[RFCv4 00/16] perf: Add backtrace post dwarf unwind

[RFCv4 00/16] perf: Add backtrace post dwarf unwind

[Jiri Olsa]

hi,
v3 does not apply to current tip anymore, sending rebased version

also available as tarball in here:
http://people.redhat.com/~jolsa/perf_post_unwind_v4.tar.bz2

v4 changes:
   - no real change from v3, just rebase
   - v3 patch 06/17 got already merged

v3 changes:
   patch 01/17
   - added HAVE_PERF_REGS config option
   patch 02/17, 04/17
   - regs and stack perf interface is more general now
   patch 06/17
   - unrelated online fix for i386 compilation
   patch 16/17
   - few namespace fixies

---
Adding the post unwinding user stack backtrace using dwarf unwind
via libunwind. The original work was done by Frederic. I mostly took
his patches and make them compile in current kernel code plus I added
some stuff here and there.

The main idea is to store user registers and portion of user
stack when the sample data during the record phase. Then during
the report, when the data is presented, perform the actual dwarf
dwarf unwind.

attached patches:
  01/16 perf: Unified API to record selective sets of arch registers
  02/16 perf: Add ability to attach registers dump to sample
  03/16 perf: Factor __output_copy to be usable with specific copy function
  04/16 perf: Add ability to attach user stack dump to sample
  05/16 perf: Add attribute to filter out user callchains
  06/16 perf, tool: Factor DSO symtab types to generic binary types
  07/16 perf, tool: Add interface to read DSO image data
  08/16 perf, tool: Add '.note' check into search for NOTE section
  09/16 perf, tool: Back [vdso] DSO with real data
  10/16 perf, tool: Add interface to arch registers sets
  11/16 perf, tool: Add libunwind dependency for dwarf cfi unwinding
  12/16 perf, tool: Support user regs and stack in sample parsing
  13/16 perf, tool: Support for dwarf cfi unwinding on post processing
  14/16 perf, tool: Support for dwarf mode callchain on perf record
  15/16 perf, tool: Add dso data caching
  16/16 perf, tool: Add dso data caching tests


I tested on Fedora. There was not much gain on i386, because the
binaries are compiled with frame pointers. Thought the dwarf
backtrace is more accurade and unwraps calls in more details
(functions that do not set the frame pointers).

I could see some improvement on x86_64, where I got full backtrace
where current code could got just the first address out of the
instruction pointer.

Example on x86_64:
[dwarf]
   perf record -g -e syscalls:sys_enter_write date

   100.00%     date  libc-2.14.90.so  [.] __GI___libc_write
               |
               --- __GI___libc_write
                   _IO_file_write@@GLIBC_2.2.5
                   new_do_write
                   _IO_do_write@@GLIBC_2.2.5
                   _IO_file_overflow@@GLIBC_2.2.5
                   0x4022cd
                   0x401ee6
                   __libc_start_main
                   0x4020b9


[frame pointer]
   perf record -g fp -e syscalls:sys_enter_write date

   100.00%     date  libc-2.14.90.so  [.] __GI___libc_write
               |
               --- __GI___libc_write

Also I tested on coreutils binaries mainly, but I could see
getting wider backtraces with dwarf unwind for more complex
application like firefox.

The unwind should go throught [vdso] object. I haven't studied
the [vsyscall] yet, so not sure there.

Attached patches should work on both x86 and x86_64. I did
some initial testing so far.

The unwind backtrace can be interrupted by following reasons:
    - bug in unwind information of processed shared library
    - bug in unwind processing code (most likely ;) )
    - insufficient dump stack size
    - wrong register value - x86_64 does not store whole
      set of registers when in exception, but so far
      it looks like RIP and RSP should be enough

thanks for comments,
jirka
---
 arch/Kconfig                                       |    6 +
 arch/x86/Kconfig                                   |    1 +
 arch/x86/include/asm/perf_event.h                  |    2 +
 arch/x86/include/asm/perf_regs.h                   |   10 +
 arch/x86/include/asm/perf_regs_32.h                |   84 +++
 arch/x86/include/asm/perf_regs_64.h                |   99 ++++
 include/linux/perf_event.h                         |   49 ++-
 include/linux/perf_regs.h                          |   28 +
 kernel/events/callchain.c                          |    4 +-
 kernel/events/core.c                               |  204 +++++++-
 kernel/events/internal.h                           |   65 ++-
 kernel/events/ring_buffer.c                        |    4 +-
 tools/perf/Makefile                                |   45 ++-
 tools/perf/arch/x86/Makefile                       |    3 +
 tools/perf/arch/x86/include/perf_regs.h            |  108 ++++
 tools/perf/arch/x86/util/unwind.c                  |  111 ++++
 tools/perf/builtin-record.c                        |   86 +++-
 tools/perf/builtin-report.c                        |   24 +-
 tools/perf/builtin-script.c                        |   56 ++-
 tools/perf/builtin-test.c                          |    7 +-
 tools/perf/builtin-top.c                           |    7 +-
 tools/perf/config/feature-tests.mak                |   25 +
 tools/perf/perf.h                                  |    9 +-
 tools/perf/util/annotate.c                         |    2 +-
 tools/perf/util/dso-test.c                         |  154 ++++++
 tools/perf/util/event.h                            |   16 +-
 tools/perf/util/evlist.c                           |   24 +
 tools/perf/util/evlist.h                           |    3 +
 tools/perf/util/evsel.c                            |   43 ++-
 tools/perf/util/include/linux/compiler.h           |    1 +
 tools/perf/util/map.c                              |   23 +-
 tools/perf/util/map.h                              |    7 +-
 tools/perf/util/perf_regs.h                        |   19 +
 tools/perf/util/python.c                           |    3 +-
 .../perf/util/scripting-engines/trace-event-perl.c |    3 +-
 .../util/scripting-engines/trace-event-python.c    |    3 +-
 tools/perf/util/session.c                          |  134 +++++-
 tools/perf/util/session.h                          |   15 +-
 tools/perf/util/symbol.c                           |  435 +++++++++++++---
 tools/perf/util/symbol.h                           |   52 ++-
 tools/perf/util/trace-event-scripting.c            |    3 +-
 tools/perf/util/trace-event.h                      |    5 +-
 tools/perf/util/unwind.c                           |  565 ++++++++++++++++++++
 tools/perf/util/unwind.h                           |   34 ++
 tools/perf/util/vdso.c                             |   90 +++
 tools/perf/util/vdso.h                             |    8 +
 46 files changed, 2487 insertions(+), 192 deletions(-)

[PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Jiri Olsa]

This brings a new API to help the selective dump of registers on
event sampling, and its implementation in x86.

Added HAVE_PERF_REGS config option to determine if the architecture
provides perf registers ABI.

The architecture must provide a non-zero and unique id to
identify the origin of a register set because interpreting a
register dump requires to know from which architecture it comes.
The achitecture is considered different between the 32 and 64 bits.
x86-32 has the id 1, x86-64 has the id 2.

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.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 arch/Kconfig                        |    6 ++
 arch/x86/Kconfig                    |    1 +
 arch/x86/include/asm/perf_regs.h    |   10 ++++
 arch/x86/include/asm/perf_regs_32.h |   84 +++++++++++++++++++++++++++++
 arch/x86/include/asm/perf_regs_64.h |   99 +++++++++++++++++++++++++++++++++++
 include/linux/perf_regs.h           |   28 ++++++++++
 6 files changed, 228 insertions(+), 0 deletions(-)
 create mode 100644 arch/x86/include/asm/perf_regs.h
 create mode 100644 arch/x86/include/asm/perf_regs_32.h
 create mode 100644 arch/x86/include/asm/perf_regs_64.h
 create mode 100644 include/linux/perf_regs.h

diff --git a/arch/Kconfig b/arch/Kconfig
index e9a9108..6c37af4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -219,6 +219,12 @@ 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 5638c74..77e155c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -59,6 +59,7 @@ 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..c2ea804
--- /dev/null
+++ b/arch/x86/include/asm/perf_regs.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+#ifdef CONFIG_X86_32
+#include "perf_regs_32.h"
+#else
+#include "perf_regs_64.h"
+#endif
+
+#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/include/asm/perf_regs_32.h b/arch/x86/include/asm/perf_regs_32.h
new file mode 100644
index 0000000..8201750
--- /dev/null
+++ b/arch/x86/include/asm/perf_regs_32.h
@@ -0,0 +1,84 @@
+#ifndef _ASM_X86_PERF_REGS_32_H
+#define _ASM_X86_PERF_REGS_32_H
+
+enum perf_event_x86_32_regs {
+	PERF_X86_32_REG_EAX,
+	PERF_X86_32_REG_EBX,
+	PERF_X86_32_REG_ECX,
+	PERF_X86_32_REG_EDX,
+	PERF_X86_32_REG_ESI,
+	PERF_X86_32_REG_EDI,
+	PERF_X86_32_REG_EBP,
+	PERF_X86_32_REG_ESP,
+	PERF_X86_32_REG_EIP,
+	PERF_X86_32_REG_FLAGS,
+	PERF_X86_32_REG_CS,
+	PERF_X86_32_REG_DS,
+	PERF_X86_32_REG_ES,
+	PERF_X86_32_REG_FS,
+	PERF_X86_32_REG_GS,
+
+	/* Non ABI */
+	PERF_X86_32_REG_MAX,
+};
+
+enum {
+	PERF_REGS_ABI_X86_32 = 1UL
+};
+
+static inline u64 perf_reg_version(void)
+{
+	return PERF_REGS_ABI_X86_32;
+}
+
+#ifdef __KERNEL__
+#define PERF_X86_32_REG_RESERVED (~((1ULL << PERF_X86_32_REG_MAX) - 1ULL))
+
+static inline int perf_reg_validate(u64 mask)
+{
+	if (mask & PERF_X86_32_REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	switch (idx) {
+	case PERF_X86_32_REG_EAX:
+		return regs->ax;
+	case PERF_X86_32_REG_EBX:
+		return regs->bx;
+	case PERF_X86_32_REG_ECX:
+		return regs->cx;
+	case PERF_X86_32_REG_EDX:
+		return regs->dx;
+	case PERF_X86_32_REG_ESI:
+		return regs->si;
+	case PERF_X86_32_REG_EDI:
+		return regs->di;
+	case PERF_X86_32_REG_EBP:
+		return regs->bp;
+	case PERF_X86_32_REG_ESP:
+		return regs->sp;
+	case PERF_X86_32_REG_EIP:
+		return regs->ip;
+	case PERF_X86_32_REG_FLAGS:
+		return regs->flags;
+	case PERF_X86_32_REG_CS:
+		return regs->cs;
+	case PERF_X86_32_REG_DS:
+		return regs->ds;
+	case PERF_X86_32_REG_ES:
+		return regs->es;
+	case PERF_X86_32_REG_FS:
+		return regs->fs;
+	case PERF_X86_32_REG_GS:
+		return regs->gs;
+	}
+
+	return 0;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_X86_PERF_REGS_32_H */
diff --git a/arch/x86/include/asm/perf_regs_64.h b/arch/x86/include/asm/perf_regs_64.h
new file mode 100644
index 0000000..63d7f1f
--- /dev/null
+++ b/arch/x86/include/asm/perf_regs_64.h
@@ -0,0 +1,99 @@
+#ifndef _ASM_X86_PERF_REGS_64_H
+#define _ASM_X86_PERF_REGS_64_H
+
+enum perf_event_x86_64_regs {
+	PERF_X86_64_REG_RAX,
+	PERF_X86_64_REG_RBX,
+	PERF_X86_64_REG_RCX,
+	PERF_X86_64_REG_RDX,
+	PERF_X86_64_REG_RSI,
+	PERF_X86_64_REG_RDI,
+	PERF_X86_64_REG_R8,
+	PERF_X86_64_REG_R9,
+	PERF_X86_64_REG_R10,
+	PERF_X86_64_REG_R11,
+	PERF_X86_64_REG_R12,
+	PERF_X86_64_REG_R13,
+	PERF_X86_64_REG_R14,
+	PERF_X86_64_REG_R15,
+	PERF_X86_64_REG_RBP,
+	PERF_X86_64_REG_RSP,
+	PERF_X86_64_REG_RIP,
+	PERF_X86_64_REG_FLAGS,
+	PERF_X86_64_REG_CS,
+	PERF_X86_64_REG_SS,
+
+	/* Non ABI */
+	PERF_X86_64_REG_MAX,
+};
+
+enum {
+	PERF_REGS_ABI_X86_64 = 2UL
+};
+
+static inline u64 perf_reg_version(void)
+{
+	return PERF_REGS_ABI_X86_64;
+}
+
+#ifdef __KERNEL__
+#define PERF_X86_64_REG_RESERVED (~((1ULL << PERF_X86_64_REG_MAX) - 1ULL))
+
+static inline int perf_reg_validate(u64 mask)
+{
+	if (mask & PERF_X86_64_REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	switch (idx) {
+	case PERF_X86_64_REG_RAX:
+		return regs->ax;
+	case PERF_X86_64_REG_RBX:
+		return regs->bx;
+	case PERF_X86_64_REG_RCX:
+		return regs->cx;
+	case PERF_X86_64_REG_RDX:
+		return regs->dx;
+	case PERF_X86_64_REG_RSI:
+		return regs->si;
+	case PERF_X86_64_REG_RDI:
+		return regs->di;
+	case PERF_X86_64_REG_R8:
+		return regs->r8;
+	case PERF_X86_64_REG_R9:
+		return regs->r9;
+	case PERF_X86_64_REG_R10:
+		return regs->r10;
+	case PERF_X86_64_REG_R11:
+		return regs->r11;
+	case PERF_X86_64_REG_R12:
+		return regs->r12;
+	case PERF_X86_64_REG_R13:
+		return regs->r13;
+	case PERF_X86_64_REG_R14:
+		return regs->r14;
+	case PERF_X86_64_REG_R15:
+		return regs->r15;
+	case PERF_X86_64_REG_RBP:
+		return regs->bp;
+	case PERF_X86_64_REG_RSP:
+		return regs->sp;
+	case PERF_X86_64_REG_RIP:
+		return regs->ip;
+	case PERF_X86_64_REG_FLAGS:
+		return regs->flags;
+	case PERF_X86_64_REG_CS:
+		return regs->cs;
+	case PERF_X86_64_REG_SS:
+		return regs->ss;
+	}
+
+	return 0;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_X86_PERF_REGS_64_H */
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
new file mode 100644
index 0000000..3d761d5
--- /dev/null
+++ b/include/linux/perf_regs.h
@@ -0,0 +1,28 @@
+#ifndef _LINUX_PERF_REGS_H
+#define _LINUX_PERF_REGS_H
+
+enum {
+	PERF_REGS_ABI_NONE = 0UL,
+};
+
+#ifdef CONFIG_HAVE_PERF_REGS
+#include <asm/perf_regs.h>
+#else
+static inline unsigned long perf_reg_version(void)
+{
+	return PERF_REGS_ABI_NONE;
+}
+
+#ifdef __KERNEL__
+static inline unsigned long perf_reg_value(struct pt_regs *regs, int idx)
+{
+	return 0;
+}
+
+static inline int perf_reg_validate(u64 mask)
+{
+	return mask ? -ENOSYS : 0;
+}
+#endif /* __KERNEL__ */
+#endif /* CONFIG_HAVE_PERF_REGS */
+#endif /* __ASM_GENERIC_PERF_REGS_H */
-- 
1.7.7.6

[PATCH 02/16] perf: Add ability to attach registers dump to sample

[Jiri Olsa]

Introducing new sample_type bit PERF_SAMPLE_REGS. Once set,
the sample_regs value determines the kind of registers going
to be attached to the sample.

