1
linux/tools/perf/util/bpf_kwork_top.c

310 lines
6.2 KiB
C
Raw Permalink Normal View History

perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
// SPDX-License-Identifier: GPL-2.0
/*
* bpf_kwork_top.c
*
* Copyright (c) 2022 Huawei Inc, Yang Jihong <yangjihong1@huawei.com>
*/
#include <time.h>
#include <fcntl.h>
#include <signal.h>
#include <stdio.h>
#include <unistd.h>
#include <linux/time64.h>
#include "util/debug.h"
#include "util/evsel.h"
#include "util/kwork.h"
#include <bpf/bpf.h>
#include <perf/cpumap.h>
#include "util/bpf_skel/kwork_top.skel.h"
/*
* This should be in sync with "util/kwork_top.bpf.c"
*/
#define MAX_COMMAND_LEN 16
struct time_data {
__u64 timestamp;
};
struct work_data {
__u64 runtime;
};
struct task_data {
__u32 tgid;
__u32 is_kthread;
char comm[MAX_COMMAND_LEN];
};
struct work_key {
__u32 type;
__u32 pid;
__u64 task_p;
};
struct task_key {
__u32 pid;
__u32 cpu;
};
struct kwork_class_bpf {
struct kwork_class *class;
void (*load_prepare)(void);
};
static struct kwork_top_bpf *skel;
void perf_kwork__top_start(void)
{
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
skel->bss->from_timestamp = (u64)ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec;
skel->bss->enabled = 1;
pr_debug("perf kwork top start at: %lld\n", skel->bss->from_timestamp);
}
void perf_kwork__top_finish(void)
{
struct timespec ts;
skel->bss->enabled = 0;
clock_gettime(CLOCK_MONOTONIC, &ts);
skel->bss->to_timestamp = (u64)ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec;
pr_debug("perf kwork top finish at: %lld\n", skel->bss->to_timestamp);
}
perf kwork top: Add BPF-based statistics on hardirq event support Use BPF to collect statistics on hardirq events based on perf BPF skeletons. Example usage: # perf kwork top -k sched,irq -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 136717.945 ms, 8 cpus %Cpu(s): 17.10% id, 0.01% hi, 0.00% si %Cpu0 [||||||||||||||||||||||||| 84.26%] %Cpu1 [||||||||||||||||||||||||| 84.77%] %Cpu2 [|||||||||||||||||||||||| 83.22%] %Cpu3 [|||||||||||||||||||||||| 80.37%] %Cpu4 [|||||||||||||||||||||||| 81.49%] %Cpu5 [||||||||||||||||||||||||| 84.68%] %Cpu6 [||||||||||||||||||||||||| 84.48%] %Cpu7 [|||||||||||||||||||||||| 80.21%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 19.78 3482.833 ms [swapper/7] 0 0 19.62 3454.219 ms [swapper/3] 0 0 18.50 3258.339 ms [swapper/4] 0 0 16.76 2842.749 ms [swapper/2] 0 0 15.71 2627.905 ms [swapper/0] 0 0 15.51 2598.206 ms [swapper/6] 0 0 15.31 2561.820 ms [swapper/5] 0 0 15.22 2548.708 ms [swapper/1] 13253 13018 2.95 513.108 ms sched-messaging 13092 13018 2.67 454.167 ms sched-messaging 13401 13018 2.66 454.790 ms sched-messaging 13240 13018 2.64 454.587 ms sched-messaging 13251 13018 2.61 442.273 ms sched-messaging 13075 13018 2.61 438.932 ms sched-messaging 13220 13018 2.60 443.245 ms sched-messaging 13235 13018 2.59 443.268 ms sched-messaging 13222 13018 2.50 426.344 ms sched-messaging 13410 13018 2.49 426.191 ms sched-messaging 13228 13018 2.46 425.121 ms sched-messaging 13379 13018 2.38 409.950 ms sched-messaging 13236 13018 2.37 413.159 ms sched-messaging 13095 13018 2.36 396.572 ms sched-messaging 13325 13018 2.35 408.089 ms sched-messaging 13242 13018 2.32 394.750 ms sched-messaging 13386 13018 2.31 396.997 ms sched-messaging 13046 13018 2.29 383.833 ms sched-messaging 13109 13018 2.28 388.482 ms sched-messaging 13388 13018 2.28 393.576 ms sched-messaging 13238 13018 2.26 388.487 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-16-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:16 -07:00
