+		free(iter);
+	}
+}
+
+static void __queue_raw_event_end(struct raw_event_queue *new)
+{
+	struct raw_event_queue *iter;
+
+	list_for_each_entry_reverse(iter, &raw_event_head, list) {
+		if (iter->timestamp < new->timestamp) {
+			list_add(&new->list, &iter->list);
+			return;
+		}
+	}
+
+	list_add(&new->list, &raw_event_head);
+}
+
+static void __queue_raw_event_before(struct raw_event_queue *new,
+				     struct raw_event_queue *iter)
+{
+	list_for_each_entry_continue_reverse(iter, &raw_event_head, list) {
+		if (iter->timestamp < new->timestamp) {
+			list_add(&new->list, &iter->list);
+			return;
+		}
+	}
+
+	list_add(&new->list, &raw_event_head);
+}
+
+static void __queue_raw_event_after(struct raw_event_queue *new,
+				     struct raw_event_queue *iter)
+{
+	list_for_each_entry_continue(iter, &raw_event_head, list) {
+		if (iter->timestamp > new->timestamp) {
+			list_add_tail(&new->list, &iter->list);
+			return;
+		}
+	}
+	list_add_tail(&new->list, &raw_event_head);
+}
+
+/* The queue is ordered by time */
+static void __queue_raw_event(struct raw_event_queue *new)
+{
+	if (!last_inserted) {
+		__queue_raw_event_end(new);
+		return;
+	}
+
+	/*
+	 * Most of the time the current event has a timestamp
+	 * very close to the last event inserted, unless we just switched
+	 * to another event buffer. Having a sorting based on a list and
+	 * on the last inserted event that is close to the current one is
+	 * probably more efficient than an rbtree based sorting.
+	 */
+	if (last_inserted->timestamp >= new->timestamp)
+		__queue_raw_event_before(new, last_inserted);
+	else
+		__queue_raw_event_after(new, last_inserted);
+}
+
+static void queue_raw_event(void *data, int raw_size, int cpu,
+			    u64 timestamp, struct thread *thread)
+{
+	struct raw_event_queue *new;
+
+	if (flush_limit == ULLONG_MAX)
+		flush_limit = timestamp + FLUSH_PERIOD;
+
+	if (timestamp < last_flush) {
+		printf("Warning: Timestamp below last timeslice flush\n");
+		return;
+	}
+
+	new = malloc(sizeof(*new));
+	if (!new)
+		die("Not enough memory\n");
+
+	new->timestamp = timestamp;
+	new->cpu = cpu;
+	new->thread = thread;
+
+	new->data = malloc(raw_size);
+	if (!new->data)
+		die("Not enough memory\n");
+
+	memcpy(new->data, data, raw_size);
+
+	__queue_raw_event(new);
+	last_inserted = new;
+
+	/*
+	 * We want to have a slice of events covering 2 * FLUSH_PERIOD
+	 * If FLUSH_PERIOD is big enough, it ensures every events that occured
+	 * in the first half of the timeslice have all been buffered and there
+	 * are none remaining (we need that because of the weakly ordered
+	 * event recording we have). Then once we reach the 2 * FLUSH_PERIOD
+	 * timeslice, we flush the first half to be gentle with the memory
+	 * (the second half can still get new events in the middle, so wait
+	 * another period to flush it)
+	 */
+	if (new->timestamp > flush_limit &&
+		new->timestamp - flush_limit > FLUSH_PERIOD) {
+		flush_limit += FLUSH_PERIOD;
+		flush_raw_event_queue(flush_limit);
+	}
+}
+
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
 	struct thread *thread;
@@ -480,7 +624,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 	if (profile_cpu != -1 && profile_cpu != (int) data.cpu)
 		return 0;
 
-	process_raw_event(data.raw_data, data.cpu, data.time, thread);
+	queue_raw_event(data.raw_data, data.raw_size, data.cpu, data.time, thread);
 
 	return 0;
 }
@@ -576,6 +720,7 @@ static void __cmd_report(void)
 	setup_pager();
 	select_key();
 	read_events();
+	flush_raw_event_queue(ULLONG_MAX);
 	sort_result();
 	print_result();
 }
@@ -608,7 +753,6 @@ static const char *record_args[] = {
 	"record",
 	"-a",
 	"-R",
-	"-M",
 	"-f",
 	"-m", "1024",
 	"-c", "1",
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5db687f..407041d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -573,7 +573,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 
 	if (symbol__init() < 0)
 		return -1;
-	setup_pager();
+	if (!script_name)
+		setup_pager();
 
 	session = perf_session__new(input_name, O_RDONLY, 0);
 	if (session == NULL)
@@ -608,7 +609,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 			return -1;
 		}
 
-		perf_header__read(&session->header, input);
 		err = scripting_ops->generate_script("perf-trace");
 		goto out;
 	}
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 9afcff2..db6ee94 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -18,3 +18,4 @@ perf-top			mainporcelain common
 perf-trace			mainporcelain common
 perf-probe			mainporcelain common
 perf-kmem			mainporcelain common
+perf-lock			mainporcelain common
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 45fbe2f..910468e 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -9,8 +9,9 @@ fi
 
 DEBUGDIR=~/.debug/
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
+NOBUILDID=0000000000000000000000000000000000000000
 
-perf buildid-list -i $PERF_DATA --with-hits > $BUILDIDS
+perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
 if [ ! -s $BUILDIDS ] ; then
 	echo "perf archive: no build-ids found"
 	rm -f $BUILDIDS
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 75f941b..6fb379b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -65,9 +65,7 @@
  * Use the __kuser_memory_barrier helper in the CPU helper page. See
  * arch/arm/kernel/entry-armv.S in the kernel source for details.
  */
-#define rmb()		asm volatile("mov r0, #0xffff0fff; mov lr, pc;" \
-				     "sub pc, r0, #95" ::: "r0", "lr", "cc", \
-				     "memory")
+#define rmb()		((void(*)(void))0xffff0fa0)()
 #define cpu_relax()	asm volatile("":::"memory")
 #endif
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c971e81..53181db 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -508,8 +508,8 @@ void show_perf_probe_events(void)
 	struct str_node *ent;
 
 	setup_pager();
-
 	memset(&pp, 0, sizeof(pp));
+
 	fd = open_kprobe_events(O_RDONLY, 0);
 	rawlist = get_trace_kprobe_event_rawlist(fd);
 	close(fd);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-02-22 17:01 ` Linus Torvalds
@ 2010-02-22 17:15   ` Frederic Weisbecker
  0 siblings, 0 replies; 376+ messages in thread
From: Frederic Weisbecker @ 2010-02-22 17:15 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Ingo Molnar, linux-kernel, Peter Zijlstra, Paul Mackerras,
	Thomas Gleixner, Andrew Morton, H. Peter Anvin

On Mon, Feb 22, 2010 at 09:01:39AM -0800, Linus Torvalds wrote:
> 
> 
> On Mon, 22 Feb 2010, Ingo Molnar wrote:
> > 
> > The reason i'm sending them post -rc8 is the fix for the Wine breakage from 
> > Frederic, which would be nice to see resolved in -final.
> 
> Umm. That commit seems to be crap.
> 
> Yes, it was wrong to not allow a NULL address breakpoint. But if you call 
> kallsyms_lookup_name(), you should check the "I couldn't find it" end 
> result for _that_ case, and 0 is the correct check there.
> 
> So the code _should_ do something like
> 
> 	if (info->name) {
> 		info->address = kallsyms_lookup_name(info->name);
> 		if (!info->address)
> 			return -EINVAL;
> 	}
> 
> and that would correctly handle both the NULL original address _and_ the 
> name lookup failure.



Ah you're right. That part in itself is buggy. Fortunately this won't ever
be reached because we don't use the info->name field anymore . It's a field I
forgot to remove when I re-adapted the new hw-breakpoint API on top of perf.
The name resolution (used by the ksym tracer and the hw-breakpoint sample
only) is done in an upper layer now, and never stored in the arch back end in any
case.

I'll remove this field and the associated dead-code for .34

Thanks.


^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2010-02-22 16:50 Ingo Molnar
@ 2010-02-22 17:01 ` Linus Torvalds
  2010-02-22 17:15   ` Frederic Weisbecker
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2010-02-22 17:01 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras, Thomas Gleixner,
	Fr??d??ric Weisbecker, Andrew Morton, H. Peter Anvin



On Mon, 22 Feb 2010, Ingo Molnar wrote:
> 
> The reason i'm sending them post -rc8 is the fix for the Wine breakage from 
> Frederic, which would be nice to see resolved in -final.

Umm. That commit seems to be crap.

Yes, it was wrong to not allow a NULL address breakpoint. But if you call 
kallsyms_lookup_name(), you should check the "I couldn't find it" end 
result for _that_ case, and 0 is the correct check there.

So the code _should_ do something like

	if (info->name) {
		info->address = kallsyms_lookup_name(info->name);
		if (!info->address)
			return -EINVAL;
	}

and that would correctly handle both the NULL original address _and_ the 
name lookup failure.

Also, note how I removed the totally bogus cast.

Anyway, I pulled, but I really wish somebody had thought through those 
cases. Somebody who knows the code better than I do (maybe there is an 
error check later for "if (info->name && !info->address)", but I didn't 
see one in a quick grep).

		Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-02-22 16:50 Ingo Molnar
  2010-02-22 17:01 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2010-02-22 16:50 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras, Thomas Gleixner,
	Fr??d??ric Weisbecker, Andrew Morton, H. Peter Anvin

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

The reason i'm sending them post -rc8 is the fix for the Wine breakage from 
Frederic, which would be nice to see resolved in -final.

Thanks,

	Ingo

------------------>
Frederic Weisbecker (2):
      hw-breakpoints: Accept breakpoints on NULL address
      hw-breakpoint: Keep track of dr7 local enable bits

Masami Hiramatsu (1):
      perf probe: Init struct probe_point and set counter correctly

Peter Zijlstra (1):
      perf_events: Fix FORK events


 arch/x86/include/asm/processor.h |    2 ++
 arch/x86/kernel/hw_breakpoint.c  |   30 +++++++-----------------------
 arch/x86/kernel/ptrace.c         |    7 +++++--
 kernel/perf_event.c              |   11 +++++------
 tools/perf/util/probe-event.c    |    3 +++
 5 files changed, 22 insertions(+), 31 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fc801ba..b753ea5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -450,6 +450,8 @@ struct thread_struct {
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
 	unsigned long           debugreg6;
+	/* Keep track of the exact dr7 value set by the user */
+	unsigned long           ptrace_dr7;
 	/* Fault info: */
 	unsigned long		cr2;
 	unsigned long		trap_no;
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 05d5fec..bb6006e 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -212,25 +212,6 @@ static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
 
-/*
- * Store a breakpoint's encoded address, length, and type.
- */
-static int arch_store_info(struct perf_event *bp)
-{
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)
-				kallsyms_lookup_name(info->name);
-	if (info->address)
-		return 0;
-
-	return -EINVAL;
-}
-
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
@@ -362,10 +343,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 		return ret;
 	}
 
-	ret = arch_store_info(bp);
-
-	if (ret < 0)
-		return ret;
+	/*
+	 * For kernel-addresses, either the address or symbol name can be
+	 * specified.
+	 */
+	if (info->name)
+		info->address = (unsigned long)
+				kallsyms_lookup_name(info->name);
 	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 017d937..0c1033d 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -702,7 +702,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 	} else if (n == 6) {
 		val = thread->debugreg6;
 	 } else if (n == 7) {
-		val = ptrace_get_dr7(thread->ptrace_bps);
+		val = thread->ptrace_dr7;
 	}
 	return val;
 }
@@ -778,8 +778,11 @@ int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
 			return rc;
 	}
 	/* All that's left is DR7 */
-	if (n == 7)
+	if (n == 7) {
 		rc = ptrace_write_dr7(tsk, val);
+		if (!rc)
+			thread->ptrace_dr7 = val;
+	}
 
 ret_path:
 	return rc;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 2b19297..2ae7409 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3259,8 +3259,6 @@ static void perf_event_task_output(struct perf_event *event,
 	task_event->event_id.tid = perf_event_tid(event, task);
 	task_event->event_id.ptid = perf_event_tid(event, current);
 
-	task_event->event_id.time = perf_clock();
-
 	perf_output_put(&handle, task_event->event_id);
 
 	perf_output_end(&handle);
@@ -3268,7 +3266,7 @@ static void perf_event_task_output(struct perf_event *event,
 
 static int perf_event_task_match(struct perf_event *event)
 {
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -3300,7 +3298,7 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_task_ctx(&cpuctx->ctx, task_event);
 	if (!ctx)
-		ctx = rcu_dereference(task_event->task->perf_event_ctxp);
+		ctx = rcu_dereference(current->perf_event_ctxp);
 	if (ctx)
 		perf_event_task_ctx(ctx, task_event);
 	put_cpu_var(perf_cpu_context);
@@ -3331,6 +3329,7 @@ static void perf_event_task(struct task_struct *task,
 			/* .ppid */
 			/* .tid  */
 			/* .ptid */
+			.time = perf_clock(),
 		},
 	};
 
@@ -3380,7 +3379,7 @@ static void perf_event_comm_output(struct perf_event *event,
 
 static int perf_event_comm_match(struct perf_event *event)
 {
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -3500,7 +3499,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 static int perf_event_mmap_match(struct perf_event *event,
 				   struct perf_mmap_event *mmap_event)
 {
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 29465d4..fde17b0 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -272,6 +272,7 @@ int synthesize_perf_probe_point(struct probe_point *pp)
 	int ret;
 
