perf_event is a utility controller whose primary role is identifying
cgroup membership to filter perf events; however, because it also
tracks some per-css state, it can't be replaced by pure cgroup
membership test. Mark the controller as implicitly enabled on the
default hierarchy so that perf events can always be filtered based on
cgroup v2 path as long as the controller is not mounted on a legacy
hierarchy.
"perf record" is updated accordingly so that it searches for both v1
and v2 hierarchies. A v1 hierarchy is used if perf_event is mounted
on it; otherwise, it uses the v2 hierarchy.
v2: Doc updated to reflect more flexible rebinding behavior.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Commit 21e6d84286 ("perf diff: Use perf_hpp__register_sort_field
interface") changed list_add() to perf_hpp__register_sort_field().
This resulted in a behavior change since the field was added to the tail
instead of the head. So the -o option is mostly ignored due to its
order in the list.
This patch fixes it by adding perf_hpp__prepend_sort_field().
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 21e6d84286 ("perf diff: Use perf_hpp__register_sort_field interface")
Link: http://lkml.kernel.org/r/20170118051457.30946-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The -o/--order option is to select column number to sort a diff result.
It does the job by adding a hpp field at the beginning of the sort list.
But it should not be added to the output field list as it has no
callbacks required by a output field.
During the setup_sorting(), the perf_hpp__setup_output_field() appends
the given sort keys to the output field if it's not there already.
Originally it was checked by fmt->list being non-empty. But commit
3f931f2c42 ("perf hists: Make hpp setup function generic") changed it
to check the ->equal callback.
Anyways, we don't need to add the pseudo hpp field to the output field
list since it won't be used for output. So just skip fields if they
have no ->color or ->entry callbacks.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 3f931f2c42 ("perf hists: Make hpp setup function generic")
Link: http://lkml.kernel.org/r/20170118051457.30946-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Previously these were being ignored, sometimes silently.
Stop doing that, emitting debug messages and handling the errors.
Testing it:
$ cat ~/.perfconfig
cat: /home/acme/.perfconfig: No such file or directory
$ perf stat -e cycles usleep 1
Performance counter stats for 'usleep 1':
938,996 cycles:u
0.003813731 seconds time elapsed
$ perf top --stdio
Error:
You may not have permission to collect system-wide stats.
Consider tweaking /proc/sys/kernel/perf_event_paranoid,
<SNIP>
[ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ]
[acme@jouet linux]$ perf report --stdio
# To display the perf.data header info, please use --header/--header-only options.
# Overhead Command Shared Object Symbol
# ........ ....... ................. .........................
71.77% usleep libc-2.24.so [.] _dl_addr
27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry
1.13% usleep [kernel.kallsyms] [k] page_fault
$
$ touch ~/.perfconfig
$ ls -la ~/.perfconfig
-rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig
$
$ perf stat -e instructions usleep 1
Performance counter stats for 'usleep 1':
244,610 instructions:u
0.000805383 seconds time elapsed
$
[root@jouet ~]# chown acme.acme ~/.perfconfig
[root@jouet ~]# perf stat -e cycles usleep 1
Warning: File /root/.perfconfig not owned by current user or root, ignoring it.
Performance counter stats for 'usleep 1':
937,615 cycles
0.000836931 seconds time elapsed
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
While propagating the errors from perf_config(), which were being
completely ignored, everything stopped working for people without a
~/.perfconfig file, because the perf_config_set__init() was considering
an error not to have a .perfconfig file, duh, fix it by checking the
errno after the failed stat() call.
It should also not return an error when it says it is ignoring the file,
and also a empty file should not return an error either.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 8beeb00f2c ("perf config: Use new perf_config_set__init() to initialize config set")
Link: http://lkml.kernel.org/n/tip-ygpbab3apbs6l8wr97xedwks@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull the latest perf/core updates from Arnaldo Carvalho de Melo:
New features:
- Introduce 'perf ftrace' a perf front end to the kernel's ftrace
function and function_graph tracer, defaulting to the "function_graph"
tracer, more work will be done in reviving this effort, forward porting
it from its initial patch submission (Namhyung Kim)
- Add 'e' and 'c' hotkeys to expand/collapse call chains for a single
hist entry in the 'perf report' and 'perf top' TUI (Jiri Olsa)
Fixes:
- Fix wrong register name for arm64, used in 'perf probe' (He Kuang)
- Fix map offsets in relocation in libbpf (Joe Stringer)
- Fix looking up dwarf unwind stack info (Matija Glavinic Pecotic)
Infrastructure changes:
- libbpf prog functions sync with what is exported via uapi (Joe Stringer)
Trivial changes:
- Remove unnecessary checks and assignments in 'perf probe's
try_to_find_absolute_address() (Markus Elfring)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add support for the __print_hex_str() macro that was added for
tracing, so that user space tools such as perf can understand
it as well.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using perf with call graph method dwarf fails to provide backtrace
support for stripped binary even though .gnu_debuglink points to *.dbg
flavor with properly populated debug symbols.
Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and
4.10.rc3. Perf is configured with libunwind, and unwind dwarf support
[1]. Test code (stress_bt.c) can be found on [2].
Running (explicitly disable other unwinding methods):
$ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \
-fno-asynchronous-unwind-tables stress_bt.c
$ perf record -N --call-graph dwarf ./stress_bt
$ perf report
results in properly generated call graph. Stripping the binary and running
it results with missing call graph. Expected result is to have call graph:
$ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \
-fno-asynchronous-unwind-tables stress_bt.c
$ objcopy --only-keep-debug stress_bt stress_bt.dbg
$ objcopy --strip-debug stress_bt
$ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt
$ perf record -N --call-graph dwarf ./stress_bt
$ perf report
Problem is that perf doesn't try to read symbols pointed by gnu
debuglink. Patch adds checking, and reading of the symbols from
debuglink and symsrc. Order of the check is to first check within dso,
then check whether symsrc is defined and try to read from it. Finally,
debuglink is checked. Default locations of debug files are discussed in
[3] and [4]. Comments on RFC are on [5].
[1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding
[2] [1]#Backtrace_stress_application
[3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html
[4] https://sourceware.org/binutils/docs/binutils/objcopy.html
[5] https://lkml.org/lkml/2016/8/22/473
Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The use_browser and perf_version_string variables are both declared in
perf.c but they are also referenced by other functions of libperf.a.
Therefore a user linking an own main() with libperf.a must declare those
two variables in their files even if the files never use the browser or
the version information.
This patch fixes this issue by moving use_browser and
perf_version_string out of perf.c to some other files.
Signed-off-by: Soramichi Akiyama <akiyama@m.soramichi.jp>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170117002237.c1aec0ce3b4d675dca018deb@m.soramichi.jp
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The --state option is to show task state when switched out. The state
is printed as a single character like in the /proc but I added 'I' for
idle state rather than 'R'.
$ perf sched timehist --state | head
Samples do not have callchains.
time cpu task name wait time sch delay run time state
[tid/pid] (msec) (msec) (msec)
-------- --- ----------------------- -------- ------------------ -----
1.753791 [3] <idle> 0.000 0.000 0.000 I
1.753834 [1] perf[27469] 0.000 0.000 0.000 S
1.753904 [3] perf[27470] 0.000 0.006 0.112 S
1.753914 [1] <idle> 0.000 0.000 0.079 I
1.753915 [3] migration/3[23] 0.000 0.002 0.011 S
1.754287 [2] <idle> 0.000 0.000 0.000 I
1.754335 [2] transmission[1773/1739] 0.000 0.004 0.047 S
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170113104523.31212-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Fix to probe on gcc generated functions on modules. Since
probing on a module is based on its symbol name, it should
be adjusted on actual symbols.
E.g. without this fix, perf probe shows probe definition
on non-exist symbol as below.
$ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -F in_range*
in_range.isra.12
$ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -D in_range
p:probe/in_range nf_nat:in_range+0
With this fix, perf probe correctly shows a probe on
gcc-generated symbol.
$ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -D in_range
p:probe/in_range nf_nat:in_range.isra.12+0
This also fixes same problem on online module as below.
$ perf probe -m i915 -D assert_plane
p:probe/assert_plane i915:assert_plane.constprop.134+0
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/148411450673.9978.14905987549651656075.stgit@devbox
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Fix to show correct locations for events on modules by relocating given
address instead of retrying after failure.
This happens when the module text size is big enough, bigger than
sh_addr, because the original code retries with given address + sh_addr
if it failed to find CU DIE at the given address.
