1 files changed, 338 insertions, 28 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0980dfe3396b..f3f7f3100336 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -23,7 +23,6 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
-#include "util/drv_configs.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/symbol.h"
@@ -39,8 +38,10 @@
 #include "util/bpf-loader.h"
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
+#include "util/cpu-set-sched.h"
 #include "util/time-utils.h"
 #include "util/units.h"
+#include "util/bpf-event.h"
 #include "asm/bug.h"
 
 #include <errno.h>
@@ -81,12 +82,17 @@ struct record {
 	bool			timestamp_boundary;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
+	cpu_set_t		affinity_mask;
 };
 
 static volatile int auxtrace_record__snapshot_started;
 static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
 static DEFINE_TRIGGER(switch_output_trigger);
 
+static const char *affinity_tags[PERF_AFFINITY_MAX] = {
+	"SYS", "NODE", "CPU"
+};
+
 static bool switch_output_signal(struct record *rec)
 {
 	return rec->switch_output.signal &&
@@ -124,6 +130,210 @@ static int record__write(struct record *rec, struct perf_mmap *map __maybe_unuse
 	return 0;
 }
 
+#ifdef HAVE_AIO_SUPPORT
+static int record__aio_write(struct aiocb *cblock, int trace_fd,
+		void *buf, size_t size, off_t off)
+{
+	int rc;
+
+	cblock->aio_fildes = trace_fd;
+	cblock->aio_buf    = buf;
+	cblock->aio_nbytes = size;
+	cblock->aio_offset = off;
+	cblock->aio_sigevent.sigev_notify = SIGEV_NONE;
+
+	do {
+		rc = aio_write(cblock);
+		if (rc == 0) {
+			break;
+		} else if (errno != EAGAIN) {
+			cblock->aio_fildes = -1;
+			pr_err("failed to queue perf data, error: %m\n");
+			break;
+		}
+	} while (1);
+
+	return rc;
+}
+
+static int record__aio_complete(struct perf_mmap *md, struct aiocb *cblock)
+{
+	void *rem_buf;
+	off_t rem_off;
+	size_t rem_size;
+	int rc, aio_errno;
+	ssize_t aio_ret, written;
+
+	aio_errno = aio_error(cblock);
+	if (aio_errno == EINPROGRESS)
+		return 0;
+
+	written = aio_ret = aio_return(cblock);
+	if (aio_ret < 0) {
+		if (aio_errno != EINTR)
+			pr_err("failed to write perf data, error: %m\n");
+		written = 0;
+	}
+
+	rem_size = cblock->aio_nbytes - written;
+
+	if (rem_size == 0) {
+		cblock->aio_fildes = -1;
+		/*
+		 * md->refcount is incremented in perf_mmap__push() for
+		 * every enqueued aio write request so decrement it because
+		 * the request is now complete.
+		 */
+		perf_mmap__put(md);
+		rc = 1;
+	} else {
+		/*
+		 * aio write request may require restart with the
+		 * reminder if the kernel didn't write whole
+		 * chunk at once.
+		 */
+		rem_off = cblock->aio_offset + written;
+		rem_buf = (void *)(cblock->aio_buf + written);
+		record__aio_write(cblock, cblock->aio_fildes,
+				rem_buf, rem_size, rem_off);
+		rc = 0;
+	}
+
+	return rc;
+}
+
+static int record__aio_sync(struct perf_mmap *md, bool sync_all)
+{
+	struct aiocb **aiocb = md->aio.aiocb;
+	struct aiocb *cblocks = md->aio.cblocks;
+	struct timespec timeout = { 0, 1000 * 1000  * 1 }; /* 1ms */
+	int i, do_suspend;
+
+	do {
+		do_suspend = 0;
+		for (i = 0; i < md->aio.nr_cblocks; ++i) {
+			if (cblocks[i].aio_fildes == -1 || record__aio_complete(md, &cblocks[i])) {
+				if (sync_all)
+					aiocb[i] = NULL;
+				else
+					return i;
+			} else {
+				/*
+				 * Started aio write is not complete yet
+				 * so it has to be waited before the
+				 * next allocation.
+				 */
+				aiocb[i] = &cblocks[i];
+				do_suspend = 1;
+			}
+		}
+		if (!do_suspend)
+			return -1;
+
+		while (aio_suspend((const struct aiocb **)aiocb, md->aio.nr_cblocks, &timeout)) {
+			if (!(errno == EAGAIN || errno == EINTR))
+				pr_err("failed to sync perf data, error: %m\n");
+		}
+	} while (1);
+}
+
+static int record__aio_pushfn(void *to, struct aiocb *cblock, void *bf, size_t size, off_t off)
+{
+	struct record *rec = to;
+	int ret, trace_fd = rec->session->data->file.fd;
+
+	rec->samples++;
+
+	ret = record__aio_write(cblock, trace_fd, bf, size, off);
+	if (!ret) {
+		rec->bytes_written += size;
+		if (switch_output_size(rec))
+			trigger_hit(&switch_output_trigger);
+	}
+
+	return ret;
+}
+
+static off_t record__aio_get_pos(int trace_fd)
+{
+	return lseek(trace_fd, 0, SEEK_CUR);
+}
+
+static void record__aio_set_pos(int trace_fd, off_t pos)
+{
+	lseek(trace_fd, pos, SEEK_SET);
+}
+
+static void record__aio_mmap_read_sync(struct record *rec)
+{
+	int i;
+	struct perf_evlist *evlist = rec->evlist;
+	struct perf_mmap *maps = evlist->mmap;
+
+	if (!rec->opts.nr_cblocks)
+		return;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct perf_mmap *map = &maps[i];
+
+		if (map->base)
+			record__aio_sync(map, true);
+	}
+}
+
+static int nr_cblocks_default = 1;
+static int nr_cblocks_max = 4;
+
+static int record__aio_parse(const struct option *opt,
+			     const char *str,
+			     int unset)
+{
+	struct record_opts *opts = (struct record_opts *)opt->value;
+
+	if (unset) {
+		opts->nr_cblocks = 0;
+	} else {
+		if (str)
+			opts->nr_cblocks = strtol(str, NULL, 0);
+		if (!opts->nr_cblocks)
+			opts->nr_cblocks = nr_cblocks_default;
+	}
+
+	return 0;
+}
+#else /* HAVE_AIO_SUPPORT */
+static int nr_cblocks_max = 0;
+
+static int record__aio_sync(struct perf_mmap *md __maybe_unused, bool sync_all __maybe_unused)
+{
+	return -1;
+}
+
+static int record__aio_pushfn(void *to __maybe_unused, struct aiocb *cblock __maybe_unused,
+		void *bf __maybe_unused, size_t size __maybe_unused, off_t off __maybe_unused)
+{
+	return -1;
+}
+
+static off_t record__aio_get_pos(int trace_fd __maybe_unused)
+{
+	return -1;
+}
+
+static void record__aio_set_pos(int trace_fd __maybe_unused, off_t pos __maybe_unused)
+{
+}
+
+static void record__aio_mmap_read_sync(struct record *rec __maybe_unused)
+{
+}
+#endif
+
+static int record__aio_enabled(struct record *rec)
+{
+	return rec->opts.nr_cblocks > 0;
+}
+
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -327,9 +537,13 @@ static int record__mmap_evlist(struct record *rec,
 	struct record_opts *opts = &rec->opts;
 	char msg[512];
 