 	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
+	pp->found = 1;
 	if (!buf)
 		die("Failed to allocate memory by zalloc.");
 	if (pp->offset) {
@@ -294,6 +295,7 @@ int synthesize_perf_probe_point(struct probe_point *pp)
 error:
 		free(pp->probes[0]);
 		pp->probes[0] = NULL;
+		pp->found = 0;
 	}
 	return ret;
 }
@@ -455,6 +457,7 @@ void show_perf_probe_events(void)
 	struct strlist *rawlist;
 	struct str_node *ent;
 
+	memset(&pp, 0, sizeof(pp));
 	fd = open_kprobe_events(O_RDONLY, 0);
 	rawlist = get_trace_kprobe_event_rawlist(fd);
 	close(fd);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-02-14  9:06 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-02-14  9:06 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras,
	Fr??d??ric Weisbecker, Arnaldo Carvalho de Melo

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Anton Blanchard (1):
      perf: Fix hypervisor sample reporting

Kirill Smelkov (1):
      perf top: Fix help text alignment

Mahesh Salgaonkar (1):
      perf: Make bp_len type to u64 generic across the arch


 include/linux/hw_breakpoint.h |    2 +-
 include/linux/perf_event.h    |    6 ++----
 kernel/hw_breakpoint.c        |    2 +-
 kernel/perf_event.c           |    2 +-
 tools/perf/builtin-top.c      |    2 +-
 tools/perf/util/event.c       |    4 ++--
 6 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 070ba06..5977b72 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -44,7 +44,7 @@ static inline int hw_breakpoint_type(struct perf_event *bp)
 	return bp->attr.bp_type;
 }
 
-static inline int hw_breakpoint_len(struct perf_event *bp)
+static inline unsigned long hw_breakpoint_len(struct perf_event *bp)
 {
 	return bp->attr.bp_len;
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8fa7187..a177698 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -211,11 +211,9 @@ struct perf_event_attr {
 		__u32		wakeup_watermark; /* bytes before wakeup   */
 	};
 
-	__u32			__reserved_2;
-
-	__u64			bp_addr;
 	__u32			bp_type;
-	__u32			bp_len;
+	__u64			bp_addr;
+	__u64			bp_len;
 };
 
 /*
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 8a5c7d5..967e661 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -360,8 +360,8 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
 	u64 old_addr = bp->attr.bp_addr;
+	u64 old_len = bp->attr.bp_len;
 	int old_type = bp->attr.bp_type;
-	int old_len = bp->attr.bp_len;
 	int err = 0;
 
 	perf_event_disable(bp);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index d27746b..2b19297 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -4580,7 +4580,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->type >= PERF_TYPE_MAX)
 		return -EINVAL;
 
-	if (attr->__reserved_1 || attr->__reserved_2)
+	if (attr->__reserved_1)
 		return -EINVAL;
 
 	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ddc584b..4b91d8c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -705,7 +705,7 @@ static void print_mapped_keys(void)
 		fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0);
 
 	fprintf(stdout,
-		"\t[K]     hide kernel_symbols symbols.             \t(%s)\n",
+		"\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
 		hide_kernel_symbols ? "yes" : "no");
 	fprintf(stdout,
 		"\t[U]     hide user symbols.               \t(%s)\n",
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bb0fd6d..8a9e6ba 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -295,10 +295,10 @@ void thread__find_addr_location(struct thread *self,
 	al->thread = self;
 	al->addr = addr;
 
-	if (cpumode & PERF_RECORD_MISC_KERNEL) {
+	if (cpumode == PERF_RECORD_MISC_KERNEL) {
 		al->level = 'k';
 		mg = &session->kmaps;
-	} else if (cpumode & PERF_RECORD_MISC_USER)
+	} else if (cpumode == PERF_RECORD_MISC_USER)
 		al->level = '.';
 	else {
 		al->level = 'H';

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-01-31 17:32 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-01-31 17:32 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras,
	Fr??d??ric Weisbecker, Jason Wessel, Thomas Gleixner,
	Arnaldo Carvalho de Melo, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Amerigo Wang (1):
      perf: Ignore perf.data.old

Jason Wessel (2):
      x86, hw_breakpoints, kgdb: Fix kgdb to use hw_breakpoint API
      perf, hw_breakpoint, kgdb: Do not take mutex for kernel debugger

Mahesh Salgaonkar (1):
      hw_breakpoints: Release the bp slot if arch_validate_hwbkpt_settings() fails.

Yong Wang (1):
      perf report: Fix segmentation fault when running with '-g none'


 arch/x86/kernel/kgdb.c        |  222 ++++++++++++++++++++++++++++++-----------
 include/linux/hw_breakpoint.h |    2 +
 kernel/hw_breakpoint.c        |   56 +++++++++--
 kernel/kgdb.c                 |    3 +
 tools/perf/.gitignore         |    1 +
 tools/perf/builtin-report.c   |    2 +-
 6 files changed, 218 insertions(+), 68 deletions(-)

diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index dd74fe7..bfba601 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -42,6 +42,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
@@ -204,40 +205,81 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 
 static struct hw_breakpoint {
 	unsigned		enabled;
-	unsigned		type;
-	unsigned		len;
 	unsigned long		addr;
+	int			len;
+	int			type;
+	struct perf_event	**pev;
 } breakinfo[4];
 
 static void kgdb_correct_hw_break(void)
 {
-	unsigned long dr7;
-	int correctit = 0;
-	int breakbit;
 	int breakno;
 
-	get_debugreg(dr7, 7);
 	for (breakno = 0; breakno < 4; breakno++) {
-		breakbit = 2 << (breakno << 1);
-		if (!(dr7 & breakbit) && breakinfo[breakno].enabled) {
-			correctit = 1;
-			dr7 |= breakbit;
-			dr7 &= ~(0xf0000 << (breakno << 2));
-			dr7 |= ((breakinfo[breakno].len << 2) |
-				 breakinfo[breakno].type) <<
-			       ((breakno << 2) + 16);
-			set_debugreg(breakinfo[breakno].addr, breakno);
-
-		} else {
-			if ((dr7 & breakbit) && !breakinfo[breakno].enabled) {
-				correctit = 1;
-				dr7 &= ~breakbit;
-				dr7 &= ~(0xf0000 << (breakno << 2));
-			}
-		}
+		struct perf_event *bp;
+		struct arch_hw_breakpoint *info;
+		int val;
+		int cpu = raw_smp_processor_id();
+		if (!breakinfo[breakno].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		info = counter_arch_bp(bp);
+		if (bp->attr.disabled != 1)
+			continue;
+		bp->attr.bp_addr = breakinfo[breakno].addr;
+		bp->attr.bp_len = breakinfo[breakno].len;
+		bp->attr.bp_type = breakinfo[breakno].type;
+		info->address = breakinfo[breakno].addr;
+		info->len = breakinfo[breakno].len;
+		info->type = breakinfo[breakno].type;
+		val = arch_install_hw_breakpoint(bp);
+		if (!val)
+			bp->attr.disabled = 0;
+	}
+	hw_breakpoint_restore();
+}
+
+static int hw_break_reserve_slot(int breakno)
+{
+	int cpu;
+	int cnt = 0;
+	struct perf_event **pevent;
+
+	for_each_online_cpu(cpu) {
+		cnt++;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_reserve_bp_slot(*pevent))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	for_each_online_cpu(cpu) {
+		cnt--;
+		if (!cnt)
+			break;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		dbg_release_bp_slot(*pevent);
 	}
-	if (correctit)
-		set_debugreg(dr7, 7);
+	return -1;
+}
+
+static int hw_break_release_slot(int breakno)
+{
+	struct perf_event **pevent;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_release_bp_slot(*pevent))
+			/*
+			 * The debugger is responisble for handing the retry on
+			 * remove failure.
+			 */
+			return -1;
+	}
+	return 0;
 }
 
 static int
@@ -251,6 +293,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 	if (i == 4)
 		return -1;
 
+	if (hw_break_release_slot(i)) {
+		printk(KERN_ERR "Cannot remove hw breakpoint at %lx\n", addr);
+		return -1;
+	}
 	breakinfo[i].enabled = 0;
 
 	return 0;
@@ -259,15 +305,23 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 static void kgdb_remove_all_hw_break(void)
 {
 	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
 
-	for (i = 0; i < 4; i++)
-		memset(&breakinfo[i], 0, sizeof(struct hw_breakpoint));
+	for (i = 0; i < 4; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
 }
 
 static int
 kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 {
-	unsigned type;
 	int i;
 
 	for (i = 0; i < 4; i++)
@@ -278,27 +332,42 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 
 	switch (bptype) {
 	case BP_HARDWARE_BREAKPOINT:
-		type = 0;
-		len  = 1;
+		len = 1;
+		breakinfo[i].type = X86_BREAKPOINT_EXECUTE;
 		break;
 	case BP_WRITE_WATCHPOINT:
-		type = 1;
+		breakinfo[i].type = X86_BREAKPOINT_WRITE;
 		break;
 	case BP_ACCESS_WATCHPOINT:
-		type = 3;
+		breakinfo[i].type = X86_BREAKPOINT_RW;
 		break;
 	default:
 		return -1;
 	}
-
-	if (len == 1 || len == 2 || len == 4)
-		breakinfo[i].len  = len - 1;
-	else
+	switch (len) {
+	case 1:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_1;
+		break;
+	case 2:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_2;
+		break;
+	case 4:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_4;
+		break;
+#ifdef CONFIG_X86_64
+	case 8:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_8;
+		break;
+#endif
+	default:
 		return -1;
-
-	breakinfo[i].enabled = 1;
+	}
 	breakinfo[i].addr = addr;
-	breakinfo[i].type = type;
+	if (hw_break_reserve_slot(i)) {
+		breakinfo[i].addr = 0;
+		return -1;
+	}
+	breakinfo[i].enabled = 1;
 
 	return 0;
 }
@@ -313,8 +382,21 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
  */
 void kgdb_disable_hw_debug(struct pt_regs *regs)
 {
+	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
+
 	/* Disable hardware debugging while we are in kgdb: */
 	set_debugreg(0UL, 7);
+	for (i = 0; i < 4; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
 }
 
 /**
@@ -378,7 +460,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			       struct pt_regs *linux_regs)
 {
 	unsigned long addr;
-	unsigned long dr6;
 	char *ptr;
 	int newPC;
 
@@ -404,20 +485,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 				   raw_smp_processor_id());
 		}
 
-		get_debugreg(dr6, 6);
-		if (!(dr6 & 0x4000)) {
-			int breakno;
-
-			for (breakno = 0; breakno < 4; breakno++) {
-				if (dr6 & (1 << breakno) &&
-				    breakinfo[breakno].type == 0) {
-					/* Set restore flag: */
-					linux_regs->flags |= X86_EFLAGS_RF;
-					break;
-				}
-			}
-		}
-		set_debugreg(0UL, 6);
 		kgdb_correct_hw_break();
 
 		return 0;
@@ -485,8 +552,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 		break;
 
 	case DIE_DEBUG:
-		if (atomic_read(&kgdb_cpu_doing_single_step) ==
-		    raw_smp_processor_id()) {
+		if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
 			if (user_mode(regs))
 				return single_step_cont(regs, args);
 			break;
@@ -539,7 +605,42 @@ static struct notifier_block kgdb_notifier = {
  */
 int kgdb_arch_init(void)
 {
-	return register_die_notifier(&kgdb_notifier);
+	int i, cpu;
+	int ret;
+	struct perf_event_attr attr;
+	struct perf_event **pevent;
+
+	ret = register_die_notifier(&kgdb_notifier);
+	if (ret != 0)
+		return ret;
+	/*
+	 * Pre-allocate the hw breakpoint structions in the non-atomic
+	 * portion of kgdb because this operation requires mutexs to
+	 * complete.
+	 */
+	attr.bp_addr = (unsigned long)kgdb_arch_init;
+	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.bp_len = HW_BREAKPOINT_LEN_1;
+	attr.bp_type = HW_BREAKPOINT_W;
+	attr.disabled = 1;
+	for (i = 0; i < 4; i++) {
+		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL);
+		if (IS_ERR(breakinfo[i].pev)) {
+			printk(KERN_ERR "kgdb: Could not allocate hw breakpoints\n");
+			breakinfo[i].pev = NULL;
+			kgdb_arch_exit();
+			return -1;
+		}
+		for_each_online_cpu(cpu) {
+			pevent = per_cpu_ptr(breakinfo[i].pev, cpu);
+			pevent[0]->hw.sample_period = 1;
+			if (pevent[0]->destroy != NULL) {
+				pevent[0]->destroy = NULL;
+				release_bp_slot(*pevent);
+			}
+		}
+	}
+	return ret;
 }
 
 /**
@@ -550,6 +651,13 @@ int kgdb_arch_init(void)
  */
 void kgdb_arch_exit(void)
 {
+	int i;
+	for (i = 0; i < 4; i++) {
+		if (breakinfo[i].pev) {
+			unregister_wide_hw_breakpoint(breakinfo[i].pev);
+			breakinfo[i].pev = NULL;
+		}
+	}
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 41235c9..070ba06 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -75,6 +75,8 @@ extern int __register_perf_hw_breakpoint(struct perf_event *bp);
 extern void unregister_hw_breakpoint(struct perf_event *bp);
 extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events);
 
+extern int dbg_reserve_bp_slot(struct perf_event *bp);
+extern int dbg_release_bp_slot(struct perf_event *bp);
 extern int reserve_bp_slot(struct perf_event *bp);
 extern void release_bp_slot(struct perf_event *bp);
 
