* [PATCH 01/12] perf: Unified API to record selective sets of arch registers
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:45 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 02/12] perf: Add ability to attach user level registers dump to sample Jiri Olsa
` (10 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
This brings a new API to help the selective dump of registers on
event sampling, and its implementation for x86 arch.
Added HAVE_PERF_REGS config option to determine if the architecture
provides perf registers ABI.
The information about desired registers will be passed in u64 mask.
It's up to the architecture to map the registers into the mask bits.
For the x86 arch implementation, both 32 and 64 bit registers
bits are defined within single enum to ensure 64 bit system can
provide register dump for compat task if needed in the future.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
[ Added missing linux/errno.h include ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
arch/Kconfig | 6 +++
arch/x86/Kconfig | 1 +
arch/x86/include/asm/perf_regs.h | 33 +++++++++++++++
arch/x86/kernel/Makefile | 2 +
arch/x86/kernel/perf_regs.c | 90 ++++++++++++++++++++++++++++++++++++++++
include/linux/perf_regs.h | 19 +++++++++
6 files changed, 151 insertions(+)
create mode 100644 arch/x86/include/asm/perf_regs.h
create mode 100644 arch/x86/kernel/perf_regs.c
create mode 100644 include/linux/perf_regs.h
diff --git a/arch/Kconfig b/arch/Kconfig
index 72f2fa1..68d827b 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -222,6 +222,12 @@ config HAVE_PERF_EVENTS_NMI
subsystem. Also has support for calculating CPU cycle events
to determine how many clock cycles in a given period.
+config HAVE_PERF_REGS
+ bool
+ help
+ Support selective register dumps for perf events. This includes
+ bit-mapping of each registers and a unique architecture id.
+
config HAVE_ARCH_JUMP_LABEL
bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 50c660d..b657353 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -60,6 +60,7 @@ config X86
select HAVE_MIXED_BREAKPOINTS_REGS
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
+ select HAVE_PERF_REGS
select ANON_INODES
select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
select HAVE_CMPXCHG_LOCAL if !M386
diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h
new file mode 100644
index 0000000..3f2207b
--- /dev/null
+++ b/arch/x86/include/asm/perf_regs.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+enum perf_event_x86_regs {
+ PERF_REG_X86_AX,
+ PERF_REG_X86_BX,
+ PERF_REG_X86_CX,
+ PERF_REG_X86_DX,
+ PERF_REG_X86_SI,
+ PERF_REG_X86_DI,
+ PERF_REG_X86_BP,
+ PERF_REG_X86_SP,
+ PERF_REG_X86_IP,
+ PERF_REG_X86_FLAGS,
+ PERF_REG_X86_CS,
+ PERF_REG_X86_SS,
+ PERF_REG_X86_DS,
+ PERF_REG_X86_ES,
+ PERF_REG_X86_FS,
+ PERF_REG_X86_GS,
+ 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,
+
+ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
+ PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+};
+#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8215e56..8d7a619 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
new file mode 100644
index 0000000..3d692352
--- /dev/null
+++ b/arch/x86/kernel/perf_regs.c
@@ -0,0 +1,90 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/stddef.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_X86_32
+#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX
+#else
+#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX
+#endif
+
+#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
+
+static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
+ PT_REGS_OFFSET(PERF_REG_X86_AX, ax),
+ PT_REGS_OFFSET(PERF_REG_X86_BX, bx),
+ PT_REGS_OFFSET(PERF_REG_X86_CX, cx),
+ PT_REGS_OFFSET(PERF_REG_X86_DX, dx),
+ PT_REGS_OFFSET(PERF_REG_X86_SI, si),
+ PT_REGS_OFFSET(PERF_REG_X86_DI, di),
+ PT_REGS_OFFSET(PERF_REG_X86_BP, bp),
+ PT_REGS_OFFSET(PERF_REG_X86_SP, sp),
+ PT_REGS_OFFSET(PERF_REG_X86_IP, ip),
+ PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags),
+ PT_REGS_OFFSET(PERF_REG_X86_CS, cs),
+ PT_REGS_OFFSET(PERF_REG_X86_SS, ss),
+#ifdef CONFIG_X86_32
+ PT_REGS_OFFSET(PERF_REG_X86_DS, ds),
+ PT_REGS_OFFSET(PERF_REG_X86_ES, es),
+ PT_REGS_OFFSET(PERF_REG_X86_FS, fs),
+ PT_REGS_OFFSET(PERF_REG_X86_GS, gs),
+#else
+ /*
+ * The pt_regs struct does not store
+ * ds, es, fs, gs in 64 bit mode.
+ */
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+#endif
+#ifdef CONFIG_X86_64
+ PT_REGS_OFFSET(PERF_REG_X86_R8, r8),
+ PT_REGS_OFFSET(PERF_REG_X86_R9, r9),
+ PT_REGS_OFFSET(PERF_REG_X86_R10, r10),
+ PT_REGS_OFFSET(PERF_REG_X86_R11, r11),
+ PT_REGS_OFFSET(PERF_REG_X86_R12, r12),
+ PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
+ PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
+ PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
+#endif
+};
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ if (WARN_ON_ONCE(idx > ARRAY_SIZE(pt_regs_offset)))
+ return 0;
+
+ return regs_get_register(regs, pt_regs_offset[idx]);
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
+
+#ifdef CONFIG_X86_32
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ return 0;
+}
+#else /* CONFIG_X86_64 */
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ if (mask & REG_NOSUPPORT)
+ return -EINVAL;
+
+ return 0;
+}
+#endif /* CONFIG_X86_32 */
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
new file mode 100644
index 0000000..a2f1a98
--- /dev/null
+++ b/include/linux/perf_regs.h
@@ -0,0 +1,19 @@
+#ifndef _LINUX_PERF_REGS_H
+#define _LINUX_PERF_REGS_H
+
+#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);
+#else
+static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ return 0;
+}
+
+static inline int perf_reg_validate(u64 mask)
+{
+ return mask ? -ENOSYS : 0;
+}
+#endif /* CONFIG_HAVE_PERF_REGS */
+#endif /* _LINUX_PERF_REGS_H */
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf: Unified API to record selective sets of arch registers
2012-08-07 13:20 ` [PATCH 01/12] perf: Unified API to record selective sets of arch registers Jiri Olsa
@ 2012-08-21 15:45 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:45 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt
Commit-ID: c5e63197db519bae1c33e41ea0342a50f39e7a93
Gitweb: http://git.kernel.org/tip/c5e63197db519bae1c33e41ea0342a50f39e7a93
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:36 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 11:21:37 -0300
perf: Unified API to record selective sets of arch registers
This brings a new API to help the selective dump of registers on event
sampling, and its implementation for x86 arch.
Added HAVE_PERF_REGS config option to determine if the architecture
provides perf registers ABI.
The information about desired registers will be passed in u64 mask.
It's up to the architecture to map the registers into the mask bits.
For the x86 arch implementation, both 32 and 64 bit registers bits are
defined within single enum to ensure 64 bit system can provide register
dump for compat task if needed in the future.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
[ Added missing linux/errno.h include ]
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
arch/Kconfig | 6 +++
arch/x86/Kconfig | 1 +
arch/x86/include/asm/perf_regs.h | 33 ++++++++++++++
arch/x86/kernel/Makefile | 2 +
arch/x86/kernel/perf_regs.c | 90 ++++++++++++++++++++++++++++++++++++++
include/linux/perf_regs.h | 19 ++++++++
6 files changed, 151 insertions(+), 0 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 72f2fa1..68d827b 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -222,6 +222,12 @@ config HAVE_PERF_EVENTS_NMI
subsystem. Also has support for calculating CPU cycle events
to determine how many clock cycles in a given period.
+config HAVE_PERF_REGS
+ bool
+ help
+ Support selective register dumps for perf events. This includes
+ bit-mapping of each registers and a unique architecture id.
+
config HAVE_ARCH_JUMP_LABEL
bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ec3a1a..3fab6ec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -60,6 +60,7 @@ config X86
select HAVE_MIXED_BREAKPOINTS_REGS
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
+ select HAVE_PERF_REGS
select ANON_INODES
select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
select HAVE_CMPXCHG_LOCAL if !M386
diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h
new file mode 100644
index 0000000..3f2207b
--- /dev/null
+++ b/arch/x86/include/asm/perf_regs.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+enum perf_event_x86_regs {
+ PERF_REG_X86_AX,
+ PERF_REG_X86_BX,
+ PERF_REG_X86_CX,
+ PERF_REG_X86_DX,
+ PERF_REG_X86_SI,
+ PERF_REG_X86_DI,
+ PERF_REG_X86_BP,
+ PERF_REG_X86_SP,
+ PERF_REG_X86_IP,
+ PERF_REG_X86_FLAGS,
+ PERF_REG_X86_CS,
+ PERF_REG_X86_SS,
+ PERF_REG_X86_DS,
+ PERF_REG_X86_ES,
+ PERF_REG_X86_FS,
+ PERF_REG_X86_GS,
+ 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,
+
+ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
+ PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+};
+#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8215e56..8d7a619 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
new file mode 100644
index 0000000..3d692352
--- /dev/null
+++ b/arch/x86/kernel/perf_regs.c
@@ -0,0 +1,90 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/stddef.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_X86_32
+#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX
+#else
+#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX
+#endif
+
+#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
+
+static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
+ PT_REGS_OFFSET(PERF_REG_X86_AX, ax),
+ PT_REGS_OFFSET(PERF_REG_X86_BX, bx),
+ PT_REGS_OFFSET(PERF_REG_X86_CX, cx),
+ PT_REGS_OFFSET(PERF_REG_X86_DX, dx),
+ PT_REGS_OFFSET(PERF_REG_X86_SI, si),
+ PT_REGS_OFFSET(PERF_REG_X86_DI, di),
+ PT_REGS_OFFSET(PERF_REG_X86_BP, bp),
+ PT_REGS_OFFSET(PERF_REG_X86_SP, sp),
+ PT_REGS_OFFSET(PERF_REG_X86_IP, ip),
+ PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags),
+ PT_REGS_OFFSET(PERF_REG_X86_CS, cs),
+ PT_REGS_OFFSET(PERF_REG_X86_SS, ss),
+#ifdef CONFIG_X86_32
+ PT_REGS_OFFSET(PERF_REG_X86_DS, ds),
+ PT_REGS_OFFSET(PERF_REG_X86_ES, es),
+ PT_REGS_OFFSET(PERF_REG_X86_FS, fs),
+ PT_REGS_OFFSET(PERF_REG_X86_GS, gs),
+#else
+ /*
+ * The pt_regs struct does not store
+ * ds, es, fs, gs in 64 bit mode.
+ */
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+#endif
+#ifdef CONFIG_X86_64
+ PT_REGS_OFFSET(PERF_REG_X86_R8, r8),
+ PT_REGS_OFFSET(PERF_REG_X86_R9, r9),
+ PT_REGS_OFFSET(PERF_REG_X86_R10, r10),
+ PT_REGS_OFFSET(PERF_REG_X86_R11, r11),
+ PT_REGS_OFFSET(PERF_REG_X86_R12, r12),
+ PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
+ PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
+ PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
+#endif
+};
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ if (WARN_ON_ONCE(idx > ARRAY_SIZE(pt_regs_offset)))
+ return 0;
+
+ return regs_get_register(regs, pt_regs_offset[idx]);
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
+
+#ifdef CONFIG_X86_32
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ return 0;
+}
+#else /* CONFIG_X86_64 */
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ if (mask & REG_NOSUPPORT)
+ return -EINVAL;
+
+ return 0;
+}
+#endif /* CONFIG_X86_32 */
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
new file mode 100644
index 0000000..a2f1a98
--- /dev/null
+++ b/include/linux/perf_regs.h
@@ -0,0 +1,19 @@
+#ifndef _LINUX_PERF_REGS_H
+#define _LINUX_PERF_REGS_H
+
+#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);
+#else
+static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ return 0;
+}
+
+static inline int perf_reg_validate(u64 mask)
+{
+ return mask ? -ENOSYS : 0;
+}
+#endif /* CONFIG_HAVE_PERF_REGS */
+#endif /* _LINUX_PERF_REGS_H */
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 02/12] perf: Add ability to attach user level registers dump to sample
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
2012-08-07 13:20 ` [PATCH 01/12] perf: Unified API to record selective sets of arch registers Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:46 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 03/12] perf: Factor __output_copy to be usable with specific copy function Jiri Olsa
` (9 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Introducing PERF_SAMPLE_REGS_USER sample type bit to trigger
the dump of user level registers on sample. Registers we want
to dump are specified by sample_regs_user bitmask.
Only user level registers are dumped at the moment. Meaning the
register values of the user space context as it was before the
user entered the kernel for whatever reason (syscall, irq,
exception, or a PMI happening in userspace).
The layout of the sample_regs_user bitmap is described in
asm/perf_regs.h for archs that support register dump.
This is going to be useful to bring Dwarf CFI based stack
unwinding on top of samples.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
[ Dump registers ABI specification. ]
Suggested-by: Stephane Eranian <eranian@google.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
arch/x86/kernel/perf_regs.c | 15 +++++++++++
include/linux/perf_event.h | 35 +++++++++++++++++++++---
include/linux/perf_regs.h | 6 +++++
kernel/events/core.c | 66 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 119 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 3d692352..c5a3e5c 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -1,5 +1,7 @@
#include <linux/errno.h>
#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
#include <linux/bug.h>
#include <linux/stddef.h>
#include <asm/perf_regs.h>
@@ -71,6 +73,11 @@ int perf_reg_validate(u64 mask)
return 0;
}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_32;
+}
#else /* CONFIG_X86_64 */
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
(1ULL << PERF_REG_X86_ES) | \
@@ -87,4 +94,12 @@ int perf_reg_validate(u64 mask)
return 0;
}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ if (test_tsk_thread_flag(task, TIF_IA32))
+ return PERF_SAMPLE_REGS_ABI_32;
+ else
+ return PERF_SAMPLE_REGS_ABI_64;
+}
#endif /* CONFIG_X86_32 */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7602ccb..3d4d847 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -130,8 +130,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_STREAM_ID = 1U << 9,
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
+ PERF_SAMPLE_REGS_USER = 1U << 12,
- PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 13, /* non-ABI */
};
/*
@@ -163,6 +164,15 @@ enum perf_branch_sample_type {
PERF_SAMPLE_BRANCH_HV)
/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+ PERF_SAMPLE_REGS_ABI_NONE = 0,
+ PERF_SAMPLE_REGS_ABI_32 = 1,
+ PERF_SAMPLE_REGS_ABI_64 = 2,
+};
+
+/*
* The format of the data returned by read() on a perf event fd,
* as specified by attr.read_format:
*
@@ -194,6 +204,7 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -271,7 +282,13 @@ struct perf_event_attr {
__u64 bp_len;
__u64 config2; /* extension of config1 */
};
- __u64 branch_sample_type; /* enum branch_sample_type */
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
};
/*
@@ -548,6 +565,9 @@ enum perf_event_type {
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ *
+ * { u64 abi; # enum perf_sample_regs_abi
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -609,6 +629,7 @@ struct perf_guest_info_callbacks {
#include <linux/static_key.h>
#include <linux/atomic.h>
#include <linux/sysfs.h>
+#include <linux/perf_regs.h>
#include <asm/local.h>
struct perf_callchain_entry {
@@ -654,6 +675,11 @@ struct perf_branch_stack {
struct perf_branch_entry entries[0];
};
+struct perf_regs_user {
+ __u64 abi;
+ struct pt_regs *regs;
+};
+
struct task_struct;
/*
@@ -1133,6 +1159,7 @@ struct perf_sample_data {
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
+ struct perf_regs_user regs_user;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -1142,7 +1169,9 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->addr = addr;
data->raw = NULL;
data->br_stack = NULL;
- data->period = period;
+ data->period = period;
+ data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
+ data->regs_user.regs = NULL;
}
extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index a2f1a98..3c73d5f 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -5,6 +5,7 @@
#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);
#else
static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
{
@@ -15,5 +16,10 @@ static inline int perf_reg_validate(u64 mask)
{
return mask ? -ENOSYS : 0;
}
+
+static inline u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_NONE;
+}
#endif /* CONFIG_HAVE_PERF_REGS */
#endif /* _LINUX_PERF_REGS_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b7935fc..d3ce975 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3756,6 +3756,37 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
+static void
+perf_output_sample_regs(struct perf_output_handle *handle,
+ struct pt_regs *regs, u64 mask)
+{
+ int bit;
+
+ for_each_set_bit(bit, (const unsigned long *) &mask,
+ sizeof(mask) * BITS_PER_BYTE) {
+ u64 val;
+
+ val = perf_reg_value(regs, bit);
+ perf_output_put(handle, val);
+ }
+}
+
+static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+ struct pt_regs *regs)
+{
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ if (regs) {
+ regs_user->regs = regs;
+ regs_user->abi = perf_reg_abi(current);
+ }
+}
+
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
@@ -4016,6 +4047,23 @@ void perf_output_sample(struct perf_output_handle *handle,
perf_output_put(handle, nr);
}
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ u64 abi = data->regs_user.abi;
+
+ /*
+ * If there are no regs to dump, notice it through
+ * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+ */
+ perf_output_put(handle, abi);
+
+ if (abi) {
+ u64 mask = event->attr.sample_regs_user;
+ perf_output_sample_regs(handle,
+ data->regs_user.regs,
+ mask);
+ }
+ }
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -4067,6 +4115,20 @@ void perf_prepare_sample(struct perf_event_header *header,
}
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ /* regs dump ABI info */
+ int size = sizeof(u64);
+
+ perf_sample_regs_user(&data->regs_user, regs);
+
+ if (data->regs_user.regs) {
+ u64 mask = event->attr.sample_regs_user;
+ size += hweight64(mask) * sizeof(u64);
+ }
+
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -6142,6 +6204,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
attr->branch_sample_type = mask;
}
}
+
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+ ret = perf_reg_validate(attr->sample_regs_user);
+
out:
return ret;
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf: Add ability to attach user level registers dump to sample
2012-08-07 13:20 ` [PATCH 02/12] perf: Add ability to attach user level registers dump to sample Jiri Olsa
@ 2012-08-21 15:46 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:46 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 4018994f3d8785275ef0e7391b75c3462c029e56
Gitweb: http://git.kernel.org/tip/4018994f3d8785275ef0e7391b75c3462c029e56
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:37 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 11:31:26 -0300
perf: Add ability to attach user level registers dump to sample
Introducing PERF_SAMPLE_REGS_USER sample type bit to trigger the dump of
user level registers on sample. Registers we want to dump are specified
by sample_regs_user bitmask.
Only user level registers are dumped at the moment. Meaning the register
values of the user space context as it was before the user entered the
kernel for whatever reason (syscall, irq, exception, or a PMI happening
in userspace).
The layout of the sample_regs_user bitmap is described in
asm/perf_regs.h for archs that support register dump.