+	if (opts->affinity != PERF_AFFINITY_SYS)
+		cpu__setup_cpunode_map();
+
 	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
-				 opts->auxtrace_snapshot_mode) < 0) {
+				 opts->auxtrace_snapshot_mode,
+				 opts->nr_cblocks, opts->affinity) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
@@ -362,7 +576,6 @@ static int record__open(struct record *rec)
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
 	struct record_opts *opts = &rec->opts;
-	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
 	/*
@@ -391,7 +604,12 @@ try_again:
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
-
+			if ((errno == EINVAL || errno == EBADF) &&
+			    pos->leader != pos &&
+			    pos->weak_group) {
+			        pos = perf_evlist__reset_weak_group(evlist, pos);
+				goto try_again;
+			}
 			rc = -errno;
 			perf_evsel__open_strerror(pos, &opts->target,
 						  errno, msg, sizeof(msg));
@@ -410,14 +628,6 @@ try_again:
 		goto out;
 	}
 
-	if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) {
-		pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
-		      err_term->val.drv_cfg, perf_evsel__name(pos), errno,
-		      str_error_r(errno, msg, sizeof(msg)));
-		rc = -1;
-		goto out;
-	}
-
 	rc = record__mmap(rec);
 	if (rc)
 		goto out;
@@ -450,10 +660,9 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int process_buildids(struct record *rec)
 {
-	struct perf_data *data = &rec->data;
 	struct perf_session *session = rec->session;
 
