perf record --off-cpu: Dump the remaining PERF_SAMPLE_ in sample_type from BPF's...

Dump the remaining PERF_SAMPLE_ data, as if it is dumping a direct
sample.

Put the stack trace, tid, off-cpu time and cgroup id into the raw_data
section, just like a direct off-cpu sample coming from BPF's
bpf_perf_event_output().

This ensures that evsel__parse_sample() correctly parses both direct
samples and accumulated samples.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
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/20241108204137.2444151-10-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20250501022809.449767-9-howardchu95@gmail.com
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 1975a02c16830d5c2be13bec4dd2cea28297243c..c7fde66bb8f951294a85b1eb822eab0fb236cf7f 100644 (file)
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -37,6 +37,8 @@ union off_cpu_data {
        u64 array[1024 / sizeof(u64)];
 };
 
+u64 off_cpu_raw[MAX_STACKS + 5];
+
 static int off_cpu_config(struct evlist *evlist)
 {
        char off_cpu_event[64];
@@ -313,6 +315,7 @@ int off_cpu_write(struct perf_session *session)
 {
        int bytes = 0, size;
        int fd, stack;
+       u32 raw_size;
        u64 sample_type, val, sid = 0;
        struct evsel *evsel;
        struct perf_data_file *file = &session->data->file;
@@ -352,46 +355,54 @@ int off_cpu_write(struct perf_session *session)
 
        while (!bpf_map_get_next_key(fd, &prev, &key)) {
                int n = 1;  /* start from perf_event_header */
-               int ip_pos = -1;
 
                bpf_map_lookup_elem(fd, &key, &val);
 
+               /* zero-fill some of the fields, will be overwritten by raw_data when parsing */
                if (sample_type & PERF_SAMPLE_IDENTIFIER)
                        data.array[n++] = sid;
-               if (sample_type & PERF_SAMPLE_IP) {
-                       ip_pos = n;
+               if (sample_type & PERF_SAMPLE_IP)
                        data.array[n++] = 0;  /* will be updated */
-               }
                if (sample_type & PERF_SAMPLE_TID)
-                       data.array[n++] = (u64)key.pid << 32 | key.tgid;
+                       data.array[n++] = 0;
                if (sample_type & PERF_SAMPLE_TIME)
                        data.array[n++] = tstamp;
-               if (sample_type & PERF_SAMPLE_ID)
-                       data.array[n++] = sid;
                if (sample_type & PERF_SAMPLE_CPU)
                        data.array[n++] = 0;
                if (sample_type & PERF_SAMPLE_PERIOD)
-                       data.array[n++] = val;
-               if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-                       int len = 0;
-
-                       /* data.array[n] is callchain->nr (updated later) */
-                       data.array[n + 1] = PERF_CONTEXT_USER;
-                       data.array[n + 2] = 0;
-
-                       bpf_map_lookup_elem(stack, &key.stack_id, &data.array[n + 2]);
-                       while (data.array[n + 2 + len])
+                       data.array[n++] = 0;
+               if (sample_type & PERF_SAMPLE_RAW) {
+                       /*
+                        *  [ size ][ data ]
+                        *  [     data     ]
+                        *  [     data     ]
+                        *  [     data     ]
+                        *  [ data ][ empty]
+                        */
+                       int len = 0, i = 0;
+                       void *raw_data = (void *)data.array + n * sizeof(u64);
+
+                       off_cpu_raw[i++] = (u64)key.pid << 32 | key.tgid;
+                       off_cpu_raw[i++] = val;
+
+                       /* off_cpu_raw[i] is callchain->nr (updated later) */
+                       off_cpu_raw[i + 1] = PERF_CONTEXT_USER;
+                       off_cpu_raw[i + 2] = 0;
+
+                       bpf_map_lookup_elem(stack, &key.stack_id, &off_cpu_raw[i + 2]);
+                       while (off_cpu_raw[i + 2 + len])
                                len++;
 
-                       /* update length of callchain */
-                       data.array[n] = len + 1;
+                       off_cpu_raw[i] = len + 1;
+                       i += len + 2;
+
+                       off_cpu_raw[i++] = key.cgroup_id;
 
-                       /* update sample ip with the first callchain entry */
-                       if (ip_pos >= 0)
-                               data.array[ip_pos] = data.array[n + 2];
+                       raw_size = i * sizeof(u64) + sizeof(u32); /* 4 bytes for alignment */
+                       memcpy(raw_data, &raw_size, sizeof(raw_size));
+                       memcpy(raw_data + sizeof(u32), off_cpu_raw, i * sizeof(u64));
 
-                       /* calculate sample callchain data array length */
-                       n += len + 2;
+                       n += i + 1;
                }
                if (sample_type & PERF_SAMPLE_CGROUP)
                        data.array[n++] = key.cgroup_id;