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 50dbd59..8a5c7d5 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -243,38 +243,70 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
  *       ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
  *            + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM
  */
-int reserve_bp_slot(struct perf_event *bp)
+static int __reserve_bp_slot(struct perf_event *bp)
 {
 	struct bp_busy_slots slots = {0};
-	int ret = 0;
-
-	mutex_lock(&nr_bp_mutex);
 
 	fetch_bp_busy_slots(&slots, bp);
 
 	/* Flexible counters need to keep at least one slot */
-	if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
-		ret = -ENOSPC;
-		goto end;
-	}
+	if (slots.pinned + (!!slots.flexible) == HBP_NUM)
+		return -ENOSPC;
 
 	toggle_bp_slot(bp, true);
 
-end:
+	return 0;
+}
+
+int reserve_bp_slot(struct perf_event *bp)
+{
+	int ret;
+
+	mutex_lock(&nr_bp_mutex);
+
+	ret = __reserve_bp_slot(bp);
+
 	mutex_unlock(&nr_bp_mutex);
 
 	return ret;
 }
 
+static void __release_bp_slot(struct perf_event *bp)
+{
+	toggle_bp_slot(bp, false);
+}
+
 void release_bp_slot(struct perf_event *bp)
 {
 	mutex_lock(&nr_bp_mutex);
 
-	toggle_bp_slot(bp, false);
+	__release_bp_slot(bp);
 
 	mutex_unlock(&nr_bp_mutex);
 }
 
+/*
+ * Allow the kernel debugger to reserve breakpoint slots without
+ * taking a lock using the dbg_* variant of for the reserve and
+ * release breakpoint slots.
+ */
+int dbg_reserve_bp_slot(struct perf_event *bp)
+{
+	if (mutex_is_locked(&nr_bp_mutex))
+		return -1;
+
+	return __reserve_bp_slot(bp);
+}
+
+int dbg_release_bp_slot(struct perf_event *bp)
+{
+	if (mutex_is_locked(&nr_bp_mutex))
+		return -1;
+
+	__release_bp_slot(bp);
+
+	return 0;
+}
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
@@ -296,6 +328,10 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
 	if (!bp->attr.disabled || !bp->overflow_handler)
 		ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
 
+	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
+	if (ret)
+		release_bp_slot(bp);
+
 	return ret;
 }
 
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 2eb517e..c7ade62 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -583,6 +583,9 @@ static void kgdb_wait(struct pt_regs *regs)
 	smp_wmb();
 	atomic_set(&cpu_in_kgdb[cpu], 1);
 
+	/* Disable any cpu specific hw breakpoints */
+	kgdb_disable_hw_debug(regs);
+
 	/* Wait till primary CPU is done with debugging */
 	while (atomic_read(&passive_cpu_wait[cpu]))
 		cpu_relax();
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index fe08660..124760b 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -13,6 +13,7 @@ perf*.xml
 perf*.html
 common-cmds.h
 perf.data
+perf.data.old
 tags
 TAGS
 cscope*
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index db10c0e..860f1ee 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -269,7 +269,7 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 
 	else if (!strncmp(tok, "none", strlen(arg))) {
 		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = true;
+		symbol_conf.use_callchain = false;
 
 		return 0;
 	}

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2010-01-21 15:38 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2010-01-21 15:38 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras, Thomas Gleixner

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arjan van de Ven (1):
      perf timechart: Use tid not pid for COMM change

Luca Barbieri (1):
      hw-breakpoints, perf: Fix broken mmiotrace due to dr6 by reference change

Pekka Enberg (2):
      perf kmem: Increase "Hit" column length
      perf kmem: Print usage help for unknown commands

Peter Zijlstra (3):
      perf: Fix perf_event_do_pending() fallback callsite
      perf: Honour event state for aux stream data
      perf: Change the is_software_event() definition

Stephane Eranian (1):
      perf: x86: Add support for the ANY bit


 arch/x86/include/asm/perf_event.h |    1 +
 arch/x86/kernel/cpu/perf_event.c  |    7 +++++++
 arch/x86/mm/kmmio.c               |    7 ++++---
 include/linux/perf_event.h        |   11 ++++++++---
 kernel/perf_event.c               |    9 +++++++++
 kernel/timer.c                    |    3 +--
 tools/perf/builtin-kmem.c         |    7 ++++---
 tools/perf/builtin-timechart.c    |    2 +-
 8 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8d9f854..1380367 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -19,6 +19,7 @@
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
 #define ARCH_PERFMON_EVENTSEL0_ENABLE			  (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
 #define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
 #define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
 #define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index d616c06..8c1c070 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1343,6 +1343,13 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
 		bits |= 0x2;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
 		bits |= 0x1;
+
+	/*
+	 * ANY bit is supported in v3 and up
+	 */
+	if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
+		bits |= 0x4;
+
 	bits <<= (idx * 4);
 	mask = 0xfULL << (idx * 4);
 
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index c0f6198..536fb68 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -538,14 +538,15 @@ static int
 kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
 {
 	struct die_args *arg = args;
+	unsigned long* dr6_p = (unsigned long *)ERR_PTR(arg->err);
 
-	if (val == DIE_DEBUG && (arg->err & DR_STEP))
-		if (post_kmmio_handler(arg->err, arg->regs) == 1) {
+	if (val == DIE_DEBUG && (*dr6_p & DR_STEP))
+		if (post_kmmio_handler(*dr6_p, arg->regs) == 1) {
 			/*
 			 * Reset the BS bit in dr6 (pointed by args->err) to
 			 * denote completion of processing
 			 */
-			(*(unsigned long *)ERR_PTR(arg->err)) &= ~DR_STEP;
+			*dr6_p &= ~DR_STEP;
 			return NOTIFY_STOP;
 		}
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c66b34f..8fa7187 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -814,9 +814,14 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	return (event->attr.type != PERF_TYPE_RAW) &&
-		(event->attr.type != PERF_TYPE_HARDWARE) &&
-		(event->attr.type != PERF_TYPE_HW_CACHE);
+	switch (event->attr.type) {
+	case PERF_TYPE_SOFTWARE:
+	case PERF_TYPE_TRACEPOINT:
+	/* for now the breakpoint stuff also works as software event */
+	case PERF_TYPE_BREAKPOINT:
+		return 1;
+	}
+	return 0;
 }
 
 extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 603c0d8..d27746b 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3268,6 +3268,9 @@ static void perf_event_task_output(struct perf_event *event,
 
 static int perf_event_task_match(struct perf_event *event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return 0;
+
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
 		return 0;
 
@@ -3377,6 +3380,9 @@ static void perf_event_comm_output(struct perf_event *event,
 
 static int perf_event_comm_match(struct perf_event *event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return 0;
+
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
 		return 0;
 
@@ -3494,6 +3500,9 @@ static void perf_event_mmap_output(struct perf_event *event,
 static int perf_event_mmap_match(struct perf_event *event,
 				   struct perf_mmap_event *mmap_event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return 0;
+
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
 		return 0;
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 15533b7..c61a794 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1198,6 +1198,7 @@ void update_process_times(int user_tick)
 	run_local_timers();
 	rcu_check_callbacks(cpu, user_tick);
 	printk_tick();
+	perf_event_do_pending();
 	scheduler_tick();
 	run_posix_cpu_timers(p);
 }
@@ -1209,8 +1210,6 @@ static void run_timer_softirq(struct softirq_action *h)
 {
 	struct tvec_base *base = __get_cpu_var(tvec_bases);
 
-	perf_event_do_pending();
-
 	hrtimer_run_pending();
 
 	if (time_after_eq(jiffies, base->timer_jiffies))
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 7ceb741..93c67bf 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -375,7 +375,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 
 	printf("%.102s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
-	printf(" Total_alloc/Per | Total_req/Per   | Hit   | Ping-pong | Frag\n");
+	printf(" Total_alloc/Per | Total_req/Per   | Hit      | Ping-pong | Frag\n");
 	printf("%.102s\n", graph_dotted_line);
 
 	next = rb_first(root);
@@ -401,7 +401,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			snprintf(buf, sizeof(buf), "%#Lx", addr);
 		printf(" %-34s |", buf);
 
-		printf(" %9llu/%-5lu | %9llu/%-5lu | %6lu | %8lu | %6.3f%%\n",
+		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
 		       (unsigned long long)data->bytes_alloc,
 		       (unsigned long)data->bytes_alloc / data->hit,
 		       (unsigned long long)data->bytes_req,
@@ -784,7 +784,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used)
 			setup_sorting(&alloc_sort, default_sort_order);
 
 		return __cmd_kmem();
-	}
+	} else
+		usage_with_options(kmem_usage, kmem_options);
 
 	return 0;
 }
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index a589a43..3f8bbcf 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -280,7 +280,7 @@ static u64 cpus_pstate_state[MAX_CPUS];
 
 static int process_comm_event(event_t *event, struct perf_session *session __used)
 {
-	pid_set_comm(event->comm.pid, event->comm.comm);
+	pid_set_comm(event->comm.tid, event->comm.comm);
 	return 0;
 }
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2009-12-31 12:00 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2009-12-31 12:00 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras, Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      perf diff: Fix usage array, it must end with a NULL entry
      perf record: We should fork only if a program was specified to run
      perf tools: Add missing header files to LIB_H Makefile variable

Heiko Carstens (1):
      kprobes: Fix distinct type warning

Tim Blechmann (1):
      perf: Rename perf_event_hw_event in design document

Wenji Huang (1):
      perf kmem: Fix statistics typo


 kernel/kprobes.c                  |    2 +-
 tools/perf/Makefile               |    8 ++++++++
 tools/perf/builtin-buildid-list.c |    2 +-
 tools/perf/builtin-diff.c         |    3 ++-
 tools/perf/builtin-kmem.c         |    4 ++--
 tools/perf/builtin-record.c       |   14 ++++++++------
 tools/perf/builtin-report.c       |    3 +--
 tools/perf/builtin-trace.c        |    4 ++--
 tools/perf/design.txt             |    8 ++++----
 9 files changed, 29 insertions(+), 19 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e5342a3..b7df302 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1035,7 +1035,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
 #ifdef CONFIG_PREEMPT
-		rp->maxactive = max(10, 2 * num_possible_cpus());
+		rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus());
 #else
 		rp->maxactive = num_possible_cpus();
 #endif
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4390d22..652a470 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -343,13 +343,18 @@ LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += util/include/asm/bitops.h
+LIB_H += util/include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
 LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
 LIB_H += perf.h
+LIB_H += util/cache.h
+LIB_H += util/callchain.h
+LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/event.h
+LIB_H += util/exec_cmd.h
 LIB_H += util/types.h
 LIB_H += util/levenshtein.h
 LIB_H += util/parse-options.h
@@ -362,6 +367,7 @@ LIB_H += util/session.h
 LIB_H += util/strbuf.h
 LIB_H += util/string.h
 LIB_H += util/strlist.h
+LIB_H += util/svghelper.h
 LIB_H += util/run-command.h
 LIB_H += util/sigchain.h
 LIB_H += util/symbol.h
@@ -370,6 +376,8 @@ LIB_H += util/values.h
 LIB_H += util/sort.h
 LIB_H += util/hist.h
 LIB_H += util/thread.h
+LIB_H += util/trace-event.h
+LIB_H += util/trace-event-perl.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index e693e67..1e99ac8 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -17,7 +17,7 @@
 static char const *input_name = "perf.data";
 static int force;
 
-static const char *const buildid_list_usage[] = {
+static const char * const buildid_list_usage[] = {
 	"perf buildid-list [<options>]",
 	NULL
 };
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 4d33b55..bd71b8c 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -189,8 +189,9 @@ out_delete:
 	return ret;
 }
 
-static const char *const diff_usage[] = {
+static const char * const diff_usage[] = {
 	"perf diff [<options>] [old_file] [new_file]",
+	NULL,
 };
 
 static const struct option options[] = {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fc21ad7..7ceb741 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -137,7 +137,7 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 	if (data && data->ptr == ptr) {
 		data->hit++;
 		data->bytes_req += bytes_req;
-		data->bytes_alloc += bytes_req;
+		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
 		if (!data)
@@ -177,7 +177,7 @@ static void insert_caller_stat(unsigned long call_site,
 	if (data && data->call_site == call_site) {
 		data->hit++;
 		data->bytes_req += bytes_req;
-		data->bytes_alloc += bytes_req;
+		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
 		if (!data)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 63136d0..2654253 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -402,7 +402,7 @@ static void atexit_header(void)
 	perf_header__write(&session->header, output, true);
 }
 
-static int __cmd_record(int argc __used, const char **argv)
+static int __cmd_record(int argc, const char **argv)
 {
 	int i, counter;
 	struct stat st;
@@ -411,6 +411,7 @@ static int __cmd_record(int argc __used, const char **argv)
 	int err;
 	unsigned long waking = 0;
 	int child_ready_pipe[2], go_pipe[2];
+	const bool forks = target_pid == -1 && argc > 0;
 	char buf;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
@@ -422,7 +423,7 @@ static int __cmd_record(int argc __used, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 
-	if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
+	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
 		perror("failed to create pipes");
 		exit(-1);
 	}
@@ -483,7 +484,7 @@ static int __cmd_record(int argc __used, const char **argv)
 
 	atexit(atexit_header);
 
-	if (target_pid == -1) {
+	if (forks) {
 		pid = fork();
 		if (pid < 0) {
 			perror("failed to fork");
@@ -550,7 +551,7 @@ static int __cmd_record(int argc __used, const char **argv)
 			return err;
 	}
 
-	if (!system_wide)
+	if (!system_wide && profile_cpu == -1)
 		event__synthesize_thread(pid, process_synthesized_event,
 					 session);
 	else
@@ -569,7 +570,8 @@ static int __cmd_record(int argc __used, const char **argv)
 	/*
 	 * Let the child rip
 	 */
-	close(go_pipe[1]);
+	if (forks)
+		close(go_pipe[1]);
 
 	for (;;) {
 		int hits = samples;
@@ -667,7 +669,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	argc = parse_options(argc, argv, options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1 && (!system_wide || profile_cpu == -1))
+	if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1)
 		usage_with_options(record_usage, options);
 
 	symbol__init();
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5c2ab53..db10c0e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -294,8 +294,7 @@ setup:
 	return 0;
 }
 
-//static const char * const report_usage[] = {
-const char * const report_usage[] = {
+static const char * const report_usage[] = {
 	"perf report [<options>] <command>",
 	NULL
 };
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e2285e2..574a215 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -512,7 +512,7 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	return path;
 }
 
-static const char * const annotate_usage[] = {
+static const char * const trace_usage[] = {
 	"perf trace [<options>] <command>",
 	NULL
 };
@@ -581,7 +581,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 
 	setup_scripting();
 
-	argc = parse_options(argc, argv, options, annotate_usage,
+	argc = parse_options(argc, argv, options, trace_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	if (symbol__init() < 0)
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index f000c30..8d0de51 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -21,7 +21,7 @@ There's one file descriptor per virtual counter used.
 The special file descriptor is opened via the perf_event_open()
 system call:
 
-   int sys_perf_event_open(struct perf_event_hw_event *hw_event_uptr,
+   int sys_perf_event_open(struct perf_event_attr *hw_event_uptr,
 			     pid_t pid, int cpu, int group_fd,
 			     unsigned long flags);
 
@@ -32,9 +32,9 @@ can be used to set the blocking mode, etc.
 Multiple counters can be kept open at a time, and the counters
 can be poll()ed.
 
