Merge branch 'linus' into x86/apic-cleanups

Conflicts:
	arch/x86/include/asm/io_apic.h

Merge reason: Resolve the conflict, update to a more recent -rc base

Signed-off-by: Ingo Molnar <mingo@elte.hu>

40 files changed, 1863 insertions, 675 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/cpumap.c b/tools/perf/util/cpumap.c
index 0f9b8d7a7d7e..3ccaa1043383 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -4,32 +4,53 @@
 #include <assert.h>
 #include <stdio.h>
 
-int cpumap[MAX_NR_CPUS];
-
-static int default_cpu_map(void)
+static struct cpu_map *cpu_map__default_new(void)
 {
-	int nr_cpus, i;
+	struct cpu_map *cpus;
+	int nr_cpus;
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	assert(nr_cpus <= MAX_NR_CPUS);
-	assert((int)nr_cpus >= 0);
+	if (nr_cpus < 0)
+		return NULL;
+
+	cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+	if (cpus != NULL) {
+		int i;
+		for (i = 0; i < nr_cpus; ++i)
+			cpus->map[i] = i;
 
-	for (i = 0; i < nr_cpus; ++i)
-		cpumap[i] = i;
+		cpus->nr = nr_cpus;
+	}
 
-	return nr_cpus;
+	return cpus;
 }
 
-static int read_all_cpu_map(void)
+static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 {
+	size_t payload_size = nr_cpus * sizeof(int);
+	struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+
+	if (cpus != NULL) {
+		cpus->nr = nr_cpus;
+		memcpy(cpus->map, tmp_cpus, payload_size);
+	}
+
+	return cpus;
+}
+
+static struct cpu_map *cpu_map__read_all_cpu_map(void)
+{
+	struct cpu_map *cpus = NULL;
 	FILE *onlnf;
 	int nr_cpus = 0;
+	int *tmp_cpus = NULL, *tmp;
+	int max_entries = 0;
 	int n, cpu, prev;
 	char sep;
 
 	onlnf = fopen("/sys/devices/system/cpu/online", "r");
 	if (!onlnf)
-		return default_cpu_map();
+		return cpu_map__default_new();
 
 	sep = 0;
 	prev = -1;
@@ -38,12 +59,28 @@ static int read_all_cpu_map(void)
 		if (n <= 0)
 			break;
 		if (prev >= 0) {
-			assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+			int new_max = nr_cpus + cpu - prev - 1;
+
+			if (new_max >= max_entries) {
+				max_entries = new_max + MAX_NR_CPUS / 2;
+				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				if (tmp == NULL)
+					goto out_free_tmp;
+				tmp_cpus = tmp;
+			}
+
 			while (++prev < cpu)
-				cpumap[nr_cpus++] = prev;
+				tmp_cpus[nr_cpus++] = prev;
+		}
+		if (nr_cpus == max_entries) {
+			max_entries += MAX_NR_CPUS;
+			tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+			if (tmp == NULL)
+				goto out_free_tmp;
+			tmp_cpus = tmp;
 		}
-		assert (nr_cpus < MAX_NR_CPUS);
-		cpumap[nr_cpus++] = cpu;
+
+		tmp_cpus[nr_cpus++] = cpu;
 		if (n == 2 && sep == '-')
 			prev = cpu;
 		else
@@ -51,24 +88,31 @@ static int read_all_cpu_map(void)
 		if (n == 1 || sep == '\n')
 			break;
 	}
-	fclose(onlnf);
-	if (nr_cpus > 0)
-		return nr_cpus;
 
-	return default_cpu_map();
+	if (nr_cpus > 0)
+		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
+	else
+		cpus = cpu_map__default_new();
+out_free_tmp:
+	free(tmp_cpus);
+	fclose(onlnf);
+	return cpus;
 }
 
-int read_cpu_map(const char *cpu_list)
+struct cpu_map *cpu_map__new(const char *cpu_list)
 {
+	struct cpu_map *cpus = NULL;
 	unsigned long start_cpu, end_cpu = 0;
 	char *p = NULL;
 	int i, nr_cpus = 0;
+	int *tmp_cpus = NULL, *tmp;
+	int max_entries = 0;
 
 	if (!cpu_list)
-		return read_all_cpu_map();
+		return cpu_map__read_all_cpu_map();
 
 	if (!isdigit(*cpu_list))
-		goto invalid;
+		goto out;
 
 	while (isdigit(*cpu_list)) {
 		p = NULL;
@@ -94,21 +138,42 @@ int read_cpu_map(const char *cpu_list)
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
-				if (cpumap[i] == (int)start_cpu)
+				if (tmp_cpus[i] == (int)start_cpu)
 					goto invalid;
 
-			assert(nr_cpus < MAX_NR_CPUS);
-			cpumap[nr_cpus++] = (int)start_cpu;
+			if (nr_cpus == max_entries) {
+				max_entries += MAX_NR_CPUS;
+				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				if (tmp == NULL)
+					goto invalid;
+				tmp_cpus = tmp;
+			}
+			tmp_cpus[nr_cpus++] = (int)start_cpu;
 		}
 		if (*p)
 			++p;
 
 		cpu_list = p;
 	}
-	if (nr_cpus > 0)
-		return nr_cpus;
 
-	return default_cpu_map();
+	if (nr_cpus > 0)
+		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
+	else
+		cpus = cpu_map__default_new();
 invalid:
-	return -1;
+	free(tmp_cpus);
+out:
+	return cpus;
+}
+
+struct cpu_map *cpu_map__dummy_new(void)
+{
+	struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+
+	if (cpus != NULL) {
+		cpus->nr = 1;
+		cpus->map[0] = -1;
+	}
+
+	return cpus;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 3e60f56e490e..f7a4f42f6307 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,7 +1,13 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
-extern int read_cpu_map(const char *cpu_list);
-extern int cpumap[];
+struct cpu_map {
+	int nr;
+	int map[];
+};
+
+struct cpu_map *cpu_map__new(const char *cpu_list);
+struct cpu_map *cpu_map__dummy_new(void);
+void *cpu_map__delete(struct cpu_map *map);
 
 #endif /* __PERF_CPUMAP_H */
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..2302ec051bb4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,7 +7,7 @@
 #include "strlist.h"
 #include "thread.h"
 
-const char *event__name[] = {
+static const char *event__name[] = {
 	[0]			 = "TOTAL",
 	[PERF_RECORD_MMAP]	 = "MMAP",
 	[PERF_RECORD_LOST]	 = "LOST",
@@ -22,13 +22,31 @@ const char *event__name[] = {
 	[PERF_RECORD_HEADER_EVENT_TYPE]	 = "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	 = "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
+	[PERF_RECORD_FINISHED_ROUND]	 = "FINISHED_ROUND",
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
+const char *event__get_event_name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(event__name))
+		return "INVALID";
+	if (!event__name[id])
+		return "UNKNOWN";
+	return event__name[id];
+}
+
+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 +67,39 @@ 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 +114,19 @@ 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 +144,25 @@ 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 +177,21 @@ 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 +205,27 @@ 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 +233,78 @@ 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 +313,18 @@ 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 {
@@ -260,7 +332,8 @@ struct process_symbol_args {
 	u64	   start;
 };
 
-static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
+static int find_symbol_cb(void *arg, const char *name, char type,
+			  u64 start, u64 end __used)
 {
 	struct process_symbol_args *args = arg;
 
@@ -286,18 +359,20 @@ 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 +380,10 @@ 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 +396,21 @@ 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 +440,8 @@ 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 +456,8 @@ 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 +473,7 @@ 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 +566,8 @@ 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 +608,8 @@ 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 +631,19 @@ 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 +758,8 @@ 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);
-
-	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);
+	struct thread *thread = perf_session__findnew(session, self->ip.pid);
 
-		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 +826,65 @@ 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..2b7e91902f10 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@ struct build_id_event {
 };
 