Currently only user level registers are supported, specified by
PERF_SAMPLE_REGS_USER sample_regs value. 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).

When PERF_SAMPLE_REGS and PERF_SAMPLE_REGS_USER are set, the
sample_regs_user bitmap lets a user choose a set of registers
to dump for the sample. The layout of this 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.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 include/linux/perf_event.h |   25 ++++++++++-
 kernel/events/core.c       |   98 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 121 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f325786..06f4b04 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			= 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 for sample_regs when PERF_SAMPLE_REGS is set.
+ * Defines register set to be attached to the sample.
+ */
+enum perf_sample_regs {
+	PERF_SAMPLE_REGS_USER	= 1U << 0, /* user registers */
+	PERF_SAMPLE_REGS_MAX	= 1U << 1, /* non-ABI */
+};
+
+/*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
  *
@@ -271,7 +281,16 @@ 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 */
+
+	__u64	sample_regs; /* enum perf_sample_regs */
+
+	/*
+	 * Arch specific mask for PERF_SAMPLE_REGS_USER setup.
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
 };
 
 /*
@@ -607,6 +626,7 @@ 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>
 
 #define PERF_MAX_STACK_DEPTH		255
@@ -1130,6 +1150,7 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
+	struct pt_regs			*regs_user;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5b06cbb..e1d9e0c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3751,6 +3751,37 @@ 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 i = 0;
+
+	do {
+		u64 val;
+
+		if (mask & 1) {
+			val = perf_reg_value(regs, i);
+			perf_output_put(handle, val);
+		}
+
+		mask >>= 1;
+		i++;
+	} while (mask);
+}
+
+static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
+{
+	if (!user_mode(regs)) {
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	return regs;
+}
+
 static void __perf_event_header__init_id(struct perf_event_header *header,
 					 struct perf_sample_data *data,
 					 struct perf_event *event)
@@ -4011,6 +4042,30 @@ void perf_output_sample(struct perf_output_handle *handle,
 			perf_output_put(handle, nr);
 		}
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS) {
+		u64 mode = event->attr.sample_regs;
+
+		if (mode & PERF_SAMPLE_REGS_USER) {
+			u64 id = PERF_REGS_ABI_NONE;
+
+			/*
+			 * If there are no regs to dump, notice it through
+			 * PERF_REGS_ABI_NONE id.
+			 */
+			if (data->regs_user)
+				id = perf_reg_version();
+
+			perf_output_put(handle, id);
+
+			if (id) {
+				u64 mask = event->attr.sample_regs_user;
+				perf_output_sample_regs(handle,
+							data->regs_user,
+							mask);
+			}
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -4062,6 +4117,24 @@ void perf_prepare_sample(struct perf_event_header *header,
 		}
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS) {
+		u64 mode = event->attr.sample_regs;
+		int size = 0;
+
+		if (mode & PERF_SAMPLE_REGS_USER) {
+			/* regs ID size */
+			size += sizeof(u64);
+
+			data->regs_user = perf_sample_regs_user(regs);
+			if (data->regs_user) {
+				u64 mask = event->attr.sample_regs_user;
+				size += hweight64(mask) * sizeof(u64);
+			}
+		}
+
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -6111,6 +6184,31 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			attr->branch_sample_type = mask;
 		}
 	}
+
+	if (attr->sample_type & PERF_SAMPLE_REGS) {
+		/* Mode must be specified. */
+		if (attr->sample_regs & ~(PERF_SAMPLE_REGS_MAX-1))
+			return -EINVAL;
+
+		/* Validate registers mask for user mode. */
+		if (attr->sample_regs & PERF_SAMPLE_REGS_USER)
+			ret = perf_reg_validate(attr->sample_regs_user);
+		else if (attr->sample_regs_user)
+			return -EINVAL;
+
+		if (ret)
+			return ret;
+	} else  {
+		/*
+		 * Registers are not required in sample, all regs
+		 * settings should be zero.
+		 */
+		if (attr->sample_regs)
+			return -EINVAL;
+		if (attr->sample_regs_user)
+			return -EINVAL;
+	}
+
 out:
 	return ret;
 
-- 
1.7.7.6

[PATCH 03/16] perf: Factor __output_copy to be usable with specific copy function

[Jiri Olsa]

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,
comming in next patches.

Signed-off-by: Frederic Weisbecker <fweisbec@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 588f52e..c77b657 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -257,4 +257,6 @@ static inline void perf_events_lapic_init(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 06f4b04..6942c13 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1307,7 +1307,7 @@ 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 b0b107f..ed8ab26 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 <asm/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 pt_regs *regs);
 extern int get_callchain_buffers(void);
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)
-- 
1.7.7.6

[PATCH 04/16] perf: Add ability to attach user stack dump to sample

[Jiri Olsa]

Introducing new sample_type bit PERF_SAMPLE_STACK. Once set,
the sample_stack value determines the stack which is going
to be attached.

Currently only user level stack is supported, specified by
PERF_SAMPLE_STACK_USER bit in sample_stack value. When set,
the sample_stack_user value determines the size of the
stack dump.

Beeing 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.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 include/linux/perf_event.h |   20 ++++++++-
 kernel/events/core.c       |  103 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+), 1 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6942c13..dcdc97e 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			= 1U << 12,
+	PERF_SAMPLE_STACK			= 1U << 13,
 
-	PERF_SAMPLE_MAX = 1U << 13,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 14,		/* non-ABI */
 };
 
 /*
@@ -173,6 +174,15 @@ enum perf_sample_regs {
 };
 
 /*
+ * Values for sample_stack when PERF_SAMPLE_STACK is set.
+ * Defines stack dump to be attached to the sample.
+ */
+enum perf_sample_stack {
+	PERF_SAMPLE_STACK_USER	= 1U << 0, /* user stack */
+	PERF_SAMPLE_STACK_MAX	= 1U << 1, /* non-ABI */
+};
+
+/*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
  *
@@ -291,6 +301,14 @@ struct perf_event_attr {
 	 * See asm/perf_regs.h for details.
 	 */
 	__u64	sample_regs_user;
+
+	__u64	sample_stack; /* enum perf_sample_stack */
+
+	/*
+	 * Defines size of the user stack to dump on samples,
+	 * for sample_stack PERF_SAMPLE_STACK_USER settings.
+	 */
+	__u64	sample_stack_user;
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e1d9e0c..0ace2c7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3770,6 +3770,45 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 	} while (mask);
 }
 
+static void
+perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
+			  struct pt_regs *regs)
+{
+	u64 size;
+
+	/* Case of a kernel thread, nothing to dump */
+	if (!regs) {
+		size = 0;
+		perf_output_put(handle, size);
+	} else {
+		unsigned long sp;
+		unsigned int rem;
+		u64 dyn_size;
+
+		/*
+		 * Static size: we always dump the size
+		 * requested by the user because most of the
+		 * time, the top of the user stack is not
+		 * paged out.
+		 */
+		size = round_up(dump_size, sizeof(u64));
+		perf_output_put(handle, size);
+
+		sp = user_stack_pointer(regs);
+		rem = __output_copy_user(handle, (void *)sp, size);
+		dyn_size = size - rem;
+
+		/* What couldn't be dumped is zero padded */
+		while (rem--) {
+			char zero = 0;
+			perf_output_put(handle, zero);
+		}
+
+		/* Dynamic size: whole dump - padding */
+		perf_output_put(handle, dyn_size);
+	}
+}
+
 static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
 {
 	if (!user_mode(regs)) {
@@ -4066,6 +4105,17 @@ void perf_output_sample(struct perf_output_handle *handle,
 			}
 		}
 	}
+
+	if (sample_type & PERF_SAMPLE_STACK) {
+		u64 mode = event->attr.sample_stack;
+
+		if (mode & PERF_SAMPLE_STACK_USER) {
+			u64 dump_size = event->attr.sample_stack_user;
+
+			perf_output_sample_ustack(handle, dump_size,
+						  data->regs_user);
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -4135,6 +4185,39 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_STACK) {
+		u64 mode = event->attr.sample_stack;
+		int size = 0;
+
+		if (mode & PERF_SAMPLE_STACK_USER) {
+			if (!data->regs_user)
+				data->regs_user = perf_sample_regs_user(regs);
+
+			/*
+			 * A first field that tells the _static_ size of the
+			 * dump. 0 if there is nothing to dump (ie: we are in
+			 * a kernel thread) otherwise the requested size.
+			 */
+			size += sizeof(u64);
+
+			/*
+			 * 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. What couldn't be dumped will be zero-padded.
+			 */
+			if (data->regs_user) {
+				u64 user_size = event->attr.sample_stack_user;
+
+				user_size = round_up(user_size, sizeof(u64));
+				size += user_size;
+				size += sizeof(u64);
+			}
+		}
+
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -6209,6 +6292,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			return -EINVAL;
 	}
 
+	if (attr->sample_type & PERF_SAMPLE_STACK) {
+		/* Mode must be specified. */
+		if (attr->sample_stack & ~(PERF_SAMPLE_STACK_MAX-1))
+			return -EINVAL;
+
+		/* Validate registers mask for user mode. */
+		if ((attr->sample_stack & PERF_SAMPLE_STACK_USER) &&
+		    (!attr->sample_stack_user))
+			return -EINVAL;
+	} else  {
+		/*
+		 * Stack dump not required in sample, all stack
+		 * settings should be zero.
+		 */
+		if (attr->sample_stack)
+			return -EINVAL;
+		if (attr->sample_stack_user)
+			return -EINVAL;
+	}
+
 out:
 	return ret;
 
-- 
1.7.7.6

[PATCH 05/16] perf: Add attribute to filter out user callchains

[Jiri Olsa]

Add the new exclude_user_callchain attribute to filter out
frame pointer based user callchains.

This is something we want to select when we use the dwarf cfi
callchain mode, because frame pointer based user callchains are
useless in this mode.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 include/linux/perf_event.h |    4 +++-
 kernel/events/callchain.c  |    4 ++--
 kernel/events/core.c       |    3 ++-
 kernel/events/internal.h   |    3 ++-
 4 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index dcdc97e..df6ba37 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -275,7 +275,9 @@ struct perf_event_attr {
 				exclude_host   :  1, /* don't count in host   */
 				exclude_guest  :  1, /* don't count in guest  */
 
-				__reserved_1   : 43;
+				exclude_user_callchain : 1, /* only record kernel callchains */
+
+				__reserved_1   : 42;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 6581a04..884e997 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -153,7 +153,7 @@ put_callchain_entry(int rctx)
 	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
 }
 
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs, int user)
 {
 	int rctx;
 	struct perf_callchain_entry *entry;
@@ -177,7 +177,7 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 			regs = NULL;
 	}
 
-	if (regs) {
+	if (user && regs) {
 		perf_callchain_store(entry, PERF_CONTEXT_USER);
 		perf_callchain_user(entry, regs);
 	}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0ace2c7..8e73a2b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4138,8 +4138,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
+		int user = !event->attr.exclude_user_callchain;
 
-		data->callchain = perf_callchain(regs);
+		data->callchain = perf_callchain(regs, user);
 
 		if (data->callchain)
 			size += data->callchain->nr;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index ed8ab26..b18465b 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -121,7 +121,8 @@ DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
 DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
 /* Callchain handling */
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs,
+						   int user);
 extern int get_callchain_buffers(void);
 extern void put_callchain_buffers(void);
 
-- 
1.7.7.6

[PATCH 06/16] perf, tool: Factor DSO symtab types to generic binary types

[Jiri Olsa]

Adding interface to access DSOs so it could be used
from another place.

New DSO binary type is added - making current SYMTAB__*
types more general:
   DSO_BINARY_TYPE__* = SYMTAB__*

Folowing function is added to return path based on the specified
binary type:
   dso__binary_type_file

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-top.c   |    2 +-
 tools/perf/util/annotate.c |    2 +-
 tools/perf/util/symbol.c   |  181 +++++++++++++++++++++++++++-----------------
 tools/perf/util/symbol.h   |   32 ++++----
 4 files changed, 129 insertions(+), 88 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6031dce..165928e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -125,7 +125,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		pr_err("Can't annotate %s: No vmlinux file was found in the "
 		       "path\n", sym->name);
 		sleep(1);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8069dfb..7d3641f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -777,7 +777,7 @@ fallback:
 		free_filename = false;
 	}
 
-	if (dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
 		char *build_id_msg = NULL;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e2ba885..5736fda 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -48,6 +48,22 @@ struct symbol_conf symbol_conf = {
 	.symfs            = "",
 };
 
+static enum dso_binary_type binary_type_symtab[] = {
+	DSO_BINARY_TYPE__KALLSYMS,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab)
+
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -318,7 +334,7 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->symtab_type = SYMTAB__NOT_FOUND;
+		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
@@ -805,9 +821,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	symbols__fixup_end(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 	else
-		dso->symtab_type = SYMTAB__KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	return dso__split_kallsyms(dso, map, filter);
 }
@@ -1562,31 +1578,96 @@ out:
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
-		[SYMTAB__KALLSYMS]	      = 'k',
-		[SYMTAB__JAVA_JIT]	      = 'j',
-		[SYMTAB__BUILD_ID_CACHE]      = 'B',
-		[SYMTAB__FEDORA_DEBUGINFO]    = 'f',
-		[SYMTAB__UBUNTU_DEBUGINFO]    = 'u',
-		[SYMTAB__BUILDID_DEBUGINFO]   = 'b',
-		[SYMTAB__SYSTEM_PATH_DSO]     = 'd',
-		[SYMTAB__SYSTEM_PATH_KMODULE] = 'K',
-		[SYMTAB__GUEST_KALLSYMS]      =  'g',
-		[SYMTAB__GUEST_KMODULE]	      =  'G',
+		[DSO_BINARY_TYPE__KALLSYMS]		= 'k',
+		[DSO_BINARY_TYPE__JAVA_JIT]		= 'j',
+		[DSO_BINARY_TYPE__BUILD_ID_CACHE]	= 'B',
+		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]	= 'f',
+		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]	= 'u',
+		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]	= 'b',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]	= 'd',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]	= 'K',
+		[DSO_BINARY_TYPE__GUEST_KALLSYMS]	= 'g',
+		[DSO_BINARY_TYPE__GUEST_KMODULE]	= 'G',
 	};
 
