22 files changed, 740 insertions, 353 deletions

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e437edb72417..deffb8c96071 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -14,7 +14,9 @@
 #include <linux/kernel.h>
 #include "debug.h"
 
-static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
+static int build_id__mark_dso_hit(event_t *event,
+				  struct sample_data *sample __used,
+				  struct perf_session *session)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -35,7 +37,8 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
 	return 0;
 }
 
-static int event__exit_del_thread(event_t *self, struct perf_session *session)
+static int event__exit_del_thread(event_t *self, struct sample_data *sample __used,
+				  struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, self->fork.tid);
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c8d81b00089d..01bbe8ecec3f 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -46,20 +46,16 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
-static int dump_printf_color(const char *fmt, const char *color, ...)
+#ifdef NO_NEWT_SUPPORT
+void ui__warning(const char *format, ...)
 {
 	va_list args;
-	int ret = 0;
 
-	if (dump_trace) {
-		va_start(args, color);
-		ret = color_vfprintf(stdout, color, fmt, args);
-		va_end(args);
-	}
-
-	return ret;
+	va_start(args, format);
+	vfprintf(stderr, format, args);
+	va_end(args);
 }
-
+#endif
 
 void trace_event(event_t *event)
 {
@@ -70,29 +66,29 @@ void trace_event(event_t *event)
 	if (!dump_trace)
 		return;
 
-	dump_printf(".");
-	dump_printf_color("\n. ... raw event: size %d bytes\n", color,
-			  event->header.size);
+	printf(".");
+	color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+		      event->header.size);
 
 	for (i = 0; i < event->header.size; i++) {
 		if ((i & 15) == 0) {
-			dump_printf(".");
-			dump_printf_color("  %04x: ", color, i);
+			printf(".");
+			color_fprintf(stdout, color, "  %04x: ", i);
 		}
 
-		dump_printf_color(" %02x", color, raw_event[i]);
+		color_fprintf(stdout, color, " %02x", raw_event[i]);
 
 		if (((i & 15) == 15) || i == event->header.size-1) {
-			dump_printf_color("  ", color);
+			color_fprintf(stdout, color, "  ");
 			for (j = 0; j < 15-(i & 15); j++)
-				dump_printf_color("   ", color);
+				color_fprintf(stdout, color, "   ");
 			for (j = i & ~15; j <= i; j++) {
-				dump_printf_color("%c", color,
-						isprint(raw_event[j]) ?
-						raw_event[j] : '.');
+				color_fprintf(stdout, color, "%c",
+					      isprint(raw_event[j]) ?
+					      raw_event[j] : '.');
 			}
-			dump_printf_color("\n", color);
+			color_fprintf(stdout, color, "\n");
 		}
 	}
-	dump_printf(".\n");
+	printf(".\n");
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 7b514082bbaf..ca35fd66b5df 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -35,4 +35,6 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #include "ui/progress.h"
 #endif
 
+void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dab9e754a281..e4cdc1ebe0fb 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -24,11 +24,19 @@ const char *event__name[] = {
 	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
+static struct sample_data synth_sample = {
+	.pid	   = -1,
+	.tid	   = -1,
+	.time	   = -1,
+	.stream_id = -1,
+	.cpu	   = -1,
+	.period	   = 1,
+};
+
+static pid_t event__synthesize_comm(event_t *event, pid_t pid, int full,
 				    event__handler_t process,
 				    struct perf_session *session)
 {
-	event_t ev;
 	char filename[PATH_MAX];
 	char bf[BUFSIZ];
 	FILE *fp;
@@ -49,34 +57,39 @@ out_race:
 		return 0;
 	}
 
-	memset(&ev.comm, 0, sizeof(ev.comm));
-	while (!ev.comm.comm[0] || !ev.comm.pid) {
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			goto out_failure;
+	memset(&event->comm, 0, sizeof(event->comm));
+
+	while (!event->comm.comm[0] || !event->comm.pid) {
+		if (fgets(bf, sizeof(bf), fp) == NULL) {
+			pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
+			goto out;
+		}
 
 		if (memcmp(bf, "Name:", 5) == 0) {
 			char *name = bf + 5;
 			while (*name && isspace(*name))
 				++name;
 			size = strlen(name) - 1;
-			memcpy(ev.comm.comm, name, size++);
+			memcpy(event->comm.comm, name, size++);
 		} else if (memcmp(bf, "Tgid:", 5) == 0) {
 			char *tgids = bf + 5;
 			while (*tgids && isspace(*tgids))
 				++tgids;
-			tgid = ev.comm.pid = atoi(tgids);
+			tgid = event->comm.pid = atoi(tgids);
 		}
 	}
 
-	ev.comm.header.type = PERF_RECORD_COMM;
+	event->comm.header.type = PERF_RECORD_COMM;
 	size = ALIGN(size, sizeof(u64));
-	ev.comm.header.size = sizeof(ev.comm) - (sizeof(ev.comm.comm) - size);
-
+	memset(event->comm.comm + size, 0, session->id_hdr_size);
+	event->comm.header.size = (sizeof(event->comm) -
+				(sizeof(event->comm.comm) - size) +
+				session->id_hdr_size);
 	if (!full) {
-		ev.comm.tid = pid;
+		event->comm.tid = pid;
 
-		process(&ev, session);
-		goto out_fclose;
+		process(event, &synth_sample, session);
+		goto out;
 	}
 
 	snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
@@ -91,22 +104,19 @@ out_race:
 		if (*end)
 			continue;
 
-		ev.comm.tid = pid;
+		event->comm.tid = pid;
 
-		process(&ev, session);
+		process(event, &synth_sample, session);
 	}
-	closedir(tasks);
 
-out_fclose:
+	closedir(tasks);
+out:
 	fclose(fp);
-	return tgid;
 
-out_failure:
-	pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
-	return -1;
+	return tgid;
 }
 
-static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
+static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid,
 					 event__handler_t process,
 					 struct perf_session *session)
 {
@@ -124,29 +134,25 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 		return -1;
 	}
 
