[GIT PULL 0/4] perf/core improvements and fixes

[GIT PULL 0/4] perf/core improvements and fixes

[Arnaldo Carvalho de Melo]

Hi Ingo,

	Please consider pulling,

- Arnaldo

The following changes since commit 43e41adc9e8c36545888d78fed2ef8d102a938dc:

  perf record: Add ability to sample call branches (2015-10-20 10:30:55 +0200)

are available in the git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo

for you to fetch changes up to bab84928dfadf8cba4d3fadcea0890de4da37be8:

  perf evsel: Print branch filter state with -vv (2015-10-20 15:54:21 -0300)

----------------------------------------------------------------
perf/core improvements and fixes:

User visible:

- Print branch filter state with verbose mode (Andi Kleen)

- Fix core dump caused by per-socket/core system-wide stat (Kan Liang)

- Update libtraceevent KVM plugin (Paolo Bonzini)

Developer stuff:

- Add fixdep to 'tools/build' .gitignore (Yunlong Song)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

----------------------------------------------------------------
Andi Kleen (1):
      perf evsel: Print branch filter state with -vv

Kan Liang (1):
      perf cpu_map: Fix core dump caused by per-socket/core system-wide stat

Paolo Bonzini (1):
      tools lib traceevent: update KVM plugin

Yunlong Song (1):
      perf build: Add fixdep to .gitignore

 tools/build/.gitignore            |  1 +
 tools/lib/traceevent/plugin_kvm.c | 25 +++++++++++++++++--------
 tools/perf/util/cpumap.c          |  2 +-
 tools/perf/util/evsel.c           |  1 +
 4 files changed, 20 insertions(+), 9 deletions(-)
 create mode 100644 tools/build/.gitignore

[PATCH 1/4] perf build: Add fixdep to .gitignore

[Arnaldo Carvalho de Melo]

From: Yunlong Song <yunlong.song@huawei.com>

Commit 7c422f5572667fef0db38d2046ecce69dcf0afc8 ("tools build: Build
fixdep helper from perf and basic libs") dynamically creates fixdep
during the perf building. Add it to .gitignore.

Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 7c422f557266 ("tools build: Build fixdep helper from perf and basic libs")
Link: http://lkml.kernel.org/r/1444899116-8220-1-git-send-email-yunlong.song@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/.gitignore | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 tools/build/.gitignore

diff --git a/tools/build/.gitignore b/tools/build/.gitignore
new file mode 100644
index 000000000000..a776371a3502
--- /dev/null
+++ b/tools/build/.gitignore
@@ -0,0 +1 @@
+fixdep
-- 
2.1.0

[PATCH 2/4] tools lib traceevent: update KVM plugin

[Arnaldo Carvalho de Melo]

From: Paolo Bonzini <pbonzini@redhat.com>

The format of the role word has changed through the years and the plugin
was never updated; some VMX exit reasons were missing too.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: kvm@vger.kernel.org
Link: http://lkml.kernel.org/r/1443695293-31127-1-git-send-email-pbonzini@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/plugin_kvm.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 88fe83dff7cd..18536f756577 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -124,7 +124,10 @@ static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
 	_ER(WBINVD,		 54)		\
 	_ER(XSETBV,		 55)		\
 	_ER(APIC_WRITE,		 56)		\
-	_ER(INVPCID,		 58)
+	_ER(INVPCID,		 58)		\
+	_ER(PML_FULL,		 62)		\
+	_ER(XSAVES,		 63)		\
+	_ER(XRSTORS,		 64)
 
 #define SVM_EXIT_REASONS \
 	_ER(EXIT_READ_CR0,	0x000)		\
@@ -352,15 +355,18 @@ static int kvm_nested_vmexit_handler(struct trace_seq *s, struct pevent_record *
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
-		unsigned glevels:4;
 		unsigned level:4;
+		unsigned cr4_pae:1;
 		unsigned quadrant:2;
-		unsigned pad_for_nice_hex_output:6;
 		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
-		unsigned cr4_pge:1;
 		unsigned nxe:1;
+		unsigned cr0_wp:1;
+		unsigned smep_and_not_wp:1;
+		unsigned smap_and_not_wp:1;
+		unsigned pad_for_nice_hex_output:8;
+		unsigned smm:8;
 	};
 };
 
