Skip to contentSkip to conversation

perf report: Fix a bug on "--call-graph none" option

PATCH In review Namhyung Kim 3 participants 3 messages Sep 30, 2015 – Oct 3, 2015 perf events

lore
Share & tools
lore

Namhyung Kim

author maintainer
#0 lore raw

PATCH 1/1 perf report: Fix a bug on "--call-graph none" option

The patch f9db0d0f1b2c ("perf callchain: Allow disabling call graphs per event") added an ability to enable/disable callchain recording per event. But it had a problem when the enablement setting is changed at 'perf report' time using -g/--call-graph option.

For example, the following scenario will get a segfault.

  $ perf record -ag sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.500 MB perf.data (2555 samples) ]
  $ perf report -g none
  perf: Segmentation fault
  -------- backtrace --------
  perf[0x53a98a]
  /usr/lib/libc.so.6(+0x335af)[0x7f4e91df95af]

This is because callchain_param.sort() callback was not set but it tried to call the function as it had the PERF_SAMPLE_CALLCHAIN bit.

---
 tools/perf/util/hist.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/hist.c +1 -1
index b3567a25f0c4..99b8e14ce010 100644
@@ -1149,7 +1149,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	struct perf_evsel *evsel = hists_to_evsel(hists);
 	bool use_callchain;
 
-	if (evsel && !symbol_conf.show_ref_callgraph)
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
 		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
 	else
 		use_callchain = symbol_conf.use_callchain;
Signature · 1 line
2.5.0
#1 lore raw

Em Wed, Sep 30, 2015 at 01:34:00PM +0900, Namhyung Kim escreveu:

Quoted 11 lines

The patch f9db0d0f1b2c ("perf callchain: Allow disabling call graphs per event") added an ability to enable/disable callchain recording per event. But it had a problem when the enablement setting is changed at 'perf report' time using -g/--call-graph option.

For example, the following scenario will get a segfault.

  $ perf record -ag sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.500 MB perf.data (2555 samples) ]
Quoted 8 lines
  $ perf report -g none
  perf: Segmentation fault
  -------- backtrace --------
  perf[0x53a98a]
  /usr/lib/libc.so.6(+0x335af)[0x7f4e91df95af]

This is because callchain_param.sort() callback was not set but it tried to call the function as it had the PERF_SAMPLE_CALLCHAIN bit.

Thanks, reproduced, tested the fix, applied.

- Arnaldo

#2 lore raw
In reply to Namhyung Kim
perf report: Fix a bug on "--call-graph none" option
Commit-ID:  208e7607459477432d3df52c32d4b961a96d4a94
Gitweb:     http://git.kernel.org/tip/208e7607459477432d3df52c32d4b961a96d4a94
Author:     Namhyung Kim <[email protected]>
AuthorDate: Wed, 30 Sep 2015 13:34:00 +0900
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Thu, 1 Oct 2015 09:54:33 -0300

perf report: Fix a bug on "--call-graph none" option

The patch f9db0d0f1b2c ("perf callchain: Allow disabling call graphs per event") added an ability to enable/disable callchain recording per event. But it had a problem when the enablement setting is changed at 'perf report' time using -g/--call-graph option.

For example, the following scenario will get a segfault.

  $ perf record -ag sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.500 MB perf.data (2555 samples) ]
  $ perf report -g none
  perf: Segmentation fault
  -------- backtrace --------
  perf[0x53a98a]
  /usr/lib/libc.so.6(+0x335af)[0x7f4e91df95af]

This is because callchain_param.sort() callback was not set but it tried to call the function as it had the PERF_SAMPLE_CALLCHAIN bit.

Cc Jiri Olsa <[email protected]>
Cc Kan Liang <[email protected]>
Cc Peter Zijlstra <[email protected]>
Fixes f9db0d0f1b2c ("perf callchain: Allow disabling call graphs per event")
---
 tools/perf/util/hist.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/hist.c +1 -1
index 0cad9e0..c346b33 100644
@@ -1151,7 +1151,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	struct perf_evsel *evsel = hists_to_evsel(hists);
 	bool use_callchain;
 
-	if (evsel && !symbol_conf.show_ref_callgraph)
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
 		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
 	else
 		use_callchain = symbol_conf.use_callchain;