-	if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
+	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
 		return '!';
 	return origin[dso->symtab_type];
 }
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size)
+{
+	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	int ret = 0;
+
+	switch (type) {
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		/* skip the locally configured cache if a symfs is given */
+		if (symbol_conf.symfs[0] ||
+		    (dso__build_id_filename(dso, file, size) == NULL))
+			ret = -1;
+		break;
+
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s.debug",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+		if (!dso->has_build_id) {
+			ret = -1;
+			break;
+		}
+
+		build_id__sprintf(dso->build_id,
+				  sizeof(dso->build_id),
+				  build_id_hex);
+		snprintf(file, size,
+			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+		snprintf(file, size, "%s%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+			 root_dir, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		snprintf(file, size, "%s%s", symbol_conf.symfs,
+			 dso->long_name);
+		break;
+
+	default:
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__NOT_FOUND:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
-	int size = PATH_MAX;
 	char *name;
 	int ret = -1;
 	int fd;
+	u_int i;
 	struct machine *machine;
-	const char *root_dir;
+	char *root_dir = (char *) "";
 	int want_symtab;
 
 	dso__set_loaded(dso, map->type);
@@ -1601,7 +1682,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	else
 		machine = NULL;
 
-	name = malloc(size);
+	name = malloc(PATH_MAX);
 	if (!name)
 		return -1;
 
@@ -1620,69 +1701,27 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
-		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
-					      SYMTAB__NOT_FOUND;
+		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
+					     DSO_BINARY_TYPE__NOT_FOUND;
 		return ret;
 	}
 
+	if (machine)
+		root_dir = machine->root_dir;
+
 	/* Iterate over candidate debug images.
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
 	want_symtab = 1;
 restart:
-	for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE;
-	     dso->symtab_type != SYMTAB__NOT_FOUND;
-	     dso->symtab_type++) {
-		switch (dso->symtab_type) {
-		case SYMTAB__BUILD_ID_CACHE:
-			/* skip the locally configured cache if a symfs is given */
-			if (symbol_conf.symfs[0] ||
-			    (dso__build_id_filename(dso, name, size) == NULL)) {
-				continue;
-			}
-			break;
-		case SYMTAB__FEDORA_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s.debug",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__UBUNTU_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__BUILDID_DEBUGINFO: {
-			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-
-			if (!dso->has_build_id)
-				continue;
+	for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
 
-			build_id__sprintf(dso->build_id,
-					  sizeof(dso->build_id),
-					  build_id_hex);
-			snprintf(name, size,
-				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
-			}
-			break;
-		case SYMTAB__SYSTEM_PATH_DSO:
-			snprintf(name, size, "%s%s",
-			     symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__GUEST_KMODULE:
-			if (map->groups && machine)
-				root_dir = machine->root_dir;
-			else
-				root_dir = "";
-			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
-				 root_dir, dso->long_name);
-			break;
+		dso->symtab_type = binary_type_symtab[i];
 
-		case SYMTAB__SYSTEM_PATH_KMODULE:
-			snprintf(name, size, "%s%s", symbol_conf.symfs,
-				 dso->long_name);
-			break;
-		default:;
-		}
+		if (dso__binary_type_file(dso, dso->symtab_type,
+					  root_dir, name, PATH_MAX))
+			continue;
 
 		/* Name is now the name of the next image to try */
 		fd = open(name, O_RDONLY);
@@ -1899,9 +1938,9 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		return NULL;
 
 	if (machine__is_host(machine))
-		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
-		dso->symtab_type = SYMTAB__GUEST_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5649d63..ba13790 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -154,6 +154,20 @@ struct addr_location {
 	s32	      cpu;
 };
 
+enum dso_binary_type {
+	DSO_BINARY_TYPE__KALLSYMS = 0,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
 enum dso_kernel_type {
 	DSO_TYPE_USER = 0,
 	DSO_TYPE_KERNEL,
@@ -165,13 +179,13 @@ struct dso {
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	enum dso_kernel_type	kernel;
+	enum dso_binary_type	symtab_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
 	u8		 sname_alloc:1;
 	u8		 lname_alloc:1;
-	unsigned char	 symtab_type;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
@@ -223,20 +237,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 				    enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
-enum symtab_type {
-	SYMTAB__KALLSYMS = 0,
-	SYMTAB__GUEST_KALLSYMS,
-	SYMTAB__JAVA_JIT,
-	SYMTAB__BUILD_ID_CACHE,
-	SYMTAB__FEDORA_DEBUGINFO,
-	SYMTAB__UBUNTU_DEBUGINFO,
-	SYMTAB__BUILDID_DEBUGINFO,
-	SYMTAB__SYSTEM_PATH_DSO,
-	SYMTAB__GUEST_KMODULE,
-	SYMTAB__SYSTEM_PATH_KMODULE,
-	SYMTAB__NOT_FOUND,
-};
-
 char dso__symtab_origin(const struct dso *dso);
 void dso__set_long_name(struct dso *dso, char *name);
 void dso__set_build_id(struct dso *dso, void *build_id);
@@ -273,4 +273,6 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size);
 #endif /* __PERF_SYMBOL */
-- 
1.7.7.6

[PATCH 07/16] perf, tool: Add interface to read DSO image data

[Jiri Olsa]

Adding following interface for DSO object to allow
reading of DSO image data:

  dso__data_fd
    - opens DSO and returns file descriptor
      Binary types are used to locate/open DSO in following order:
        DSO_BINARY_TYPE__BUILD_ID_CACHE
        DSO_BINARY_TYPE__SYSTEM_PATH_DSO
      In other word we first try to open DSO build-id path,
      and if that fails we try to open DSO system path.

  dso__data_read_offset
    - reads DSO data from specified offset

  dso__data_read_addr
    - reads DSO data from specified addres/map.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/symbol.c |  107 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/symbol.h |    8 +++
 2 files changed, 115 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 5736fda..041ffa5 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -64,6 +64,14 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab)
 
+static enum dso_binary_type binary_type_data[] = {
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__DATA_CNT sizeof(binary_type_data)
+
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -335,6 +343,7 @@ struct dso *dso__new(const char *name)
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
@@ -2830,3 +2839,101 @@ struct map *dso__new_map(const char *name)
 
 	return map;
 }
+
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	char *root_dir = (char *) "";
+	char *name;
+	int fd;
+
+	name = malloc(PATH_MAX);
+	if (!name)
+		return -ENOMEM;
+
+	if (machine)
+		root_dir = machine->root_dir;
+
+	if (dso__binary_type_file(dso, dso->data_type,
+				  root_dir, name, PATH_MAX))
+		return -EINVAL;
+
+	fd = open(name, O_RDONLY);
+	free(name);
+	return fd;
+}
+
+int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int i = 0;
+
+	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+		return open_dso(dso, machine);
+
+	do {
+		int fd;
+
+		dso->data_type = binary_type_data[i++];
+
+		fd = open_dso(dso, machine);
+		if (fd >= 0)
+			return fd;
+
+	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+
+	return -EINVAL;
+}
+
+static ssize_t dso_cache_read(struct dso *dso __used, u64 offset __used,
+			      u8 *data __used, ssize_t size __used)
+{
+	return -EINVAL;
+}
+
+static int dso_cache_add(struct dso *dso __used, u64 offset __used,
+			 u8 *data __used, ssize_t size __used)
+{
+	return 0;
+}
+
+static ssize_t read_dso_data(struct dso *dso, struct machine *machine,
+		     u64 offset, u8 *data, ssize_t size)
+{
+	ssize_t rsize = -1;
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return -1;
+
+	do {
+		if (-1 == lseek(fd, offset, SEEK_SET))
+			break;
+
+		rsize = read(fd, data, size);
+		if (-1 == rsize)
+			break;
+
+		if (dso_cache_add(dso, offset, data, size))
+			pr_err("Failed to add data int dso cache.");
+
+	} while (0);
+
+	close(fd);
+	return rsize;
+}
+
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	if (dso_cache_read(dso, offset, data, size))
+		return read_dso_data(dso, machine, offset, data, size);
+	return 0;
+}
+
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size)
+{
+	u64 offset = map->map_ip(map, addr);
+	return dso__data_read_offset(dso, machine, offset, data, size);
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ba13790..32da5e6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -180,6 +180,7 @@ struct dso {
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	enum dso_kernel_type	kernel;
 	enum dso_binary_type	symtab_type;
+	enum dso_binary_type	data_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
@@ -275,4 +276,11 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
 int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 			  char *root_dir, char *file, size_t size);
+
+int dso__data_fd(struct dso *dso, struct machine *machine);
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size);
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size);
 #endif /* __PERF_SYMBOL */
-- 
1.7.7.6

[PATCH 08/16] perf, tool: Add '.note' check into search for NOTE section

[Jiri Olsa]

Adding '.note' section name to be check when looking for notes
section. The '.note' name is used by kernel VDSO.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/symbol.c |   29 +++++++++++++++++++++++------
 1 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 041ffa5..6955c3c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1472,14 +1472,31 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 		goto out;
 	}
 
-	sec = elf_section_by_name(elf, &ehdr, &shdr,
-				  ".note.gnu.build-id", NULL);
-	if (sec == NULL) {
+	/*
+	 * Check following sections for notes:
+	 *   '.note.gnu.build-id'
+	 *   '.notes'
+	 *   '.note' (VDSO specific)
+	 */
+	do {
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".note.gnu.build-id", NULL);
+		if (sec)
+			break;
+
 		sec = elf_section_by_name(elf, &ehdr, &shdr,
 					  ".notes", NULL);
-		if (sec == NULL)
-			goto out;
-	}
+		if (sec)
+			break;
+
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".note", NULL);
+		if (sec)
+			break;
+
+		return err;
+
+	} while (0);
 
 	data = elf_getdata(sec, NULL);
 	if (data == NULL)
-- 
1.7.7.6

[PATCH 09/16] perf, tool: Back [vdso] DSO with real data

[Jiri Olsa]

Storing data for VDSO shared object, because we need it for
the unwind process.

The idea is that VDSO shared object is same for all process
on a running system, so it makes no difference if we store
it inside the tracer - perf.

The record command:
When [vdso] map memory is hit, we retrieve [vdso] DSO image
and store it into temporary file. During the build-id
processing the [vdso] DSO image is stored in build-id db,
and build-id refference is made inside perf.data. The temporary
file is removed when record is finished.

The report command:
We read build-id from perf.data and store [vdso] DSO object.
This object is refferenced and attached to map when the MMAP
events are processed. Thus during the SAMPLE event processing
we have correct mmap/dso attached.

Adding following API for vdso object:
  vdso__file
    - vdso temp file path

  vdso__get_file
    - finds and store VDSO image into temp file,
      the temp file path is returned

  vdso__exit
    - removes temporary VDSO image if there's any

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/Makefile       |    2 +
 tools/perf/util/map.c     |   23 ++++++++++-
 tools/perf/util/session.c |    2 +
 tools/perf/util/vdso.c    |   90 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/vdso.h    |    8 ++++
 5 files changed, 123 insertions(+), 2 deletions(-)
 create mode 100644 tools/perf/util/vdso.c
 create mode 100644 tools/perf/util/vdso.h

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1d3d513..cf5c71e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -319,6 +319,7 @@ LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
 LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
+LIB_H += util/vdso.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -382,6 +383,7 @@ LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
 LIB_OBJS += $(OUTPUT)util/cgroup.o
 LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/vdso.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 35ae568..1649ea0 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -7,6 +7,7 @@
 #include <stdio.h>
 #include <unistd.h>
 #include "map.h"
+#include "vdso.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -18,10 +19,14 @@ static inline int is_anon_memory(const char *filename)
 	return strcmp(filename, "//anon") == 0;
 }
 
+static inline int is_vdso_memory(const char *filename)
+{
+	return !strcmp(filename, "[vdso]");
+}
+
 static inline int is_no_dso_memory(const char *filename)
 {
 	return !strcmp(filename, "[stack]") ||
-	       !strcmp(filename, "[vdso]")  ||
 	       !strcmp(filename, "[heap]");
 }
 
@@ -50,9 +55,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 	if (self != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
-		int anon, no_dso;
+		int anon, no_dso, vdso;
 
 		anon = is_anon_memory(filename);
+		vdso = is_vdso_memory(filename);
 		no_dso = is_no_dso_memory(filename);
 
 		if (anon) {
@@ -60,10 +66,23 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 			filename = newfilename;
 		}
 
+		if (vdso) {
+			filename = (char *) vdso__file;
+			pgoff = 0;
+		}
+
 		dso = __dsos__findnew(dsos__list, filename);
 		if (dso == NULL)
 			goto out_delete;
 
+		if (vdso && !dso->has_build_id) {
+			char *file_vdso = vdso__get_file();
+			if (file_vdso)
+				dso__set_long_name(dso, file_vdso);
+			else
+				no_dso = 1;
+		}
+
 		map__init(self, type, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 93d355d..83f5884 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
 #include "sort.h"
 #include "util.h"
 #include "cpumap.h"
+#include "vdso.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -209,6 +210,7 @@ void perf_session__delete(struct perf_session *self)
 	machine__exit(&self->host_machine);
 	close(self->fd);
 	free(self);
+	vdso__exit();
 }
 
 void machine__remove_thread(struct machine *self, struct thread *th)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
new file mode 100644
index 0000000..e964482
--- /dev/null
+++ b/tools/perf/util/vdso.c
@@ -0,0 +1,90 @@
+
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include "vdso.h"
+#include "util.h"
+
+const char vdso__file[] = "/tmp/vdso.so";
+static bool vdso_found;
+
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		pr_err("vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], "[vdso]", 6))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}
+
+char *vdso__get_file(void)
+{
+	char *vdso = NULL;
+	char *buf = NULL;
+	void *start, *end;
+
+	do {
+		int fd, size;
+
+		if (vdso_found) {
+			vdso = (char *) vdso__file;
+			break;
+		}
+
+		if (find_vdso_map(&start, &end))
+			break;
+
+		size = end - start;
+		buf = malloc(size);
+		if (!buf)
+			break;
+
+		memcpy(buf, start, size);
+
+		fd = open(vdso__file, O_CREAT|O_WRONLY|O_TRUNC, S_IRWXU);
+		if (fd < 0)
+			break;
+
+		if (size == write(fd, buf, size))
+			vdso = (char *) vdso__file;
+
+		close(fd);
+	} while (0);
+
+	if (buf)
+		free(buf);
+
+	vdso_found = (vdso != NULL);
+	return vdso;
+}
+
+void vdso__exit(void)
+{
+	if (vdso_found)
+		unlink(vdso__file);
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
new file mode 100644
index 0000000..908b041
--- /dev/null
+++ b/tools/perf/util/vdso.h
@@ -0,0 +1,8 @@
+#ifndef __VDSO__
+#define __VDSO__
+
+extern const char vdso__file[];
+char *vdso__get_file(void);
+void  vdso__exit(void);
+
+#endif /* __VDSO__ */
-- 
1.7.7.6

[PATCH 10/16] perf, tool: Add interface to arch registers sets

[Jiri Olsa]

Adding header files to access unified API for arch registers.