This is going to be useful to bring Dwarf CFI based stack unwinding on
top of samples.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
[ Dump registers ABI specification. ]
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Suggested-by: Stephane Eranian <eranian@google.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-3-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
arch/x86/kernel/perf_regs.c | 15 ++++++++++
include/linux/perf_event.h | 35 +++++++++++++++++++++--
include/linux/perf_regs.h | 6 ++++
kernel/events/core.c | 66 +++++++++++++++++++++++++++++++++++++++++++
4 files changed, 119 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 3d692352..c5a3e5c 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -1,5 +1,7 @@
#include <linux/errno.h>
#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
#include <linux/bug.h>
#include <linux/stddef.h>
#include <asm/perf_regs.h>
@@ -71,6 +73,11 @@ int perf_reg_validate(u64 mask)
return 0;
}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_32;
+}
#else /* CONFIG_X86_64 */
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
(1ULL << PERF_REG_X86_ES) | \
@@ -87,4 +94,12 @@ int perf_reg_validate(u64 mask)
return 0;
}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ if (test_tsk_thread_flag(task, TIF_IA32))
+ return PERF_SAMPLE_REGS_ABI_32;
+ else
+ return PERF_SAMPLE_REGS_ABI_64;
+}
#endif /* CONFIG_X86_32 */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7602ccb..3d4d847 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -130,8 +130,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_STREAM_ID = 1U << 9,
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
+ PERF_SAMPLE_REGS_USER = 1U << 12,
- PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 13, /* non-ABI */
};
/*
@@ -163,6 +164,15 @@ enum perf_branch_sample_type {
PERF_SAMPLE_BRANCH_HV)
/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+ PERF_SAMPLE_REGS_ABI_NONE = 0,
+ PERF_SAMPLE_REGS_ABI_32 = 1,
+ PERF_SAMPLE_REGS_ABI_64 = 2,
+};
+
+/*
* The format of the data returned by read() on a perf event fd,
* as specified by attr.read_format:
*
@@ -194,6 +204,7 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -271,7 +282,13 @@ struct perf_event_attr {
__u64 bp_len;
__u64 config2; /* extension of config1 */
};
- __u64 branch_sample_type; /* enum branch_sample_type */
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
};
/*
@@ -548,6 +565,9 @@ enum perf_event_type {
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ *
+ * { u64 abi; # enum perf_sample_regs_abi
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -609,6 +629,7 @@ struct perf_guest_info_callbacks {
#include <linux/static_key.h>
#include <linux/atomic.h>
#include <linux/sysfs.h>
+#include <linux/perf_regs.h>
#include <asm/local.h>
struct perf_callchain_entry {
@@ -654,6 +675,11 @@ struct perf_branch_stack {
struct perf_branch_entry entries[0];
};
+struct perf_regs_user {
+ __u64 abi;
+ struct pt_regs *regs;
+};
+
struct task_struct;
/*
@@ -1133,6 +1159,7 @@ struct perf_sample_data {
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
+ struct perf_regs_user regs_user;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -1142,7 +1169,9 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->addr = addr;
data->raw = NULL;
data->br_stack = NULL;
- data->period = period;
+ data->period = period;
+ data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
+ data->regs_user.regs = NULL;
}
extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index a2f1a98..3c73d5f 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -5,6 +5,7 @@
#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);
#else
static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
{
@@ -15,5 +16,10 @@ static inline int perf_reg_validate(u64 mask)
{
return mask ? -ENOSYS : 0;
}
+
+static inline u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_NONE;
+}
#endif /* CONFIG_HAVE_PERF_REGS */
#endif /* _LINUX_PERF_REGS_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b7935fc..d3ce975 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3756,6 +3756,37 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
+static void
+perf_output_sample_regs(struct perf_output_handle *handle,
+ struct pt_regs *regs, u64 mask)
+{
+ int bit;
+
+ for_each_set_bit(bit, (const unsigned long *) &mask,
+ sizeof(mask) * BITS_PER_BYTE) {
+ u64 val;
+
+ val = perf_reg_value(regs, bit);
+ perf_output_put(handle, val);
+ }
+}
+
+static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+ struct pt_regs *regs)
+{
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ if (regs) {
+ regs_user->regs = regs;
+ regs_user->abi = perf_reg_abi(current);
+ }
+}
+
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
@@ -4016,6 +4047,23 @@ void perf_output_sample(struct perf_output_handle *handle,
perf_output_put(handle, nr);
}
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ u64 abi = data->regs_user.abi;
+
+ /*
+ * If there are no regs to dump, notice it through
+ * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+ */
+ perf_output_put(handle, abi);
+
+ if (abi) {
+ u64 mask = event->attr.sample_regs_user;
+ perf_output_sample_regs(handle,
+ data->regs_user.regs,
+ mask);
+ }
+ }
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -4067,6 +4115,20 @@ void perf_prepare_sample(struct perf_event_header *header,
}
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ /* regs dump ABI info */
+ int size = sizeof(u64);
+
+ perf_sample_regs_user(&data->regs_user, regs);
+
+ if (data->regs_user.regs) {
+ u64 mask = event->attr.sample_regs_user;
+ size += hweight64(mask) * sizeof(u64);
+ }
+
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -6142,6 +6204,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
attr->branch_sample_type = mask;
}
}
+
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+ ret = perf_reg_validate(attr->sample_regs_user);
+
out:
return ret;
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 03/12] perf: Factor __output_copy to be usable with specific copy function
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
2012-08-07 13:20 ` [PATCH 01/12] perf: Unified API to record selective sets of arch registers Jiri Olsa
2012-08-07 13:20 ` [PATCH 02/12] perf: Add ability to attach user level registers dump to sample Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:47 ` [tip:perf/core] " tip-bot for Frederic Weisbecker
2012-08-07 13:20 ` [PATCH 04/12] perf: Add perf_output_skip function to skip bytes in sample Jiri Olsa
` (8 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler, Ingo Molnar,
Jiri Olsa, Masami Hiramatsu, Paul Mackerras, Peter Zijlstra,
Robert Richter, Stephane Eranian, Tom Zanussi, Ulrich Drepper
From: Frederic Weisbecker <fweisbec@gmail.com>
Adding a generic way to use __output_copy function with
specific copy function via DEFINE_PERF_OUTPUT_COPY macro.
Using this to add new __output_copy_user function, that provides
output copy from user pointers. For x86 the copy_from_user_nmi
function is used and __copy_from_user_inatomic for the rest
of the architectures.
This new function will be used in user stack dump on sample,
coming in next patches.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
arch/x86/include/asm/perf_event.h | 2 ++
include/linux/perf_event.h | 2 +-
kernel/events/internal.h | 62 ++++++++++++++++++++++++++-------------
kernel/events/ring_buffer.c | 4 +--
4 files changed, 46 insertions(+), 24 deletions(-)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index cb4e43b..4fabcdf 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -262,4 +262,6 @@ static inline void perf_check_microcode(void) { }
static inline void amd_pmu_disable_virt(void) { }
#endif
+#define arch_perf_out_copy_user copy_from_user_nmi
+
#endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3d4d847..d41394a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1319,7 +1319,7 @@ static inline bool has_branch_stack(struct perf_event *event)
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);
-extern void perf_output_copy(struct perf_output_handle *handle,
+extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
extern int perf_swevent_get_recursion_context(void);
extern void perf_swevent_put_recursion_context(int rctx);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index a096c19..7fd5408 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -2,6 +2,7 @@
#define _KERNEL_EVENTS_INTERNAL_H
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
/* Buffer handling */
@@ -76,30 +77,49 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb)
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
}
-static inline void
-__output_copy(struct perf_output_handle *handle,
- const void *buf, unsigned int len)
+#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \
+static inline unsigned int \
+func_name(struct perf_output_handle *handle, \
+ const void *buf, unsigned int len) \
+{ \
+ unsigned long size, written; \
+ \
+ do { \
+ size = min_t(unsigned long, handle->size, len); \
+ \
+ written = memcpy_func(handle->addr, buf, size); \
+ \
+ len -= written; \
+ handle->addr += written; \
+ buf += written; \
+ handle->size -= written; \
+ if (!handle->size) { \
+ struct ring_buffer *rb = handle->rb; \
+ \
+ handle->page++; \
+ handle->page &= rb->nr_pages - 1; \
+ handle->addr = rb->data_pages[handle->page]; \
+ handle->size = PAGE_SIZE << page_order(rb); \
+ } \
+ } while (len && written == size); \
+ \
+ return len; \
+}
+
+static inline int memcpy_common(void *dst, const void *src, size_t n)
{
- do {
- unsigned long size = min_t(unsigned long, handle->size, len);
-
- memcpy(handle->addr, buf, size);
-
- len -= size;
- handle->addr += size;
- buf += size;
- handle->size -= size;
- if (!handle->size) {
- struct ring_buffer *rb = handle->rb;
-
- handle->page++;
- handle->page &= rb->nr_pages - 1;
- handle->addr = rb->data_pages[handle->page];
- handle->size = PAGE_SIZE << page_order(rb);
- }
- } while (len);
+ memcpy(dst, src, n);
+ return n;
}
+DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
+
+#ifndef arch_perf_out_copy_user
+#define arch_perf_out_copy_user __copy_from_user_inatomic
+#endif
+
+DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
+
/* Callchain handling */
extern struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 6ddaba4..b4c2ad3 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -182,10 +182,10 @@ out:
return -ENOSPC;
}
-void perf_output_copy(struct perf_output_handle *handle,
+unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len)
{
- __output_copy(handle, buf, len);
+ return __output_copy(handle, buf, len);
}
void perf_output_end(struct perf_output_handle *handle)
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf: Factor __output_copy to be usable with specific copy function
2012-08-07 13:20 ` [PATCH 03/12] perf: Factor __output_copy to be usable with specific copy function Jiri Olsa
@ 2012-08-21 15:47 ` tip-bot for Frederic Weisbecker
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Frederic Weisbecker @ 2012-08-21 15:47 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 91d7753a45f8525dc75b6be01e427dc1c378dc16
Gitweb: http://git.kernel.org/tip/91d7753a45f8525dc75b6be01e427dc1c378dc16
Author: Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Tue, 7 Aug 2012 15:20:38 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 11:44:06 -0300
perf: Factor __output_copy to be usable with specific copy function
Adding a generic way to use __output_copy function with specific copy
function via DEFINE_PERF_OUTPUT_COPY macro.
Using this to add new __output_copy_user function, that provides output
copy from user pointers. For x86 the copy_from_user_nmi function is used
and __copy_from_user_inatomic for the rest of the architectures.
This new function will be used in user stack dump on sample, coming in
next patches.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-4-git-send-email-jolsa@redhat.com
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
arch/x86/include/asm/perf_event.h | 2 +
include/linux/perf_event.h | 2 +-
kernel/events/internal.h | 62 ++++++++++++++++++++++++------------
kernel/events/ring_buffer.c | 4 +-
4 files changed, 46 insertions(+), 24 deletions(-)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index cb4e43b..4fabcdf 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -262,4 +262,6 @@ static inline void perf_check_microcode(void) { }
static inline void amd_pmu_disable_virt(void) { }
#endif
+#define arch_perf_out_copy_user copy_from_user_nmi
+
#endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3d4d847..d41394a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1319,7 +1319,7 @@ static inline bool has_branch_stack(struct perf_event *event)
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);
-extern void perf_output_copy(struct perf_output_handle *handle,
+extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
extern int perf_swevent_get_recursion_context(void);
extern void perf_swevent_put_recursion_context(int rctx);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index a096c19..7fd5408 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -2,6 +2,7 @@
#define _KERNEL_EVENTS_INTERNAL_H
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
/* Buffer handling */
@@ -76,30 +77,49 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb)
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
}
-static inline void
-__output_copy(struct perf_output_handle *handle,
- const void *buf, unsigned int len)
+#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \
+static inline unsigned int \
+func_name(struct perf_output_handle *handle, \
+ const void *buf, unsigned int len) \
+{ \
+ unsigned long size, written; \
+ \
+ do { \
+ size = min_t(unsigned long, handle->size, len); \
+ \
+ written = memcpy_func(handle->addr, buf, size); \
+ \
+ len -= written; \
+ handle->addr += written; \
+ buf += written; \
+ handle->size -= written; \
+ if (!handle->size) { \
+ struct ring_buffer *rb = handle->rb; \
+ \
+ handle->page++; \
+ handle->page &= rb->nr_pages - 1; \
+ handle->addr = rb->data_pages[handle->page]; \
+ handle->size = PAGE_SIZE << page_order(rb); \
+ } \
+ } while (len && written == size); \
+ \
+ return len; \
+}
+
+static inline int memcpy_common(void *dst, const void *src, size_t n)
{
- do {
- unsigned long size = min_t(unsigned long, handle->size, len);
-
- memcpy(handle->addr, buf, size);
-
- len -= size;
- handle->addr += size;
- buf += size;
- handle->size -= size;
- if (!handle->size) {
- struct ring_buffer *rb = handle->rb;
-
- handle->page++;
- handle->page &= rb->nr_pages - 1;
- handle->addr = rb->data_pages[handle->page];
- handle->size = PAGE_SIZE << page_order(rb);
- }
- } while (len);
+ memcpy(dst, src, n);
+ return n;
}
+DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
+
+#ifndef arch_perf_out_copy_user
+#define arch_perf_out_copy_user __copy_from_user_inatomic
+#endif
+
+DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
+
/* Callchain handling */
extern struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 6ddaba4..b4c2ad3 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -182,10 +182,10 @@ out:
return -ENOSPC;
}
-void perf_output_copy(struct perf_output_handle *handle,
+unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len)
{
- __output_copy(handle, buf, len);
+ return __output_copy(handle, buf, len);
}
void perf_output_end(struct perf_output_handle *handle)
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 04/12] perf: Add perf_output_skip function to skip bytes in sample
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (2 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 03/12] perf: Factor __output_copy to be usable with specific copy function Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:48 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 05/12] perf: Add ability to attach user stack dump to sample Jiri Olsa
` (7 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Introducing perf_output_skip function to be able to skip data
within the perf ring buffer.
When writing data into perf ring buffer we first reserve needed
place in ring buffer and then copy the actual data.
There's a possibility we won't be able to fill all the reserved
size with data, so we need a way to skip the remaining bytes.
This is going to be useful when storing the user stack dump,
where we might end up with less data than we originally requested.
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
include/linux/perf_event.h | 2 ++
kernel/events/internal.h | 4 ++++
kernel/events/ring_buffer.c | 6 ++++++
3 files changed, 12 insertions(+)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d41394a..8a73f75 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1321,6 +1321,8 @@ extern int perf_output_begin(struct perf_output_handle *handle,
extern void perf_output_end(struct perf_output_handle *handle);
extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
+extern unsigned int perf_output_skip(struct perf_output_handle *handle,
+ unsigned int len);
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);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 7fd5408..ce7bdfc 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -114,6 +114,10 @@ static inline int memcpy_common(void *dst, const void *src, size_t n)
DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
+#define MEMCPY_SKIP(dst, src, n) (n)
+
+DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP)
+
#ifndef arch_perf_out_copy_user
#define arch_perf_out_copy_user __copy_from_user_inatomic
#endif
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index b4c2ad3..23cb34f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -188,6 +188,12 @@ unsigned int perf_output_copy(struct perf_output_handle *handle,
return __output_copy(handle, buf, len);
}
+unsigned int perf_output_skip(struct perf_output_handle *handle,
+ unsigned int len)
+{
+ return __output_skip(handle, NULL, len);
+}
+
void perf_output_end(struct perf_output_handle *handle)
{
perf_output_put_handle(handle);
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf: Add perf_output_skip function to skip bytes in sample
2012-08-07 13:20 ` [PATCH 04/12] perf: Add perf_output_skip function to skip bytes in sample Jiri Olsa
@ 2012-08-21 15:48 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:48 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 5685e0ff45f5df67e79e9b052b6ffd501ff38c11
Gitweb: http://git.kernel.org/tip/5685e0ff45f5df67e79e9b052b6ffd501ff38c11
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:39 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 12:16:22 -0300
perf: Add perf_output_skip function to skip bytes in sample
Introducing perf_output_skip function to be able to skip data within the
perf ring buffer.
When writing data into perf ring buffer we first reserve needed place in
ring buffer and then copy the actual data.
There's a possibility we won't be able to fill all the reserved size
with data, so we need a way to skip the remaining bytes.
This is going to be useful when storing the user stack dump, where we
might end up with less data than we originally requested.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-5-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
include/linux/perf_event.h | 2 ++
kernel/events/internal.h | 4 ++++
kernel/events/ring_buffer.c | 6 ++++++
3 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d41394a..8a73f75 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1321,6 +1321,8 @@ extern int perf_output_begin(struct perf_output_handle *handle,
extern void perf_output_end(struct perf_output_handle *handle);
extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
+extern unsigned int perf_output_skip(struct perf_output_handle *handle,
+ unsigned int len);
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);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 7fd5408..ce7bdfc 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -114,6 +114,10 @@ static inline int memcpy_common(void *dst, const void *src, size_t n)
DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
+#define MEMCPY_SKIP(dst, src, n) (n)
+
+DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP)
+
#ifndef arch_perf_out_copy_user
#define arch_perf_out_copy_user __copy_from_user_inatomic
#endif
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index b4c2ad3..23cb34f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -188,6 +188,12 @@ unsigned int perf_output_copy(struct perf_output_handle *handle,
return __output_copy(handle, buf, len);
}
+unsigned int perf_output_skip(struct perf_output_handle *handle,
+ unsigned int len)
+{
+ return __output_skip(handle, NULL, len);
+}
+
void perf_output_end(struct perf_output_handle *handle)
{
perf_output_put_handle(handle);
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 05/12] perf: Add ability to attach user stack dump to sample
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (3 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 04/12] perf: Add perf_output_skip function to skip bytes in sample Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:49 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 06/12] perf: Add attribute to filter out callchains Jiri Olsa
` (6 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Introducing PERF_SAMPLE_STACK_USER sample type bit to trigger
the dump of the user level stack on sample. The size of the
dump is specified by sample_stack_user value.
Being able to dump parts of the user stack, starting from the
stack pointer, will be useful to make a post mortem dwarf CFI
based stack unwinding.
Added HAVE_PERF_USER_STACK_DUMP config option to determine if
the architecture provides user stack dump on perf event samples.
This needs access to the user stack pointer which is not unified
across architectures. Enabling this for x86 architecture.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
arch/Kconfig | 7 +++
arch/x86/Kconfig | 1 +
include/linux/perf_event.h | 18 +++++-
kernel/events/core.c | 150 ++++++++++++++++++++++++++++++++++++++++++++-
kernel/events/internal.h | 16 +++++
5 files changed, 190 insertions(+), 2 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 68d827b..2a83a3f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -228,6 +228,13 @@ config HAVE_PERF_REGS
Support selective register dumps for perf events. This includes
bit-mapping of each registers and a unique architecture id.
+config HAVE_PERF_USER_STACK_DUMP
+ bool
+ help
+ Support user stack dumps for perf event samples. This needs
+ access to the user stack pointer which is not unified across
+ architectures.
+
config HAVE_ARCH_JUMP_LABEL
bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b657353..61ac5c0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -61,6 +61,7 @@ config X86
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
select ANON_INODES
select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
select HAVE_CMPXCHG_LOCAL if !M386
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8a73f75..d1d25f6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -131,8 +131,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
PERF_SAMPLE_REGS_USER = 1U << 12,
+ PERF_SAMPLE_STACK_USER = 1U << 13,
- PERF_SAMPLE_MAX = 1U << 13, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */
};
/*
@@ -205,6 +206,7 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
+#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -289,6 +291,14 @@ struct perf_event_attr {
* See asm/perf_regs.h for details.
*/
__u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
+
+ /* Align to u64. */
+ __u32 __reserved_2;
};
/*
@@ -568,6 +578,10 @@ enum perf_event_type {
*
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+ *
+ * { u64 size;
+ * char data[size];
+ * u64 dyn_size; } && PERF_SAMPLE_STACK_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -1160,6 +1174,7 @@ struct perf_sample_data {
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
struct perf_regs_user regs_user;
+ u64 stack_user_size;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -1172,6 +1187,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->period = period;
data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
data->regs_user.regs = NULL;
+ data->stack_user_size = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3ce975..2ba8904 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -36,6 +36,7 @@
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
+#include <linux/mm_types.h>
#include "internal.h"
@@ -3787,6 +3788,101 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
}
}
+/*
+ * Get remaining task size from user stack pointer.
