[PATCH v3 0/3] csky: perf callchain dwarf support

[PATCH v3 0/3] csky: perf callchain dwarf support

[Mao Han]

This patch set add perf DWARF unwinding support for C-SKY.
Including user registers/stack dump API, and libdw support.

CC: Peter Zijlstra <peterz@infradead.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: Arnaldo Carvalho de Melo <acme@kernel.org>
CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
CC: Jiri Olsa <jolsa@redhat.com>
CC: Namhyung Kim <namhyung@kernel.org>
CC: Guo Ren <guoren@kernel.org>

Changes since v2:
  - use same registers name as struct pt_regs
  - code convention

Changes since v1:
  - seperate the callchain support using frame pointer

Mao Han (3):
  perf: use hweight64 instead of hweight_long
  csky: Add support for perf registers sampling
  csky: add support for libdw

 arch/csky/Kconfig                            |   2 +
 arch/csky/include/uapi/asm/perf_regs.h       |  51 ++++++++++++++
 arch/csky/kernel/Makefile                    |   1 +
 arch/csky/kernel/perf_regs.c                 |  40 +++++++++++
 tools/arch/csky/include/uapi/asm/perf_regs.h |  51 ++++++++++++++
 tools/perf/Makefile.config                   |   6 +-
 tools/perf/arch/csky/Build                   |   1 +
 tools/perf/arch/csky/Makefile                |   3 +
 tools/perf/arch/csky/include/perf_regs.h     | 100 +++++++++++++++++++++++++++
 tools/perf/arch/csky/util/Build              |   2 +
 tools/perf/arch/csky/util/dwarf-regs.c       |  49 +++++++++++++
 tools/perf/arch/csky/util/unwind-libdw.c     |  78 +++++++++++++++++++++
 tools/perf/util/evsel.c                      |   2 +-
 13 files changed, 384 insertions(+), 2 deletions(-)
 create mode 100644 arch/csky/include/uapi/asm/perf_regs.h
 create mode 100644 arch/csky/kernel/perf_regs.c
 create mode 100644 tools/arch/csky/include/uapi/asm/perf_regs.h
 create mode 100644 tools/perf/arch/csky/Build
 create mode 100644 tools/perf/arch/csky/Makefile
 create mode 100644 tools/perf/arch/csky/include/perf_regs.h
 create mode 100644 tools/perf/arch/csky/util/Build
 create mode 100644 tools/perf/arch/csky/util/dwarf-regs.c
 create mode 100644 tools/perf/arch/csky/util/unwind-libdw.c

-- 
2.7.4

[PATCH v3 1/3] perf: use hweight64 instead of hweight_long

[Mao Han]

On 32-bits platform with more than 32 registers, the 64 bits mask is
truncate to the lower 32 bits and the return value of hweight_long will
always smaller than 32. When kernel outputs more than 32 registers, but
the user perf program only counts 32, there will be a data mismatch
result to overflow check fail.

CC: Peter Zijlstra <peterz@infradead.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: Arnaldo Carvalho de Melo <acme@kernel.org>
CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
CC: Jiri Olsa <jolsa@redhat.com>
CC: Namhyung Kim <namhyung@kernel.org>

Signed-off-by: Mao Han <han_mao@c-sky.com>
---
 tools/perf/util/evsel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7835e05..73c78be 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2322,7 +2322,7 @@ 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;
-- 
2.7.4

[PATCH v3 2/3] csky: Add support for perf registers sampling

[Mao Han]

This patch implements the perf registers sampling and validation API
for csky arch. The valid registers and their register ID are defined in
perf_regs.h. Perf tool can backtrace in userspace with unwind library
and the registers/user stack dump support.