+	event->header.type = PERF_RECORD_MMAP;
+	/*
+	 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+	 */
+	event->header.misc = PERF_RECORD_MISC_USER;
+
 	while (1) {
 		char bf[BUFSIZ], *pbf = bf;
-		event_t ev = {
-			.header = {
-				.type = PERF_RECORD_MMAP,
-				/*
-				 * Just like the kernel, see __perf_event_mmap
-				 * in kernel/perf_event.c
-				 */
-				.misc = PERF_RECORD_MISC_USER,
-			 },
-		};
 		int n;
 		size_t size;
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = hex2u64(pbf, &ev.mmap.start);
+		n = hex2u64(pbf, &event->mmap.start);
 		if (n < 0)
 			continue;
 		pbf += n + 1;
-		n = hex2u64(pbf, &ev.mmap.len);
+		n = hex2u64(pbf, &event->mmap.len);
 		if (n < 0)
 			continue;
 		pbf += n + 3;
@@ -161,19 +167,21 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 				continue;
 
 			pbf += 3;
-			n = hex2u64(pbf, &ev.mmap.pgoff);
+			n = hex2u64(pbf, &event->mmap.pgoff);
 
 			size = strlen(execname);
 			execname[size - 1] = '\0'; /* Remove \n */
-			memcpy(ev.mmap.filename, execname, size);
+			memcpy(event->mmap.filename, execname, size);
 			size = ALIGN(size, sizeof(u64));
-			ev.mmap.len -= ev.mmap.start;
-			ev.mmap.header.size = (sizeof(ev.mmap) -
-					       (sizeof(ev.mmap.filename) - size));
-			ev.mmap.pid = tgid;
-			ev.mmap.tid = pid;
-
-			process(&ev, session);
+			event->mmap.len -= event->mmap.start;
+			event->mmap.header.size = (sizeof(event->mmap) -
+					        (sizeof(event->mmap.filename) - size));
+			memset(event->mmap.filename + size, 0, session->id_hdr_size);
+			event->mmap.header.size += session->id_hdr_size;
+			event->mmap.pid = tgid;
+			event->mmap.tid = pid;
+
+			process(event, &synth_sample, session);
 		}
 	}
 
@@ -187,20 +195,27 @@ int event__synthesize_modules(event__handler_t process,
 {
 	struct rb_node *nd;
 	struct map_groups *kmaps = &machine->kmaps;
-	u16 misc;
+	event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
+
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP;
 
 	/*
 	 * kernel uses 0 for user space maps, see kernel/perf_event.c
 	 * __perf_event_mmap
 	 */
 	if (machine__is_host(machine))
-		misc = PERF_RECORD_MISC_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
 	else
-		misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
 	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
 	     nd; nd = rb_next(nd)) {
-		event_t ev;
 		size_t size;
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 
@@ -208,39 +223,78 @@ int event__synthesize_modules(event__handler_t process,
 			continue;
 
 		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
-		memset(&ev, 0, sizeof(ev));
-		ev.mmap.header.misc = misc;
-		ev.mmap.header.type = PERF_RECORD_MMAP;
-		ev.mmap.header.size = (sizeof(ev.mmap) -
-				        (sizeof(ev.mmap.filename) - size));
-		ev.mmap.start = pos->start;
-		ev.mmap.len   = pos->end - pos->start;
-		ev.mmap.pid   = machine->pid;
-
-		memcpy(ev.mmap.filename, pos->dso->long_name,
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+				        (sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, session->id_hdr_size);
+		event->mmap.header.size += session->id_hdr_size;
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pid   = machine->pid;
+
+		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		process(&ev, session);
+		process(event, &synth_sample, session);
 	}
 
+	free(event);
 	return 0;
 }
 
-int event__synthesize_thread(pid_t pid, event__handler_t process,
-			     struct perf_session *session)
+static int __event__synthesize_thread(event_t *comm_event, event_t *mmap_event,
+				      pid_t pid, event__handler_t process,
+				      struct perf_session *session)
 {
-	pid_t tgid = event__synthesize_comm(pid, 1, process, session);
+	pid_t tgid = event__synthesize_comm(comm_event, pid, 1, process,
+					    session);
 	if (tgid == -1)
 		return -1;
-	return event__synthesize_mmap_events(pid, tgid, process, session);
+	return event__synthesize_mmap_events(mmap_event, pid, tgid,
+					     process, session);
+}
+
+int event__synthesize_thread(pid_t pid, event__handler_t process,
+			     struct perf_session *session)
+{
+	event_t *comm_event, *mmap_event;
+	int err = -1;
+
+	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	err = __event__synthesize_thread(comm_event, mmap_event, pid,
+					 process, session);
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
 }
 
-void event__synthesize_threads(event__handler_t process,
-			       struct perf_session *session)
+int event__synthesize_threads(event__handler_t process,
+			      struct perf_session *session)
 {
 	DIR *proc;
 	struct dirent dirent, *next;
+	event_t *comm_event, *mmap_event;
+	int err = -1;
+
+	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
 
 	proc = opendir("/proc");
+	if (proc == NULL)
+		goto out_free_mmap;
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -249,10 +303,18 @@ void event__synthesize_threads(event__handler_t process,
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		event__synthesize_thread(pid, process, session);
+		__event__synthesize_thread(comm_event, mmap_event, pid,
+					   process, session);
 	}
 
 	closedir(proc);
+	err = 0;
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
 }
 
 struct process_symbol_args {
@@ -286,18 +348,20 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 	char path[PATH_MAX];
 	char name_buff[PATH_MAX];
 	struct map *map;
-
-	event_t ev = {
-		.header = {
-			.type = PERF_RECORD_MMAP,
-		},
-	};
+	int err;
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
 	struct process_symbol_args args = { .name = symbol_name, };
+	event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
+
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
 
 	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
 	if (machine__is_host(machine)) {
@@ -305,10 +369,10 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
 		 * see kernel/perf_event.c __perf_event_mmap
 		 */
-		ev.header.misc = PERF_RECORD_MISC_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
 		filename = "/proc/kallsyms";
 	} else {
-		ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 		if (machine__is_default_guest(machine))
 			filename = (char *) symbol_conf.default_guest_kallsyms;
 		else {
@@ -321,17 +385,21 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 		return -ENOENT;
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
-	size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
+	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
 			"%s%s", mmap_name, symbol_name) + 1;
 	size = ALIGN(size, sizeof(u64));
-	ev.mmap.header.size = (sizeof(ev.mmap) -
-			(sizeof(ev.mmap.filename) - size));
-	ev.mmap.pgoff = args.start;
-	ev.mmap.start = map->start;
-	ev.mmap.len   = map->end - ev.mmap.start;
-	ev.mmap.pid   = machine->pid;
-
-	return process(&ev, session);
+	event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = (sizeof(event->mmap) -
+			(sizeof(event->mmap.filename) - size) + session->id_hdr_size);
+	event->mmap.pgoff = args.start;
+	event->mmap.start = map->start;
+	event->mmap.len   = map->end - event->mmap.start;
+	event->mmap.pid   = machine->pid;
+
+	err = process(event, &synth_sample, session);
+	free(event);
+
+	return err;
 }
 
 static void thread__comm_adjust(struct thread *self, struct hists *hists)
@@ -361,7 +429,8 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm,
 	return 0;
 }
 
-int event__process_comm(event_t *self, struct perf_session *session)
+int event__process_comm(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, self->comm.tid);
 
@@ -376,7 +445,8 @@ int event__process_comm(event_t *self, struct perf_session *session)
 	return 0;
 }
 