+ *
+ * It'd be better to take stack vma map and limit this more
+ * precisly, but there's no way to get it safely under interrupt,
+ * so using TASK_SIZE as limit.
+ */
+static u64 perf_ustack_task_size(struct pt_regs *regs)
+{
+ unsigned long addr = perf_user_stack_pointer(regs);
+
+ if (!addr || addr >= TASK_SIZE)
+ return 0;
+
+ return TASK_SIZE - addr;
+}
+
+static u16
+perf_sample_ustack_size(u16 stack_size, u16 header_size,
+ struct pt_regs *regs)
+{
+ u64 task_size;
+
+ /* No regs, no stack pointer, no dump. */
+ if (!regs)
+ return 0;
+
+ /*
+ * Check if we fit in with the requested stack size into the:
+ * - TASK_SIZE
+ * If we don't, we limit the size to the TASK_SIZE.
+ *
+ * - remaining sample size
+ * If we don't, we customize the stack size to
+ * fit in to the remaining sample size.
+ */
+
+ task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs));
+ stack_size = min(stack_size, (u16) task_size);
+
+ /* Current header size plus static size and dynamic size. */
+ header_size += 2 * sizeof(u64);
+
+ /* Do we fit in with the current stack dump size? */
+ if ((u16) (header_size + stack_size) < header_size) {
+ /*
+ * If we overflow the maximum size for the sample,
+ * we customize the stack dump size to fit in.
+ */
+ stack_size = USHRT_MAX - header_size - sizeof(u64);
+ stack_size = round_up(stack_size, sizeof(u64));
+ }
+
+ return stack_size;
+}
+
+static void
+perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
+ struct pt_regs *regs)
+{
+ /* Case of a kernel thread, nothing to dump */
+ if (!regs) {
+ u64 size = 0;
+ perf_output_put(handle, size);
+ } else {
+ unsigned long sp;
+ unsigned int rem;
+ u64 dyn_size;
+
+ /*
+ * We dump:
+ * static size
+ * - the size requested by user or the best one we can fit
+ * in to the sample max size
+ * data
+ * - user stack dump data
+ * dynamic size
+ * - the actual dumped size
+ */
+
+ /* Static size. */
+ perf_output_put(handle, dump_size);
+
+ /* Data. */
+ sp = perf_user_stack_pointer(regs);
+ rem = __output_copy_user(handle, (void *) sp, dump_size);
+ dyn_size = dump_size - rem;
+
+ perf_output_skip(handle, rem);
+
+ /* Dynamic size. */
+ perf_output_put(handle, dyn_size);
+ }
+}
+
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
@@ -4064,6 +4160,11 @@ void perf_output_sample(struct perf_output_handle *handle,
mask);
}
}
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ perf_output_sample_ustack(handle,
+ data->stack_user_size,
+ data->regs_user.regs);
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -4129,6 +4230,35 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_STACK_USER) {
+ /*
+ * Either we need PERF_SAMPLE_STACK_USER bit to be allways
+ * processed as the last one or have additional check added
+ * in case new sample type is added, because we could eat
+ * up the rest of the sample size.
+ */
+ struct perf_regs_user *uregs = &data->regs_user;
+ u16 stack_size = event->attr.sample_stack_user;
+ u16 size = sizeof(u64);
+
+ if (!uregs->abi)
+ perf_sample_regs_user(uregs, regs);
+
+ stack_size = perf_sample_ustack_size(stack_size, header->size,
+ uregs->regs);
+
+ /*
+ * If there is something to dump, add space for the dump
+ * itself and for the field that tells the dynamic size,
+ * which is how many have been actually dumped.
+ */
+ if (stack_size)
+ size += sizeof(u64) + stack_size;
+
+ data->stack_user_size = stack_size;
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -6205,8 +6335,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
}
}
- if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
ret = perf_reg_validate(attr->sample_regs_user);
+ if (ret)
+ return ret;
+ }
+
+ if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
+ if (!arch_perf_have_user_stack_dump())
+ return -ENOSYS;
+
+ /*
+ * We have __u32 type for the size, but so far
+ * we can only use __u16 as maximum due to the
+ * __u16 sample size limit.
+ */
+ if (attr->sample_stack_user >= USHRT_MAX)
+ ret = -EINVAL;
+ else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
+ ret = -EINVAL;
+ }
out:
return ret;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index ce7bdfc..d56a64c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -158,4 +158,20 @@ static inline void put_recursion_context(int *recursion, int rctx)
recursion[rctx]--;
}
+#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+ return true;
+}
+
+#define perf_user_stack_pointer(regs) user_stack_pointer(regs)
+#else
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+ return false;
+}
+
+#define perf_user_stack_pointer(regs) 0
+#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */
+
#endif /* _KERNEL_EVENTS_INTERNAL_H */
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf: Add ability to attach user stack dump to sample
2012-08-07 13:20 ` [PATCH 05/12] perf: Add ability to attach user stack dump to sample Jiri Olsa
@ 2012-08-21 15:49 ` tip-bot for Jiri Olsa
2012-08-21 17:11 ` Peter Zijlstra
0 siblings, 1 reply; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:49 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: c5ebcedb566ef17bda7b02686e0d658a7bb42ee7
Gitweb: http://git.kernel.org/tip/c5ebcedb566ef17bda7b02686e0d658a7bb42ee7
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:40 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 12:17:58 -0300
perf: Add ability to attach user stack dump to sample
Introducing PERF_SAMPLE_STACK_USER sample type bit to trigger the dump
of the user level stack on sample. The size of the dump is specified by
sample_stack_user value.
Being able to dump parts of the user stack, starting from the stack
pointer, will be useful to make a post mortem dwarf CFI based stack
unwinding.
Added HAVE_PERF_USER_STACK_DUMP config option to determine if the
architecture provides user stack dump on perf event samples. This needs
access to the user stack pointer which is not unified across
architectures. Enabling this for x86 architecture.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-6-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
arch/Kconfig | 7 ++
arch/x86/Kconfig | 1 +
include/linux/perf_event.h | 18 +++++-
kernel/events/core.c | 150 +++++++++++++++++++++++++++++++++++++++++++-
kernel/events/internal.h | 16 +++++
5 files changed, 190 insertions(+), 2 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 68d827b..2a83a3f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -228,6 +228,13 @@ config HAVE_PERF_REGS
Support selective register dumps for perf events. This includes
bit-mapping of each registers and a unique architecture id.
+config HAVE_PERF_USER_STACK_DUMP
+ bool
+ help
+ Support user stack dumps for perf event samples. This needs
+ access to the user stack pointer which is not unified across
+ architectures.
+
config HAVE_ARCH_JUMP_LABEL
bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3fab6ec..a2d19ee 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -61,6 +61,7 @@ config X86
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
select ANON_INODES
select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
select HAVE_CMPXCHG_LOCAL if !M386
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8a73f75..d1d25f6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -131,8 +131,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
PERF_SAMPLE_REGS_USER = 1U << 12,
+ PERF_SAMPLE_STACK_USER = 1U << 13,
- PERF_SAMPLE_MAX = 1U << 13, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */
};
/*
@@ -205,6 +206,7 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
+#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -289,6 +291,14 @@ struct perf_event_attr {
* See asm/perf_regs.h for details.
*/
__u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
+
+ /* Align to u64. */
+ __u32 __reserved_2;
};
/*
@@ -568,6 +578,10 @@ enum perf_event_type {
*
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+ *
+ * { u64 size;
+ * char data[size];
+ * u64 dyn_size; } && PERF_SAMPLE_STACK_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -1160,6 +1174,7 @@ struct perf_sample_data {
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
struct perf_regs_user regs_user;
+ u64 stack_user_size;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -1172,6 +1187,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->period = period;
data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
data->regs_user.regs = NULL;
+ data->stack_user_size = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3ce975..2ba8904 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -36,6 +36,7 @@
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
+#include <linux/mm_types.h>
#include "internal.h"
@@ -3787,6 +3788,101 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
}
}
+/*
+ * Get remaining task size from user stack pointer.
+ *
+ * It'd be better to take stack vma map and limit this more
+ * precisly, but there's no way to get it safely under interrupt,
+ * so using TASK_SIZE as limit.
+ */
+static u64 perf_ustack_task_size(struct pt_regs *regs)
+{
+ unsigned long addr = perf_user_stack_pointer(regs);
+
+ if (!addr || addr >= TASK_SIZE)
+ return 0;
+
+ return TASK_SIZE - addr;
+}
+
+static u16
+perf_sample_ustack_size(u16 stack_size, u16 header_size,
+ struct pt_regs *regs)
+{
+ u64 task_size;
+
+ /* No regs, no stack pointer, no dump. */
+ if (!regs)
+ return 0;
+
+ /*
+ * Check if we fit in with the requested stack size into the:
+ * - TASK_SIZE
+ * If we don't, we limit the size to the TASK_SIZE.
+ *
+ * - remaining sample size
+ * If we don't, we customize the stack size to
+ * fit in to the remaining sample size.
+ */
+
+ task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs));
+ stack_size = min(stack_size, (u16) task_size);
+
+ /* Current header size plus static size and dynamic size. */
+ header_size += 2 * sizeof(u64);
+
+ /* Do we fit in with the current stack dump size? */
+ if ((u16) (header_size + stack_size) < header_size) {
+ /*
+ * If we overflow the maximum size for the sample,
+ * we customize the stack dump size to fit in.
+ */
+ stack_size = USHRT_MAX - header_size - sizeof(u64);
+ stack_size = round_up(stack_size, sizeof(u64));
+ }
+
+ return stack_size;
+}
+
+static void
+perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
+ struct pt_regs *regs)
+{
+ /* Case of a kernel thread, nothing to dump */
+ if (!regs) {
+ u64 size = 0;
+ perf_output_put(handle, size);
+ } else {
+ unsigned long sp;
+ unsigned int rem;
+ u64 dyn_size;
+
+ /*
+ * We dump:
+ * static size
+ * - the size requested by user or the best one we can fit
+ * in to the sample max size
+ * data
+ * - user stack dump data
+ * dynamic size
+ * - the actual dumped size
+ */
+
+ /* Static size. */
+ perf_output_put(handle, dump_size);
+
+ /* Data. */
+ sp = perf_user_stack_pointer(regs);
+ rem = __output_copy_user(handle, (void *) sp, dump_size);
+ dyn_size = dump_size - rem;
+
+ perf_output_skip(handle, rem);
+
+ /* Dynamic size. */
+ perf_output_put(handle, dyn_size);
+ }
+}
+
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
@@ -4064,6 +4160,11 @@ void perf_output_sample(struct perf_output_handle *handle,
mask);
}
}
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ perf_output_sample_ustack(handle,
+ data->stack_user_size,
+ data->regs_user.regs);
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -4129,6 +4230,35 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_STACK_USER) {
+ /*
+ * Either we need PERF_SAMPLE_STACK_USER bit to be allways
+ * processed as the last one or have additional check added
+ * in case new sample type is added, because we could eat
+ * up the rest of the sample size.
+ */
+ struct perf_regs_user *uregs = &data->regs_user;
+ u16 stack_size = event->attr.sample_stack_user;
+ u16 size = sizeof(u64);
+
+ if (!uregs->abi)
+ perf_sample_regs_user(uregs, regs);
+
+ stack_size = perf_sample_ustack_size(stack_size, header->size,
+ uregs->regs);
+
+ /*
+ * If there is something to dump, add space for the dump
+ * itself and for the field that tells the dynamic size,
+ * which is how many have been actually dumped.
+ */
+ if (stack_size)
+ size += sizeof(u64) + stack_size;
+
+ data->stack_user_size = stack_size;
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -6205,8 +6335,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
}
}
- if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
ret = perf_reg_validate(attr->sample_regs_user);
+ if (ret)
+ return ret;
+ }
+
+ if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
+ if (!arch_perf_have_user_stack_dump())
+ return -ENOSYS;
+
+ /*
+ * We have __u32 type for the size, but so far
+ * we can only use __u16 as maximum due to the
+ * __u16 sample size limit.
+ */
+ if (attr->sample_stack_user >= USHRT_MAX)
+ ret = -EINVAL;
+ else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
+ ret = -EINVAL;
+ }
out:
return ret;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index ce7bdfc..d56a64c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -158,4 +158,20 @@ static inline void put_recursion_context(int *recursion, int rctx)
recursion[rctx]--;
}
+#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+ return true;
+}
+
+#define perf_user_stack_pointer(regs) user_stack_pointer(regs)
+#else
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+ return false;
+}
+
+#define perf_user_stack_pointer(regs) 0
+#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */
+
#endif /* _KERNEL_EVENTS_INTERNAL_H */
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [tip:perf/core] perf: Add ability to attach user stack dump to sample
2012-08-21 15:49 ` [tip:perf/core] " tip-bot for Jiri Olsa
@ 2012-08-21 17:11 ` Peter Zijlstra
2012-08-22 8:35 ` [PATCH] perf: Keep the perf_event_attr on version 3 Jiri Olsa
0 siblings, 1 reply; 32+ messages in thread
From: Peter Zijlstra @ 2012-08-21 17:11 UTC (permalink / raw)
To: mingo, eranian, acme, gorcunov, benjamin.redelings, jolsa,
fweisbec, robert.richter, drepper, tglx, cjashfor, asharma,
paulus, linux-kernel, hpa, fche, tzanussi, masami.hiramatsu.pt,
mingo
Cc: linux-tip-commits
On Tue, 2012-08-21 at 08:49 -0700, tip-bot for Jiri Olsa wrote:
> #define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
> +#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
Both are introduced in this patch set, there's no release in between,
why are we doing two version increments? Seems like pointless version
space inflation to me.
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH] perf: Keep the perf_event_attr on version 3
2012-08-21 17:11 ` Peter Zijlstra
@ 2012-08-22 8:35 ` Jiri Olsa
2012-08-22 18:18 ` Arnaldo Carvalho de Melo
2012-08-27 16:57 ` [tip:perf/core] perf tools: " tip-bot for Jiri Olsa
0 siblings, 2 replies; 32+ messages in thread
From: Jiri Olsa @ 2012-08-22 8:35 UTC (permalink / raw)
To: Peter Zijlstra
Cc: mingo, eranian, acme, gorcunov, benjamin.redelings, fweisbec,
robert.richter, drepper, tglx, cjashfor, asharma, paulus,
linux-kernel, hpa, fche, tzanussi, masami.hiramatsu.pt, mingo
On Tue, Aug 21, 2012 at 07:11:56PM +0200, Peter Zijlstra wrote:
> On Tue, 2012-08-21 at 08:49 -0700, tip-bot for Jiri Olsa wrote:
> > #define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
> > +#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
>
> Both are introduced in this patch set, there's no release in between,
> why are we doing two version increments? Seems like pointless version
> space inflation to me.
not sure why I did that, attached patch returns that to version3
jirka
---
Stashing version 4 under version 3 and removing version 4,
because both version changes were within single patchset.
Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
include/linux/perf_event.h | 4 ++--
| 1 -
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 297ca3d..28f9cee 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -205,8 +205,8 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
-#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
-#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
+ /* add: sample_stack_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1e5b6aa..5ed4812 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1831,7 +1831,6 @@ static const int attr_file_abi_sizes[] = {
[1] = PERF_ATTR_SIZE_VER1,
[2] = PERF_ATTR_SIZE_VER2,
[3] = PERF_ATTR_SIZE_VER3,
- [4] = PERF_ATTR_SIZE_VER4,
0,
};
--
1.7.11.4
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [PATCH] perf: Keep the perf_event_attr on version 3
2012-08-22 8:35 ` [PATCH] perf: Keep the perf_event_attr on version 3 Jiri Olsa
@ 2012-08-22 18:18 ` Arnaldo Carvalho de Melo
2012-08-22 18:21 ` Peter Zijlstra
2012-08-27 16:57 ` [tip:perf/core] perf tools: " tip-bot for Jiri Olsa
1 sibling, 1 reply; 32+ messages in thread
From: Arnaldo Carvalho de Melo @ 2012-08-22 18:18 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Jiri Olsa, mingo, eranian, gorcunov, benjamin.redelings,
fweisbec, robert.richter, drepper, tglx, cjashfor, asharma,
paulus, linux-kernel, hpa, fche, tzanussi, masami.hiramatsu.pt,
mingo
Em Wed, Aug 22, 2012 at 10:35:40AM +0200, Jiri Olsa escreveu:
> On Tue, Aug 21, 2012 at 07:11:56PM +0200, Peter Zijlstra wrote:
> > On Tue, 2012-08-21 at 08:49 -0700, tip-bot for Jiri Olsa wrote:
> > > #define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
> > > +#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
> >
> > Both are introduced in this patch set, there's no release in between,
> > why are we doing two version increments? Seems like pointless version
> > space inflation to me.
>
> not sure why I did that, attached patch returns that to version3
I'm lazy so couldn't quickly find any problem in applying this patch,
Peter, can you see any problem?
Will add your Acked-by if you can't.
- Arnaldo
> jirka
>
> ---
> Stashing version 4 under version 3 and removing version 4,
> because both version changes were within single patchset.
>
> Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
> Cc: Ingo Molnar <mingo@elte.hu>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
> Cc: Frederic Weisbecker <fweisbec@gmail.com>
> Signed-off-by: Jiri Olsa <jolsa@redhat.com>
> ---
> include/linux/perf_event.h | 4 ++--
> tools/perf/util/header.c | 1 -
> 2 files changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 297ca3d..28f9cee 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -205,8 +205,8 @@ enum perf_event_read_format {
> #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
> #define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
> #define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
> -#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
> -#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
> +#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
> + /* add: sample_stack_user */
>
> /*
> * Hardware event_id to monitor via a performance monitoring event:
> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
> index 1e5b6aa..5ed4812 100644
> --- a/tools/perf/util/header.c
> +++ b/tools/perf/util/header.c
> @@ -1831,7 +1831,6 @@ static const int attr_file_abi_sizes[] = {
> [1] = PERF_ATTR_SIZE_VER1,
> [2] = PERF_ATTR_SIZE_VER2,
> [3] = PERF_ATTR_SIZE_VER3,
> - [4] = PERF_ATTR_SIZE_VER4,
> 0,
> };
>
> --
> 1.7.11.4
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH] perf: Keep the perf_event_attr on version 3
2012-08-22 18:18 ` Arnaldo Carvalho de Melo
@ 2012-08-22 18:21 ` Peter Zijlstra
0 siblings, 0 replies; 32+ messages in thread
From: Peter Zijlstra @ 2012-08-22 18:21 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Jiri Olsa, mingo, eranian, gorcunov, benjamin.redelings,
fweisbec, robert.richter, drepper, tglx, cjashfor, asharma,
paulus, linux-kernel, hpa, fche, tzanussi, masami.hiramatsu.pt,
mingo
On Wed, 2012-08-22 at 15:18 -0300, Arnaldo Carvalho de Melo wrote:
> I'm lazy so couldn't quickly find any problem in applying this patch,
> Peter, can you see any problem?
>
> Will add your Acked-by if you can't.
No its fine, thanks!