-When creating a new counter fd, 'perf_event_hw_event' is:
+When creating a new counter fd, 'perf_event_attr' is:
 
-struct perf_event_hw_event {
+struct perf_event_attr {
         /*
          * The MSB of the config word signifies if the rest contains cpu
          * specific (raw) counter configuration data, if unset, the next
@@ -399,7 +399,7 @@ Notification of new events is possible through poll()/select()/epoll() and
 fcntl() managing signals.
 
 Normally a notification is generated for every page filled, however one can
-additionally set perf_event_hw_event.wakeup_events to generate one every
+additionally set perf_event_attr.wakeup_events to generate one every
 so many counter overflow events.
 
 Future work will include a splice() interface to the ring-buffer.

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2009-12-18 18:59 Ingo Molnar
  0 siblings, 0 replies; 376+ messages in thread
From: Ingo Molnar @ 2009-12-18 18:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: linux-kernel, Peter Zijlstra, Paul Mackerras, Thomas Gleixner,
	Andrew Morton

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf session: Make events_stats u64 to avoid overflow on 32-bit arches

Frederic Weisbecker (3):
      perf events, x86/stacktrace: Make stack walking optional
      perf events, x86/stacktrace: Fix performance/softlockup by providing a special frame pointer-only stack walker
      hw-breakpoints: Fix hardware breakpoints -> perf events dependency

Masami Hiramatsu (4):
      perf probe: Fix libdwarf include path for Debian
      perf probe: Check whether debugfs path is correct
      kprobe-tracer: Check new event/group name
      perf probe: Check new event name

Peter Zijlstra (1):
      perf events: Dont report side-band events on each cpu for per-task-per-cpu events

Robert P. J. Day (1):
      perf events: Remove unused perf_counter.h header file


 arch/Kconfig                      |    4 +-
 arch/x86/Kconfig                  |    2 +
 arch/x86/include/asm/stacktrace.h |   24 ++
 arch/x86/kernel/cpu/perf_event.c  |    1 +
 arch/x86/kernel/dumpstack.c       |   33 +++-
 arch/x86/kernel/dumpstack.h       |    6 -
 arch/x86/kernel/dumpstack_32.c    |    2 +-
 arch/x86/kernel/dumpstack_64.c    |    4 +-
 arch/x86/kernel/stacktrace.c      |   18 +-
 arch/x86/oprofile/backtrace.c     |    9 +-
 include/linux/perf_counter.h      |  444 -------------------------------------
 kernel/perf_event.c               |   32 ++--
 kernel/trace/trace_kprobe.c       |   31 ++-
 kernel/trace/trace_sysprof.c      |    1 +
 tools/perf/Makefile               |    3 +-
 tools/perf/builtin-probe.c        |    4 +
 tools/perf/builtin-report.c       |    2 +-
 tools/perf/util/event.h           |    4 +-
 tools/perf/util/probe-event.c     |   15 ++
 tools/perf/util/probe-finder.h    |   59 +++---
 20 files changed, 175 insertions(+), 523 deletions(-)
 delete mode 100644 include/linux/perf_counter.h

diff --git a/arch/Kconfig b/arch/Kconfig
index d828758..9d055b4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -135,9 +135,7 @@ config HAVE_DEFAULT_NO_SPIN_MUTEXES
 
 config HAVE_HW_BREAKPOINT
 	bool
-	depends on HAVE_PERF_EVENTS
-	select ANON_INODES
-	select PERF_EVENTS
+	depends on PERF_EVENTS
 
 config HAVE_USER_RETURN_NOTIFIER
 	bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3b2a5ac..55298e8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -50,6 +50,8 @@ config X86
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
 	select HAVE_HW_BREAKPOINT
+	select PERF_EVENTS
+	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
 
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index cf86a5e..35e8912 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -5,6 +5,29 @@ extern int kstack_depth_to_print;
 
 int x86_is_stack_id(int id, char *name);
 
+struct thread_info;
+struct stacktrace_ops;
+
+typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+				      unsigned long *stack,
+				      unsigned long bp,
+				      const struct stacktrace_ops *ops,
+				      void *data,
+				      unsigned long *end,
+				      int *graph);
+
+extern unsigned long
+print_context_stack(struct thread_info *tinfo,
+		    unsigned long *stack, unsigned long bp,
+		    const struct stacktrace_ops *ops, void *data,
+		    unsigned long *end, int *graph);
+
+extern unsigned long
+print_context_stack_bp(struct thread_info *tinfo,
+		       unsigned long *stack, unsigned long bp,
+		       const struct stacktrace_ops *ops, void *data,
+		       unsigned long *end, int *graph);
+
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
@@ -14,6 +37,7 @@ struct stacktrace_ops {
 	void (*address)(void *data, unsigned long address, int reliable);
 	/* On negative return stop dumping */
 	int (*stack)(void *data, char *name);
+	walk_stack_t	walk_stack;
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 45506d5..c223b7e 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2336,6 +2336,7 @@ static const struct stacktrace_ops backtrace_ops = {
 	.warning_symbol		= backtrace_warning_symbol,
 	.stack			= backtrace_stack,
 	.address		= backtrace_address,
+	.walk_stack		= print_context_stack_bp,
 };
 
 #include "../dumpstack.h"
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 0a0aa1c..c56bc28 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -109,6 +109,30 @@ print_context_stack(struct thread_info *tinfo,
 	}
 	return bp;
 }
+EXPORT_SYMBOL_GPL(print_context_stack);
+
+unsigned long
+print_context_stack_bp(struct thread_info *tinfo,
+		       unsigned long *stack, unsigned long bp,
+		       const struct stacktrace_ops *ops, void *data,
+		       unsigned long *end, int *graph)
+{
+	struct stack_frame *frame = (struct stack_frame *)bp;
+	unsigned long *ret_addr = &frame->return_address;
+
+	while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
+		unsigned long addr = *ret_addr;
+
+		if (__kernel_text_address(addr)) {
+			ops->address(data, addr, 1);
+			frame = frame->next_frame;
+			ret_addr = &frame->return_address;
+			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+		}
+	}
+	return (unsigned long)frame;
+}
+EXPORT_SYMBOL_GPL(print_context_stack_bp);
 
 
 static void
@@ -141,10 +165,11 @@ static void print_trace_address(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops print_trace_ops = {
-	.warning = print_trace_warning,
-	.warning_symbol = print_trace_warning_symbol,
-	.stack = print_trace_stack,
-	.address = print_trace_address,
+	.warning		= print_trace_warning,
+	.warning_symbol		= print_trace_warning_symbol,
+	.stack			= print_trace_stack,
+	.address		= print_trace_address,
+	.walk_stack		= print_context_stack,
 };
 
 void
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 81086c2..4fd1420 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -14,12 +14,6 @@
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
-extern unsigned long
-print_context_stack(struct thread_info *tinfo,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data,
-		unsigned long *end, int *graph);
-
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp, char *log_lvl);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index e0ed4c7..ae775ca 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -58,7 +58,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 
 		context = (struct thread_info *)
 			((unsigned long)stack & (~(THREAD_SIZE - 1)));
-		bp = print_context_stack(context, stack, bp, ops, data, NULL, &graph);
+		bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph);
 
 		stack = (unsigned long *)context->previous_esp;
 		if (!stack)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index b13af53..0ad9597 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -188,8 +188,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			if (ops->stack(data, id) < 0)
 				break;
 
-			bp = print_context_stack(tinfo, stack, bp, ops,
-						 data, estack_end, &graph);
+			bp = ops->walk_stack(tinfo, stack, bp, ops,
+					     data, estack_end, &graph);
 			ops->stack(data, "<EOE>");
 			/*
 			 * We link to the next stack via the
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index c3eb207..922eefb 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -53,17 +53,19 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops save_stack_ops = {
-	.warning = save_stack_warning,
-	.warning_symbol = save_stack_warning_symbol,
-	.stack = save_stack_stack,
-	.address = save_stack_address,
+	.warning	= save_stack_warning,
+	.warning_symbol	= save_stack_warning_symbol,
+	.stack		= save_stack_stack,
+	.address	= save_stack_address,
+	.walk_stack	= print_context_stack,
 };
 
 static const struct stacktrace_ops save_stack_ops_nosched = {
-	.warning = save_stack_warning,
-	.warning_symbol = save_stack_warning_symbol,
-	.stack = save_stack_stack,
-	.address = save_stack_address_nosched,
+	.warning	= save_stack_warning,
+	.warning_symbol	= save_stack_warning_symbol,
+	.stack		= save_stack_stack,
+	.address	= save_stack_address_nosched,
+	.walk_stack	= print_context_stack,
 };
 
 /*
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 044897b..3855096 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -41,10 +41,11 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 }
 
 static struct stacktrace_ops backtrace_ops = {
-	.warning = backtrace_warning,
-	.warning_symbol = backtrace_warning_symbol,
-	.stack = backtrace_stack,
-	.address = backtrace_address,
+	.warning	= backtrace_warning,
+	.warning_symbol	= backtrace_warning_symbol,
+	.stack		= backtrace_stack,
+	.address	= backtrace_address,
+	.walk_stack	= print_context_stack,
 };
 
