perf/tools: fix perf_evsel__fallback() for paranoid=2 and -b
PATCH 1/1 perf/tools: fix perf_evsel__fallback() for paranoid=2 and -b
When perf_event_paranoid=2, regular users are prevented from sampling at the kernel level. However, it the user passes an event without a privilege level, the tool will force :u when it detects paranoid>1. This works well, except when branch sampling is requested. It has a more stringent requirement especially with exclude_hv.
$ perf record ls [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB /tmp/perf.data ]
But:
$ perf record -b ls Error: You may not have permission to collect stats.
Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN).
The current value is 2:
-1: Allow use of (almost) all events by all users
>= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN
To make this setting permanent, edit /etc/sysctl.conf too, e.g.:
kernel.perf_event_paranoid = -1
The problem is that in the fallback cod only exclude_kernel is checked and if set, then exclude_hv is not forced to 1. When branch sampling is enabled exclude_hv must be set.
This patch fixes the bug in the fallback code by considering the value of exclude_hv and not just exclude_kernel. We prefer this approach to give a chance to exclude_hv=0.
--- tools/perf/util/evsel.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/perf/util/evsel.c +2 -1
@@ -2424,7 +2424,8 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,zfree (&evsel->name);return true; - }else if (err ==EACCES && !evsel->core.attr.exclude_kernel && + }else if (err ==EACCES && + (!evsel->core.attr.exclude_kernel || !evsel->core.attr.exclude_hv) && (paranoid =perf_event_paranoid ()) >1 ) {const char *name =perf_evsel__name (evsel);char *new_name;
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Quoted 33 lines · Stephane Eranian
When perf_event_paranoid=2, regular users are prevented from sampling at the kernel level. However, it the user passes an event without a privilege level, the tool will force :u when it detects paranoid>1. This works well, except when branch sampling is requested. It has a more stringent requirement especially with
exclude_hv.$ perf record ls [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB /tmp/perf.data ]But:
$ perf record -b ls Error: You may not have permission to collect stats.Consider tweaking
/proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (withoutCAP_SYS_ADMIN).The current value is 2:
-1: Allow use of (almost) all events by all users
>= 0: Disallow raw tracepoint access by users withoutCAP_IOC_LOCK>= 1: Disallow CPU event access by users withoutCAP_SYS_ADMIN>= 2: Disallow kernel profiling by users withoutCAP_SYS_ADMINTo make this setting permanent, edit
/etc/sysctl.conftoo, e.g.:kernel.perf_event_paranoid = -1
The problem is that in the fallback cod only
exclude_kernelis checked and if set, thenexclude_hvis not forced to 1. When branch sampling is enabledexclude_hvmust be set.
Quoted 5 lines
This patch fixes the bug in the fallback code by considering the value of
exclude_hvand not justexclude_kernel. We prefer this approach to give a chance to exclude_hv=0.Signed-off-by Stephane Eranian <[email protected]>
thanks,
jirka
Quoted 21 lines
--- tools/perf/util/evsel.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)tools/perf/util/evsel.c +2
-1@@ -2424,7 +2424,8 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,zfree (&evsel->name);return true; - }else if (err ==EACCES && !evsel->core.attr.exclude_kernel && + }else if (err ==EACCES && + (!evsel->core.attr.exclude_kernel || !evsel->core.attr.exclude_hv) && (paranoid =perf_event_paranoid ()) >1 ) {const char *name =perf_evsel__name (evsel);char *new_name;Signature · 1 line
2.25.1.696.g5e7596f4ac-goog