^ permalink raw reply [flat|nested] 32+ messages in thread
* [tip:perf/core] perf tools: Keep the perf_event_attr on version 3
2012-08-22 8:35 ` [PATCH] perf: Keep the perf_event_attr on version 3 Jiri Olsa
2012-08-22 18:18 ` Arnaldo Carvalho de Melo
@ 2012-08-27 16:57 ` tip-bot for Jiri Olsa
1 sibling, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-27 16:57 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt
Commit-ID: 1659d129ed014b715b0b2120e6fd929bdd33ed03
Gitweb: http://git.kernel.org/tip/1659d129ed014b715b0b2120e6fd929bdd33ed03
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Wed, 22 Aug 2012 10:35:40 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 22 Aug 2012 15:33:12 -0300
perf tools: Keep the perf_event_attr on version 3
Stashing version 4 under version 3 and removing version 4, because both
version changes were within single patchset.
Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/20120822083540.GB1003@krava.brq.redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
include/linux/perf_event.h | 4 ++--
| 1 -
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 297ca3d..28f9cee 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -205,8 +205,8 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
-#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */
-#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
+ /* add: sample_stack_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 63aad31..9696e64 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2011,7 +2011,6 @@ static const int attr_file_abi_sizes[] = {
[1] = PERF_ATTR_SIZE_VER1,
[2] = PERF_ATTR_SIZE_VER2,
[3] = PERF_ATTR_SIZE_VER3,
- [4] = PERF_ATTR_SIZE_VER4,
0,
};
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 06/12] perf: Add attribute to filter out callchains
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (4 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 05/12] perf: Add ability to attach user stack dump to sample Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:50 ` [tip:perf/core] " tip-bot for Frederic Weisbecker
2012-08-07 13:20 ` [PATCH 07/12] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check Jiri Olsa
` (5 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler, Ingo Molnar,
Jiri Olsa, Masami Hiramatsu, Paul Mackerras, Peter Zijlstra,
Robert Richter, Stephane Eranian, Tom Zanussi, Ulrich Drepper
From: Frederic Weisbecker <fweisbec@gmail.com>
Introducing following bits to the the perf_event_attr struct:
- exclude_callchain_kernel to filter out kernel callchain
from the sample dump
- exclude_callchain_user to filter out user callchain
from the sample dump
We need to be able to disable standard user callchain dump
when we use the dwarf cfi callchain mode, because frame
pointer based user callchains are useless in this mode.
Implementing also exclude_callchain_kernel to have complete
set of options.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
[ Added kernel callchains filtering ]
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
include/linux/perf_event.h | 5 ++++-
kernel/events/callchain.c | 38 ++++++++++++++++++++++++--------------
2 files changed, 28 insertions(+), 15 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d1d25f6..297ca3d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -268,7 +268,10 @@ struct perf_event_attr {
exclude_host : 1, /* don't count in host */
exclude_guest : 1, /* don't count in guest */
- __reserved_1 : 43;
+ exclude_callchain_kernel : 1, /* exclude kernel callchains */
+ exclude_callchain_user : 1, /* exclude user callchains */
+
+ __reserved_1 : 41;
union {
__u32 wakeup_events; /* wakeup every n events */
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 98d4597..c772061 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -159,6 +159,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
int rctx;
struct perf_callchain_entry *entry;
+ int kernel = !event->attr.exclude_callchain_kernel;
+ int user = !event->attr.exclude_callchain_user;
+
+ if (!kernel && !user)
+ return NULL;
entry = get_callchain_entry(&rctx);
if (rctx == -1)
@@ -169,24 +174,29 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
entry->nr = 0;
- if (!user_mode(regs)) {
+ if (kernel && !user_mode(regs)) {
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
perf_callchain_kernel(entry, regs);
- if (current->mm)
- regs = task_pt_regs(current);
- else
- regs = NULL;
}
- 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);
+ if (user) {
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ 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);
+ }
}
exit_put:
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf: Add attribute to filter out callchains
2012-08-07 13:20 ` [PATCH 06/12] perf: Add attribute to filter out callchains Jiri Olsa
@ 2012-08-21 15:50 ` tip-bot for Frederic Weisbecker
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Frederic Weisbecker @ 2012-08-21 15:50 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: d077526485d5c9b12fe85d0b2b3b7041e6bc5f91
Gitweb: http://git.kernel.org/tip/d077526485d5c9b12fe85d0b2b3b7041e6bc5f91
Author: Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Tue, 7 Aug 2012 15:20:41 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 12:40:57 -0300
perf: Add attribute to filter out callchains
Introducing following bits to the the perf_event_attr struct:
- exclude_callchain_kernel to filter out kernel callchain
from the sample dump
- exclude_callchain_user to filter out user callchain
from the sample dump
We need to be able to disable standard user callchain dump when we use
the dwarf cfi callchain mode, because frame pointer based user
callchains are useless in this mode.
Implementing also exclude_callchain_kernel to have complete set of
options.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
[ Added kernel callchains filtering ]
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-7-git-send-email-jolsa@redhat.com
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
include/linux/perf_event.h | 5 ++++-
kernel/events/callchain.c | 38 ++++++++++++++++++++++++--------------
2 files changed, 28 insertions(+), 15 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d1d25f6..297ca3d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -268,7 +268,10 @@ struct perf_event_attr {
exclude_host : 1, /* don't count in host */
exclude_guest : 1, /* don't count in guest */
- __reserved_1 : 43;
+ exclude_callchain_kernel : 1, /* exclude kernel callchains */
+ exclude_callchain_user : 1, /* exclude user callchains */
+
+ __reserved_1 : 41;
union {
__u32 wakeup_events; /* wakeup every n events */
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 98d4597..c772061 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -159,6 +159,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
int rctx;
struct perf_callchain_entry *entry;
+ int kernel = !event->attr.exclude_callchain_kernel;
+ int user = !event->attr.exclude_callchain_user;
+
+ if (!kernel && !user)
+ return NULL;
entry = get_callchain_entry(&rctx);
if (rctx == -1)
@@ -169,24 +174,29 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
entry->nr = 0;
- if (!user_mode(regs)) {
+ if (kernel && !user_mode(regs)) {
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
perf_callchain_kernel(entry, regs);
- if (current->mm)
- regs = task_pt_regs(current);
- else
- regs = NULL;
}
- 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);
+ if (user) {
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ 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);
+ }
}
exit_put:
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 07/12] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (5 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 06/12] perf: Add attribute to filter out callchains Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:51 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 08/12] perf tools: Add interface to arch registers sets Jiri Olsa
` (4 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Updating attr_file_abi_sizes array with PERF_ATTR_SIZE_VER2 version,
so we have the swap check complete.
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
| 1 +
1 file changed, 1 insertion(+)
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 74ea3c2..db91425 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1829,6 +1829,7 @@ out_free:
static const int attr_file_abi_sizes[] = {
[0] = PERF_ATTR_SIZE_VER0,
[1] = PERF_ATTR_SIZE_VER1,
+ [2] = PERF_ATTR_SIZE_VER2,
0,
};
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check
2012-08-07 13:20 ` [PATCH 07/12] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check Jiri Olsa
@ 2012-08-21 15:51 ` tip-bot for Jiri Olsa
2012-08-21 17:12 ` Peter Zijlstra
0 siblings, 1 reply; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:51 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 239cc47819ec5e1acde42d416755c332ed5cf2c8
Gitweb: http://git.kernel.org/tip/239cc47819ec5e1acde42d416755c332ed5cf2c8
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:42 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 16:32:03 -0300
perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check
Updating attr_file_abi_sizes array with PERF_ATTR_SIZE_VER2 version, so
we have the swap check complete.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-8-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
| 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b2da439..dd5a53c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1829,6 +1829,7 @@ out_free:
static const int attr_file_abi_sizes[] = {
[0] = PERF_ATTR_SIZE_VER0,
[1] = PERF_ATTR_SIZE_VER1,
+ [2] = PERF_ATTR_SIZE_VER2,
0,
};
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [tip:perf/core] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check
2012-08-21 15:51 ` [tip:perf/core] " tip-bot for Jiri Olsa
@ 2012-08-21 17:12 ` Peter Zijlstra
2012-08-22 8:31 ` Jiri Olsa
0 siblings, 1 reply; 32+ messages in thread
From: Peter Zijlstra @ 2012-08-21 17:12 UTC (permalink / raw)
To: mingo, eranian, acme, gorcunov, benjamin.redelings, jolsa,
fweisbec, robert.richter, drepper, tglx, cjashfor, asharma,
paulus, linux-kernel, hpa, fche, tzanussi, masami.hiramatsu.pt,
mingo
Cc: linux-tip-commits
On Tue, 2012-08-21 at 08:51 -0700, tip-bot for Jiri Olsa wrote:
> @@ -1829,6 +1829,7 @@ out_free:
> static const int attr_file_abi_sizes[] = {
> [0] = PERF_ATTR_SIZE_VER0,
> [1] = PERF_ATTR_SIZE_VER1,
> + [2] = PERF_ATTR_SIZE_VER2,
> 0,
> };
Didn't we just get to VER4 ?
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [tip:perf/core] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check
2012-08-21 17:12 ` Peter Zijlstra
@ 2012-08-22 8:31 ` Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: Jiri Olsa @ 2012-08-22 8:31 UTC (permalink / raw)
To: Peter Zijlstra
Cc: mingo, eranian, acme, gorcunov, benjamin.redelings, fweisbec,
robert.richter, drepper, tglx, cjashfor, asharma, paulus,
linux-kernel, hpa, fche, tzanussi, masami.hiramatsu.pt, mingo,
linux-tip-commits
On Tue, Aug 21, 2012 at 07:12:10PM +0200, Peter Zijlstra wrote:
> On Tue, 2012-08-21 at 08:51 -0700, tip-bot for Jiri Olsa wrote:
> > @@ -1829,6 +1829,7 @@ out_free:
> > static const int attr_file_abi_sizes[] = {
> > [0] = PERF_ATTR_SIZE_VER0,
> > [1] = PERF_ATTR_SIZE_VER1,
> > + [2] = PERF_ATTR_SIZE_VER2,
> > 0,
> > };
>
> Didn't we just get to VER4 ?
that's leftover for the branch_sample_type addition
jirka
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH 08/12] perf tools: Add interface to arch registers sets
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (6 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 07/12] perf tools: Adding PERF_ATTR_SIZE_VER2 to the header swap check Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:52 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 09/12] perf tools: Add libunwind dependency for DWARF CFI unwinding Jiri Olsa
` (3 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Adding header files to access unified API for arch registers.
util/perf_regs.h - global perf_reg declarations
arch/x86/include/perf_regs.h - x86 arch specific
Adding perf_reg_name function to obtain register name based
on the reg ID value, and PERF_REGS_MASK macro with mask
definition of all current arch registers (will be used in
unwind patches).
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/Makefile | 13 +++++-
tools/perf/arch/x86/include/perf_regs.h | 80 +++++++++++++++++++++++++++++++++
tools/perf/util/perf_regs.h | 14 ++++++
3 files changed, 106 insertions(+), 1 deletion(-)
create mode 100644 tools/perf/arch/x86/include/perf_regs.h
create mode 100644 tools/perf/util/perf_regs.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 35655c3..f5bf476 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -50,13 +50,15 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-e s/s390x/s390/ -e s/parisc64/parisc/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-e s/sh[234].*/sh/ )
+NO_PERF_REGS := 1
CC = $(CROSS_COMPILE)gcc
AR = $(CROSS_COMPILE)ar
# Additional ARCH settings for x86
ifeq ($(ARCH),i386)
- ARCH := x86
+ ARCH := x86
+ NO_PERF_REGS := 0
endif
ifeq ($(ARCH),x86_64)
ARCH := x86
@@ -69,6 +71,7 @@ ifeq ($(ARCH),x86_64)
ARCH_CFLAGS := -DARCH_X86_64
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
+ NO_PERF_REGS := 0
endif
# Treat warnings as errors unless directed not to
@@ -321,6 +324,7 @@ LIB_H += $(TRACE_EVENT_DIR)event-parse.h
LIB_H += util/target.h
LIB_H += util/rblist.h
LIB_H += util/intlist.h
+LIB_H += util/perf_regs.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -674,6 +678,13 @@ else
endif
endif
+ifeq ($(NO_PERF_REGS),0)
+ ifeq ($(ARCH),x86)
+ LIB_H += arch/x86/include/perf_regs.h
+ endif
+else
+ BASIC_CFLAGS += -DNO_PERF_REGS
+endif
ifdef NO_STRLCPY
BASIC_CFLAGS += -DNO_STRLCPY
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
new file mode 100644
index 0000000..46fc9f1
--- /dev/null
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -0,0 +1,80 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include "../../util/types.h"
+#include "../../../../../arch/x86/include/asm/perf_regs.h"
+
+#ifndef ARCH_X86_64
+#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#else
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#endif
+#define PERF_REG_IP PERF_REG_X86_IP
+#define PERF_REG_SP PERF_REG_X86_SP
+
+static inline const char *perf_reg_name(int id)
+{
+ switch (id) {
+ case PERF_REG_X86_AX:
+ return "AX";
+ case PERF_REG_X86_BX:
+ return "BX";
+ case PERF_REG_X86_CX:
+ return "CX";
+ case PERF_REG_X86_DX:
+ return "DX";
+ case PERF_REG_X86_SI:
+ return "SI";
+ case PERF_REG_X86_DI:
+ return "DI";
+ case PERF_REG_X86_BP:
+ return "BP";
+ case PERF_REG_X86_SP:
+ return "SP";
+ case PERF_REG_X86_IP:
+ return "IP";
+ case PERF_REG_X86_FLAGS:
+ return "FLAGS";
+ case PERF_REG_X86_CS:
+ return "CS";
+ case PERF_REG_X86_SS:
+ return "SS";
+ case PERF_REG_X86_DS:
+ return "DS";
+ case PERF_REG_X86_ES:
+ return "ES";
+ case PERF_REG_X86_FS:
+ return "FS";
+ case PERF_REG_X86_GS:
+ return "GS";
+#ifdef ARCH_X86_64
+ case PERF_REG_X86_R8:
+ return "R8";
+ case PERF_REG_X86_R9:
+ return "R9";
+ case PERF_REG_X86_R10:
+ return "R10";
+ case PERF_REG_X86_R11:
+ return "R11";
+ case PERF_REG_X86_R12:
+ return "R12";
+ case PERF_REG_X86_R13:
+ return "R13";
+ case PERF_REG_X86_R14:
+ return "R14";
+ case PERF_REG_X86_R15:
+ return "R15";
+#endif /* ARCH_X86_64 */
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
new file mode 100644
index 0000000..9bd6c4e
--- /dev/null
+++ b/tools/perf/util/perf_regs.h
@@ -0,0 +1,14 @@
+#ifndef __PERF_REGS_H
+#define __PERF_REGS_H
+
+#ifndef NO_PERF_REGS
+#include <perf_regs.h>
+#else
+#define PERF_REGS_MASK 0
+
+static inline const char *perf_reg_name(int id __used)
+{
+ return NULL;
+}
+#endif /* NO_PERF_REGS */
+#endif /* __PERF_REGS_H */
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf tools: Add interface to arch registers sets
2012-08-07 13:20 ` [PATCH 08/12] perf tools: Add interface to arch registers sets Jiri Olsa
@ 2012-08-21 15:52 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:52 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 2bcd355b71dafa5793a680c5db043abe9f708418
Gitweb: http://git.kernel.org/tip/2bcd355b71dafa5793a680c5db043abe9f708418
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:43 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 16:32:59 -0300
perf tools: Add interface to arch registers sets
Adding header files to access unified API for arch registers.
util/perf_regs.h - global perf_reg declarations
arch/x86/include/perf_regs.h - x86 arch specific
Adding perf_reg_name function to obtain register name based on the reg
ID value, and PERF_REGS_MASK macro with mask definition of all current
arch registers (will be used in unwind patches).
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-9-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile | 13 +++++-
tools/perf/arch/x86/include/perf_regs.h | 80 +++++++++++++++++++++++++++++++
tools/perf/util/perf_regs.h | 14 +++++
3 files changed, 106 insertions(+), 1 deletions(-)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index de6aa8c..27ae84b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -55,13 +55,15 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-e s/s390x/s390/ -e s/parisc64/parisc/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-e s/sh[234].*/sh/ )
+NO_PERF_REGS := 1
CC = $(CROSS_COMPILE)gcc
AR = $(CROSS_COMPILE)ar
# Additional ARCH settings for x86
ifeq ($(ARCH),i386)
- ARCH := x86
+ ARCH := x86
+ NO_PERF_REGS := 0
endif
ifeq ($(ARCH),x86_64)
ARCH := x86
@@ -74,6 +76,7 @@ ifeq ($(ARCH),x86_64)
ARCH_CFLAGS := -DARCH_X86_64
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
+ NO_PERF_REGS := 0
endif
# Treat warnings as errors unless directed not to
@@ -326,6 +329,7 @@ LIB_H += $(TRACE_EVENT_DIR)event-parse.h
LIB_H += util/target.h
LIB_H += util/rblist.h
LIB_H += util/intlist.h
+LIB_H += util/perf_regs.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -704,6 +708,13 @@ else
endif
endif
+ifeq ($(NO_PERF_REGS),0)
+ ifeq ($(ARCH),x86)
+ LIB_H += arch/x86/include/perf_regs.h
+ endif
+else
+ BASIC_CFLAGS += -DNO_PERF_REGS
+endif
ifdef NO_STRLCPY
BASIC_CFLAGS += -DNO_STRLCPY
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
new file mode 100644
index 0000000..46fc9f1
--- /dev/null
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -0,0 +1,80 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include "../../util/types.h"
+#include "../../../../../arch/x86/include/asm/perf_regs.h"
+
+#ifndef ARCH_X86_64
+#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#else
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#endif
+#define PERF_REG_IP PERF_REG_X86_IP
+#define PERF_REG_SP PERF_REG_X86_SP
+
+static inline const char *perf_reg_name(int id)
+{
+ switch (id) {
+ case PERF_REG_X86_AX:
+ return "AX";
+ case PERF_REG_X86_BX:
+ return "BX";
+ case PERF_REG_X86_CX:
+ return "CX";
+ case PERF_REG_X86_DX:
+ return "DX";
+ case PERF_REG_X86_SI:
+ return "SI";
+ case PERF_REG_X86_DI:
+ return "DI";
+ case PERF_REG_X86_BP:
+ return "BP";
+ case PERF_REG_X86_SP:
+ return "SP";
+ case PERF_REG_X86_IP:
+ return "IP";
+ case PERF_REG_X86_FLAGS:
+ return "FLAGS";
+ case PERF_REG_X86_CS:
+ return "CS";
+ case PERF_REG_X86_SS:
+ return "SS";
+ case PERF_REG_X86_DS:
+ return "DS";
+ case PERF_REG_X86_ES:
+ return "ES";
+ case PERF_REG_X86_FS:
+ return "FS";
+ case PERF_REG_X86_GS:
+ return "GS";
+#ifdef ARCH_X86_64
+ case PERF_REG_X86_R8:
+ return "R8";
+ case PERF_REG_X86_R9:
+ return "R9";
+ case PERF_REG_X86_R10:
+ return "R10";
+ case PERF_REG_X86_R11:
+ return "R11";
+ case PERF_REG_X86_R12:
+ return "R12";
+ case PERF_REG_X86_R13:
+ return "R13";
+ case PERF_REG_X86_R14:
+ return "R14";
+ case PERF_REG_X86_R15:
+ return "R15";
+#endif /* ARCH_X86_64 */
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
new file mode 100644
index 0000000..9bd6c4e
--- /dev/null
+++ b/tools/perf/util/perf_regs.h
@@ -0,0 +1,14 @@
+#ifndef __PERF_REGS_H
+#define __PERF_REGS_H
+
+#ifndef NO_PERF_REGS
+#include <perf_regs.h>
+#else
+#define PERF_REGS_MASK 0
+
+static inline const char *perf_reg_name(int id __used)
+{
+ return NULL;
+}
+#endif /* NO_PERF_REGS */
+#endif /* __PERF_REGS_H */
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 09/12] perf tools: Add libunwind dependency for DWARF CFI unwinding
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (7 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 08/12] perf tools: Add interface to arch registers sets Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:53 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 10/12] perf tools: Support user regs and stack in sample parsing Jiri Olsa
` (2 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Adding libunwind to be linked with perf if available. It's required
for the to get dwarf cfi unwinding support.