 enum perf_user_event_type { /* above any possible kernel type */
+	PERF_RECORD_USER_TYPE_START		= 64,
 	PERF_RECORD_HEADER_ATTR			= 64,
 	PERF_RECORD_HEADER_EVENT_TYPE		= 65,
 	PERF_RECORD_HEADER_TRACING_DATA		= 66,
@@ -135,12 +136,15 @@ 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,
@@ -150,18 +154,24 @@ 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[];
+const char *event__get_event_name(unsigned int id);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
new file mode 100644
index 000000000000..c95267e63c5b
--- /dev/null
+++ b/tools/perf/util/evsel.c
@@ -0,0 +1,186 @@
+#include "evsel.h"
+#include "../perf.h"
+#include "util.h"
+#include "cpumap.h"
+#include "thread.h"
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx)
+{
+	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+
+	if (evsel != NULL) {
+		evsel->idx	   = idx;
+		evsel->attr.type   = type;
+		evsel->attr.config = config;
+		INIT_LIST_HEAD(&evsel->node);
+	}
+
+	return evsel;
+}
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+	return evsel->fd != NULL ? 0 : -ENOMEM;
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+{
+	evsel->counts = zalloc((sizeof(*evsel->counts) +
+				(ncpus * sizeof(struct perf_counts_values))));
+	return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_fd(struct perf_evsel *evsel)
+{
+	xyarray__delete(evsel->fd);
+	evsel->fd = NULL;
+}
+
+void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < ncpus; cpu++)
+		for (thread = 0; thread < nthreads; ++thread) {
+			close(FD(evsel, cpu, thread));
+			FD(evsel, cpu, thread) = -1;
+		}
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+	assert(list_empty(&evsel->node));
+	xyarray__delete(evsel->fd);
+	free(evsel);
+}
+
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+			      int cpu, int thread, bool scale)
+{
+	struct perf_counts_values count;
+	size_t nv = scale ? 3 : 1;
+
+	if (FD(evsel, cpu, thread) < 0)
+		return -EINVAL;
+
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+		return -ENOMEM;
+
+	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
+		return -errno;
+
+	if (scale) {
+		if (count.run == 0)
+			count.val = 0;
+		else if (count.run < count.ena)
+			count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
+	} else
+		count.ena = count.run = 0;
+
+	evsel->counts->cpu[cpu] = count;
+	return 0;
+}
+
+int __perf_evsel__read(struct perf_evsel *evsel,
+		       int ncpus, int nthreads, bool scale)
+{
+	size_t nv = scale ? 3 : 1;
+	int cpu, thread;
+	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
+
+	aggr->val = 0;
+
+	for (cpu = 0; cpu < ncpus; cpu++) {
+		for (thread = 0; thread < nthreads; thread++) {
+			if (FD(evsel, cpu, thread) < 0)
+				continue;
+
+			if (readn(FD(evsel, cpu, thread),
+				  &count, nv * sizeof(u64)) < 0)
+				return -errno;
+
+			aggr->val += count.val;
+			if (scale) {
+				aggr->ena += count.ena;
+				aggr->run += count.run;
+			}
+		}
+	}
+
+	evsel->counts->scaled = 0;
+	if (scale) {
+		if (aggr->run == 0) {
+			evsel->counts->scaled = -1;
+			aggr->val = 0;
+			return 0;
+		}
+
+		if (aggr->run < aggr->ena) {
+			evsel->counts->scaled = 1;
+			aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
+		}
+	} else
+		aggr->ena = aggr->run = 0;
+
+	return 0;
+}
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
+{
+	int cpu;
+
+	if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, 1) < 0)
+		return -1;
+
+	for (cpu = 0; cpu < cpus->nr; cpu++) {
+		FD(evsel, cpu, 0) = sys_perf_event_open(&evsel->attr, -1,
+							cpus->map[cpu], -1, 0);
+		if (FD(evsel, cpu, 0) < 0)
+			goto out_close;
+	}
+
+	return 0;
+
+out_close:
+	while (--cpu >= 0) {
+		close(FD(evsel, cpu, 0));
+		FD(evsel, cpu, 0) = -1;
+	}
+	return -1;
+}
+
+int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
+{
+	int thread;
+
+	if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, 1, threads->nr))
+		return -1;
+
+	for (thread = 0; thread < threads->nr; thread++) {
+		FD(evsel, 0, thread) = sys_perf_event_open(&evsel->attr,
+							   threads->map[thread], -1, -1, 0);
+		if (FD(evsel, 0, thread) < 0)
+			goto out_close;
+	}
+
+	return 0;
+
+out_close:
+	while (--thread >= 0) {
+		close(FD(evsel, 0, thread));
+		FD(evsel, 0, thread) = -1;
+	}
+	return -1;
+}
+
+int perf_evsel__open(struct perf_evsel *evsel, 
+		     struct cpu_map *cpus, struct thread_map *threads)
+{
+	if (threads == NULL)
+		return perf_evsel__open_per_cpu(evsel, cpus);
+
+	return perf_evsel__open_per_thread(evsel, threads);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
new file mode 100644
index 000000000000..a0ccd69c3fc2
--- /dev/null
+++ b/tools/perf/util/evsel.h
@@ -0,0 +1,115 @@
+#ifndef __PERF_EVSEL_H
+#define __PERF_EVSEL_H 1
+
+#include <linux/list.h>
+#include <stdbool.h>
+#include "../../../include/linux/perf_event.h"
+#include "types.h"
+#include "xyarray.h"
+ 
+struct perf_counts_values {
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+struct perf_counts {
+	s8		   	  scaled;
+	struct perf_counts_values aggr;
+	struct perf_counts_values cpu[];
+};
+
+struct perf_evsel {
+	struct list_head	node;
+	struct perf_event_attr	attr;
+	char			*filter;
+	struct xyarray		*fd;
+	struct perf_counts	*counts;
+	int			idx;
+	void			*priv;
+};
+
+struct cpu_map;
+struct thread_map;
+
+struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx);
+void perf_evsel__delete(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_fd(struct perf_evsel *evsel);
+void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads);
+int perf_evsel__open(struct perf_evsel *evsel, 
+		     struct cpu_map *cpus, struct thread_map *threads);
+
+#define perf_evsel__match(evsel, t, c)		\
+	(evsel->attr.type == PERF_TYPE_##t &&	\
+	 evsel->attr.config == PERF_COUNT_##c)
+
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+			      int cpu, int thread, bool scale);
+
+/**
+ * perf_evsel__read_on_cpu - Read out the results on a CPU and thread
+ *
+ * @evsel - event selector to read value
+ * @cpu - CPU of interest
+ * @thread - thread of interest
+ */
+static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+					  int cpu, int thread)
+{
+	return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
+}
+
+/**
+ * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
+ *
+ * @evsel - event selector to read value
+ * @cpu - CPU of interest
+ * @thread - thread of interest
+ */
+static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
+						 int cpu, int thread)
+{
+	return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
+}
+
+int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
+		       bool scale);
+
+/**
+ * perf_evsel__read - Read the aggregate results on all CPUs
+ *
+ * @evsel - event selector to read value
+ * @ncpus - Number of cpus affected, from zero
+ * @nthreads - Number of threads affected, from zero
+ */
+static inline int perf_evsel__read(struct perf_evsel *evsel,
+				    int ncpus, int nthreads)
+{
+	return __perf_evsel__read(evsel, ncpus, nthreads, false);
+}
+
+/**
+ * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
+ *
+ * @evsel - event selector to read value
+ * @ncpus - Number of cpus affected, from zero
+ * @nthreads - Number of threads affected, from zero
+ */
+static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
+					  int ncpus, int nthreads)
+{
+	return __perf_evsel__read(evsel, ncpus, nthreads, true);
+}
+
+#endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d7e67b167ea3..989fa2dee2fd 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);
@@ -265,15 +270,16 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms)
 {
 	const size_t size = PATH_MAX;
-	char *filename = malloc(size),
+	char *realname = realpath(name, NULL),
+	     *filename = malloc(size),
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
-	if (filename == NULL || linkname == NULL)
+	if (realname == NULL || filename == NULL || linkname == NULL)
 		goto out_free;
 
 	len = snprintf(filename, size, "%s%s%s",
-		       debugdir, is_kallsyms ? "/" : "", name);
+		       debugdir, is_kallsyms ? "/" : "", realname);
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
@@ -283,7 +289,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 		if (is_kallsyms) {
 			 if (copyfile("/proc/kallsyms", filename))
 				goto out_free;
-		} else if (link(name, filename) && copyfile(name, filename))
+		} else if (link(realname, filename) && copyfile(name, filename))
 			goto out_free;
 	}
 
@@ -300,6 +306,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (symlink(targetname, linkname) == 0)
 		err = 0;
 out_free:
+	free(realname);
 	free(filename);
 	free(linkname);
 	return err;
@@ -431,8 +438,10 @@ 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)
@@ -454,7 +463,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 
 		/* Write trace info */
 		trace_sec->offset = lseek(fd, 0, SEEK_CUR);
-		read_tracing_data(fd, attrs, nr_counters);
+		read_tracing_data(fd, &evsel_list);
 		trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
 	}
 
@@ -597,7 +606,7 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 static int perf_header__getbuffer64(struct perf_header *self,
 				    int fd, void *buf, size_t size)
 {
-	if (do_read(fd, buf, size) <= 0)
+	if (readn(fd, buf, size) <= 0)
 		return -1;
 
 	if (self->needs_swap)
@@ -653,7 +662,7 @@ int perf_file_header__read(struct perf_file_header *self,
 {
 	lseek(fd, 0, SEEK_SET);
 
-	if (do_read(fd, self, sizeof(*self)) <= 0 ||
+	if (readn(fd, self, sizeof(*self)) <= 0 ||
 	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
 		return -1;
 
@@ -814,7 +823,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
 				       struct perf_header *ph, int fd,
 				       bool repipe)
 {
-	if (do_read(fd, self, sizeof(*self)) <= 0 ||
+	if (readn(fd, self, sizeof(*self)) <= 0 ||
 	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
 		return -1;
 
@@ -939,6 +948,24 @@ 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)
 {
@@ -946,11 +973,16 @@ perf_header__find_attr(u64 id, struct perf_header *header)
 
 	/*
 	 * We set id to -1 if the data file doesn't contain sample
-	 * ids. Check for this and avoid walking through the entire
-	 * list of ids which may be large.
+	 * ids. This can happen when the data file contains one type
+	 * of event and in that case, the header can still store the
+	 * event attribute information. Check for this and avoid
+	 * walking through the entire list of ids which may be large.
 	 */
-	if (id == -1ULL)
+	if (id == -1ULL) {
+		if (header->attrs > 0)
+			return &header->attr[0]->attr;
 		return NULL;
+	}
 
 	for (i = 0; i < header->attrs; i++) {
 		struct perf_header_attr *attr = header->attr[i];
@@ -980,21 +1012,23 @@ 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;
@@ -1064,7 +1098,7 @@ 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;
 }
@@ -1099,8 +1133,7 @@ int event__process_event_type(event_t *self,
 	return 0;
 }
 
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-				   int nb_events,
+int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
 				   event__handler_t process,
 				   struct perf_session *session __unused)
 {
@@ -1111,7 +1144,7 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
 	memset(&ev, 0, sizeof(ev));
 
 	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
-	size = read_tracing_data_size(fd, pattrs, nb_events);
+	size = read_tracing_data_size(fd, pattrs);
 	if (size <= 0)
 		return size;
 	aligned_size = ALIGN(size, sizeof(u64));
@@ -1119,9 +1152,9 @@ 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);
+	err = read_tracing_data(fd, pattrs);
 	write_padded(fd, NULL, 0, padding);
 
 	return aligned_size;
@@ -1179,7 +1212,7 @@ 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..33f16be7b72f 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,
@@ -111,8 +113,7 @@ int event__synthesize_event_types(event__handler_t process,
 int event__process_event_type(event_t *self,
 			      struct perf_session *session);
 