-int event__process_lost(event_t *self, struct perf_session *session)
+int event__process_lost(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
 	session->hists.stats.total_lost += self->lost.lost;
@@ -392,7 +462,7 @@ static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
 	 * a zero sized synthesized MMAP event for the kernel.
 	 */
 	if (maps[MAP__FUNCTION]->end == 0)
-		maps[MAP__FUNCTION]->end = ~0UL;
+		maps[MAP__FUNCTION]->end = ~0ULL;
 }
 
 static int event__process_kernel_mmap(event_t *self,
@@ -485,7 +555,8 @@ out_problem:
 	return -1;
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+int event__process_mmap(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	struct machine *machine;
 	struct thread *thread;
@@ -526,7 +597,8 @@ out_problem:
 	return 0;
 }
 
-int event__process_task(event_t *self, struct perf_session *session)
+int event__process_task(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, self->fork.tid);
 	struct thread *parent = perf_session__findnew(session, self->fork.ptid);
@@ -548,18 +620,19 @@ int event__process_task(event_t *self, struct perf_session *session)
 	return 0;
 }
 
-int event__process(event_t *event, struct perf_session *session)
+int event__process(event_t *event, struct sample_data *sample,
+		   struct perf_session *session)
 {
 	switch (event->header.type) {
 	case PERF_RECORD_COMM:
-		event__process_comm(event, session);
+		event__process_comm(event, sample, session);
 		break;
 	case PERF_RECORD_MMAP:
-		event__process_mmap(event, session);
+		event__process_mmap(event, sample, session);
 		break;
 	case PERF_RECORD_FORK:
 	case PERF_RECORD_EXIT:
-		event__process_task(event, session);
+		event__process_task(event, sample, session);
 		break;
 	default:
 		break;
@@ -674,32 +747,8 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 			     symbol_filter_t filter)
 {
 	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread;
-
-	event__parse_sample(self, session->sample_type, data);
+	struct thread *thread = perf_session__findnew(session, self->ip.pid);
 
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n",
-		    self->header.misc, data->pid, data->tid, data->ip,
-		    data->period, data->cpu);
-
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-		unsigned int i;
-
-		dump_printf("... chain: nr:%Lu\n", data->callchain->nr);
-
-		if (!ip_callchain__valid(data->callchain, self)) {
-			pr_debug("call-chain problem with event, "
-				 "skipping it.\n");
-			goto out_filtered;
-		}
-
-		if (dump_trace) {
-			for (i = 0; i < data->callchain->nr; i++)
-				dump_printf("..... %2d: %016Lx\n",
-					    i, data->callchain->ips[i]);
-		}
-	}
-	thread = perf_session__findnew(session, self->ip.pid);
 	if (thread == NULL)
 		return -1;
 
@@ -766,9 +815,65 @@ out_filtered:
 	return 0;
 }
 
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data)
+static int event__parse_id_sample(const event_t *event,
+				  struct perf_session *session,
+				  struct sample_data *sample)
 {
-	const u64 *array = event->sample.array;
+	const u64 *array;
+	u64 type;
+
+	sample->cpu = sample->pid = sample->tid = -1;
+	sample->stream_id = sample->id = sample->time = -1ULL;
+
+	if (!session->sample_id_all)
+		return 0;
+
+	array = event->sample.array;
+	array += ((event->header.size -
+		   sizeof(event->header)) / sizeof(u64)) - 1;
+	type = session->sample_type;
+
+	if (type & PERF_SAMPLE_CPU) {
+		u32 *p = (u32 *)array;
+		sample->cpu = *p;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		sample->stream_id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		sample->id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		sample->time = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u32 *p = (u32 *)array;
+		sample->pid = p[0];
+		sample->tid = p[1];
+	}
+
+	return 0;
+}
+
+int event__parse_sample(const event_t *event, struct perf_session *session,
+			struct sample_data *data)
+{
+	const u64 *array;
+	u64 type;
+
+	if (event->header.type != PERF_RECORD_SAMPLE)
+		return event__parse_id_sample(event, session, data);
+
+	array = event->sample.array;
+	type = session->sample_type;
 
 	if (type & PERF_SAMPLE_IP) {
 		data->ip = event->ip.ip;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8e790dae7026..a95ab18575ce 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -135,12 +135,15 @@ void event__print_totals(void);
 
 struct perf_session;
 
-typedef int (*event__handler_t)(event_t *event, struct perf_session *session);
+typedef int (*event__handler_synth_t)(event_t *event, 
+				      struct perf_session *session);
+typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
+				struct perf_session *session);
 
 int event__synthesize_thread(pid_t pid, event__handler_t process,
 			     struct perf_session *session);
-void event__synthesize_threads(event__handler_t process,
-			       struct perf_session *session);
+int event__synthesize_threads(event__handler_t process,
+			      struct perf_session *session);
 int event__synthesize_kernel_mmap(event__handler_t process,
 				struct perf_session *session,
 				struct machine *machine,
@@ -150,17 +153,23 @@ int event__synthesize_modules(event__handler_t process,
 			      struct perf_session *session,
 			      struct machine *machine);
 
-int event__process_comm(event_t *self, struct perf_session *session);
-int event__process_lost(event_t *self, struct perf_session *session);
-int event__process_mmap(event_t *self, struct perf_session *session);
-int event__process_task(event_t *self, struct perf_session *session);
-int event__process(event_t *event, struct perf_session *session);
+int event__process_comm(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process_lost(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process_mmap(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process_task(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process(event_t *event, struct sample_data *sample,
+		   struct perf_session *session);
 
 struct addr_location;
 int event__preprocess_sample(const event_t *self, struct perf_session *session,
 			     struct addr_location *al, struct sample_data *data,
 			     symbol_filter_t filter);
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data);
+int event__parse_sample(const event_t *event, struct perf_session *session,
+			struct sample_data *sample);
 
 extern const char *event__name[];
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 64a85bafde63..16a16021eaa6 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -152,6 +152,11 @@ void perf_header__set_feat(struct perf_header *self, int feat)
 	set_bit(feat, self->adds_features);
 }
 
+void perf_header__clear_feat(struct perf_header *self, int feat)
+{
+	clear_bit(feat, self->adds_features);
+}
+
 bool perf_header__has_feat(const struct perf_header *self, int feat)
 {
 	return test_bit(feat, self->adds_features);
@@ -431,8 +436,10 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 	int idx = 0, err;
 
 	session = container_of(self, struct perf_session, header);
-	if (perf_session__read_build_ids(session, true))
-		perf_header__set_feat(self, HEADER_BUILD_ID);
+
+	if (perf_header__has_feat(self, HEADER_BUILD_ID &&
+	    !perf_session__read_build_ids(session, true)))
+		perf_header__clear_feat(self, HEADER_BUILD_ID);
 
 	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
 	if (!nr_sections)
@@ -939,6 +946,24 @@ u64 perf_header__sample_type(struct perf_header *header)
 	return type;
 }
 