In addition adding a way to obtain register name based on the
API ID value.

Also adding 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>
---
 tools/perf/Makefile                     |   13 ++++-
 tools/perf/arch/x86/include/perf_regs.h |  108 +++++++++++++++++++++++++++++++
 tools/perf/util/perf_regs.h             |   19 ++++++
 3 files changed, 139 insertions(+), 1 deletions(-)
 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 cf5c71e..44b99bb 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_DEFS := 1
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
 
 # Additional ARCH settings for x86
 ifeq ($(ARCH),i386)
-        ARCH := x86
+	ARCH := x86
+	NO_PERF_REGS_DEFS := 0
 endif
 ifeq ($(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_DEFS := 0
 endif
 
 # Treat warnings as errors unless directed not to
@@ -320,6 +323,7 @@ LIB_H += util/cgroup.h
 LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
 LIB_H += util/vdso.h
+LIB_H += util/perf_regs.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -665,6 +669,13 @@ else
 	endif
 endif
 
+ifeq ($(NO_PERF_REGS_DEFS),0)
+	ifeq ($(ARCH),x86)
+		LIB_H += arch/x86/include/perf_regs.h
+	endif
+else
+	BASIC_CFLAGS += -DNO_PERF_REGS_DEFS
+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..d6070ec
--- /dev/null
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -0,0 +1,108 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include "../../util/types.h"
+
+#ifdef ARCH_X86_64
+#include "../../../../../arch/x86/include/asm/perf_regs_64.h"
+
+#define PERF_REGS_MASK ((1 << PERF_X86_64_REG_MAX) - 1)
+#define PERF_REG_IP PERF_X86_64_REG_RIP
+#define PERF_REG_SP PERF_X86_64_REG_RSP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_X86_64_REG_RAX:
+		return "RAX";
+	case PERF_X86_64_REG_RBX:
+		return "RBX";
+	case PERF_X86_64_REG_RCX:
+		return "RCX";
+	case PERF_X86_64_REG_RDX:
+		return "RDX";
+	case PERF_X86_64_REG_RSI:
+		return "RSI";
+	case PERF_X86_64_REG_RDI:
+		return "RDI";
+	case PERF_X86_64_REG_R8:
+		return "R8";
+	case PERF_X86_64_REG_R9:
+		return "R9";
+	case PERF_X86_64_REG_R10:
+		return "R10";
+	case PERF_X86_64_REG_R11:
+		return "R11";
+	case PERF_X86_64_REG_R12:
+		return "R12";
+	case PERF_X86_64_REG_R13:
+		return "R13";
+	case PERF_X86_64_REG_R14:
+		return "R14";
+	case PERF_X86_64_REG_R15:
+		return "R15";
+	case PERF_X86_64_REG_RBP:
+		return "RBP";
+	case PERF_X86_64_REG_RSP:
+		return "RSP";
+	case PERF_X86_64_REG_RIP:
+		return "RIP";
+	case PERF_X86_64_REG_FLAGS:
+		return "FLAGS";
+	case PERF_X86_64_REG_CS:
+		return "CS";
+	case PERF_X86_64_REG_SS:
+		return "SS";
+	default:
+		return NULL;
+	}
+	return NULL;
+}
+#else
+#include "../../../../../arch/x86/include/asm/perf_regs_32.h"
+
+#define PERF_REGS_MASK ((1 << PERF_X86_32_REG_MAX) - 1)
+#define PERF_REG_IP PERF_X86_32_REG_EIP
+#define PERF_REG_SP PERF_X86_32_REG_ESP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_X86_32_REG_EAX:
+		return "EAX";
+	case PERF_X86_32_REG_EBX:
+		return "EBX";
+	case PERF_X86_32_REG_ECX:
+		return "ECX";
+	case PERF_X86_32_REG_EDX:
+		return "EDX";
+	case PERF_X86_32_REG_ESI:
+		return "ESI";
+	case PERF_X86_32_REG_EDI:
+		return "EDI";
+	case PERF_X86_32_REG_EBP:
+		return "EBP";
+	case PERF_X86_32_REG_ESP:
+		return "ESP";
+	case PERF_X86_32_REG_EIP:
+		return "EIP";
+	case PERF_X86_32_REG_FLAGS:
+		return "FLAGS";
+	case PERF_X86_32_REG_CS:
+		return "CS";
+	case PERF_X86_32_REG_DS:
+		return "DS";
+	case PERF_X86_32_REG_ES:
+		return "ES";
+	case PERF_X86_32_REG_FS:
+		return "FS";
+	case PERF_X86_32_REG_GS:
+		return "GS";
+	default:
+		return NULL;
+	}
+	return NULL;
+}
+#endif /* ARCH_X86_64 */
+#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..d65cbf9
--- /dev/null
+++ b/tools/perf/util/perf_regs.h
@@ -0,0 +1,19 @@
+#ifndef __PERF_REGS_H
+#define __PERF_REGS_H
+
+#ifndef NO_PERF_REGS_DEFS
+#include <perf_regs.h>
+#else
+#define PERF_REGS_MASK	0
+
+static inline const char *perf_reg_name(int id __used)
+{
+	return NULL;
+}
+
+static inline unsigned long perf_reg_version(void)
+{
+	return 0;
+}
+#endif /* NO_PERF_REGS_DEFS */
+#endif /* __PERF_REGS_H */
-- 
1.7.7.6

[PATCH 11/16] perf, tool: Add libunwind dependency for dwarf cfi unwinding

[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.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/Makefile                 |   27 ++++++++++++++++++++++++++-
 tools/perf/config/feature-tests.mak |   25 +++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 1 deletions(-)

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 44b99bb..acc4421 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -59,6 +59,7 @@ AR = $(CROSS_COMPILE)ar
 ifeq ($(ARCH),i386)
 	ARCH := x86
 	NO_PERF_REGS_DEFS := 0
+	LIBUNWIND_LIBS = -lunwind -lunwind-x86
 endif
 ifeq ($(ARCH),x86_64)
 	ARCH := x86
@@ -72,6 +73,7 @@ ifeq ($(ARCH),x86_64)
 		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
 	endif
 	NO_PERF_REGS_DEFS := 0
+	LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
 endif
 
 # Treat warnings as errors unless directed not to
@@ -92,7 +94,7 @@ ifdef PARSER_DEBUG
 	PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
 endif
 
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(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 = $(LDFLAGS)
@@ -458,6 +460,21 @@ ifneq ($(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),)
@@ -489,6 +506,14 @@ 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 d9084e0..51cd201 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -141,3 +141,28 @@ 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
-- 
1.7.7.6

[PATCH 12/16] perf, tool: Support user regs and stack in sample parsing

[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 comming in shortly.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-test.c |    3 +-
 tools/perf/util/event.h   |   16 ++++++++++++-
 tools/perf/util/evlist.c  |   24 +++++++++++++++++++
 tools/perf/util/evlist.h  |    3 ++
 tools/perf/util/evsel.c   |   30 +++++++++++++++++++++++-
 tools/perf/util/python.c  |    3 +-
 tools/perf/util/session.c |   56 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/session.h |   12 ++++++++-
 8 files changed, 141 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 5a8727c..082d279 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -564,7 +564,7 @@ static int test__basic_mmap(void)
 		}
 
 		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample, false);
+					       false, 0, 0, 0, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
@@ -790,6 +790,7 @@ static int test__PERF_RECORD(void)
 
 				err = perf_event__parse_sample(event, sample_type,
 							       sample_size, true,
+							       0, 0, 0,
 							       &sample, false);
 				if (err < 0) {
 					if (verbose)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1b19728..4b03b68 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 version;
+	u64 *regs;
+};
+
+struct stack_dump {
+	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
@@ -199,7 +211,9 @@ const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample, bool swapped);
+			     u64 sample_regs_mode, u64 sample_regs_user,
+			     u64 sample_stack, struct perf_sample *data,
+			     bool swapped);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4ac5f5a..548caa0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -676,6 +676,30 @@ bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
 	return true;
 }
 
+u64 perf_evlist__sample_regs(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_regs;
+}
+
+u64 perf_evlist__sample_regs_user(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_regs_user;
+}
+
+u64 perf_evlist__sample_stack(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_stack;
+}
+
 u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
 {
 	struct perf_evsel *first;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 58abb63..206810c 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -117,6 +117,9 @@ u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
 
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_regs(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_regs_user(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_stack(const struct perf_evlist *evlist);
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 				   struct list_head *list,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 57e4ce5..8d21d2c 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"
@@ -454,7 +455,9 @@ static bool sample_overlap(const union perf_event *event,
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *data, bool swapped)
+			     u64 sample_regs, u64 sample_regs_user,
+			     u64 sample_stack, struct perf_sample *data,
+			     bool swapped)
 {
 	const u64 *array;
 
@@ -592,6 +595,31 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 		sz /= sizeof(u64);
 		array += sz;
 	}
+
+	if (type & PERF_SAMPLE_REGS) {
+		if (sample_regs & PERF_SAMPLE_REGS_USER) {
+			data->user_regs.version = *array++;
+			if (data->user_regs.version) {
+				data->user_regs.regs = (u64 *)array;
+				array += hweight_long(sample_regs_user);
+			}
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK) {
+		if (sample_stack & PERF_SAMPLE_STACK_USER) {
+			u64 size = *array++;
+
+			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;
 }
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index e03b58a..d91ff53 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -807,7 +807,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
 		err = perf_event__parse_sample(event, first->attr.sample_type,
 					       perf_evsel__sample_size(first),
-					       sample_id_all, &pevent->sample, false);
+					       sample_id_all, 0, 0, 0,
+					       &pevent->sample, false);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 83f5884..17688c6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,7 @@
 #include "util.h"
 #include "cpumap.h"
 #include "vdso.h"
+#include "perf_regs.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -87,6 +88,9 @@ void perf_session__update_sample_type(struct perf_session *self)
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
 	self->host_machine.id_hdr_size = self->id_hdr_size;
+	self->sample_regs = perf_evlist__sample_regs(self->evlist);
+	self->sample_regs_user = perf_evlist__sample_regs_user(self->evlist);
+	self->sample_stack = perf_evlist__sample_stack(self->evlist);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -804,6 +808,52 @@ static void branch_stack__printf(struct perf_sample *sample)
 			sample->branch_stack->entries[i].to);
 }
 
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+	int i = 0, rid = 0;
+
+	do {
+		u64 val;
+
+		if (mask & 1) {
+			val = regs[i++];
+			printf(".... %-5s 0x%" PRIx64 "\n",
+			       perf_reg_name(rid), val);
+		}
+
+		rid++;
+		mask >>= 1;
+
+	} while (mask);
+}
+
+static void regs_user__printf(struct perf_sample *sample, u64 mask)
+{
+	struct regs_dump *user_regs = &sample->user_regs;
+
+	if (!user_regs->version ||
+	    (user_regs->version != perf_reg_version()))
+		return;
+
+	printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+
+	regs_dump__printf(mask, user_regs->regs);
+}
+
+static void regs__printf(struct perf_sample *sample,
+			struct perf_session *session)
+{
+	if ((session->sample_regs & PERF_SAMPLE_REGS_USER))
+		regs_user__printf(sample, session->sample_regs_user);
+}
+
+static void stack__printf(struct perf_sample *sample, u64 sample_stack)
+{
+	if ((sample_stack & PERF_SAMPLE_STACK_USER))
+		printf("... ustack: size %" PRIu64 "\n",
+		       sample->user_stack.size);
+}
+
 static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
@@ -854,6 +904,12 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 
 	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
 		branch_stack__printf(sample);
+
+	if (session->sample_type & PERF_SAMPLE_REGS)
+		regs__printf(sample, session);
+
+	if (session->sample_type & PERF_SAMPLE_STACK)
+		stack__printf(sample, session->sample_stack);
 }
 
 static struct machine *
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7a5434c..c32c3ec 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -42,6 +42,9 @@ struct perf_session {
 	struct hists		hists;
 	u64			sample_type;
 	int			sample_size;
+	u64			sample_regs;
+	u64			sample_regs_user;
+	u64			sample_stack;
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
@@ -132,9 +135,14 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 					     const union perf_event *event,
 					     struct perf_sample *sample)
 {
-	return perf_event__parse_sample(event, session->sample_type,
+	return perf_event__parse_sample(event,
+					session->sample_type,
 					session->sample_size,
-					session->sample_id_all, sample,
+					session->sample_id_all,
+					session->sample_regs,
+					session->sample_regs_user,
+					session->sample_stack,
+					sample,
 					session->header.needs_swap);
 }
 
-- 
1.7.7.6

[PATCH 13/16] perf, tool: Support for dwarf cfi unwinding on post processing

[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);