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-				   int nb_events,
+int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
 				   event__handler_t process,
 				   struct perf_session *session);
 int event__process_tracing_data(event_t *self,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2022e8740994..c749ba6136a0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -356,7 +356,7 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 
 static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 				     int depth, int depth_mask, int period,
-				     u64 total_samples, int hits,
+				     u64 total_samples, u64 hits,
 				     int left_margin)
 {
 	int i;
@@ -1092,6 +1092,12 @@ int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
 	FILE *file;
 	int err = 0;
 	u64 len;
+	char symfs_filename[PATH_MAX];
+
+	if (filename) {
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
+	}
 
 	if (filename == NULL) {
 		if (dso->has_build_id) {
@@ -1100,9 +1106,9 @@ int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
 			return -ENOMEM;
 		}
 		goto fallback;
-	} else if (readlink(filename, command, sizeof(command)) < 0 ||
+	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
 		   strstr(command, "[kernel.kallsyms]") ||
-		   access(filename, R_OK)) {
+		   access(symfs_filename, R_OK)) {
 		free(filename);
 fallback:
 		/*
@@ -1111,6 +1117,8 @@ fallback:
 		 * DSO is the same as when 'perf record' ran.
 		 */
 		filename = dso->long_name;
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
 		free_filename = false;
 	}
 
@@ -1137,7 +1145,7 @@ fallback:
 		 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
-		 filename, filename);
+		 symfs_filename, filename);
 
 	pr_debug("Executing: %s\n", command);
 
@@ -1168,10 +1176,13 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp)
 	size_t ret = 0;
 
 	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
-		if (!event__name[i])
+		const char *name = event__get_event_name(i);
+
+		if (!strcmp(name, "UNKNOWN"))
 			continue;
-		ret += fprintf(fp, "%10s events: %10d\n",
-			       event__name[i], self->stats.nr_events[i]);
+
+		ret += fprintf(fp, "%16s events: %10d\n", name,
+			       self->stats.nr_events[i]);
 	}
 
 	return ret;
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..649083f27e08 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,6 +1,7 @@
 #include "../../../include/linux/hw_breakpoint.h"
 #include "util.h"
 #include "../perf.h"
+#include "evsel.h"
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
@@ -12,8 +13,7 @@
 
 int				nr_counters;
 
-struct perf_event_attr		attrs[MAX_COUNTERS];
-char				*filters[MAX_COUNTERS];
+LIST_HEAD(evsel_list);
 
 struct event_symbol {
 	u8		type;
@@ -266,10 +266,10 @@ static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
 	return name;
 }
 
-const char *event_name(int counter)
+const char *event_name(struct perf_evsel *evsel)
 {
-	u64 config = attrs[counter].config;
-	int type = attrs[counter].type;
+	u64 config = evsel->attr.config;
+	int type = evsel->attr.type;
 
 	return __event_name(type, config);
 }
@@ -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
@@ -810,9 +814,6 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 			return -1;
 
 	for (;;) {
-		if (nr_counters == MAX_COUNTERS)
-			return -1;
-
 		memset(&attr, 0, sizeof(attr));
 		ret = parse_event_symbols(&str, &attr);
 		if (ret == EVT_FAILED)
@@ -822,8 +823,13 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 			return -1;
 
 		if (ret != EVT_HANDLED_ALL) {
-			attrs[nr_counters] = attr;
-			nr_counters++;
+			struct perf_evsel *evsel;
+			evsel = perf_evsel__new(attr.type, attr.config,
+						nr_counters);
+			if (evsel == NULL)
+				return -1;
+			list_add_tail(&evsel->node, &evsel_list);
+			++nr_counters;
 		}
 
 		if (*str == 0)
@@ -840,21 +846,22 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 int parse_filter(const struct option *opt __used, const char *str,
 		 int unset __used)
 {
-	int i = nr_counters - 1;
-	int len = strlen(str);
+	struct perf_evsel *last = NULL;
 
-	if (i < 0 || attrs[i].type != PERF_TYPE_TRACEPOINT) {
+	if (!list_empty(&evsel_list))
+		last = list_entry(evsel_list.prev, struct perf_evsel, node);
+
+	if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
 		fprintf(stderr,
 			"-F option should follow a -e tracepoint option\n");
 		return -1;
 	}
 
-	filters[i] = malloc(len + 1);
-	if (!filters[i]) {
+	last->filter = strdup(str);
+	if (last->filter == NULL) {
 		fprintf(stderr, "not enough memory to hold filter string\n");
 		return -1;
 	}
-	strcpy(filters[i], str);
 
 	return 0;
 }
@@ -906,6 +913,47 @@ static void print_tracepoint_events(void)
 }
 
 /*
+ * Check whether event is in <debugfs_mount_point>/tracing/events
+ */
+
+int is_valid_tracepoint(const char *event_string)
+{
+	DIR *sys_dir, *evt_dir;
+	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	char evt_path[MAXPATHLEN];
+	char dir_path[MAXPATHLEN];
+
+	if (debugfs_valid_mountpoint(debugfs_path))
+		return 0;
+
+	sys_dir = opendir(debugfs_path);
+	if (!sys_dir)
+		return 0;
+
+	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+
+		snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+			 sys_dirent.d_name);
+		evt_dir = opendir(dir_path);
+		if (!evt_dir)
+			continue;
+
+		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+			snprintf(evt_path, MAXPATHLEN, "%s:%s",
+				 sys_dirent.d_name, evt_dirent.d_name);
+			if (!strcmp(evt_path, event_string)) {
+				closedir(evt_dir);
+				closedir(sys_dir);
+				return 1;
+			}
+		}
+		closedir(evt_dir);
+	}
+	closedir(sys_dir);
+	return 0;
+}
+
+/*
  * Print the help text for the event symbols:
  */
 void print_events(void)
@@ -963,3 +1011,26 @@ void print_events(void)
 
 	exit(129);
 }
+
+int perf_evsel_list__create_default(void)
+{
+	struct perf_evsel *evsel = perf_evsel__new(PERF_TYPE_HARDWARE,
+						   PERF_COUNT_HW_CPU_CYCLES, 0);
+	if (evsel == NULL)
+		return -ENOMEM;
+
+	list_add(&evsel->node, &evsel_list);
+	++nr_counters;
+	return 0;
+}
+
+void perf_evsel_list__delete(void)
+{
+	struct perf_evsel *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &evsel_list, node) {
+		list_del_init(&pos->node);
+		perf_evsel__delete(pos);
+	}
+	nr_counters = 0;
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index fc4ab3fe877a..b82cafb83772 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -4,6 +4,16 @@
  * Parse symbolic events/counts passed in as options:
  */
 
+#include "../../../include/linux/perf_event.h"
+
+struct list_head;
+struct perf_evsel;
+
+extern struct list_head evsel_list;
+
+int perf_evsel_list__create_default(void);
+void perf_evsel_list__delete(void);
+
 struct option;
 
 struct tracepoint_path {
@@ -13,14 +23,11 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
-extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events);
+extern bool have_tracepoints(struct list_head *evsel_list);
 
 extern int			nr_counters;
 
-extern struct perf_event_attr attrs[MAX_COUNTERS];
-extern char *filters[MAX_COUNTERS];
-
-extern const char *event_name(int ctr);
+const char *event_name(struct perf_evsel *event);
 extern const char *__event_name(int type, u64 config);
 
 extern int parse_events(const struct option *opt, const char *str, int unset);
@@ -29,9 +36,9 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 #define EVENTS_HELP_MAX (128*1024)
 
 extern void print_events(void);
+extern int is_valid_tracepoint(const char *event_string);
 
 extern char debugfs_path[];
 extern int valid_debugfs_mount(const char *debugfs);
 
-
 #endif /* __PERF_PARSE_EVENTS_H */
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-event.c b/tools/perf/util/probe-event.c
index 3b6a5297bf16..128aaab0aeda 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -95,7 +95,7 @@ static int init_vmlinux(void)
 		goto out;
 
 	if (machine__create_kernel_maps(&machine) < 0) {
-		pr_debug("machine__create_kernel_maps ");
+		pr_debug("machine__create_kernel_maps() failed.\n");
 		goto out;
 	}
 out:
@@ -114,6 +114,8 @@ static struct symbol *__find_kernel_function_by_name(const char *name,
 const char *kernel_get_module_path(const char *module)
 {
 	struct dso *dso;
+	struct map *map;
+	const char *vmlinux_name;
 
 	if (module) {
 		list_for_each_entry(dso, &machine.kernel_dsos, node) {
@@ -123,10 +125,17 @@ const char *kernel_get_module_path(const char *module)
 		}
 		pr_debug("Failed to find module %s.\n", module);
 		return NULL;
+	}
+
+	map = machine.vmlinux_maps[MAP__FUNCTION];
+	dso = map->dso;
+
+	vmlinux_name = symbol_conf.vmlinux_name;
+	if (vmlinux_name) {
+		if (dso__load_vmlinux(dso, map, vmlinux_name, NULL) <= 0)
+			return NULL;
 	} else {
-		dso = machine.vmlinux_maps[MAP__FUNCTION]->dso;
-		if (dso__load_vmlinux_path(dso,
-			 machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
+		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
 			pr_debug("Failed to load kernel map.\n");
 			return NULL;
 		}
@@ -140,7 +149,8 @@ static int open_vmlinux(const char *module)
 {
 	const char *path = kernel_get_module_path(module);
 	if (!path) {
-		pr_err("Failed to find path of %s module", module ?: "kernel");
+		pr_err("Failed to find path of %s module.\n",
+		       module ?: "kernel");
 		return -ENOENT;
 	}
 	pr_debug("Try to open %s\n", path);
@@ -217,7 +227,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 		pr_warning("Warning: No dwarf info found in the vmlinux - "
 			"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
 		if (!need_dwarf) {
-			pr_debug("Trying to use symbols.\nn");
+			pr_debug("Trying to use symbols.\n");
 			return 0;
 		}
 	}
@@ -286,42 +296,49 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 #define LINEBUF_SIZE 256
 #define NR_ADDITIONAL_LINES 2
 