Also building perf with the dwarf call frame informations by default,
so that we can unwind callchains in perf itself.
Adding LIBUNWIND_DIR Makefile variable allowing user to specify
the directory with libunwind to be linked. This is used for
debug purposes.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/Makefile | 30 +++++++++++++++++++++++++++++-
tools/perf/config/feature-tests.mak | 25 +++++++++++++++++++++++++
2 files changed, 54 insertions(+), 1 deletion(-)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index f5bf476..076ba2f 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -38,6 +38,9 @@ include config/utilities.mak
# Define NO_NEWT if you do not want TUI support.
#
# Define NO_DEMANGLE if you do not want C++ symbol demangling.
+#
+# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
+# backtrace post unwind.
$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -59,6 +62,7 @@ AR = $(CROSS_COMPILE)ar
ifeq ($(ARCH),i386)
ARCH := x86
NO_PERF_REGS := 0
+ LIBUNWIND_LIBS = -lunwind -lunwind-x86
endif
ifeq ($(ARCH),x86_64)
ARCH := x86
@@ -72,6 +76,7 @@ ifeq ($(ARCH),x86_64)
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
NO_PERF_REGS := 0
+ LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
endif
# Treat warnings as errors unless directed not to
@@ -92,7 +97,7 @@ ifdef PARSER_DEBUG
PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
endif
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -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 = $(LDFLAGS)
@@ -461,6 +466,21 @@ ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y)
endif # Dwarf support
endif # NO_DWARF
+ifndef NO_LIBUNWIND
+# for linking with debug library, run like:
+# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+ifdef LIBUNWIND_DIR
+ LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include
+ LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+endif
+
+FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND)),y)
+ msg := $(warning No libunwind found. Please install libunwind >= 0.99);
+ NO_LIBUNWIND := 1
+endif # Libunwind support
+endif # NO_LIBUNWIND
+
-include arch/$(ARCH)/Makefile
ifneq ($(OUTPUT),)
@@ -492,6 +512,14 @@ else
endif # PERF_HAVE_DWARF_REGS
endif # NO_DWARF
+ifdef NO_LIBUNWIND
+ BASIC_CFLAGS += -DNO_LIBUNWIND_SUPPORT
+else
+ EXTLIBS += $(LIBUNWIND_LIBS)
+ BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
+ BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
+endif
+
ifdef NO_NEWT
BASIC_CFLAGS += -DNO_NEWT_SUPPORT
else
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 6c18785..2f1156a 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -154,3 +154,28 @@ int main(void)
return 0;
}
endef
+
+ifndef NO_LIBUNWIND
+define SOURCE_LIBUNWIND
+#include <libunwind.h>
+#include <stdlib.h>
+
+extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+int main(void)
+{
+ unw_addr_space_t addr_space;
+ addr_space = unw_create_addr_space(NULL, 0);
+ unw_init_remote(NULL, addr_space, NULL);
+ dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL);
+ return 0;
+}
+endef
+endif
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf tools: Add libunwind dependency for DWARF CFI unwinding
2012-08-07 13:20 ` [PATCH 09/12] perf tools: Add libunwind dependency for DWARF CFI unwinding Jiri Olsa
@ 2012-08-21 15:53 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:53 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 6a40cd90f5deb6dec322eeb54587ae55a934db2c
Gitweb: http://git.kernel.org/tip/6a40cd90f5deb6dec322eeb54587ae55a934db2c
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:44 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 16:46:07 -0300
perf tools: Add libunwind dependency for DWARF CFI unwinding
Adding libunwind to be linked with perf if available. It's required
for the to get dwarf cfi unwinding support.
Also building perf with the dwarf call frame informations by default,
so that we can unwind callchains in perf itself.
Adding LIBUNWIND_DIR Makefile variable allowing user to specify
the directory with libunwind to be linked. This is used for
debug purposes.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-10-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile | 29 ++++++++++++++++++++++++++++-
tools/perf/config/feature-tests.mak | 25 +++++++++++++++++++++++++
2 files changed, 53 insertions(+), 1 deletions(-)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 27ae84b..0aee6a9 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -43,6 +43,8 @@ include config/utilities.mak
#
# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
#
+# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
+# backtrace post unwind.
$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -64,6 +66,7 @@ AR = $(CROSS_COMPILE)ar
ifeq ($(ARCH),i386)
ARCH := x86
NO_PERF_REGS := 0
+ LIBUNWIND_LIBS = -lunwind -lunwind-x86
endif
ifeq ($(ARCH),x86_64)
ARCH := x86
@@ -77,6 +80,7 @@ ifeq ($(ARCH),x86_64)
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
NO_PERF_REGS := 0
+ LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
endif
# Treat warnings as errors unless directed not to
@@ -97,7 +101,7 @@ ifdef PARSER_DEBUG
PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
endif
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -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 = $(LDFLAGS)
@@ -476,6 +480,21 @@ ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y)
endif
endif # NO_LIBELF
+ifndef NO_LIBUNWIND
+# for linking with debug library, run like:
+# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+ifdef LIBUNWIND_DIR
+ LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include
+ LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+endif
+
+FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND)),y)
+ msg := $(warning No libunwind found. Please install libunwind >= 0.99);
+ NO_LIBUNWIND := 1
+endif # Libunwind support
+endif # NO_LIBUNWIND
+
-include arch/$(ARCH)/Makefile
ifneq ($(OUTPUT),)
@@ -522,6 +541,14 @@ endif # PERF_HAVE_DWARF_REGS
endif # NO_DWARF
endif # NO_LIBELF
+ifdef NO_LIBUNWIND
+ BASIC_CFLAGS += -DNO_LIBUNWIND_SUPPORT
+else
+ EXTLIBS += $(LIBUNWIND_LIBS)
+ BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
+ BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
+endif
+
ifdef NO_NEWT
BASIC_CFLAGS += -DNO_NEWT_SUPPORT
else
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 6c18785..2f1156a 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -154,3 +154,28 @@ int main(void)
return 0;
}
endef
+
+ifndef NO_LIBUNWIND
+define SOURCE_LIBUNWIND
+#include <libunwind.h>
+#include <stdlib.h>
+
+extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+int main(void)
+{
+ unw_addr_space_t addr_space;
+ addr_space = unw_create_addr_space(NULL, 0);
+ unw_init_remote(NULL, addr_space, NULL);
+ dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL);
+ return 0;
+}
+endef
+endif
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 10/12] perf tools: Support user regs and stack in sample parsing
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (8 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 09/12] perf tools: Add libunwind dependency for DWARF CFI unwinding Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:54 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 11/12] perf tools: Support for DWARF CFI unwinding on post processing Jiri Olsa
2012-08-07 13:20 ` [PATCH 12/12] perf tools: Support for DWARF mode callchain Jiri Olsa
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
Adding following info to be parsed out of the event sample:
- user register set
- user stack dump
Both are global and specific to all events within the session.
This info will be used in the unwind patches coming in shortly.
Adding simple output printout (report -D) for both register and
stack dumps.
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
[ Use evsel->attr.sample_regs_user ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/util/event.h | 12 ++++++++++++
tools/perf/util/evsel.c | 28 ++++++++++++++++++++++++++++
| 2 ++
tools/perf/util/session.c | 41 ++++++++++++++++++++++++++++++++++++++---
4 files changed, 80 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d84870b..0e088d0 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -69,6 +69,16 @@ struct sample_event {
u64 array[];
};
+struct regs_dump {
+ u64 *regs;
+};
+
+struct stack_dump {
+ u16 offset;
+ u64 size;
+ char *data;
+};
+
struct perf_sample {
u64 ip;
u32 pid, tid;
@@ -82,6 +92,8 @@ struct perf_sample {
void *raw_data;
struct ip_callchain *callchain;
struct branch_stack *branch_stack;
+ struct regs_dump user_regs;
+ struct stack_dump user_stack;
};
#define BUILD_ID_SIZE 20
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2eaae14..a2da682 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -8,6 +8,7 @@
*/
#include <byteswap.h>
+#include <linux/bitops.h>
#include "asm/bug.h"
#include "evsel.h"
#include "evlist.h"
@@ -733,6 +734,7 @@ 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;
+ u64 regs_user = evsel->attr.sample_regs_user;
const u64 *array;
/*
@@ -869,6 +871,32 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
sz /= sizeof(u64);
array += sz;
}
+
+ if (type & PERF_SAMPLE_REGS_USER) {
+ /* First u64 tells us if we have any regs in sample. */
+ u64 avail = *array++;
+
+ if (avail) {
+ data->user_regs.regs = (u64 *)array;
+ array += hweight_long(regs_user);
+ }
+ }
+
+ if (type & PERF_SAMPLE_STACK_USER) {
+ u64 size = *array++;
+
+ data->user_stack.offset = ((char *)(array - 1)
+ - (char *) event);
+
+ if (!size) {
+ data->user_stack.size = 0;
+ } else {
+ data->user_stack.data = (char *)array;
+ array += size / sizeof(*array);
+ data->user_stack.size = *array;
+ }
+ }
+
return 0;
}
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index db91425..24c489b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1830,6 +1830,8 @@ static const int attr_file_abi_sizes[] = {
[0] = PERF_ATTR_SIZE_VER0,
[1] = PERF_ATTR_SIZE_VER1,
[2] = PERF_ATTR_SIZE_VER2,
+ [3] = PERF_ATTR_SIZE_VER3,
+ [4] = PERF_ATTR_SIZE_VER4,
0,
};
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2437fb0..c9ed7e3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,7 @@
#include "util.h"
#include "cpumap.h"
#include "event-parse.h"
+#include "perf_regs.h"
static int perf_session__open(struct perf_session *self, bool force)
{
@@ -860,6 +861,34 @@ static void branch_stack__printf(struct perf_sample *sample)
sample->branch_stack->entries[i].to);
}
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+ unsigned rid, i = 0;
+
+ for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+ u64 val = regs[i++];
+
+ printf(".... %-5s 0x%" PRIx64 "\n",
+ perf_reg_name(rid), val);
+ }
+}
+
+static void regs_user__printf(struct perf_sample *sample, u64 mask)
+{
+ struct regs_dump *user_regs = &sample->user_regs;
+
+ if (user_regs->regs) {
+ printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+ regs_dump__printf(mask, user_regs->regs);
+ }
+}
+
+static void stack_user__printf(struct stack_dump *dump)
+{
+ printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
+ dump->size, dump->offset);
+}
+
static void perf_session__print_tstamp(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample)
@@ -897,7 +926,7 @@ static void dump_event(struct perf_session *session, union perf_event *event,
event->header.size, perf_event__name(event->header.type));
}
-static void dump_sample(struct perf_session *session, union perf_event *event,
+static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *sample)
{
u64 sample_type;
@@ -909,13 +938,19 @@ 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);
- sample_type = perf_evlist__sample_type(session->evlist);
+ sample_type = evsel->attr.sample_type;
if (sample_type & PERF_SAMPLE_CALLCHAIN)
callchain__printf(sample);
if (sample_type & PERF_SAMPLE_BRANCH_STACK)
branch_stack__printf(sample);
+
+ if (sample_type & PERF_SAMPLE_REGS_USER)
+ regs_user__printf(sample, evsel->attr.sample_regs_user);
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ stack_user__printf(&sample->user_stack);
}
static struct machine *
@@ -973,7 +1008,7 @@ static int perf_session_deliver_event(struct perf_session *session,
switch (event->header.type) {
case PERF_RECORD_SAMPLE:
- dump_sample(session, event, sample);
+ dump_sample(evsel, event, sample);
if (evsel == NULL) {
++session->hists.stats.nr_unknown_id;
return 0;
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf tools: Support user regs and stack in sample parsing
2012-08-07 13:20 ` [PATCH 10/12] perf tools: Support user regs and stack in sample parsing Jiri Olsa
@ 2012-08-21 15:54 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:54 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 0f6a30150ca2e0cf4f893e7173d61434a3c02e0e
Gitweb: http://git.kernel.org/tip/0f6a30150ca2e0cf4f893e7173d61434a3c02e0e
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:45 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 10 Aug 2012 16:47:02 -0300
perf tools: Support user regs and stack in sample parsing
Adding following info to be parsed out of the event sample:
- user register set
- user stack dump
Both are global and specific to all events within the session.
This info will be used in the unwind patches coming in shortly.
Adding simple output printout (report -D) for both register and
stack dumps.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-11-git-send-email-jolsa@redhat.com
[ Use evsel->attr.sample_regs_user ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/event.h | 12 ++++++++++++
tools/perf/util/evsel.c | 28 ++++++++++++++++++++++++++++
| 2 ++
tools/perf/util/session.c | 41 ++++++++++++++++++++++++++++++++++++++---
4 files changed, 80 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d84870b..0e088d0 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -69,6 +69,16 @@ struct sample_event {
u64 array[];
};
+struct regs_dump {
+ u64 *regs;
+};
+
+struct stack_dump {
+ u16 offset;
+ u64 size;
+ char *data;
+};
+
struct perf_sample {
u64 ip;
u32 pid, tid;
@@ -82,6 +92,8 @@ struct perf_sample {
void *raw_data;
struct ip_callchain *callchain;
struct branch_stack *branch_stack;
+ struct regs_dump user_regs;
+ struct stack_dump user_stack;
};
#define BUILD_ID_SIZE 20
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2eaae14..a2da682 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -8,6 +8,7 @@
*/
#include <byteswap.h>
+#include <linux/bitops.h>
#include "asm/bug.h"
#include "evsel.h"
#include "evlist.h"
@@ -733,6 +734,7 @@ 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;
+ u64 regs_user = evsel->attr.sample_regs_user;
const u64 *array;
/*
@@ -869,6 +871,32 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
sz /= sizeof(u64);
array += sz;
}
+
+ if (type & PERF_SAMPLE_REGS_USER) {
+ /* First u64 tells us if we have any regs in sample. */
+ u64 avail = *array++;
+
+ if (avail) {
+ data->user_regs.regs = (u64 *)array;
+ array += hweight_long(regs_user);
+ }
+ }
+
+ if (type & PERF_SAMPLE_STACK_USER) {
+ u64 size = *array++;
+
+ data->user_stack.offset = ((char *)(array - 1)
+ - (char *) event);
+
+ if (!size) {
+ data->user_stack.size = 0;
+ } else {
+ data->user_stack.data = (char *)array;
+ array += size / sizeof(*array);
+ data->user_stack.size = *array;
+ }
+ }
+
return 0;
}
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index dd5a53c..7e7d34f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1830,6 +1830,8 @@ static const int attr_file_abi_sizes[] = {
[0] = PERF_ATTR_SIZE_VER0,
[1] = PERF_ATTR_SIZE_VER1,
[2] = PERF_ATTR_SIZE_VER2,
+ [3] = PERF_ATTR_SIZE_VER3,
+ [4] = PERF_ATTR_SIZE_VER4,
0,
};
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2437fb0..c9ed7e3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,7 @@
#include "util.h"
#include "cpumap.h"
#include "event-parse.h"
+#include "perf_regs.h"
static int perf_session__open(struct perf_session *self, bool force)
{
@@ -860,6 +861,34 @@ static void branch_stack__printf(struct perf_sample *sample)
sample->branch_stack->entries[i].to);
}
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+ unsigned rid, i = 0;
+
+ for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+ u64 val = regs[i++];
+
+ printf(".... %-5s 0x%" PRIx64 "\n",
+ perf_reg_name(rid), val);
+ }
+}
+
+static void regs_user__printf(struct perf_sample *sample, u64 mask)
+{
+ struct regs_dump *user_regs = &sample->user_regs;
+
+ if (user_regs->regs) {
+ printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+ regs_dump__printf(mask, user_regs->regs);
+ }
+}
+
+static void stack_user__printf(struct stack_dump *dump)
+{
+ printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
+ dump->size, dump->offset);
+}
+
static void perf_session__print_tstamp(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample)
@@ -897,7 +926,7 @@ static void dump_event(struct perf_session *session, union perf_event *event,
event->header.size, perf_event__name(event->header.type));
}
-static void dump_sample(struct perf_session *session, union perf_event *event,
+static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *sample)
{
u64 sample_type;
@@ -909,13 +938,19 @@ 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);
- sample_type = perf_evlist__sample_type(session->evlist);
+ sample_type = evsel->attr.sample_type;
if (sample_type & PERF_SAMPLE_CALLCHAIN)
callchain__printf(sample);
if (sample_type & PERF_SAMPLE_BRANCH_STACK)
branch_stack__printf(sample);
+
+ if (sample_type & PERF_SAMPLE_REGS_USER)
+ regs_user__printf(sample, evsel->attr.sample_regs_user);
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ stack_user__printf(&sample->user_stack);
}
static struct machine *
@@ -973,7 +1008,7 @@ static int perf_session_deliver_event(struct perf_session *session,
switch (event->header.type) {
case PERF_RECORD_SAMPLE:
- dump_sample(session, event, sample);
+ dump_sample(evsel, event, sample);
if (evsel == NULL) {
++session->hists.stats.nr_unknown_id;
return 0;
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 11/12] perf tools: Support for DWARF CFI unwinding on post processing
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (9 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 10/12] perf tools: Support user regs and stack in sample parsing Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:55 ` [tip:perf/core] " tip-bot for Jiri Olsa
2012-08-07 13:20 ` [PATCH 12/12] perf tools: Support for DWARF mode callchain Jiri Olsa
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
This brings the support for DWARF cfi unwinding on perf post
processing. Call frame informations are retrieved and then passed
to libunwind that requests memory and register content from the
applications.
Adding unwind object to handle the user stack backtrace based
on the user register values and user stack dump.
The unwind object access the libunwind via remote interface
and provides to it all the necessary data to unwind the stack.