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.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                        |   24 +-
 tools/perf/builtin-script.c                        |   56 ++-
 tools/perf/builtin-top.c                           |    5 +-
 tools/perf/util/include/linux/compiler.h           |    1 +
 tools/perf/util/map.h                              |    7 +-
 .../perf/util/scripting-engines/trace-event-perl.c |    3 +-
 .../util/scripting-engines/trace-event-python.c    |    3 +-
 tools/perf/util/session.c                          |   76 +++-
 tools/perf/util/session.h                          |    3 +-
 tools/perf/util/trace-event-scripting.c            |    3 +-
 tools/perf/util/trace-event.h                      |    5 +-
 tools/perf/util/unwind.c                           |  565 ++++++++++++++++++++
 tools/perf/util/unwind.h                           |   34 ++
 16 files changed, 848 insertions(+), 53 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 acc4421..857a5f0 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -326,6 +326,7 @@ LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
 LIB_H += util/vdso.h
 LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -512,6 +513,7 @@ 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..aed7f5a
--- /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_X86_64_REG_RAX;
+		break;
+	case UNW_X86_64_RDX:
+		id = PERF_X86_64_REG_RDX;
+		break;
+	case UNW_X86_64_RCX:
+		id = PERF_X86_64_REG_RCX;
+		break;
+	case UNW_X86_64_RBX:
+		id = PERF_X86_64_REG_RBX;
+		break;
+	case UNW_X86_64_RSI:
+		id = PERF_X86_64_REG_RSI;
+		break;
+	case UNW_X86_64_RDI:
+		id = PERF_X86_64_REG_RDI;
+		break;
+	case UNW_X86_64_RBP:
+		id = PERF_X86_64_REG_RBP;
+		break;
+	case UNW_X86_64_RSP:
+		id = PERF_X86_64_REG_RSP;
+		break;
+	case UNW_X86_64_R8:
+		id = PERF_X86_64_REG_R8;
+		break;
+	case UNW_X86_64_R9:
+		id = PERF_X86_64_REG_R9;
+		break;
+	case UNW_X86_64_R10:
+		id = PERF_X86_64_REG_R10;
+		break;
+	case UNW_X86_64_R11:
+		id = PERF_X86_64_REG_R11;
+		break;
+	case UNW_X86_64_R12:
+		id = PERF_X86_64_REG_R12;
+		break;
+	case UNW_X86_64_R13:
+		id = PERF_X86_64_REG_R13;
+		break;
+	case UNW_X86_64_R14:
+		id = PERF_X86_64_REG_R14;
+		break;
+	case UNW_X86_64_R15:
+		id = PERF_X86_64_REG_R15;
+		break;
+	case UNW_X86_64_RIP:
+		id = PERF_X86_64_REG_RIP;
+		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_X86_32_REG_EAX;
+		break;
+	case UNW_X86_EDX:
+		id = PERF_X86_32_REG_EDX;
+		break;
+	case UNW_X86_ECX:
+		id = PERF_X86_32_REG_ECX;
+		break;
+	case UNW_X86_EBX:
+		id = PERF_X86_32_REG_EBX;
+		break;
+	case UNW_X86_ESI:
+		id = PERF_X86_32_REG_ESI;
+		break;
+	case UNW_X86_EDI:
+		id = PERF_X86_32_REG_EDI;
+		break;
+	case UNW_X86_EBP:
+		id = PERF_X86_32_REG_EBP;
+		break;
+	case UNW_X86_ESP:
+		id = PERF_X86_32_REG_ESP;
+		break;
+	case UNW_X86_EIP:
+		id = PERF_X86_32_REG_EIP;
+		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 d58e414..16de63b 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, evsel, al->thread,
-						 sample->callchain, &parent);
+		err = machine__resolve_callchain(rep->session, machine, evsel,
+						 al->thread, sample, &parent);
 		if (err)
 			return err;
 	}
@@ -130,7 +130,8 @@ out:
 	return err;
 }
 
-static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
+static int perf_evsel__add_hist_entry(struct perf_session *session,
+				      struct perf_evsel *evsel,
 				      struct addr_location *al,
 				      struct perf_sample *sample,
 				      struct machine *machine)
@@ -140,8 +141,8 @@ 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, evsel, al->thread,
-						 sample->callchain, &parent);
+		err = machine__resolve_callchain(session, machine, evsel,
+						 al->thread, sample, &parent);
 		if (err)
 			return err;
 	}
@@ -213,7 +214,8 @@ static int process_sample_event(struct perf_tool *tool,
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
 
-		if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+		if (perf_evsel__add_hist_entry(rep->session, evsel, &al,
+					       sample, machine)) {
 			pr_debug("problem incrementing symbol period, skipping event\n");
 			return -1;
 		}
@@ -396,17 +398,17 @@ 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 8e395a5..5760cee 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -28,6 +28,11 @@ static bool			system_wide;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
+struct perf_script {
+	struct perf_tool tool;
+	struct perf_session *session;
+};
+
 enum perf_output_field {
 	PERF_OUTPUT_COMM            = 1U << 0,
 	PERF_OUTPUT_TID             = 1U << 1,
@@ -373,7 +378,8 @@ static void print_sample_addr(union perf_event *event,
 	}
 }
 
-static void print_sample_bts(union perf_event *event,
+static void print_sample_bts(struct perf_session *session,
+			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct machine *machine,
@@ -387,7 +393,7 @@ static void print_sample_bts(union perf_event *event,
 			printf(" ");
 		else
 			printf("\n");
-		perf_event__print_ip(event, sample, machine, evsel,
+		perf_event__print_ip(session, event, sample, machine, evsel,
 				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
 				     PRINT_FIELD(SYMOFFSET));
 	}
@@ -401,7 +407,8 @@ static void print_sample_bts(union perf_event *event,
 	printf("\n");
 }
 
-static void process_event(union perf_event *event __unused,
+static void process_event(struct perf_session *session,
+			  union perf_event *event __unused,
 			  struct perf_sample *sample,
 			  struct perf_evsel *evsel,
 			  struct machine *machine,
@@ -415,7 +422,8 @@ static void process_event(union perf_event *event __unused,
 	print_sample_start(sample, thread, attr);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(event, sample, evsel, machine, thread);
+		print_sample_bts(session, event, sample, evsel,
+				 machine, thread);
 		return;
 	}
 
@@ -431,7 +439,7 @@ static void process_event(union perf_event *event __unused,
 			printf(" ");
 		else
 			printf("\n");
-		perf_event__print_ip(event, sample, machine, evsel,
+		perf_event__print_ip(session, event, sample, machine, evsel,
 				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
 				     PRINT_FIELD(SYMOFFSET));
 	}
@@ -488,6 +496,8 @@ static int process_sample_event(struct perf_tool *tool __used,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	struct perf_script *script = container_of(tool, struct perf_script,
+						  tool);
 	struct addr_location al;
 	struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
 
@@ -520,24 +530,27 @@ static int process_sample_event(struct perf_tool *tool __used,
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
 		return 0;
 
-	scripting_ops->process_event(event, sample, evsel, machine, thread);
+	scripting_ops->process_event(script->session, event, sample, evsel,
+				     machine, thread);
 
 	evsel->hists.stats.total_period += sample->period;
 	return 0;
 }
 
-static struct perf_tool perf_script = {
-	.sample		 = process_sample_event,
-	.mmap		 = perf_event__process_mmap,
-	.comm		 = perf_event__process_comm,
-	.exit		 = perf_event__process_task,
-	.fork		 = perf_event__process_task,
-	.attr		 = perf_event__process_attr,
-	.event_type	 = perf_event__process_event_type,
-	.tracing_data	 = perf_event__process_tracing_data,
-	.build_id	 = perf_event__process_build_id,
-	.ordered_samples = true,
-	.ordering_requires_timestamps = true,
+static struct perf_script perf_script = {
+	.tool = {
+		.sample		 = process_sample_event,
+		.mmap		 = perf_event__process_mmap,
+		.comm		 = perf_event__process_comm,
+		.exit		 = perf_event__process_task,
+		.fork		 = perf_event__process_task,
+		.attr		 = perf_event__process_attr,
+		.event_type	 = perf_event__process_event_type,
+		.tracing_data	 = perf_event__process_tracing_data,
+		.build_id	 = perf_event__process_build_id,
+		.ordered_samples = true,
+		.ordering_requires_timestamps = true,
+	},
 };
 
 extern volatile int session_done;
@@ -553,7 +566,7 @@ static int __cmd_script(struct perf_session *session)
 
 	signal(SIGINT, sig_handler);
 
-	ret = perf_session__process_events(session, &perf_script);
+	ret = perf_session__process_events(session, &perf_script.tool);
 
 	if (debug_mode)
 		pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
@@ -1335,10 +1348,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 	if (!script_name)
 		setup_pager();
 
-	session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_script);
+	session = perf_session__new(input_name, O_RDONLY, 0, false,
+				    &perf_script.tool);
 	if (session == NULL)
 		return -ENOMEM;
 
+	perf_script.session = session;
+
 	if (cpu_list) {
 		if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
 			return -1;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 165928e..2aa6141 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -774,8 +774,9 @@ 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, evsel, al.thread,
-							 sample->callchain, &parent);
+			err = machine__resolve_callchain(top->session,
+						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 81371ba..a27a0a1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -156,9 +156,12 @@ 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);
 
-int machine__resolve_callchain(struct machine *machine,
+struct perf_session;
+struct perf_sample;
+int machine__resolve_callchain(struct perf_session *session,
+			       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/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 4c1b3d7..40d7a4a 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -368,7 +368,8 @@ static void perl_process_event_generic(union perf_event *pevent __unused,
 	LEAVE;
 }
 
-static void perl_process_event(union perf_event *pevent,
+static void perl_process_event(struct perf_session *session __used,
+			       union perf_event *pevent,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct machine *machine,
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index acb9795..c6cc453 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -209,7 +209,8 @@ static inline struct event_format *find_cache_event(int type)
 	return event;
 }
 
-static void python_process_event(union perf_event *pevent __unused,
+static void python_process_event(struct perf_session *session,
+				 union perf_event *pevent __unused,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel __unused,
 				 struct machine *machine __unused,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 17688c6..f3410c0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,6 +16,7 @@
 #include "cpumap.h"
 #include "vdso.h"
 #include "perf_regs.h"
+#include "unwind.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -294,17 +295,17 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 	return bi;
 }
 
-int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct ip_callchain *chain,
-			       struct symbol **parent)
+static int
+resolve_callchain_sample(struct machine *machine,
+			 struct perf_evsel *evsel,
+			 struct thread *thread,
+			 struct ip_callchain *chain,
+			 struct symbol **parent)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	unsigned int i;
 	int err;
 
-	callchain_cursor_reset(&evsel->hists.callchain_cursor);
-
 	for (i = 0; i < chain->nr; i++) {
 		u64 ip;
 		struct addr_location al;
@@ -317,11 +318,14 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 		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:
 				break;
 			}
@@ -329,7 +333,7 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 		}
 
 		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 &&
@@ -348,6 +352,51 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 	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);
+}
+
+static bool perf_session__has_uregs(struct perf_session *self)
+{
+	return (self->sample_type & PERF_SAMPLE_REGS) &&
+	       (self->sample_regs & PERF_SAMPLE_REGS_USER);
+}
+
+static bool perf_session__has_ustack(struct perf_session *self)
+{
+	return (self->sample_type & PERF_SAMPLE_STACK) &&
+	       (self->sample_stack & PERF_SAMPLE_STACK_USER);
+}
+
+int machine__resolve_callchain(struct perf_session *session,
+			       struct machine *self,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent)
+{
+	int ret;
+
+	callchain_cursor_reset(&evsel->hists.callchain_cursor);
+
+	ret = resolve_callchain_sample(self, evsel, thread,
+				       sample->callchain, parent);
+	if (ret)
+		return ret;
+
+	if (!perf_session__has_uregs(session) ||
+	   (!perf_session__has_ustack(session)))
+		return 0;
+
+	return unwind__get_entries(unwind_entry,
+				   &evsel->hists.callchain_cursor,
+				   self, thread,
+				   session->sample_regs_user, sample);
+}
+
 static int process_event_synth_tracing_data_stub(union perf_event *event __used,
 						 struct perf_session *session __used)
 {
@@ -1481,7 +1530,8 @@ 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,
+void perf_event__print_ip(struct perf_session *session,
+			  union perf_event *event, struct perf_sample *sample,
 			  struct machine *machine, struct perf_evsel *evsel,
 			  int print_sym, int print_dso, int print_symoffset)
 {
@@ -1498,8 +1548,8 @@ 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, evsel, al.thread,
-						sample->callchain, NULL) != 0) {
+		if (machine__resolve_callchain(session, 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 c32c3ec..f64de80 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -157,7 +157,8 @@ static inline int perf_session__synthesize_sample(struct perf_session *session,
 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,
+void perf_event__print_ip(struct perf_session *session,
+			  union perf_event *event, struct perf_sample *sample,
 			  struct machine *machine, struct perf_evsel *evsel,
 			  int print_sym, int print_dso, int print_symoffset);
 
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 18ae6c1..496c8d2 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -35,7 +35,8 @@ static int stop_script_unsupported(void)
 	return 0;
 }
 
-static void process_event_unsupported(union perf_event *event __unused,
+static void process_event_unsupported(struct perf_session *session __used,
+				      union perf_event *event __unused,
 				      struct perf_sample *sample __unused,
 				      struct perf_evsel *evsel __unused,
 				      struct machine *machine __unused,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 639852a..e38fe82 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -72,11 +72,14 @@ 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);
 	int (*stop_script) (void);
-	void (*process_event) (union perf_event *event,
+	void (*process_event) (struct perf_session *session,
+			       union perf_event *event,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct machine *machine,
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
new file mode 100644
index 0000000..fd54b7c
--- /dev/null
+++ b/tools/perf/util/unwind.c
@@ -0,0 +1,565 @@
+/*
+ * 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;
+
+	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.version) {
+		*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 %p %lx\n",
+		 (void *)addr, (unsigned long)*valp);
+	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.version) {
+		*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.version)
+		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 */
-- 
1.7.7.6

[PATCH 14/16] perf, tool: Support for dwarf mode callchain on perf record

[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 ommited 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: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-record.c |   86 ++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/perf.h           |    9 ++++-
 tools/perf/util/evsel.c     |   13 ++++++-
 3 files changed, 104 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e5cb084..8479bf0 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 +741,78 @@ error:
 	return ret;
 }
 
+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[20];
+	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. */
+	snprintf(buf, 20, "%s", 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) {
+				char *endptr;
+				unsigned long size;
+
+				size = strtoul(tok, &endptr, 0);
+				if (*endptr) {
+					pr_err("callchain: Incorrect stack "
+					       "dump size: %s\n", tok);
+					ret = -1;
+				}
+
+				rec->opts.stack_dump_size = size;
+			}
+
+			pr_debug("callchain: stack dump size %lu\n",
+				 rec->opts.stack_dump_size);
+#endif
+		} else {
+			pr_err("callchain: Unknown -g option "
+			       "value: %s\n", name);
+			break;
+		}
+
+	} while (0);
+
+	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 +884,9 @@ 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 14f1034..2cd9c15 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 {
 	int	     branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
+	unsigned long stack_dump_size;
 };
 
 #endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8d21d2c..520d4b2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -16,6 +16,7 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.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))
@@ -106,9 +107,19 @@ 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|PERF_SAMPLE_STACK;
+			attr->sample_regs = PERF_SAMPLE_REGS_USER;
+			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_stack = PERF_SAMPLE_STACK_USER;
+			attr->sample_stack_user = opts->stack_dump_size;
+			attr->exclude_user_callchain = 1;
+		}
+	}
+
 	if (perf_target__has_cpu(&opts->target))
 		attr->sample_type	|= PERF_SAMPLE_CPU;
 
-- 
1.7.7.6

[PATCH 15/16] perf, tool: Add dso data caching

[Jiri Olsa]

Adding dso data caching so we dont need to open/read/close,
each time we want dso data.

The DSO data caching affects following functions:
  dso__data_read_offset
  dso__data_read_addr

Each DSO read tries to find the data (based on offset) inside
the cache. If it's not present it fills the cache from file,
and returns the data. If it is present, data are returned
with no file read.