-static int show_one_line(FILE *fp, int l, bool skip, bool show_num)
+static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 {
 	char buf[LINEBUF_SIZE];
-	const char *color = PERF_COLOR_BLUE;
-
-	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-		goto error;
-	if (!skip) {
-		if (show_num)
-			fprintf(stdout, "%7d  %s", l, buf);
-		else
-			color_fprintf(stdout, color, "         %s", buf);
-	}
+	const char *color = show_num ? "" : PERF_COLOR_BLUE;
+	const char *prefix = NULL;
 
-	while (strlen(buf) == LINEBUF_SIZE - 1 &&
-	       buf[LINEBUF_SIZE - 2] != '\n') {
+	do {
 		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
 			goto error;
-		if (!skip) {
-			if (show_num)
-				fprintf(stdout, "%s", buf);
-			else
-				color_fprintf(stdout, color, "%s", buf);
+		if (skip)
+			continue;
+		if (!prefix) {
+			prefix = show_num ? "%7d  " : "         ";
+			color_fprintf(stdout, color, prefix, l);
 		}
-	}
+		color_fprintf(stdout, color, "%s", buf);
 
-	return 0;
+	} while (strchr(buf, '\n') == NULL);
+
+	return 1;
 error:
-	if (feof(fp))
-		pr_warning("Source file is shorter than expected.\n");
-	else
+	if (ferror(fp)) {
 		pr_warning("File read error: %s\n", strerror(errno));
+		return -1;
+	}
+	return 0;
+}
 
-	return -1;
+static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
+{
+	int rv = __show_one_line(fp, l, skip, show_num);
+	if (rv == 0) {
+		pr_warning("Source file is shorter than expected.\n");
+		rv = -1;
+	}
+	return rv;
 }
 
+#define show_one_line_with_num(f,l)	_show_one_line(f,l,false,true)
+#define show_one_line(f,l)		_show_one_line(f,l,false,false)
+#define skip_one_line(f,l)		_show_one_line(f,l,true,false)
+#define show_one_line_or_eof(f,l)	__show_one_line(f,l,false,false)
+
 /*
  * Show line-range always requires debuginfo to find source file and
  * line number.
@@ -370,7 +387,7 @@ int show_line_range(struct line_range *lr, const char *module)
 		fprintf(stdout, "<%s:%d>\n", lr->function,
 			lr->start - lr->offset);
 	else
-		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+		fprintf(stdout, "<%s:%d>\n", lr->path, lr->start);
 
 	fp = fopen(lr->path, "r");
 	if (fp == NULL) {
@@ -379,26 +396,30 @@ int show_line_range(struct line_range *lr, const char *module)
 		return -errno;
 	}
 	/* Skip to starting line number */
-	while (l < lr->start && ret >= 0)
-		ret = show_one_line(fp, l++, true, false);
-	if (ret < 0)
-		goto end;
+	while (l < lr->start) {
+		ret = skip_one_line(fp, l++);
+		if (ret < 0)
+			goto end;
+	}
 
 	list_for_each_entry(ln, &lr->line_list, list) {
-		while (ln->line > l && ret >= 0)
-			ret = show_one_line(fp, (l++) - lr->offset,
-					    false, false);
-		if (ret >= 0)
-			ret = show_one_line(fp, (l++) - lr->offset,
-					    false, true);
+		for (; ln->line > l; l++) {
+			ret = show_one_line(fp, l - lr->offset);
+			if (ret < 0)
+				goto end;
+		}
+		ret = show_one_line_with_num(fp, l++ - lr->offset);
 		if (ret < 0)
 			goto end;
 	}
 
 	if (lr->end == INT_MAX)
 		lr->end = l + NR_ADDITIONAL_LINES;
-	while (l <= lr->end && !feof(fp) && ret >= 0)
-		ret = show_one_line(fp, (l++) - lr->offset, false, false);
+	while (l <= lr->end) {
+		ret = show_one_line_or_eof(fp, l++ - lr->offset);
+		if (ret <= 0)
+			break;
+	}
 end:
 	fclose(fp);
 	return ret;
@@ -457,7 +478,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 
 	fd = open_vmlinux(module);
 	if (fd < 0) {
-		pr_warning("Failed to open debuginfo file.\n");
+		pr_warning("Failed to open debug information file.\n");
 		return fd;
 	}
 
@@ -517,56 +538,87 @@ int show_available_vars(struct perf_probe_event *pevs __unused,
 }
 #endif
 
+static int parse_line_num(char **ptr, int *val, const char *what)
+{
+	const char *start = *ptr;
+
+	errno = 0;
+	*val = strtol(*ptr, ptr, 0);
+	if (errno || *ptr == start) {
+		semantic_error("'%s' is not a valid number.\n", what);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Stuff 'lr' according to the line range described by 'arg'.
+ * The line range syntax is described by:
+ *
+ *         SRC[:SLN[+NUM|-ELN]]
+ *         FNC[:SLN[+NUM|-ELN]]
+ */
 int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
-	const char *ptr;
-	char *tmp;
-	/*
-	 * <Syntax>
-	 * SRC:SLN[+NUM|-ELN]
-	 * FUNC[:SLN[+NUM|-ELN]]
-	 */
-	ptr = strchr(arg, ':');
-	if (ptr) {
-		lr->start = (int)strtoul(ptr + 1, &tmp, 0);
-		if (*tmp == '+') {
-			lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0);
-			lr->end--;	/*
-					 * Adjust the number of lines here.
-					 * If the number of lines == 1, the
-					 * the end of line should be equal to
-					 * the start of line.
-					 */
-		} else if (*tmp == '-')
-			lr->end = (int)strtoul(tmp + 1, &tmp, 0);
-		else
-			lr->end = INT_MAX;
+	char *range, *name = strdup(arg);
+	int err;
+
+	if (!name)
+		return -ENOMEM;
+
+	lr->start = 0;
+	lr->end = INT_MAX;
+
+	range = strchr(name, ':');
+	if (range) {
+		*range++ = '\0';
+
+		err = parse_line_num(&range, &lr->start, "start line");
+		if (err)
+			goto err;
+
+		if (*range == '+' || *range == '-') {
+			const char c = *range++;
+
+			err = parse_line_num(&range, &lr->end, "end line");
+			if (err)
+				goto err;
+
+			if (c == '+') {
+				lr->end += lr->start;
+				/*
+				 * Adjust the number of lines here.
+				 * If the number of lines == 1, the
+				 * the end of line should be equal to
+				 * the start of line.
+				 */
+				lr->end--;
+			}
+		}
+
 		pr_debug("Line range is %d to %d\n", lr->start, lr->end);
+
+		err = -EINVAL;
 		if (lr->start > lr->end) {
 			semantic_error("Start line must be smaller"
 				       " than end line.\n");
-			return -EINVAL;
+			goto err;
 		}
-		if (*tmp != '\0') {
-			semantic_error("Tailing with invalid character '%d'.\n",
-				       *tmp);
-			return -EINVAL;
+		if (*range != '\0') {
+			semantic_error("Tailing with invalid str '%s'.\n", range);
+			goto err;
 		}
-		tmp = strndup(arg, (ptr - arg));
-	} else {
-		tmp = strdup(arg);
-		lr->end = INT_MAX;
 	}
 
-	if (tmp == NULL)
-		return -ENOMEM;
-
-	if (strchr(tmp, '.'))
-		lr->file = tmp;
+	if (strchr(name, '.'))
+		lr->file = name;
 	else
-		lr->function = tmp;
+		lr->function = name;
 
 	return 0;
+err:
+	free(name);
+	return err;
 }
 
 /* Check the name is good for event/group */
@@ -690,39 +742,40 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 
 	/* Exclusion check */
 	if (pp->lazy_line && pp->line) {
-		semantic_error("Lazy pattern can't be used with line number.");
+		semantic_error("Lazy pattern can't be used with"
+			       " line number.\n");
 		return -EINVAL;
 	}
 
 	if (pp->lazy_line && pp->offset) {
-		semantic_error("Lazy pattern can't be used with offset.");
+		semantic_error("Lazy pattern can't be used with offset.\n");
 		return -EINVAL;
 	}
 
 	if (pp->line && pp->offset) {
-		semantic_error("Offset can't be used with line number.");
+		semantic_error("Offset can't be used with line number.\n");
 		return -EINVAL;
 	}
 
 	if (!pp->line && !pp->lazy_line && pp->file && !pp->function) {
 		semantic_error("File always requires line number or "
-			       "lazy pattern.");
+			       "lazy pattern.\n");
 		return -EINVAL;
 	}
 
 	if (pp->offset && !pp->function) {
-		semantic_error("Offset requires an entry function.");
+		semantic_error("Offset requires an entry function.\n");
 		return -EINVAL;
 	}
 
 	if (pp->retprobe && !pp->function) {
-		semantic_error("Return probe requires an entry function.");
+		semantic_error("Return probe requires an entry function.\n");
 		return -EINVAL;
 	}
 
 	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
-			       "return probe.");
+			       "return probe.\n");
 		return -EINVAL;
 	}
 
@@ -996,7 +1049,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 
 	return tmp - buf;
 error:
-	pr_debug("Failed to synthesize perf probe argument: %s",
+	pr_debug("Failed to synthesize perf probe argument: %s\n",
 		 strerror(-ret));
 	return ret;
 }
@@ -1024,13 +1077,13 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 			goto error;
 	}
 	if (pp->file) {
-		len = strlen(pp->file) - 31;
-		if (len < 0)
-			len = 0;
-		tmp = strchr(pp->file + len, '/');
-		if (!tmp)
-			tmp = pp->file + len;
-		ret = e_snprintf(file, 32, "@%s", tmp + 1);
+		tmp = pp->file;
+		len = strlen(tmp);
+		if (len > 30) {
+			tmp = strchr(pp->file + len - 30, '/');
+			tmp = tmp ? tmp + 1 : pp->file + len - 30;
+		}
+		ret = e_snprintf(file, 32, "@%s", tmp);
 		if (ret <= 0)
 			goto error;
 	}
@@ -1046,7 +1099,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 
 	return buf;
 error:
-	pr_debug("Failed to synthesize perf probe point: %s",
+	pr_debug("Failed to synthesize perf probe point: %s\n",
 		 strerror(-ret));
 	if (buf)
 		free(buf);
@@ -1787,7 +1840,7 @@ static int del_trace_probe_event(int fd, const char *group,
 
 	ret = e_snprintf(buf, 128, "%s:%s", group, event);
 	if (ret < 0) {
-		pr_err("Failed to copy event.");
+		pr_err("Failed to copy event.\n");
 		return ret;
 	}
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 3991d73d1cff..ab83b6ac5d65 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -117,28 +117,6 @@ static void line_list__free(struct list_head *head)
 }
 