+bool perf_header__sample_id_all(const struct perf_header *header)
+{
+	bool value = false, first = true;
+	int i;
+
+	for (i = 0; i < header->attrs; i++) {
+		struct perf_header_attr *attr = header->attr[i];
+
+		if (first) {
+			value = attr->attr.sample_id_all;
+			first = false;
+		} else if (value != attr->attr.sample_id_all)
+			die("non matching sample_id_all");
+	}
+
+	return value;
+}
+
 struct perf_event_attr *
 perf_header__find_attr(u64 id, struct perf_header *header)
 {
@@ -985,21 +1010,23 @@ int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 
 	ev = malloc(size);
 
+	if (ev == NULL)
+		return -ENOMEM;
+
 	ev->attr.attr = *attr;
 	memcpy(ev->attr.id, id, ids * sizeof(u64));
 
 	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
 	ev->attr.header.size = size;
 
-	err = process(ev, session);
+	err = process(ev, NULL, session);
 
 	free(ev);
 
 	return err;
 }
 
-int event__synthesize_attrs(struct perf_header *self,
-			    event__handler_t process,
+int event__synthesize_attrs(struct perf_header *self, event__handler_t process,
 			    struct perf_session *session)
 {
 	struct perf_header_attr	*attr;
@@ -1069,7 +1096,7 @@ int event__synthesize_event_type(u64 event_id, char *name,
 	ev.event_type.header.size = sizeof(ev.event_type) -
 		(sizeof(ev.event_type.event_type.name) - size);
 
-	err = process(&ev, session);
+	err = process(&ev, NULL, session);
 
 	return err;
 }
@@ -1124,7 +1151,7 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
 	ev.tracing_data.header.size = sizeof(ev.tracing_data);
 	ev.tracing_data.size = aligned_size;
 
-	process(&ev, session);
+	process(&ev, NULL, session);
 
 	err = read_tracing_data(fd, pattrs, nb_events);
 	write_padded(fd, NULL, 0, padding);
@@ -1184,7 +1211,7 @@ int event__synthesize_build_id(struct dso *pos, u16 misc,
 	ev.build_id.header.size = sizeof(ev.build_id) + len;
 	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
 
-	err = process(&ev, session);
+	err = process(&ev, NULL, session);
 
 	return err;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 402ac2454cf8..6335965e1f93 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -81,9 +81,11 @@ void perf_header_attr__delete(struct perf_header_attr *self);
 int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
 
 u64 perf_header__sample_type(struct perf_header *header);
+bool perf_header__sample_id_all(const struct perf_header *header);
 struct perf_event_attr *
 perf_header__find_attr(u64 id, struct perf_header *header);
 void perf_header__set_feat(struct perf_header *self, int feat);
+void perf_header__clear_feat(struct perf_header *self, int feat);
 bool perf_header__has_feat(const struct perf_header *self, int feat);
 
 int perf_header__process_sections(struct perf_header *self, int fd,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 587d375d3430..ee789856a8c9 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,8 +52,10 @@ struct sym_priv {
 struct events_stats {
 	u64 total_period;
 	u64 total_lost;
+	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
 };
 
 enum hist_column {
diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h
new file mode 100644
index 000000000000..acffd5e4d1d4
--- /dev/null
+++ b/tools/perf/util/include/asm/cpufeature.h
@@ -0,0 +1,9 @@
+
+#ifndef PERF_CPUFEATURE_H
+#define PERF_CPUFEATURE_H
+
+/* cpufeature.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define X86_FEATURE_REP_GOOD 0
+
+#endif	/* PERF_CPUFEATURE_H */
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
new file mode 100644
index 000000000000..bb4198e7837a
--- /dev/null
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -0,0 +1,11 @@
+
+#ifndef PERF_DWARF2_H
+#define PERF_DWARF2_H
+
+/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define CFI_STARTPROC
+#define CFI_ENDPROC
+
+#endif	/* PERF_DWARF2_H */
+
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index bb4ac2e05385..8be0b968ca0b 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -13,6 +13,11 @@ static inline void set_bit(int nr, unsigned long *addr)
 	addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
 }
 
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+	addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+}
+
 static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
new file mode 100644
index 000000000000..06387cffe125
--- /dev/null
+++ b/tools/perf/util/include/linux/linkage.h
@@ -0,0 +1,13 @@
+
+#ifndef PERF_LINUX_LINKAGE_H_
+#define PERF_LINUX_LINKAGE_H_
+
+/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
+
+#define ENTRY(name)				\
+	.globl name;				\
+	name:
+
+#define ENDPROC(name)
+
+#endif	/* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4af5bd59cfd1..c305305a3884 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -434,7 +434,7 @@ parse_single_tracepoint_event(char *sys_name,
 	id = atoll(id_buf);
 	attr->config = id;
 	attr->type = PERF_TYPE_TRACEPOINT;
-	*strp = evt_name + evt_length;
+	*strp += strlen(sys_name) + evt_length + 1; /* + 1 for the ':' */
 
 	attr->sample_type |= PERF_SAMPLE_RAW;
 	attr->sample_type |= PERF_SAMPLE_TIME;
@@ -495,7 +495,7 @@ static enum event_result parse_tracepoint_event(const char **strp,
 				    struct perf_event_attr *attr)
 {
 	const char *evt_name;
-	char *flags;
+	char *flags = NULL, *comma_loc;
 	char sys_name[MAX_EVENT_LENGTH];
 	unsigned int sys_length, evt_length;
 
@@ -514,6 +514,11 @@ static enum event_result parse_tracepoint_event(const char **strp,
 	sys_name[sys_length] = '\0';
 	evt_name = evt_name + 1;
 
+	comma_loc = strchr(evt_name, ',');
+	if (comma_loc) {
+		/* take the event name up to the comma */
+		evt_name = strndup(evt_name, comma_loc - evt_name);
+	}
 	flags = strchr(evt_name, ':');
 	if (flags) {
 		/* split it out: */
@@ -524,9 +529,8 @@ static enum event_result parse_tracepoint_event(const char **strp,
 	evt_length = strlen(evt_name);
 	if (evt_length >= MAX_EVENT_LENGTH)
 		return EVT_FAILED;
-
 	if (strpbrk(evt_name, "*?")) {
-		*strp = evt_name + evt_length;
+		*strp += strlen(sys_name) + evt_length;
 		return parse_multiple_tracepoint_event(sys_name, evt_name,
 						       flags);
 	} else
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index c7d72dce54b2..abc31a1dac1a 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -119,6 +119,10 @@ struct option {
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
+	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
 
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bba69d455699..beaefc3c1223 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -34,9 +34,9 @@ extern int find_available_vars_at(int fd, struct perf_probe_event *pev,
 				  bool externs);
 
 #include <dwarf.h>
-#include <libdw.h>
-#include <libdwfl.h>
-#include <version.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <elfutils/version.h>
 
 struct probe_finder {
 	struct perf_probe_event	*pev;		/* Target probe event */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b059dc50cc2d..93680818e244 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -1,5 +1,5 @@
 /*
- * trace-event-perl.  Feed perf trace events to an embedded Perl interpreter.
+ * trace-event-perl.  Feed perf script events to an embedded Perl interpreter.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
@@ -411,8 +411,8 @@ static int perl_generate_script(const char *outfile)
 		return -1;
 	}
 