The unwind interface provides following function:
unwind__get_entries
And callback (specified in above function) to retrieve
the backtrace entries:
typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry,
void *arg);
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
[ Replaced use of perf_session by usage of perf_evsel ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/Makefile | 2 +
tools/perf/arch/x86/Makefile | 3 +
tools/perf/arch/x86/util/unwind.c | 111 ++++++
tools/perf/builtin-report.c | 18 +-
tools/perf/builtin-script.c | 6 +-
tools/perf/builtin-top.c | 6 +-
tools/perf/util/include/linux/compiler.h | 1 +
tools/perf/util/map.h | 5 +-
tools/perf/util/session.c | 66 +++-
tools/perf/util/session.h | 6 +-
tools/perf/util/trace-event.h | 2 +
tools/perf/util/unwind.c | 567 +++++++++++++++++++++++++++++++
tools/perf/util/unwind.h | 34 ++
13 files changed, 796 insertions(+), 31 deletions(-)
create mode 100644 tools/perf/arch/x86/util/unwind.c
create mode 100644 tools/perf/util/unwind.c
create mode 100644 tools/perf/util/unwind.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 076ba2f..ed47921 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -330,6 +330,7 @@ LIB_H += util/target.h
LIB_H += util/rblist.h
LIB_H += util/intlist.h
LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -518,6 +519,7 @@ else
EXTLIBS += $(LIBUNWIND_LIBS)
BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
+ LIB_OBJS += $(OUTPUT)util/unwind.o
endif
ifdef NO_NEWT
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 744e629..815841c 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -2,4 +2,7 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+endif
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind.c
new file mode 100644
index 0000000..78d956e
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind.c
@@ -0,0 +1,111 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+#ifdef ARCH_X86_64
+int unwind__arch_reg_id(int regnum)
+{
+ int id;
+
+ switch (regnum) {
+ case UNW_X86_64_RAX:
+ id = PERF_REG_X86_AX;
+ break;
+ case UNW_X86_64_RDX:
+ id = PERF_REG_X86_DX;
+ break;
+ case UNW_X86_64_RCX:
+ id = PERF_REG_X86_CX;
+ break;
+ case UNW_X86_64_RBX:
+ id = PERF_REG_X86_BX;
+ break;
+ case UNW_X86_64_RSI:
+ id = PERF_REG_X86_SI;
+ break;
+ case UNW_X86_64_RDI:
+ id = PERF_REG_X86_DI;
+ break;
+ case UNW_X86_64_RBP:
+ id = PERF_REG_X86_BP;
+ break;
+ case UNW_X86_64_RSP:
+ id = PERF_REG_X86_SP;
+ break;
+ case UNW_X86_64_R8:
+ id = PERF_REG_X86_R8;
+ break;
+ case UNW_X86_64_R9:
+ id = PERF_REG_X86_R9;
+ break;
+ case UNW_X86_64_R10:
+ id = PERF_REG_X86_R10;
+ break;
+ case UNW_X86_64_R11:
+ id = PERF_REG_X86_R11;
+ break;
+ case UNW_X86_64_R12:
+ id = PERF_REG_X86_R12;
+ break;
+ case UNW_X86_64_R13:
+ id = PERF_REG_X86_R13;
+ break;
+ case UNW_X86_64_R14:
+ id = PERF_REG_X86_R14;
+ break;
+ case UNW_X86_64_R15:
+ id = PERF_REG_X86_R15;
+ break;
+ case UNW_X86_64_RIP:
+ id = PERF_REG_X86_IP;
+ break;
+ default:
+ pr_err("unwind: invalid reg id %d\n", regnum);
+ return -EINVAL;
+ }
+
+ return id;
+}
+#else
+int unwind__arch_reg_id(int regnum)
+{
+ int id;
+
+ switch (regnum) {
+ case UNW_X86_EAX:
+ id = PERF_REG_X86_AX;
+ break;
+ case UNW_X86_EDX:
+ id = PERF_REG_X86_DX;
+ break;
+ case UNW_X86_ECX:
+ id = PERF_REG_X86_CX;
+ break;
+ case UNW_X86_EBX:
+ id = PERF_REG_X86_BX;
+ break;
+ case UNW_X86_ESI:
+ id = PERF_REG_X86_SI;
+ break;
+ case UNW_X86_EDI:
+ id = PERF_REG_X86_DI;
+ break;
+ case UNW_X86_EBP:
+ id = PERF_REG_X86_BP;
+ break;
+ case UNW_X86_ESP:
+ id = PERF_REG_X86_SP;
+ break;
+ case UNW_X86_EIP:
+ id = PERF_REG_X86_IP;
+ break;
+ default:
+ pr_err("unwind: invalid reg id %d\n", regnum);
+ return -EINVAL;
+ }
+
+ return id;
+}
+#endif /* ARCH_X86_64 */
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7c88a24..d618253 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -69,8 +69,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
- err = machine__resolve_callchain(machine, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
if (err)
return err;
}
@@ -140,8 +140,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
- err = machine__resolve_callchain(machine, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
if (err)
return err;
}
@@ -397,17 +397,17 @@ static int __cmd_report(struct perf_report *rep)
desc);
}
- if (dump_trace) {
- perf_session__fprintf_nr_events(session, stdout);
- goto out_delete;
- }
-
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
+ if (dump_trace) {
+ perf_session__fprintf_nr_events(session, stdout);
+ goto out_delete;
+ }
+
nr_samples = 0;
list_for_each_entry(pos, &session->evlist->entries, node) {
struct hists *hists = &pos->hists;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 1e60ab7..1dfe091 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -401,7 +401,7 @@ static void print_sample_bts(union perf_event *event,
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine,
+ perf_evsel__print_ip(evsel, event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
@@ -415,7 +415,7 @@ static void print_sample_bts(union perf_event *event,
printf("\n");
}
-static void process_event(union perf_event *event __unused,
+static void process_event(union perf_event *event,
struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
@@ -446,7 +446,7 @@ static void process_event(union perf_event *event __unused,
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine,
+ perf_evsel__print_ip(evsel, event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 68cd61e..e45a1ba 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -783,8 +783,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
- err = machine__resolve_callchain(machine, al.thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel,
+ al.thread, sample,
+ &parent);
+
if (err)
return;
}
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index 547628e..2dc8671 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -10,5 +10,6 @@
#endif
#define __used __attribute__((__unused__))
+#define __packed __attribute__((__packed__))
#endif
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 03a1e9b..2d98286 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -157,9 +157,12 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid);
void machine__exit(struct machine *self);
void machine__delete(struct machine *self);
+struct perf_evsel;
+struct perf_sample;
int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel,
struct thread *thread,
- struct ip_callchain *chain,
+ struct perf_sample *sample,
struct symbol **parent);
int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
u64 addr);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c9ed7e3..f7bb7ae 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,6 +16,7 @@
#include "cpumap.h"
#include "event-parse.h"
#include "perf_regs.h"
+#include "unwind.h"
static int perf_session__open(struct perf_session *self, bool force)
{
@@ -289,10 +290,11 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
return bi;
}
-int machine__resolve_callchain(struct machine *self,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent)
+static int machine__resolve_callchain_sample(struct machine *machine,
+ struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent)
+
{
u8 cpumode = PERF_RECORD_MISC_USER;
unsigned int i;
@@ -317,11 +319,14 @@ int machine__resolve_callchain(struct machine *self,
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
case PERF_CONTEXT_HV:
- cpumode = PERF_RECORD_MISC_HYPERVISOR; break;
+ cpumode = PERF_RECORD_MISC_HYPERVISOR;
+ break;
case PERF_CONTEXT_KERNEL:
- cpumode = PERF_RECORD_MISC_KERNEL; break;
+ cpumode = PERF_RECORD_MISC_KERNEL;
+ break;
case PERF_CONTEXT_USER:
- cpumode = PERF_RECORD_MISC_USER; break;
+ cpumode = PERF_RECORD_MISC_USER;
+ break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
@@ -336,7 +341,7 @@ int machine__resolve_callchain(struct machine *self,
}
al.filtered = false;
- thread__find_addr_location(thread, self, cpumode,
+ thread__find_addr_location(thread, machine, cpumode,
MAP__FUNCTION, ip, &al, NULL);
if (al.sym != NULL) {
if (sort__has_parent && !*parent &&
@@ -355,6 +360,40 @@ int machine__resolve_callchain(struct machine *self,
return 0;
}
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+ struct callchain_cursor *cursor = arg;
+ return callchain_cursor_append(cursor, entry->ip,
+ entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct perf_sample *sample,
+ struct symbol **parent)
+
+{
+ int ret;
+
+ callchain_cursor_reset(&callchain_cursor);
+
+ ret = machine__resolve_callchain_sample(machine, thread,
+ sample->callchain, parent);
+ if (ret)
+ return ret;
+
+ /* Can we do dwarf post unwind? */
+ if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+ (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+ return 0;
+
+ return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+ thread, evsel->attr.sample_regs_user,
+ sample);
+
+}
+
static int process_event_synth_tracing_data_stub(union perf_event *event __used,
struct perf_session *session __used)
{
@@ -1533,9 +1572,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
return NULL;
}
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, int print_sym,
- int print_dso, int print_symoffset)
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine,
+ int print_sym, int print_dso, int print_symoffset)
{
struct addr_location al;
struct callchain_cursor_node *node;
@@ -1549,8 +1588,9 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
if (symbol_conf.use_callchain && sample->callchain) {
- if (machine__resolve_callchain(machine, al.thread,
- sample->callchain, NULL) != 0) {
+
+ if (machine__resolve_callchain(machine, evsel, al.thread,
+ sample, NULL) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
return;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 1f7ec87..176a609 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -129,9 +129,9 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, int print_sym,
- int print_dso, int print_symoffset);
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine,
+ int print_sym, int print_dso, int print_symoffset);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 8fef1d6..0c3fd45 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -74,6 +74,8 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
void tracing_data_put(struct tracing_data *tdata);
+struct perf_session;
+
struct scripting_ops {
const char *name;
int (*start_script) (const char *script, int argc, const char **argv);
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
new file mode 100644
index 0000000..00a42aa
--- /dev/null
+++ b/tools/perf/util/unwind.c
@@ -0,0 +1,567 @@
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ * Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "util.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */
+#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit 0xff
+#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */
+#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */
+#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */
+#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */
+#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr 0x00 /* absolute value */
+#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */
+#define DW_EH_PE_aligned 0x50 /* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect 0x80
+ * #define DW_EH_PE_uleb128 0x01
+ * #define DW_EH_PE_udata2 0x02
+ * #define DW_EH_PE_sleb128 0x09
+ * #define DW_EH_PE_sdata2 0x0a
+ * #define DW_EH_PE_textrel 0x20
+ * #define DW_EH_PE_datarel 0x30
+ */
+
+struct unwind_info {
+ struct perf_sample *sample;
+ struct machine *machine;
+ struct thread *thread;
+ u64 sample_uregs;
+};
+
+#define dw_read(ptr, type, end) ({ \
+ type *__p = (type *) ptr; \
+ type __v; \
+ if ((__p + 1) > (type *) end) \
+ return -EINVAL; \
+ __v = *__p++; \
+ ptr = (typeof(ptr)) __p; \
+ __v; \
+ })
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+ u8 encoding)
+{
+ u8 *cur = *p;
+ *val = 0;
+
+ switch (encoding) {
+ case DW_EH_PE_omit:
+ *val = 0;
+ goto out;
+ case DW_EH_PE_ptr:
+ *val = dw_read(cur, unsigned long, end);
+ goto out;
+ default:
+ break;
+ }
+
+ switch (encoding & DW_EH_PE_APPL_MASK) {
+ case DW_EH_PE_absptr:
+ break;
+ case DW_EH_PE_pcrel:
+ *val = (unsigned long) cur;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if ((encoding & 0x07) == 0x00)
+ encoding |= DW_EH_PE_udata4;
+
+ switch (encoding & DW_EH_PE_FORMAT_MASK) {
+ case DW_EH_PE_sdata4:
+ *val += dw_read(cur, s32, end);
+ break;
+ case DW_EH_PE_udata4:
+ *val += dw_read(cur, u32, end);
+ break;
+ case DW_EH_PE_sdata8:
+ *val += dw_read(cur, s64, end);
+ break;
+ case DW_EH_PE_udata8:
+ *val += dw_read(cur, u64, end);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ out:
+ *p = cur;
+ return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({ \
+ u64 __v; \
+ if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \
+ return -EINVAL; \
+ } \
+ __v; \
+ })
+
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+ GElf_Shdr *shp, const char *name)
+{
+ Elf_Scn *sec = NULL;
+
+ while ((sec = elf_nextscn(elf, sec)) != NULL) {
+ char *str;
+
+ gelf_getshdr(sec, shp);
+ str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+ if (!strcmp(name, str))
+ break;
+ }
+
+ return sec;
+}
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ u64 offset = 0;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL)
+ return 0;
+
+ do {
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ break;
+
+ if (!elf_section_by_name(elf, &ehdr, &shdr, name))
+ break;
+
+ offset = shdr.sh_offset;
+ } while (0);
+
+ elf_end(elf);
+ return offset;
+}
+
+struct table_entry {
+ u32 start_ip_offset;
+ u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+ unsigned char version;
+ unsigned char eh_frame_ptr_enc;
+ unsigned char fde_count_enc;
+ unsigned char table_enc;
+
+ /*
+ * The rest of the header is variable-length and consists of the
+ * following members:
+ *
+ * encoded_t eh_frame_ptr;
+ * encoded_t fde_count;
+ */
+
+ /* A single encoded pointer should not be more than 8 bytes. */
+ u64 enc[2];
+
+ /*
+ * struct {
+ * encoded_t start_ip;
+ * encoded_t fde_addr;
+ * } binary_search_table[fde_count];
+ */
+ char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+ u64 offset, u64 *table_data, u64 *segbase,
+ u64 *fde_count)
+{
+ struct eh_frame_hdr hdr;
+ u8 *enc = (u8 *) &hdr.enc;
+ u8 *end = (u8 *) &hdr.data;
+ ssize_t r;
+
+ r = dso__data_read_offset(dso, machine, offset,
+ (u8 *) &hdr, sizeof(hdr));
+ if (r != sizeof(hdr))
+ return -EINVAL;
+
+ /* We dont need eh_frame_ptr, just skip it. */
+ dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+ *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+ *segbase = offset;
+ *table_data = (enc - (u8 *) &hdr) + offset;
+ return 0;
+}
+
+static int read_unwind_spec(struct dso *dso, struct machine *machine,
+ u64 *table_data, u64 *segbase, u64 *fde_count)
+{
+ int ret = -EINVAL, fd;
+ u64 offset;
+
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return -EINVAL;
+
+ offset = elf_section_offset(fd, ".eh_frame_hdr");
+ close(fd);
+
+ if (offset)
+ ret = unwind_spec_ehframe(dso, machine, offset,
+ table_data, segbase,
+ fde_count);
+
+ /* TODO .debug_frame check if eh_frame_hdr fails */
+ return ret;
+}
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+ struct addr_location al;
+
+ thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al);
+ return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+ int need_unwind_info, void *arg)
+{
+ struct unwind_info *ui = arg;
+ struct map *map;
+ unw_dyn_info_t di;
+ u64 table_data, segbase, fde_count;
+
+ map = find_map(ip, ui);
+ if (!map || !map->dso)
+ return -EINVAL;
+
+ pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+ if (read_unwind_spec(map->dso, ui->machine,
+ &table_data, &segbase, &fde_count))
+ return -EINVAL;
+
+ memset(&di, 0, sizeof(di));
+ di.format = UNW_INFO_FORMAT_REMOTE_TABLE;
+ di.start_ip = map->start;
+ di.end_ip = map->end;
+ di.u.rti.segbase = map->start + segbase;
+ di.u.rti.table_data = map->start + table_data;
+ di.u.rti.table_len = fde_count * sizeof(struct table_entry)
+ / sizeof(unw_word_t);
+ return dwarf_search_unwind_table(as, ip, &di, pi,
+ need_unwind_info, arg);
+}
+
+static int access_fpreg(unw_addr_space_t __used as, unw_regnum_t __used num,
+ unw_fpreg_t __used *val, int __used __write,
+ void __used *arg)
+{
+ pr_err("unwind: access_fpreg unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __used as,
+ unw_word_t __used *dil_addr,
+ void __used *arg)
+{
+ return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __used as, unw_cursor_t __used *cu,
+ void __used *arg)
+{
+ pr_err("unwind: resume unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __used as, unw_word_t __used addr,
+ char __used *bufp, size_t __used buf_len,
+ unw_word_t __used *offp, void __used *arg)
+{
+ pr_err("unwind: get_proc_name unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+ unw_word_t *data)
+{
+ struct addr_location al;
+ ssize_t size;
+
+ thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, addr, &al);
+ if (!al.map) {
+ pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+ return -1;
+ }
+
+ if (!al.map->dso)
+ return -1;
+
+ size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+ addr, (u8 *) data, sizeof(*data));
+
+ return !(size == sizeof(*data));
+}
+
+static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
+ u64 sample_regs)
+{
+ int i, idx = 0;
+
+ if (!(sample_regs & (1 << id)))
+ return -EINVAL;
+
+ for (i = 0; i < id; i++) {
+ if (sample_regs & (1 << i))
+ idx++;
+ }
+
+ *valp = regs->regs[idx];
+ return 0;
+}
+
+static int access_mem(unw_addr_space_t __used as,
+ unw_word_t addr, unw_word_t *valp,
+ int __write, void *arg)
+{
+ struct unwind_info *ui = arg;
+ struct stack_dump *stack = &ui->sample->user_stack;
+ unw_word_t start, end;
+ int offset;
+ int ret;
+
+ /* Don't support write, probably not needed. */
+ if (__write || !stack || !ui->sample->user_regs.regs) {
+ *valp = 0;
+ return 0;
+ }
+
+ ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
+ ui->sample_uregs);
+ if (ret)
+ return ret;
+
+ end = start + stack->size;
+
+ /* Check overflow. */
+ if (addr + sizeof(unw_word_t) < addr)
+ return -EINVAL;
+
+ if (addr < start || addr + sizeof(unw_word_t) >= end) {
+ ret = access_dso_mem(ui, addr, valp);
+ if (ret) {
+ pr_debug("unwind: access_mem %p not inside range %p-%p\n",
+ (void *)addr, (void *)start, (void *)end);
+ *valp = 0;
+ return ret;
+ }
+ return 0;
+ }
+
+ offset = addr - start;
+ *valp = *(unw_word_t *)&stack->data[offset];
+ pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
+ (void *)addr, (unsigned long)*valp, offset);
+ return 0;
+}
+
+static int access_reg(unw_addr_space_t __used as,
+ unw_regnum_t regnum, unw_word_t *valp,
+ int __write, void *arg)
+{
+ struct unwind_info *ui = arg;
+ int id, ret;
+
+ /* Don't support write, I suspect we don't need it. */
+ if (__write) {
+ pr_err("unwind: access_reg w %d\n", regnum);
+ return 0;
+ }
+
+ if (!ui->sample->user_regs.regs) {
+ *valp = 0;
+ return 0;
+ }
+
+ id = unwind__arch_reg_id(regnum);
+ if (id < 0)
+ return -EINVAL;
+
+ ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+ if (ret) {
+ pr_err("unwind: can't read reg %d\n", regnum);
+ return ret;
+ }
+
+ pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+ return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __used as,
+ unw_proc_info_t *pi __used,
+ void *arg __used)
+{
+ pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread, struct machine *machine,
+ unwind_entry_cb_t cb, void *arg)
+{
+ struct unwind_entry e;
+ struct addr_location al;
+
+ thread__find_addr_location(thread, machine,
+ PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al, NULL);
+
+ e.ip = ip;
+ e.map = al.map;
+ e.sym = al.sym;
+
+ pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+ al.sym ? al.sym->name : "''",
+ ip,
+ al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+ return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+ switch (err) {
+ case UNW_EINVAL:
+ pr_err("unwind: Only supports local.\n");
+ break;
+ case UNW_EUNSPEC:
+ pr_err("unwind: Unspecified error.\n");
+ break;
+ case UNW_EBADREG:
+ pr_err("unwind: Register unavailable.\n");
+ break;
+ default:
+ break;
+ }
+}
+
+static unw_accessors_t accessors = {
+ .find_proc_info = find_proc_info,
+ .put_unwind_info = put_unwind_info,
+ .get_dyn_info_list_addr = get_dyn_info_list_addr,
+ .access_mem = access_mem,
+ .access_reg = access_reg,
+ .access_fpreg = access_fpreg,
+ .resume = resume,
+ .get_proc_name = get_proc_name,
+};
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+ void *arg)
+{
+ unw_addr_space_t addr_space;
+ unw_cursor_t c;
+ int ret;
+
+ addr_space = unw_create_addr_space(&accessors, 0);
+ if (!addr_space) {
+ pr_err("unwind: Can't create unwind address space.\n");
+ return -ENOMEM;
+ }
+
+ ret = unw_init_remote(&c, addr_space, ui);
+ if (ret)
+ display_error(ret);
+
+ while (!ret && (unw_step(&c) > 0)) {
+ unw_word_t ip;
+
+ unw_get_reg(&c, UNW_REG_IP, &ip);
+ ret = entry(ip, ui->thread, ui->machine, cb, arg);
+ }
+
+ unw_destroy_addr_space(addr_space);
+ return ret;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+ struct machine *machine, struct thread *thread,
+ u64 sample_uregs, struct perf_sample *data)
+{
+ unw_word_t ip;
+ struct unwind_info ui = {
+ .sample = data,
+ .sample_uregs = sample_uregs,
+ .thread = thread,
+ .machine = machine,
+ };
+ int ret;
+
+ if (!data->user_regs.regs)
+ return -EINVAL;
+
+ ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+ if (ret)
+ return ret;
+
+ ret = entry(ip, thread, machine, cb, arg);
+ if (ret)
+ return -ENOMEM;
+
+ return get_entries(&ui, cb, arg);
+}
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
new file mode 100644
index 0000000..919bd6a
--- /dev/null
+++ b/tools/perf/util/unwind.h
@@ -0,0 +1,34 @@
+#ifndef __UNWIND_H
+#define __UNWIND_H
+
+#include "types.h"
+#include "event.h"
+#include "symbol.h"
+
+struct unwind_entry {
+ struct map *map;
+ struct symbol *sym;
+ u64 ip;
+};
+
+typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
+
+#ifndef NO_LIBUNWIND_SUPPORT
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+ struct machine *machine,
+ struct thread *thread,
+ u64 sample_uregs,
+ struct perf_sample *data);
+int unwind__arch_reg_id(int regnum);
+#else
+static inline int
+unwind__get_entries(unwind_entry_cb_t cb __used, void *arg __used,
+ struct machine *machine __used,
+ struct thread *thread __used,
+ u64 sample_uregs __used,
+ struct perf_sample *data __used)
+{
+ return 0;
+}
+#endif /* NO_LIBUNWIND_SUPPORT */
+#endif /* __UNWIND_H */
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf tools: Support for DWARF CFI unwinding on post processing
2012-08-07 13:20 ` [PATCH 11/12] perf tools: Support for DWARF CFI unwinding on post processing Jiri Olsa
@ 2012-08-21 15:55 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:55 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 71ad0f5e4e361c8bca864c7d09d14b64af6bc2fc
Gitweb: http://git.kernel.org/tip/71ad0f5e4e361c8bca864c7d09d14b64af6bc2fc
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:46 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Sat, 11 Aug 2012 15:06:56 -0300
perf tools: Support for DWARF CFI unwinding on post processing
This brings the support for DWARF cfi unwinding on perf post
processing. Call frame informations are retrieved and then passed
to libunwind that requests memory and register content from the
applications.