 /* Dwarf FL wrappers */
-
-static int __linux_kernel_find_elf(Dwfl_Module *mod,
-				   void **userdata,
-				   const char *module_name,
-				   Dwarf_Addr base,
-				   char **file_name, Elf **elfp)
-{
-	int fd;
-	const char *path = kernel_get_module_path(module_name);
-
-	if (path) {
-		fd = open(path, O_RDONLY);
-		if (fd >= 0) {
-			*file_name = strdup(path);
-			return fd;
-		}
-	}
-	/* If failed, try to call standard method */
-	return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
-					  file_name, elfp);
-}
-
 static char *debuginfo_path;	/* Currently dummy */
 
 static const Dwfl_Callbacks offline_callbacks = {
@@ -151,14 +129,6 @@ static const Dwfl_Callbacks offline_callbacks = {
 	.find_elf = dwfl_build_id_find_elf,
 };
 
-static const Dwfl_Callbacks kernel_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.find_elf = __linux_kernel_find_elf,
-	.section_address = dwfl_linux_kernel_module_section_address,
-};
-
 /* Get a Dwarf from offline image */
 static Dwarf *dwfl_init_offline_dwarf(int fd, Dwfl **dwflp, Dwarf_Addr *bias)
 {
@@ -185,6 +155,38 @@ error:
 	return dbg;
 }
 
+#if _ELFUTILS_PREREQ(0, 148)
+/* This method is buggy if elfutils is older than 0.148 */
+static int __linux_kernel_find_elf(Dwfl_Module *mod,
+				   void **userdata,
+				   const char *module_name,
+				   Dwarf_Addr base,
+				   char **file_name, Elf **elfp)
+{
+	int fd;
+	const char *path = kernel_get_module_path(module_name);
+
+	pr_debug2("Use file %s for %s\n", path, module_name);
+	if (path) {
+		fd = open(path, O_RDONLY);
+		if (fd >= 0) {
+			*file_name = strdup(path);
+			return fd;
+		}
+	}
+	/* If failed, try to call standard method */
+	return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
+					  file_name, elfp);
+}
+
+static const Dwfl_Callbacks kernel_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
+
+	.find_elf = __linux_kernel_find_elf,
+	.section_address = dwfl_linux_kernel_module_section_address,
+};
+
 /* Get a Dwarf from live kernel image */
 static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **dwflp,
 					  Dwarf_Addr *bias)
@@ -205,11 +207,34 @@ static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **dwflp,
 	dbg = dwfl_addrdwarf(*dwflp, addr, bias);
 	/* Here, check whether we could get a real dwarf */
 	if (!dbg) {
+		pr_debug("Failed to find kernel dwarf at %lx\n",
+			 (unsigned long)addr);
 		dwfl_end(*dwflp);
 		*dwflp = NULL;
 	}
 	return dbg;
 }
+#else
+/* With older elfutils, this just support kernel module... */
+static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr __used, Dwfl **dwflp,
+					  Dwarf_Addr *bias)
+{
+	int fd;
+	const char *path = kernel_get_module_path("kernel");
+
+	if (!path) {
+		pr_err("Failed to find vmlinux path\n");
+		return NULL;
+	}
+
+	pr_debug2("Use file %s for debuginfo\n", path);
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return NULL;
+
+	return dwfl_init_offline_dwarf(fd, dwflp, bias);
+}
+#endif
 
 /* Dwarf wrappers */
 
@@ -627,8 +652,8 @@ static_var:
 	regs = get_arch_regstr(regn);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
-		pr_warning("Mapping for DWARF register number %u "
-			   "missing on this architecture.", regn);
+		pr_warning("Mapping for the register number %u "
+			   "missing on this architecture.\n", regn);
 		return -ERANGE;
 	}
 
@@ -674,13 +699,14 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		if (ret != DW_TAG_pointer_type &&
 		    ret != DW_TAG_array_type) {
 			pr_warning("Failed to cast into string: "
-				   "%s(%s) is not a pointer nor array.",
+				   "%s(%s) is not a pointer nor array.\n",
 				   dwarf_diename(vr_die), dwarf_diename(&type));
 			return -EINVAL;
 		}
 		if (ret == DW_TAG_pointer_type) {
 			if (die_get_real_type(&type, &type) == NULL) {
-				pr_warning("Failed to get a type information.");
+				pr_warning("Failed to get a type"
+					   " information.\n");
 				return -ENOENT;
 			}
 			while (*ref_ptr)
@@ -695,7 +721,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		if (!die_compare_name(&type, "char") &&
 		    !die_compare_name(&type, "unsigned char")) {
 			pr_warning("Failed to cast into string: "
-				   "%s is not (unsigned) char *.",
+				   "%s is not (unsigned) char *.\n",
 				   dwarf_diename(vr_die));
 			return -EINVAL;
 		}
@@ -805,8 +831,8 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			return -EINVAL;
 		}
 		if (field->name[0] == '[') {
-			pr_err("Semantic error: %s is not a pointor nor array.",
-			       varname);
+			pr_err("Semantic error: %s is not a pointor"
+			       " nor array.\n", varname);
 			return -EINVAL;
 		}
 		if (field->ref) {
@@ -953,7 +979,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
 	name = dwarf_diename(sp_die);
 	if (name) {
 		if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-			pr_warning("Failed to get entry pc of %s\n",
+			pr_warning("Failed to get entry address of %s\n",
 				   dwarf_diename(sp_die));
 			return -ENOENT;
 		}
@@ -969,7 +995,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
 	if (retprobe) {
 		if (eaddr != paddr) {
 			pr_warning("Return probe must be on the head of"
-				   " a real function\n");
+				   " a real function.\n");
 			return -EINVAL;
 		}
 		tp->retprobe = true;
@@ -1008,7 +1034,7 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf)
 		Dwarf_Frame *frame;
 		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
-			pr_warning("Failed to get CFA on 0x%jx\n",
+			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
 			return -ENOENT;
 		}
@@ -1035,7 +1061,7 @@ static int find_probe_point_by_line(struct probe_finder *pf)
 	int ret = 0;
 
 	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found in this CU.\n");
+		pr_warning("No source lines found.\n");
 		return -ENOENT;
 	}
 
@@ -1137,7 +1163,7 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 	}
 
 	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found in this CU.\n");
+		pr_warning("No source lines found.\n");
 		return -ENOENT;
 	}
 
@@ -1195,7 +1221,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 	else {
 		/* Get probe address */
 		if (dwarf_entrypc(in_die, &addr) != 0) {
-			pr_warning("Failed to get entry pc of %s.\n",
+			pr_warning("Failed to get entry address of %s.\n",
 				   dwarf_diename(in_die));
 			param->retval = -ENOENT;
 			return DWARF_CB_ABORT;
@@ -1236,8 +1262,8 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 			param->retval = find_probe_point_lazy(sp_die, pf);
 		else {
 			if (dwarf_entrypc(sp_die, &pf->addr) != 0) {
-				pr_warning("Failed to get entry pc of %s.\n",
-					   dwarf_diename(sp_die));
+				pr_warning("Failed to get entry address of "
+					   "%s.\n", dwarf_diename(sp_die));
 				param->retval = -ENOENT;
 				return DWARF_CB_ABORT;
 			}
@@ -1279,7 +1305,7 @@ static int find_probes(int fd, struct probe_finder *pf)
 
 	dbg = dwfl_init_offline_dwarf(fd, &dwfl, &bias);
 	if (!dbg) {
-		pr_warning("No dwarf info found in the vmlinux - "
+		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
 		return -EBADF;
 	}
@@ -1524,7 +1550,7 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 	/* Open the live linux kernel */
 	dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias);
 	if (!dbg) {
-		pr_warning("No dwarf info found in the vmlinux - "
+		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
 		ret = -EINVAL;
 		goto end;
@@ -1534,7 +1560,8 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 	addr += bias;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr - bias, &cudie)) {
-		pr_warning("No CU DIE is found at %lx\n", addr);
+		pr_warning("Failed to find debug information for address %lx\n",
+			   addr);
 		ret = -EINVAL;
 		goto end;
 	}
@@ -1659,7 +1686,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
 	line_list__init(&lf->lr->line_list);
 	if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found in this CU.\n");
+		pr_warning("No source lines found.\n");
 		return -ENOENT;
 	}
 
@@ -1784,7 +1811,7 @@ int find_line_range(int fd, struct line_range *lr)
 
 	dbg = dwfl_init_offline_dwarf(fd, &dwfl, &bias);
 	if (!dbg) {
-		pr_warning("No dwarf info found in the vmlinux - "
+		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
 		return -EBADF;
 	}
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..6fb4694d05fa 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)
@@ -85,7 +125,9 @@ static void perf_session__destroy_kernel_maps(struct perf_session *self)
 	machines__destroy_guest_kernel_maps(&self->machines);
 }
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe)
+struct perf_session *perf_session__new(const char *filename, int mode,
+				       bool force, bool repipe,
+				       struct perf_event_ops *ops)
 {
 	size_t len = filename ? strlen(filename) + 1 : 0;
 	struct perf_session *self = zalloc(sizeof(*self) + len);
@@ -101,10 +143,20 @@ 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) {
@@ -120,6 +172,13 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 	}
 
 	perf_session__update_sample_type(self);
+
+	if (ops && ops->ordering_requires_timestamps &&
+	    ops->ordered_samples && !self->sample_id_all) {
+		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
+		ops->ordered_samples = false;
+	}
+
 out:
 	return self;
 out_free:
@@ -230,7 +289,15 @@ 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 +329,7 @@ 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 +337,13 @@ 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 +453,61 @@ static event__swap_op event__swap_ops[] = {
 
 struct sample_queue {
 	u64			timestamp;
-	struct sample_event	*event;
+	u64			file_offset;
+	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,
+				      u64 file_offset);
+
 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;
+			break;
 