Any address smaller than sh_addr always fails and it retries with the
correct address, but addresses bigger than sh_addr will get a CU DIE
which is on the given address (not adjusted by sh_addr).
In my environment(x86-64), the sh_addr of ".text" section is 0x10030.
Since i915 is a huge kernel module, we can see this issue as below.
$ grep "[Tt] .*\[i915\]" /proc/kallsyms | sort | head -n1
ffffffffc0270000 t i915_switcheroo_can_switch [i915]
ffffffffc0270000 + 0x10030 = ffffffffc0280030, so we'll check
symbols cross this boundary.
$ grep "[Tt] .*\[i915\]" /proc/kallsyms | grep -B1 ^ffffffffc028\
| head -n 2
ffffffffc027ff80 t haswell_init_clock_gating [i915]
ffffffffc0280110 t valleyview_init_clock_gating [i915]
So setup probes on both function and see what happen.
$ sudo ./perf probe -m i915 -a haswell_init_clock_gating \
-a valleyview_init_clock_gating
Added new events:
probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)
You can now use it in all perf tools, such as:
perf record -e probe:valleyview_init_clock_gating -aR sleep 1
$ sudo ./perf probe -l
probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
probe:valleyview_init_clock_gating (on i915_vga_set_decode:4@gpu/drm/i915/i915_drv.c in i915)
As you can see, haswell_init_clock_gating is correctly shown,
but valleyview_init_clock_gating is not.
With this patch, both events are shown correctly.
$ sudo ./perf probe -l
probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
Committer notes:
In my case:
# perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating
Added new events:
probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)
You can now use it in all perf tools, such as:
perf record -e probe:valleyview_init_clock_gating -aR sleep 1
# perf probe -l
probe:haswell_init_clock_gating (on i915_getparam+432@gpu/drm/i915/i915_drv.c in i915)
probe:valleyview_init_clock_gating (on __i915_printk+240@gpu/drm/i915/i915_drv.c in i915)
#
# readelf -SW /lib/modules/4.9.0+/build/vmlinux | egrep -w '.text|Name'
[Nr] Name Type Address Off Size ES Flg Lk Inf Al
[ 1] .text PROGBITS ffffffff81000000 200000 822fd3 00 AX 0 0 4096
#
So both are b0rked, now with the fix:
# perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating
Added new events:
probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)
You can now use it in all perf tools, such as:
perf record -e probe:valleyview_init_clock_gating -aR sleep 1
# perf probe -l
probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
#
Both looks correct.
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/148411436777.9978.1440275861947194930.stgit@devbox
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf fixes from Ingo Molnar:
"Misc race fixes uncovered by fuzzing efforts, a Sparse fix, two PMU
driver fixes, plus miscellanous tooling fixes"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Reject non sampling events with precise_ip
perf/x86/intel: Account interrupts for PEBS errors
perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race
perf/core: Fix sys_perf_event_open() vs. hotplug
perf/x86/intel: Use ULL constant to prevent undefined shift behaviour
perf/x86/intel/uncore: Fix hardcoded socket 0 assumption in the Haswell init code
perf/x86: Set pmu->module in Intel PMU modules
perf probe: Fix to probe on gcc generated symbols for offline kernel
perf probe: Fix --funcs to show correct symbols for offline module
perf symbols: Robustify reading of build-id from sysfs
perf tools: Install tools/lib/traceevent plugins with install-bin
tools lib traceevent: Fix prev/next_prio for deadline tasks
perf record: Fix --switch-output documentation and comment
perf record: Make __record_options static
tools lib subcmd: Add OPT_STRING_OPTARG_SET option
perf probe: Fix to get correct modname from elf header
samples/bpf trace_output_user: Remove duplicate sys/ioctl.h include
samples/bpf sock_example: Avoid getting ethhdr from two includes
perf sched timehist: Show total scheduling time
It's now possible to specify the threshold time for perf.data like:
$ perf record --switch-output=30s ...
Once it's reached, the current data are dumped in to the
perf.data.<timestamp> file and session does on.
$ perf record --switch-output=30s ...
[ perf record: dump data: Woken up 44 times ]
[ perf record: Dump perf.data.2017010213043746 ]
...
The time is expected to be a number with appended unit
character - s/m/h/d.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Wang Nan <wangnan0@huawei.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1483955520-29063-7-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