 struct frame_head {
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
deleted file mode 100644
index e3fb256..0000000
--- a/include/linux/perf_counter.h
+++ /dev/null
@@ -1,444 +0,0 @@
-/*
- *  NOTE: this file will be removed in a future kernel release, it is
- *  provided as a courtesy copy of user-space code that relies on the
- *  old (pre-rename) symbols and constants.
- *
- *  Performance events:
- *
- *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
- *    Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar
- *    Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra
- *
- *  Data type definitions, declarations, prototypes.
- *
- *    Started by: Thomas Gleixner and Ingo Molnar
- *
- *  For licencing details see kernel-base/COPYING
- */
-#ifndef _LINUX_PERF_COUNTER_H
-#define _LINUX_PERF_COUNTER_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-#include <asm/byteorder.h>
-
-/*
- * User-space ABI bits:
- */
-
-/*
- * attr.type
- */
-enum perf_type_id {
-	PERF_TYPE_HARDWARE			= 0,
-	PERF_TYPE_SOFTWARE			= 1,
-	PERF_TYPE_TRACEPOINT			= 2,
-	PERF_TYPE_HW_CACHE			= 3,
-	PERF_TYPE_RAW				= 4,
-
-	PERF_TYPE_MAX,				/* non-ABI */
-};
-
-/*
- * Generalized performance counter event types, used by the
- * attr.event_id parameter of the sys_perf_counter_open()
- * syscall:
- */
-enum perf_hw_id {
-	/*
-	 * Common hardware events, generalized by the kernel:
-	 */
-	PERF_COUNT_HW_CPU_CYCLES		= 0,
-	PERF_COUNT_HW_INSTRUCTIONS		= 1,
-	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
-	PERF_COUNT_HW_CACHE_MISSES		= 3,
-	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
-	PERF_COUNT_HW_BRANCH_MISSES		= 5,
-	PERF_COUNT_HW_BUS_CYCLES		= 6,
-
-	PERF_COUNT_HW_MAX,			/* non-ABI */
-};
-
-/*
- * Generalized hardware cache counters:
- *
- *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
- *       { read, write, prefetch } x
- *       { accesses, misses }
- */
-enum perf_hw_cache_id {
-	PERF_COUNT_HW_CACHE_L1D			= 0,
-	PERF_COUNT_HW_CACHE_L1I			= 1,
-	PERF_COUNT_HW_CACHE_LL			= 2,
-	PERF_COUNT_HW_CACHE_DTLB		= 3,
-	PERF_COUNT_HW_CACHE_ITLB		= 4,
-	PERF_COUNT_HW_CACHE_BPU			= 5,
-
-	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
-};
-
-enum perf_hw_cache_op_id {
-	PERF_COUNT_HW_CACHE_OP_READ		= 0,
-	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
-	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
-
-	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
-};
-
-enum perf_hw_cache_op_result_id {
-	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
-	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
-
-	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
-};
-
-/*
- * Special "software" counters provided by the kernel, even if the hardware
- * does not support performance counters. These counters measure various
- * physical and sw events of the kernel (and allow the profiling of them as
- * well):
- */
-enum perf_sw_ids {
-	PERF_COUNT_SW_CPU_CLOCK			= 0,
-	PERF_COUNT_SW_TASK_CLOCK		= 1,
-	PERF_COUNT_SW_PAGE_FAULTS		= 2,
-	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
-	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
-	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
-	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
-	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
-	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
-
-	PERF_COUNT_SW_MAX,			/* non-ABI */
-};
-
-/*
- * Bits that can be set in attr.sample_type to request information
- * in the overflow packets.
- */
-enum perf_counter_sample_format {
-	PERF_SAMPLE_IP				= 1U << 0,
-	PERF_SAMPLE_TID				= 1U << 1,
-	PERF_SAMPLE_TIME			= 1U << 2,
-	PERF_SAMPLE_ADDR			= 1U << 3,
-	PERF_SAMPLE_READ			= 1U << 4,
-	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
-	PERF_SAMPLE_ID				= 1U << 6,
-	PERF_SAMPLE_CPU				= 1U << 7,
-	PERF_SAMPLE_PERIOD			= 1U << 8,
-	PERF_SAMPLE_STREAM_ID			= 1U << 9,
-	PERF_SAMPLE_RAW				= 1U << 10,
-
-	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
-};
-
-/*
- * The format of the data returned by read() on a perf counter fd,
- * as specified by attr.read_format:
- *
- * struct read_format {
- *	{ u64		value;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
- *	  { u64		id;           } && PERF_FORMAT_ID
- *	} && !PERF_FORMAT_GROUP
- *
- *	{ u64		nr;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
- *	  { u64		value;
- *	    { u64	id;           } && PERF_FORMAT_ID
- *	  }		cntr[nr];
- *	} && PERF_FORMAT_GROUP
- * };
- */
-enum perf_counter_read_format {
-	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
-	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
-	PERF_FORMAT_ID				= 1U << 2,
-	PERF_FORMAT_GROUP			= 1U << 3,
-
-	PERF_FORMAT_MAX = 1U << 4, 		/* non-ABI */
-};
-
-#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
-
-/*
- * Hardware event to monitor via a performance monitoring counter:
- */
-struct perf_counter_attr {
-
-	/*
-	 * Major type: hardware/software/tracepoint/etc.
-	 */
-	__u32			type;
-
-	/*
-	 * Size of the attr structure, for fwd/bwd compat.
-	 */
-	__u32			size;
-
-	/*
-	 * Type specific configuration information.
-	 */
-	__u64			config;
-
-	union {
-		__u64		sample_period;
-		__u64		sample_freq;
-	};
-
-	__u64			sample_type;
-	__u64			read_format;
-
-	__u64			disabled       :  1, /* off by default        */
-				inherit	       :  1, /* children inherit it   */
-				pinned	       :  1, /* must always be on PMU */
-				exclusive      :  1, /* only group on PMU     */
-				exclude_user   :  1, /* don't count user      */
-				exclude_kernel :  1, /* ditto kernel          */
-				exclude_hv     :  1, /* ditto hypervisor      */
-				exclude_idle   :  1, /* don't count when idle */
-				mmap           :  1, /* include mmap data     */
-				comm	       :  1, /* include comm data     */
-				freq           :  1, /* use freq, not period  */
-				inherit_stat   :  1, /* per task counts       */
-				enable_on_exec :  1, /* next exec enables     */
-				task           :  1, /* trace fork/exit       */
-				watermark      :  1, /* wakeup_watermark      */
-
-				__reserved_1   : 49;
-
-	union {
-		__u32		wakeup_events;	  /* wakeup every n events */
-		__u32		wakeup_watermark; /* bytes before wakeup   */
-	};
-	__u32			__reserved_2;
-
-	__u64			__reserved_3;
-};
-
-/*
- * Ioctls that can be done on a perf counter fd:
- */
-#define PERF_COUNTER_IOC_ENABLE		_IO ('$', 0)
-#define PERF_COUNTER_IOC_DISABLE	_IO ('$', 1)
-#define PERF_COUNTER_IOC_REFRESH	_IO ('$', 2)
-#define PERF_COUNTER_IOC_RESET		_IO ('$', 3)
-#define PERF_COUNTER_IOC_PERIOD		_IOW('$', 4, u64)
-#define PERF_COUNTER_IOC_SET_OUTPUT	_IO ('$', 5)
-#define PERF_COUNTER_IOC_SET_FILTER	_IOW('$', 6, char *)
-
-enum perf_counter_ioc_flags {
-	PERF_IOC_FLAG_GROUP		= 1U << 0,
-};
-
-/*
- * Structure of the page that can be mapped via mmap
- */
-struct perf_counter_mmap_page {
-	__u32	version;		/* version number of this structure */
-	__u32	compat_version;		/* lowest version this is compat with */
-
-	/*
-	 * Bits needed to read the hw counters in user-space.
-	 *
-	 *   u32 seq;
-	 *   s64 count;
-	 *
-	 *   do {
-	 *     seq = pc->lock;
-	 *
-	 *     barrier()
-	 *     if (pc->index) {
-	 *       count = pmc_read(pc->index - 1);
-	 *       count += pc->offset;
-	 *     } else
-	 *       goto regular_read;
-	 *
-	 *     barrier();
-	 *   } while (pc->lock != seq);
-	 *
-	 * NOTE: for obvious reason this only works on self-monitoring
-	 *       processes.
-	 */
-	__u32	lock;			/* seqlock for synchronization */
-	__u32	index;			/* hardware counter identifier */
-	__s64	offset;			/* add to hardware counter value */
-	__u64	time_enabled;		/* time counter active */
-	__u64	time_running;		/* time counter on cpu */
-
-		/*
-		 * Hole for extension of the self monitor capabilities
-		 */
-
-	__u64	__reserved[123];	/* align to 1k */
-
-	/*
-	 * Control data for the mmap() data buffer.
-	 *
-	 * User-space reading the @data_head value should issue an rmb(), on
-	 * SMP capable platforms, after reading this value -- see
-	 * perf_counter_wakeup().
-	 *
-	 * When the mapping is PROT_WRITE the @data_tail value should be
-	 * written by userspace to reflect the last read data. In this case
-	 * the kernel will not over-write unread data.
-	 */
-	__u64   data_head;		/* head in the data section */
-	__u64	data_tail;		/* user-space written tail */
-};
-
-#define PERF_EVENT_MISC_CPUMODE_MASK		(3 << 0)
-#define PERF_EVENT_MISC_CPUMODE_UNKNOWN		(0 << 0)
-#define PERF_EVENT_MISC_KERNEL			(1 << 0)
-#define PERF_EVENT_MISC_USER			(2 << 0)
-#define PERF_EVENT_MISC_HYPERVISOR		(3 << 0)
-
-struct perf_event_header {
-	__u32	type;
-	__u16	misc;
-	__u16	size;
-};
-
-enum perf_event_type {
-
-	/*
-	 * The MMAP events record the PROT_EXEC mappings so that we can
-	 * correlate userspace IPs to code. They have the following structure:
-	 *
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *
-	 *	u32				pid, tid;
-	 *	u64				addr;
-	 *	u64				len;
-	 *	u64				pgoff;
-	 *	char				filename[];
-	 * };
-	 */
-	PERF_EVENT_MMAP			= 1,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *	u64				id;
-	 *	u64				lost;
-	 * };
-	 */
-	PERF_EVENT_LOST			= 2,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *
-	 *	u32				pid, tid;
-	 *	char				comm[];
-	 * };
-	 */
-	PERF_EVENT_COMM			= 3,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *	u32				pid, ppid;
-	 *	u32				tid, ptid;
-	 *	u64				time;
-	 * };
-	 */
-	PERF_EVENT_EXIT			= 4,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *	u64				time;
-	 *	u64				id;
-	 *	u64				stream_id;
-	 * };
-	 */
-	PERF_EVENT_THROTTLE		= 5,
-	PERF_EVENT_UNTHROTTLE		= 6,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *	u32				pid, ppid;
-	 *	u32				tid, ptid;
-	 *	u64				time;
-	 * };
-	 */
-	PERF_EVENT_FORK			= 7,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *	u32				pid, tid;
-	 *
-	 *	struct read_format		values;
-	 * };
-	 */
-	PERF_EVENT_READ			= 8,
-
-	/*
-	 * struct {
-	 *	struct perf_event_header	header;
-	 *
-	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
-	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
-	 *	{ u64			time;     } && PERF_SAMPLE_TIME
-	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
-	 *	{ u64			id;	  } && PERF_SAMPLE_ID
-	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
-	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
-	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
-	 *
-	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
-	 *
-	 *	{ u64			nr,
-	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
-	 *
-	 *	#
-	 *	# The RAW record below is opaque data wrt the ABI
-	 *	#
-	 *	# That is, the ABI doesn't make any promises wrt to
-	 *	# the stability of its content, it may vary depending
-	 *	# on event, hardware, kernel version and phase of
-	 *	# the moon.
-	 *	#
-	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
-	 *	#
-	 *
-	 *	{ u32			size;
-	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
-	 * };
-	 */
-	PERF_EVENT_SAMPLE		= 9,
-
-	PERF_EVENT_MAX,			/* non-ABI */
-};
-
-enum perf_callchain_context {
-	PERF_CONTEXT_HV			= (__u64)-32,
-	PERF_CONTEXT_KERNEL		= (__u64)-128,
-	PERF_CONTEXT_USER		= (__u64)-512,
-
-	PERF_CONTEXT_GUEST		= (__u64)-2048,
-	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
-	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
-
-	PERF_CONTEXT_MAX		= (__u64)-4095,
-};
-
-#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
-#define PERF_FLAG_FD_OUTPUT		(1U << 1)
-
-/*
- * In case some app still references the old symbols:
- */
-
-#define __NR_perf_counter_open		__NR_perf_event_open
-
-#define PR_TASK_PERF_COUNTERS_DISABLE	PR_TASK_PERF_EVENTS_DISABLE
-#define PR_TASK_PERF_COUNTERS_ENABLE	PR_TASK_PERF_EVENTS_ENABLE
-
-#endif /* _LINUX_PERF_COUNTER_H */
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 8ab8698..03cc061 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1381,6 +1381,9 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
 
+		if (event->cpu != -1 && event->cpu != smp_processor_id())
+			continue;
+
 		hwc = &event->hw;
 
 		interrupts = hwc->interrupts;
@@ -3265,6 +3268,9 @@ static void perf_event_task_output(struct perf_event *event,
 
 static int perf_event_task_match(struct perf_event *event)
 {
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		return 0;
+
 	if (event->attr.comm || event->attr.mmap || event->attr.task)
 		return 1;
 
@@ -3290,12 +3296,11 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_task_ctx(&cpuctx->ctx, task_event);
-	put_cpu_var(perf_cpu_context);
-
 	if (!ctx)
 		ctx = rcu_dereference(task_event->task->perf_event_ctxp);
 	if (ctx)
 		perf_event_task_ctx(ctx, task_event);
+	put_cpu_var(perf_cpu_context);
 	rcu_read_unlock();
 }
 
@@ -3372,6 +3377,9 @@ static void perf_event_comm_output(struct perf_event *event,
 
 static int perf_event_comm_match(struct perf_event *event)
 {
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		return 0;
+
 	if (event->attr.comm)
 		return 1;
 
@@ -3408,15 +3416,10 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_comm_ctx(&cpuctx->ctx, comm_event);
-	put_cpu_var(perf_cpu_context);
-
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
 	ctx = rcu_dereference(current->perf_event_ctxp);
 	if (ctx)
 		perf_event_comm_ctx(ctx, comm_event);
+	put_cpu_var(perf_cpu_context);
 	rcu_read_unlock();
 }
 
@@ -3491,6 +3494,9 @@ static void perf_event_mmap_output(struct perf_event *event,
 static int perf_event_mmap_match(struct perf_event *event,
 				   struct perf_mmap_event *mmap_event)
 {
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		return 0;
+
 	if (event->attr.mmap)
 		return 1;
 
@@ -3564,15 +3570,10 @@ got_name:
 	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
-	put_cpu_var(perf_cpu_context);
-
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
 	ctx = rcu_dereference(current->perf_event_ctxp);
 	if (ctx)
 		perf_event_mmap_ctx(ctx, mmap_event);
+	put_cpu_var(perf_cpu_context);
 	rcu_read_unlock();
 
 	kfree(buf);
@@ -3863,6 +3864,9 @@ static int perf_swevent_match(struct perf_event *event,
 				struct perf_sample_data *data,
 				struct pt_regs *regs)
 {
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		return 0;
+
 	if (!perf_swevent_is_counting(event))
 		return 0;
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7ecab06..375f81a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -282,6 +282,18 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
 				struct pt_regs *regs);
 
+/* Check the name is good for event/group */
+static int check_event_name(const char *name)
+{
+	if (!isalpha(*name) && *name != '_')
+		return 0;
+	while (*++name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return 0;
+	}
+	return 1;
+}
+
 /*
  * Allocate new trace_probe and initialize it (including kprobes).
  */
@@ -293,10 +305,11 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 					     int nargs, int is_return)
 {
 	struct trace_probe *tp;
+	int ret = -ENOMEM;
 
 	tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
 	if (!tp)
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(ret);
 
 	if (symbol) {
 		tp->symbol = kstrdup(symbol, GFP_KERNEL);
@@ -312,14 +325,20 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	else
 		tp->rp.kp.pre_handler = kprobe_dispatcher;
 
