1 files changed, 112 insertions, 151 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 56f8142ff97f..65681a1a292a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-record.c
  *
@@ -50,7 +51,6 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
-#include <asm/bug.h>
 #include <linux/time64.h>
 
 struct switch_output {
@@ -66,7 +66,7 @@ struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
 	u64			bytes_written;
-	struct perf_data_file	file;
+	struct perf_data	data;
 	struct auxtrace_record	*itr;
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
@@ -78,6 +78,7 @@ struct record {
 	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	bool			timestamp_filename;
+	bool			timestamp_boundary;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
 };
@@ -107,7 +108,7 @@ static bool switch_output_time(struct record *rec)
 
 static int record__write(struct record *rec, void *bf, size_t size)
 {
-	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
+	if (perf_data__write(rec->session->data, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
@@ -129,107 +130,12 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, event, event->header.size);
 }
 
-static int
-backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
-{
-	struct perf_event_header *pheader;
-	u64 evt_head = head;
-	int size = mask + 1;
-
-	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
-	pheader = (struct perf_event_header *)(buf + (head & mask));
-	*start = head;
-	while (true) {
-		if (evt_head - head >= (unsigned int)size) {
-			pr_debug("Finished reading backward ring buffer: rewind\n");
-			if (evt_head - head > (unsigned int)size)
-				evt_head -= pheader->size;
-			*end = evt_head;
-			return 0;
-		}
-
-		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
-
-		if (pheader->size == 0) {
-			pr_debug("Finished reading backward ring buffer: get start\n");
-			*end = evt_head;
-			return 0;
-		}
-
-		evt_head += pheader->size;
-		pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
-	}
-	WARN_ONCE(1, "Shouldn't get here\n");
-	return -1;
-}
-
-static int
-rb_find_range(void *data, int mask, u64 head, u64 old,
-	      u64 *start, u64 *end, bool backward)
-{
-	if (!backward) {
-		*start = old;
-		*end = head;
-		return 0;
-	}
-
-	return backward_rb_find_range(data, mask, head, start, end);
-}
-
-static int
-record__mmap_read(struct record *rec, struct perf_mmap *md,
-		  bool overwrite, bool backward)
+static int record__pushfn(void *to, void *bf, size_t size)
 {
-	u64 head = perf_mmap__read_head(md);
-	u64 old = md->prev;
-	u64 end = head, start = old;
-	unsigned char *data = md->base + page_size;
-	unsigned long size;
-	void *buf;
-	int rc = 0;
-
-	if (rb_find_range(data, md->mask, head,
-			  old, &start, &end, backward))
-		return -1;
-
-	if (start == end)
-		return 0;
+	struct record *rec = to;
 
 	rec->samples++;
-
-	size = end - start;
-	if (size > (unsigned long)(md->mask) + 1) {
-		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
-
-		md->prev = head;
-		perf_mmap__consume(md, overwrite || backward);
-		return 0;
-	}
-
-	if ((start & md->mask) + size != (end & md->mask)) {
-		buf = &data[start & md->mask];
-		size = md->mask + 1 - (start & md->mask);
-		start += size;
-
-		if (record__write(rec, buf, size) < 0) {
-			rc = -1;
-			goto out;
-		}
-	}
-
-	buf = &data[start & md->mask];
-	size = end - start;
-	start += size;
-
-	if (record__write(rec, buf, size) < 0) {
-		rc = -1;
-		goto out;
-	}
-
-	md->prev = head;
-	perf_mmap__consume(md, overwrite || backward);
-out:
-	return rc;
+	return record__write(rec, bf, size);
 }
 
 static volatile int done;
@@ -268,13 +174,13 @@ static int record__process_auxtrace(struct perf_tool *tool,
 				    size_t len1, void *data2, size_t len2)
 {
 	struct record *rec = container_of(tool, struct record, tool);
-	struct perf_data_file *file = &rec->file;
+	struct perf_data *data = &rec->data;
 	size_t padding;
 	u8 pad[8] = {0};
 
-	if (!perf_data_file__is_pipe(file)) {
+	if (!perf_data__is_pipe(data)) {
 		off_t file_offset;
-		int fd = perf_data_file__fd(file);
+		int fd = perf_data__fd(data);
 		int err;
 
 		file_offset = lseek(fd, 0, SEEK_CUR);
@@ -395,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
 	struct record_opts *opts = &rec->opts;
 	char msg[512];
 