@@ -385,15 +391,18 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct pevent_record *record,
 	if (pevent_is_file_bigendian(event->pevent) ==
 	    pevent_is_host_bigendian(event->pevent)) {
 
-		trace_seq_printf(s, "%u/%u q%u%s %s%s %spge %snxe",
+		trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
 				 role.level,
-				 role.glevels,
 				 role.quadrant,
 				 role.direct ? " direct" : "",
 				 access_str[role.access],
 				 role.invalid ? " invalid" : "",
-				 role.cr4_pge ? "" : "!",
-				 role.nxe ? "" : "!");
+				 role.cr4_pae ? "" : "!",
+				 role.nxe ? "" : "!",
+				 role.cr0_wp ? "" : "!",
+				 role.smep_and_not_wp ? " smep" : "",
+				 role.smap_and_not_wp ? " smap" : "",
+				 role.smm ? " smm" : "");
 	} else
 		trace_seq_printf(s, "WORD: %08x", role.word);
 
-- 
2.1.0

[PATCH 3/4] perf cpu_map: Fix core dump caused by per-socket/core system-wide stat

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@intel.com>

Perf will core dump if --per-socket/core -a are applied for perf stat.

The root cause is that cpu_map__build_map set refcnt of evlist's cpu_map
to 1.  It should set refcnt for the newly created cpu_map, not evlist's
cpu_map.

Here is the example:

  # perf stat -e cycles --per-socket -a sleep 1

   Performance counter stats for 'system wide':

  S0       36         30,196,257      cycles
  S1       28         15,823,536      cycles

       1.001126828 seconds time elapsed

  *** Error in `./perf': corrupted double-linked list: 0x00000000021f9090 ***
  ======= Backtrace: =========
  /lib64/libc.so.6[0x3002e7bbe7]
  /lib64/libc.so.6[0x3002e7d2b5]
  ./perf(perf_evsel__delete+0x28)[0x485bdd]
  ./perf[0x4800e8]
  ./perf(perf_evlist__delete+0x5e)[0x482cd5]
  ./perf(cmd_stat+0xf25)[0x432328]
  ./perf[0x4768e0]
  ./perf[0x476ad6]
  ./perf[0x476b41]
  ./perf(main+0x1d0)[0x476db2]
  /lib64/libc.so.6(__libc_start_main+0xf5)[0x3002e21b45]
  ./perf[0x4202c5]

Signed-off-by: Kan Liang <kan.liang@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/1444388363-35936-1-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cpumap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index b36845347f01..aa6b490aa471 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -285,7 +285,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
-	atomic_set(&cpus->refcnt, 1);
+	atomic_set(&c->refcnt, 1);
 	*res = c;
 	return 0;
 }
-- 
2.1.0

[PATCH 4/4] perf evsel: Print branch filter state with -vv

[Arnaldo Carvalho de Melo]

From: Andi Kleen <ak@linux.intel.com>

Add a missing field to the perf_event_attr debug output.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1445366797-30894-4-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8be867ccefe9..11bf3f2c51cd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1229,6 +1229,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(config, p_hex);
 	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
 	PRINT_ATTRf(sample_type, p_sample_type);
+	PRINT_ATTRf(branch_sample_type, p_unsigned);
 	PRINT_ATTRf(read_format, p_read_format);
 
 	PRINT_ATTRf(disabled, p_unsigned);
-- 
2.1.0

Re: [GIT PULL 0/4] perf/core improvements and fixes

[Ingo Molnar]

* Arnaldo Carvalho de Melo <acme@kernel.org> wrote:

> Hi Ingo,
> 
> 	Please consider pulling,
> 
> - Arnaldo
> 
> The following changes since commit 43e41adc9e8c36545888d78fed2ef8d102a938dc:
> 
>   perf record: Add ability to sample call branches (2015-10-20 10:30:55 +0200)
> 
> are available in the git repository at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo
> 
> for you to fetch changes up to bab84928dfadf8cba4d3fadcea0890de4da37be8:
> 
>   perf evsel: Print branch filter state with -vv (2015-10-20 15:54:21 -0300)
> 
> ----------------------------------------------------------------
> perf/core improvements and fixes:
> 
> User visible:
> 
> - Print branch filter state with verbose mode (Andi Kleen)
> 
> - Fix core dump caused by per-socket/core system-wide stat (Kan Liang)
> 
> - Update libtraceevent KVM plugin (Paolo Bonzini)
> 
> Developer stuff:
> 
> - Add fixdep to 'tools/build' .gitignore (Yunlong Song)
> 
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> 
> ----------------------------------------------------------------
> Andi Kleen (1):
>       perf evsel: Print branch filter state with -vv
> 
> Kan Liang (1):
>       perf cpu_map: Fix core dump caused by per-socket/core system-wide stat
> 
> Paolo Bonzini (1):
>       tools lib traceevent: update KVM plugin
> 
> Yunlong Song (1):
>       perf build: Add fixdep to .gitignore
> 
>  tools/build/.gitignore            |  1 +
>  tools/lib/traceevent/plugin_kvm.c | 25 +++++++++++++++++--------
>  tools/perf/util/cpumap.c          |  2 +-
>  tools/perf/util/evsel.c           |  1 +
>  4 files changed, 20 insertions(+), 9 deletions(-)
>  create mode 100644 tools/build/.gitignore

Pulled, thanks a lot Arnaldo!

	Ingo

Re: [PATCH 4/4] perf evsel: Print branch filter state with -vv

[Peter Zijlstra]

On Tue, Oct 20, 2015 at 05:25:07PM -0300, Arnaldo Carvalho de Melo wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Add a missing field to the perf_event_attr debug output.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Link: http://lkml.kernel.org/r/1445366797-30894-4-git-send-email-andi@firstfloor.org
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> ---
>  tools/perf/util/evsel.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 8be867ccefe9..11bf3f2c51cd 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1229,6 +1229,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
>  	PRINT_ATTRf(config, p_hex);
>  	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
>  	PRINT_ATTRf(sample_type, p_sample_type);
> +	PRINT_ATTRf(branch_sample_type, p_unsigned);
>  	PRINT_ATTRf(read_format, p_read_format);

As said in the original thread, this is the wrong place, it should be
between config2 and sample_regs_user.

Re: [PATCH 4/4] perf evsel: Print branch filter state with -vv

[Ingo Molnar]

* Peter Zijlstra <peterz@infradead.org> wrote:

> On Tue, Oct 20, 2015 at 05:25:07PM -0300, Arnaldo Carvalho de Melo wrote:
> > From: Andi Kleen <ak@linux.intel.com>
> > 
> > Add a missing field to the perf_event_attr debug output.
> > 
> > Signed-off-by: Andi Kleen <ak@linux.intel.com>
> > Cc: Jiri Olsa <jolsa@kernel.org>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Link: http://lkml.kernel.org/r/1445366797-30894-4-git-send-email-andi@firstfloor.org
> > Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> > ---
> >  tools/perf/util/evsel.c | 1 +
> >  1 file changed, 1 insertion(+)
> > 
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 8be867ccefe9..11bf3f2c51cd 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -1229,6 +1229,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
> >  	PRINT_ATTRf(config, p_hex);
> >  	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
> >  	PRINT_ATTRf(sample_type, p_sample_type);
> > +	PRINT_ATTRf(branch_sample_type, p_unsigned);
> >  	PRINT_ATTRf(read_format, p_read_format);
> 
> As said in the original thread, this is the wrong place, it should be
> between config2 and sample_regs_user.

Ok, I've unpulled these updates, since I haven't pushed these bits out yet.

Thanks,

	Ingo

Re: [PATCH 4/4] perf evsel: Print branch filter state with -vv

[Arnaldo Carvalho de Melo]

Em Wed, Oct 21, 2015 at 11:25:25AM +0200, Ingo Molnar escreveu:
> * Peter Zijlstra <peterz@infradead.org> wrote:
> > On Tue, Oct 20, 2015 at 05:25:07PM -0300, Arnaldo Carvalho de Melo wrote:
> > > From: Andi Kleen <ak@linux.intel.com>

> > > Add a missing field to the perf_event_attr debug output.