static void irq_load_prepare(void)
{
bpf_program__set_autoload(skel->progs.on_irq_handler_entry, true);
bpf_program__set_autoload(skel->progs.on_irq_handler_exit, true);
}
static struct kwork_class_bpf kwork_irq_bpf = {
.load_prepare = irq_load_prepare,
};
perf kwork top: Add BPF-based statistics on softirq event support Use BPF to collect statistics on softirq events based on perf BPF skeletons. Example usage: # perf kwork top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 135445.704 ms, 8 cpus %Cpu(s): 28.35% id, 0.00% hi, 0.25% si %Cpu0 [|||||||||||||||||||| 69.85%] %Cpu1 [|||||||||||||||||||||| 74.10%] %Cpu2 [||||||||||||||||||||| 71.18%] %Cpu3 [|||||||||||||||||||| 69.61%] %Cpu4 [|||||||||||||||||||||| 74.05%] %Cpu5 [|||||||||||||||||||| 69.33%] %Cpu6 [|||||||||||||||||||| 69.71%] %Cpu7 [|||||||||||||||||||||| 73.77%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 30.43 5271.005 ms [swapper/5] 0 0 30.17 5226.644 ms [swapper/3] 0 0 30.08 5210.257 ms [swapper/6] 0 0 29.89 5177.177 ms [swapper/0] 0 0 28.51 4938.672 ms [swapper/2] 0 0 25.93 4223.464 ms [swapper/7] 0 0 25.69 4181.411 ms [swapper/4] 0 0 25.63 4173.804 ms [swapper/1] 16665 16265 2.16 360.600 ms sched-messaging 16537 16265 2.05 356.275 ms sched-messaging 16503 16265 2.01 343.063 ms sched-messaging 16424 16265 1.97 336.876 ms sched-messaging 16580 16265 1.94 323.658 ms sched-messaging 16515 16265 1.92 321.616 ms sched-messaging 16659 16265 1.91 325.538 ms sched-messaging 16634 16265 1.88 327.766 ms sched-messaging 16454 16265 1.87 326.843 ms sched-messaging 16382 16265 1.87 322.591 ms sched-messaging 16642 16265 1.86 320.506 ms sched-messaging 16582 16265 1.86 320.164 ms sched-messaging 16315 16265 1.86 326.872 ms sched-messaging 16637 16265 1.85 323.766 ms sched-messaging 16506 16265 1.82 311.688 ms sched-messaging 16512 16265 1.81 304.643 ms sched-messaging 16560 16265 1.80 314.751 ms sched-messaging 16320 16265 1.80 313.405 ms sched-messaging 16442 16265 1.80 314.403 ms sched-messaging 16626 16265 1.78 295.380 ms sched-messaging 16600 16265 1.77 309.444 ms sched-messaging 16550 16265 1.76 301.161 ms sched-messaging 16525 16265 1.75 296.560 ms sched-messaging 16314 16265 1.75 298.338 ms sched-messaging 16595 16265 1.74 304.390 ms sched-messaging 16555 16265 1.74 287.564 ms sched-messaging 16520 16265 1.74 295.734 ms sched-messaging 16507 16265 1.73 293.956 ms sched-messaging 16593 16265 1.72 296.443 ms sched-messaging 16531 16265 1.72 299.950 ms sched-messaging 16281 16265 1.72 301.339 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-17-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:17 -07:00
static void softirq_load_prepare(void)
{
bpf_program__set_autoload(skel->progs.on_softirq_entry, true);
bpf_program__set_autoload(skel->progs.on_softirq_exit, true);
}
static struct kwork_class_bpf kwork_softirq_bpf = {
.load_prepare = softirq_load_prepare,
};
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
static void sched_load_prepare(void)
{
bpf_program__set_autoload(skel->progs.on_switch, true);
}
static struct kwork_class_bpf kwork_sched_bpf = {
.load_prepare = sched_load_prepare,
};
static struct kwork_class_bpf *
kwork_class_bpf_supported_list[KWORK_CLASS_MAX] = {