CC: Guo Ren <guoren@kernel.org>

Signed-off-by: Mao Han <han_mao@c-sky.com>
---
 arch/csky/Kconfig                      |  2 ++
 arch/csky/include/uapi/asm/perf_regs.h | 51 ++++++++++++++++++++++++++++++++++
 arch/csky/kernel/Makefile              |  1 +
 arch/csky/kernel/perf_regs.c           | 40 ++++++++++++++++++++++++++
 4 files changed, 94 insertions(+)
 create mode 100644 arch/csky/include/uapi/asm/perf_regs.h
 create mode 100644 arch/csky/kernel/perf_regs.c

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index c4974cf..8e45c7a 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -38,6 +38,8 @@ config CSKY
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/csky/include/uapi/asm/perf_regs.h b/arch/csky/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..ee323d8
--- /dev/null
+++ b/arch/csky/include/uapi/asm/perf_regs.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#ifndef _ASM_CSKY_PERF_REGS_H
+#define _ASM_CSKY_PERF_REGS_H
+
+/* Index of struct pt_regs */
+enum perf_event_csky_regs {
+	PERF_REG_CSKY_TLS,
+	PERF_REG_CSKY_LR,
+	PERF_REG_CSKY_PC,
+	PERF_REG_CSKY_SR,
+	PERF_REG_CSKY_SP,
+	PERF_REG_CSKY_ORIG_A0,
+	PERF_REG_CSKY_A0,
+	PERF_REG_CSKY_A1,
+	PERF_REG_CSKY_A2,
+	PERF_REG_CSKY_A3,
+	PERF_REG_CSKY_REGS0,
+	PERF_REG_CSKY_REGS1,
+	PERF_REG_CSKY_REGS2,
+	PERF_REG_CSKY_REGS3,
+	PERF_REG_CSKY_REGS4,
+	PERF_REG_CSKY_REGS5,
+	PERF_REG_CSKY_REGS6,
+	PERF_REG_CSKY_REGS7,
+	PERF_REG_CSKY_REGS8,
+	PERF_REG_CSKY_REGS9,
+#if defined(__CSKYABIV2__)
+	PERF_REG_CSKY_EXREGS0,
+	PERF_REG_CSKY_EXREGS1,
+	PERF_REG_CSKY_EXREGS2,
+	PERF_REG_CSKY_EXREGS3,
+	PERF_REG_CSKY_EXREGS4,
+	PERF_REG_CSKY_EXREGS5,
+	PERF_REG_CSKY_EXREGS6,
+	PERF_REG_CSKY_EXREGS7,
+	PERF_REG_CSKY_EXREGS8,
+	PERF_REG_CSKY_EXREGS9,
+	PERF_REG_CSKY_EXREGS10,
+	PERF_REG_CSKY_EXREGS11,
+	PERF_REG_CSKY_EXREGS12,
+	PERF_REG_CSKY_EXREGS13,
+	PERF_REG_CSKY_EXREGS14,
+	PERF_REG_CSKY_HI,
+	PERF_REG_CSKY_LO,
+	PERF_REG_CSKY_DCSR,
+#endif
+	PERF_REG_CSKY_MAX,
+};
+#endif /* _ASM_CSKY_PERF_REGS_H */
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
index 4c462f5..1624b04 100644
--- a/arch/csky/kernel/Makefile
+++ b/arch/csky/kernel/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o
 obj-$(CONFIG_STACKTRACE)		+= stacktrace.o
 obj-$(CONFIG_CSKY_PMU_V1)		+= perf_event.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_callchain.o
+obj-$(CONFIG_HAVE_PERF_REGS)            += perf_regs.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c
new file mode 100644
index 0000000..88f1875
--- /dev/null
+++ b/arch/csky/kernel/perf_regs.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_CSKY_MAX))
+		return 0;
+
+	return ((long *)regs)[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_CSKY_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+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);
+}
-- 
2.7.4

[PATCH v3 3/3] csky: add support for libdw

[Mao Han]

This patch add support for DWARF register mappings and libdw registers
initialization, which is used by perf callchain analyzing when
--call-graph=dwarf is given.