-	fprintf(ofp, "# perf trace event handlers, "
-		"generated by perf trace -g perl\n");
+	fprintf(ofp, "# perf script event handlers, "
+		"generated by perf script -g perl\n");
 
 	fprintf(ofp, "# Licensed under the terms of the GNU GPL"
 		" License version 2\n\n");
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 33a632523743..c6d99334bdfa 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -442,8 +442,8 @@ static int python_generate_script(const char *outfile)
 		fprintf(stderr, "couldn't open %s\n", fname);
 		return -1;
 	}
-	fprintf(ofp, "# perf trace event handlers, "
-		"generated by perf trace -g python\n");
+	fprintf(ofp, "# perf script event handlers, "
+		"generated by perf script -g python\n");
 
 	fprintf(ofp, "# Licensed under the terms of the GNU GPL"
 		" License version 2\n\n");
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fa9d652c2dc3..3074d38897e6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -65,9 +65,49 @@ out_close:
 	return -1;
 }
 
+static void perf_session__id_header_size(struct perf_session *session)
+{
+       struct sample_data *data;
+       u64 sample_type = session->sample_type;
+       u16 size = 0;
+
+	if (!session->sample_id_all)
+		goto out;
+
+       if (sample_type & PERF_SAMPLE_TID)
+               size += sizeof(data->tid) * 2;
+
+       if (sample_type & PERF_SAMPLE_TIME)
+               size += sizeof(data->time);
+
+       if (sample_type & PERF_SAMPLE_ID)
+               size += sizeof(data->id);
+
+       if (sample_type & PERF_SAMPLE_STREAM_ID)
+               size += sizeof(data->stream_id);
+
+       if (sample_type & PERF_SAMPLE_CPU)
+               size += sizeof(data->cpu) * 2;
+out:
+       session->id_hdr_size = size;
+}
+
+void perf_session__set_sample_id_all(struct perf_session *session, bool value)
+{
+	session->sample_id_all = value;
+	perf_session__id_header_size(session);
+}
+
+void perf_session__set_sample_type(struct perf_session *session, u64 type)
+{
+	session->sample_type = type;
+}
+
 void perf_session__update_sample_type(struct perf_session *self)
 {
 	self->sample_type = perf_header__sample_type(&self->header);
+	self->sample_id_all = perf_header__sample_id_all(&self->header);
+	perf_session__id_header_size(self);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -101,10 +141,20 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 	INIT_LIST_HEAD(&self->dead_threads);
 	self->hists_tree = RB_ROOT;
 	self->last_match = NULL;
-	self->mmap_window = 32;
+	/*
+	 * On 64bit we can mmap the data file in one go. No need for tiny mmap
+	 * slices. On 32bit we use 32MB.
+	 */
+#if BITS_PER_LONG == 64
+	self->mmap_window = ULLONG_MAX;
+#else
+	self->mmap_window = 32 * 1024 * 1024ULL;
+#endif
 	self->machines = RB_ROOT;
 	self->repipe = repipe;
-	INIT_LIST_HEAD(&self->ordered_samples.samples_head);
+	INIT_LIST_HEAD(&self->ordered_samples.samples);
+	INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
+	INIT_LIST_HEAD(&self->ordered_samples.to_free);
 	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
 
 	if (mode == O_RDONLY) {
@@ -230,7 +280,15 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
 	return syms;
 }
 
+static int process_event_synth_stub(event_t *event __used,
+				    struct perf_session *session __used)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_event_stub(event_t *event __used,
+			      struct sample_data *sample __used,
 			      struct perf_session *session __used)
 {
 	dump_printf(": unhandled!\n");
@@ -262,7 +320,7 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 	if (handler->exit == NULL)
 		handler->exit = process_event_stub;
 	if (handler->lost == NULL)
-		handler->lost = process_event_stub;
+		handler->lost = event__process_lost;
 	if (handler->read == NULL)
 		handler->read = process_event_stub;
 	if (handler->throttle == NULL)
@@ -270,13 +328,13 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 	if (handler->unthrottle == NULL)
 		handler->unthrottle = process_event_stub;
 	if (handler->attr == NULL)
-		handler->attr = process_event_stub;
+		handler->attr = process_event_synth_stub;
 	if (handler->event_type == NULL)
-		handler->event_type = process_event_stub;
+		handler->event_type = process_event_synth_stub;
 	if (handler->tracing_data == NULL)
-		handler->tracing_data = process_event_stub;
+		handler->tracing_data = process_event_synth_stub;
 	if (handler->build_id == NULL)
-		handler->build_id = process_event_stub;
+		handler->build_id = process_event_synth_stub;
 	if (handler->finished_round == NULL) {
 		if (handler->ordered_samples)
 			handler->finished_round = process_finished_round;
@@ -386,33 +444,58 @@ static event__swap_op event__swap_ops[] = {
 
 struct sample_queue {
 	u64			timestamp;
-	struct sample_event	*event;
+	event_t			*event;
 	struct list_head	list;
 };
 
+static void perf_session_free_sample_buffers(struct perf_session *session)
+{
+	struct ordered_samples *os = &session->ordered_samples;
+
+	while (!list_empty(&os->to_free)) {
+		struct sample_queue *sq;
+
+		sq = list_entry(os->to_free.next, struct sample_queue, list);
+		list_del(&sq->list);
+		free(sq);
+	}
+}
+
+static int perf_session_deliver_event(struct perf_session *session,
+				      event_t *event,
+				      struct sample_data *sample,
+				      struct perf_event_ops *ops);
+
 static void flush_sample_queue(struct perf_session *s,
 			       struct perf_event_ops *ops)
 {
-	struct list_head *head = &s->ordered_samples.samples_head;
-	u64 limit = s->ordered_samples.next_flush;
+	struct ordered_samples *os = &s->ordered_samples;
+	struct list_head *head = &os->samples;
 	struct sample_queue *tmp, *iter;
+	struct sample_data sample;
+	u64 limit = os->next_flush;
+	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
 
 	if (!ops->ordered_samples || !limit)
 		return;
 
 	list_for_each_entry_safe(iter, tmp, head, list) {
 		if (iter->timestamp > limit)
-			return;
-
-		if (iter == s->ordered_samples.last_inserted)
-			s->ordered_samples.last_inserted = NULL;
+			break;
 
-		ops->sample((event_t *)iter->event, s);
+		event__parse_sample(iter->event, s, &sample);
+		perf_session_deliver_event(s, iter->event, &sample, ops);
 