Each data read is cached by reading cache page sized/alligned
amount of DSO data. The cache page size is hardcoded to 4096.
The cache is using RB tree with file offset as a sort key.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/symbol.c |  154 ++++++++++++++++++++++++++++++++++++++++------
 tools/perf/util/symbol.h |   11 +++
 2 files changed, 147 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6955c3c..292ccee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,6 +29,7 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
+static void dso_cache__free(struct rb_root *root);
 static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
@@ -342,6 +343,7 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+		dso->cache = RB_ROOT;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
@@ -376,6 +378,7 @@ void dso__delete(struct dso *dso)
 		free((char *)dso->short_name);
 	if (dso->lname_alloc)
 		free(dso->long_name);
+	dso_cache__free(&dso->cache);
 	free(dso);
 }
 
@@ -2900,22 +2903,87 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	return -EINVAL;
 }
 
-static ssize_t dso_cache_read(struct dso *dso __used, u64 offset __used,
-			      u8 *data __used, ssize_t size __used)
+static void
+dso_cache__free(struct rb_root *root)
 {
-	return -EINVAL;
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct dso_cache *cache;
+
+		cache = rb_entry(next, struct dso_cache, rb_node);
+		next = rb_next(&cache->rb_node);
+		rb_erase(&cache->rb_node, root);
+		free(cache);
+	}
 }
 
-static int dso_cache_add(struct dso *dso __used, u64 offset __used,
-			 u8 *data __used, ssize_t size __used)
+static struct dso_cache*
+dso_cache__find(struct rb_root *root, u64 offset)
 {
-	return 0;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+		else
+			return cache;
+	}
+	return NULL;
+}
+
+static void
+dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+	u64 offset = new->offset;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+}
+
+static ssize_t
+dso_cache__memcpy(struct dso_cache *cache, u64 offset,
+		  u8 *data, u64 size)
+{
+	u64 cache_offset = offset - cache->offset;
+	u64 cache_size   = min(cache->size - cache_offset, size);
+
+	memcpy(data, cache->data + cache_offset, cache_size);
+	return cache_size;
 }
 
-static ssize_t read_dso_data(struct dso *dso, struct machine *machine,
-		     u64 offset, u8 *data, ssize_t size)
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+		 u64 offset, u8 *data, ssize_t size)
 {
-	ssize_t rsize = -1;
+	struct dso_cache *cache;
+	ssize_t ret;
 	int fd;
 
 	fd = dso__data_fd(dso, machine);
@@ -2923,28 +2991,78 @@ static ssize_t read_dso_data(struct dso *dso, struct machine *machine,
 		return -1;
 
 	do {
-		if (-1 == lseek(fd, offset, SEEK_SET))
+		u64 cache_offset;
+
+		ret = -ENOMEM;
+
+		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+		if (!cache)
 			break;
 
-		rsize = read(fd, data, size);
-		if (-1 == rsize)
+		cache_offset = offset & DSO__DATA_CACHE_MASK;
+		ret = -EINVAL;
+
+		if (-1 == lseek(fd, cache_offset, SEEK_SET))
 			break;
 
-		if (dso_cache_add(dso, offset, data, size))
-			pr_err("Failed to add data int dso cache.");
+		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		if (ret <= 0)
+			break;
+
+		cache->offset = cache_offset;
+		cache->size   = ret;
+		dso_cache__insert(&dso->cache, cache);
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
 
 	} while (0);
 
+	if (ret <= 0)
+		free(cache);
+
 	close(fd);
-	return rsize;
+	return ret;
+}
+
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+
+	cache = dso_cache__find(&dso->cache, offset);
+	if (cache)
+		return dso_cache__memcpy(cache, offset, data, size);
+	else
+		return dso_cache__read(dso, machine, offset, data, size);
 }
 
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size)
 {
-	if (dso_cache_read(dso, offset, data, size))
-		return read_dso_data(dso, machine, offset, data, size);
-	return 0;
+	ssize_t r = 0;
+	u8 *p = data;
+
+	do {
+		ssize_t ret;
+
+		ret = dso_cache_read(dso, machine, offset, p, size);
+		if (ret < 0)
+			return ret;
+
+		/* Reached EOF, return what we have. */
+		if (!ret)
+			break;
+
+		BUG_ON(ret > size);
+
+		r      += ret;
+		p      += ret;
+		offset += ret;
+		size   -= ret;
+
+	} while (size);
+
+	return r;
 }
 
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 32da5e6..4a117b9 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -174,10 +174,21 @@ enum dso_kernel_type {
 	DSO_TYPE_GUEST_KERNEL
 };
 
+#define DSO__DATA_CACHE_SIZE 4096
+#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
+
+struct dso_cache {
+	struct rb_node	rb_node;
+	u64 offset;
+	u64 size;
+	char data[0];
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 cache;
 	enum dso_kernel_type	kernel;
 	enum dso_binary_type	symtab_type;
 	enum dso_binary_type	data_type;
-- 
1.7.7.6

[PATCH 16/16] perf, tool: Add dso data caching tests

[Jiri Olsa]

Adding automated test for DSO data reading. Testing raw/cached
reads from different file/cache locations.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/Makefile        |    1 +
 tools/perf/builtin-test.c  |    4 +
 tools/perf/util/dso-test.c |  154 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/symbol.h   |    1 +
 4 files changed, 160 insertions(+), 0 deletions(-)
 create mode 100644 tools/perf/util/dso-test.c

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 857a5f0..26c5dc8 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -362,6 +362,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
 LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/dso-test.o
 LIB_OBJS += $(OUTPUT)util/color.o
 LIB_OBJS += $(OUTPUT)util/pager.o
 LIB_OBJS += $(OUTPUT)util/header.o
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 082d279..68fd431 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -1143,6 +1143,10 @@ static struct test {
 		.func = test__perf_pmu,
 	},
 	{
+		.desc = "Test dso data interface",
+		.func = dso__test_data,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/util/dso-test.c b/tools/perf/util/dso-test.c
new file mode 100644
index 0000000..ec62977
--- /dev/null
+++ b/tools/perf/util/dso-test.c
@@ -0,0 +1,154 @@
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "symbol.h"
+
+#define TEST_ASSERT_VAL(text, cond) \
+do { \
+	if (!(cond)) { \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1; \
+	} \
+} while (0)
+
+static char *test_file(int size)
+{
+	static char buf_templ[] = "/tmp/test-XXXXXX";
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC);
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data__offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data__offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+#define OFFSETS_CNT (sizeof(offsets) / sizeof(struct test_data__offset))
+
+int dso__test_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	int i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < (int) OFFSETS_CNT; i++) {
+		struct test_data__offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 4a117b9..0c3d78c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -294,4 +294,5 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size);
+int dso__test_data(void);
 #endif /* __PERF_SYMBOL */
-- 
1.7.7.6

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> +enum perf_event_x86_32_regs {
> +       PERF_X86_32_REG_EAX,
> +       PERF_X86_32_REG_EBX,
> +       PERF_X86_32_REG_ECX,
> +       PERF_X86_32_REG_EDX,
> +       PERF_X86_32_REG_ESI,
> +       PERF_X86_32_REG_EDI,
> +       PERF_X86_32_REG_EBP,
> +       PERF_X86_32_REG_ESP,
> +       PERF_X86_32_REG_EIP,
> +       PERF_X86_32_REG_FLAGS,
> +       PERF_X86_32_REG_CS,
> +       PERF_X86_32_REG_DS,
> +       PERF_X86_32_REG_ES,
> +       PERF_X86_32_REG_FS,
> +       PERF_X86_32_REG_GS,
> +
> +       /* Non ABI */
> +       PERF_X86_32_REG_MAX,
> +};

> +enum perf_event_x86_64_regs {
> +       PERF_X86_64_REG_RAX,
> +       PERF_X86_64_REG_RBX,
> +       PERF_X86_64_REG_RCX,
> +       PERF_X86_64_REG_RDX,
> +       PERF_X86_64_REG_RSI,
> +       PERF_X86_64_REG_RDI,
> +       PERF_X86_64_REG_R8,
> +       PERF_X86_64_REG_R9,
> +       PERF_X86_64_REG_R10,
> +       PERF_X86_64_REG_R11,
> +       PERF_X86_64_REG_R12,
> +       PERF_X86_64_REG_R13,
> +       PERF_X86_64_REG_R14,
> +       PERF_X86_64_REG_R15,
> +       PERF_X86_64_REG_RBP,
> +       PERF_X86_64_REG_RSP,
> +       PERF_X86_64_REG_RIP,
> +       PERF_X86_64_REG_FLAGS,
> +       PERF_X86_64_REG_CS,
> +       PERF_X86_64_REG_SS,
> +
> +       /* Non ABI */
> +       PERF_X86_64_REG_MAX,
> +}; 

So why bother with two different APIs? Why not have only the x86_64 one
and maybe add a warning/error/fail whatever when x86_64 regs are
selected on i386/compat tasks.

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> +static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
> +{
> +       switch (idx) {
> +       case PERF_X86_32_REG_EAX:
> +               return regs->ax;
> +       case PERF_X86_32_REG_EBX:
> +               return regs->bx;
> +       case PERF_X86_32_REG_ECX:
> +               return regs->cx;
> +       case PERF_X86_32_REG_EDX:
> +               return regs->dx;
> +       case PERF_X86_32_REG_ESI:
> +               return regs->si;
> +       case PERF_X86_32_REG_EDI:
> +               return regs->di;
> +       case PERF_X86_32_REG_EBP:
> +               return regs->bp;
> +       case PERF_X86_32_REG_ESP:
> +               return regs->sp;
> +       case PERF_X86_32_REG_EIP:
> +               return regs->ip;
> +       case PERF_X86_32_REG_FLAGS:
> +               return regs->flags;
> +       case PERF_X86_32_REG_CS:
> +               return regs->cs;
> +       case PERF_X86_32_REG_DS:
> +               return regs->ds;
> +       case PERF_X86_32_REG_ES:
> +               return regs->es;
> +       case PERF_X86_32_REG_FS:
> +               return regs->fs;
> +       case PERF_X86_32_REG_GS:
> +               return regs->gs;
> +       }
> +
> +       return 0;
> +} 

This is just sad... is there really no saner way to write this? I
suppose you're going to iterate your sample_regs bitmap and call this
function for every bit. GCC isn't known to generate particularly sane
code for switches :/

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
>  /*
> + * Values for sample_regs when PERF_SAMPLE_REGS is set.
> + * Defines register set to be attached to the sample.
> + */
> +enum perf_sample_regs {
> +       PERF_SAMPLE_REGS_USER   = 1U << 0, /* user registers */
> +       PERF_SAMPLE_REGS_MAX    = 1U << 1, /* non-ABI */
> +};



> +       __u64   sample_regs; /* enum perf_sample_regs */
> +
> +       /*
> +        * Arch specific mask for PERF_SAMPLE_REGS_USER setup.
> +        * Defines set of user regs to dump on samples.
> +        * See asm/perf_regs.h for details.
> +        */
> +       __u64   sample_regs_user; 

This all just smells.. :/

So you're wasting 64 bits to specify PERF_SAMPLE_REGS_USER while also
implying we'll need another u64 for every other value of
perf_sample_regs?

What are we doing here and why?

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> +perf_output_sample_regs(struct perf_output_handle *handle,
> +                       struct pt_regs *regs, u64 mask)
> +{
> +       int i = 0;
> +
> +       do {
> +               u64 val;
> +
> +               if (mask & 1) {
> +                       val = perf_reg_value(regs, i);
> +                       perf_output_put(handle, val);
> +               }
> +
> +               mask >>= 1;
> +               i++;
> +       } while (mask);
> +} 

we have bitmap functions available that can do this far faster on a
number of architectures (like x86) that have bit scanning instructions.

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:

> --- 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			= 1U << 12,
>  
> -	PERF_SAMPLE_MAX = 1U << 12,		/* non-ABI */
> +	PERF_SAMPLE_MAX = 1U << 13,		/* non-ABI */
>  };

There's a comment update missing for PERF_RECORD_SAMPLE that describes
the output this bit generates.

> @@ -4011,6 +4042,30 @@ void perf_output_sample(struct perf_output_handle *handle,
>  			perf_output_put(handle, nr);
>  		}
>  	}
> +
> +	if (sample_type & PERF_SAMPLE_REGS) {
> +		u64 mode = event->attr.sample_regs;
> +
> +		if (mode & PERF_SAMPLE_REGS_USER) {
> +			u64 id = PERF_REGS_ABI_NONE;
> +
> +			/*
> +			 * If there are no regs to dump, notice it through
> +			 * PERF_REGS_ABI_NONE id.
> +			 */
> +			if (data->regs_user)
> +				id = perf_reg_version();

OK, so I don't like this.. why does this exists at all? Why not use a
length field instead?

> +			perf_output_put(handle, id);
> +
> +			if (id) {
> +				u64 mask = event->attr.sample_regs_user;
> +				perf_output_sample_regs(handle,
> +							data->regs_user,
> +							mask);
> +			}
> +		}
> +	}
>  }

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Stephane Eranian]

On Thu, May 24, 2012 at 11:50 AM, Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:
> On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
>>  /*
>> + * Values for sample_regs when PERF_SAMPLE_REGS is set.
>> + * Defines register set to be attached to the sample.
>> + */
>> +enum perf_sample_regs {
>> +       PERF_SAMPLE_REGS_USER   = 1U << 0, /* user registers */
>> +       PERF_SAMPLE_REGS_MAX    = 1U << 1, /* non-ABI */
>> +};
>
>
>
>> +       __u64   sample_regs; /* enum perf_sample_regs */
>> +
>> +       /*
>> +        * Arch specific mask for PERF_SAMPLE_REGS_USER setup.
>> +        * Defines set of user regs to dump on samples.
>> +        * See asm/perf_regs.h for details.
>> +        */
>> +       __u64   sample_regs_user;
>
> This all just smells.. :/
>
> So you're wasting 64 bits to specify PERF_SAMPLE_REGS_USER while also
> implying we'll need another u64 for every other value of
> perf_sample_regs?
>
> What are we doing here and why?
>
I think this is related to a discusion we had earlier about which
machine state you want
to sample.

There are 3 possible machine states:
  1- user level (even when sample is in kernel AND assuming you did
not hit a kernel only thread)
  2- interrupted state (@ PMU interrupt)
  3- precise state (state captured by PEBS on Intel, for instance)

Jiri is only interested in 1/. I am interested in the other two as well.

Question: is there a situation where we could need more than one machine
state per sample?

If not, then a single bitmask is enough.