CC: Peter Zijlstra <peterz@infradead.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: Arnaldo Carvalho de Melo <acme@kernel.org>
CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
CC: Jiri Olsa <jolsa@redhat.com>
CC: Namhyung Kim <namhyung@kernel.org>

Signed-off-by: Mao Han <han_mao@c-sky.com>
---
 tools/arch/csky/include/uapi/asm/perf_regs.h |  51 ++++++++++++++
 tools/perf/Makefile.config                   |   6 +-
 tools/perf/arch/csky/Build                   |   1 +
 tools/perf/arch/csky/Makefile                |   3 +
 tools/perf/arch/csky/include/perf_regs.h     | 100 +++++++++++++++++++++++++++
 tools/perf/arch/csky/util/Build              |   2 +
 tools/perf/arch/csky/util/dwarf-regs.c       |  49 +++++++++++++
 tools/perf/arch/csky/util/unwind-libdw.c     |  78 +++++++++++++++++++++
 8 files changed, 289 insertions(+), 1 deletion(-)
 create mode 100644 tools/arch/csky/include/uapi/asm/perf_regs.h
 create mode 100644 tools/perf/arch/csky/Build
 create mode 100644 tools/perf/arch/csky/Makefile
 create mode 100644 tools/perf/arch/csky/include/perf_regs.h
 create mode 100644 tools/perf/arch/csky/util/Build
 create mode 100644 tools/perf/arch/csky/util/dwarf-regs.c
 create mode 100644 tools/perf/arch/csky/util/unwind-libdw.c

