[PATCH v2] perf/x86: fix filter_events() bug with event mappings

[PATCH v2] perf/x86: fix filter_events() bug with event mappings

[Stephane Eranian]

This patch fixes a bug in the filter_events() function.

The patch fixes the bug whereby if some mappings did not
exist, e.g., STALLED_CYCLES_FRONTEND, then any event after it
in the attrs array would disappear from the published list of
events in /sys/devices/cpu/events. This could be verified
easily on any system post SNB (which do not publish
STALLED_CYCLES_FRONTEND):

	$ ./perf stat -e cycles,ref-cycles true
 	Performance counter stats for 'true':
              1,217,348      cycles
	<not supported>      ref-cycles

The problem is that in filter_events() there is an assumption
that the argument (attrs) is organized in increasing continuous
event indexes related to the event_map(). But if we remove the
non-supported events by shifing the position in the array, then
the lookup x86_pmu.event_map() needs to compensate for it, otherwise
we are looking up the wrong index. This patch corrects this problem
by compensating for the deleted events and with that ref-cycles
reappears (here shown on Haswell):
	$ perf stat -e ref-cycles,cycles true
 	Performance counter stats for 'true':
         4,525,910      ref-cycles
         1,064,920      cycles
       0.002943888 seconds time elapsed

This problem was introduced into commit 8300daa26.

Fixes: 8300daa26 ("perf/x86: Filter out undefined events from sysfs events attribute")

In V2, we dropped the attrs[j] = NULL fix because it was superfluous.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 arch/x86/kernel/cpu/perf_event.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e7e63a9..1b443db 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1534,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs)
 {
 	struct device_attribute *d;
 	struct perf_pmu_events_attr *pmu_attr;
+	int offset = 0;
 	int i, j;
 
 	for (i = 0; attrs[i]; i++) {
@@ -1542,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs)
 		/* str trumps id */
 		if (pmu_attr->event_str)
 			continue;
-		if (x86_pmu.event_map(i))
+		if (x86_pmu.event_map(i + offset))
 			continue;
 
 		for (j = i; attrs[j]; j++)
@@ -1550,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs)
 
 		/* Check the shifted attr. */
 		i--;
+
+		/*
+		 * event_map() is index based, the attrs array is organized
+		 * by increasing event index. If we shift the events, then
+		 * we need to compensate for the event_map(), otherwise
+		 * we are looking up the wrong event in the map
+		 */
+		offset++;
 	}
 }
 
-- 
2.5.0

Re: [PATCH v2] perf/x86: fix filter_events() bug with event mappings

[Peter Zijlstra]

On Mon, Dec 07, 2015 at 08:33:25PM +0100, Stephane Eranian wrote:
> Fixes: 8300daa26 ("perf/x86: Filter out undefined events from sysfs events attribute")

Please put the below in your .gitconfig, the alias is just a convenient
helper to generate the right string, but the abbrev is the important
part, we've already had hash collisions with the short thingies.


[core]
        abbrev = 12
[alias]
        one = show -s --pretty='format:%h (\"%s\")'

[tip:perf/core] perf/x86: Fix filter_events() bug with event mappings

[tip-bot for Stephane Eranian]

Commit-ID:  61b87cae6361ea6af161c1ffa549898892707b19
Gitweb:     http://git.kernel.org/tip/61b87cae6361ea6af161c1ffa549898892707b19
Author:     Stephane Eranian <eranian@google.com>
AuthorDate: Mon, 7 Dec 2015 20:33:25 +0100
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 6 Jan 2016 11:15:33 +0100

perf/x86: Fix filter_events() bug with event mappings

This patch fixes a bug in the filter_events() function.

The patch fixes the bug whereby if some mappings did not
exist, e.g., STALLED_CYCLES_FRONTEND, then any event after it
in the attrs array would disappear from the published list of
events in /sys/devices/cpu/events. This could be verified
easily on any system post SNB (which do not publish
STALLED_CYCLES_FRONTEND):

	$ ./perf stat -e cycles,ref-cycles true
	Performance counter stats for 'true':
              1,217,348      cycles
	<not supported>      ref-cycles

The problem is that in filter_events() there is an assumption
that the argument (attrs) is organized in increasing continuous
event indexes related to the event_map(). But if we remove the
non-supported events by shifing the position in the array, then
the lookup x86_pmu.event_map() needs to compensate for it, otherwise
we are looking up the wrong index. This patch corrects this problem
by compensating for the deleted events and with that ref-cycles
reappears (here shown on Haswell):

	$ perf stat -e ref-cycles,cycles true
	Performance counter stats for 'true':
         4,525,910      ref-cycles
         1,064,920      cycles
       0.002943888 seconds time elapsed

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: jolsa@kernel.org
Cc: kan.liang@intel.com
Fixes: 8300daa26755 ("perf/x86: Filter out undefined events from sysfs events attribute")
Link: http://lkml.kernel.org/r/1449516805-6637-1-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e7e63a9..1b443db 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1534,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs)
 {
 	struct device_attribute *d;
 	struct perf_pmu_events_attr *pmu_attr;
+	int offset = 0;
 	int i, j;
 
 	for (i = 0; attrs[i]; i++) {
@@ -1542,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs)
 		/* str trumps id */
 		if (pmu_attr->event_str)
 			continue;
-		if (x86_pmu.event_map(i))
+		if (x86_pmu.event_map(i + offset))
 			continue;
 
 		for (j = i; attrs[j]; j++)
@@ -1550,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs)
 
 		/* Check the shifted attr. */
 		i--;
+
+		/*
+		 * event_map() is index based, the attrs array is organized
+		 * by increasing event index. If we shift the events, then
+		 * we need to compensate for the event_map(), otherwise
+		 * we are looking up the wrong event in the map
+		 */
+		offset++;
 	}
 }