-		s->ordered_samples.last_flush = iter->timestamp;
+		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
-		free(iter->event);
-		free(iter);
+		list_add(&iter->list, &os->sample_cache);
+	}
+
+	if (list_empty(head)) {
+		os->last_sample = NULL;
+	} else if (last_ts <= limit) {
+		os->last_sample =
+			list_entry(head->prev, struct sample_queue, list);
 	}
 }
 
@@ -465,176 +548,224 @@ static int process_finished_round(event_t *event __used,
 	return 0;
 }
 
-static void __queue_sample_end(struct sample_queue *new, struct list_head *head)
-{
-	struct sample_queue *iter;
-
-	list_for_each_entry_reverse(iter, head, list) {
-		if (iter->timestamp < new->timestamp) {
-			list_add(&new->list, &iter->list);
-			return;
-		}
-	}
-
-	list_add(&new->list, head);
-}
-
-static void __queue_sample_before(struct sample_queue *new,
-				  struct sample_queue *iter,
-				  struct list_head *head)
-{
-	list_for_each_entry_continue_reverse(iter, head, list) {
-		if (iter->timestamp < new->timestamp) {
-			list_add(&new->list, &iter->list);
-			return;
-		}
-	}
-
-	list_add(&new->list, head);
-}
-
-static void __queue_sample_after(struct sample_queue *new,
-				 struct sample_queue *iter,
-				 struct list_head *head)
-{
-	list_for_each_entry_continue(iter, head, list) {
-		if (iter->timestamp > new->timestamp) {
-			list_add_tail(&new->list, &iter->list);
-			return;
-		}
-	}
-	list_add_tail(&new->list, head);
-}
-
 /* The queue is ordered by time */
-static void __queue_sample_event(struct sample_queue *new,
-				 struct perf_session *s)
+static void __queue_event(struct sample_queue *new, struct perf_session *s)
 {
-	struct sample_queue *last_inserted = s->ordered_samples.last_inserted;
-	struct list_head *head = &s->ordered_samples.samples_head;
+	struct ordered_samples *os = &s->ordered_samples;
+	struct sample_queue *sample = os->last_sample;
+	u64 timestamp = new->timestamp;
+	struct list_head *p;
 
+	os->last_sample = new;
 
-	if (!last_inserted) {
-		__queue_sample_end(new, head);
+	if (!sample) {
+		list_add(&new->list, &os->samples);
+		os->max_timestamp = timestamp;
 		return;
 	}
 
 	/*
-	 * Most of the time the current event has a timestamp
-	 * very close to the last event inserted, unless we just switched
-	 * to another event buffer. Having a sorting based on a list and
-	 * on the last inserted event that is close to the current one is
-	 * probably more efficient than an rbtree based sorting.
+	 * last_sample might point to some random place in the list as it's
+	 * the last queued event. We expect that the new event is close to
+	 * this.
 	 */
-	if (last_inserted->timestamp >= new->timestamp)
-		__queue_sample_before(new, last_inserted, head);
-	else
-		__queue_sample_after(new, last_inserted, head);
+	if (sample->timestamp <= timestamp) {
+		while (sample->timestamp <= timestamp) {
+			p = sample->list.next;
+			if (p == &os->samples) {
+				list_add_tail(&new->list, &os->samples);
+				os->max_timestamp = timestamp;
+				return;
+			}
+			sample = list_entry(p, struct sample_queue, list);
+		}
+		list_add_tail(&new->list, &sample->list);
+	} else {
+		while (sample->timestamp > timestamp) {
+			p = sample->list.prev;
+			if (p == &os->samples) {
+				list_add(&new->list, &os->samples);
+				return;
+			}
+			sample = list_entry(p, struct sample_queue, list);
+		}
+		list_add(&new->list, &sample->list);
+	}
 }
 
-static int queue_sample_event(event_t *event, struct sample_data *data,
-			      struct perf_session *s)
+#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
+
+static int perf_session_queue_event(struct perf_session *s, event_t *event,
+				    struct sample_data *data)
 {
+	struct ordered_samples *os = &s->ordered_samples;
+	struct list_head *sc = &os->sample_cache;
 	u64 timestamp = data->time;
 	struct sample_queue *new;
 
+	if (!timestamp)
+		return -ETIME;
 
 	if (timestamp < s->ordered_samples.last_flush) {
 		printf("Warning: Timestamp below last timeslice flush\n");
 		return -EINVAL;
 	}
 
-	new = malloc(sizeof(*new));
-	if (!new)
-		return -ENOMEM;
-
-	new->timestamp = timestamp;
-
-	new->event = malloc(event->header.size);
-	if (!new->event) {
-		free(new);
-		return -ENOMEM;
+	if (!list_empty(sc)) {
+		new = list_entry(sc->next, struct sample_queue, list);
+		list_del(&new->list);
+	} else if (os->sample_buffer) {
+		new = os->sample_buffer + os->sample_buffer_idx;
+		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
+			os->sample_buffer = NULL;
+	} else {
+		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
+		if (!os->sample_buffer)
+			return -ENOMEM;
+		list_add(&os->sample_buffer->list, &os->to_free);
+		os->sample_buffer_idx = 2;
+		new = os->sample_buffer + 1;
 	}
 
-	memcpy(new->event, event, event->header.size);
-
-	__queue_sample_event(new, s);
-	s->ordered_samples.last_inserted = new;
+	new->timestamp = timestamp;
+	new->event = event;
 
-	if (new->timestamp > s->ordered_samples.max_timestamp)
-		s->ordered_samples.max_timestamp = new->timestamp;
+	__queue_event(new, s);
 
 	return 0;
 }
 
-static int perf_session__process_sample(event_t *event, struct perf_session *s,
-					struct perf_event_ops *ops)
+static void callchain__dump(struct sample_data *sample)
 {
-	struct sample_data data;
-
-	if (!ops->ordered_samples)
-		return ops->sample(event, s);
+	unsigned int i;
 
-	bzero(&data, sizeof(struct sample_data));
-	event__parse_sample(event, s->sample_type, &data);
+	if (!dump_trace)
+		return;
 
-	queue_sample_event(event, &data, s);
+	printf("... chain: nr:%Lu\n", sample->callchain->nr);
 
-	return 0;
+	for (i = 0; i < sample->callchain->nr; i++)
+		printf("..... %2d: %016Lx\n", i, sample->callchain->ips[i]);
 }
 
-static int perf_session__process_event(struct perf_session *self,
+static void perf_session__print_tstamp(struct perf_session *session,
 				       event_t *event,
-				       struct perf_event_ops *ops,
-				       u64 offset, u64 head)
+				       struct sample_data *sample)
 {
-	trace_event(event);
-
-	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]);
-		hists__inc_nr_events(&self->hists, event->header.type);
+	if (event->header.type != PERF_RECORD_SAMPLE &&
+	    !session->sample_id_all) {
+		fputs("-1 -1 ", stdout);
+		return;
 	}
 