diff --git a/tools/arch/csky/include/uapi/asm/perf_regs.h b/tools/arch/csky/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..ee323d8
--- /dev/null
+++ b/tools/arch/csky/include/uapi/asm/perf_regs.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#ifndef _ASM_CSKY_PERF_REGS_H
+#define _ASM_CSKY_PERF_REGS_H
+
+/* Index of struct pt_regs */
+enum perf_event_csky_regs {
+	PERF_REG_CSKY_TLS,
+	PERF_REG_CSKY_LR,
+	PERF_REG_CSKY_PC,
+	PERF_REG_CSKY_SR,
+	PERF_REG_CSKY_SP,
+	PERF_REG_CSKY_ORIG_A0,
+	PERF_REG_CSKY_A0,
+	PERF_REG_CSKY_A1,
+	PERF_REG_CSKY_A2,
+	PERF_REG_CSKY_A3,
+	PERF_REG_CSKY_REGS0,
+	PERF_REG_CSKY_REGS1,
+	PERF_REG_CSKY_REGS2,
+	PERF_REG_CSKY_REGS3,
+	PERF_REG_CSKY_REGS4,
+	PERF_REG_CSKY_REGS5,
+	PERF_REG_CSKY_REGS6,
+	PERF_REG_CSKY_REGS7,
+	PERF_REG_CSKY_REGS8,
+	PERF_REG_CSKY_REGS9,
+#if defined(__CSKYABIV2__)
+	PERF_REG_CSKY_EXREGS0,
+	PERF_REG_CSKY_EXREGS1,
+	PERF_REG_CSKY_EXREGS2,
+	PERF_REG_CSKY_EXREGS3,
+	PERF_REG_CSKY_EXREGS4,
+	PERF_REG_CSKY_EXREGS5,
+	PERF_REG_CSKY_EXREGS6,
+	PERF_REG_CSKY_EXREGS7,
+	PERF_REG_CSKY_EXREGS8,
+	PERF_REG_CSKY_EXREGS9,
+	PERF_REG_CSKY_EXREGS10,
+	PERF_REG_CSKY_EXREGS11,
+	PERF_REG_CSKY_EXREGS12,
+	PERF_REG_CSKY_EXREGS13,
+	PERF_REG_CSKY_EXREGS14,
+	PERF_REG_CSKY_HI,
+	PERF_REG_CSKY_LO,
+	PERF_REG_CSKY_DCSR,
+#endif
+	PERF_REG_CSKY_MAX,
+};
+#endif /* _ASM_CSKY_PERF_REGS_H */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fe3f97e..42985ae 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -59,6 +59,10 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(SRCARCH),csky)
+  NO_PERF_REGS := 0
+endif
+
 ifeq ($(ARCH),s390)
   NO_PERF_REGS := 0
   NO_SYSCALL_TABLE := 0
@@ -77,7 +81,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
diff --git a/tools/perf/arch/csky/Build b/tools/perf/arch/csky/Build
new file mode 100644
index 0000000..e4e5f33
--- /dev/null
+++ b/tools/perf/arch/csky/Build
@@ -0,0 +1 @@
+perf-y += util/
diff --git a/tools/perf/arch/csky/Makefile b/tools/perf/arch/csky/Makefile
new file mode 100644
index 0000000..7fbca17
--- /dev/null
+++ b/tools/perf/arch/csky/Makefile
@@ -0,0 +1,3 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+endif
diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h
new file mode 100644
index 0000000..8f336ea
--- /dev/null
+++ b/tools/perf/arch/csky/include/perf_regs.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_CSKY_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_CSKY_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+
+#define PERF_REG_IP	PERF_REG_CSKY_PC
+#define PERF_REG_SP	PERF_REG_CSKY_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_CSKY_A0:
+		return "a0";
+	case PERF_REG_CSKY_A1:
+		return "a1";
+	case PERF_REG_CSKY_A2:
+		return "a2";
+	case PERF_REG_CSKY_A3:
+		return "a3";
+	case PERF_REG_CSKY_REGS0:
+		return "regs0";
+	case PERF_REG_CSKY_REGS1:
+		return "regs1";
+	case PERF_REG_CSKY_REGS2:
+		return "regs2";
+	case PERF_REG_CSKY_REGS3:
+		return "regs3";
+	case PERF_REG_CSKY_REGS4:
+		return "regs4";
+	case PERF_REG_CSKY_REGS5:
+		return "regs5";
+	case PERF_REG_CSKY_REGS6:
+		return "regs6";
+	case PERF_REG_CSKY_REGS7:
+		return "regs7";
+	case PERF_REG_CSKY_REGS8:
+		return "regs8";
+	case PERF_REG_CSKY_REGS9:
+		return "regs9";
+	case PERF_REG_CSKY_SP:
+		return "sp";
+	case PERF_REG_CSKY_LR:
+		return "lr";
+	case PERF_REG_CSKY_PC:
+		return "pc";
+#if defined(__CSKYABIV2__)
+	case PERF_REG_CSKY_EXREGS0:
+		return "exregs0";
+	case PERF_REG_CSKY_EXREGS1:
+		return "exregs1";
+	case PERF_REG_CSKY_EXREGS2:
+		return "exregs2";
+	case PERF_REG_CSKY_EXREGS3:
+		return "exregs3";
+	case PERF_REG_CSKY_EXREGS4:
+		return "exregs4";
+	case PERF_REG_CSKY_EXREGS5:
+		return "exregs5";
+	case PERF_REG_CSKY_EXREGS6:
+		return "exregs6";
+	case PERF_REG_CSKY_EXREGS7:
+		return "exregs7";
+	case PERF_REG_CSKY_EXREGS8:
+		return "exregs8";
+	case PERF_REG_CSKY_EXREGS9:
+		return "exregs9";
+	case PERF_REG_CSKY_EXREGS10:
+		return "exregs10";
+	case PERF_REG_CSKY_EXREGS11:
+		return "exregs11";
+	case PERF_REG_CSKY_EXREGS12:
+		return "exregs12";
+	case PERF_REG_CSKY_EXREGS13:
+		return "exregs13";
+	case PERF_REG_CSKY_EXREGS14:
+		return "exregs14";
+	case PERF_REG_CSKY_TLS:
+		return "tls";
+	case PERF_REG_CSKY_HI:
+		return "hi";
+	case PERF_REG_CSKY_LO:
+		return "lo";
+#endif
