Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - AMD range breakpoints support:

     Extend breakpoint tools and core to support address range through
     perf event with initial backend support for AMD extended
     breakpoints.

     The syntax is:

         perf record -e mem:addr/len:type

     For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)

         perf record -e mem:0x1000/512:w

   - event throttling/rotating fixes

   - various event group handling fixes, cleanups and general paranoia
     code to be more robust against bugs in the future.

    - kernel stack overhead fixes

  User-visible tooling side changes:

   - Show precise number of samples in at the end of a 'record' session,
     if processing build ids, since we will then traverse the whole
     perf.data file and see all the PERF_RECORD_SAMPLE records,
     otherwise stop showing the previous off-base heuristicly counted
     number of "samples" (Namhyung Kim).

   - Support to read compressed module from build-id cache (Namhyung
     Kim)

   - Enable sampling loads and stores simultaneously in 'perf mem'
     (Stephane Eranian)

   - 'perf diff' output improvements (Namhyung Kim)

   - Fix error reporting for evsel pgfault constructor (Arnaldo Carvalho
     de Melo)

  Tooling side infrastructure changes:

   - Cache eh/debug frame offset for dwarf unwind (Namhyung Kim)

   - Support parsing parameterized events (Cody P Schafer)

   - Add support for IP address formats in libtraceevent (David Ahern)

  Plus other misc fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  perf: Decouple unthrottling and rotating
  perf: Drop module reference on event init failure
  perf: Use POLLIN instead of POLL_IN for perf poll data in flag
  perf: Fix put_event() ctx lock
  perf: Fix move_group() order
  perf: Fix event->ctx locking
  perf: Add a bit of paranoia
  perf symbols: Convert lseek + read to pread
  perf tools: Use perf_data_file__fd() consistently
  perf symbols: Support to read compressed module from build-id cache
  perf evsel: Set attr.task bit for a tracking event
  perf header: Set header version correctly
  perf record: Show precise number of samples
  perf tools: Do not use __perf_session__process_events() directly
  perf callchain: Cache eh/debug frame offset for dwarf unwind
  perf tools: Provide stub for missing pthread_attr_setaffinity_np
  perf evsel: Don't rely on malloc working for sz 0
  tools lib traceevent: Add support for IP address formats
  perf ui/tui: Show fatal error message only if exists
  perf tests: Fix typo in sample-parsing.c
  ...

1 files changed, 48 insertions, 22 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8648c6d3003d..404ab3434052 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -190,16 +190,30 @@ out:
 	return rc;
 }
 
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct record *rec = container_of(tool, struct record, tool);
+
+	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_session *session = rec->session;
-	u64 start = session->header.data_offset;
 
-	u64 size = lseek(file->fd, 0, SEEK_CUR);
+	u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
 	if (size == 0)
 		return 0;
 
+	file->size = size;
+
 	/*
 	 * During this process, it'll load kernel map and replace the
 	 * dso->long_name to a real pathname it found.  In this case
@@ -211,9 +225,7 @@ static int process_buildids(struct record *rec)
 	 */
 	symbol_conf.ignore_vmlinux_buildid = true;
 
-	return __perf_session__process_events(session, start,
-					      size - start,
-					      size, &build_id__mark_dso_hit_ops);
+	return perf_session__process_events(session, &rec->tool);
 }
 
 static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
@@ -322,6 +334,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
 	bool disabled = false, draining = false;
+	int fd;
 
 	rec->progname = argv[0];
 
@@ -336,6 +349,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		return -1;
 	}
 
+	fd = perf_data_file__fd(file);
 	rec->session = session;
 
 	record__init_features(rec);
@@ -360,12 +374,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
 	if (file->is_pipe) {
-		err = perf_header__write_pipe(file->fd);
+		err = perf_header__write_pipe(fd);
 		if (err < 0)
 			goto out_child;
 	} else {
-		err = perf_session__write_header(session, rec->evlist,
-						 file->fd, false);
+		err = perf_session__write_header(session, rec->evlist, fd, false);
 		if (err < 0)
 			goto out_child;
 	}
@@ -397,7 +410,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			 * return this more properly and also
 			 * propagate errors that now are calling die()
 			 */
-			err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
+			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
 								  process_synthesized_event);
 			if (err <= 0) {
 				pr_err("Couldn't record tracing data.\n");
@@ -504,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
-	if (!quiet) {
+	if (!quiet)
 		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
-		/*
-		 * Approximate RIP event size: 24 bytes.
-		 */
-		fprintf(stderr,
-			"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
-			(double)rec->bytes_written / 1024.0 / 1024.0,
-			file->path,
-			rec->bytes_written / 24);
-	}
-
 out_child:
 	if (forks) {
 		int exit_status;
@@ -535,13 +538,29 @@ out_child:
 	} else
 		status = err;
 
+	/* this will be recalculated during process_buildids() */
+	rec->samples = 0;
+
 	if (!err && !file->is_pipe) {
 		rec->session->header.data_size += rec->bytes_written;
 
 		if (!rec->no_buildid)
 			process_buildids(rec);
-		perf_session__write_header(rec->session, rec->evlist,
-					   file->fd, true);
+		perf_session__write_header(rec->session, rec->evlist, fd, true);
+	}
+
+	if (!err && !quiet) {
+		char samples[128];
+
+		if (rec->samples)
+			scnprintf(samples, sizeof(samples),
+				  " (%" PRIu64 " samples)", rec->samples);
+		else
+			samples[0] = '\0';
+
+		fprintf(stderr,	"[ perf record: Captured and wrote %.3f MB %s%s ]\n",
+			perf_data_file__size(file) / 1024.0 / 1024.0,
+			file->path, samples);
 	}
 
 out_delete_session:
@@ -720,6 +739,13 @@ static struct record record = {
 			.default_per_cpu = true,
 		},
 	},
+	.tool = {
+		.sample		= process_sample_event,
+		.fork		= perf_event__process_fork,
+		.comm		= perf_event__process_comm,
+		.mmap		= perf_event__process_mmap,
+		.mmap2		= perf_event__process_mmap2,
+	},
 };
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "