linux_dsm_epyc7002/tools/perf
Arnaldo Carvalho de Melo a8f23d8f8a 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>
2013-10-17 17:38:29 -03:00
..
arch tools/perf: Standardize feature support define names to: HAVE_{FEATURE}_SUPPORT 2013-10-09 08:48:28 +02:00
bench perf bench: Fix failing assertions in numa bench 2013-10-11 12:17:38 -03:00
config tools/perf/build: Simplify the autodep inclusion rule 2013-10-14 10:29:18 -03:00
Documentation perf trace: Use vfs_getname hook if available 2013-10-16 11:18:24 -03:00
python perf python: Remove duplicate TID bit from mask 2013-08-07 17:35:25 -03:00
scripts perf script: Fix broken include in Context.xs 2013-07-10 13:47:00 -03:00
tests perf tests: Fix memory leak in dso-data.c 2013-10-14 10:28:54 -03:00
ui perf annotate: Another fix for annotate_browser__callq() 2013-10-14 12:21:18 -03:00
util perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid 2013-10-17 17:38:29 -03:00
.gitignore perf tools: Ignore 'perf timechart' output file 2013-10-11 12:17:37 -03:00
bash_completion perf completion: Use more comp words 2013-10-09 11:12:31 -03:00
builtin-annotate.c perf tools: Separate out GTK codes to libperf-gtk.so 2013-10-09 15:55:25 -03:00
builtin-bench.c tools/perf: Standardize feature support define names to: HAVE_{FEATURE}_SUPPORT 2013-10-09 08:48:28 +02:00
builtin-buildid-cache.c perf buildid-cache: Add ability to add kcore to the cache 2013-10-14 12:20:38 -03:00
builtin-buildid-list.c perf symbols: Generalize filter in __fprintf_buildid methods 2012-12-09 08:46:07 -03:00
builtin-diff.c tools/perf: Add support for record transaction flags 2013-10-04 10:06:12 +02:00
builtin-evlist.c perf evlist: Pass the event_group info via perf_attr_details 2013-02-06 18:09:28 -03:00
builtin-help.c perf help: Fix --help for builtins 2012-10-22 12:35:49 -02:00
builtin-inject.c tools/perf: Standardize feature support define names to: HAVE_{FEATURE}_SUPPORT 2013-10-09 08:48:28 +02:00
builtin-kmem.c perf kmem: Make it work again on non NUMA machines 2013-09-24 14:13:46 -03:00
builtin-kvm.c perf tools: Check mmap pages value early 2013-10-09 11:24:10 -03:00
builtin-list.c perf list: List kernel supplied event aliases 2013-07-12 13:53:53 -03:00
builtin-lock.c perf lock: Account for lock average wait time 2013-10-09 11:24:01 -03:00
builtin-mem.c perf tools: Add attr->mmap2 support 2013-09-11 10:09:32 -03:00
builtin-probe.c tools/perf: Standardize feature support define names to: HAVE_{FEATURE}_SUPPORT 2013-10-09 08:48:28 +02:00
builtin-record.c perf tools: Check mmap pages value early 2013-10-09 11:24:10 -03:00
builtin-report.c perf tools: Separate out GTK codes to libperf-gtk.so 2013-10-09 15:55:25 -03:00
builtin-sched.c perf tools: change machine__findnew_thread() to set thread pid 2013-08-29 11:51:31 -03:00
builtin-script.c perf session: Check for SIGINT in more loops 2013-09-19 11:32:17 -03:00
builtin-stat.c perf stat: Add units to nanosec-based counters 2013-10-11 12:17:46 -03:00
builtin-timechart.c perf timechart: Remove event types framework only user 2013-07-15 16:14:47 -03:00
builtin-top.c perf symbols: Add new option --ignore-vmlinux for perf top 2013-10-09 11:42:20 -03:00
builtin-trace.c perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid 2013-10-17 17:38:29 -03:00
builtin.h perf tools: Add new mem command for memory access profiling 2013-04-01 12:21:44 -03:00
command-list.txt perf tools: Add new mem command for memory access profiling 2013-04-01 12:21:44 -03:00
CREDITS perf_counter tools: Add CREDITS file for Git contributors 2009-06-24 19:54:29 +02:00
design.txt perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP 2012-05-31 11:38:42 -03:00
Makefile tools/perf/build: Pass through DEBUG parameter 2013-10-14 10:29:07 -03:00
Makefile.perf perf tools: Implement summary output for 'make install' 2013-10-11 12:18:11 -03:00
MANIFEST perf tools: Introduce tools/lib/lk library 2013-03-15 13:06:00 -03:00
perf-archive.sh perf archive: Make 'f' the last parameter for tar 2012-09-17 13:10:42 -03:00
perf.c perf trace: Add 'trace' alias to 'perf trace' 2013-10-11 12:17:10 -03:00
perf.h tools/perf: Add support for record transaction flags 2013-10-04 10:06:12 +02:00