perf kwork top: Add BPF-based statistics on hardirq event support Use BPF to collect statistics on hardirq events based on perf BPF skeletons. Example usage: # perf kwork top -k sched,irq -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 136717.945 ms, 8 cpus %Cpu(s): 17.10% id, 0.01% hi, 0.00% si %Cpu0 [||||||||||||||||||||||||| 84.26%] %Cpu1 [||||||||||||||||||||||||| 84.77%] %Cpu2 [|||||||||||||||||||||||| 83.22%] %Cpu3 [|||||||||||||||||||||||| 80.37%] %Cpu4 [|||||||||||||||||||||||| 81.49%] %Cpu5 [||||||||||||||||||||||||| 84.68%] %Cpu6 [||||||||||||||||||||||||| 84.48%] %Cpu7 [|||||||||||||||||||||||| 80.21%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 19.78 3482.833 ms [swapper/7] 0 0 19.62 3454.219 ms [swapper/3] 0 0 18.50 3258.339 ms [swapper/4] 0 0 16.76 2842.749 ms [swapper/2] 0 0 15.71 2627.905 ms [swapper/0] 0 0 15.51 2598.206 ms [swapper/6] 0 0 15.31 2561.820 ms [swapper/5] 0 0 15.22 2548.708 ms [swapper/1] 13253 13018 2.95 513.108 ms sched-messaging 13092 13018 2.67 454.167 ms sched-messaging 13401 13018 2.66 454.790 ms sched-messaging 13240 13018 2.64 454.587 ms sched-messaging 13251 13018 2.61 442.273 ms sched-messaging 13075 13018 2.61 438.932 ms sched-messaging 13220 13018 2.60 443.245 ms sched-messaging 13235 13018 2.59 443.268 ms sched-messaging 13222 13018 2.50 426.344 ms sched-messaging 13410 13018 2.49 426.191 ms sched-messaging 13228 13018 2.46 425.121 ms sched-messaging 13379 13018 2.38 409.950 ms sched-messaging 13236 13018 2.37 413.159 ms sched-messaging 13095 13018 2.36 396.572 ms sched-messaging 13325 13018 2.35 408.089 ms sched-messaging 13242 13018 2.32 394.750 ms sched-messaging 13386 13018 2.31 396.997 ms sched-messaging 13046 13018 2.29 383.833 ms sched-messaging 13109 13018 2.28 388.482 ms sched-messaging 13388 13018 2.28 393.576 ms sched-messaging 13238 13018 2.26 388.487 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-16-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:16 -07:00
[KWORK_CLASS_IRQ] = &kwork_irq_bpf,
perf kwork top: Add BPF-based statistics on softirq event support Use BPF to collect statistics on softirq events based on perf BPF skeletons. Example usage: # perf kwork top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 135445.704 ms, 8 cpus %Cpu(s): 28.35% id, 0.00% hi, 0.25% si %Cpu0 [|||||||||||||||||||| 69.85%] %Cpu1 [|||||||||||||||||||||| 74.10%] %Cpu2 [||||||||||||||||||||| 71.18%] %Cpu3 [|||||||||||||||||||| 69.61%] %Cpu4 [|||||||||||||||||||||| 74.05%] %Cpu5 [|||||||||||||||||||| 69.33%] %Cpu6 [|||||||||||||||||||| 69.71%] %Cpu7 [|||||||||||||||||||||| 73.77%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 30.43 5271.005 ms [swapper/5] 0 0 30.17 5226.644 ms [swapper/3] 0 0 30.08 5210.257 ms [swapper/6] 0 0 29.89 5177.177 ms [swapper/0] 0 0 28.51 4938.672 ms [swapper/2] 0 0 25.93 4223.464 ms [swapper/7] 0 0 25.69 4181.411 ms [swapper/4] 0 0 25.63 4173.804 ms [swapper/1] 16665 16265 2.16 360.600 ms sched-messaging 16537 16265 2.05 356.275 ms sched-messaging 16503 16265 2.01 343.063 ms sched-messaging 16424 16265 1.97 336.876 ms sched-messaging 16580 16265 1.94 323.658 ms sched-messaging 16515 16265 1.92 321.616 ms sched-messaging 16659 16265 1.91 325.538 ms sched-messaging 16634 16265 1.88 327.766 ms sched-messaging 16454 16265 1.87 326.843 ms sched-messaging 16382 16265 1.87 322.591 ms sched-messaging 16642 16265 1.86 320.506 ms sched-messaging 16582 16265 1.86 320.164 ms sched-messaging 16315 16265 1.86 326.872 ms sched-messaging 16637 16265 1.85 323.766 ms sched-messaging 16506 16265 1.82 311.688 ms sched-messaging 16512 16265 1.81 304.643 ms sched-messaging 16560 16265 1.80 314.751 ms