perf record --off-cpu: Preparation of off-cpu BPF program

Set the perf_event map in BPF for dumping off-cpu samples, and set the
offcpu_thresh to specify the threshold.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Gautam Menghani <gautam@linux.ibm.com>
Tested-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: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241108204137.2444151-5-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20250501022809.449767-4-howardchu95@gmail.com
[ Added some missing iteration variables to off_cpu_config() and fixed up
  a manually edited patch hunk line boundary line ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 2101aa2b7c4270f85cba456d6f672c01a56eaf6d..1975a02c16830d5c2be13bec4dd2cea28297243c 100644 (file)
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -13,6 +13,7 @@
 #include "util/cgroup.h"
 #include "util/strlist.h"
 #include <bpf/bpf.h>
+#include <internal/xyarray.h>
 
 #include "bpf_skel/off_cpu.skel.h"
 
@@ -60,6 +61,9 @@ static int off_cpu_config(struct evlist *evlist)
 static void off_cpu_start(void *arg)
 {
        struct evlist *evlist = arg;
+       struct evsel *evsel;
+       struct perf_cpu pcpu;
+       int i;
 
        /* update task filter for the given workload */
        if (skel->rodata->has_task && skel->rodata->uses_tgid &&
@@ -73,6 +77,26 @@ static void off_cpu_start(void *arg)
                bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
        }
 
+       /* update BPF perf_event map */
+       evsel = evlist__find_evsel_by_str(evlist, OFFCPU_EVENT);
+       if (evsel == NULL) {
+               pr_err("%s evsel not found\n", OFFCPU_EVENT);
+               return;
+       }
+
+       perf_cpu_map__for_each_cpu(pcpu, i, evsel->core.cpus) {
+               int err;
+               int cpu_nr = pcpu.cpu;
+
+               err = bpf_map__update_elem(skel->maps.offcpu_output, &cpu_nr, sizeof(int),
+                                          xyarray__entry(evsel->core.fd, cpu_nr, 0),
+                                          sizeof(int), BPF_ANY);
+               if (err) {
+                       pr_err("Failed to update perf event map for direct off-cpu dumping\n");
+                       return;
+               }
+       }
+
        skel->bss->enabled = 1;
 }
 

diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c152116df72f9bc19bbd70d45ecf8115de03afa3..a5002e25b2593e4ba8332fcc316ea6d62dcd51cf 100644 (file)
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -18,6 +18,8 @@
 #define MAX_STACKS   32
 #define MAX_ENTRIES  102400
 
+#define MAX_CPUS  4096
+
 struct tstamp_data {
        __u32 stack_id;
        __u32 state;
@@ -39,6 +41,13 @@ struct {
        __uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
+struct {
+       __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+       __uint(key_size, sizeof(int));
+       __uint(value_size, sizeof(int));
+       __uint(max_entries, MAX_CPUS);
+} offcpu_output SEC(".maps");
+
 struct {
        __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
        __uint(map_flags, BPF_F_NO_PREALLOC);