-	if (!event)
+	if (!event || !check_event_name(event)) {
+		ret = -EINVAL;
 		goto error;
+	}
+
 	tp->call.name = kstrdup(event, GFP_KERNEL);
 	if (!tp->call.name)
 		goto error;
 
-	if (!group)
+	if (!group || !check_event_name(group)) {
+		ret = -EINVAL;
 		goto error;
+	}
+
 	tp->call.system = kstrdup(group, GFP_KERNEL);
 	if (!tp->call.system)
 		goto error;
@@ -330,7 +349,7 @@ error:
 	kfree(tp->call.name);
 	kfree(tp->symbol);
 	kfree(tp);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(ret);
 }
 
 static void free_probe_arg(struct probe_arg *arg)
@@ -695,10 +714,10 @@ static int create_trace_probe(int argc, char **argv)
 	if (!event) {
 		/* Make a new event name */
 		if (symbol)
-			snprintf(buf, MAX_EVENT_NAME_LEN, "%c@%s%+ld",
+			snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld",
 				 is_return ? 'r' : 'p', symbol, offset);
 		else
-			snprintf(buf, MAX_EVENT_NAME_LEN, "%c@0x%p",
+			snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p",
 				 is_return ? 'r' : 'p', addr);
 		event = buf;
 	}
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index f669396..a7974a5 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -93,6 +93,7 @@ static const struct stacktrace_ops backtrace_ops = {
 	.warning_symbol		= backtrace_warning_symbol,
 	.stack			= backtrace_stack,
 	.address		= backtrace_address,
+	.walk_stack		= print_context_stack,
 };
 
 static int
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7814dbb..4390d22 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -487,10 +487,11 @@ else
 	msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <libdwarf/dwarf.h>'; echo '\#include <libdwarf/libdwarf.h>'; echo 'int main(void) { Dwarf_Debug dbg; Dwarf_Error err; Dwarf_Ranges *rng; dwarf_init(0, DW_DLC_READ, 0, 0, &dbg, &err); dwarf_get_ranges(dbg, 0, &rng, 0, 0, &err); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -ldwarf -lelf -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#ifndef _MIPS_SZLONG'; echo '\#define _MIPS_SZLONG 0'; echo '\#endif'; echo '\#include <dwarf.h>'; echo '\#include <libdwarf.h>'; echo 'int main(void) { Dwarf_Debug dbg; Dwarf_Error err; Dwarf_Ranges *rng; dwarf_init(0, DW_DLC_READ, 0, 0, &dbg, &err); dwarf_get_ranges(dbg, 0, &rng, 0, 0, &err); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/libdwarf -ldwarf -lelf -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 	msg := $(warning No libdwarf.h found or old libdwarf.h found, disables dwarf support. Please install libdwarf-dev/libdwarf-devel >= 20081231);
 	BASIC_CFLAGS += -DNO_LIBDWARF
 else
+	BASIC_CFLAGS += -I/usr/include/libdwarf
 	EXTLIBS += -lelf -ldwarf
 	LIB_OBJS += util/probe-finder.o
 endif
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 7e741f5..c1e6774 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -38,6 +38,7 @@
 #include "util/strlist.h"
 #include "util/event.h"
 #include "util/debug.h"
+#include "util/debugfs.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/session.h"
@@ -205,6 +206,9 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 	if ((!session.nr_probe && !session.dellist && !session.list_events))
 		usage_with_options(probe_usage, options);
 
+	if (debugfs_valid_mountpoint(debugfs_path) < 0)
+		die("Failed to find debugfs path.");
+
 	if (session.list_events) {
 		if (session.nr_probe != 0 || session.dellist) {
 			pr_warning("  Error: Don't use --list with"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index e50a6b1..5c2ab53 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -224,7 +224,7 @@ static int __cmd_report(void)
 
 	perf_session__collapse_resort(session);
 	perf_session__output_resort(session, session->events_stats.total);
-	fprintf(stdout, "# Samples: %ld\n#\n", session->events_stats.total);
+	fprintf(stdout, "# Samples: %Ld\n#\n", session->events_stats.total);
 	perf_session__fprintf_hists(session, NULL, false, stdout);
 	if (sort_order == default_sort_order &&
 	    parent_pattern == default_parent_pattern)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8027309..690a96d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -95,8 +95,8 @@ typedef union event_union {
 } event_t;
 
 struct events_stats {
-	unsigned long total;
-	unsigned long lost;
+	u64 total;
+	u64 lost;
 };
 
 void event__print_totals(void);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2ca6215..29465d4 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -62,6 +62,18 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 	return ret;
 }
 
+/* Check the name is good for event/group */
+static bool check_event_name(const char *name)
+{
+	if (!isalpha(*name) && *name != '_')
+		return false;
+	while (*++name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return false;
+	}
+	return true;
+}
+
 /* Parse probepoint definition. */
 static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 {
@@ -82,6 +94,9 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		ptr = strchr(arg, ':');
 		if (ptr)	/* Group name is not supported yet. */
 			semantic_error("Group name is not supported yet.");
+		if (!check_event_name(arg))
+			semantic_error("%s is bad for event name -it must "
+				       "follow C symbol-naming rule.", arg);
 		pp->event = strdup(arg);
 		arg = tmp;
 	}
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 5e4050c..a4086aa 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -1,9 +1,9 @@
 #ifndef _PROBE_FINDER_H
 #define _PROBE_FINDER_H
 
-#define MAX_PATH_LEN 256
-#define MAX_PROBE_BUFFER 1024
-#define MAX_PROBES 128
+#define MAX_PATH_LEN		 256
+#define MAX_PROBE_BUFFER	1024
+#define MAX_PROBES		 128
 
 static inline int is_c_varname(const char *name)
 {
@@ -12,48 +12,53 @@ static inline int is_c_varname(const char *name)
 }
 
 struct probe_point {
-	char	*event;		/* Event name */
-	char	*group;		/* Event group */
+	char			*event;			/* Event name */
+	char			*group;			/* Event group */
 
 	/* Inputs */
-	char	*file;		/* File name */
-	int	line;		/* Line number */
+	char			*file;			/* File name */
+	int			line;			/* Line number */
 
-	char	*function;	/* Function name */
-	int	offset;		/* Offset bytes */
+	char			*function;		/* Function name */
+	int			offset;			/* Offset bytes */
 
-	int	nr_args;	/* Number of arguments */
-	char	**args;		/* Arguments */
+	int			nr_args;		/* Number of arguments */
+	char			**args;			/* Arguments */
 
-	int	retprobe;	/* Return probe */
+	int			retprobe;		/* Return probe */
 
 	/* Output */
-	int	found;		/* Number of found probe points */
-	char	*probes[MAX_PROBES];	/* Output buffers (will be allocated)*/
+	int			found;			/* Number of found probe points */
+	char			*probes[MAX_PROBES];	/* Output buffers (will be allocated)*/
 };
 
 #ifndef NO_LIBDWARF
 extern int find_probepoint(int fd, struct probe_point *pp);
 
-#include <libdwarf/dwarf.h>
-#include <libdwarf/libdwarf.h>
+/* Workaround for undefined _MIPS_SZLONG bug in libdwarf.h: */
+#ifndef _MIPS_SZLONG
+# define _MIPS_SZLONG		0
+#endif
+
+#include <dwarf.h>
+#include <libdwarf.h>
 
 struct probe_finder {
-	struct probe_point	*pp;	/* Target probe point */
+	struct probe_point	*pp;			/* Target probe point */
 
 	/* For function searching */
-	Dwarf_Addr	addr;		/* Address */
-	Dwarf_Unsigned	fno;		/* File number */
-	Dwarf_Unsigned	lno;		/* Line number */
-	Dwarf_Off	inl_offs;	/* Inline offset */
-	Dwarf_Die	cu_die;		/* Current CU */
+	Dwarf_Addr		addr;			/* Address */
+	Dwarf_Unsigned		fno;			/* File number */
+	Dwarf_Unsigned		lno;			/* Line number */
+	Dwarf_Off		inl_offs;		/* Inline offset */
+	Dwarf_Die		cu_die;			/* Current CU */
 
 	/* For variable searching */
-	Dwarf_Addr	cu_base;	/* Current CU base address */
-	Dwarf_Locdesc	fbloc;		/* Location of Current Frame Base */
-	const char	*var;		/* Current variable name */
-	char		*buf;		/* Current output buffer */
-	int		len;		/* Length of output buffer */
+	Dwarf_Addr		cu_base;		/* Current CU base address */
+	Dwarf_Locdesc		fbloc;			/* Location of Current Frame Base */
+	const char		*var;			/* Current variable name */
+	char			*buf;			/* Current output buffer */
+	int			len;			/* Length of output buffer */
 };
 #endif /* NO_LIBDWARF */
 

^ permalink raw reply related	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2009-09-22 14:59   ` Ingo Molnar
@ 2009-09-22 15:13     ` Linus Torvalds
  0 siblings, 0 replies; 376+ messages in thread
From: Linus Torvalds @ 2009-09-22 15:13 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Benjamin Herrenschmidt, linux-kernel, Paul Mackerras, Peter Zijlstra



On Tue, 22 Sep 2009, Ingo Molnar wrote:
>
> hm, i think it's mirroring - the repo itself looks good on 
> master.kernel.org:

Yeah, I see it on master, not on the public sites.

I pulled it from there and just fixed the descriptions (since I prefer the 
messages to point to the public sites that everybody can see)

		Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2009-09-22 14:49 ` Linus Torvalds
@ 2009-09-22 14:59   ` Ingo Molnar
  2009-09-22 15:13     ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2009-09-22 14:59 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Benjamin Herrenschmidt, linux-kernel, Paul Mackerras, Peter Zijlstra


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> 
> 
> On Tue, 22 Sep 2009, Ingo Molnar wrote:
> > 
> > Please pull the latest perf-fixes-for-linus git tree from:
> > 
> >    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus
> > 
> > This fixes a brown paperbag build error in PowerPC caused by the rename.
> 
> Hmm. Forgot to push? I'm getting
> 
> 	fatal: Couldn't find remote ref perf-fixes-for-linus
> 
> but maybe it's due to exta-long mirroring delays too.

hm, i think it's mirroring - the repo itself looks good on 
master.kernel.org:

[mingo@hera tip]$ hostname
hera.kernel.org
[mingo@hera tip]$ git log perf-fixes-for-linus |head
commit a8f90e906783f1f815120eefe813b23cb396e9bd
Author: Paul Mackerras <paulus@samba.org>
Date:   Tue Sep 22 09:48:08 2009 +1000

    perf_event, powerpc: Fix compilation after big perf_counter rename
    
    This fixes two places in the powerpc perf_event (perf_counter) code
    where 'list_entry' needs to be changed to 'group_entry', but were
    missed in commit 65abc865 ("perf_counter: Rename list_entry ->
    group_entry, counter_list -> group_list").

	Ingo

^ permalink raw reply	[flat|nested] 376+ messages in thread

* Re: [GIT PULL] perf fixes
  2009-09-22  7:51 Ingo Molnar
@ 2009-09-22 14:49 ` Linus Torvalds
  2009-09-22 14:59   ` Ingo Molnar
  0 siblings, 1 reply; 376+ messages in thread
From: Linus Torvalds @ 2009-09-22 14:49 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: Benjamin Herrenschmidt, linux-kernel, Paul Mackerras, Peter Zijlstra



On Tue, 22 Sep 2009, Ingo Molnar wrote:
> 
> Please pull the latest perf-fixes-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus
> 
> This fixes a brown paperbag build error in PowerPC caused by the rename.

Hmm. Forgot to push? I'm getting

	fatal: Couldn't find remote ref perf-fixes-for-linus

but maybe it's due to exta-long mirroring delays too.

		Linus

^ permalink raw reply	[flat|nested] 376+ messages in thread

* [GIT PULL] perf fixes
@ 2009-09-22  7:51 Ingo Molnar
  2009-09-22 14:49 ` Linus Torvalds
  0 siblings, 1 reply; 376+ messages in thread
From: Ingo Molnar @ 2009-09-22  7:51 UTC (permalink / raw)
  To: Linus Torvalds, Benjamin Herrenschmidt
  Cc: linux-kernel, Paul Mackerras, Peter Zijlstra

Linus,

Please pull the latest perf-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus

This fixes a brown paperbag build error in PowerPC caused by the rename.

Would it be possible for you to pull this fix as the first thing today, 
to keep it together with 43c1266, the merge commit of the rename, to 
minimize the bisection breakage window for PowerPC?

