perf: Add pipe-specific header read/write and event processing code

This patch makes several changes to allow the perf event stream
to be sent and received over a pipe:

- adds pipe-specific versions of the header read/write code

- adds pipe-specific version of the event processing code

- adds a range of event types to be used for header or other
  pseudo events, above the range used by the kernel

- checks the return value of event handlers, which they can use
  to skip over large events during event processing rather than actually
  reading them into event objects.

- unifies the multiple do_read() functions and updates its
  users.

Note that none of these changes affect the existing perf data
file format or processing - this code only comes into play if
perf output is sent to stdout (or is read from stdin).

Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fweisbec@gmail.com
Cc: rostedt@goodmis.org
Cc: k-keiichi@bx.jp.nec.com
Cc: acme@ghostprotocols.net
LKML-Reference: <1270184365-8281-2-git-send-email-tzanussi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

6 files changed, 202 insertions, 29 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9a951368723..d060fc50c8a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -487,7 +487,7 @@ static int __cmd_record(int argc, const char **argv)
 	}
 
 	if (!file_new) {
-		err = perf_header__read(&session->header, output);
+		err = perf_header__read(session, output);
 		if (err < 0)
 			return err;
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7f7cf8539cf..5c1eba67130 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -83,6 +83,10 @@ struct build_id_event {
 	char			 filename[];
 };
 
+enum perf_header_event_type { /* above any possible kernel type */
+	PERF_RECORD_HEADER_MAX			= 64,
+};
+
 typedef union event_union {
 	struct perf_event_header	header;
 	struct ip_event			ip;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6c9aa16ee51..8d05337d1a5 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -427,6 +427,25 @@ out_free:
 	return err;
 }
 
+int perf_header__write_pipe(int fd)
+{
+	struct perf_pipe_file_header f_header;
+	int err;
+
+	f_header = (struct perf_pipe_file_header){
+		.magic	   = PERF_MAGIC,
+		.size	   = sizeof(f_header),
+	};
+
+	err = do_write(fd, &f_header, sizeof(f_header));
+	if (err < 0) {
+		pr_debug("failed to write perf pipe header\n");
+		return err;
+	}
+
+	return 0;
+}
+
 int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 {
 	struct perf_file_header f_header;
@@ -518,25 +537,10 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 	return 0;
 }
 
-static int do_read(int fd, void *buf, size_t size)
-{
-	while (size) {
-		int ret = read(fd, buf, size);
-
-		if (ret <= 0)
-			return -1;
-
-		size -= ret;
-		buf += ret;
-	}
-
-	return 0;
-}
-
 static int perf_header__getbuffer64(struct perf_header *self,
 				    int fd, void *buf, size_t size)
 {
-	if (do_read(fd, buf, size))
+	if (do_read(fd, buf, size) <= 0)
 		return -1;
 
 	if (self->needs_swap)
@@ -592,7 +596,7 @@ int perf_file_header__read(struct perf_file_header *self,
 {
 	lseek(fd, 0, SEEK_SET);
 
-	if (do_read(fd, self, sizeof(*self)) ||
+	if (do_read(fd, self, sizeof(*self)) <= 0 ||
 	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
 		return -1;
 
@@ -662,13 +666,51 @@ static int perf_file_section__process(struct perf_file_section *self,
 	return 0;
 }
 
-int perf_header__read(struct perf_header *self, int fd)
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+				       struct perf_header *ph, int fd)
 {
+	if (do_read(fd, self, sizeof(*self)) <= 0 ||
+	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+		return -1;
+
+	if (self->size != sizeof(*self)) {
+		u64 size = bswap_64(self->size);
+
+		if (size != sizeof(*self))
+			return -1;
+
+		ph->needs_swap = true;
+	}
+
+	return 0;
+}
+
+static int perf_header__read_pipe(struct perf_session *session, int fd)
+{
+	struct perf_header *self = &session->header;
+	struct perf_pipe_file_header f_header;
+
+	if (perf_file_header__read_pipe(&f_header, self, fd) < 0) {
+		pr_debug("incompatible file format\n");
+		return -EINVAL;
+	}
+
+	session->fd = fd;
+
+	return 0;
+}
+
+int perf_header__read(struct perf_session *session, int fd)
+{
+	struct perf_header *self = &session->header;
 	struct perf_file_header	f_header;
 	struct perf_file_attr	f_attr;
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
 
