Merge tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "New features:

  perf ftrace:

   - Add -n/--use-nsec option to the 'latency' subcommand.

     Default: usecs:

     $ sudo perf ftrace latency -T dput -a sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |    2098375 | #############################  |
          1 - 2    us |         61 |                                |
          2 - 4    us |         33 |                                |
          4 - 8    us |         13 |                                |
          8 - 16   us |        124 |                                |
         16 - 32   us |        123 |                                |
         32 - 64   us |          1 |                                |
         64 - 128  us |          0 |                                |
        128 - 256  us |          1 |                                |
        256 - 512  us |          0 |                                |

     Better granularity with nsec:

     $ sudo perf ftrace latency -T dput -a -n sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |          0 |                                |
          1 - 2    ns |          0 |                                |
          2 - 4    ns |          0 |                                |
          4 - 8    ns |          0 |                                |
          8 - 16   ns |          0 |                                |
         16 - 32   ns |          0 |                                |
         32 - 64   ns |          0 |                                |
         64 - 128  ns |    1163434 | ##############                 |
        128 - 256  ns |     914102 | #############                  |
        256 - 512  ns |        884 |                                |
        512 - 1024 ns |        613 |                                |
          1 - 2    us |         31 |                                |
          2 - 4    us |         17 |                                |
          4 - 8    us |          7 |                                |
          8 - 16   us |        123 |                                |
         16 - 32   us |         83 |                                |

  perf lock:

   - Add -c/--combine-locks option to merge lock instances in the same
     class into a single entry.

     # perf lock report -c
                    Name acquired contended avg wait(ns) total wait(ns) max wait(ns) min wait(ns)

           rcu_read_lock   251225         0            0              0            0            0
      hrtimer_bases.lock    39450         0            0              0            0            0
     &sb->s_type->i_l...    10301         1          662            662          662          662
        ptlock_ptr(page)    10173         2          701           1402          760          642
     &(ei->i_block_re...     8732         0            0              0            0            0
            &xa->xa_lock     8088         0            0              0            0            0
             &base->lock     6705         0            0              0            0            0
             &p->pi_lock     5549         0            0              0            0            0
     &dentry->d_lockr...     5010         4         1274           5097         1844          789
               &ep->lock     3958         0            0              0            0            0

      - Add -F/--field option to customize the list of fields to output:

     $ perf lock report -F contended,wait_max -k avg_wait
                     Name contended max wait(ns) avg wait(ns)

           slock-AF_INET6         1        23543        23543
        &lruvec->lru_lock         5        18317        11254
           slock-AF_INET6         1        10379        10379
               rcu_node_1         1         2104         2104
      &dentry->d_lockr...         1         1844         1844
      &dentry->d_lockr...         1         1672         1672
         &newf->file_lock        15         2279         1025
      &dentry->d_lockr...         1          792          792

   - Add --synth=no option for record, as there is no need to symbolize,
     lock names comes from the tracepoints.

  perf record:

   - Threaded recording, opt-in, via the new --threads command line
     option.

   - Improve AMD IBS (Instruction-Based Sampling) error handling
     messages.

  perf script:

   - Add 'brstackinsnlen' field (use it with -F) for branch stacks.

   - Output branch sample type in 'perf script'.

  perf report:

   - Add "addr_from" and "addr_to" sort dimensions.

   - Print branch stack entry type in 'perf report --dump-raw-trace'

   - Fix symbolization for chrooted workloads.

  Hardware tracing:

  Intel PT:

   - Add CFE (Control Flow Event) and EVD (Event Data) packets support.

   - Add MODE.Exec IFLAG bit support.

     Explanation about these features from the "Intel® 64 and IA-32
     architectures software developer’s manual combined volumes: 1, 2A,
     2B, 2C, 2D, 3A, 3B, 3C, 3D, and 4" PDF at:

        https://cdrdv2.intel.com/v1/dl/getContent/671200

     At page 3951:
      "32.2.4

       Event Trace is a capability that exposes details about the
       asynchronous events, when they are generated, and when their
       corresponding software event handler completes execution. These
       include:

        o Interrupts, including NMI and SMI, including the interrupt
          vector when defined.

        o Faults, exceptions including the fault vector.

           - Page faults additionally include the page fault address,
             when in context.

        o Event handler returns, including IRET and RSM.

        o VM exits and VM entries.¹

           - VM exits include the values written to the “exit reason”
             and “exit qualification” VMCS fields. INIT and SIPI events.

        o TSX aborts, including the abort status returned for the RTM
          instructions.

        o Shutdown.

