perf record: Fix perf_can_aux_sample_size()
Adrian Hunter
reviewerPATCH 1/1 perf record: Fix perf_can_aux_sample_size()
perf_can_aux_sample_size() always returned true because it did not pass the attribute size to sys_perf_event_open, nor correctly check the return value and errno.
Before:
# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
Error:
The sys_perf_event_open() syscall returned with 7 (Argument list too long) for event (branch-misses:u).
/bin/dmesg | grep -i perf may provide additional information.After:
# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
AUX area sampling is not supported by kernel--- tools/perf/util/record.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/perf/util/record.c +2 -1
@@ -143,6 +143,7 @@ bool perf_can_record_cpu_wide(void)bool perf_can_aux_sample (void ) {struct perf_event_attr attr = { + .size =sizeof (struct perf_event_attr ), .exclude_kernel =1 ,/* * Non-zero value causes the kernel to calculate the effective
@@ -158,7 +159,7 @@ bool perf_can_aux_sample(void)* then we assume that it is supported. We are relying on the kernel to * validate the attribute size before anything else that could be wrong. */ -if (fd == -E2BIG ) +if (fd <0 && errno ==E2BIG )return false;if (fd >=0 )close (fd);
Signature · 1 line
2.17.1
Em Fri, Nov 22, 2019 at 11:48:56AM +0200, Adrian Hunter escreveu:
Quoted 11 lines
perf_can_aux_sample_size()always returned true because it did not pass the attribute size tosys_perf_event_open, nor correctly check the return value and errno.Before:
# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' Error: The sys_perf_event_open() syscall returned with 7 (Argument list too long) for event (branch-misses:u). /bin/dmesg | grep -i perf may provide additional information.
Quoted 4 lines
After:
# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' AUX area sampling is not supported by kernel
Since this hasn't been sent to Ingo, I combined it with the patch that introduced the problem, this one:
c31d79e7a052 perf record: Add a function to test for kernel support for AUX area sampling
Thanks for the quick fix,
- Arnaldo
Quoted 28 lines
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/record.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)tools/perf/util/record.c +2
-1@@ -143,6 +143,7 @@ bool perf_can_record_cpu_wide(void)bool perf_can_aux_sample (void ) {struct perf_event_attr attr = { + .size =sizeof (struct perf_event_attr ), .exclude_kernel =1 ,/* * Non-zero value causes the kernel to calculate the effective @@ -158,7 +159,7 @@ bool perf_can_aux_sample(void)* then we assume that it is supported. We are relying on the kernel to * validate the attribute size before anything else that could be wrong. */ -if (fd == -E2BIG ) +if (fd <0 && errno ==E2BIG )return false;if (fd >=0 )close (fd);Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Em Fri, Nov 22, 2019 at 10:42:57AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 17 lines
Em Fri, Nov 22, 2019 at 11:48:56AM +0200, Adrian Hunter escreveu:
Quoted 11 lines
perf_can_aux_sample_size()always returned true because it did not pass the attribute size tosys_perf_event_open, nor correctly check the return value and errno.Before:
# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' Error: The sys_perf_event_open() syscall returned with 7 (Argument list too long) for event (branch-misses:u). /bin/dmesg | grep -i perf may provide additional information.Quoted 4 lines
After:
# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' AUX area sampling is not supported by kernel
Quoted 6 lines
Since this hasn't been sent to Ingo, I combined it with the patch that introduced the problem, this one:
c31d79e7a052perf record: Add a function to test for kernel support for AUX area samplingThanks for the quick fix,
Wrapping up, at the end of the series I now get:
[root@quaco ~]# perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' AUX area sampling is not supported by kernel
[root@quaco ~]#
[root@quaco ~]# uname -a
Linux quaco 5.4.0-rc8 #1 SMP Mon Nov 18 06:15:31 -03 2019 x86_64 x86_64 x86_64 GNU/Linux [root@quaco ~]#
Thanks,
- Arnaldo