perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid

kernel/events/core.c has:

  /*
   * perf event paranoia level:
   *  -1 - not paranoid at all
   *   0 - disallow raw tracepoint access for unpriv
   *   1 - disallow cpu events for unpriv
   *   2 - disallow kernel profiling for unpriv
   */
  int sysctl_perf_event_paranoid __read_mostly = 1;

So, with the default being 1, a non-root user can trace his stuff:

  [acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
  1
  [acme@zoo ~]$ yes > /dev/null &
  [1] 15338
  [acme@zoo ~]$ trace -p 15338 | head -5
       0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
  [acme@zoo ~]$
  [acme@zoo ~]$ trace --duration 1 sleep 1
    1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250                           ) = 0
  [acme@zoo ~]$
  [acme@zoo ~]$ trace -- usleep 1 | tail -5
       0.905 ( 0.002 ms): brk(                                                     ) = 0x1c82000
       0.910 ( 0.003 ms): brk(brk: 0x1ca3000                                       ) = 0x1ca3000
       0.913 ( 0.001 ms): brk(                                                     ) = 0x1ca3000
       0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280                           ) = 0
       0.995 ( 0.000 ms): exit_group(
  [acme@zoo ~]$

But can't do system wide tracing:

  [acme@zoo ~]$ trace
  Error:	Operation not permitted.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 1.
  [acme@zoo ~]$

  [acme@zoo ~]$ trace --cpu 0
  Error:	Operation not permitted.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 1.
  [acme@zoo ~]$

If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:

  [acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
  [acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
  2
  [acme@zoo ~]$
  [acme@zoo ~]$ trace usleep 1
  Error:	Permission denied.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For your workloads it needs to be <= 1
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 2.
  [acme@zoo ~]$
  [acme@zoo ~]$ trace
  Error:	Permission denied.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For your workloads it needs to be <= 1
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 2.
  [acme@zoo ~]$
  [acme@zoo ~]$ trace --cpu 1
  Error:	Permission denied.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For your workloads it needs to be <= 1
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 2.
  [acme@zoo ~]$

If the user manages to get what he/she wants, convincing root not
to be paranoid at all...

  [root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
  [root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
  -1
  [root@zoo ~]#

  [acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
  root       729 Xorg
  [acme@zoo ~]$
  [acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg  | head -5
      23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
      23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096     ) = 8
      23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096     ) = -1 EAGAIN Resource temporarily unavailable
      23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
      23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
  [acme@zoo ~]$

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Arnaldo Carvalho de Melo 2013-10-17 17:38:29 -03:00
Родитель 97a07f10c3
Коммит a8f23d8f8a
3 изменённых файлов: 48 добавлений и 6 удалений

Просмотреть файл

@ -1713,10 +1713,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
}
err = perf_evlist__open(evlist);
if (err < 0) {
fprintf(trace->output, "Couldn't create the events: %s\n", strerror(errno));
goto out_delete_maps;
}
if (err < 0)
goto out_error_open;
err = perf_evlist__mmap(evlist, UINT_MAX, false);
if (err < 0) {
@ -1813,14 +1811,21 @@ out_delete_evlist:
out:
trace->live = false;
return err;
out_error_tp:
{
char errbuf[BUFSIZ];
out_error_tp:
perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
goto out_error;
out_error_open:
perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
out_error:
fprintf(trace->output, "%s\n", errbuf);
}
goto out_delete_evlist;
}
}
static int trace__replay(struct trace *trace)
{

Просмотреть файл

@ -1153,3 +1153,39 @@ int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
return 0;
}
int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
int err, char *buf, size_t size)
{
int printed, value;
char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
switch (err) {
case EACCES:
case EPERM:
printed = scnprintf(buf, size,
"Error:\t%s.\n"
"Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
break;
printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
if (value >= 2) {
printed += scnprintf(buf + printed, size - printed,
"For your workloads it needs to be <= 1\nHint:\t");
}
printed += scnprintf(buf + printed, size - printed,
"For system wide tracing it needs to be set to -1");
printed += scnprintf(buf + printed, size - printed,
".\nHint:\tThe current value is %d.", value);
break;
default:
scnprintf(buf, size, "%s", emsg);
break;
}
return 0;
}

Просмотреть файл

@ -169,6 +169,7 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{