       Additionally, it provides indication of the status of the
       Interrupt Flag (IF), to indicate when interrupts are masked"

  ARM CoreSight:

   - Use advertised caps/min_interval as default sample_period on ARM
     spe.

   - Update deduction of TRCCONFIGR register for branch broadcast on
     ARM's CoreSight ETM.

  Vendor Events (JSON):

  Intel:

   - Update events and metrics for: Alderlake, Broadwell, Broadwell DE,
     BroadwellX, CascadelakeX, Elkhartlake, Bonnell, Goldmont,
     GoldmontPlus, Westmere EP-DP, Haswell, HaswellX, Icelake, IcelakeX,
     Ivybridge, Ivytown, Jaketown, Knights Landing, Nehalem EP,
     Sandybridge, Silvermont, Skylake, Skylake Server, SkylakeX,
     Tigerlake, TremontX, Westmere EP-SP, and Westmere EX.

  ARM:

   - Add support for HiSilicon CPA PMU aliasing.

  perf stat:

   - Fix forked applications enablement of counters.

   - The 'slots' should only be printed on a different order than the
     one specified on the command line when 'topdown' events are
     present, fix it.

  Miscellaneous:

   - Sync msr-index, cpufeatures header files with the kernel sources.

   - Stop using some deprecated libbpf APIs in 'perf trace'.

   - Fix some spelling mistakes.

   - Refactor the maps pointers usage to pave the way for using refcount
     debugging.

   - Only offer the --tui option on perf top, report and annotate when
     perf was built with libslang.

   - Don't mention --to-ctf in 'perf data --help' when not linking with
     the required library, libbabeltrace.

   - Use ARRAY_SIZE() instead of ad hoc equivalent, spotted by
     array_size.cocci.

   - Enhance the matching of sub-commands abbreviations:
	'perf c2c rec' -> 'perf c2c record'
	'perf c2c recport -> error

   - Set build-id using build-id header on new mmap records.

   - Fix generation of 'perf --version' string.

  perf test:

   - Add test for the arm_spe event.

   - Add test to check unwinding using fame-pointer (fp) mode on arm64.

   - Make metric testing more robust in 'perf test'.

   - Add error message for unsupported branch stack cases.

  libperf:

   - Add API for allocating new thread map array.

   - Fix typo in perf_evlist__open() failure error messages in libperf
     tests.

  perf c2c:

   - Replace bitmap_weight() with bitmap_empty() where appropriate"

* tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (143 commits)
  perf evsel: Improve AMD IBS (Instruction-Based Sampling) error handling messages
  perf python: Add perf_env stubs that will be needed in evsel__open_strerror()
  perf tools: Enhance the matching of sub-commands abbreviations
  libperf tests: Fix typo in perf_evlist__open() failure error messages
  tools arm64: Import cputype.h
  perf lock: Add -F/--field option to control output
  perf lock: Extend struct lock_key to have print function
  perf lock: Add --synth=no option for record
  tools headers cpufeatures: Sync with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  perf stat: Fix forked applications enablement of counters
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf evsel: Make evsel__env() always return a valid env
  perf build-id: Fix spelling mistake "Cant" -> "Can't"
  perf header: Fix spelling mistake "could't" -> "couldn't"
  perf script: Add 'brstackinsnlen' for branch stacks
  perf parse-events: Move slots only with topdown
  perf ftrace latency: Update documentation
  perf ftrace latency: Add -n/--use-nsec option
  perf tools: Fix version kernel tag
  ...

1 files changed, 182 insertions, 31 deletions

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 498b05708db5..3b8dfe603e50 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -39,7 +39,8 @@
 
 #ifdef HAVE_ZSTD_SUPPORT
 static int perf_session__process_compressed_event(struct perf_session *session,
-						  union perf_event *event, u64 file_offset)
+						  union perf_event *event, u64 file_offset,
+						  const char *file_path)
 {
 	void *src;
 	size_t decomp_size, src_size;
@@ -61,6 +62,7 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 	}
 
 	decomp->file_pos = file_offset;
+	decomp->file_path = file_path;
 	decomp->mmap_len = mmap_len;
 	decomp->head = 0;
 
