diff options
| author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2019-11-04 16:09:48 -0300 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2019-11-12 08:20:53 -0300 |
| commit | f2baa060cd766f4e585339423891e0063179d702 (patch) | |
| tree | 27fd8fc96e06161dba7946499c897f52568127d7 /tools/perf | |
| parent | de90d513b2464d28a17fc4eaada97f4ad742ba00 (diff) | |
perf symbols: Stop using map->groups, we can use kmaps instead
To test that that function is being called I just added a probe on that
place, enabled it via 'perf trace' asking for at most 16 levels of
backtraces, system wide, and then ran 'perf top' on another xterm,
voilà:
# perf probe -x ~/bin/perf dso__process_kernel_symbol
Added new event:
probe_perf:dso__process_kernel_symbol (on dso__process_kernel_symbol in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:dso__process_kernel_symbol -aR sleep 1
# perf trace -e probe_perf:dso__process_kernel_symbol/max-stack=16/ --max-events=2
# perf trace -e probe_perf:dso__process_kernel_symbol/max-stack=16/ --max-events=2
0.000 :17345/17345 probe_perf:dso__process_kernel_symbol(__probe_ip: 5680224)
dso__process_kernel_symbol (/home/acme/bin/perf)
dso__load_vmlinux (/home/acme/bin/perf)
dso__load_vmlinux_path (/home/acme/bin/perf)
dso__load (/home/acme/bin/perf)
map__load (/home/acme/bin/perf)
thread__find_map (/home/acme/bin/perf)
machine__resolve (/home/acme/bin/perf)
deliver_event (/home/acme/bin/perf)
__ordered_events__flush.part.0 (/home/acme/bin/perf)
process_thread (/home/acme/bin/perf)
start_thread (/usr/lib64/libpthread-2.29.so)
0.064 :17345/17345 probe_perf:dso__process_kernel_symbol(__probe_ip: 5680224)
dso__process_kernel_symbol (/home/acme/bin/perf)
dso__load_vmlinux (/home/acme/bin/perf)
dso__load_vmlinux_path (/home/acme/bin/perf)
dso__load (/home/acme/bin/perf)
map__load (/home/acme/bin/perf)
thread__find_map (/home/acme/bin/perf)
machine__resolve (/home/acme/bin/perf)
deliver_event (/home/acme/bin/perf)
__ordered_events__flush.part.0 (/home/acme/bin/perf)
process_thread (/home/acme/bin/perf)
start_thread (/usr/lib64/libpthread-2.29.so)
#
# perf stat -e probe_perf:dso__process_kernel_symbol
^C
Performance counter stats for 'system wide':
107,308 probe_perf:dso__process_kernel_symbol
8.215399813 seconds time elapsed
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-5fy66x5hr5ct9pmw84jkiwvm@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf')
| -rw-r--r-- | tools/perf/util/symbol-elf.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66f4be1df573..16776d5fbaea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -934,7 +934,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, * we still are sure to have a reference to this DSO via * *curr_map->dso. */ - dsos__add(&map->groups->machine->dsos, curr_dso); + dsos__add(&kmaps->machine->dsos, curr_dso); /* kmaps already got it */ map__put(curr_map); dso__set_loaded(curr_dso); |