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/csky/util/Build b/tools/perf/arch/csky/util/Build
new file mode 100644
index 0000000..1160bb2
--- /dev/null
+++ b/tools/perf/arch/csky/util/Build
@@ -0,0 +1,2 @@
+perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/csky/util/dwarf-regs.c b/tools/perf/arch/csky/util/dwarf-regs.c
new file mode 100644
index 0000000..3591ca1
--- /dev/null
+++ b/tools/perf/arch/csky/util/dwarf-regs.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+// Mapping of DWARF debug register numbers into register names.
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+#if defined(__CSKYABIV2__)
+#define CSKY_MAX_REGS 71
+const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = {
+	/* r0 ~ r8 */
+	"%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", "%regs2", "%regs3",
+	/* r9 ~ r15 */
+	"%regs4", "%regs5", "%regs6", "%regs7", "%regs8", "%regs9", "%sp",
+	"%lr",
+	/* r16 ~ r23 */
+	"%exregs0", "%exregs1", "%exregs2", "%exregs3", "%exregs4",
+	"%exregs5", "%exregs6", "%exregs7",
+	/* r24 ~ r31 */
+	"%exregs8", "%exregs9", "%exregs10", "%exregs11", "%exregs12",
+	"%exregs13", "%exregs14", "%tls",
+	"%pc", "%cc", "%hi", "%lo", NULL, NULL, NULL, NULL,
+	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+	NULL, NULL, NULL, NULL, "%vr0", "%vr1", "%vr2", "%vr3",
+	"%vr4", "%vr5", "%vr6", "%vr7", "%vr8", "%vr9", "%vr10", "%vr11",
+	"%vr12", "%vr13", "%vr14", "%vr15", NULL, NULL, "%epc",
+};
+#else
+#define CSKY_MAX_REGS 70
+const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = {
+	/* r0 ~ r8 */
+	"%sp", "%regs9", "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1",
+	/* r9 ~ r15 */
+	"%regs2", "%regs3", "%regs4", "%regs5", "%regs6", "%regs7", "%regs8",
+	"%lr",
+	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+	"%vap", "%cc", "%vfp", "%epc", "%hi", "%lo", "%fr0", "%fr1",
+	"%fr2", "%fr3", "%fr4", "%fr5", "%fr6", "%fr7", "%fr8", "%fr9",
+	"%fr10", "%fr11", "%fr12", "%fr13", "%fr14", "%fr15", "%fr16", "%fr17",
+	"%fr18", "%fr19", "%fr20", "%fr21", "%fr22", "%fr23", "%fr24", "%fr25",
+	"%fr26", "%fr27", "%fr28", "%fr29", "%fr30", "%fr31"
+};
+#endif
+
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n < CSKY_MAX_REGS) ? csky_dwarf_regs_table[n] : NULL;
+}
diff --git a/tools/perf/arch/csky/util/unwind-libdw.c b/tools/perf/arch/csky/util/unwind-libdw.c
new file mode 100644
index 0000000..078951b
--- /dev/null
+++ b/tools/perf/arch/csky/util/unwind-libdw.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_CSKY_MAX];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_CSKY_##r);	\
+	val;							\
+})
+
+#if defined(__CSKYABIV2__)
+	dwarf_regs[0]  = REG(A0);
+	dwarf_regs[1]  = REG(A1);
+	dwarf_regs[2]  = REG(A2);
+	dwarf_regs[3]  = REG(A3);
+	dwarf_regs[4]  = REG(REGS0);
+	dwarf_regs[5]  = REG(REGS1);
+	dwarf_regs[6]  = REG(REGS2);
+	dwarf_regs[7]  = REG(REGS3);
+	dwarf_regs[8]  = REG(REGS4);
+	dwarf_regs[9]  = REG(REGS5);
+	dwarf_regs[10] = REG(REGS6);
+	dwarf_regs[11] = REG(REGS7);
+	dwarf_regs[12] = REG(REGS8);
+	dwarf_regs[13] = REG(REGS9);
+	dwarf_regs[14] = REG(SP);
+	dwarf_regs[15] = REG(LR);
+	dwarf_regs[16] = REG(EXREGS0);
+	dwarf_regs[17] = REG(EXREGS1);
+	dwarf_regs[18] = REG(EXREGS2);
+	dwarf_regs[19] = REG(EXREGS3);
+	dwarf_regs[20] = REG(EXREGS4);
+	dwarf_regs[21] = REG(EXREGS5);
+	dwarf_regs[22] = REG(EXREGS6);
+	dwarf_regs[23] = REG(EXREGS7);
+	dwarf_regs[24] = REG(EXREGS8);
+	dwarf_regs[25] = REG(EXREGS9);
+	dwarf_regs[26] = REG(EXREGS10);
+	dwarf_regs[27] = REG(EXREGS11);
+	dwarf_regs[28] = REG(EXREGS12);
+	dwarf_regs[29] = REG(EXREGS13);
+	dwarf_regs[30] = REG(EXREGS14);
+	dwarf_regs[31] = REG(TLS);
+	dwarf_regs[32] = REG(PC);
+#else
+	dwarf_regs[0]  = REG(SP);
+	dwarf_regs[1]  = REG(REGS9);
+	dwarf_regs[2]  = REG(A0);
+	dwarf_regs[3]  = REG(A1);
+	dwarf_regs[4]  = REG(A2);
+	dwarf_regs[5]  = REG(A3);
+	dwarf_regs[6]  = REG(REGS0);
+	dwarf_regs[7]  = REG(REGS1);
+	dwarf_regs[8]  = REG(REGS2);
+	dwarf_regs[9]  = REG(REGS3);
+	dwarf_regs[10] = REG(REGS4);
+	dwarf_regs[11] = REG(REGS5);
+	dwarf_regs[12] = REG(REGS6);
+	dwarf_regs[13] = REG(REGS7);
+	dwarf_regs[14] = REG(REGS8);
+	dwarf_regs[15] = REG(LR);
+	dwarf_regs[32] = REG(PC);
+#endif
+	dwfl_thread_state_register_pc(thread, dwarf_regs[32]);
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_CSKY_MAX,
+					   dwarf_regs);
+}
-- 
2.7.4