sched-messaging 16320 16265 1.80 313.405 ms sched-messaging 16442 16265 1.80 314.403 ms sched-messaging 16626 16265 1.78 295.380 ms sched-messaging 16600 16265 1.77 309.444 ms sched-messaging 16550 16265 1.76 301.161 ms sched-messaging 16525 16265 1.75 296.560 ms sched-messaging 16314 16265 1.75 298.338 ms sched-messaging 16595 16265 1.74 304.390 ms sched-messaging 16555 16265 1.74 287.564 ms sched-messaging 16520 16265 1.74 295.734 ms sched-messaging 16507 16265 1.73 293.956 ms sched-messaging 16593 16265 1.72 296.443 ms sched-messaging 16531 16265 1.72 299.950 ms sched-messaging 16281 16265 1.72 301.339 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-17-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:17 -07:00
[KWORK_CLASS_SOFTIRQ] = &kwork_softirq_bpf,
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
[KWORK_CLASS_SCHED] = &kwork_sched_bpf,
};
static bool valid_kwork_class_type(enum kwork_class_type type)
{
return type >= 0 && type < KWORK_CLASS_MAX;
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
}
static int setup_filters(struct perf_kwork *kwork)
{
if (kwork->cpu_list) {
perf cpumap: Use perf_cpu_map__for_each_cpu when possible Rather than manually iterating the CPU map, use perf_cpu_map__for_each_cpu(). When possible tidy local variables. Reviewed-by: James Clark <james.clark@arm.com> Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Ghiti <alexghiti@rivosinc.com> Cc: Andrew Jones <ajones@ventanamicro.com> Cc: André Almeida <andrealmeid@igalia.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paran Lee <p4ranlee@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: Yang Jihong <yangjihong1@huawei.com> Cc: Yang Li <yang.lee@linux.alibaba.com> Cc: Yanteng Si <siyanteng@loongson.cn> Link: https://lore.kernel.org/r/20240202234057.2085863-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-02-02 16:40:57 -07:00
int idx, nr_cpus, fd;
struct perf_cpu_map *map;
struct perf_cpu cpu;
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
fd = bpf_map__fd(skel->maps.kwork_top_cpu_filter);
if (fd < 0) {
pr_debug("Invalid cpu filter fd\n");
return -1;
}
map = perf_cpu_map__new(kwork->cpu_list);
if (!map) {
pr_debug("Invalid cpu_list\n");
return -1;
}
nr_cpus = libbpf_num_possible_cpus();
perf cpumap: Use perf_cpu_map__for_each_cpu when possible Rather than manually iterating the CPU map, use perf_cpu_map__for_each_cpu(). When possible tidy local variables. Reviewed-by: James Clark <james.clark@arm.com> Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Ghiti <alexghiti@rivosinc.com> Cc: Andrew Jones <ajones@ventanamicro.com> Cc: André Almeida <andrealmeid@igalia.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paran Lee <p4ranlee@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: Yang Jihong <yangjihong1@huawei.com> Cc: Yang Li <yang.lee@linux.alibaba.com> Cc: Yanteng Si <siyanteng@loongson.cn> Link: https://lore.kernel.org/r/20240202234057.2085863-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-02-02 16:40:57 -07:00
perf_cpu_map__for_each_cpu(cpu, idx, map) {
u8 val = 1;
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
if (cpu.cpu >= nr_cpus) {
perf_cpu_map__put(map);
pr_err("Requested cpu %d too large\n", cpu.cpu);
return -1;
}
bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY);
}
perf_cpu_map__put(map);
}
return 0;
}