-	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode) < 0) {
 		if (errno == EPERM) {
@@ -433,6 +339,22 @@ static int record__open(struct record *rec)
 	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
+	/*
+	 * For initial_delay we need to add a dummy event so that we can track
+	 * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+	 * real events, the ones asked by the user.
+	 */
+	if (opts->initial_delay) {
+		if (perf_evlist__add_dummy(evlist))
+			return -ENOMEM;
+
+		pos = perf_evlist__first(evlist);
+		pos->tracking = 0;
+		pos = perf_evlist__last(evlist);
+		pos->tracking = 1;
+		pos->attr.enable_on_exec = 1;
+	}
+
 	perf_evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
@@ -450,6 +372,8 @@ try_again:
 			ui__error("%s\n", msg);
 			goto out;
 		}
+
+		pos->supported = true;
 	}
 
 	if (perf_evlist__apply_filters(evlist, &pos)) {
@@ -486,17 +410,24 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct record *rec = container_of(tool, struct record, tool);
 
-	rec->samples++;
+	if (rec->evlist->first_sample_time == 0)
+		rec->evlist->first_sample_time = sample->time;
 
+	rec->evlist->last_sample_time = sample->time;
+
+	if (rec->buildid_all)
+		return 0;
+
+	rec->samples++;
 	return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 }
 
 static int process_buildids(struct record *rec)
 {
-	struct perf_data_file *file  = &rec->file;
+	struct perf_data *data = &rec->data;
 	struct perf_session *session = rec->session;
 
-	if (file->size == 0)
+	if (data->size == 0)
 		return 0;
 
 	/*
@@ -512,9 +443,11 @@ static int process_buildids(struct record *rec)
 
 	/*
 	 * If --buildid-all is given, it marks all DSO regardless of hits,
-	 * so no need to process samples.
+	 * so no need to process samples. But if timestamp_boundary is enabled,
+	 * it still needs to walk on all samples to get the timestamps of
+	 * first/last samples.
 	 */
-	if (rec->buildid_all)
+	if (rec->buildid_all && !rec->timestamp_boundary)
 		rec->tool.sample = NULL;
 
 	return perf_session__process_events(session);
@@ -555,7 +488,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
-				    bool backward)
+				    bool overwrite)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
@@ -565,19 +498,18 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	if (!evlist)
 		return 0;
 
-	maps = backward ? evlist->backward_mmap : evlist->mmap;
+	maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
 	if (!maps)
 		return 0;
 
-	if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+	if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
 		if (maps[i].base) {
-			if (record__mmap_read(rec, &maps[i],
-					      evlist->overwrite, backward) != 0) {
+			if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -597,7 +529,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
-	if (backward)
+	if (overwrite)
 		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
 	return rc;
@@ -640,14 +572,14 @@ static void record__init_features(struct record *rec)
 static void
 record__finish_output(struct record *rec)
 {
-	struct perf_data_file *file = &rec->file;
-	int fd = perf_data_file__fd(file);
+	struct perf_data *data = &rec->data;
+	int fd = perf_data__fd(data);
 
-	if (file->is_pipe)
+	if (data->is_pipe)
 		return;
 
 	rec->session->header.data_size += rec->bytes_written;
-	file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+	data->size = lseek(perf_data__fd(data), 0, SEEK_CUR);
 
 	if (!rec->no_buildid) {
 		process_buildids(rec);
@@ -686,7 +618,7 @@ static int record__synthesize(struct record *rec, bool tail);
 static int
 record__switch_output(struct record *rec, bool at_exit)
 {
-	struct perf_data_file *file = &rec->file;
+	struct perf_data *data = &rec->data;
 	int fd, err;
 
 	/* Same Size:      "2015122520103046"*/
@@ -704,7 +636,7 @@ record__switch_output(struct record *rec, bool at_exit)
 		return -EINVAL;
 	}
 
-	fd = perf_data_file__switch(file, timestamp,
+	fd = perf_data__switch(data, timestamp,
 				    rec->session->header.data_offset,
 				    at_exit);
 	if (fd >= 0 && !at_exit) {
@@ -714,7 +646,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
 	if (!quiet)
 		fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
-			file->path, timestamp);
+			data->file.path, timestamp);
 
 	/* Output tracking events */
 	if (!at_exit) {
@@ -769,8 +701,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
 	if (evlist) {
 		if (evlist->mmap && evlist->mmap[0].base)
 			return evlist->mmap[0].base;
-		if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-			return evlist->backward_mmap[0].base;
+		if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+			return evlist->overwrite_mmap[0].base;
 	}
 	return NULL;
 }
@@ -789,16 +721,16 @@ static int record__synthesize(struct record *rec, bool tail)
 {
 	struct perf_session *session = rec->session;
 	struct machine *machine = &session->machines.host;
-	struct perf_data_file *file = &rec->file;
+	struct perf_data *data = &rec->data;
 	struct record_opts *opts = &rec->opts;
 	struct perf_tool *tool = &rec->tool;
-	int fd = perf_data_file__fd(file);
+	int fd = perf_data__fd(data);
 	int err = 0;
 
 	if (rec->opts.tail_synthesize != tail)
 		return 0;
 