Re: [PATCH v3 1/3] perf: use hweight64 instead of hweight_long

[Arnaldo Carvalho de Melo]

Em Wed, Apr 10, 2019 at 04:16:43PM +0800, Mao Han escreveu:
> On 32-bits platform with more than 32 registers, the 64 bits mask is
> truncate to the lower 32 bits and the return value of hweight_long will
> always smaller than 32. When kernel outputs more than 32 registers, but
> the user perf program only counts 32, there will be a data mismatch
> result to overflow check fail.
> 
> CC: Peter Zijlstra <peterz@infradead.org>
> CC: Ingo Molnar <mingo@redhat.com>
> CC: Arnaldo Carvalho de Melo <acme@kernel.org>
> CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> CC: Jiri Olsa <jolsa@redhat.com>
> CC: Namhyung Kim <namhyung@kernel.org>
> 
> Signed-off-by: Mao Han <han_mao@c-sky.com>
> ---
>  tools/perf/util/evsel.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 7835e05..73c78be 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -2322,7 +2322,7 @@ 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;

Later on, in the same function, perf_evsel__parse_sample() we have:

        data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
        if (type & PERF_SAMPLE_REGS_INTR) {
                OVERFLOW_CHECK_u64(array);
                data->intr_regs.abi = *array;
                array++;

                if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
                        u64 mask = evsel->attr.sample_regs_intr;

                        sz = hweight_long(mask) * sizeof(u64);
                        OVERFLOW_CHECK(array, sz, max_size);
                        data->intr_regs.mask = mask;
                        data->intr_regs.regs = (u64 *)array;
                        array = (void *)array + sz;
                }
        }

You forgot to convert that one, doing it for you,

Thanks,

- Arnaldo

Re: [PATCH v3 1/3] perf: use hweight64 instead of hweight_long

[Arnaldo Carvalho de Melo]

Em Wed, Apr 10, 2019 at 10:08:41AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, Apr 10, 2019 at 04:16:43PM +0800, Mao Han escreveu:
> > On 32-bits platform with more than 32 registers, the 64 bits mask is
> > truncate to the lower 32 bits and the return value of hweight_long will
> > always smaller than 32. When kernel outputs more than 32 registers, but
> > the user perf program only counts 32, there will be a data mismatch
> > result to overflow check fail.
> > 
> > CC: Peter Zijlstra <peterz@infradead.org>
> > CC: Ingo Molnar <mingo@redhat.com>
> > CC: Arnaldo Carvalho de Melo <acme@kernel.org>
> > CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> > CC: Jiri Olsa <jolsa@redhat.com>
> > CC: Namhyung Kim <namhyung@kernel.org>
> > 
> > Signed-off-by: Mao Han <han_mao@c-sky.com>
> > ---
> >  tools/perf/util/evsel.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 7835e05..73c78be 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -2322,7 +2322,7 @@ 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;
> 
> Later on, in the same function, perf_evsel__parse_sample() we have:
> 
>         data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
>         if (type & PERF_SAMPLE_REGS_INTR) {
>                 OVERFLOW_CHECK_u64(array);
>                 data->intr_regs.abi = *array;
>                 array++;
> 
>                 if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
>                         u64 mask = evsel->attr.sample_regs_intr;
> 
>                         sz = hweight_long(mask) * sizeof(u64);
>                         OVERFLOW_CHECK(array, sz, max_size);
>                         data->intr_regs.mask = mask;
>                         data->intr_regs.regs = (u64 *)array;
>                         array = (void *)array + sz;
>                 }
>         }
> 
> You forgot to convert that one, doing it for you,