-		if (iter == s->ordered_samples.last_inserted)
-			s->ordered_samples.last_inserted = NULL;
+		event__parse_sample(iter->event, s, &sample);
+		perf_session_deliver_event(s, iter->event, &sample, ops,
+					   iter->file_offset);
 
-		ops->sample((event_t *)iter->event, s);
-
-		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);
 	}
 }
 
@@ -465,178 +560,265 @@ 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, u64 file_offset)
 {
+	struct ordered_samples *os = &s->ordered_samples;
+	struct list_head *sc = &os->sample_cache;
 	u64 timestamp = data->time;
 	struct sample_queue *new;
 
+	if (!timestamp || timestamp == ~0ULL)
+		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;
+	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;
+	}
 
 	new->timestamp = timestamp;
+	new->file_offset = file_offset;
+	new->event = event;
 
-	new->event = malloc(event->header.size);
-	if (!new->event) {
-		free(new);
-		return -ENOMEM;
-	}
+	__queue_event(new, s);
 
-	memcpy(new->event, event, event->header.size);
+	return 0;
+}
 
-	__queue_sample_event(new, s);
-	s->ordered_samples.last_inserted = new;
+static void callchain__printf(struct sample_data *sample)
+{
+	unsigned int i;
 
-	if (new->timestamp > s->ordered_samples.max_timestamp)
-		s->ordered_samples.max_timestamp = new->timestamp;
+	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_sample(event_t *event, struct perf_session *s,
-					struct perf_event_ops *ops)
+static void perf_session__print_tstamp(struct perf_session *session,
+				       event_t *event,
+				       struct sample_data *sample)
 {
-	struct sample_data data;
+	if (event->header.type != PERF_RECORD_SAMPLE &&
+	    !session->sample_id_all) {
+		fputs("-1 -1 ", stdout);
+		return;
+	}
 
-	if (!ops->ordered_samples)
-		return ops->sample(event, s);
+	if ((session->sample_type & PERF_SAMPLE_CPU))
+		printf("%u ", sample->cpu);
 
-	bzero(&data, sizeof(struct sample_data));
-	event__parse_sample(event, s->sample_type, &data);
+	if (session->sample_type & PERF_SAMPLE_TIME)
+		printf("%Lu ", sample->time);
+}
 
-	queue_sample_event(event, &data, s);
+static void dump_event(struct perf_session *session, event_t *event,
+		       u64 file_offset, struct sample_data *sample)
+{
+	if (!dump_trace)
+		return;
 
-	return 0;
+	printf("\n%#Lx [%#x]: event: %d\n", file_offset, event->header.size,
+	       event->header.type);
+
+	trace_event(event);
+
+	if (sample)
+		perf_session__print_tstamp(session, event, sample);
+
+	printf("%#Lx [%#x]: PERF_RECORD_%s", file_offset, event->header.size,
+	       event__get_event_name(event->header.type));
 }
 
-static int perf_session__process_event(struct perf_session *self,
-				       event_t *event,
-				       struct perf_event_ops *ops,
-				       u64 offset, u64 head)
+static void dump_sample(struct perf_session *session, event_t *event,
+			struct sample_data *sample)
 {
-	trace_event(event);
+	if (!dump_trace)
+		return;
 
-	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);
-	}
+	printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
+	       sample->pid, sample->tid, sample->ip, sample->period);
 
-	if (self->header.needs_swap && event__swap_ops[event->header.type])
-		event__swap_ops[event->header.type](event);
+	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
+		callchain__printf(sample);
+}
+
+static int perf_session_deliver_event(struct perf_session *session,
+				      event_t *event,
+				      struct sample_data *sample,
+				      struct perf_event_ops *ops,
+				      u64 file_offset)
+{
+	dump_event(session, event, file_offset, sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		return perf_session__process_sample(event, self, ops);
+		dump_sample(session, event, sample);
+		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__preprocess_sample(struct perf_session *session,
+					   event_t *event, struct sample_data *sample)
+{
+	if (event->header.type != PERF_RECORD_SAMPLE ||
+	    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+		return 0;
+
+	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 -EINVAL;
+	}
+	return 0;
+}
+
+static int perf_session__process_user_event(struct perf_session *session, event_t *event,
+					    struct perf_event_ops *ops, u64 file_offset)
+{
+	dump_event(session, event, file_offset, NULL);
+
+	/* These events are processed right away */
+	switch (event->header.type) {
 	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;
+		return -EINVAL;
 	}
 }
 
+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;
+
+	if (session->header.needs_swap && event__swap_ops[event->header.type])
+		event__swap_ops[event->header.type](event);
+
+	if (event->header.type >= PERF_RECORD_HEADER_MAX)
+		return -EINVAL;
+
+	hists__inc_nr_events(&session->hists, event->header.type);
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return perf_session__process_user_event(session, event, ops, file_offset);
+
+	/*
+	 * For all kernel events we get the sample data
+	 */
+	event__parse_sample(event, session, &sample);
+
+	/* Preprocess sample records - precheck callchains */
+	if (perf_session__preprocess_sample(session, event, &sample))
+		return 0;
+
+	if (ops->ordered_samples) {
+		ret = perf_session_queue_event(session, event, &sample,
+					       file_offset);
+		if (ret != -ETIME)
+			return ret;
+	}
+
+	return perf_session_deliver_event(session, event, &sample, ops,
+					  file_offset);
+}
+
 void perf_event_header__bswap(struct perf_event_header *self)
 {
 	self->type = bswap_32(self->type);
@@ -656,21 +838,33 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 	return thread;
 }
 
-int do_read(int fd, void *buf, size_t size)
+static void perf_session__warn_about_errors(const struct perf_session *session,
+					    const struct perf_event_ops *ops)
 {
-	void *buf_start = buf;
-
-	while (size) {
-		int ret = read(fd, buf, size);
-
-		if (ret <= 0)
-			return ret;
+	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);
+	}
 
-		size -= ret;
-		buf += ret;
+	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);
 	}
 
-	return buf - buf_start;
+ 	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]);
+ 	}
 }
 
 #define session_done()	(*(volatile int *)(&session_done))
@@ -690,7 +884,7 @@ static int __perf_session__process_pipe_events(struct perf_session *self,
 
 	head = 0;
 more:
-	err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+	err = readn(self->fd, &event, sizeof(struct perf_event_header));
 	if (err <= 0) {
 		if (err == 0)
 			goto done;
@@ -710,8 +904,7 @@ more:
 	p += sizeof(struct perf_event_header);
 
 	if (size - sizeof(struct perf_event_header)) {
-		err = do_read(self->fd, p,
-			      size - sizeof(struct perf_event_header));
+		err = readn(self->fd, p, size - sizeof(struct perf_event_header));
 		if (err <= 0) {
 			if (err == 0) {
 				pr_err("unexpected end of event stream\n");
@@ -724,8 +917,7 @@ 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);
 		/*
@@ -740,9 +932,6 @@ more:
 
 	head += size;
 
-	dump_printf("\n%#Lx [%#x]: event: %d\n",
-		    head, event.header.size, event.header.type);
-
 	if (skip > 0)
 		head += skip;
 
@@ -751,82 +940,91 @@ more:
 done:
 	err = 0;
 out_err:
+	perf_session__warn_about_errors(self, ops);
+	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);
-
 	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 +1037,24 @@ 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);
+	perf_session__warn_about_errors(session, ops);
+	perf_session_free_sample_buffers(session);
 	return err;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9fa0fc2a863f..decd83f274fd 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);
 
@@ -63,16 +71,19 @@ struct perf_event_ops {
 			lost,
 			read,
 			throttle,
-			unthrottle,
-			attr,
+			unthrottle;
+	event_synth_op	attr,
 			event_type,
 			tracing_data,
 			build_id;
 	event_op2	finished_round;
 	bool		ordered_samples;
+	bool		ordering_requires_timestamps;
 };
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe);
+struct perf_session *perf_session__new(const char *filename, int mode,
+				       bool force, bool repipe,
+				       struct perf_event_ops *ops);
 void perf_session__delete(struct perf_session *self);
 
 void perf_event_header__bswap(struct perf_event_header *self);
@@ -98,8 +109,9 @@ void mem_bswap_64(void *src, int byte_size);
 
 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/string.c b/tools/perf/util/string.c
index 0409fc7c0058..8fc0bd3a3a4a 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -259,7 +259,7 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space)
 		if (!*pat)	/* Tail wild card matches all */
 			return true;
 		while (*str)
-			if (strglobmatch(str++, pat))
+			if (__match_glob(str++, pat, ignore_space))
 				return true;
 	}
 	return !*str && !*pat;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b39f499e575a..15ccfba8cdf8 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -22,6 +22,10 @@
 #include <limits.h>
 #include <sys/utsname.h>
 
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 128
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
@@ -41,6 +45,7 @@ struct symbol_conf symbol_conf = {
 	.exclude_other	  = true,
 	.use_modules	  = true,
 	.try_vmlinux_path = true,
+	.symfs            = "",
 };
 
 int dso__name_len(const struct dso *self)
@@ -92,7 +97,7 @@ static void symbols__fixup_end(struct rb_root *self)
 		prev = curr;
 		curr = rb_entry(nd, struct symbol, rb_node);
 
-		if (prev->end == prev->start)
+		if (prev->end == prev->start && prev->end != curr->start)
 			prev->end = curr->start - 1;
 	}
 
