kevin/linux
1
Fork 0
Code

perf stat: Constify control data for BPF

Browse Source 
The control knobs set before loading BPF programs should be declared as
'const volatile' so that it can be optimized by the BPF core.

Committer testing:

  root@x1:~# perf stat --bpf-counters -e cpu_core/cycles/,cpu_core/instructions/ sleep 1

   Performance counter stats for 'sleep 1':

           2,442,583      cpu_core/cycles/
           2,494,425      cpu_core/instructions/

         1.002687372 seconds time elapsed

         0.001126000 seconds user
         0.001166000 seconds sys

  root@x1:~# perf trace -e bpf --max-events 10 perf stat --bpf-counters -e cpu_core/cycles/,cpu_core/instructions/ sleep 1
       0.000 ( 0.019 ms): perf/2944119 bpf(cmd: OBJ_GET, uattr: 0x7fffdf5cdd40, size: 20)            = 5
       0.021 ( 0.002 ms): perf/2944119 bpf(cmd: OBJ_GET_INFO_BY_FD, uattr: 0x7fffdf5cdcd0, size: 16) = 0
       0.030 ( 0.005 ms): perf/2944119 bpf(cmd: MAP_LOOKUP_ELEM, uattr: 0x7fffdf5ceda0, size: 32)    = 0
       0.037 ( 0.004 ms): perf/2944119 bpf(cmd: LINK_GET_FD_BY_ID, uattr: 0x7fffdf5ced80, size: 12)  = -1 ENOENT (No such file or directory)
       0.189 ( 0.004 ms): perf/2944119 bpf(cmd: 36, uattr: 0x7fffdf5cec10, size: 8)                  = -1 EOPNOTSUPP (Operation not supported)
       0.201 ( 0.095 ms): perf/2944119 bpf(cmd: PROG_LOAD, uattr: 0x7fffdf5ce940, size: 148)         = 10
       0.305 ( 0.026 ms): perf/2944119 bpf(cmd: PROG_LOAD, uattr: 0x7fffdf5cea00, size: 148)         = 10
       0.347 ( 0.012 ms): perf/2944119 bpf(cmd: BTF_LOAD, uattr: 0x7fffdf5ce8e0, size: 40)           = 10
       0.364 ( 0.004 ms): perf/2944119 bpf(cmd: BTF_LOAD, uattr: 0x7fffdf5ce950, size: 40)           = 10
       0.376 ( 0.006 ms): perf/2944119 bpf(cmd: BTF_LOAD, uattr: 0x7fffdf5ce730, size: 40)           = 10
  root@x1:~#
   Performance counter stats for 'sleep 1':

             271,221      cpu_core/cycles/
             139,150      cpu_core/instructions/

         1.002881677 seconds time elapsed

         0.001318000 seconds user
         0.001314000 seconds sys

  root@x1:~#

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240902200515.2103769-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Namhyung Kim 2024-09-02 13:05:11 -07:00 committed by Arnaldo Carvalho de Melo
parent 18f41f1ba5
commit 76d3685400
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tools/perf/util/bpf_counter_cgroup.c
View File

@ -61,6 +61,9 @@ static int bperf_load_program(struct evlist *evlist)
skel->rodata->num_cpus = total_cpus; skel->rodata->num_cpus = total_cpus;
skel->rodata->num_events = evlist->core.nr_entries / nr_cgroups; skel->rodata->num_events = evlist->core.nr_entries / nr_cgroups;
if (cgroup_is_v2("perf_event") > 0)
skel->rodata->use_cgroup_v2 = 1;
BUG_ON(evlist->core.nr_entries % nr_cgroups != 0); BUG_ON(evlist->core.nr_entries % nr_cgroups != 0);
/* we need one copy of events per cpu for reading */ /* we need one copy of events per cpu for reading */
@ -82,9 +85,6 @@ static int bperf_load_program(struct evlist *evlist)
goto out; goto out;
} }
if (cgroup_is_v2("perf_event") > 0)
skel->bss->use_cgroup_v2 = 1;
err = -1; err = -1;
cgrp_switch = evsel__new(&cgrp_switch_attr); cgrp_switch = evsel__new(&cgrp_switch_attr);

2
tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
View File

@ -57,9 +57,9 @@ struct cgroup___old {
const volatile __u32 num_events = 1; const volatile __u32 num_events = 1;
const volatile __u32 num_cpus = 1; const volatile __u32 num_cpus = 1;
const volatile int use_cgroup_v2 = 0;
int enabled = 0; int enabled = 0;
int use_cgroup_v2 = 0;
int perf_subsys_id = -1; int perf_subsys_id = -1;
static inline __u64 get_cgroup_v1_ancestor_id(struct cgroup *cgrp, int level) static inline __u64 get_cgroup_v1_ancestor_id(struct cgroup *cgrp, int level)