Also in perf_event__sample_event_size() we need to do the same thing,
right?

- Arnaldo

Re: [PATCH v3 1/3] perf: use hweight64 instead of hweight_long

[Arnaldo Carvalho de Melo]

Em Wed, Apr 10, 2019 at 10:10:42AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, Apr 10, 2019 at 10:08:41AM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Wed, Apr 10, 2019 at 04:16:43PM +0800, Mao Han escreveu:
> > > On 32-bits platform with more than 32 registers, the 64 bits mask is
> > > truncate to the lower 32 bits and the return value of hweight_long will
> > > always smaller than 32. When kernel outputs more than 32 registers, but
> > > the user perf program only counts 32, there will be a data mismatch
> > > result to overflow check fail.
> > > 
> > > CC: Peter Zijlstra <peterz@infradead.org>
> > > CC: Ingo Molnar <mingo@redhat.com>
> > > CC: Arnaldo Carvalho de Melo <acme@kernel.org>
> > > CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> > > CC: Jiri Olsa <jolsa@redhat.com>
> > > CC: Namhyung Kim <namhyung@kernel.org>
> > > 
> > > Signed-off-by: Mao Han <han_mao@c-sky.com>
> > > ---
> > >  tools/perf/util/evsel.c | 2 +-
> > >  1 file changed, 1 insertion(+), 1 deletion(-)
> > > 
> > > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > > index 7835e05..73c78be 100644
> > > --- a/tools/perf/util/evsel.c
> > > +++ b/tools/perf/util/evsel.c
> > > @@ -2322,7 +2322,7 @@ 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;
> > 
> > Later on, in the same function, perf_evsel__parse_sample() we have:
> > 
> >         data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
> >         if (type & PERF_SAMPLE_REGS_INTR) {
> >                 OVERFLOW_CHECK_u64(array);
> >                 data->intr_regs.abi = *array;
> >                 array++;
> > 
> >                 if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
> >                         u64 mask = evsel->attr.sample_regs_intr;
> > 
> >                         sz = hweight_long(mask) * sizeof(u64);
> >                         OVERFLOW_CHECK(array, sz, max_size);
> >                         data->intr_regs.mask = mask;
> >                         data->intr_regs.regs = (u64 *)array;
> >                         array = (void *)array + sz;
> >                 }
> >         }
> > 
> > You forgot to convert that one, doing it for you,
> 
> Also in perf_event__sample_event_size() we need to do the same thing,
> right?

and perf_event__synthesize_sample()

Done, resulting patch is at the end of this messages, and matches the
kernel, that uses only hweight64().

I've also added Fixes tags to the patches that used hweight_long() in
various places, to help with the stable trees backporting process,
please consider doing it next time.

- Arnaldo

commit 21e6dfe04861c2c1b529f2759850bc62a80ca050
Author: Mao Han <han_mao@c-sky.com>
Date:   Wed Apr 10 16:16:43 2019 +0800

    perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user)
    
    On 32-bits platform with more than 32 registers, the 64 bits mask is
    truncate to the lower 32 bits and the return value of hweight_long will
    always smaller than 32. When kernel outputs more than 32 registers, but
    the user perf program only counts 32, there will be a data mismatch
    result to overflow check fail.
    