Adding unwind object to handle the user stack backtrace based
on the user register values and user stack dump.
The unwind object access the libunwind via remote interface
and provides to it all the necessary data to unwind the stack.
The unwind interface provides following function:
unwind__get_entries
And callback (specified in above function) to retrieve
the backtrace entries:
typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry,
void *arg);
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-12-git-send-email-jolsa@redhat.com
[ Replaced use of perf_session by usage of perf_evsel ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile | 2 +
tools/perf/arch/x86/Makefile | 3 +
tools/perf/arch/x86/util/unwind.c | 111 ++++++
tools/perf/builtin-report.c | 18 +-
tools/perf/builtin-script.c | 4 +-
tools/perf/builtin-top.c | 6 +-
tools/perf/util/include/linux/compiler.h | 1 +
tools/perf/util/map.h | 5 +-
tools/perf/util/session.c | 66 +++-
tools/perf/util/session.h | 6 +-
tools/perf/util/trace-event.h | 2 +
tools/perf/util/unwind.c | 567 ++++++++++++++++++++++++++++++
tools/perf/util/unwind.h | 34 ++
13 files changed, 795 insertions(+), 30 deletions(-)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0aee6a9..e457afa 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -334,6 +334,7 @@ LIB_H += util/target.h
LIB_H += util/rblist.h
LIB_H += util/intlist.h
LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -547,6 +548,7 @@ else
EXTLIBS += $(LIBUNWIND_LIBS)
BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
+ LIB_OBJS += $(OUTPUT)util/unwind.o
endif
ifdef NO_NEWT
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 744e629..815841c 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -2,4 +2,7 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+endif
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind.c
new file mode 100644
index 0000000..78d956e
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind.c
@@ -0,0 +1,111 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+#ifdef ARCH_X86_64
+int unwind__arch_reg_id(int regnum)
+{
+ int id;
+
+ switch (regnum) {
+ case UNW_X86_64_RAX:
+ id = PERF_REG_X86_AX;
+ break;
+ case UNW_X86_64_RDX:
+ id = PERF_REG_X86_DX;
+ break;
+ case UNW_X86_64_RCX:
+ id = PERF_REG_X86_CX;
+ break;
+ case UNW_X86_64_RBX:
+ id = PERF_REG_X86_BX;
+ break;
+ case UNW_X86_64_RSI:
+ id = PERF_REG_X86_SI;
+ break;
+ case UNW_X86_64_RDI:
+ id = PERF_REG_X86_DI;
+ break;
+ case UNW_X86_64_RBP:
+ id = PERF_REG_X86_BP;
+ break;
+ case UNW_X86_64_RSP:
+ id = PERF_REG_X86_SP;
+ break;
+ case UNW_X86_64_R8:
+ id = PERF_REG_X86_R8;
+ break;
+ case UNW_X86_64_R9:
+ id = PERF_REG_X86_R9;
+ break;
+ case UNW_X86_64_R10:
+ id = PERF_REG_X86_R10;
+ break;
+ case UNW_X86_64_R11:
+ id = PERF_REG_X86_R11;
+ break;
+ case UNW_X86_64_R12:
+ id = PERF_REG_X86_R12;
+ break;
+ case UNW_X86_64_R13:
+ id = PERF_REG_X86_R13;
+ break;
+ case UNW_X86_64_R14:
+ id = PERF_REG_X86_R14;
+ break;
+ case UNW_X86_64_R15:
+ id = PERF_REG_X86_R15;
+ break;
+ case UNW_X86_64_RIP:
+ id = PERF_REG_X86_IP;
+ break;
+ default:
+ pr_err("unwind: invalid reg id %d\n", regnum);
+ return -EINVAL;
+ }
+
+ return id;
+}
+#else
+int unwind__arch_reg_id(int regnum)
+{
+ int id;
+
+ switch (regnum) {
+ case UNW_X86_EAX:
+ id = PERF_REG_X86_AX;
+ break;
+ case UNW_X86_EDX:
+ id = PERF_REG_X86_DX;
+ break;
+ case UNW_X86_ECX:
+ id = PERF_REG_X86_CX;
+ break;
+ case UNW_X86_EBX:
+ id = PERF_REG_X86_BX;
+ break;
+ case UNW_X86_ESI:
+ id = PERF_REG_X86_SI;
+ break;
+ case UNW_X86_EDI:
+ id = PERF_REG_X86_DI;
+ break;
+ case UNW_X86_EBP:
+ id = PERF_REG_X86_BP;
+ break;
+ case UNW_X86_ESP:
+ id = PERF_REG_X86_SP;
+ break;
+ case UNW_X86_EIP:
+ id = PERF_REG_X86_IP;
+ break;
+ default:
+ pr_err("unwind: invalid reg id %d\n", regnum);
+ return -EINVAL;
+ }
+
+ return id;
+}
+#endif /* ARCH_X86_64 */
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7c88a24..d618253 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -69,8 +69,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
- err = machine__resolve_callchain(machine, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
if (err)
return err;
}
@@ -140,8 +140,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
- err = machine__resolve_callchain(machine, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
if (err)
return err;
}
@@ -397,17 +397,17 @@ static int __cmd_report(struct perf_report *rep)
desc);
}
- if (dump_trace) {
- perf_session__fprintf_nr_events(session, stdout);
- goto out_delete;
- }
-
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
+ if (dump_trace) {
+ perf_session__fprintf_nr_events(session, stdout);
+ goto out_delete;
+ }
+
nr_samples = 0;
list_for_each_entry(pos, &session->evlist->entries, node) {
struct hists *hists = &pos->hists;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 30a9cb8..2d6e3b2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -380,7 +380,7 @@ static void print_sample_bts(union perf_event *event,
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine,
+ perf_evsel__print_ip(evsel, event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
@@ -422,7 +422,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine,
+ perf_evsel__print_ip(evsel, event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 68cd61e..e45a1ba 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -783,8 +783,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
- err = machine__resolve_callchain(machine, al.thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel,
+ al.thread, sample,
+ &parent);
+
if (err)
return;
}
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index 547628e..2dc8671 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -10,5 +10,6 @@
#endif
#define __used __attribute__((__unused__))
+#define __packed __attribute__((__packed__))
#endif
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 1e183d1..c98ab19 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -158,9 +158,12 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid);
void machine__exit(struct machine *self);
void machine__delete(struct machine *self);
+struct perf_evsel;
+struct perf_sample;
int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel,
struct thread *thread,
- struct ip_callchain *chain,
+ struct perf_sample *sample,
struct symbol **parent);
int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
u64 addr);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c9ed7e3..f7bb7ae 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,6 +16,7 @@
#include "cpumap.h"
#include "event-parse.h"
#include "perf_regs.h"
+#include "unwind.h"
static int perf_session__open(struct perf_session *self, bool force)
{
@@ -289,10 +290,11 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
return bi;
}
-int machine__resolve_callchain(struct machine *self,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent)
+static int machine__resolve_callchain_sample(struct machine *machine,
+ struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent)
+
{
u8 cpumode = PERF_RECORD_MISC_USER;
unsigned int i;
@@ -317,11 +319,14 @@ int machine__resolve_callchain(struct machine *self,
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
case PERF_CONTEXT_HV:
- cpumode = PERF_RECORD_MISC_HYPERVISOR; break;
+ cpumode = PERF_RECORD_MISC_HYPERVISOR;
+ break;
case PERF_CONTEXT_KERNEL:
- cpumode = PERF_RECORD_MISC_KERNEL; break;
+ cpumode = PERF_RECORD_MISC_KERNEL;
+ break;
case PERF_CONTEXT_USER:
- cpumode = PERF_RECORD_MISC_USER; break;
+ cpumode = PERF_RECORD_MISC_USER;
+ break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
@@ -336,7 +341,7 @@ int machine__resolve_callchain(struct machine *self,
}
al.filtered = false;
- thread__find_addr_location(thread, self, cpumode,
+ thread__find_addr_location(thread, machine, cpumode,
MAP__FUNCTION, ip, &al, NULL);
if (al.sym != NULL) {
if (sort__has_parent && !*parent &&
@@ -355,6 +360,40 @@ int machine__resolve_callchain(struct machine *self,
return 0;
}
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+ struct callchain_cursor *cursor = arg;
+ return callchain_cursor_append(cursor, entry->ip,
+ entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct perf_sample *sample,
+ struct symbol **parent)
+
+{
+ int ret;
+
+ callchain_cursor_reset(&callchain_cursor);
+
+ ret = machine__resolve_callchain_sample(machine, thread,
+ sample->callchain, parent);
+ if (ret)
+ return ret;
+
+ /* Can we do dwarf post unwind? */
+ if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+ (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+ return 0;
+
+ return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+ thread, evsel->attr.sample_regs_user,
+ sample);
+
+}
+
static int process_event_synth_tracing_data_stub(union perf_event *event __used,
struct perf_session *session __used)
{
@@ -1533,9 +1572,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
return NULL;
}
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, int print_sym,
- int print_dso, int print_symoffset)
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine,
+ int print_sym, int print_dso, int print_symoffset)
{
struct addr_location al;
struct callchain_cursor_node *node;
@@ -1549,8 +1588,9 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
if (symbol_conf.use_callchain && sample->callchain) {
- if (machine__resolve_callchain(machine, al.thread,
- sample->callchain, NULL) != 0) {
+
+ if (machine__resolve_callchain(machine, evsel, al.thread,
+ sample, NULL) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
return;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 1f7ec87..176a609 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -129,9 +129,9 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, int print_sym,
- int print_dso, int print_symoffset);
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine,
+ int print_sym, int print_dso, int print_symoffset);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 7575dfd..a55fd37 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -77,6 +77,8 @@ void tracing_data_put(struct tracing_data *tdata);
struct addr_location;
+struct perf_session;
+
struct scripting_ops {
const char *name;
int (*start_script) (const char *script, int argc, const char **argv);
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
new file mode 100644
index 0000000..00a42aa
--- /dev/null
+++ b/tools/perf/util/unwind.c
@@ -0,0 +1,567 @@
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ * Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "util.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */
+#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit 0xff
+#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */
+#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */
+#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */
+#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */
+#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr 0x00 /* absolute value */
+#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */
+#define DW_EH_PE_aligned 0x50 /* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect 0x80
+ * #define DW_EH_PE_uleb128 0x01
+ * #define DW_EH_PE_udata2 0x02
+ * #define DW_EH_PE_sleb128 0x09
+ * #define DW_EH_PE_sdata2 0x0a
+ * #define DW_EH_PE_textrel 0x20
+ * #define DW_EH_PE_datarel 0x30
+ */
+
+struct unwind_info {
+ struct perf_sample *sample;
+ struct machine *machine;
+ struct thread *thread;
+ u64 sample_uregs;
+};
+
+#define dw_read(ptr, type, end) ({ \
+ type *__p = (type *) ptr; \
+ type __v; \
+ if ((__p + 1) > (type *) end) \
+ return -EINVAL; \
+ __v = *__p++; \
+ ptr = (typeof(ptr)) __p; \
+ __v; \
+ })
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+ u8 encoding)
+{
+ u8 *cur = *p;
+ *val = 0;
+
+ switch (encoding) {
+ case DW_EH_PE_omit:
+ *val = 0;
+ goto out;
+ case DW_EH_PE_ptr:
+ *val = dw_read(cur, unsigned long, end);
+ goto out;
+ default:
+ break;
+ }
+
+ switch (encoding & DW_EH_PE_APPL_MASK) {
+ case DW_EH_PE_absptr:
+ break;
+ case DW_EH_PE_pcrel:
+ *val = (unsigned long) cur;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if ((encoding & 0x07) == 0x00)
+ encoding |= DW_EH_PE_udata4;
+
+ switch (encoding & DW_EH_PE_FORMAT_MASK) {
+ case DW_EH_PE_sdata4:
+ *val += dw_read(cur, s32, end);
+ break;
+ case DW_EH_PE_udata4:
+ *val += dw_read(cur, u32, end);
+ break;
+ case DW_EH_PE_sdata8:
+ *val += dw_read(cur, s64, end);
+ break;
+ case DW_EH_PE_udata8:
+ *val += dw_read(cur, u64, end);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ out:
+ *p = cur;
+ return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({ \
+ u64 __v; \
+ if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \
+ return -EINVAL; \
+ } \
+ __v; \
+ })
+
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+ GElf_Shdr *shp, const char *name)
+{
+ Elf_Scn *sec = NULL;
+
+ while ((sec = elf_nextscn(elf, sec)) != NULL) {
+ char *str;
+
+ gelf_getshdr(sec, shp);
+ str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+ if (!strcmp(name, str))
+ break;
+ }
+
+ return sec;
+}
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ u64 offset = 0;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL)
+ return 0;
+
+ do {
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ break;
+
+ if (!elf_section_by_name(elf, &ehdr, &shdr, name))
+ break;
+
+ offset = shdr.sh_offset;
+ } while (0);
+
+ elf_end(elf);
+ return offset;
+}
+
+struct table_entry {
+ u32 start_ip_offset;
+ u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+ unsigned char version;
+ unsigned char eh_frame_ptr_enc;
+ unsigned char fde_count_enc;
+ unsigned char table_enc;
+
+ /*
+ * The rest of the header is variable-length and consists of the
+ * following members:
+ *
+ * encoded_t eh_frame_ptr;
+ * encoded_t fde_count;
+ */
+
+ /* A single encoded pointer should not be more than 8 bytes. */
+ u64 enc[2];
+
+ /*
+ * struct {
+ * encoded_t start_ip;
+ * encoded_t fde_addr;
+ * } binary_search_table[fde_count];
+ */
+ char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+ u64 offset, u64 *table_data, u64 *segbase,
+ u64 *fde_count)
+{
+ struct eh_frame_hdr hdr;
+ u8 *enc = (u8 *) &hdr.enc;
+ u8 *end = (u8 *) &hdr.data;
+ ssize_t r;
+
+ r = dso__data_read_offset(dso, machine, offset,
+ (u8 *) &hdr, sizeof(hdr));
+ if (r != sizeof(hdr))
+ return -EINVAL;
+
+ /* We dont need eh_frame_ptr, just skip it. */
+ dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+ *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+ *segbase = offset;
+ *table_data = (enc - (u8 *) &hdr) + offset;
+ return 0;
+}
+
+static int read_unwind_spec(struct dso *dso, struct machine *machine,
+ u64 *table_data, u64 *segbase, u64 *fde_count)
+{
+ int ret = -EINVAL, fd;
+ u64 offset;
+
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return -EINVAL;
+
+ offset = elf_section_offset(fd, ".eh_frame_hdr");
+ close(fd);
+
+ if (offset)
+ ret = unwind_spec_ehframe(dso, machine, offset,
+ table_data, segbase,
+ fde_count);
+
+ /* TODO .debug_frame check if eh_frame_hdr fails */
+ return ret;
+}
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+ struct addr_location al;
+
+ thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al);
+ return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+ int need_unwind_info, void *arg)
+{
+ struct unwind_info *ui = arg;
+ struct map *map;
+ unw_dyn_info_t di;
+ u64 table_data, segbase, fde_count;
+
+ map = find_map(ip, ui);
+ if (!map || !map->dso)
+ return -EINVAL;
+
+ pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+ if (read_unwind_spec(map->dso, ui->machine,
+ &table_data, &segbase, &fde_count))
+ return -EINVAL;
+
+ memset(&di, 0, sizeof(di));
+ di.format = UNW_INFO_FORMAT_REMOTE_TABLE;
+ di.start_ip = map->start;
+ di.end_ip = map->end;
+ di.u.rti.segbase = map->start + segbase;
+ di.u.rti.table_data = map->start + table_data;
+ di.u.rti.table_len = fde_count * sizeof(struct table_entry)
+ / sizeof(unw_word_t);
+ return dwarf_search_unwind_table(as, ip, &di, pi,
+ need_unwind_info, arg);
+}
+
+static int access_fpreg(unw_addr_space_t __used as, unw_regnum_t __used num,
+ unw_fpreg_t __used *val, int __used __write,
+ void __used *arg)
+{
+ pr_err("unwind: access_fpreg unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __used as,
+ unw_word_t __used *dil_addr,
+ void __used *arg)
+{
+ return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __used as, unw_cursor_t __used *cu,
+ void __used *arg)
+{
+ pr_err("unwind: resume unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __used as, unw_word_t __used addr,
+ char __used *bufp, size_t __used buf_len,
+ unw_word_t __used *offp, void __used *arg)
+{
+ pr_err("unwind: get_proc_name unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+ unw_word_t *data)
+{
+ struct addr_location al;
+ ssize_t size;
+
+ thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, addr, &al);
+ if (!al.map) {
+ pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+ return -1;
+ }
+
+ if (!al.map->dso)
+ return -1;
+
+ size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+ addr, (u8 *) data, sizeof(*data));
+
+ return !(size == sizeof(*data));
+}
+
+static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
+ u64 sample_regs)
+{
+ int i, idx = 0;
+
+ if (!(sample_regs & (1 << id)))
+ return -EINVAL;
+