-	if (data->size == 0)
+	if (perf_data__size(&rec->data) == 0)
 		return 0;
 
 	/*
@@ -513,6 +722,16 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
+static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
+{
+	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
+	    !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
+		CPU_ZERO(&rec->affinity_mask);
+		CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
+		sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+	}
+}
+
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
 				    bool overwrite)
 {
@@ -520,6 +739,8 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	int i;
 	int rc = 0;
 	struct perf_mmap *maps;
+	int trace_fd = rec->data.file.fd;
+	off_t off;
 
 	if (!evlist)
 		return 0;
@@ -531,13 +752,31 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
 		return 0;
 
+	if (record__aio_enabled(rec))
+		off = record__aio_get_pos(trace_fd);
+
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		struct perf_mmap *map = &maps[i];
 
 		if (map->base) {
-			if (perf_mmap__push(map, rec, record__pushfn) != 0) {
-				rc = -1;
-				goto out;
+			record__adjust_affinity(rec, map);
+			if (!record__aio_enabled(rec)) {
+				if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+					rc = -1;
+					goto out;
+				}
+			} else {
+				int idx;
+				/*
+				 * Call record__aio_sync() to wait till map->data buffer
+				 * becomes available after previous aio write request.
+				 */
+				idx = record__aio_sync(map, false);
+				if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
+					record__aio_set_pos(trace_fd, off);
+					rc = -1;
+					goto out;
+				}
 			}
 		}
 
@@ -548,6 +787,9 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		}
 	}
 
+	if (record__aio_enabled(rec))
+		record__aio_set_pos(trace_fd, off);
+
 	/*
 	 * Mark the round finished in case we wrote
 	 * at least one event.
@@ -592,6 +834,9 @@ static void record__init_features(struct record *rec)
 	if (!rec->opts.full_auxtrace)
 		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 
+	if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+		perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
@@ -605,7 +850,7 @@ record__finish_output(struct record *rec)
 		return;
 
 	rec->session->header.data_size += rec->bytes_written;
-	data->size = lseek(perf_data__fd(data), 0, SEEK_CUR);
+	data->file.size = lseek(perf_data__fd(data), 0, SEEK_CUR);
 
 	if (!rec->no_buildid) {
 		process_buildids(rec);
@@ -633,8 +878,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
 	err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
 						 process_synthesized_event,
 						 &rec->session->machines.host,
-						 rec->opts.sample_address,
-						 rec->opts.proc_map_timeout);
+						 rec->opts.sample_address);
 	thread_map__put(thread_map);
 	return err;
 }
@@ -650,6 +894,8 @@ record__switch_output(struct record *rec, bool at_exit)
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
 
+	record__aio_mmap_read_sync(rec);
+
 	record__synthesize(rec, true);
 	if (target__none(&rec->opts.target))
 		record__synthesize_workload(rec, true);
@@ -672,7 +918,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
 	if (!quiet)
 		fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
-			data->file.path, timestamp);
+			data->path, timestamp);
 
 	/* Output tracking events */
 	if (!at_exit) {
@@ -847,9 +1093,14 @@ static int record__synthesize(struct record *rec, bool tail)
 		return err;
 	}
 
+	err = perf_event__synthesize_bpf_events(tool, process_synthesized_event,
+						machine, opts);
+	if (err < 0)
+		pr_warning("Couldn't synthesize bpf events.\n");
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
 					    process_synthesized_event, opts->sample_address,
-					    opts->proc_map_timeout, 1);
+					    1);
 out:
 	return err;
 }
@@ -897,6 +1148,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	record__init_features(rec);
 
+	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+		session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
 	if (forks) {
 		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
 						    argv, data->is_pipe,
@@ -1157,6 +1411,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		record__synthesize_workload(rec, true);
 
 out_child:
+	record__aio_mmap_read_sync(rec);
+
 	if (forks) {
 		int exit_status;
 
@@ -1205,7 +1461,7 @@ out_child:
 
 		fprintf(stderr,	"[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
 			perf_data__size(data) / 1024.0 / 1024.0,
-			data->file.path, postfix, samples);
+			data->path, postfix, samples);
 	}
 
 out_delete_session:
@@ -1290,6 +1546,13 @@ static int perf_record_config(const char *var, const char *value, void *cb)
 		var = "call-graph.record-mode";
 		return perf_default_config(var, value, cb);
 	}
+#ifdef HAVE_AIO_SUPPORT
+	if (!strcmp(var, "record.aio")) {
+		rec->opts.nr_cblocks = strtol(value, NULL, 0);
+		if (!rec->opts.nr_cblocks)
+			rec->opts.nr_cblocks = nr_cblocks_default;
+	}
+#endif
 
 	return 0;
 }
@@ -1337,6 +1600,19 @@ static const struct clockid_map clockids[] = {
 	CLOCKID_END,
 };
 
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+	struct timespec res;
+
+	*res_ns = 0;
+	if (!clock_getres(clk_id, &res))
+		*res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+	else
+		pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+	return 0;
+}
+
 static int parse_clockid(const struct option *opt, const char *str, int unset)
 {
 	struct record_opts *opts = (struct record_opts *)opt->value;
@@ -1360,7 +1636,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 
 	/* if its a number, we're done */
 	if (sscanf(str, "%d", &opts->clockid) == 1)
-		return 0;
+		return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
 
 	/* allow a "CLOCK_" prefix to the name */
 	if (!strncasecmp(str, "CLOCK_", 6))
@@ -1369,7 +1645,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	for (cm = clockids; cm->name; cm++) {
 		if (!strcasecmp(str, cm->name)) {
 			opts->clockid = cm->clockid;
-			return 0;
+			return get_clockid_res(opts->clockid,
+					       &opts->clockid_res_ns);
 		}
 	}
 
@@ -1378,6 +1655,21 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	return -1;
 }
 
+static int record__parse_affinity(const struct option *opt, const char *str, int unset)
+{
+	struct record_opts *opts = (struct record_opts *)opt->value;
+
+	if (unset || !str)
+		return 0;
+
+	if (!strcasecmp(str, "node"))
+		opts->affinity = PERF_AFFINITY_NODE;
+	else if (!strcasecmp(str, "cpu"))
+		opts->affinity = PERF_AFFINITY_CPU;
+
+	return 0;
+}
+
 static int record__parse_mmap_pages(const struct option *opt,
 				    const char *str,
 				    int unset __maybe_unused)
@@ -1521,7 +1813,6 @@ static struct record record = {
 			.uses_mmap   = true,
 			.default_per_cpu = true,
 		},
-		.proc_map_timeout     = 500,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -1571,7 +1862,7 @@ static struct option __record_options[] = {
 	OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
 		    "list of cpus to monitor"),
 	OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
-	OPT_STRING('o', "output", &record.data.file.path, "file",
+	OPT_STRING('o', "output", &record.data.path, "file",
 		    "output file name"),
 	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
 			&record.opts.no_inherit_set,
@@ -1579,6 +1870,7 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
 		    "synthesize non-sample events at the end of output"),
 	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
+	OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"),
 	OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
 		    "Fail if the specified frequency can't be used"),
 	OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
@@ -1651,7 +1943,7 @@ static struct option __record_options[] = {
 	parse_clockid),
 	OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
 			  "opts", "AUX area tracing Snapshot Mode", ""),
-	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
+	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,
 		    "Record namespaces events"),
@@ -1681,6 +1973,14 @@ static struct option __record_options[] = {
 			  "signal"),
 	OPT_BOOLEAN(0, "dry-run", &dry_run,
 		    "Parse options then exit"),
+#ifdef HAVE_AIO_SUPPORT
+	OPT_CALLBACK_OPTARG(0, "aio", &record.opts,
+		     &nr_cblocks_default, "n", "Use <n> control blocks in asynchronous trace writing mode (default: 1, max: 4)",
+		     record__aio_parse),
+#endif
+	OPT_CALLBACK(0, "affinity", &record.opts, "node|cpu",
+		     "Set affinity mask of trace reading thread to NUMA node cpu mask or cpu of processed mmap buffer",
+		     record__parse_affinity),
 	OPT_END()
 };
 
@@ -1715,6 +2015,9 @@ int cmd_record(int argc, const char **argv)
 # undef REASON
 #endif
 
+	CPU_ZERO(&rec->affinity_mask);
+	rec->opts.affinity = PERF_AFFINITY_SYS;
+
 	rec->evlist = perf_evlist__new();
 	if (rec->evlist == NULL)
 		return -ENOMEM;
@@ -1873,6 +2176,13 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
+	if (rec->opts.nr_cblocks > nr_cblocks_max)
+		rec->opts.nr_cblocks = nr_cblocks_max;
+	if (verbose > 0)
+		pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
+
+	pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+
 	err = __cmd_record(&record, argc, argv);
 out:
 	perf_evlist__delete(rec->evlist);