@@ -100,7 +102,8 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
-				       u64 file_offset);
+				       u64 file_offset,
+				       const char *file_path);
 
 static int perf_session__open(struct perf_session *session, int repipe_fd)
 {
@@ -182,7 +185,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 						    ordered_events);
 
 	return perf_session__deliver_event(session, event->event,
-					   session->tool, event->file_offset);
+					   session->tool, event->file_offset,
+					   event->file_path);
 }
 
 struct perf_session *__perf_session__new(struct perf_data *data,
@@ -471,7 +475,8 @@ static int process_event_time_conv_stub(struct perf_session *perf_session __mayb
 
 static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused,
 						       union perf_event *event __maybe_unused,
-						       u64 file_offset __maybe_unused)
+						       u64 file_offset __maybe_unused,
+						       const char *file_path __maybe_unused)
 {
        dump_printf(": unhandled!\n");
        return 0;
@@ -1072,9 +1077,9 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 }
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-			      u64 timestamp, u64 file_offset)
+			      u64 timestamp, u64 file_offset, const char *file_path)
 {
-	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset);
+	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset, file_path);
 }
 
 static void callchain__lbr_callstack_printf(struct perf_sample *sample)
@@ -1154,14 +1159,15 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 		struct branch_entry *e = &entries[i];
 
 		if (!callstack) {
-			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
+			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s\n",
 				i, e->from, e->to,
 				(unsigned short)e->flags.cycles,
 				e->flags.mispred ? "M" : " ",
 				e->flags.predicted ? "P" : " ",
 				e->flags.abort ? "A" : " ",
 				e->flags.in_tx ? "T" : " ",
-				(unsigned)e->flags.reserved);
+				(unsigned)e->flags.reserved,
+				e->flags.type ? branch_type_name(e->flags.type) : "");
 		} else {
 			printf("..... %2"PRIu64": %016" PRIx64 "\n",
 				i, i > 0 ? e->from : e->to);
@@ -1277,13 +1283,14 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 }
 
 static void dump_event(struct evlist *evlist, union perf_event *event,
-		       u64 file_offset, struct perf_sample *sample)
+		       u64 file_offset, struct perf_sample *sample,
+		       const char *file_path)
 {
 	if (!dump_trace)
 		return;
 
-	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
-	       file_offset, event->header.size, event->header.type);
+	printf("\n%#" PRIx64 "@%s [%#x]: event: %d\n",
+	       file_offset, file_path, event->header.size, event->header.type);
 
 	trace_event(event);
 	if (event->header.type == PERF_RECORD_SAMPLE && evlist->trace_event_sample_raw)
@@ -1486,12 +1493,13 @@ static int machines__deliver_event(struct machines *machines,
 				   struct evlist *evlist,
 				   union perf_event *event,
 				   struct perf_sample *sample,
-				   struct perf_tool *tool, u64 file_offset)
+				   struct perf_tool *tool, u64 file_offset,
+				   const char *file_path)
 {
 	struct evsel *evsel;
 	struct machine *machine;
 
-	dump_event(evlist, event, file_offset, sample);
+	dump_event(evlist, event, file_offset, sample, file_path);
 
 	evsel = evlist__id2evsel(evlist, sample->id);
 
@@ -1573,7 +1581,8 @@ static int machines__deliver_event(struct machines *machines,
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
-				       u64 file_offset)
+				       u64 file_offset,
+				       const char *file_path)
 {
 	struct perf_sample sample;
 	int ret = evlist__parse_sample(session->evlist, event, &sample);
@@ -1590,7 +1599,7 @@ static int perf_session__deliver_event(struct perf_session *session,
 		return 0;
 
 	ret = machines__deliver_event(&session->machines, session->evlist,
-				      event, &sample, tool, file_offset);
+				      event, &sample, tool, file_offset, file_path);
 
 	if (dump_trace && sample.aux_sample.size)
 		auxtrace__dump_auxtrace_sample(session, &sample);
@@ -1600,7 +1609,8 @@ static int perf_session__deliver_event(struct perf_session *session,
 
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
-					    u64 file_offset)
+					    u64 file_offset,
+					    const char *file_path)
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
@@ -1610,7 +1620,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 
 	if (event->header.type != PERF_RECORD_COMPRESSED ||
 	    tool->compressed == perf_session__process_compressed_event_stub)
-		dump_event(session->evlist, event, file_offset, &sample);
+		dump_event(session->evlist, event, file_offset, &sample, file_path);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
@@ -1669,9 +1679,9 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_FEATURE:
 		return tool->feature(session, event);
 	case PERF_RECORD_COMPRESSED:
-		err = tool->compressed(session, event, file_offset);
+		err = tool->compressed(session, event, file_offset, file_path);
 		if (err)
-			dump_event(session->evlist, event, file_offset, &sample);
+			dump_event(session->evlist, event, file_offset, &sample, file_path);
 		return err;
 	default:
 		return -EINVAL;
@@ -1688,9 +1698,9 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, 0);
+		return perf_session__process_user_event(session, event, 0, NULL);
 
