linux-kernel - [PATCH v7 09/10] perf record --off-cpu: Dump the remaining samples in BPF's stack trace map

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20241108204137.2444151-10-howardchu95@gmail.com>
Date: Fri,  8 Nov 2024 12:41:36 -0800
From: Howard Chu <howardchu95@...il.com>
To: acme@...nel.org,
	peterz@...radead.org
Cc: namhyung@...nel.org,
	irogers@...gle.com,
	mingo@...hat.com,
	mark.rutland@....com,
	james.clark@...aro.org,
	alexander.shishkin@...ux.intel.com,
	jolsa@...nel.org,
	adrian.hunter@...el.com,
	kan.liang@...ux.intel.com,
	linux-perf-users@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Howard Chu <howardchu95@...il.com>
Subject: [PATCH v7 09/10] perf record --off-cpu: Dump the remaining samples in BPF's stack trace map

Dump the remaining samples, 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@...nel.org>
Signed-off-by: Howard Chu <howardchu95@...il.com>
---
 tools/perf/util/bpf_off_cpu.c | 62 +++++++++++++++++++++--------------
 1 file changed, 38 insertions(+), 24 deletions(-)

diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index cfe5b17393e9..f1be354e2fe7 100644
--- 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];
@@ -61,6 +63,9 @@ 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, err;
 
 	/* update task filter for the given workload */
 	if (skel->rodata->has_task && skel->rodata->uses_tgid &&
@@ -304,6 +309,7 @@ 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;
@@ -343,46 +349,54 @@ 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;
-- 
2.43.0