+ for (i = 0; i < id; i++) {
+ if (sample_regs & (1 << i))
+ idx++;
+ }
+
+ *valp = regs->regs[idx];
+ return 0;
+}
+
+static int access_mem(unw_addr_space_t __used as,
+ unw_word_t addr, unw_word_t *valp,
+ int __write, void *arg)
+{
+ struct unwind_info *ui = arg;
+ struct stack_dump *stack = &ui->sample->user_stack;
+ unw_word_t start, end;
+ int offset;
+ int ret;
+
+ /* Don't support write, probably not needed. */
+ if (__write || !stack || !ui->sample->user_regs.regs) {
+ *valp = 0;
+ return 0;
+ }
+
+ ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
+ ui->sample_uregs);
+ if (ret)
+ return ret;
+
+ end = start + stack->size;
+
+ /* Check overflow. */
+ if (addr + sizeof(unw_word_t) < addr)
+ return -EINVAL;
+
+ if (addr < start || addr + sizeof(unw_word_t) >= end) {
+ ret = access_dso_mem(ui, addr, valp);
+ if (ret) {
+ pr_debug("unwind: access_mem %p not inside range %p-%p\n",
+ (void *)addr, (void *)start, (void *)end);
+ *valp = 0;
+ return ret;
+ }
+ return 0;
+ }
+
+ offset = addr - start;
+ *valp = *(unw_word_t *)&stack->data[offset];
+ pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
+ (void *)addr, (unsigned long)*valp, offset);
+ return 0;
+}
+
+static int access_reg(unw_addr_space_t __used as,
+ unw_regnum_t regnum, unw_word_t *valp,
+ int __write, void *arg)
+{
+ struct unwind_info *ui = arg;
+ int id, ret;
+
+ /* Don't support write, I suspect we don't need it. */
+ if (__write) {
+ pr_err("unwind: access_reg w %d\n", regnum);
+ return 0;
+ }
+
+ if (!ui->sample->user_regs.regs) {
+ *valp = 0;
+ return 0;
+ }
+
+ id = unwind__arch_reg_id(regnum);
+ if (id < 0)
+ return -EINVAL;
+
+ ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+ if (ret) {
+ pr_err("unwind: can't read reg %d\n", regnum);
+ return ret;
+ }
+
+ pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+ return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __used as,
+ unw_proc_info_t *pi __used,
+ void *arg __used)
+{
+ pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread, struct machine *machine,
+ unwind_entry_cb_t cb, void *arg)
+{
+ struct unwind_entry e;
+ struct addr_location al;
+
+ thread__find_addr_location(thread, machine,
+ PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al, NULL);
+
+ e.ip = ip;
+ e.map = al.map;
+ e.sym = al.sym;
+
+ pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+ al.sym ? al.sym->name : "''",
+ ip,
+ al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+ return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+ switch (err) {
+ case UNW_EINVAL:
+ pr_err("unwind: Only supports local.\n");
+ break;
+ case UNW_EUNSPEC:
+ pr_err("unwind: Unspecified error.\n");
+ break;
+ case UNW_EBADREG:
+ pr_err("unwind: Register unavailable.\n");
+ break;
+ default:
+ break;
+ }
+}
+
+static unw_accessors_t accessors = {
+ .find_proc_info = find_proc_info,
+ .put_unwind_info = put_unwind_info,
+ .get_dyn_info_list_addr = get_dyn_info_list_addr,
+ .access_mem = access_mem,
+ .access_reg = access_reg,
+ .access_fpreg = access_fpreg,
+ .resume = resume,
+ .get_proc_name = get_proc_name,
+};
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+ void *arg)
+{
+ unw_addr_space_t addr_space;
+ unw_cursor_t c;
+ int ret;
+
+ addr_space = unw_create_addr_space(&accessors, 0);
+ if (!addr_space) {
+ pr_err("unwind: Can't create unwind address space.\n");
+ return -ENOMEM;
+ }
+
+ ret = unw_init_remote(&c, addr_space, ui);
+ if (ret)
+ display_error(ret);
+
+ while (!ret && (unw_step(&c) > 0)) {
+ unw_word_t ip;
+
+ unw_get_reg(&c, UNW_REG_IP, &ip);
+ ret = entry(ip, ui->thread, ui->machine, cb, arg);
+ }
+
+ unw_destroy_addr_space(addr_space);
+ return ret;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+ struct machine *machine, struct thread *thread,
+ u64 sample_uregs, struct perf_sample *data)
+{
+ unw_word_t ip;
+ struct unwind_info ui = {
+ .sample = data,
+ .sample_uregs = sample_uregs,
+ .thread = thread,
+ .machine = machine,
+ };
+ int ret;
+
+ if (!data->user_regs.regs)
+ return -EINVAL;
+
+ ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+ if (ret)
+ return ret;
+
+ ret = entry(ip, thread, machine, cb, arg);
+ if (ret)
+ return -ENOMEM;
+
+ return get_entries(&ui, cb, arg);
+}
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
new file mode 100644
index 0000000..919bd6a
--- /dev/null
+++ b/tools/perf/util/unwind.h
@@ -0,0 +1,34 @@
+#ifndef __UNWIND_H
+#define __UNWIND_H
+
+#include "types.h"
+#include "event.h"
+#include "symbol.h"
+
+struct unwind_entry {
+ struct map *map;
+ struct symbol *sym;
+ u64 ip;
+};
+
+typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
+
+#ifndef NO_LIBUNWIND_SUPPORT
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+ struct machine *machine,
+ struct thread *thread,
+ u64 sample_uregs,
+ struct perf_sample *data);
+int unwind__arch_reg_id(int regnum);
+#else
+static inline int
+unwind__get_entries(unwind_entry_cb_t cb __used, void *arg __used,
+ struct machine *machine __used,
+ struct thread *thread __used,
+ u64 sample_uregs __used,
+ struct perf_sample *data __used)
+{
+ return 0;
+}
+#endif /* NO_LIBUNWIND_SUPPORT */
+#endif /* __UNWIND_H */
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH 12/12] perf tools: Support for DWARF mode callchain
2012-08-07 13:20 [PATCHv10 00/12] perf: Add backtrace post dwarf unwind Jiri Olsa
` (10 preceding siblings ...)
2012-08-07 13:20 ` [PATCH 11/12] perf tools: Support for DWARF CFI unwinding on post processing Jiri Olsa
@ 2012-08-07 13:20 ` Jiri Olsa
2012-08-21 15:55 ` [tip:perf/core] " tip-bot for Jiri Olsa
11 siblings, 1 reply; 32+ messages in thread
From: Jiri Olsa @ 2012-08-07 13:20 UTC (permalink / raw)
To: linux-kernel
Cc: Arnaldo Carvalho de Melo, Arun Sharma, Benjamin Redelings,
Corey Ashford, Cyrill Gorcunov, Frank Ch. Eigler,
Frederic Weisbecker, Ingo Molnar, Masami Hiramatsu,
Paul Mackerras, Peter Zijlstra, Robert Richter, Stephane Eranian,
Tom Zanussi, Ulrich Drepper, Jiri Olsa
This patch enables perf to use the DWARF unwind code.
It extends the perf record '-g' option with following arguments:
'fp' - provides framepointer based user
stack backtrace
'dwarf[,size]' - provides DWARF (libunwind) based user stack
backtrace. The size specifies the size of the
user stack dump. If omitted it is 8192 by default.
If libunwind is found during the perf build, then the 'dwarf'
argument becomes available for record command. The 'fp' stays as
default option in any case.
Examples: (perf compiled with libunwind)
perf record -g dwarf ls
- provides dwarf unwind with 8192 as stack dump size
perf record -g dwarf,4096 ls
- provides dwarf unwind with 4096 as stack dump size
perf record -g -- ls
perf record -g fp ls
- provides frame pointer unwind
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/builtin-record.c | 114 +++++++++++++++++++++++++++++++++++++++++++-
tools/perf/perf.h | 9 +++-
tools/perf/util/evsel.c | 13 ++++-
3 files changed, 132 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4db6e1b..22dd05d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -31,6 +31,15 @@
#include <sched.h>
#include <sys/mman.h>
+#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
+
+#ifdef NO_LIBUNWIND_SUPPORT
+static char callchain_help[] = CALLCHAIN_HELP "[fp]";
+#else
+static unsigned long default_stack_dump_size = 8192;
+static char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+#endif
+
enum write_mode_t {
WRITE_FORCE,
WRITE_APPEND
@@ -732,6 +741,106 @@ error:
return ret;
}
+#ifndef NO_LIBUNWIND_SUPPORT
+static int get_stack_size(char *str, unsigned long *_size)
+{
+ char *endptr;
+ unsigned long size;
+ unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
+
+ size = strtoul(str, &endptr, 0);
+
+ do {
+ if (*endptr)
+ break;
+
+ size = round_up(size, sizeof(u64));
+ if (!size || size > max_size)
+ break;
+
+ *_size = size;
+ return 0;
+
+ } while (0);
+
+ pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+ max_size, str);
+ return -1;
+}
+#endif /* !NO_LIBUNWIND_SUPPORT */
+
+static int
+parse_callchain_opt(const struct option *opt __used, const char *arg,
+ int unset)
+{
+ struct perf_record *rec = (struct perf_record *)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)
+ return -ENOMEM;
+
+ strcpy(buf, arg);
+
+ tok = strtok_r((char *)buf, ",", &saveptr);
+ name = tok ? : (char *)buf;
+
+ do {
+ /* Framepointer style */
+ if (!strncmp(name, "fp", sizeof("fp"))) {
+ if (!strtok_r(NULL, ",", &saveptr)) {
+ rec->opts.call_graph = CALLCHAIN_FP;
+ ret = 0;
+ } else
+ pr_err("callchain: No more arguments "
+ "needed for -g fp\n");
+ break;
+
+#ifndef NO_LIBUNWIND_SUPPORT
+ /* Dwarf style */
+ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+ ret = 0;
+ rec->opts.call_graph = CALLCHAIN_DWARF;
+ rec->opts.stack_dump_size = default_stack_dump_size;
+
+ tok = strtok_r(NULL, ",", &saveptr);
+ if (tok) {
+ unsigned long size = 0;
+
+ ret = get_stack_size(tok, &size);
+ rec->opts.stack_dump_size = size;
+ }
+
+ if (!ret)
+ pr_debug("callchain: stack dump size %d\n",
+ rec->opts.stack_dump_size);
+#endif /* !NO_LIBUNWIND_SUPPORT */
+ } else {
+ pr_err("callchain: Unknown -g option "
+ "value: %s\n", arg);
+ break;
+ }
+
+ } while (0);
+
+ free(buf);
+
+ if (!ret)
+ pr_debug("callchain: type %d\n", rec->opts.call_graph);
+
+ return ret;
+}
+
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -803,8 +912,9 @@ 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_BOOLEAN('g', "call-graph", &record.opts.call_graph,
- "do call-graph (stack chain/backtrace) recording"),
+ OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]",
+ callchain_help, &parse_callchain_opt,
+ "fp"),
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/perf.h b/tools/perf/perf.h
index f960ccb..87f4ec6 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -209,9 +209,15 @@ void pthread__unblock_sigwinch(void);
#include "util/target.h"
+enum perf_call_graph_mode {
+ CALLCHAIN_NONE,
+ CALLCHAIN_FP,
+ CALLCHAIN_DWARF
+};
+
struct perf_record_opts {
struct perf_target target;
- bool call_graph;
+ int call_graph;
bool group;
bool inherit_stat;
bool no_delay;
@@ -230,6 +236,7 @@ struct perf_record_opts {
u64 branch_stack;
u64 default_interval;
u64 user_interval;
+ u16 stack_dump_size;
};
#endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a2da682..9c54e8f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -17,6 +17,8 @@
#include "thread_map.h"
#include "target.h"
#include "../../../include/linux/hw_breakpoint.h"
+#include "../../include/linux/perf_event.h"
+#include "perf_regs.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))
@@ -368,9 +370,18 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
attr->mmap_data = track;
}
- if (opts->call_graph)
+ if (opts->call_graph) {
attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
+ if (opts->call_graph == CALLCHAIN_DWARF) {
+ attr->sample_type |= PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_STACK_USER;
+ attr->sample_regs_user = PERF_REGS_MASK;
+ attr->sample_stack_user = opts->stack_dump_size;
+ attr->exclude_callchain_user = 1;
+ }
+ }
+
if (perf_target__has_cpu(&opts->target))
attr->sample_type |= PERF_SAMPLE_CPU;
--
1.7.11.2
^ permalink raw reply related [flat|nested] 32+ messages in thread* [tip:perf/core] perf tools: Support for DWARF mode callchain
2012-08-07 13:20 ` [PATCH 12/12] perf tools: Support for DWARF mode callchain Jiri Olsa
@ 2012-08-21 15:55 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 32+ messages in thread
From: tip-bot for Jiri Olsa @ 2012-08-21 15:55 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, eranian, mingo, gorcunov, a.p.zijlstra, benjamin.redelings,
jolsa, drepper, robert.richter, fweisbec, tglx, cjashfor,
asharma, linux-kernel, hpa, fche, paulus, tzanussi,
masami.hiramatsu.pt, mingo
Commit-ID: 26d330226b9cf6208daae9b0b3697980c8fb51d8
Gitweb: http://git.kernel.org/tip/26d330226b9cf6208daae9b0b3697980c8fb51d8
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Tue, 7 Aug 2012 15:20:47 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Sat, 11 Aug 2012 15:07:18 -0300
perf tools: Support for DWARF mode callchain
This patch enables perf to use the DWARF unwind code.
It extends the perf record '-g' option with following arguments:
'fp' - provides framepointer based user
stack backtrace
'dwarf[,size]' - provides DWARF (libunwind) based user stack
backtrace. The size specifies the size of the
user stack dump. If omitted it is 8192 by default.
If libunwind is found during the perf build, then the 'dwarf' argument
becomes available for record command. The 'fp' stays as default option
in any case.
Examples: (perf compiled with libunwind)
perf record -g dwarf ls
- provides dwarf unwind with 8192 as stack dump size
perf record -g dwarf,4096 ls
- provides dwarf unwind with 4096 as stack dump size
perf record -g -- ls
perf record -g fp ls
- provides frame pointer unwind
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-record.c | 114 ++++++++++++++++++++++++++++++++++++++++++-
tools/perf/perf.h | 9 +++-
tools/perf/util/evsel.c | 13 +++++-
3 files changed, 132 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4db6e1b..22dd05d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -31,6 +31,15 @@
#include <sched.h>
#include <sys/mman.h>
+#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
+
+#ifdef NO_LIBUNWIND_SUPPORT
+static char callchain_help[] = CALLCHAIN_HELP "[fp]";
+#else
+static unsigned long default_stack_dump_size = 8192;
+static char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+#endif
+
enum write_mode_t {
WRITE_FORCE,
WRITE_APPEND
@@ -732,6 +741,106 @@ error:
return ret;
}
+#ifndef NO_LIBUNWIND_SUPPORT
+static int get_stack_size(char *str, unsigned long *_size)
+{
+ char *endptr;
+ unsigned long size;
+ unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
+
+ size = strtoul(str, &endptr, 0);
+
+ do {
+ if (*endptr)
+ break;
+
+ size = round_up(size, sizeof(u64));
+ if (!size || size > max_size)
+ break;
+
+ *_size = size;
+ return 0;
+
+ } while (0);
+
+ pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+ max_size, str);
+ return -1;
+}
+#endif /* !NO_LIBUNWIND_SUPPORT */
+
+static int
+parse_callchain_opt(const struct option *opt __used, const char *arg,
+ int unset)
+{
+ struct perf_record *rec = (struct perf_record *)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)
+ return -ENOMEM;
+
+ strcpy(buf, arg);
+
+ tok = strtok_r((char *)buf, ",", &saveptr);
+ name = tok ? : (char *)buf;
+
+ do {
+ /* Framepointer style */
+ if (!strncmp(name, "fp", sizeof("fp"))) {
+ if (!strtok_r(NULL, ",", &saveptr)) {
+ rec->opts.call_graph = CALLCHAIN_FP;
+ ret = 0;
+ } else
+ pr_err("callchain: No more arguments "
+ "needed for -g fp\n");
+ break;
+
+#ifndef NO_LIBUNWIND_SUPPORT
+ /* Dwarf style */
+ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+ ret = 0;
+ rec->opts.call_graph = CALLCHAIN_DWARF;
+ rec->opts.stack_dump_size = default_stack_dump_size;
+
+ tok = strtok_r(NULL, ",", &saveptr);
+ if (tok) {
+ unsigned long size = 0;
+
+ ret = get_stack_size(tok, &size);
+ rec->opts.stack_dump_size = size;
+ }
+
+ if (!ret)
+ pr_debug("callchain: stack dump size %d\n",
+ rec->opts.stack_dump_size);
+#endif /* !NO_LIBUNWIND_SUPPORT */
+ } else {
+ pr_err("callchain: Unknown -g option "
+ "value: %s\n", arg);
+ break;
+ }
+
+ } while (0);
+
+ free(buf);
+
+ if (!ret)
+ pr_debug("callchain: type %d\n", rec->opts.call_graph);
+
+ return ret;
+}
+
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -803,8 +912,9 @@ 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_BOOLEAN('g', "call-graph", &record.opts.call_graph,
- "do call-graph (stack chain/backtrace) recording"),
+ OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]",
+ callchain_help, &parse_callchain_opt,
+ "fp"),
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/perf.h b/tools/perf/perf.h
index f960ccb..87f4ec6 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -209,9 +209,15 @@ void pthread__unblock_sigwinch(void);
#include "util/target.h"
+enum perf_call_graph_mode {
+ CALLCHAIN_NONE,
+ CALLCHAIN_FP,
+ CALLCHAIN_DWARF
+};
+
struct perf_record_opts {
struct perf_target target;
- bool call_graph;
+ int call_graph;
bool group;
bool inherit_stat;
bool no_delay;
@@ -230,6 +236,7 @@ struct perf_record_opts {
u64 branch_stack;
u64 default_interval;
u64 user_interval;
+ u16 stack_dump_size;
};
#endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a2da682..9c54e8f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -17,6 +17,8 @@
#include "thread_map.h"
#include "target.h"
#include "../../../include/linux/hw_breakpoint.h"
+#include "../../include/linux/perf_event.h"
+#include "perf_regs.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))
@@ -368,9 +370,18 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
attr->mmap_data = track;
}
- if (opts->call_graph)
+ if (opts->call_graph) {
attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
+ if (opts->call_graph == CALLCHAIN_DWARF) {
+ attr->sample_type |= PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_STACK_USER;
+ attr->sample_regs_user = PERF_REGS_MASK;
+ attr->sample_stack_user = opts->stack_dump_size;
+ attr->exclude_callchain_user = 1;
+ }
+ }
+
if (perf_target__has_cpu(&opts->target))
attr->sample_type |= PERF_SAMPLE_CPU;
^ permalink raw reply related [flat|nested] 32+ messages in thread