perf kwork: Constify control data for BPF 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 kwork report --use-bpf Starting trace, Hit <Ctrl+C> to stop and report ^C Kwork Name | Cpu | Total Runtime | Count | Max runtime | Max runtime start | Max runtime end | -------------------------------------------------------------------------------------------------------------------------------- (w)intel_atomic_commit_work [ | 0009 | 18.680 ms | 2 | 18.553 ms | 362410.681580 s | 362410.700133 s | (w)pm_runtime_work | 0007 | 13.300 ms | 1 | 13.300 ms | 362410.254996 s | 362410.268295 s | (w)intel_atomic_commit_work [ | 0009 | 9.846 ms | 2 | 9.717 ms | 362410.172352 s | 362410.182069 s | (w)acpi_ec_event_processor | 0002 | 8.106 ms | 1 | 8.106 ms | 362410.463187 s | 362410.471293 s | (s)SCHED:7 | 0000 | 1.351 ms | 106 | 0.063 ms | 362410.658017 s | 362410.658080 s | i915:157 | 0008 | 0.994 ms | 13 | 0.361 ms | 362411.222125 s | 362411.222486 s | (s)SCHED:7 | 0001 | 0.703 ms | 98 | 0.047 ms | 362410.245004 s | 362410.245051 s | (s)SCHED:7 | 0005 | 0.674 ms | 42 | 0.074 ms | 362411.483039 s | 362411.483113 s | (s)NET_RX:3 | 0001 | 0.556 ms | 10 | 0.079 ms | 362411.066388 s | 362411.066467 s | <SNIP> root@x1:~# perf trace -e bpf --max-events 5 perf kwork report --use-bpf 0.000 ( 0.016 ms): perf/2948007 bpf(cmd: 36, uattr: 0x7ffededa6660, size: 8) = -1 EOPNOTSUPP (Operation not supported) 0.026 ( 0.106 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6390, size: 148) = 12 0.152 ( 0.032 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6450, size: 148) = 12 26.247 ( 0.138 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6300, size: 148) = 12 26.396 ( 0.012 ms): perf/2948007 bpf(uattr: 0x7ffededa64b0, size: 80) = 12 Starting trace, Hit <Ctrl+C> to stop and report 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> Cc: Yang Jihong <yangjihong@bytedance.com> Link: https://lore.kernel.org/r/20240902200515.2103769-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-09-02 13:05:13 -07:00
int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork)
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
{
struct bpf_program *prog;
struct kwork_class *class;
struct kwork_class_bpf *class_bpf;
enum kwork_class_type type;
skel = kwork_top_bpf__open();
if (!skel) {
pr_debug("Failed to open kwork top skeleton\n");
return -1;
}
/*
* set all progs to non-autoload,
* then set corresponding progs according to config
*/
bpf_object__for_each_program(prog, skel->obj)
bpf_program__set_autoload(prog, false);
list_for_each_entry(class, &kwork->class_list, list) {
type = class->type;
if (!valid_kwork_class_type(type) ||
!kwork_class_bpf_supported_list[type]) {
pr_err("Unsupported bpf trace class %s\n", class->name);
goto out;
}
class_bpf = kwork_class_bpf_supported_list[type];
class_bpf->class = class;
if (class_bpf->load_prepare)
class_bpf->load_prepare();
}
perf kwork: Constify control data for BPF 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 kwork report --use-bpf Starting trace, Hit <Ctrl+C> to stop and report ^C Kwork Name | Cpu | Total Runtime | Count | Max runtime | Max runtime start | Max runtime end | -------------------------------------------------------------------------------------------------------------------------------- (w)intel_atomic_commit_work [ | 0009 | 18.680 ms | 2 | 18.553 ms | 362410.681580 s | 362410.700133 s | (w)pm_runtime_work | 0007 | 13.300 ms | 1 | 13.300 ms | 362410.254996 s | 362410.268295 s | (w)intel_atomic_commit_work [ | 0009 | 9.846 ms | 2 | 9.717 ms | 362410.172352 s | 362410.182069 s | (w)acpi_ec_event_processor | 0002 | 