+	if (session->fd_pipe)
+		return perf_header__read_pipe(session, fd);
+
 	if (perf_file_header__read(&f_header, self, fd) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c059f08cf87..6562ece6706 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,11 @@ struct perf_file_header {
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
+struct perf_pipe_file_header {
+	u64				magic;
+	u64				size;
+};
+
 struct perf_header;
 
 int perf_file_header__read(struct perf_file_header *self,
@@ -60,8 +65,9 @@ struct perf_header {
 int perf_header__init(struct perf_header *self);
 void perf_header__exit(struct perf_header *self);
 
-int perf_header__read(struct perf_header *self, int fd);
+int perf_header__read(struct perf_session *session, int fd);
 int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_header__write_pipe(int fd);
 
 int perf_header__add_attr(struct perf_header *self,
 			  struct perf_header_attr *attr);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ddf288fca3e..2c1277cb4ae 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,16 @@ static int perf_session__open(struct perf_session *self, bool force)
 {
 	struct stat input_stat;
 
+	if (!strcmp(self->filename, "-")) {
+		self->fd_pipe = true;
+		self->fd = STDIN_FILENO;
+
+		if (perf_header__read(self, self->fd) < 0)
+			pr_err("incompatible file format");
+
+		return 0;
+	}
+
 	self->fd = open(self->filename, O_RDONLY);
 	if (self->fd < 0) {
 		pr_err("failed to open file: %s", self->filename);
@@ -38,7 +48,7 @@ static int perf_session__open(struct perf_session *self, bool force)
 		goto out_close;
 	}
 
-	if (perf_header__read(&self->header, self->fd) < 0) {
+	if (perf_header__read(self, self->fd) < 0) {
 		pr_err("incompatible file format");
 		goto out_close;
 	}
@@ -52,6 +62,11 @@ out_close:
 	return -1;
 }
 
+void perf_session__update_sample_type(struct perf_session *self)
+{
+	self->sample_type = perf_header__sample_type(&self->header);
+}
+
 struct perf_session *perf_session__new(const char *filename, int mode, bool force)
 {
 	size_t len = filename ? strlen(filename) + 1 : 0;
@@ -85,7 +100,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 			goto out_delete;
 	}
 
-	self->sample_type = perf_header__sample_type(&self->header);
+	perf_session__update_sample_type(self);
 out:
 	return self;
 out_free:
@@ -200,14 +215,17 @@ static const char *event__name[] = {
 	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
 };
 
-unsigned long event__total[PERF_RECORD_MAX];
+unsigned long event__total[PERF_RECORD_HEADER_MAX];
 
 void event__print_totals(void)
 {
 	int i;
-	for (i = 0; i < PERF_RECORD_MAX; ++i)
+	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+		if (!event__name[i])
+			continue;
 		pr_info("%10s events: %10ld\n",
 			event__name[i], event__total[i]);
+	}
 }
 
 void mem_bswap_64(void *src, int byte_size)
@@ -271,7 +289,7 @@ static event__swap_op event__swap_ops[] = {
 	[PERF_RECORD_LOST]   = event__all64_swap,
 	[PERF_RECORD_READ]   = event__read_swap,
 	[PERF_RECORD_SAMPLE] = event__all64_swap,
-	[PERF_RECORD_MAX]    = NULL,
+	[PERF_RECORD_HEADER_MAX]    = NULL,
 };
 
 static int perf_session__process_event(struct perf_session *self,
@@ -281,7 +299,7 @@ static int perf_session__process_event(struct perf_session *self,
 {
 	trace_event(event);
 