> > > +++ b/tools/perf/util/evsel.c
> > > @@ -1229,6 +1229,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
> > >  	PRINT_ATTRf(config, p_hex);
> > >  	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
> > >  	PRINT_ATTRf(sample_type, p_sample_type);
> > > +	PRINT_ATTRf(branch_sample_type, p_unsigned);
> > >  	PRINT_ATTRf(read_format, p_read_format);

> > As said in the original thread, this is the wrong place, it should be
> > between config2 and sample_regs_user.
 
> Ok, I've unpulled these updates, since I haven't pushed these bits out yet.

I'll fix this as pointed out by Peter and resubmit.

- Arnaldo

Re: [PATCH 4/4] perf evsel: Print branch filter state with -vv

[Arnaldo Carvalho de Melo]

Em Wed, Oct 21, 2015 at 10:32:15AM +0200, Peter Zijlstra escreveu:
> On Tue, Oct 20, 2015 at 05:25:07PM -0300, Arnaldo Carvalho de Melo wrote:
> > From: Andi Kleen <ak@linux.intel.com>
> > 
> > Add a missing field to the perf_event_attr debug output.
> > 
> > Signed-off-by: Andi Kleen <ak@linux.intel.com>
> > Cc: Jiri Olsa <jolsa@kernel.org>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Link: http://lkml.kernel.org/r/1445366797-30894-4-git-send-email-andi@firstfloor.org
> > Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> > ---
> >  tools/perf/util/evsel.c | 1 +
> >  1 file changed, 1 insertion(+)
> > 
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 8be867ccefe9..11bf3f2c51cd 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -1229,6 +1229,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
> >  	PRINT_ATTRf(config, p_hex);
> >  	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
> >  	PRINT_ATTRf(sample_type, p_sample_type);
> > +	PRINT_ATTRf(branch_sample_type, p_unsigned);
> >  	PRINT_ATTRf(read_format, p_read_format);
> 
> As said in the original thread, this is the wrong place, it should be
> between config2 and sample_regs_user.

Like below, right? Acked?

commit 528946c2fcb5cdd3b75b691b316b5bdeaa7d46d0
Author: Andi Kleen <ak@linux.intel.com>
Date:   Tue Oct 20 11:46:36 2015 -0700

    perf evsel: Print branch filter state with -vv
    
    Add a missing field to the perf_event_attr debug output.
    
    Signed-off-by: Andi Kleen <ak@linux.intel.com>
    Cc: Jiri Olsa <jolsa@kernel.org>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Link: http://lkml.kernel.org/r/1445366797-30894-4-git-send-email-andi@firstfloor.org
    [ Print it between config2 and sample_regs_user (peterz)]
    Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8be867ccefe9..ab05fa52a5cd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1262,6 +1262,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(bp_type, p_unsigned);
 	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
 	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
+	PRINT_ATTRf(branch_sample_type, p_unsigned);
 	PRINT_ATTRf(sample_regs_user, p_hex);
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
 	PRINT_ATTRf(clockid, p_signed);

Re: [PATCH 4/4] perf evsel: Print branch filter state with -vv

[Peter Zijlstra]

On Wed, Oct 21, 2015 at 03:07:55PM -0300, Arnaldo Carvalho de Melo wrote:
> commit 528946c2fcb5cdd3b75b691b316b5bdeaa7d46d0
> Author: Andi Kleen <ak@linux.intel.com>
> Date:   Tue Oct 20 11:46:36 2015 -0700
> 
>     perf evsel: Print branch filter state with -vv
>     
>     Add a missing field to the perf_event_attr debug output.
>     
>     Signed-off-by: Andi Kleen <ak@linux.intel.com>
>     Cc: Jiri Olsa <jolsa@kernel.org>
>     Cc: Peter Zijlstra <peterz@infradead.org>
>     Link: http://lkml.kernel.org/r/1445366797-30894-4-git-send-email-andi@firstfloor.org
>     [ Print it between config2 and sample_regs_user (peterz)]
>     Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> 
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 8be867ccefe9..ab05fa52a5cd 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1262,6 +1262,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
>  	PRINT_ATTRf(bp_type, p_unsigned);
>  	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
>  	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
> +	PRINT_ATTRf(branch_sample_type, p_unsigned);
>  	PRINT_ATTRf(sample_regs_user, p_hex);
>  	PRINT_ATTRf(sample_stack_user, p_unsigned);
>  	PRINT_ATTRf(clockid, p_signed);

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>