8.106 ms | 1 | 8.106 ms | 362410.463187 s | 362410.471293 s | (s)SCHED:7 | 0000 | 1.351 ms | 106 | 0.063 ms | 362410.658017 s | 362410.658080 s | i915:157 | 0008 | 0.994 ms | 13 | 0.361 ms | 362411.222125 s | 362411.222486 s | (s)SCHED:7 | 0001 | 0.703 ms | 98 | 0.047 ms | 362410.245004 s | 362410.245051 s | (s)SCHED:7 | 0005 | 0.674 ms | 42 | 0.074 ms | 362411.483039 s | 362411.483113 s | (s)NET_RX:3 | 0001 | 0.556 ms | 10 | 0.079 ms | 362411.066388 s | 362411.066467 s | <SNIP> root@x1:~# perf trace -e bpf --max-events 5 perf kwork report --use-bpf 0.000 ( 0.016 ms): perf/2948007 bpf(cmd: 36, uattr: 0x7ffededa6660, size: 8) = -1 EOPNOTSUPP (Operation not supported) 0.026 ( 0.106 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6390, size: 148) = 12 0.152 ( 0.032 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6450, size: 148) = 12 26.247 ( 0.138 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6300, size: 148) = 12 26.396 ( 0.012 ms): perf/2948007 bpf(uattr: 0x7ffededa64b0, size: 80) = 12 Starting trace, Hit <Ctrl+C> to stop and report 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> Cc: Yang Jihong <yangjihong@bytedance.com> Link: https://lore.kernel.org/r/20240902200515.2103769-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-09-02 13:05:13 -07:00
if (kwork->cpu_list)
skel->rodata->has_cpu_filter = 1;
perf kwork top: Implements BPF-based cpu usage statistics Use BPF to collect statistics on the CPU usage based on perf BPF skeletons. Example usage: # perf kwork top -h Usage: perf kwork top [<options>] -b, --use-bpf Use BPF to measure task cpu usage -C, --cpu <cpu> list of cpus to profile -i, --input <file> input file name -n, --name <name> event name to profile -s, --sort <key[,key2...]> sort by key(s): rate, runtime, tid --time <str> Time span for analysis (start,stop) # # perf kwork -k sched top -b Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 160702.425 ms, 8 cpus %Cpu(s): 36.00% id, 0.00% hi, 0.00% si %Cpu0 [|||||||||||||||||| 61.66%] %Cpu1 [|||||||||||||||||| 61.27%] %Cpu2 [||||||||||||||||||| 66.40%] %Cpu3 [|||||||||||||||||| 61.28%] %Cpu4 [|||||||||||||||||| 61.82%] %Cpu5 [||||||||||||||||||||||| 77.41%] %Cpu6 [|||||||||||||||||| 61.73%] %Cpu7 [|||||||||||||||||| 63.25%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 38.72 8089.463 ms [swapper/1] 0 0 38.71 8084.547 ms [swapper/3] 0 0 38.33 8007.532 ms [swapper/0] 0 0 38.26 7992.985 ms [swapper/6] 0 0 38.17 7971.865 ms [swapper/4] 0 0 36.74 7447.765 ms [swapper/7] 0 0 33.59 6486.942 ms [swapper/2] 0 0 22.58 3771.268 ms [swapper/5] 9545 9351 2.48 447.136 ms sched-messaging 9574 9351 2.09 418.583 ms sched-messaging 9724 9351 2.05 372.407 ms sched-messaging 9531 9351 2.01 368.804 ms sched-messaging 9512 9351 2.00 362.250 ms sched-messaging 9514 9351 1.95 357.767 ms sched-messaging 9538 9351 1.86 384.476 ms sched-messaging 9712 9351 1.84 386.490 ms sched-messaging 9723 9351 1.83 380.021 ms sched-messaging 9722 9351 1.82 382.738 ms sched-messaging 9517 9351 1.81 354.794 ms sched-messaging 9559 9351 1.79 344.305 ms sched-messaging 9725 9351 1.77 365.315 ms sched-messaging <SNIP> # perf kwork -k sched top -b -n perf Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 151563.332 ms, 8 cpus %Cpu(s): 26.49% id, 0.00% hi, 0.00% si %Cpu0 [ 0.01%] %Cpu1 [ 0.00%] %Cpu2 [ 0.00%] %Cpu3 [ 0.00%] %Cpu4 [ 0.00%] %Cpu5 [ 0.00%] %Cpu6 [ 0.00%] %Cpu7 [ 0.00%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 9754 9754 0.01 2.303 ms perf # # perf kwork -k sched top -b -C 2,3,4 Starting trace, Hit <Ctrl+C> to stop and report ^C Total : 48016.721 ms, 3 cpus %Cpu(s): 27.82% id, 0.00% hi, 0.00% si %Cpu2 [|||||||||||||||||||||| 74.68%] %Cpu3 [||||||||||||||||||||| 71.06%] %Cpu4 [||||||||||||||||||||| 70.91%] PID SPID %CPU RUNTIME COMMMAND ------------------------------------------------------------- 0 0 29.08 4734.998 ms [swapper/4] 0 0 28.93 4710.029 ms [swapper/3] 0 0 25.31 3912.363 ms [swapper/2] 10248 10158 1.62 264.931 ms sched-messaging 10253 10158 1.62 265.136 ms sched-messaging 10158 10158 1.60 263.013 ms bash 10360 10158 1.49 243.639 ms sched-messaging 10413 10158 1.48 238.604 ms sched-messaging 10531 10158 1.47 234.067 ms sched-messaging 10400 10158 1.47 240.631 ms sched-messaging 10355 10158 1.47 230.586 ms sched-messaging 10377 10158 1.43 234.835 ms sched-messaging 10526 10158 1.42 232.045 ms sched-messaging 10298 10158 1.41 222.396 ms sched-messaging 10410 10158 1.38 221.853 ms sched-messaging 10364 10158 1.38 226.042 ms sched-messaging 10480 10158 1.36 213.633 ms sched-messaging 10370 10158 1.36 223.620 ms sched-messaging 10553 10158 1.34 217.169 ms sched-messaging 10291 10158 1.34 211.516 ms sched-messaging 10251 10158 1.34 218.813 ms sched-messaging 10522 10158 1.33 218.498 ms sched-messaging 10288 10158 1.33 216.787 ms sched-messaging <SNIP> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-08-12 01:49:15 -07:00
if (kwork_top_bpf__load(skel)) {
pr_debug("Failed to load kwork top skeleton\n");
goto out;
}
if (setup_filters(kwork))
goto out;
if (kwork_top_bpf__attach(skel)) {
pr_debug("Failed to attach kwork top skeleton\n");
goto out;
}
return 0;
out:
kwork_top_bpf__destroy(skel);
return -1;
}
static void read_task_info(struct kwork_work *work)
{
int fd;
struct task_data data;
struct task_key key = {
.pid = work->id,
.cpu = work->cpu,
};
fd = bpf_map__fd(skel->maps.kwork_top_tasks);
if (fd < 0) {
pr_debug("Invalid top tasks map fd\n");
return;
}
if (!bpf_map_lookup_elem(fd, &key, &data)) {
work->tgid = data.tgid;
work->is_kthread = data.is_kthread;
work->name = strdup(data.comm);
}
}
static int add_work(struct perf_kwork *kwork, struct work_key *key,
struct work_data *data, int cpu)
{
struct kwork_class_bpf *bpf_trace;
struct kwork_work *work;
struct kwork_work tmp = {
.id = key->pid,
.cpu = cpu,
.name = NULL,
};
enum kwork_class_type type = key->type;
if (!valid_kwork_class_type(type)) {
pr_debug("Invalid class type %d to add work\n", type);
return -1;
}
bpf_trace = kwork_class_bpf_supported_list[type];
tmp.class = bpf_trace->class;
work = perf_kwork_add_work(kwork, tmp.class, &tmp);
if (!work)
return -1;
work->total_runtime = data->runtime;
read_task_info(work);
return 0;
}
int perf_kwork__top_read_bpf(struct perf_kwork *kwork)
{
int i, fd, nr_cpus;
struct work_data *data;
struct work_key key, prev;
fd = bpf_map__fd(skel->maps.kwork_top_works);
if (fd < 0) {
pr_debug("Invalid top runtime fd\n");
return -1;
}
nr_cpus = libbpf_num_possible_cpus();
data = calloc(nr_cpus, sizeof(struct work_data));
if (!data)
return -1;
memset(&prev, 0, sizeof(prev));
while (!bpf_map_get_next_key(fd, &prev, &key)) {
if ((bpf_map_lookup_elem(fd, &key, data)) != 0) {
pr_debug("Failed to lookup top elem\n");
return -1;
}
for (i = 0; i < nr_cpus; i++) {
if (data[i].runtime == 0)
continue;
if (add_work(kwork, &key, &data[i], i))
return -1;
}
prev = key;
}
free(data);
return 0;
}
void perf_kwork__top_cleanup_bpf(void)
{
kwork_top_bpf__destroy(skel);
}