 Thanks,

	Ingo

------------------>
Paul Mackerras (1):
      perf_event, powerpc: Fix compilation after big perf_counter rename


 arch/powerpc/include/asm/perf_event.h |    4 +-
 arch/powerpc/kernel/perf_event.c      |   38 ++++++++++++++++----------------
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 2499aaa..3288ce3 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -14,7 +14,7 @@
 
 #define MAX_HWEVENTS		8
 #define MAX_EVENT_ALTERNATIVES	8
-#define MAX_LIMITED_HWEVENTS	2
+#define MAX_LIMITED_HWCOUNTERS	2
 
 /*
  * This struct provides the constants and functions needed to
@@ -22,7 +22,7 @@
  */
 struct power_pmu {
 	const char	*name;
-	int		n_event;
+	int		n_counter;
 	int		max_alternatives;
 	unsigned long	add_fields;
 	unsigned long	test_adder;
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 197b7d9..bbcbae1 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -30,8 +30,8 @@ struct cpu_hw_events {
 	u64 events[MAX_HWEVENTS];
 	unsigned int flags[MAX_HWEVENTS];
 	unsigned long mmcr[3];
-	struct perf_event *limited_event[MAX_LIMITED_HWEVENTS];
-	u8  limited_hwidx[MAX_LIMITED_HWEVENTS];
+	struct perf_event *limited_counter[MAX_LIMITED_HWCOUNTERS];
+	u8  limited_hwidx[MAX_LIMITED_HWCOUNTERS];
 	u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 	unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 	unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
@@ -253,7 +253,7 @@ static int power_check_constraints(struct cpu_hw_events *cpuhw,
 	unsigned long addf = ppmu->add_fields;
 	unsigned long tadd = ppmu->test_adder;
 
-	if (n_ev > ppmu->n_event)
+	if (n_ev > ppmu->n_counter)
 		return -1;
 
 	/* First see if the events will go on as-is */
@@ -426,7 +426,7 @@ static int is_limited_pmc(int pmcnum)
 		&& (pmcnum == 5 || pmcnum == 6);
 }
 
-static void freeze_limited_events(struct cpu_hw_events *cpuhw,
+static void freeze_limited_counters(struct cpu_hw_events *cpuhw,
 				    unsigned long pmc5, unsigned long pmc6)
 {
 	struct perf_event *event;
@@ -434,7 +434,7 @@ static void freeze_limited_events(struct cpu_hw_events *cpuhw,
 	int i;
 
 	for (i = 0; i < cpuhw->n_limited; ++i) {
-		event = cpuhw->limited_event[i];
+		event = cpuhw->limited_counter[i];
 		if (!event->hw.idx)
 			continue;
 		val = (event->hw.idx == 5) ? pmc5 : pmc6;
@@ -445,7 +445,7 @@ static void freeze_limited_events(struct cpu_hw_events *cpuhw,
 	}
 }
 
-static void thaw_limited_events(struct cpu_hw_events *cpuhw,
+static void thaw_limited_counters(struct cpu_hw_events *cpuhw,
 				  unsigned long pmc5, unsigned long pmc6)
 {
 	struct perf_event *event;
@@ -453,7 +453,7 @@ static void thaw_limited_events(struct cpu_hw_events *cpuhw,
 	int i;
 
 	for (i = 0; i < cpuhw->n_limited; ++i) {
-		event = cpuhw->limited_event[i];
+		event = cpuhw->limited_counter[i];
 		event->hw.idx = cpuhw->limited_hwidx[i];
 		val = (event->hw.idx == 5) ? pmc5 : pmc6;
 		atomic64_set(&event->hw.prev_count, val);
@@ -495,9 +495,9 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
 		       "i" (SPRN_PMC5), "i" (SPRN_PMC6));
 
 	if (mmcr0 & MMCR0_FC)
-		freeze_limited_events(cpuhw, pmc5, pmc6);
+		freeze_limited_counters(cpuhw, pmc5, pmc6);
 	else
-		thaw_limited_events(cpuhw, pmc5, pmc6);
+		thaw_limited_counters(cpuhw, pmc5, pmc6);
 
 	/*
 	 * Write the full MMCR0 including the event overflow interrupt
@@ -653,7 +653,7 @@ void hw_perf_enable(void)
 			continue;
 		idx = hwc_index[i] + 1;
 		if (is_limited_pmc(idx)) {
-			cpuhw->limited_event[n_lim] = event;
+			cpuhw->limited_counter[n_lim] = event;
 			cpuhw->limited_hwidx[n_lim] = idx;
 			++n_lim;
 			continue;
@@ -702,7 +702,7 @@ static int collect_events(struct perf_event *group, int max_count,
 		flags[n] = group->hw.event_base;
 		events[n++] = group->hw.config;
 	}
-	list_for_each_entry(event, &group->sibling_list, list_entry) {
+	list_for_each_entry(event, &group->sibling_list, group_entry) {
 		if (!is_software_event(event) &&
 		    event->state != PERF_EVENT_STATE_OFF) {
 			if (n >= max_count)
@@ -742,7 +742,7 @@ int hw_perf_group_sched_in(struct perf_event *group_leader,
 		return 0;
 	cpuhw = &__get_cpu_var(cpu_hw_events);
 	n0 = cpuhw->n_events;
-	n = collect_events(group_leader, ppmu->n_event - n0,
+	n = collect_events(group_leader, ppmu->n_counter - n0,
 			   &cpuhw->event[n0], &cpuhw->events[n0],
 			   &cpuhw->flags[n0]);
 	if (n < 0)
@@ -764,7 +764,7 @@ int hw_perf_group_sched_in(struct perf_event *group_leader,
 	cpuctx->active_oncpu += n;
 	n = 1;
 	event_sched_in(group_leader, cpu);
-	list_for_each_entry(sub, &group_leader->sibling_list, list_entry) {
+	list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
 		if (sub->state != PERF_EVENT_STATE_OFF) {
 			event_sched_in(sub, cpu);
 			++n;
@@ -797,7 +797,7 @@ static int power_pmu_enable(struct perf_event *event)
 	 */
 	cpuhw = &__get_cpu_var(cpu_hw_events);
 	n0 = cpuhw->n_events;
-	if (n0 >= ppmu->n_event)
+	if (n0 >= ppmu->n_counter)
 		goto out;
 	cpuhw->event[n0] = event;
 	cpuhw->events[n0] = event->hw.config;
@@ -848,11 +848,11 @@ static void power_pmu_disable(struct perf_event *event)
 		}
 	}
 	for (i = 0; i < cpuhw->n_limited; ++i)
-		if (event == cpuhw->limited_event[i])
+		if (event == cpuhw->limited_counter[i])
 			break;
 	if (i < cpuhw->n_limited) {
 		while (++i < cpuhw->n_limited) {
-			cpuhw->limited_event[i-1] = cpuhw->limited_event[i];
+			cpuhw->limited_counter[i-1] = cpuhw->limited_counter[i];
 			cpuhw->limited_hwidx[i-1] = cpuhw->limited_hwidx[i];
 		}
 		--cpuhw->n_limited;
@@ -1078,7 +1078,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	 */
 	n = 0;
 	if (event->group_leader != event) {
-		n = collect_events(event->group_leader, ppmu->n_event - 1,
+		n = collect_events(event->group_leader, ppmu->n_counter - 1,
 				   ctrs, events, cflags);
 		if (n < 0)
 			return ERR_PTR(-EINVAL);
@@ -1230,7 +1230,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 	int nmi;
 
 	if (cpuhw->n_limited)
-		freeze_limited_events(cpuhw, mfspr(SPRN_PMC5),
+		freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
 					mfspr(SPRN_PMC6));
 
 	perf_read_regs(regs);
@@ -1260,7 +1260,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 	 * Any that we processed in the previous loop will not be negative.
 	 */
 	if (!found) {
-		for (i = 0; i < ppmu->n_event; ++i) {
+		for (i = 0; i < ppmu->n_counter; ++i) {
 			if (is_limited_pmc(i + 1))
 				continue;
 			val = read_pmc(i + 1);

^ permalink raw reply related	[flat|nested] 376+ messages in thread

end of thread, other threads:[~2023-01-06 21:19 UTC | newest]