@@ -121,7 +126,7 @@ 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)
@@ -295,7 +300,9 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 {
 	struct rb_node **p = &self->rb_node;
 	struct rb_node *parent = NULL;
-	struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s;
+	struct symbol_name_rb_node *symn, *s;
+
+	symn = container_of(sym, struct symbol_name_rb_node, sym);
 
 	while (*p != NULL) {
 		parent = *p;
@@ -423,16 +430,25 @@ size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
 
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
-						     char type, u64 start))
+					  char type, u64 start, u64 end))
 {
 	char *line = NULL;
 	size_t n;
-	int err = 0;
+	int err = -1;
+	u64 prev_start = 0;
+	char prev_symbol_type = 0;
+	char *prev_symbol_name;
 	FILE *file = fopen(filename, "r");
 
 	if (file == NULL)
 		goto out_failure;
 
+	prev_symbol_name = malloc(KSYM_NAME_LEN);
+	if (prev_symbol_name == NULL)
+		goto out_close;
+
+	err = 0;
+
 	while (!feof(file)) {
 		u64 start;
 		int line_len, len;
@@ -452,14 +468,33 @@ int kallsyms__parse(const char *filename, void *arg,
 			continue;
 
 		symbol_type = toupper(line[len]);
-		symbol_name = line + len + 2;
+		len += 2;
+		symbol_name = line + len;
+		len = line_len - len;
 
-		err = process_symbol(arg, symbol_name, symbol_type, start);
-		if (err)
+		if (len >= KSYM_NAME_LEN) {
+			err = -1;
 			break;
+		}
+
+		if (prev_symbol_type) {
+			u64 end = start;
+			if (end != prev_start)
+				--end;
+			err = process_symbol(arg, prev_symbol_name,
+					     prev_symbol_type, prev_start, end);
+			if (err)
+				break;
+		}
+
+		memcpy(prev_symbol_name, symbol_name, len + 1);
+		prev_symbol_type = symbol_type;
+		prev_start = start;
 	}
 
+	free(prev_symbol_name);
 	free(line);
+out_close:
 	fclose(file);
 	return err;
 
@@ -481,7 +516,7 @@ static u8 kallsyms2elf_type(char type)
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,
-				       char type, u64 start)
+				       char type, u64 start, u64 end)
 {
 	struct symbol *sym;
 	struct process_kallsyms_args *a = arg;
@@ -490,11 +525,8 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	if (!symbol_type__is_a(type, a->map->type))
 		return 0;
 
-	/*
-	 * Will fix up the end later, when we have all symbols sorted.
-	 */
-	sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
-
+	sym = symbol__new(start, end - start + 1,
+			  kallsyms2elf_type(type), name);
 	if (sym == NULL)
 		return -ENOMEM;
 	/*
@@ -530,7 +562,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 	struct machine *machine = kmaps->machine;
 	struct map *curr_map = map;
 	struct symbol *pos;
-	int count = 0;
+	int count = 0, moved = 0;	
 	struct rb_root *root = &self->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
@@ -588,6 +620,11 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			char dso_name[PATH_MAX];
 			struct dso *dso;
 
+			if (count == 0) {
+				curr_map = map;
+				goto filter_symbol;
+			}
+
 			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
@@ -613,7 +650,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			map_groups__insert(kmaps, curr_map);
 			++kernel_range;
 		}
-
+filter_symbol:
 		if (filter && filter(curr_map, pos)) {
 discard_symbol:		rb_erase(&pos->rb_node, root);
 			symbol__delete(pos);
@@ -621,8 +658,9 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 			if (curr_map != map) {
 				rb_erase(&pos->rb_node, root);
 				symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
-			}
-			count++;
+				++moved;
+			} else
+				++count;
 		}
 	}
 
@@ -632,7 +670,7 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 		dso__set_loaded(curr_map->dso, curr_map->type);
 	}
 
-	return count;
+	return count + moved;
 }
 
 int dso__load_kallsyms(struct dso *self, const char *filename,
@@ -641,7 +679,6 @@ int dso__load_kallsyms(struct dso *self, const char *filename,
 	if (dso__load_all_kallsyms(self, filename, map) < 0)
 		return -1;
 
-	symbols__fixup_end(&self->symbols[map->type]);
 	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
 		self->origin = DSO__ORIG_GUEST_KERNEL;
 	else
@@ -831,8 +868,11 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 	char sympltname[1024];
 	Elf *elf;
 	int nr = 0, symidx, fd, err = 0;
+	char name[PATH_MAX];
 
-	fd = open(self->long_name, O_RDONLY);
+	snprintf(name, sizeof(name), "%s%s",
+		 symbol_conf.symfs, self->long_name);
+	fd = open(name, O_RDONLY);
 	if (fd < 0)
 		goto out;
 
@@ -1444,16 +1484,19 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	     self->origin++) {
 		switch (self->origin) {
 		case DSO__ORIG_BUILD_ID_CACHE:
-			if (dso__build_id_filename(self, name, size) == NULL)
+			/* skip the locally configured cache if a symfs is given */
+			if (symbol_conf.symfs[0] ||
+			    (dso__build_id_filename(self, name, size) == NULL)) {
 				continue;
+			}
 			break;
 		case DSO__ORIG_FEDORA:
-			snprintf(name, size, "/usr/lib/debug%s.debug",
-				 self->long_name);
+			snprintf(name, size, "%s/usr/lib/debug%s.debug",
+				 symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_UBUNTU:
-			snprintf(name, size, "/usr/lib/debug%s",
-				 self->long_name);
+			snprintf(name, size, "%s/usr/lib/debug%s",
+				 symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_BUILDID: {
 			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
@@ -1465,19 +1508,26 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 					  sizeof(self->build_id),
 					  build_id_hex);
 			snprintf(name, size,
-				 "/usr/lib/debug/.build-id/%.2s/%s.debug",
-				 build_id_hex, build_id_hex + 2);
+				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
 			}
 			break;
 		case DSO__ORIG_DSO:
-			snprintf(name, size, "%s", self->long_name);
+			snprintf(name, size, "%s%s",
+			     symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_GUEST_KMODULE:
 			if (map->groups && map->groups->machine)
 				root_dir = map->groups->machine->root_dir;
 			else
 				root_dir = "";
-			snprintf(name, size, "%s%s", root_dir, self->long_name);
+			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
+				 root_dir, self->long_name);
+			break;
+
+		case DSO__ORIG_KMODULE:
+			snprintf(name, size, "%s%s", symbol_conf.symfs,
+				 self->long_name);
 			break;
 
 		default:
@@ -1772,21 +1822,24 @@ out_failure:
 	return -1;
 }
 
-static int dso__load_vmlinux(struct dso *self, struct map *map,
-			     const char *vmlinux, symbol_filter_t filter)
+int dso__load_vmlinux(struct dso *self, struct map *map,
+		      const char *vmlinux, symbol_filter_t filter)
 {
 	int err = -1, fd;
+	char symfs_vmlinux[PATH_MAX];
 
-	fd = open(vmlinux, O_RDONLY);
+	snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s/%s",
+		 symbol_conf.symfs, vmlinux);
+	fd = open(symfs_vmlinux, O_RDONLY);
 	if (fd < 0)
 		return -1;
 
 	dso__set_loaded(self, map->type);
-	err = dso__load_sym(self, map, vmlinux, fd, filter, 0, 0);
+	err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
 	close(fd);
 
 	if (err > 0)
-		pr_debug("Using %s for symbols\n", vmlinux);
+		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 
 	return err;
 }
@@ -1828,8 +1881,8 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	const char *kallsyms_filename = NULL;
 	char *kallsyms_allocated_filename = NULL;
 	/*
-	 * Step 1: if the user specified a vmlinux filename, use it and only
-	 * it, reporting errors to the user if it cannot be used.
+	 * Step 1: if the user specified a kallsyms or vmlinux filename, use
+	 * it and only it, reporting errors to the user if it cannot be used.
 	 *
 	 * For instance, try to analyse an ARM perf.data file _without_ a
 	 * build-id, or if the user specifies the wrong path to the right
@@ -1842,6 +1895,11 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	 * validation in dso__load_vmlinux and will bail out if they don't
 	 * match.
 	 */
+	if (symbol_conf.kallsyms_name != NULL) {
+		kallsyms_filename = symbol_conf.kallsyms_name;
+		goto do_kallsyms;
+	}
+
 	if (symbol_conf.vmlinux_name != NULL) {
 		err = dso__load_vmlinux(self, map,
 					symbol_conf.vmlinux_name, filter);
@@ -1859,6 +1917,10 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 			goto out_fixup;
 	}
 
+	/* do not try local files if a symfs was given */
+	if (symbol_conf.symfs[0] != 0)
+		return -1;
+
 	/*
 	 * Say the kernel DSO was created when processing the build-id header table,
 	 * we have a build-id, so check if it is the same as the running kernel,
@@ -2123,14 +2185,55 @@ static struct dso *machine__create_kernel(struct machine *self)
 	return kernel;
 }
 
+struct process_args {
+	u64 start;
+};
+
+static int symbol__in_kernel(void *arg, const char *name,
+			     char type __used, u64 start, u64 end __used)
+{
+	struct process_args *args = arg;
+
+	if (strchr(name, '['))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
+/* Figure out the start address of kernel map from /proc/kallsyms */
+static u64 machine__get_kernel_start_addr(struct machine *machine)
+{
+	const char *filename;
+	char path[PATH_MAX];
+	struct process_args args;
+
+	if (machine__is_host(machine)) {
+		filename = "/proc/kallsyms";
+	} else {
+		if (machine__is_default_guest(machine))
+			filename = (char *)symbol_conf.default_guest_kallsyms;
+		else {
+			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+			filename = path;
+		}
+	}
+
+	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
+		return 0;
+
+	return args.start;
+}
+
 int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
 {
 	enum map_type type;
+	u64 start = machine__get_kernel_start_addr(self);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		self->vmlinux_maps[type] = map__new2(0, kernel, type);
+		self->vmlinux_maps[type] = map__new2(start, kernel, type);
 		if (self->vmlinux_maps[type] == NULL)
 			return -1;
 
