From e3b03b6c1a4f3b4564be08809f58584592621a0a Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 5 May 2016 16:04:03 -0700
Subject: perf stat: Avoid fractional digits for integer scales

When the scaling factor is a full integer don't display fractional
digits. This avoids unnecessary .00 output for topdown metrics with
scale factors.

v2: Remove redundant check.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1462489447-31832-7-git-send-email-andi@firstfloor.org
[ Rename 'round' to 'stat_round' as 'round' is defined in math.h,
  included by this patch, and this breaks the build on ubuntu 12.04 ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5645a8361de6..16a923c1633b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -66,6 +66,7 @@
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
+#include <math.h>
 
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"
@@ -986,12 +987,12 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	const char *fmt;
 
 	if (csv_output) {
-		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
 	} else {
 		if (big_num)
-			fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
 		else
-			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
 	}
 
 	aggr_printout(evsel, id, nr);
@@ -1995,7 +1996,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 				    union perf_event *event,
 				    struct perf_session *session)
 {
-	struct stat_round_event *round = &event->stat_round;
+	struct stat_round_event *stat_round = &event->stat_round;
 	struct perf_evsel *counter;
 	struct timespec tsh, *ts = NULL;
 	const char **argv = session->header.env.cmdline_argv;
@@ -2004,12 +2005,12 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	evlist__for_each(evsel_list, counter)
 		perf_stat_process_counter(&stat_config, counter);
 
-	if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
-		update_stats(&walltime_nsecs_stats, round->time);
+	if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
+		update_stats(&walltime_nsecs_stats, stat_round->time);
 
-	if (stat_config.interval && round->time) {
-		tsh.tv_sec  = round->time / NSECS_PER_SEC;
-		tsh.tv_nsec = round->time % NSECS_PER_SEC;
+	if (stat_config.interval && stat_round->time) {
+		tsh.tv_sec  = stat_round->time / NSECS_PER_SEC;
+		tsh.tv_nsec = stat_round->time % NSECS_PER_SEC;
 		ts = &tsh;
 	}
 
-- 
cgit v1.2.3


From 6ae98ba611ed1c11ddc5645475bc03b46a3c04e7 Mon Sep 17 00:00:00 2001
From: He Kuang <hekuang@huawei.com>
Date: Thu, 12 May 2016 08:43:11 +0000
Subject: perf symbols: Store vdso buildid unconditionally

When unwinding callchains on a different machine, vdso info should be
available so the unwind process won't be interrupted if address falls
into vdso region. But in most cases, the addresses of sample events are
not in vdso range, the buildid of a zero hit vdso won't be stored into
perf.data.

This patch stores vdso buildid regardless of whether the vdso is hit or
not.

Signed-off-by: He Kuang <hekuang@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ekaterina Tumanova <tumanova@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1463042596-61703-3-git-send-email-hekuang@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/build-id.c | 2 +-
 tools/perf/util/dso.c      | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff425e1232c..67e5966503b2 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -256,7 +256,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 		size_t name_len;
 		bool in_kernel = false;
 
-		if (!pos->hit)
+		if (!pos->hit && !dso__is_vdso(pos))
 			continue;
 
 		if (dso__is_vdso(pos)) {
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 3357479082ca..75b75615e2f8 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,6 +7,7 @@
 #include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
+#include "vdso.h"
 
 char dso__symtab_origin(const struct dso *dso)
 {
@@ -1169,7 +1170,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	struct dso *pos;
 
 	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
+		if (with_hits && !pos->hit && !dso__is_vdso(pos))
 			continue;
 		if (pos->has_build_id) {
 			have_build_id = true;
-- 
cgit v1.2.3


From b0404be8d6186f9f3c23e2b5ff247e667be90652 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 13 May 2016 15:01:01 +0900
Subject: perf stat: Fix indentation of stalled backend cycle

The commit 140aeadc1fb5 ("perf stat: Abstract stat metrics printing")
changed how shadow metrics are printed, but it missed to update the
width of the stalled backend cycles event to 7.2% like others.  This
resulted in misaligned output like below:

  Performance counter stats for 'pwd':

          0.638313      task-clock (msec)         #    0.567 CPUs utilized
                 0      context-switches          #    0.000 K/sec
                 0      cpu-migrations            #    0.000 K/sec
                54      page-faults               #    0.085 M/sec
           885,600      cycles                    #    1.387 GHz
           558,438      stalled-cycles-frontend   #   63.06% frontend cycles idle
           431,355      stalled-cycles-backend    #  48.71% backend cycles idle
           674,956      instructions              #    0.76  insn per cycle
                                                  #    0.83  stalled cycles per insn
           130,380      branches                  #  204.257 M/sec
     <not counted>      branch-misses

       0.001125426 seconds time elapsed

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 140aeadc1fb5 ("perf stat: Abstract stat metrics printing")
Link: http://lkml.kernel.org/r/1463119263-5569-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/stat-shadow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index fdb71961143e..61200fcac5ef 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -188,7 +188,7 @@ static void print_stalled_cycles_backend(int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
+	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
 static void print_branch_misses(int cpu,
-- 
cgit v1.2.3


From daf4f4786e8af371048e72cb37ac05190e89198a Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 13 May 2016 15:01:02 +0900
Subject: perf stat: Update runtime using cpu-clock event

Currently only the task-clock event updates the runtime_nsec so it
cannot show the metric when using cpu-clock events.  However cpu clock
works basically same as task-clock, so no need to not update the runtime
IMHO.

Before:

  # perf stat -a -e cpu-clock,context-switches,page-faults,cycles sleep 0.1

    Performance counter stats for 'system wide':

         1217.759506      cpu-clock (msec)
                  93      context-switches
                  61      page-faults
          18,958,022      cycles

         0.101393794 seconds time elapsed

After:

   Performance counter stats for 'system wide':

         1220.471884      cpu-clock (msec)          #   12.013 CPUs utilized
                 118      context-switches          #    0.097 K/sec
                  59      page-faults               #    0.048 K/sec
          17,941,247      cycles                    #    0.015 GHz

         0.101594777 seconds time elapsed

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1463119263-5569-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/stat-shadow.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 61200fcac5ef..aa9efe08762b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 {
 	int ctx = evsel_context(counter);
 
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
+	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
 		update_stats(&runtime_nsecs_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
@@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
+		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / ratio);
-- 
cgit v1.2.3


From a1f3d56761df31f0ffeb215b974e26d5613e92a4 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 13 May 2016 15:01:03 +0900
Subject: perf stat: Use cpu-clock event for cpu targets

Currently 'perf stat' always counts task-clock event by default.  But
it's somewhat confusing for system-wide targets (especially with 'sleep
N' as the 'sleep' task just sleeps and doesn't use cputime).  Changing
to cpu-clock event instead for that case makes more sense IMHO.

Before:
  # perf stat -a sleep 0.1

   Performance counter stats for 'system wide':

        403.038603      task-clock (msec)     #    4.001 CPUs utilized
               150      context-switches      #    0.372 K/sec
                 7      cpu-migrations        #    0.017 K/sec
                71      page-faults           #    0.176 K/sec
        23,705,169      cycles                #    0.059 GHz
        15,888,166      instructions          #    0.67  insn per cycle
         3,326,078      branches              #    8.253 M/sec
            87,643      branch-misses         #    2.64% of all branches

       0.100737009 seconds time elapsed

  #

After:

  # perf stat -a sleep 0.1

   Performance counter stats for 'system wide':

        404.271182      cpu-clock (msec)      #    4.000 CPUs utilized
               143      context-switches      #    0.354 K/sec
                13      cpu-migrations        #    0.032 K/sec
                73      page-faults           #    0.181 K/sec
        22,119,220      cycles                #    0.055 GHz
        13,622,065      instructions          #    0.62  insn per cycle
         2,918,769      branches              #    7.220 M/sec
            85,033      branch-misses         #    2.91% of all branches

       0.101073089 seconds time elapsed

  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1463119263-5569-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 16a923c1633b..efdd23221c16 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1905,6 +1905,9 @@ static int add_default_attributes(void)
 	}
 
 	if (!evsel_list->nr_entries) {
+		if (target__has_cpu(&target))
+			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
+
 		if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
 			return -1;
 		if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
-- 
cgit v1.2.3


From 0a77582f0407e7f9b5d775bebc31297a1b890be0 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sun, 15 May 2016 12:19:40 +0900
Subject: perf symbols: Introduce DSO__NAME_KALLSYMS and DSO__NAME_KCORE

Instead of using a raw string, use DSO__NAME_KALLSYMS and
DSO__NAME_KCORE macros for kallsyms and kcore.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20160515031935.4017.50971.stgit@devbox
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-buildid-cache.c |  8 ++++----
 tools/perf/util/annotate.c         |  2 +-
 tools/perf/util/machine.c          |  2 +-
 tools/perf/util/symbol.c           | 10 +++++-----
 tools/perf/util/symbol.h           |  3 +++
 5 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 632efc6b79a0..d75bded21fe0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -119,8 +119,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
 	if (build_id_cache__kcore_buildid(from_dir, sbuildid) < 0)
 		return -1;
 
-	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
-		  buildid_dir, sbuildid);
+	scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s",
+		  buildid_dir, DSO__NAME_KCORE, sbuildid);
 
 	if (!force &&
 	    !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
@@ -131,8 +131,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
 	if (build_id_cache__kcore_dir(dir, sizeof(dir)))
 		return -1;
 
-	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s",
-		  buildid_dir, sbuildid, dir);
+	scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s/%s",
+		  buildid_dir, DSO__NAME_KCORE, sbuildid, dir);
 
 	if (mkdir_p(to_dir, 0755))
 		return -1;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4db73d5a0dbc..b811924e5e1b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1122,7 +1122,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	} else if (dso__is_kcore(dso)) {
 		goto fallback;
 	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
-		   strstr(command, "[kernel.kallsyms]") ||
+		   strstr(command, DSO__NAME_KALLSYMS) ||
 		   access(symfs_filename, R_OK)) {
 		free(filename);
 fallback:
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 639a2903065e..18dd96bdde05 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -709,7 +709,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
 	if (machine__is_host(machine)) {
 		vmlinux_name = symbol_conf.vmlinux_name;
 		if (!vmlinux_name)
-			vmlinux_name = "[kernel.kallsyms]";
+			vmlinux_name = DSO__NAME_KALLSYMS;
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[kernel]", DSO_TYPE_KERNEL);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7fb33304fb4e..2252b545ff43 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1662,8 +1662,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
-	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
-		  sbuild_id);
+	scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
+		  DSO__NAME_KCORE, sbuild_id);
 
 	/* Use /proc/kallsyms if possible */
 	if (is_host) {
@@ -1699,8 +1699,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 	if (!find_matching_kcore(map, path, sizeof(path)))
 		return strdup(path);
 
-	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
-		  buildid_dir, sbuild_id);
+	scnprintf(path, sizeof(path), "%s/%s/%s",
+		  buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
 
 	if (access(path, F_OK)) {
 		pr_err("No kallsyms or vmlinux with build-id %s was found\n",
@@ -1769,7 +1769,7 @@ do_kallsyms:
 
 	if (err > 0 && !dso__is_kcore(dso)) {
 		dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
-		dso__set_long_name(dso, "[kernel.kallsyms]", false);
+		dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2b5e4ed76fcb..25f2fd672c2e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -44,6 +44,9 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
+#define DSO__NAME_KCORE		"[kernel.kcore]"
+
 /** struct symbol - symtab entry
  *
  * @ignore - resolvable but tools ignore it (e.g. idle routines)
-- 
cgit v1.2.3


From a29d5c9b8167dbc21a7ca8c0302e3799f9063b4e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 May 2016 21:16:54 -0300
Subject: perf tools: Separate accounting of contexts and real addresses in a
 stack trace

The perf_sample->ip_callchain->nr value includes all the entries in the
ip_callchain->ip[] array, real addresses and PERF_CONTEXT_{KERNEL,USER,etc},
while what the user expects is that what is in the kernel.perf_event_max_stack
sysctl or in the upcoming per event perf_event_attr.sample_max_stack knob be
honoured in terms of IP addresses in the stack trace.

So match the kernel support and validate chain->nr taking into account
both kernel.perf_event_max_stack and kernel.perf_event_max_contexts_per_stack.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-mgx0jpzfdq4uq4abfa40byu0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf.c         |  3 +++
 tools/perf/util/machine.c | 26 +++++++++++++++++---------
 tools/perf/util/util.c    |  3 ++-
 tools/perf/util/util.h    |  3 ++-
 4 files changed, 24 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 797000842d40..15982cee5ef3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -549,6 +549,9 @@ int main(int argc, const char **argv)
 	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
 		sysctl_perf_event_max_stack = value;
 
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
 	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
 		cmd = "perf-help";
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 18dd96bdde05..7ba9fadb68af 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1811,9 +1811,9 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
 	struct branch_stack *branch = sample->branch_stack;
 	struct ip_callchain *chain = sample->callchain;
-	int chain_nr = min(max_stack, (int)chain->nr);
+	int chain_nr = chain->nr;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err;
+	int i, j, err, nr_entries, nr_contexts;
 	int skip_idx = -1;
 	int first_call = 0;
 
@@ -1828,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain->nr < sysctl_perf_event_max_stack)
+	if (chain_nr < sysctl_perf_event_max_stack)
 		skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
@@ -1889,12 +1889,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
-
-	for (i = first_call; i < chain_nr; i++) {
+	for (i = first_call, nr_entries = 0, nr_contexts = 0;
+	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 
 		if (callchain_param.order == ORDER_CALLEE)
@@ -1908,6 +1904,14 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
+		if (ip >= PERF_CONTEXT_MAX) {
+			if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack)
+				goto out_corrupted_callchain;
+		} else {
+			if (++nr_entries > sysctl_perf_event_max_stack)
+				goto out_corrupted_callchain;
+		}
+
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
@@ -1915,6 +1919,10 @@ check_calls:
 	}
 
 	return 0;
+
+out_corrupted_callchain:
+	pr_warning("corrupted callchain. skipping...\n");
+	return 0;
 }
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eab077ad6ca9..23504ad5d6dd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -33,7 +33,8 @@ struct callchain_param	callchain_param = {
 unsigned int page_size;
 int cacheline_size;
 
-unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
 bool test_attr__enabled;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7651633a8dc7..1e8c3167b9fb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig);
 
 extern unsigned int page_size;
 extern int cacheline_size;
-extern unsigned int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
 
 struct parse_tag {
 	char tag;
-- 
cgit v1.2.3