-	if (self->header.needs_swap && event__swap_ops[event->header.type])
-		event__swap_ops[event->header.type](event);
+	if ((session->sample_type & PERF_SAMPLE_CPU))
+		printf("%u ", sample->cpu);
+
+	if (session->sample_type & PERF_SAMPLE_TIME)
+		printf("%Lu ", sample->time);
+}
 
+static int perf_session_deliver_event(struct perf_session *session,
+				      event_t *event,
+				      struct sample_data *sample,
+				      struct perf_event_ops *ops)
+{
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		return perf_session__process_sample(event, self, ops);
+		return ops->sample(event, sample, session);
 	case PERF_RECORD_MMAP:
-		return ops->mmap(event, self);
+		return ops->mmap(event, sample, session);
 	case PERF_RECORD_COMM:
-		return ops->comm(event, self);
+		return ops->comm(event, sample, session);
 	case PERF_RECORD_FORK:
-		return ops->fork(event, self);
+		return ops->fork(event, sample, session);
 	case PERF_RECORD_EXIT:
-		return ops->exit(event, self);
+		return ops->exit(event, sample, session);
 	case PERF_RECORD_LOST:
-		return ops->lost(event, self);
+		return ops->lost(event, sample, session);
 	case PERF_RECORD_READ:
-		return ops->read(event, self);
+		return ops->read(event, sample, session);
 	case PERF_RECORD_THROTTLE:
-		return ops->throttle(event, self);
+		return ops->throttle(event, sample, session);
 	case PERF_RECORD_UNTHROTTLE:
-		return ops->unthrottle(event, self);
+		return ops->unthrottle(event, sample, session);
+	default:
+		++session->hists.stats.nr_unknown_events;
+		return -1;
+	}
+}
+
+static int perf_session__process_event(struct perf_session *session,
+				       event_t *event,
+				       struct perf_event_ops *ops,
+				       u64 file_offset)
+{
+	struct sample_data sample;
+	int ret;
+
+	trace_event(event);
+
+	if (session->header.needs_swap && event__swap_ops[event->header.type])
+		event__swap_ops[event->header.type](event);
+
+	if (event->header.type >= PERF_RECORD_MMAP &&
+	    event->header.type <= PERF_RECORD_SAMPLE) {
+		event__parse_sample(event, session, &sample);
+		if (dump_trace)
+			perf_session__print_tstamp(session, event, &sample);
+	}
+
+	if (event->header.type < PERF_RECORD_HEADER_MAX) {
+		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
+			    file_offset, event->header.size,
+			    event__name[event->header.type]);
+		hists__inc_nr_events(&session->hists, event->header.type);
+	}
+
+	/* These events are processed right away */
+	switch (event->header.type) {
+	case PERF_RECORD_SAMPLE:
+		dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n",
+			    event->header.misc,
+			    sample.pid, sample.tid, sample.ip, sample.period);
+
+		if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
+			if (!ip_callchain__valid(sample.callchain, event)) {
+				pr_debug("call-chain problem with event, "
+					 "skipping it.\n");
+				++session->hists.stats.nr_invalid_chains;
+				session->hists.stats.total_invalid_chains +=
+					sample.period;
+				return 0;
+			}
+
+			callchain__dump(&sample);
+		}
+		break;
+
 	case PERF_RECORD_HEADER_ATTR:
-		return ops->attr(event, self);
+		return ops->attr(event, session);
 	case PERF_RECORD_HEADER_EVENT_TYPE:
-		return ops->event_type(event, self);
+		return ops->event_type(event, session);
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
-		lseek(self->fd, offset + head, SEEK_SET);
-		return ops->tracing_data(event, self);
+		lseek(session->fd, file_offset, SEEK_SET);
+		return ops->tracing_data(event, session);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return ops->build_id(event, self);
+		return ops->build_id(event, session);
 	case PERF_RECORD_FINISHED_ROUND:
-		return ops->finished_round(event, self, ops);
+		return ops->finished_round(event, session, ops);
 	default:
-		++self->hists.stats.nr_unknown_events;
-		return -1;
+		break;
 	}
+
+	if (ops->ordered_samples) {
+		ret = perf_session_queue_event(session, event, &sample);
+		if (ret != -ETIME)
+			return ret;
+	}
+
+	return perf_session_deliver_event(session, event, &sample, ops);
 }
 
 void perf_event_header__bswap(struct perf_event_header *self)
@@ -724,8 +855,7 @@ more:
 	}
 
 	if (size == 0 ||
-	    (skip = perf_session__process_event(self, &event, ops,
-						0, head)) < 0) {
+	    (skip = perf_session__process_event(self, &event, ops, head)) < 0) {
 		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
 			    head, event.header.size, event.header.type);
 		/*
@@ -751,82 +881,93 @@ more:
 done:
 	err = 0;
 out_err:
+	perf_session_free_sample_buffers(self);
 	return err;
 }
 
-int __perf_session__process_events(struct perf_session *self,
+int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_event_ops *ops)
 {
-	int err, mmap_prot, mmap_flags;
-	u64 head, shift;
-	u64 offset = 0;
-	size_t	page_size;
+	u64 head, page_offset, file_offset, file_pos, progress_next;
+	int err, mmap_prot, mmap_flags, map_idx = 0;
+	struct ui_progress *progress;
+	size_t	page_size, mmap_size;
+	char *buf, *mmaps[8];
 	event_t *event;
 	uint32_t size;
-	char *buf;
-	struct ui_progress *progress = ui_progress__new("Processing events...",
-							self->size);
-	if (progress == NULL)
-		return -1;
 
 	perf_event_ops__fill_defaults(ops);
 
 	page_size = sysconf(_SC_PAGESIZE);
 
-	head = data_offset;
-	shift = page_size * (head / page_size);
-	offset += shift;
-	head -= shift;
+	page_offset = page_size * (data_offset / page_size);
+	file_offset = page_offset;
+	head = data_offset - page_offset;
+
+	if (data_offset + data_size < file_size)
+		file_size = data_offset + data_size;
+
+	progress_next = file_size / 16;
+	progress = ui_progress__new("Processing events...", file_size);
+	if (progress == NULL)
+		return -1;
+
+	mmap_size = session->mmap_window;
+	if (mmap_size > file_size)
+		mmap_size = file_size;
+
+	memset(mmaps, 0, sizeof(mmaps));
 
 	mmap_prot  = PROT_READ;
 	mmap_flags = MAP_SHARED;
 
-	if (self->header.needs_swap) {
+	if (session->header.needs_swap) {
 		mmap_prot  |= PROT_WRITE;
 		mmap_flags = MAP_PRIVATE;
 	}
 remap:
-	buf = mmap(NULL, page_size * self->mmap_window, mmap_prot,
-		   mmap_flags, self->fd, offset);
+	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd,
+		   file_offset);
 	if (buf == MAP_FAILED) {
 		pr_err("failed to mmap file\n");
 		err = -errno;
 		goto out_err;
 	}
+	mmaps[map_idx] = buf;
+	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
+	file_pos = file_offset + head;
 
 more:
 	event = (event_t *)(buf + head);
-	ui_progress__update(progress, offset);
 