@@ -2208,9 +2311,6 @@ static int vmlinux_path__init(void)
 	struct utsname uts;
 	char bf[PATH_MAX];
 
-	if (uname(&uts) < 0)
-		return -1;
-
 	vmlinux_path = malloc(sizeof(char *) * 5);
 	if (vmlinux_path == NULL)
 		return -1;
@@ -2223,6 +2323,14 @@ static int vmlinux_path__init(void)
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
+
+	/* only try running kernel version if no symfs was given */
+	if (symbol_conf.symfs[0] != 0)
+		return 0;
+
+	if (uname(&uts) < 0)
+		return -1;
+
 	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
@@ -2282,6 +2390,8 @@ static int setup_list(struct strlist **list, const char *list_str,
 
 int symbol__init(void)
 {
+	const char *symfs;
+
 	if (symbol_conf.initialized)
 		return 0;
 
@@ -2310,6 +2420,18 @@ int symbol__init(void)
 		       symbol_conf.sym_list_str, "symbol") < 0)
 		goto out_free_comm_list;
 
+	/*
+	 * A path to symbols of "/" is identical to ""
+	 * reset here for simplicity.
+	 */
+	symfs = realpath(symbol_conf.symfs, NULL);
+	if (symfs == NULL)
+		symfs = symbol_conf.symfs;
+	if (strcmp(symfs, "/") == 0)
+		symbol_conf.symfs = "";
+	if (symfs != symbol_conf.symfs)
+		free((void *)symfs);
+
 	symbol_conf.initialized = true;
 	return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 038f2201ee09..670cd1c88f54 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -72,6 +72,7 @@ struct symbol_conf {
 			show_cpu_utilization,
 			initialized;
 	const char	*vmlinux_name,
+			*kallsyms_name,
 			*source_prefix,
 			*field_sep;
 	const char	*default_guest_vmlinux_name,
@@ -85,6 +86,7 @@ struct symbol_conf {
        struct strlist	*dso_list,
 			*comm_list,
 			*sym_list;
+	const char	*symfs;
 };
 
 extern struct symbol_conf symbol_conf;
@@ -166,6 +168,8 @@ void dso__sort_by_name(struct dso *self, enum map_type type);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
 int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
+int dso__load_vmlinux(struct dso *self, struct map *map,
+		      const char *vmlinux, symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *self, struct map *map,
 			   symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
@@ -213,7 +217,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 int build_id__sprintf(const u8 *self, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
-					  char type, u64 start));
+					  char type, u64 start, u64 end));
 
 void machine__destroy_kernel_maps(struct machine *self);
 int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 8c72d888e449..00f4eade2e3e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -16,35 +16,50 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
-int find_all_tid(int pid, pid_t ** all_tid)
+struct thread_map *thread_map__new_by_pid(pid_t pid)
 {
+	struct thread_map *threads;
 	char name[256];
 	int items;
 	struct dirent **namelist = NULL;
-	int ret = 0;
 	int i;
 
 	sprintf(name, "/proc/%d/task", pid);
 	items = scandir(name, &namelist, filter, NULL);
 	if (items <= 0)
-                return -ENOENT;
-	*all_tid = malloc(sizeof(pid_t) * items);
-	if (!*all_tid) {
-		ret = -ENOMEM;
-		goto failure;
-	}
-
-	for (i = 0; i < items; i++)
-		(*all_tid)[i] = atoi(namelist[i]->d_name);
+                return NULL;
 
-	ret = items;
+	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+	if (threads != NULL) {
+		for (i = 0; i < items; i++)
+			threads->map[i] = atoi(namelist[i]->d_name);
+		threads->nr = items;
+	}
 
-failure:
 	for (i=0; i<items; i++)
 		free(namelist[i]);
 	free(namelist);
 
-	return ret;
+	return threads;
+}
+
+struct thread_map *thread_map__new_by_tid(pid_t tid)
+{
+	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+	if (threads != NULL) {
+		threads->map[0] = tid;
+		threads->nr	= 1;
+	}
+
+	return threads;
+}
+
+struct thread_map *thread_map__new(pid_t pid, pid_t tid)
+{
+	if (pid != -1)
+		return thread_map__new_by_pid(pid);
+	return thread_map__new_by_tid(tid);
 }
 
 static struct thread *thread__new(pid_t pid)
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 688500ff826f..d7574101054a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -18,11 +18,24 @@ struct thread {
 	int			comm_len;
 };
 
+struct thread_map {
+	int nr;
+	int map[];
+};
+
 struct perf_session;
 
 void thread__delete(struct thread *self);
 
-int find_all_tid(int pid, pid_t ** all_tid);
+struct thread_map *thread_map__new_by_pid(pid_t pid);
+struct thread_map *thread_map__new_by_tid(pid_t tid);
+struct thread_map *thread_map__new(pid_t pid, pid_t tid);
+
+static inline void thread_map__delete(struct thread_map *threads)
+{
+	free(threads);
+}
+
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index b1572601286c..35729f4c40cb 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -34,11 +34,13 @@
 #include <ctype.h>
 #include <errno.h>
 #include <stdbool.h>
+#include <linux/list.h>
 #include <linux/kernel.h>
 
 #include "../perf.h"
 #include "trace-event.h"
 #include "debugfs.h"
+#include "evsel.h"
 
 #define VERSION "0.5"
 
@@ -469,16 +471,17 @@ out:
 }
 
 static struct tracepoint_path *
-get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events)
+get_tracepoints_path(struct list_head *pattrs)
 {
 	struct tracepoint_path path, *ppath = &path;
-	int i, nr_tracepoints = 0;
+	struct perf_evsel *pos;
+	int nr_tracepoints = 0;
 
-	for (i = 0; i < nb_events; i++) {
-		if (pattrs[i].type != PERF_TYPE_TRACEPOINT)
+	list_for_each_entry(pos, pattrs, node) {
+		if (pos->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 		++nr_tracepoints;
-		ppath->next = tracepoint_id_to_path(pattrs[i].config);
+		ppath->next = tracepoint_id_to_path(pos->attr.config);
 		if (!ppath->next)
 			die("%s\n", "No memory to alloc tracepoints list");
 		ppath = ppath->next;
@@ -487,21 +490,21 @@ get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events)
 	return nr_tracepoints > 0 ? path.next : NULL;
 }
 
-bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events)
+bool have_tracepoints(struct list_head *pattrs)
 {
-	int i;
+	struct perf_evsel *pos;
 
-	for (i = 0; i < nb_events; i++)
-		if (pattrs[i].type == PERF_TYPE_TRACEPOINT)
+	list_for_each_entry(pos, pattrs, node)
+		if (pos->attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 
 	return false;
 }
 
-int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
+int read_tracing_data(int fd, struct list_head *pattrs)
 {
 	char buf[BUFSIZ];
-	struct tracepoint_path *tps = get_tracepoints_path(pattrs, nb_events);
+	struct tracepoint_path *tps = get_tracepoints_path(pattrs);
 
 	/*
 	 * What? No tracepoints? No sense writing anything here, bail out.
@@ -545,14 +548,13 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
 	return 0;
 }
 
-ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
-			       int nb_events)
+ssize_t read_tracing_data_size(int fd, struct list_head *pattrs)
 {
 	ssize_t size;
 	int err = 0;
 
 	calc_data_size = 1;
-	err = read_tracing_data(fd, pattrs, nb_events);
+	err = read_tracing_data(fd, pattrs);
 	size = calc_data_size - 1;
 	calc_data_size = 0;
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b3e86b1e4444..b5f12ca24d99 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -262,9 +262,8 @@ raw_field_value(struct event *event, const char *name, void *data);
 void *raw_field_ptr(struct event *event, const char *name, void *data);
 unsigned long long eval_flag(const char *flag);
 
-int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
-ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
-			       int nb_events);
+int read_tracing_data(int fd, struct list_head *pattrs);
+ssize_t read_tracing_data_size(int fd, struct list_head *pattrs);
 
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {
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);
+}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 214265674ddd..5b3ea49aa63e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -114,3 +114,20 @@ unsigned long convert_unit(unsigned long value, char *unit)
 
 	return value;
 }
+
+int readn(int fd, void *buf, size_t n)
+{
+	void *buf_start = buf;
+
+	while (n) {
+		int ret = read(fd, buf, n);
+
+		if (ret <= 0)
+			return ret;
+
+		n -= ret;
+		buf += ret;
+	}
+
+	return buf - buf_start;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7562707ddd1c..e833f26f3bfc 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -265,6 +265,7 @@ void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
 unsigned long convert_unit(unsigned long value, char *unit);
+int readn(int fd, void *buf, size_t size);
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
new file mode 100644
index 000000000000..22afbf6c536a
--- /dev/null
+++ b/tools/perf/util/xyarray.c
@@ -0,0 +1,20 @@
+#include "xyarray.h"
+#include "util.h"
+
+struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
+{
+	size_t row_size = ylen * entry_size;
+	struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size);
+
+	if (xy != NULL) {
+		xy->entry_size = entry_size;
+		xy->row_size   = row_size;
+	}
+
+	return xy;
+}
+
+void xyarray__delete(struct xyarray *xy)
+{
+	free(xy);
+}
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
new file mode 100644
index 000000000000..c488a07275dd
--- /dev/null
+++ b/tools/perf/util/xyarray.h
@@ -0,0 +1,20 @@
+#ifndef _PERF_XYARRAY_H_
+#define _PERF_XYARRAY_H_ 1
+
+#include <sys/types.h>
+
+struct xyarray {
+	size_t row_size;
+	size_t entry_size;
+	char contents[];
+};
+
+struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
+void xyarray__delete(struct xyarray *xy);
+
+static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
+{
+	return &xy->contents[x * xy->row_size + y * xy->entry_size];
+}
+
+#endif /* _PERF_XYARRAY_H_ */