1 files changed, 150 insertions, 10 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 23332861de6e..b5063d3b6fd0 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -55,6 +55,9 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include <linux/time64.h>
@@ -91,8 +94,11 @@ struct record {
 	struct switch_output	switch_output;
 	unsigned long long	samples;
 	cpu_set_t		affinity_mask;
+	unsigned long		output_max_size;	/* = 0: unlimited */
 };
 
+static volatile int done;
+
 static volatile int auxtrace_record__snapshot_started;
 static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
 static DEFINE_TRIGGER(switch_output_trigger);
@@ -120,6 +126,12 @@ static bool switch_output_time(struct record *rec)
 	       trigger_is_ready(&switch_output_trigger);
 }
 
+static bool record__output_max_size_exceeded(struct record *rec)
+{
+	return rec->output_max_size &&
+	       (rec->bytes_written >= rec->output_max_size);
+}
+
 static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 			 void *bf, size_t size)
 {
@@ -132,6 +144,13 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 
 	rec->bytes_written += size;
 
+	if (record__output_max_size_exceeded(rec) && !done) {
+		fprintf(stderr, "[ perf record: perf size limit reached (%" PRIu64 " KB),"
+				" stopping session ]\n",
+				rec->bytes_written >> 10);
+		done = 1;
+	}
+
 	if (switch_output_size(rec))
 		trigger_hit(&switch_output_trigger);
 
@@ -197,7 +216,7 @@ static int record__aio_complete(struct mmap *md, struct aiocb *cblock)
 		 * every aio write request started in record__aio_push() so
 		 * decrement it because the request is now complete.
 		 */
-		perf_mmap__put(md);
+		perf_mmap__put(&md->core);
 		rc = 1;
 	} else {
 		/*
@@ -276,7 +295,7 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 
 	if (record__comp_enabled(aio->rec)) {
 		size = zstd_compress(aio->rec->session, aio->data + aio->size,
-				     perf_mmap__mmap_len(map) - aio->size,
+				     mmap__mmap_len(map) - aio->size,
 				     buf, size);
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
@@ -293,7 +312,7 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 		 * after started aio request completion or at record__aio_push()
 		 * if the request failed to start.
 		 */
-		perf_mmap__get(map);
+		perf_mmap__get(&map->core);
 	}
 
 	aio->size += size;
@@ -332,7 +351,7 @@ static int record__aio_push(struct record *rec, struct mmap *map, off_t *off)
 		 * map->refcount is decremented in record__aio_complete() after
 		 * aio write operation finishes successfully.
 		 */
-		perf_mmap__put(map);
+		perf_mmap__put(&map->core);
 	}
 
 	return ret;
@@ -488,7 +507,7 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
-		size = zstd_compress(rec->session, map->data, perf_mmap__mmap_len(map), bf, size);
+		size = zstd_compress(rec->session, map->data, mmap__mmap_len(map), bf, size);
 		bf   = map->data;
 	}
 
@@ -496,7 +515,6 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	return record__write(rec, map, bf, size);
 }
 
-static volatile int done;
 static volatile int signr = -1;
 static volatile int child_finished;
 
@@ -537,7 +555,7 @@ static int record__process_auxtrace(struct perf_tool *tool,
 	size_t padding;
 	u8 pad[8] = {0};
 
-	if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) {
+	if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) {
 		off_t file_offset;
 		int fd = perf_data__fd(data);
 		int err;
@@ -662,6 +680,11 @@ static int record__auxtrace_init(struct record *rec)
 	if (err)
 		return err;
 
+	err = auxtrace_parse_sample_options(rec->itr, rec->evlist, &rec->opts,
+					    rec->opts.auxtrace_sample_opts);
+	if (err)
+		return err;
+
 	return auxtrace_parse_filters(rec->evlist);
 }
 
@@ -699,10 +722,43 @@ static int record__auxtrace_init(struct record *rec __maybe_unused)
 
 #endif
 
+static bool record__kcore_readable(struct machine *machine)
+{
+	char kcore[PATH_MAX];
+	int fd;
+
+	scnprintf(kcore, sizeof(kcore), "%s/proc/kcore", machine->root_dir);
+
+	fd = open(kcore, O_RDONLY);
+	if (fd < 0)
+		return false;
+
+	close(fd);
+
+	return true;
+}
+
+static int record__kcore_copy(struct machine *machine, struct perf_data *data)
+{
+	char from_dir[PATH_MAX];
+	char kcore_dir[PATH_MAX];
+	int ret;
+
+	snprintf(from_dir, sizeof(from_dir), "%s/proc", machine->root_dir);
+
+	ret = perf_data__make_kcore_dir(data, kcore_dir, sizeof(kcore_dir));
+	if (ret)
+		return ret;
+
+	return kcore_copy(from_dir, kcore_dir);
+}
+
 static int record__mmap_evlist(struct record *rec,
 			       struct evlist *evlist)
 {
 	struct record_opts *opts = &rec->opts;
+	bool auxtrace_overwrite = opts->auxtrace_snapshot_mode ||
+				  opts->auxtrace_sample_mode;
 	char msg[512];
 
 	if (opts->affinity != PERF_AFFINITY_SYS)
@@ -710,7 +766,7 @@ static int record__mmap_evlist(struct record *rec,
 
 	if (evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
-				 opts->auxtrace_snapshot_mode,
+				 auxtrace_overwrite,
 				 opts->nr_cblocks, opts->affinity,
 				 opts->mmap_flush, opts->comp_level) < 0) {
 		if (errno == EPERM) {
@@ -997,6 +1053,7 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
 		}
 
 		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
+		    !rec->opts.auxtrace_sample_mode &&
 		    record__auxtrace_mmap_read(rec, map) != 0) {
 			rc = -1;
 			goto out;
@@ -1272,6 +1329,15 @@ static int record__synthesize(struct record *rec, bool tail)
 	if (err)
 		goto out;
 
+	/* Synthesize id_index before auxtrace_info */
+	if (rec->opts.auxtrace_sample_mode) {
+		err = perf_event__synthesize_id_index(tool,
+						      process_synthesized_event,
+						      session->evlist, machine);
+		if (err)
+			goto out;
+	}
+
 	if (rec->opts.full_auxtrace) {
 		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
 					session, process_synthesized_event);
@@ -1383,6 +1449,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	session->header.env.comp_type  = PERF_COMP_ZSTD;
 	session->header.env.comp_level = rec->opts.comp_level;
 
+	if (rec->opts.kcore &&
+	    !record__kcore_readable(&session->machines.host)) {
+		pr_err("ERROR: kcore is not readable.\n");
+		return -1;
+	}
+
 	record__init_features(rec);
 
 	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
@@ -1414,6 +1486,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 	session->header.env.comp_mmap_len = session->evlist->core.mmap_len;
 
+	if (rec->opts.kcore) {
+		err = record__kcore_copy(&session->machines.host, data);
+		if (err) {
+			pr_err("ERROR: Failed to copy kcore\n");
+			goto out_child;
+		}
+	}
+
 	err = bpf__apply_obj_config();
 	if (err) {
 		char errbuf[BUFSIZ];
@@ -1936,6 +2016,33 @@ static int record__parse_affinity(const struct option *opt, const char *str, int
 	return 0;
 }
 
+static int parse_output_max_size(const struct option *opt,
+				 const char *str, int unset)
+{
+	unsigned long *s = (unsigned long *)opt->value;
+	static struct parse_tag tags_size[] = {
+		{ .tag  = 'B', .mult = 1       },
+		{ .tag  = 'K', .mult = 1 << 10 },
+		{ .tag  = 'M', .mult = 1 << 20 },
+		{ .tag  = 'G', .mult = 1 << 30 },
+		{ .tag  = 0 },
+	};
+	unsigned long val;
+
+	if (unset) {
+		*s = 0;
+		return 0;
+	}
+
+	val = parse_tag_value(str, tags_size);
+	if (val != (unsigned long) -1) {
+		*s = val;
+		return 0;
+	}
+
+	return -1;
+}
+
 static int record__parse_mmap_pages(const struct option *opt,
 				    const char *str,
 				    int unset __maybe_unused)
@@ -2058,6 +2165,31 @@ static const char * const __record_usage[] = {
 };
 const char * const *record_usage = __record_usage;
 
+static int build_id__process_mmap(struct perf_tool *tool, union perf_event *event,
+				  struct perf_sample *sample, struct machine *machine)
+{
+	/*
+	 * We already have the kernel maps, put in place via perf_session__create_kernel_maps()
+	 * no need to add them twice.
+	 */
+	if (!(event->header.misc & PERF_RECORD_MISC_USER))
+		return 0;
+	return perf_event__process_mmap(tool, event, sample, machine);
+}
+
+static int build_id__process_mmap2(struct perf_tool *tool, union perf_event *event,
+				   struct perf_sample *sample, struct machine *machine)
+{
+	/*
+	 * We already have the kernel maps, put in place via perf_session__create_kernel_maps()
+	 * no need to add them twice.
+	 */
+	if (!(event->header.misc & PERF_RECORD_MISC_USER))
+		return 0;
+
+	return perf_event__process_mmap2(tool, event, sample, machine);
+}
+
 /*
  * XXX Ideally would be local to cmd_record() and passed to a record__new
  * because we need to have access to it in record__exit, that is called
@@ -2087,8 +2219,8 @@ static struct record record = {
 		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
 		.namespaces	= perf_event__process_namespaces,
-		.mmap		= perf_event__process_mmap,
-		.mmap2		= perf_event__process_mmap2,
+		.mmap		= build_id__process_mmap,
+		.mmap2		= build_id__process_mmap2,
 		.ordered_events	= true,
 	},
 };
@@ -2184,6 +2316,7 @@ static struct option __record_options[] = {
 		     parse_cgroups),
 	OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
 		  "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"),
 	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
 		   "user to profile"),
 
@@ -2213,6 +2346,8 @@ static struct option __record_options[] = {
 	parse_clockid),
 	OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
 			  "opts", "AUX area tracing Snapshot Mode", ""),
+	OPT_STRING_OPTARG(0, "aux-sample", &record.opts.auxtrace_sample_opts,
+			  "opts", "sample AUX area", ""),
 	OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
@@ -2262,6 +2397,8 @@ static struct option __record_options[] = {
 			    "n", "Compressed records using specified level (default: 1 - fastest compression, 22 - greatest compression)",
 			    record__parse_comp_level),
 #endif
+	OPT_CALLBACK(0, "max-size", &record.output_max_size,
+		     "size", "Limit the maximum size of the output file", parse_output_max_size),
 	OPT_END()
 };
 
@@ -2322,6 +2459,9 @@ int cmd_record(int argc, const char **argv)
 
 	}
 
+	if (rec->opts.kcore)
+		rec->data.is_dir = true;
+
 	if (rec->opts.comp_level != 0) {
 		pr_debug("Compression enabled, disabling build id collection at the end of the session.\n");
 		rec->no_buildid = true;