-	if (self->header.needs_swap)
+	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 	size = event->header.size;
 	if (size == 0)
 		size = 8;
 
-	if (head + event->header.size >= page_size * self->mmap_window) {
-		int munmap_ret;
-
-		shift = page_size * (head / page_size);
-
-		munmap_ret = munmap(buf, page_size * self->mmap_window);
-		assert(munmap_ret == 0);
+	if (head + event->header.size >= mmap_size) {
+		if (mmaps[map_idx]) {
+			munmap(mmaps[map_idx], mmap_size);
+			mmaps[map_idx] = NULL;
+		}
 
-		offset += shift;
-		head -= shift;
+		page_offset = page_size * (head / page_size);
+		file_offset += page_offset;
+		head -= page_offset;
 		goto remap;
 	}
 
 	size = event->header.size;
 
 	dump_printf("\n%#Lx [%#x]: event: %d\n",
-		    offset + head, event->header.size, event->header.type);
+		    file_pos, event->header.size, event->header.type);
 
 	if (size == 0 ||
-	    perf_session__process_event(self, event, ops, offset, head) < 0) {
+	    perf_session__process_event(session, event, ops, file_pos) < 0) {
 		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
-			    offset + head, event->header.size,
+			    file_offset + head, event->header.size,
 			    event->header.type);
 		/*
 		 * assume we lost track of the stream, check alignment, and
@@ -839,19 +980,49 @@ more:
 	}
 
 	head += size;
+	file_pos += size;
 
-	if (offset + head >= data_offset + data_size)
-		goto done;
+	if (file_pos >= progress_next) {
+		progress_next += file_size / 16;
+		ui_progress__update(progress, file_pos);
+	}
 
-	if (offset + head < file_size)
+	if (file_pos < file_size)
 		goto more;
-done:
+
 	err = 0;
 	/* do the final flush for ordered samples */
-	self->ordered_samples.next_flush = ULLONG_MAX;
-	flush_sample_queue(self, ops);
+	session->ordered_samples.next_flush = ULLONG_MAX;
+	flush_sample_queue(session, ops);
 out_err:
 	ui_progress__delete(progress);
+
+	if (ops->lost == event__process_lost &&
+	    session->hists.stats.total_lost != 0) {
+		ui__warning("Processed %Lu events and LOST %Lu!\n\n"
+			    "Check IO/CPU overload!\n\n",
+			    session->hists.stats.total_period,
+			    session->hists.stats.total_lost);
+	}
+
+	if (session->hists.stats.nr_unknown_events != 0) {
+		ui__warning("Found %u unknown events!\n\n"
+			    "Is this an older tool processing a perf.data "
+			    "file generated by a more recent tool?\n\n"
+			    "If that is not the case, consider "
+			    "reporting to linux-kernel@vger.kernel.org.\n\n",
+			    session->hists.stats.nr_unknown_events);
+	}
+
+ 	if (session->hists.stats.nr_invalid_chains != 0) {
+ 		ui__warning("Found invalid callchains!\n\n"
+ 			    "%u out of %u events were discarded for this reason.\n\n"
+ 			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
+ 			    session->hists.stats.nr_invalid_chains,
+ 			    session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
+ 	}
+
+	perf_session_free_sample_buffers(session);
 	return err;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9fa0fc2a863f..ac36f99f14af 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -17,8 +17,12 @@ struct ordered_samples {
 	u64			last_flush;
 	u64			next_flush;
 	u64			max_timestamp;
-	struct list_head	samples_head;
-	struct sample_queue	*last_inserted;
+	struct list_head	samples;
+	struct list_head	sample_cache;
+	struct list_head	to_free;
+	struct sample_queue	*sample_buffer;
+	struct sample_queue	*last_sample;
+	int			sample_buffer_idx;
 };
 
 struct perf_session {
@@ -42,6 +46,8 @@ struct perf_session {
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
+	bool			sample_id_all;
+	u16			id_hdr_size;
 	int			cwdlen;
 	char			*cwd;
 	struct ordered_samples	ordered_samples;
@@ -50,7 +56,9 @@ struct perf_session {
 
 struct perf_event_ops;
 
-typedef int (*event_op)(event_t *self, struct perf_session *session);
+typedef int (*event_op)(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+typedef int (*event_synth_op)(event_t *self, struct perf_session *session);
 typedef int (*event_op2)(event_t *self, struct perf_session *session,
 			 struct perf_event_ops *ops);
 
@@ -63,8 +71,8 @@ struct perf_event_ops {
 			lost,
 			read,
 			throttle,
-			unthrottle,
-			attr,
+			unthrottle;
+	event_synth_op	attr,
 			event_type,
 			tracing_data,
 			build_id;
@@ -100,6 +108,8 @@ int perf_session__create_kernel_maps(struct perf_session *self);
 
 int do_read(int fd, void *buf, size_t size);
 void perf_session__update_sample_type(struct perf_session *self);
+void perf_session__set_sample_id_all(struct perf_session *session, bool value);
+void perf_session__set_sample_type(struct perf_session *session, u64 type);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b62a553cc67d..f44fa541d56e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -170,7 +170,7 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
 		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
-	return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
+	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
 /* --sort symbol */
@@ -196,7 +196,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
 
 	if (verbose) {
 		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-		ret += repsep_snprintf(bf, size, "%*Lx %c ",
+		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
 				       BITS_PER_LONG / 4, self->ip, o);
 	}
 
@@ -205,7 +205,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
 		ret += repsep_snprintf(bf + ret, size - ret, "%s",
 				       self->ms.sym->name);
 	else
-		ret += repsep_snprintf(bf + ret, size - ret, "%*Lx",
+		ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
 				       BITS_PER_LONG / 4, self->ip);
 
 	return ret;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index d628c8d1cf5e..c217b12f178c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -121,7 +121,7 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
 	 * We still haven't the actual symbols, so guess the
 	 * last map final address.
 	 */
-	curr->end = ~0UL;
+	curr->end = ~0ULL;
 }
 
 static void map_groups__fixup_end(struct map_groups *self)
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 056c69521a38..7b5a8926624e 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -104,10 +104,24 @@ out_destroy_form:
 	return rc;
 }
 
-static const char yes[] = "Yes", no[] = "No";
+static const char yes[] = "Yes", no[] = "No",
+		  warning_str[] = "Warning!", ok[] = "Ok";
 
 bool ui__dialog_yesno(const char *msg)
 {
 	/* newtWinChoice should really be accepting const char pointers... */
 	return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1;
 }
+
+void ui__warning(const char *format, ...)
+{
+	va_list args;
+
+	va_start(args, format);
+	if (use_browser > 0)
+		newtWinMessagev((char *)warning_str, (char *)ok,
+				(char *)format, args);
+	else
+		vfprintf(stderr, format, args);
+	va_end(args);
+}