-	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0);
+	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0, NULL);
 }
 
 static void event_swap(union perf_event *event, bool sample_id_all)
@@ -1787,7 +1797,8 @@ int perf_session__peek_events(struct perf_session *session, u64 offset,
 }
 
 static s64 perf_session__process_event(struct perf_session *session,
-				       union perf_event *event, u64 file_offset)
+				       union perf_event *event, u64 file_offset,
+				       const char *file_path)
 {
 	struct evlist *evlist = session->evlist;
 	struct perf_tool *tool = session->tool;
@@ -1802,7 +1813,7 @@ static s64 perf_session__process_event(struct perf_session *session,
 	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, file_offset);
+		return perf_session__process_user_event(session, event, file_offset, file_path);
 
 	if (tool->ordered_events) {
 		u64 timestamp = -1ULL;
@@ -1811,12 +1822,12 @@ static s64 perf_session__process_event(struct perf_session *session,
 		if (ret && ret != -1)
 			return ret;
 
-		ret = perf_session__queue_event(session, event, timestamp, file_offset);
+		ret = perf_session__queue_event(session, event, timestamp, file_offset, file_path);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session__deliver_event(session, event, tool, file_offset);
+	return perf_session__deliver_event(session, event, tool, file_offset, file_path);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -2043,7 +2054,7 @@ more:
 		}
 	}
 
-	if ((skip = perf_session__process_event(session, event, head)) < 0) {
+	if ((skip = perf_session__process_event(session, event, head, "pipe")) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       head, event->header.size, event->header.type);
 		err = -EINVAL;
@@ -2140,7 +2151,8 @@ static int __perf_session__process_decomp_events(struct perf_session *session)
 		size = event->header.size;
 
 		if (size < sizeof(struct perf_event_header) ||
-		    (skip = perf_session__process_event(session, event, decomp->file_pos)) < 0) {
+		    (skip = perf_session__process_event(session, event, decomp->file_pos,
+							decomp->file_path)) < 0) {
 			pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 				decomp->file_pos + decomp->head, event->header.size, event->header.type);
 			return -EINVAL;
@@ -2171,10 +2183,12 @@ struct reader;
 
 typedef s64 (*reader_cb_t)(struct perf_session *session,
 			   union perf_event *event,
-			   u64 file_offset);
+			   u64 file_offset,
+			   const char *file_path);
 
 struct reader {
 	int		 fd;
+	const char	 *path;
 	u64		 data_size;
 	u64		 data_offset;
 	reader_cb_t	 process;
@@ -2186,6 +2200,8 @@ struct reader {
 	u64		 file_pos;
 	u64		 file_offset;
 	u64		 head;
+	u64		 size;
+	bool		 done;
 	struct zstd_data   zstd_data;
 	struct decomp_data decomp_data;
 };
@@ -2292,7 +2308,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
 	skip = -EINVAL;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = rd->process(session, event, rd->file_pos)) < 0) {
+	    (skip = rd->process(session, event, rd->file_pos, rd->path)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       rd->file_offset + rd->head, event->header.size,
 		       event->header.type, strerror(-skip));
@@ -2303,6 +2319,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
 	if (skip)
 		size += skip;
 
+	rd->size += size;
 	rd->head += size;
 	rd->file_pos += size;
 
@@ -2359,15 +2376,17 @@ out:
 
 static s64 process_simple(struct perf_session *session,
 			  union perf_event *event,
-			  u64 file_offset)
+			  u64 file_offset,
+			  const char *file_path)
 {
-	return perf_session__process_event(session, event, file_offset);
+	return perf_session__process_event(session, event, file_offset, file_path);
 }
 
 static int __perf_session__process_events(struct perf_session *session)
 {
 	struct reader rd = {
 		.fd		= perf_data__fd(session->data),
+		.path		= session->data->file.path,
 		.data_size	= session->header.data_size,
 		.data_offset	= session->header.data_offset,
 		.process	= process_simple,
@@ -2411,6 +2430,135 @@ out_err:
 	return err;
 }
 