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Peter Zijlstra]

On Thu, 2012-05-24 at 12:06 +0200, Stephane Eranian wrote:

> > What are we doing here and why?
> >
> I think this is related to a discusion we had earlier about which
> machine state you want
> to sample.
> 
> There are 3 possible machine states:
>   1- user level (even when sample is in kernel AND assuming you did
> not hit a kernel only thread)
>   2- interrupted state (@ PMU interrupt)
>   3- precise state (state captured by PEBS on Intel, for instance)
> 
> Jiri is only interested in 1/. I am interested in the other two as well.
> 
> Question: is there a situation where we could need more than one machine
> state per sample?

Well, IIRC you always wanted both 2 and 3 at the same time to compute
skid, thus:

> If not, then a single bitmask is enough.

Indeed, so then we get to multiple bitmasks and unless you want to be
restricted to the same bitmap for all these types this setup won't
actually work.

Also, all that was missing from the changelog.

Re: [PATCH 04/16] perf: Add ability to attach user stack dump to sample

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> @@ -173,6 +174,15 @@ enum perf_sample_regs {
>  };
>  
>  /*
> + * Values for sample_stack when PERF_SAMPLE_STACK is set.
> + * Defines stack dump to be attached to the sample.
> + */
> +enum perf_sample_stack {
> +       PERF_SAMPLE_STACK_USER  = 1U << 0, /* user stack */
> +       PERF_SAMPLE_STACK_MAX   = 1U << 1, /* non-ABI */
> +};
> +
> +/*
>   * The format of the data returned by read() on a perf event fd,
>   * as specified by attr.read_format:
>   *
> @@ -291,6 +301,14 @@ struct perf_event_attr {
>          * See asm/perf_regs.h for details.
>          */
>         __u64   sample_regs_user;
> +
> +       __u64   sample_stack; /* enum perf_sample_stack */
> +
> +       /*
> +        * Defines size of the user stack to dump on samples,
> +        * for sample_stack PERF_SAMPLE_STACK_USER settings.
> +        */
> +       __u64   sample_stack_user;
>  }; 

And here we have a similarly weird set-up. If you're ever going to add
another type, you have to make another __u64 since clearly another type
cannot use sample_stack_user per the name.

Thus, if you get another size variable you might as well use that to
discover the state that is now sample_stack.

Re: [PATCH 04/16] perf: Add ability to attach user stack dump to sample

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> +static void
> +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
> +                         struct pt_regs *regs)
> +{
> +       u64 size;
> +
> +       /* Case of a kernel thread, nothing to dump */
> +       if (!regs) {
> +               size = 0;
> +               perf_output_put(handle, size);
> +       } else {
> +               unsigned long sp;
> +               unsigned int rem;
> +               u64 dyn_size;
> +
> +               /*
> +                * Static size: we always dump the size
> +                * requested by the user because most of the
> +                * time, the top of the user stack is not
> +                * paged out.
> +                */
> +               size = round_up(dump_size, sizeof(u64));

You also do this in the prepare thing..

> +               perf_output_put(handle, size);
> +
> +               sp = user_stack_pointer(regs);
> +               rem = __output_copy_user(handle, (void *)sp, size);
> +               dyn_size = size - rem;
> +
> +               /* What couldn't be dumped is zero padded */
> +               while (rem--) {
> +                       char zero = 0;
> +                       perf_output_put(handle, zero);
> +               }

Does this matter? If we don't write it the worst that can happen is that
we leave previous ring-bugger content around, but since we already are
privileged to read that (and very likely already have) there's no
problem with that..

I know not zero-ing is ugly, but its also faster.. and do we care about
them silly zeros?

> +
> +               /* Dynamic size: whole dump - padding */
> +               perf_output_put(handle, dyn_size);
> +       }
> +}
> +
>  static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
>  {
>         if (!user_mode(regs)) {
> @@ -4066,6 +4105,17 @@ void perf_output_sample(struct perf_output_handle *handle,
>                         }
>                 }
>         }
> +
> +       if (sample_type & PERF_SAMPLE_STACK) {
> +               u64 mode = event->attr.sample_stack;
> +
> +               if (mode & PERF_SAMPLE_STACK_USER) {
> +                       u64 dump_size = event->attr.sample_stack_user;
> +
> +                       perf_output_sample_ustack(handle, dump_size,
> +                                                 data->regs_user);

OK, so that function is called _ustack() I read that as userstack, so
why this strange split up?

> +               }
> +       }
>  }
>  
>  void perf_prepare_sample(struct perf_event_header *header,
> @@ -4135,6 +4185,39 @@ void perf_prepare_sample(struct perf_event_header *header,
>  
>                 header->size += size;
>         }
> +
> +       if (sample_type & PERF_SAMPLE_STACK) {
> +               u64 mode = event->attr.sample_stack;
> +               int size = 0;
> +
> +               if (mode & PERF_SAMPLE_STACK_USER) {

This is very much similar to ->sample_stack_user, since a non-zero size
usually means you want something.

> +                       if (!data->regs_user)
> +                               data->regs_user = perf_sample_regs_user(regs);
> +
> +                       /*
> +                        * A first field that tells the _static_ size of the
> +                        * dump. 0 if there is nothing to dump (ie: we are in
> +                        * a kernel thread) otherwise the requested size.
> +                        */
> +                       size += sizeof(u64);
> +
> +                       /*
> +                        * 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. What couldn't be dumped will be zero-padded.
> +                        */
> +                       if (data->regs_user) {
> +                               u64 user_size = event->attr.sample_stack_user;
> +
> +                               user_size = round_up(user_size, sizeof(u64));

Right, and here we go again.. so how about you either reject sizes that
aren't properly aligned in perf_copy_attr() or just fix it up there.

> +                               size += user_size;
> +                               size += sizeof(u64);
> +                       }
> +               }
> +
> +               header->size += size;
> +       }
>  } 

Re: [PATCH 05/16] perf: Add attribute to filter out user callchains

[Peter Zijlstra]

On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> Add the new exclude_user_callchain attribute to filter out
> frame pointer based user callchains.
> 
> This is something we want to select when we use the dwarf cfi
> callchain mode, because frame pointer based user callchains are
> useless in this mode.
> 
> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> Signed-off-by: Jiri Olsa <jolsa@redhat.com>
> ---
>  include/linux/perf_event.h |    4 +++-
>  kernel/events/callchain.c  |    4 ++--
>  kernel/events/core.c       |    3 ++-
>  kernel/events/internal.h   |    3 ++-
>  4 files changed, 9 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index dcdc97e..df6ba37 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -275,7 +275,9 @@ struct perf_event_attr {
>  				exclude_host   :  1, /* don't count in host   */
>  				exclude_guest  :  1, /* don't count in guest  */
>  
> -				__reserved_1   : 43;
> +				exclude_user_callchain : 1, /* only record kernel callchains */

*sigh* I guess if we're going to do this we might as well do a complete
option set and also allow excluding kernel and possible hv if anybody
actually implemented that.

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Jiri Olsa]

On Thu, May 24, 2012 at 12:42:22PM +0200, Peter Zijlstra wrote:
> On Thu, 2012-05-24 at 12:06 +0200, Stephane Eranian wrote:
> 
> > > What are we doing here and why?
> > >
> > I think this is related to a discusion we had earlier about which
> > machine state you want
> > to sample.
> > 
> > There are 3 possible machine states:
> >   1- user level (even when sample is in kernel AND assuming you did
> > not hit a kernel only thread)
> >   2- interrupted state (@ PMU interrupt)
> >   3- precise state (state captured by PEBS on Intel, for instance)
> > 
> > Jiri is only interested in 1/. I am interested in the other two as well.
> > 
> > Question: is there a situation where we could need more than one machine
> > state per sample?
> 
> Well, IIRC you always wanted both 2 and 3 at the same time to compute
> skid, thus:
> 
> > If not, then a single bitmask is enough.
> 
> Indeed, so then we get to multiple bitmasks and unless you want to be
> restricted to the same bitmap for all these types this setup won't
> actually work.

My intention was to make this general. I could just add
bitmask for each type (user regs mask for now) but I wanted
to be consistent with other SAMPLE_* stuff..

So current patch adds PERF_SAMPLE_REGS sample_type bit.
Once it is set, the 'sample_regs' value is checked for what
type of registers you want for sample.

Each type then has separate bitmask in case you want different
registers for each type. Allowing whatever combination of regs dump
being added to the sample, since it seems there's no firm
decision on what combination might be needed.

Sure we can make the same with bitmasks for each regs type,
and check the presence in sample by bitmask being not empty.

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Stephane Eranian]

2012/5/24 Peter Zijlstra <a.p.zijlstra@chello.nl>:
> On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
>> +enum perf_event_x86_32_regs {
>> +       PERF_X86_32_REG_EAX,
>> +       PERF_X86_32_REG_EBX,
>> +       PERF_X86_32_REG_ECX,
>> +       PERF_X86_32_REG_EDX,
>> +       PERF_X86_32_REG_ESI,
>> +       PERF_X86_32_REG_EDI,
>> +       PERF_X86_32_REG_EBP,
>> +       PERF_X86_32_REG_ESP,
>> +       PERF_X86_32_REG_EIP,
>> +       PERF_X86_32_REG_FLAGS,
>> +       PERF_X86_32_REG_CS,
>> +       PERF_X86_32_REG_DS,
>> +       PERF_X86_32_REG_ES,
>> +       PERF_X86_32_REG_FS,
>> +       PERF_X86_32_REG_GS,
>> +
>> +       /* Non ABI */
>> +       PERF_X86_32_REG_MAX,
>> +};
>
>> +enum perf_event_x86_64_regs {
>> +       PERF_X86_64_REG_RAX,
>> +       PERF_X86_64_REG_RBX,
>> +       PERF_X86_64_REG_RCX,
>> +       PERF_X86_64_REG_RDX,
>> +       PERF_X86_64_REG_RSI,
>> +       PERF_X86_64_REG_RDI,
>> +       PERF_X86_64_REG_R8,
>> +       PERF_X86_64_REG_R9,
>> +       PERF_X86_64_REG_R10,
>> +       PERF_X86_64_REG_R11,
>> +       PERF_X86_64_REG_R12,
>> +       PERF_X86_64_REG_R13,
>> +       PERF_X86_64_REG_R14,
>> +       PERF_X86_64_REG_R15,
>> +       PERF_X86_64_REG_RBP,
>> +       PERF_X86_64_REG_RSP,
>> +       PERF_X86_64_REG_RIP,
>> +       PERF_X86_64_REG_FLAGS,
>> +       PERF_X86_64_REG_CS,
>> +       PERF_X86_64_REG_SS,
>> +
>> +       /* Non ABI */
>> +       PERF_X86_64_REG_MAX,
>> +};
>
> So why bother with two different APIs? Why not have only the x86_64 one
> and maybe add a warning/error/fail whatever when x86_64 regs are
> selected on i386/compat tasks.
>
>
I agree with Peter here especially after our earlier discussion about how
to handle 32-bit ABI threads on a 64-bit ABI kernel. You should simply
fill in the record with zeroes when the register does not exists. You cannot
predict what will be sampled in system-wide mode.

The only sanity check you can do is on 32-bit ABI kernel, reject any 64-bit
ABI only regs but then that would require invoking arch specific code from
perf_copy_attr()....

Re: [PATCH 04/16] perf: Add ability to attach user stack dump to sample

[Jiri Olsa]

On Thu, May 24, 2012 at 12:51:20PM +0200, Peter Zijlstra wrote:
> On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> > +static void

SNIP

> > +               /* What couldn't be dumped is zero padded */
> > +               while (rem--) {
> > +                       char zero = 0;
> > +                       perf_output_put(handle, zero);
> > +               }
> 
> Does this matter? If we don't write it the worst that can happen is that
> we leave previous ring-bugger content around, but since we already are
> privileged to read that (and very likely already have) there's no
> problem with that..
> 
> I know not zero-ing is ugly, but its also faster.. and do we care about
> them silly zeros?
hm, I dont think we care.. seems like this can go out


> > +       if (sample_type & PERF_SAMPLE_STACK) {
> > +               u64 mode = event->attr.sample_stack;
> > +
> > +               if (mode & PERF_SAMPLE_STACK_USER) {
> > +                       u64 dump_size = event->attr.sample_stack_user;
> > +
> > +                       perf_output_sample_ustack(handle, dump_size,
> > +                                                 data->regs_user);
> 
> OK, so that function is called _ustack() I read that as userstack, so
> why this strange split up?
ook


> 
> > +               }
> > +       }
> >  }
> >  
> >  void perf_prepare_sample(struct perf_event_header *header,
> > @@ -4135,6 +4185,39 @@ void perf_prepare_sample(struct perf_event_header *header,
> >  
> >                 header->size += size;
> >         }
> > +
> > +       if (sample_type & PERF_SAMPLE_STACK) {
> > +               u64 mode = event->attr.sample_stack;
> > +               int size = 0;
> > +
> > +               if (mode & PERF_SAMPLE_STACK_USER) {
> 
> This is very much similar to ->sample_stack_user, since a non-zero size
> usually means you want something.

ok, same case as for the regs bitmask stuf then..
we can use the size to check the presence in sample

> 
> > +                       if (!data->regs_user)
> > +                               data->regs_user = perf_sample_regs_user(regs);
> > +
> > +                       /*
> > +                        * A first field that tells the _static_ size of the
> > +                        * dump. 0 if there is nothing to dump (ie: we are in
> > +                        * a kernel thread) otherwise the requested size.
> > +                        */
> > +                       size += sizeof(u64);
> > +
> > +                       /*
> > +                        * 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. What couldn't be dumped will be zero-padded.
> > +                        */
> > +                       if (data->regs_user) {
> > +                               u64 user_size = event->attr.sample_stack_user;
> > +
> > +                               user_size = round_up(user_size, sizeof(u64));
> 
> Right, and here we go again.. so how about you either reject sizes that
> aren't properly aligned in perf_copy_attr() or just fix it up there.

right, we can do that in the attr check

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Jiri Olsa]

On Thu, May 24, 2012 at 02:13:19PM +0200, Stephane Eranian wrote:
> 2012/5/24 Peter Zijlstra <a.p.zijlstra@chello.nl>:
> > On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> >> +enum perf_event_x86_32_regs {
> >> +       PERF_X86_32_REG_EAX,
> >> +       PERF_X86_32_REG_EBX,
> >> +       PERF_X86_32_REG_ECX,
> >> +       PERF_X86_32_REG_EDX,
> >> +       PERF_X86_32_REG_ESI,
> >> +       PERF_X86_32_REG_EDI,
> >> +       PERF_X86_32_REG_EBP,
> >> +       PERF_X86_32_REG_ESP,
> >> +       PERF_X86_32_REG_EIP,
> >> +       PERF_X86_32_REG_FLAGS,
> >> +       PERF_X86_32_REG_CS,
> >> +       PERF_X86_32_REG_DS,
> >> +       PERF_X86_32_REG_ES,
> >> +       PERF_X86_32_REG_FS,
> >> +       PERF_X86_32_REG_GS,
> >> +
> >> +       /* Non ABI */
> >> +       PERF_X86_32_REG_MAX,
> >> +};
> >
> >> +enum perf_event_x86_64_regs {
> >> +       PERF_X86_64_REG_RAX,
> >> +       PERF_X86_64_REG_RBX,
> >> +       PERF_X86_64_REG_RCX,
> >> +       PERF_X86_64_REG_RDX,
> >> +       PERF_X86_64_REG_RSI,
> >> +       PERF_X86_64_REG_RDI,
> >> +       PERF_X86_64_REG_R8,
> >> +       PERF_X86_64_REG_R9,
> >> +       PERF_X86_64_REG_R10,
> >> +       PERF_X86_64_REG_R11,
> >> +       PERF_X86_64_REG_R12,
> >> +       PERF_X86_64_REG_R13,
> >> +       PERF_X86_64_REG_R14,
> >> +       PERF_X86_64_REG_R15,
> >> +       PERF_X86_64_REG_RBP,
> >> +       PERF_X86_64_REG_RSP,
> >> +       PERF_X86_64_REG_RIP,
> >> +       PERF_X86_64_REG_FLAGS,
> >> +       PERF_X86_64_REG_CS,
> >> +       PERF_X86_64_REG_SS,
> >> +
> >> +       /* Non ABI */
> >> +       PERF_X86_64_REG_MAX,
> >> +};
> >
> > So why bother with two different APIs? Why not have only the x86_64 one
> > and maybe add a warning/error/fail whatever when x86_64 regs are
> > selected on i386/compat tasks.
> >
> >
> I agree with Peter here especially after our earlier discussion about how
> to handle 32-bit ABI threads on a 64-bit ABI kernel. You should simply
> fill in the record with zeroes when the register does not exists. You cannot
> predict what will be sampled in system-wide mode.
> 
> The only sanity check you can do is on 32-bit ABI kernel, reject any 64-bit
> ABI only regs but then that would require invoking arch specific code from
> perf_copy_attr()....

ok, looks like this could work.. and fix the confusion for compat tasks

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Peter Zijlstra]

On Thu, 2012-05-24 at 13:52 +0200, Jiri Olsa wrote:
> 
> My intention was to make this general. I could just add
> bitmask for each type (user regs mask for now) but I wanted
> to be consistent with other SAMPLE_* stuff..
> 
> So current patch adds PERF_SAMPLE_REGS sample_type bit.
> Once it is set, the 'sample_regs' value is checked for what
> type of registers you want for sample.
> 
> Each type then has separate bitmask in case you want different
> registers for each type. Allowing whatever combination of regs dump
> being added to the sample, since it seems there's no firm
> decision on what combination might be needed.
> 
> Sure we can make the same with bitmasks for each regs type,
> and check the presence in sample by bitmask being not empty. 

Right, I don't know. But none of this was in the changelog.

Also, I just checked, there's architectures with more than 64 GP
registers ;-) (IA64 has 128 64bit integer registers for instance).

Now IA64 is the only one I could find, and we don't actually support
perf for it, and seeing how 'popular' IA64 is we might never, but still.

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Frederic Weisbecker]

On Thu, May 24, 2012 at 11:43:56AM +0200, Peter Zijlstra wrote:
> On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> > +static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
> > +{
> > +       switch (idx) {
> > +       case PERF_X86_32_REG_EAX:
> > +               return regs->ax;
> > +       case PERF_X86_32_REG_EBX:
> > +               return regs->bx;
> > +       case PERF_X86_32_REG_ECX:
> > +               return regs->cx;
> > +       case PERF_X86_32_REG_EDX:
> > +               return regs->dx;
> > +       case PERF_X86_32_REG_ESI:
> > +               return regs->si;
> > +       case PERF_X86_32_REG_EDI:
> > +               return regs->di;
> > +       case PERF_X86_32_REG_EBP:
> > +               return regs->bp;
> > +       case PERF_X86_32_REG_ESP:
> > +               return regs->sp;
> > +       case PERF_X86_32_REG_EIP:
> > +               return regs->ip;
> > +       case PERF_X86_32_REG_FLAGS:
> > +               return regs->flags;
> > +       case PERF_X86_32_REG_CS:
> > +               return regs->cs;
> > +       case PERF_X86_32_REG_DS:
> > +               return regs->ds;
> > +       case PERF_X86_32_REG_ES:
> > +               return regs->es;
> > +       case PERF_X86_32_REG_FS:
> > +               return regs->fs;
> > +       case PERF_X86_32_REG_GS:
> > +               return regs->gs;
> > +       }
> > +
> > +       return 0;
> > +} 
> 
> This is just sad... is there really no saner way to write this? I
> suppose you're going to iterate your sample_regs bitmap and call this
> function for every bit. GCC isn't known to generate particularly sane
> code for switches :/
> 

Do you think that compat regs are always a subset of native regs in all
archs as in x86? Sounds logic but I'm asking just in case. If so then yeah
this should work.

Re: [PATCH 02/16] perf: Add ability to attach registers dump to sample

[Frederic Weisbecker]

On Thu, May 24, 2012 at 01:52:06PM +0200, Jiri Olsa wrote:
> On Thu, May 24, 2012 at 12:42:22PM +0200, Peter Zijlstra wrote:
> > On Thu, 2012-05-24 at 12:06 +0200, Stephane Eranian wrote:
> > 
> > > > What are we doing here and why?
> > > >
> > > I think this is related to a discusion we had earlier about which
> > > machine state you want
> > > to sample.
> > > 
> > > There are 3 possible machine states:
> > >   1- user level (even when sample is in kernel AND assuming you did
> > > not hit a kernel only thread)
> > >   2- interrupted state (@ PMU interrupt)
> > >   3- precise state (state captured by PEBS on Intel, for instance)
> > > 
> > > Jiri is only interested in 1/. I am interested in the other two as well.
> > > 
> > > Question: is there a situation where we could need more than one machine
> > > state per sample?
> > 
> > Well, IIRC you always wanted both 2 and 3 at the same time to compute
> > skid, thus:
> > 
> > > If not, then a single bitmask is enough.
> > 
> > Indeed, so then we get to multiple bitmasks and unless you want to be
> > restricted to the same bitmap for all these types this setup won't
> > actually work.
> 
> My intention was to make this general. I could just add
> bitmask for each type (user regs mask for now) but I wanted
> to be consistent with other SAMPLE_* stuff..
> 
> So current patch adds PERF_SAMPLE_REGS sample_type bit.
> Once it is set, the 'sample_regs' value is checked for what
> type of registers you want for sample.
> 
> Each type then has separate bitmask in case you want different
> registers for each type. Allowing whatever combination of regs dump
> being added to the sample, since it seems there's no firm
> decision on what combination might be needed.
> 
> Sure we can make the same with bitmasks for each regs type,
> and check the presence in sample by bitmask being not empty.

I believe we should allow the record of user regs and precise/irq
as well in the same time. Unless we get some real proof that both
will never be used at the same time. I really don't want us to be
limited in the future for ABI reasons.

Re: [PATCH 04/16] perf: Add ability to attach user stack dump to sample

[Frederic Weisbecker]

On Thu, May 24, 2012 at 12:51:20PM +0200, Peter Zijlstra wrote:
> On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> > +static void
> > +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
> > +                         struct pt_regs *regs)
> > +{
> > +       u64 size;
> > +
> > +       /* Case of a kernel thread, nothing to dump */
> > +       if (!regs) {
> > +               size = 0;
> > +               perf_output_put(handle, size);
> > +       } else {
> > +               unsigned long sp;
> > +               unsigned int rem;
> > +               u64 dyn_size;
> > +
> > +               /*
> > +                * Static size: we always dump the size
> > +                * requested by the user because most of the
> > +                * time, the top of the user stack is not
> > +                * paged out.
> > +                */
> > +               size = round_up(dump_size, sizeof(u64));
> 
> You also do this in the prepare thing..
> 
> > +               perf_output_put(handle, size);
> > +
> > +               sp = user_stack_pointer(regs);
> > +               rem = __output_copy_user(handle, (void *)sp, size);
> > +               dyn_size = size - rem;
> > +
> > +               /* What couldn't be dumped is zero padded */
> > +               while (rem--) {
> > +                       char zero = 0;
> > +                       perf_output_put(handle, zero);
> > +               }
> 
> Does this matter? If we don't write it the worst that can happen is that
> we leave previous ring-bugger content around, but since we already are
> privileged to read that (and very likely already have) there's no
> problem with that..
> 
> I know not zero-ing is ugly, but its also faster.. and do we care about
> them silly zeros?

The problem there is that the unwinder may then deal with random values
from previous records in the buffer and think it is some real stack values.
This may give strange results. At least zeroing was limiting this effect.

I think the best would be to do like you say: if we can't dump everything
then just leave the state of the buffer as is. But also output in the end
the effective size of the stack that has been dumped. So that we know what
we can give to the unwinder and what we can not.

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Peter Zijlstra]

On Thu, 2012-06-07 at 11:46 +0200, Frederic Weisbecker wrote:
> 
> Do you think that compat regs are always a subset of native regs in all
> archs as in x86? Sounds logic but I'm asking just in case. If so then yeah
> this should work. 

I can't answer this authoritatively but it would seem strange if this
were not the case. But even if it were so, you could always frob both
sets in a single space such that the shared registers overlap etc. 

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Frederic Weisbecker]

On Thu, Jun 07, 2012 at 12:29:23PM +0200, Peter Zijlstra wrote:
> On Thu, 2012-06-07 at 11:46 +0200, Frederic Weisbecker wrote:
> > 
> > Do you think that compat regs are always a subset of native regs in all
> > archs as in x86? Sounds logic but I'm asking just in case. If so then yeah
> > this should work. 
> 
> I can't answer this authoritatively but it would seem strange if this
> were not the case. But even if it were so, you could always frob both
> sets in a single space such that the shared registers overlap etc. 

Looks good. Let's take that direction then.

Re: [PATCH 01/16] perf: Unified API to record selective sets of arch registers

[Stephane Eranian]

On Thu, Jun 7, 2012 at 12:29 PM, Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:
> On Thu, 2012-06-07 at 11:46 +0200, Frederic Weisbecker wrote:
>>
>> Do you think that compat regs are always a subset of native regs in all
>> archs as in x86? Sounds logic but I'm asking just in case. If so then yeah
>> this should work.
>
> I can't answer this authoritatively but it would seem strange if this
> were not the case. But even if it were so, you could always frob both
> sets in a single space such that the shared registers overlap etc.

Agreed.

Re: [PATCH 04/16] perf: Add ability to attach user stack dump to sample

[Jiri Olsa]

On Thu, Jun 07, 2012 at 12:07:56PM +0200, Frederic Weisbecker wrote:
> On Thu, May 24, 2012 at 12:51:20PM +0200, Peter Zijlstra wrote:
> > On Wed, 2012-05-23 at 21:32 +0200, Jiri Olsa wrote:
> > > +static void
> > > +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
> > > +                         struct pt_regs *regs)
> > > +{
> > > +       u64 size;
> > > +
> > > +       /* Case of a kernel thread, nothing to dump */
> > > +       if (!regs) {
> > > +               size = 0;
> > > +               perf_output_put(handle, size);
> > > +       } else {
> > > +               unsigned long sp;
> > > +               unsigned int rem;
> > > +               u64 dyn_size;
> > > +
> > > +               /*
> > > +                * Static size: we always dump the size
> > > +                * requested by the user because most of the
> > > +                * time, the top of the user stack is not
> > > +                * paged out.
> > > +                */
> > > +               size = round_up(dump_size, sizeof(u64));
> > 
> > You also do this in the prepare thing..
> > 
> > > +               perf_output_put(handle, size);
> > > +
> > > +               sp = user_stack_pointer(regs);
> > > +               rem = __output_copy_user(handle, (void *)sp, size);
> > > +               dyn_size = size - rem;
> > > +
> > > +               /* What couldn't be dumped is zero padded */
> > > +               while (rem--) {
> > > +                       char zero = 0;
> > > +                       perf_output_put(handle, zero);
> > > +               }
> > 
> > Does this matter? If we don't write it the worst that can happen is that
> > we leave previous ring-bugger content around, but since we already are
> > privileged to read that (and very likely already have) there's no
> > problem with that..
> > 
> > I know not zero-ing is ugly, but its also faster.. and do we care about
> > them silly zeros?
> 
> The problem there is that the unwinder may then deal with random values
> from previous records in the buffer and think it is some real stack values.
> This may give strange results. At least zeroing was limiting this effect.
> 
> I think the best would be to do like you say: if we can't dump everything
> then just leave the state of the buffer as is. But also output in the end
> the effective size of the stack that has been dumped. So that we know what
> we can give to the unwinder and what we can not.

yep, thats the case right now.. just putting away the zeros

jirka

[PATCH 16/16] perf, tool: Add dso data caching tests

[Jiri Olsa]

Adding automated test for DSO data reading. Testing raw/cached
reads from different file/cache locations.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/Makefile        |    1 +
 tools/perf/builtin-test.c  |    4 +
 tools/perf/util/dso-test.c |  154 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/symbol.h   |    1 +
 4 files changed, 160 insertions(+), 0 deletions(-)
 create mode 100644 tools/perf/util/dso-test.c

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3614b1a..dc56c8e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -342,6 +342,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
 LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/dso-test.o
 LIB_OBJS += $(OUTPUT)util/color.o
 LIB_OBJS += $(OUTPUT)util/pager.o
 LIB_OBJS += $(OUTPUT)util/header.o
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index a434aaa..83ff5ba 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -1662,6 +1662,10 @@ static struct test {
 		.func = test__perf_pmu,
 	},
 	{
+		.desc = "Test dso data interface",
+		.func = dso__test_data,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/util/dso-test.c b/tools/perf/util/dso-test.c
new file mode 100644
index 0000000..ec62977
--- /dev/null
+++ b/tools/perf/util/dso-test.c
@@ -0,0 +1,154 @@
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "symbol.h"
+
+#define TEST_ASSERT_VAL(text, cond) \
+do { \
+	if (!(cond)) { \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1; \
+	} \
+} while (0)
+
+static char *test_file(int size)
+{
+	static char buf_templ[] = "/tmp/test-XXXXXX";
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC);
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data__offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data__offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+#define OFFSETS_CNT (sizeof(offsets) / sizeof(struct test_data__offset))
+
+int dso__test_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	int i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < (int) OFFSETS_CNT; i++) {
+		struct test_data__offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index e5744c0..897b35e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -288,4 +288,5 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size);
+int dso__test_data(void);
 #endif /* __PERF_SYMBOL */
-- 
1.7.7.6