-	if (event->header.type < PERF_RECORD_MAX) {
+	if (event->header.type < PERF_RECORD_HEADER_MAX) {
 		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
 			    offset + head, event->header.size,
 			    event__name[event->header.type]);
@@ -376,6 +394,101 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 	return thread;
 }
 
+int do_read(int fd, void *buf, size_t size)
+{
+	void *buf_start = buf;
+
+	while (size) {
+		int ret = read(fd, buf, size);
+
+		if (ret <= 0)
+			return ret;
+
+		size -= ret;
+		buf += ret;
+	}
+
+	return buf - buf_start;
+}
+
+#define session_done()	(*(volatile int *)(&session_done))
+volatile int session_done;
+
+static int __perf_session__process_pipe_events(struct perf_session *self,
+					       struct perf_event_ops *ops)
+{
+	event_t event;
+	uint32_t size;
+	int skip = 0;
+	u64 head;
+	int err;
+	void *p;
+
+	perf_event_ops__fill_defaults(ops);
+
+	head = 0;
+more:
+	err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+	if (err <= 0) {
+		if (err == 0)
+			goto done;
+
+		pr_err("failed to read event header\n");
+		goto out_err;
+	}
+
+	if (self->header.needs_swap)
+		perf_event_header__bswap(&event.header);
+
+	size = event.header.size;
+	if (size == 0)
+		size = 8;
+
+	p = &event;
+	p += sizeof(struct perf_event_header);
+
+	err = do_read(self->fd, p, size - sizeof(struct perf_event_header));
+	if (err <= 0) {
+		if (err == 0) {
+			pr_err("unexpected end of event stream\n");
+			goto done;
+		}
+
+		pr_err("failed to read event data\n");
+		goto out_err;
+	}
+
+	if (size == 0 ||
+	    (skip = perf_session__process_event(self, &event, ops,
+						0, head)) < 0) {
+		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+			    head, event.header.size, event.header.type);
+		/*
+		 * assume we lost track of the stream, check alignment, and
+		 * increment a single u64 in the hope to catch on again 'soon'.
+		 */
+		if (unlikely(head & 7))
+			head &= ~7ULL;
+
+		size = 8;
+	}
+
+	head += size;
+
+	dump_printf("\n%#Lx [%#x]: event: %d\n",
+		    head, event.header.size, event.header.type);
+
+	if (skip > 0)
+		head += skip;
+
+	if (!session_done())
+		goto more;
+done:
+	err = 0;
+out_err:
+	return err;
+}
+
 int __perf_session__process_events(struct perf_session *self,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_event_ops *ops)
@@ -499,9 +612,13 @@ out_getcwd_err:
 		self->cwdlen = strlen(self->cwd);
 	}
 
-	err = __perf_session__process_events(self, self->header.data_offset,
-					     self->header.data_size,
-					     self->size, ops);
+	if (!self->fd_pipe)
+		err = __perf_session__process_events(self,
+						     self->header.data_offset,
+						     self->header.data_size,
+						     self->size, ops);
+	else
+		err = __perf_session__process_pipe_events(self, ops);
 out_err:
 	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 27f4c2dc715..5f789113665 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -27,6 +27,7 @@ struct perf_session {
 	u64			sample_type;
 	struct ref_reloc_sym	ref_reloc_sym;
 	int			fd;
+	bool			fd_pipe;
 	int			cwdlen;
 	char			*cwd;
 	char filename[0];
@@ -92,6 +93,9 @@ static inline struct map *
 	return map_groups__new_module(&self->kmaps, start, filename);
 }
 
+int do_read(int fd, void *buf, size_t size);
+void perf_session__update_sample_type(struct perf_session *self);
+
 #ifdef NO_NEWT_SUPPORT
 static inline int perf_session__browse_hists(struct rb_root *hists __used,
 					      u64 nr_hists __used,