+/*
+ * Processing 2 MB of data from each reader in sequence,
+ * because that's the way the ordered events sorting works
+ * most efficiently.
+ */
+#define READER_MAX_SIZE (2 * 1024 * 1024)
+
+/*
+ * This function reads, merge and process directory data.
+ * It assumens the version 1 of directory data, where each
+ * data file holds per-cpu data, already sorted by kernel.
+ */
+static int __perf_session__process_dir_events(struct perf_session *session)
+{
+	struct perf_data *data = session->data;
+	struct perf_tool *tool = session->tool;
+	int i, ret, readers, nr_readers;
+	struct ui_progress prog;
+	u64 total_size = perf_data__size(session->data);
+	struct reader *rd;
+
+	perf_tool__fill_defaults(tool);
+
+	ui_progress__init_size(&prog, total_size, "Sorting events...");
+
+	nr_readers = 1;
+	for (i = 0; i < data->dir.nr; i++) {
+		if (data->dir.files[i].size)
+			nr_readers++;
+	}
+
+	rd = zalloc(nr_readers * sizeof(struct reader));
+	if (!rd)
+		return -ENOMEM;
+
+	rd[0] = (struct reader) {
+		.fd		 = perf_data__fd(session->data),
+		.path		 = session->data->file.path,
+		.data_size	 = session->header.data_size,
+		.data_offset	 = session->header.data_offset,
+		.process	 = process_simple,
+		.in_place_update = session->data->in_place_update,
+	};
+	ret = reader__init(&rd[0], NULL);
+	if (ret)
+		goto out_err;
+	ret = reader__mmap(&rd[0], session);
+	if (ret)
+		goto out_err;
+	readers = 1;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		if (!data->dir.files[i].size)
+			continue;
+		rd[readers] = (struct reader) {
+			.fd		 = data->dir.files[i].fd,
+			.path		 = data->dir.files[i].path,
+			.data_size	 = data->dir.files[i].size,
+			.data_offset	 = 0,
+			.process	 = process_simple,
+			.in_place_update = session->data->in_place_update,
+		};
+		ret = reader__init(&rd[readers], NULL);
+		if (ret)
+			goto out_err;
+		ret = reader__mmap(&rd[readers], session);
+		if (ret)
+			goto out_err;
+		readers++;
+	}
+
+	i = 0;
+	while (readers) {
+		if (session_done())
+			break;
+
+		if (rd[i].done) {
+			i = (i + 1) % nr_readers;
+			continue;
+		}
+		if (reader__eof(&rd[i])) {
+			rd[i].done = true;
+			readers--;
+			continue;
+		}
+
+		session->active_decomp = &rd[i].decomp_data;
+		ret = reader__read_event(&rd[i], session, &prog);
+		if (ret < 0) {
+			goto out_err;
+		} else if (ret == READER_NODATA) {
+			ret = reader__mmap(&rd[i], session);
+			if (ret)
+				goto out_err;
+		}
+
+		if (rd[i].size >= READER_MAX_SIZE) {
+			rd[i].size = 0;
+			i = (i + 1) % nr_readers;
+		}
+	}
+
+	ret = ordered_events__flush(&session->ordered_events, OE_FLUSH__FINAL);
+	if (ret)
+		goto out_err;
+
+	ret = perf_session__flush_thread_stacks(session);
+out_err:
+	ui_progress__finish();
+
+	if (!tool->no_warn)
+		perf_session__warn_about_errors(session);
+
+	/*
+	 * We may switching perf.data output, make ordered_events
+	 * reusable.
+	 */
+	ordered_events__reinit(&session->ordered_events);
+
+	session->one_mmap = false;
+
+	session->active_decomp = &session->decomp_data;
+	for (i = 0; i < nr_readers; i++)
+		reader__release_decomp(&rd[i]);
+	zfree(&rd);
+
+	return ret;
+}
+
 int perf_session__process_events(struct perf_session *session)
 {
 	if (perf_session__register_idle_thread(session) < 0)
@@ -2419,6 +2567,9 @@ int perf_session__process_events(struct perf_session *session)
 	if (perf_data__is_pipe(session->data))
 		return __perf_session__process_pipe_events(session);
 
+	if (perf_data__is_dir(session->data))
+		return __perf_session__process_dir_events(session);
+
 	return __perf_session__process_events(session);
 }