-	if (file->is_pipe) {
+	if (data->is_pipe) {
 		err = perf_event__synthesize_features(
 			tool, session, rec->evlist, process_synthesized_event);
 		if (err < 0) {
@@ -844,26 +776,50 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 	}
 
-	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/kallsyms permission or run as root.\n");
-
-	err = perf_event__synthesize_modules(tool, process_synthesized_event,
-					     machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/modules permission or run as root.\n");
+	if (!perf_evlist__exclude_kernel(rec->evlist)) {
+		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+							 machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/kallsyms permission or run as root.\n");
+
+		err = perf_event__synthesize_modules(tool, process_synthesized_event,
+						     machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/modules permission or run as root.\n");
+	}
 
 	if (perf_guest) {
 		machines__process_guests(&session->machines,
 					 perf_event__synthesize_guest_os, tool);
 	}
 
+	err = perf_event__synthesize_extra_attr(&rec->tool,
+						rec->evlist,
+						process_synthesized_event,
+						data->is_pipe);
+	if (err)
+		goto out;
+
+	err = perf_event__synthesize_thread_map2(&rec->tool, rec->evlist->threads,
+						 process_synthesized_event,
+						NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->cpus,
+					     process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize cpu map.\n");
+		return err;
+	}
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
 					    process_synthesized_event, opts->sample_address,
-					    opts->proc_map_timeout);
+					    opts->proc_map_timeout, 1);
 out:
 	return err;
 }
@@ -877,7 +833,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
 	struct record_opts *opts = &rec->opts;
-	struct perf_data_file *file = &rec->file;
+	struct perf_data *data = &rec->data;
 	struct perf_session *session;
 	bool disabled = false, draining = false;
 	int fd;
@@ -903,20 +859,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		signal(SIGUSR2, SIG_IGN);
 	}
 
-	session = perf_session__new(file, false, tool);
+	session = perf_session__new(data, false, tool);
 	if (session == NULL) {
 		pr_err("Perf session creation failed.\n");
 		return -1;
 	}
 
-	fd = perf_data_file__fd(file);
+	fd = perf_data__fd(data);
 	rec->session = session;
 
 	record__init_features(rec);
 
 	if (forks) {
 		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
-						    argv, file->is_pipe,
+						    argv, data->is_pipe,
 						    workload_exec_failed_signal);
 		if (err < 0) {
 			pr_err("Couldn't run the workload!\n");
@@ -952,7 +908,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (!rec->evlist->nr_groups)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
-	if (file->is_pipe) {
+	if (data->is_pipe) {
 		err = perf_header__write_pipe(fd);
 		if (err < 0)
 			goto out_child;
@@ -1213,8 +1169,8 @@ out_child:
 			samples[0] = '\0';
 
 		fprintf(stderr,	"[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
-			perf_data_file__size(file) / 1024.0 / 1024.0,
-			file->path, postfix, samples);
+			perf_data__size(data) / 1024.0 / 1024.0,
+			data->file.path, postfix, samples);
 	}
 
 out_delete_session:
@@ -1578,7 +1534,7 @@ 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.file.path, "file",
+	OPT_STRING('o', "output", &record.data.file.path, "file",
 		    "output file name"),
 	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
 			&record.opts.no_inherit_set,
@@ -1643,6 +1599,9 @@ static struct option __record_options[] = {
 	OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
 		    "sample selected machine registers on interrupt,"
 		    " use -I ? to list register names", parse_regs),
+	OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
+		    "sample selected machine registers on interrupt,"
+		    " use -I ? to list register names", parse_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
 	OPT_CALLBACK('k', "clockid", &record.opts,
@@ -1672,6 +1631,8 @@ static struct option __record_options[] = {
 		    "Record build-id of all DSOs regardless of hits"),
 	OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
 		    "append timestamp to output filename"),
+	OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
+		    "Record timestamp boundary (time of first/last samples)"),
 	OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
 			  &record.switch_output.set, "signal,size,time",
 			  "Switch output when receive SIGUSR2 or cross size,time threshold",
@@ -1785,7 +1746,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = -ENOMEM;
 
-	if (symbol_conf.kptr_restrict)
+	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"
@@ -1855,8 +1816,8 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
-	/* Enable ignoring missing threads when -u option is defined. */
-	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+	/* Enable ignoring missing threads when -u/-p option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid;
 
 	err = -ENOMEM;
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)