Thread overview: 376+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-05-05 12:47 [GIT PULL] perf fixes Ingo Molnar
2019-05-05 22:10 ` pr-tracker-bot
  -- strict thread matches above, loose matches on Subject: below --
2023-01-06 11:57 Ingo Molnar
2023-01-06 21:19 ` pr-tracker-bot
2022-10-02 10:56 Ingo Molnar
2022-10-02 16:47 ` Linus Torvalds
2022-10-03 10:55   ` Ingo Molnar
2022-10-02 17:20 ` pr-tracker-bot
2022-08-28 14:35 Ingo Molnar
2022-08-28 18:18 ` pr-tracker-bot
2022-08-06 19:10 Ingo Molnar
2022-08-07  0:50 ` pr-tracker-bot
2021-07-11 13:26 Ingo Molnar
2021-07-11 18:22 ` pr-tracker-bot
2021-06-12 12:48 Ingo Molnar
2021-06-12 19:09 ` pr-tracker-bot
2021-03-21 10:56 Ingo Molnar
2021-03-21 18:45 ` pr-tracker-bot
2020-08-15 11:21 Ingo Molnar
2020-08-16  1:55 ` pr-tracker-bot
2020-04-25  9:19 Ingo Molnar
2020-04-25 19:30 ` pr-tracker-bot
2020-03-24  9:19 Ingo Molnar
2020-03-24 17:15 ` pr-tracker-bot
2020-03-02  7:23 Ingo Molnar
2020-03-03 23:35 ` pr-tracker-bot
2020-02-15  8:53 Ingo Molnar
2020-02-15 21:25 ` pr-tracker-bot
2020-01-18 17:58 Ingo Molnar
2020-01-18 21:05 ` pr-tracker-bot
2019-12-21 16:16 Ingo Molnar
2019-12-21 18:55 ` pr-tracker-bot
2019-12-17 11:34 Ingo Molnar
2019-12-17 19:06 ` Linus Torvalds
2019-12-18  6:58   ` Ingo Molnar
2019-12-17 19:20 ` pr-tracker-bot
2019-12-01 22:15 Ingo Molnar
2019-12-02  4:40 ` pr-tracker-bot
2019-11-16 21:33 Ingo Molnar
2019-11-17  0:35 ` pr-tracker-bot
2019-11-01 17:48 Ingo Molnar
2019-11-01 18:48 ` Linus Torvalds
2019-11-01 20:30   ` Ingo Molnar
2019-11-01 21:01     ` Ingo Molnar
2019-11-01 22:15     ` Linus Torvalds
2019-11-01 19:10 ` pr-tracker-bot
2019-10-12 13:31 Ingo Molnar
2019-10-12 22:35 ` pr-tracker-bot
2019-07-14 12:01 Ingo Molnar
2019-07-14 18:45 ` pr-tracker-bot
2019-06-29  8:54 Ingo Molnar
2019-06-29 11:45 ` pr-tracker-bot
2019-06-02 17:39 Ingo Molnar
2019-06-02 18:15 ` pr-tracker-bot
2019-05-16 16:05 Ingo Molnar
2019-05-16 18:20 ` pr-tracker-bot
2019-04-20  7:43 Ingo Molnar
2019-04-20 19:25 ` pr-tracker-bot
2019-04-12 13:06 Ingo Molnar
2019-04-13  4:05 ` pr-tracker-bot
2019-02-17 10:10 Ingo Molnar
2019-02-17 16:50 ` pr-tracker-bot
2019-02-10  9:01 Ingo Molnar
2019-02-10 18:30 ` pr-tracker-bot
2019-01-11  7:44 Ingo Molnar
2019-01-11 18:00 ` pr-tracker-bot
2018-11-30  6:25 Ingo Molnar
2018-11-30 21:00 ` pr-tracker-bot
2018-11-17 10:55 Ingo Molnar
2018-11-18 20:05 ` pr-tracker-bot
2018-10-20  8:10 Ingo Molnar
2018-10-20 13:28 ` Greg Kroah-Hartman
2018-10-11  9:12 Ingo Molnar
2018-10-11 12:32 ` Greg Kroah-Hartman
2018-10-11  8:59 Ingo Molnar
2018-10-05  9:42 Ingo Molnar
2018-10-05  9:55 ` Ingo Molnar
2018-10-05 23:30   ` Greg Kroah-Hartman
2018-09-15 13:11 Ingo Molnar
2018-07-30 17:53 Ingo Molnar
2018-07-13 19:59 Ingo Molnar
2018-06-30  8:44 Ingo Molnar
2018-06-04  9:04 Ingo Molnar
2018-03-31 10:40 Ingo Molnar
2018-03-25  8:53 Ingo Molnar
2018-02-06 21:29 Ingo Molnar
2017-12-06 22:17 Ingo Molnar
2017-11-26 12:40 Ingo Molnar
2017-11-05 14:40 Ingo Molnar
2017-11-09  8:13 ` Markus Trippelsdorf
2017-10-14 16:04 Ingo Molnar
2017-09-13 18:00 Ingo Molnar
2017-09-12 15:32 Ingo Molnar
2017-07-21 10:15 Ingo Molnar
2017-06-10  8:39 Ingo Molnar
2017-05-12  7:31 Ingo Molnar
2017-03-07 20:30 Ingo Molnar
2017-02-28  8:01 Ingo Molnar
2017-02-11 18:12 Ingo Molnar
2017-02-02 21:01 Ingo Molnar
2017-01-18  9:27 Ingo Molnar
2017-01-15  9:59 Ingo Molnar
2016-12-23 22:50 Ingo Molnar
2016-12-07 18:45 Ingo Molnar
2016-11-23  9:00 Ingo Molnar
2016-11-14  7:56 Ingo Molnar
2016-10-28 19:41 Ingo Molnar
2016-10-18 11:07 Ingo Molnar
2016-09-13 18:14 Ingo Molnar
2016-08-18 20:38 Ingo Molnar
2016-08-12 19:35 Ingo Molnar
2016-07-26 14:13 Ingo Molnar
2016-07-08 13:42 Ingo Molnar
2016-06-10 12:50 Ingo Molnar
2016-05-13 18:51 Ingo Molnar
2016-05-06 11:26 Ingo Molnar
2016-04-28 17:56 Ingo Molnar
2016-04-03 11:00 Ingo Molnar
2016-02-20 11:14 Ingo Molnar
2016-01-14 10:03 Ingo Molnar
2016-01-08 12:46 Ingo Molnar
2015-12-08  4:22 Ingo Molnar
2015-09-17  8:02 Ingo Molnar
2015-09-02 18:11 Ingo Molnar
2015-08-22 12:19 Ingo Molnar
2015-08-14  7:12 Ingo Molnar
2015-07-18  2:53 Ingo Molnar
2015-07-06 15:29 Ingo Molnar
2015-06-13 14:29 Ingo Molnar
2015-06-05  8:37 Ingo Molnar
2015-05-15  7:17 Ingo Molnar
2015-05-06 12:52 Ingo Molnar
2015-04-03 13:11 Ingo Molnar
2015-03-17 16:48 Ingo Molnar
2015-03-01 17:00 Ingo Molnar
2015-02-20 13:40 Ingo Molnar
2015-01-30 18:44 Ingo Molnar
2015-01-17 14:15 Ingo Molnar
2015-01-11  8:42 Ingo Molnar
2014-11-20  7:46 Ingo Molnar
2014-10-31 11:13 Ingo Molnar
2014-11-03  9:02 ` Paul Bolle
2014-11-03 10:04   ` Peter Zijlstra
2014-09-19 10:46 Ingo Molnar
2014-08-24 20:25 Ingo Molnar
2014-07-16 11:11 Ingo Molnar
2014-06-18 16:39 Ingo Molnar
2014-05-22  8:04 Ingo Molnar
2014-05-01  6:34 Ingo Molnar
2014-04-20  8:02 Ingo Molnar
2014-04-19 10:41 Ingo Molnar
2014-04-16 13:04 Ingo Molnar
2014-03-22  9:06 Ingo Molnar
2014-03-16 16:34 Ingo Molnar
2014-03-02  8:51 Ingo Molnar
2014-02-22 19:16 Ingo Molnar
2014-02-09  8:01 Ingo Molnar
2014-01-25  7:30 Ingo Molnar
2014-01-19 12:08 Ingo Molnar
2013-12-19 16:52 Ingo Molnar
2013-12-02 14:39 Ingo Molnar
2013-11-15 19:46 Ingo Molnar
2013-11-01  9:56 Ingo Molnar
2013-10-29 10:04 Ingo Molnar
2013-10-26 12:24 Ingo Molnar
2013-10-28  8:28 ` Markus Trippelsdorf
2013-10-28  9:02   ` ------------------------------ Markus Trippelsdorf
2013-10-28  9:34     ` Markus Trippelsdorf
2013-10-28 12:34       ` Arnaldo Carvalho de Melo
2013-10-28 12:42         ` Arnaldo Carvalho de Melo
2013-10-28 12:59           ` Markus Trippelsdorf
2013-10-29  9:50           ` Stephane Eranian
2013-10-29 10:06             ` Ingo Molnar
2013-10-29 12:47             ` Arnaldo Carvalho de Melo
2013-10-08 12:12 Ingo Molnar
2013-09-28 18:03 Ingo Molnar
2013-09-29 11:47 ` Markus Trippelsdorf
2013-09-29 21:33   ` Andi Kleen
2013-09-29 22:47     ` Markus Trippelsdorf
2013-09-30  6:27     ` Ingo Molnar
2013-09-30 18:54       ` Andi Kleen
2013-10-01  8:42         ` Ingo Molnar
2013-09-25 18:00 Ingo Molnar
2013-09-18 16:06 Ingo Molnar
2013-09-12 13:38 Ingo Molnar
2013-09-12 18:03 ` Linus Torvalds
2013-09-12 18:10   ` Linus Torvalds
2013-09-12 18:43     ` Arnaldo Carvalho de Melo
2013-09-12 19:12       ` Arnaldo Carvalho de Melo
2013-09-12 19:13         ` Linus Torvalds
2013-09-12 19:55       ` Ingo Molnar
2013-09-12 19:58       ` David Ahern
2013-09-12 20:02         ` Arnaldo Carvalho de Melo
2013-09-12 20:31           ` Ingo Molnar
2013-09-12 20:43             ` Ingo Molnar
2013-09-12 20:18         ` Ingo Molnar
2013-09-12 20:38           ` Arnaldo Carvalho de Melo
2013-09-12 20:46             ` Ingo Molnar
2013-09-12 21:09               ` David Ahern
2013-09-12 21:18                 ` Ingo Molnar
2013-09-12 22:10                   ` David Ahern
2013-09-13  5:09                     ` Ingo Molnar
2013-09-13  9:32                       ` Jean Pihet
2013-09-13  9:45                         ` Ingo Molnar
2013-09-13 17:15                           ` Jean Pihet
2013-09-12 18:51     ` Linus Torvalds
2013-09-12 20:33       ` Ingo Molnar
2013-09-12 20:38         ` Linus Torvalds
2013-09-12 20:49           ` Ingo Molnar
2013-09-12 20:52             ` Linus Torvalds
2013-09-12 21:01               ` Ingo Molnar
2013-09-12 20:10     ` Ingo Molnar
2013-08-13 16:51 Ingo Molnar
2013-07-10  8:52 Ingo Molnar
2013-06-26  8:52 Ingo Molnar
2013-06-20  8:58 Ingo Molnar
2013-05-05 10:10 Ingo Molnar
2013-04-21  8:16 Ingo Molnar
2013-04-14 15:20 Ingo Molnar
2013-03-21  9:56 Ingo Molnar
2013-03-11 14:28 Ingo Molnar
2013-02-26  7:02 Ingo Molnar
2013-03-14 20:32 ` Linus Torvalds
2013-03-14 21:06   ` Linus Torvalds
2013-03-14 22:09     ` Stephane Eranian
2013-03-14 22:17       ` Linus Torvalds
2013-03-14 22:19         ` Stephane Eranian
2013-03-14 22:42           ` Stephane Eranian
2013-03-14 22:53             ` Stephane Eranian
2013-03-14 23:11               ` Stephane Eranian
2013-03-15  0:24                 ` Stephane Eranian
2013-03-15  1:06                   ` Linus Torvalds
2013-03-15  8:01                     ` Stephane Eranian
2013-03-15 10:50                       ` Stephane Eranian
2013-02-04 18:20 Ingo Molnar
2012-12-01 11:11 Ingo Molnar
2012-10-26 14:44 Ingo Molnar
2012-10-23 11:02 Ingo Molnar
2012-10-20  0:56 Ingo Molnar
2012-09-21 19:08 Ingo Molnar
2012-09-13 14:39 Ingo Molnar
2012-08-23 10:59 Ingo Molnar
2012-08-20  9:08 Ingo Molnar
2012-08-21  7:59 ` Ingo Molnar
2012-08-05 17:43 Ingo Molnar
2012-08-03 16:40 Ingo Molnar
2012-07-14  7:51 Ingo Molnar
2012-06-22 13:36 Ingo Molnar
2012-06-22 18:07 ` Linus Torvalds
2012-06-22 18:38   ` Hagen Paul Pfeifer
2012-06-22 18:52     ` Linus Torvalds
2012-06-22 19:06       ` Hagen Paul Pfeifer
2012-06-22 19:54         ` Steven Rostedt
     [not found]           ` <86448d73-2e19-416f-8104-ce72aa5d76eb@email.android.com>
2012-06-22 23:18             ` Steven Rostedt
2012-06-23  0:51               ` Arjan van de Ven
2012-06-23  1:57                 ` Steven Rostedt
2012-06-23 18:25                 ` H. Peter Anvin
2012-06-22 18:50   ` Steven Rostedt
2012-06-15 18:48 Ingo Molnar
2012-06-08  9:20 Ingo Molnar
2012-05-30 15:39 Ingo Molnar
2012-05-17  8:19 Ingo Molnar
2012-04-27  6:32 Ingo Molnar
2012-04-16 17:48 Ingo Molnar
2012-04-14 10:54 Ingo Molnar
2012-04-03 22:40 Ingo Molnar
2012-03-13 16:56 Ingo Molnar
2012-03-05  9:27 Ingo Molnar
2012-03-02 10:47 Ingo Molnar
2012-02-10 12:45 Ingo Molnar
2012-02-02 10:00 Ingo Molnar
2012-01-26 18:11 Ingo Molnar
2011-12-29 21:02 Ingo Molnar
2011-12-09  6:16 Ingo Molnar
2011-12-05 19:13 Ingo Molnar
2011-11-07 18:49 Ingo Molnar
2011-11-07 19:00 ` Linus Torvalds
2011-11-07 19:50   ` Ingo Molnar
2011-08-22 17:00 Ingo Molnar
2011-08-11  8:17 Ingo Molnar
2011-07-07 18:11 Ingo Molnar
2011-06-19  8:44 Ingo Molnar
2011-06-13  9:53 Ingo Molnar
2011-06-08 13:46 Ingo Molnar
2011-05-28 16:34 Ingo Molnar
2011-05-24  2:41 Ingo Molnar
2011-05-23 13:41 Ingo Molnar
2011-05-23 22:10 ` Eric Dumazet
2011-05-23 22:19   ` Frederic Weisbecker
2011-05-23 22:22     ` Eric Dumazet
2011-05-20 17:18 Ingo Molnar
2011-05-17 22:07 Ingo Molnar
2011-05-07 18:20 Ingo Molnar
2011-04-29 18:17 Ingo Molnar
2011-04-22 13:42 Ingo Molnar
2011-04-19 15:56 Ingo Molnar
2011-04-16 10:03 Ingo Molnar
2011-04-07 17:48 Ingo Molnar
2011-04-02 10:25 Ingo Molnar
2011-03-25 13:11 Ingo Molnar
2011-03-10  7:53 Ingo Molnar
2011-02-28 17:34 Ingo Molnar
2011-02-22 16:03 Ingo Molnar
2011-02-15 16:58 Ingo Molnar
2011-02-06 11:27 Ingo Molnar
2011-02-03 15:47 Ingo Molnar
2011-01-24 13:34 Ingo Molnar
2011-01-24 19:48 ` Linus Torvalds
2011-01-24 20:07   ` Ingo Molnar
2011-01-24 20:11     ` Ingo Molnar
2011-01-24 20:17       ` Ingo Molnar
2011-01-24 20:17     ` Linus Torvalds
2011-01-24 20:27       ` Linus Torvalds
2011-01-24 20:38         ` Arnaldo Carvalho de Melo
2011-01-24 21:13           ` Linus Torvalds
2011-01-24 21:25           ` Ingo Molnar
2011-01-24 22:00             ` Arnaldo Carvalho de Melo
2011-01-25  0:16               ` Ingo Molnar
2011-01-24 20:37       ` Davidlohr Bueso
2011-01-24 20:14   ` Arnaldo Carvalho de Melo
2011-01-18 18:59 Ingo Molnar
2011-01-18  9:42 Ingo Molnar
2011-01-15 15:24 Ingo Molnar
2011-01-11 11:32 Ingo Molnar
2011-01-03 19:04 Ingo Molnar
2010-12-23 12:56 Ingo Molnar
2010-12-19 15:34 Ingo Molnar
2010-12-08  7:55 Ingo Molnar
2010-11-28 17:36 Ingo Molnar
2010-11-26 13:20 Ingo Molnar
2010-11-11 10:38 Ingo Molnar
2010-10-30 18:21 Ingo Molnar
2010-10-13 15:21 Ingo Molnar
2010-10-05 14:49 Ingo Molnar
2010-09-26  8:38 Ingo Molnar
2010-09-21 19:39 Ingo Molnar
2010-09-10 14:26 Ingo Molnar
2010-08-25 17:44 Ingo Molnar
2010-08-24 19:06 Ingo Molnar
2010-08-19 14:55 Ingo Molnar
2010-08-18  8:14 Ingo Molnar
2010-07-23 19:41 Ingo Molnar
2010-07-16 17:30 Ingo Molnar
2010-07-08  4:36 Frederic Weisbecker
2010-07-08  4:40 ` Frederic Weisbecker
2010-07-08  6:36 ` Ingo Molnar
2010-07-04 20:24 Ingo Molnar
2010-06-10 10:25 Ingo Molnar
2010-06-02 12:28 Ingo Molnar
2010-05-31 23:02 Frederic Weisbecker
2010-06-01  6:59 ` Ingo Molnar
2010-05-30 19:27 Ingo Molnar
2010-05-20  9:44 Frederic Weisbecker
2010-05-20 12:40 ` Ingo Molnar
2010-05-11 19:18 Ingo Molnar
2010-05-12  0:39 ` Linus Torvalds
2010-04-06 17:49 Ingo Molnar
2010-04-04 10:15 Ingo Molnar
2010-04-03 10:47 Frederic Weisbecker
2010-03-28  5:11 Frederic Weisbecker
2010-03-29  3:33 ` Ingo Molnar
2010-03-26 15:16 Ingo Molnar
2010-03-16 16:06 Ingo Molnar
2010-03-11 19:12 Ingo Molnar
2010-02-22 16:50 Ingo Molnar
2010-02-22 17:01 ` Linus Torvalds
2010-02-22 17:15   ` Frederic Weisbecker
2010-02-14  9:06 Ingo Molnar
2010-01-31 17:32 Ingo Molnar
2010-01-21 15:38 Ingo Molnar
2009-12-31 12:00 Ingo Molnar
2009-12-18 18:59 Ingo Molnar
2009-09-22  7:51 Ingo Molnar
2009-09-22 14:49 ` Linus Torvalds
2009-09-22 14:59   ` Ingo Molnar
2009-09-22 15:13     ` Linus Torvalds

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).