    Signed-off-by: Mao Han <han_mao@c-sky.com>
    Cc: Adrian Hunter <adrian.hunter@intel.com>
    Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
    Cc: Jiri Olsa <jolsa@redhat.com>
    Cc: Namhyung Kim <namhyung@kernel.org>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Cc: Stephane Eranian <eranian@google.com>
    Fixes: 6a21c0b5c2ab ("perf tools: Add core support for sampling intr machine state regs")
    Fixes: d03f2170546d ("perf tools: Expand perf_event__synthesize_sample()")
    Fixes: 0f6a30150ca2 ("perf tools: Support user regs and stack in sample parsing")
    Link: http://lkml.kernel.org/r/29ad7947dc8fd1ff0abd2093a72cc27a2446be9f.1554883878.git.han_mao@c-sky.com
    Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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 {

Re: [PATCH v3 1/3] perf: use hweight64 instead of hweight_long

[Mao Han]

On Wed, Apr 10, 2019 at 10:28:37AM -0300, Arnaldo Carvalho de Melo wrote:
> > > You forgot to convert that one, doing it for you,
> > 
> > Also in perf_event__sample_event_size() we need to do the same thing,
> > right?
> 
> and perf_event__synthesize_sample()
> 
> Done, resulting patch is at the end of this messages, and matches the
> kernel, that uses only hweight64().
> 
> I've also added Fixes tags to the patches that used hweight_long() in
> various places, to help with the stable trees backporting process,
> please consider doing it next time.
> 
> - Arnaldo
>

Thanks for help improving the patch and the suggestion.
Tested with the new patch on C-SKY, seems work fine.

Mao Han

[tip:perf/urgent] perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user)

[tip-bot for Mao Han]

Commit-ID:  21e6dfe04861c2c1b529f2759850bc62a80ca050
Gitweb:     https://git.kernel.org/tip/21e6dfe04861c2c1b529f2759850bc62a80ca050
Author:     Mao Han <han_mao@c-sky.com>
AuthorDate: Wed, 10 Apr 2019 16:16:43 +0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 10 Apr 2019 10:25:28 -0300

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

On 32-bits platform with more than 32 registers, the 64 bits mask is
truncate to the lower 32 bits and the return value of hweight_long will
always smaller than 32. When kernel outputs more than 32 registers, but
the user perf program only counts 32, there will be a data mismatch
result to overflow check fail.

Signed-off-by: Mao Han <han_mao@c-sky.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Fixes: 6a21c0b5c2ab ("perf tools: Add core support for sampling intr machine state regs")
Fixes: d03f2170546d ("perf tools: Expand perf_event__synthesize_sample()")
Fixes: 0f6a30150ca2 ("perf tools: Support user regs and stack in sample parsing")
Link: http://lkml.kernel.org/r/29ad7947dc8fd1ff0abd2093a72cc27a2446be9f.1554883878.git.han_mao@c-sky.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

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 {

[tip:perf/urgent] perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user)

[tip-bot for Mao Han]

Commit-ID:  3a5b64f05d7fe36dea0dde26423e3044fbacd482
Gitweb:     https://git.kernel.org/tip/3a5b64f05d7fe36dea0dde26423e3044fbacd482
Author:     Mao Han <han_mao@c-sky.com>
AuthorDate: Wed, 10 Apr 2019 16:16:43 +0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 16 Apr 2019 11:27:53 -0300

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

On 32-bits platform with more than 32 registers, the 64 bits mask is
truncate to the lower 32 bits and the return value of hweight_long will
always smaller than 32. When kernel outputs more than 32 registers, but
the user perf program only counts 32, there will be a data mismatch
result to overflow check fail.

Signed-off-by: Mao Han <han_mao@c-sky.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Fixes: 6a21c0b5c2ab ("perf tools: Add core support for sampling intr machine state regs")
Fixes: d03f2170546d ("perf tools: Expand perf_event__synthesize_sample()")
Fixes: 0f6a30150ca2 ("perf tools: Support user regs and stack in sample parsing")
Link: http://lkml.kernel.org/r/29ad7947dc8fd1ff0abd2093a72cc27a2446be9f.1554883878.git.han_mao@c-sky.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

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 {