22 files changed, 931 insertions, 554 deletions

diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 26d4d3fd6de..ad73300f7ba 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -23,12 +23,7 @@ if test -d ../../.git -o -f ../../.git &&
 then
 	VN=$(echo "$VN" | sed -e 's/-/./g');
 else
-	eval $(grep '^VERSION[[:space:]]*=' ../../Makefile|tr -d ' ')
-	eval $(grep '^PATCHLEVEL[[:space:]]*=' ../../Makefile|tr -d ' ')
-	eval $(grep '^SUBLEVEL[[:space:]]*=' ../../Makefile|tr -d ' ')
-	eval $(grep '^EXTRAVERSION[[:space:]]*=' ../../Makefile|tr -d ' ')
-
-	VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}"
+	VN=$(MAKEFLAGS= make -sC ../.. kernelversion)
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1023f67633a..3c1b8a63210 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -9,21 +9,21 @@
 #include "thread_map.h"
 
 static const char *perf_event__names[] = {
-	[0]			 = "TOTAL",
-	[PERF_RECORD_MMAP]	 = "MMAP",
-	[PERF_RECORD_LOST]	 = "LOST",
-	[PERF_RECORD_COMM]	 = "COMM",
-	[PERF_RECORD_EXIT]	 = "EXIT",
-	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
-	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-	[PERF_RECORD_FORK]	 = "FORK",
-	[PERF_RECORD_READ]	 = "READ",
-	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
-	[PERF_RECORD_HEADER_ATTR]	 = "ATTR",
-	[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",
+	[0]					= "TOTAL",
+	[PERF_RECORD_MMAP]			= "MMAP",
+	[PERF_RECORD_LOST]			= "LOST",
+	[PERF_RECORD_COMM]			= "COMM",
+	[PERF_RECORD_EXIT]			= "EXIT",
+	[PERF_RECORD_THROTTLE]			= "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE]		= "UNTHROTTLE",
+	[PERF_RECORD_FORK]			= "FORK",
+	[PERF_RECORD_READ]			= "READ",
+	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
+	[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",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -537,9 +537,18 @@ static int perf_event__process_kernel_mmap(union perf_event *event,
 			goto out_problem;
 
 		perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 event->mmap.pgoff);
+
+		/*
+		 * Avoid using a zero address (kptr_restrict) for the ref reloc
+		 * symbol. Effectively having zero here means that at record
+		 * time /proc/sys/kernel/kptr_restrict was non zero.
+		 */
+		if (event->mmap.pgoff != 0) {
+			perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+								 symbol_name,
+								 event->mmap.pgoff);
+		}
+
 		if (machine__is_default_guest(machine)) {
 			/*
 			 * preload dso of guest kernel and modules
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 9c35170fb37..1d7f66488a8 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -56,6 +56,13 @@ struct read_event {
 	u64 id;
 };
 
+
+#define PERF_SAMPLE_MASK				\
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
+	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];
@@ -178,6 +185,7 @@ int perf_event__preprocess_sample(const union perf_event *self,
 const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     bool sample_id_all, struct perf_sample *sample);
+			     int sample_size, bool sample_id_all,
+			     struct perf_sample *sample);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cefa20d..b021ea9265c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -165,11 +165,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	/* XXX Move this to perf.c, making it generally available */
 	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-	struct perf_mmap *md = &evlist->mmap[cpu];
+	struct perf_mmap *md = &evlist->mmap[idx];
 	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
@@ -234,36 +234,122 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
-	int cpu;
+	int i;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		if (evlist->mmap[i].base != NULL) {
+			munmap(evlist->mmap[i].base, evlist->mmap_len);
+			evlist->mmap[i].base = NULL;
 		}
 	}
+
+	free(evlist->mmap);
+	evlist->mmap = NULL;
 }
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
-	evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+	evlist->nr_mmaps = evlist->cpus->nr;
+	if (evlist->cpus->map[0] == -1)
+		evlist->nr_mmaps = evlist->threads->nr;
+	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
-			       int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
+			       int idx, int prot, int mask, int fd)
 {
-	evlist->mmap[cpu].prev = 0;
-	evlist->mmap[cpu].mask = mask;
-	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+	evlist->mmap[idx].prev = 0;
+	evlist->mmap[idx].mask = mask;
+	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[cpu].base == MAP_FAILED)
+	if (evlist->mmap[idx].base == MAP_FAILED)
 		return -1;
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
 }
 
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+{
+	struct perf_evsel *evsel;
+	int cpu, thread;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		int output = -1;
+
+		for (thread = 0; thread < evlist->threads->nr; thread++) {
+			list_for_each_entry(evsel, &evlist->entries, node) {
+				int fd = FD(evsel, cpu, thread);
+
+				if (output == -1) {
+					output = fd;
+					if (__perf_evlist__mmap(evlist, cpu,
+								prot, mask, output) < 0)
+						goto out_unmap;
+				} else {
+					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+						goto out_unmap;
+				}
+
+				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+					goto out_unmap;
+			}
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		if (evlist->mmap[cpu].base != NULL) {
+			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+			evlist->mmap[cpu].base = NULL;
+		}
+	}
+	return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+{
+	struct perf_evsel *evsel;
+	int thread;
+
+	for (thread = 0; thread < evlist->threads->nr; thread++) {
+		int output = -1;
+
+		list_for_each_entry(evsel, &evlist->entries, node) {
+			int fd = FD(evsel, 0, thread);
+
+			if (output == -1) {
+				output = fd;
+				if (__perf_evlist__mmap(evlist, thread,
+							prot, mask, output) < 0)
+					goto out_unmap;
+			} else {
+				if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+					goto out_unmap;
+			}
+
+			if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+			    perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
+				goto out_unmap;
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (thread = 0; thread < evlist->threads->nr; thread++) {
+		if (evlist->mmap[thread].base != NULL) {
+			munmap(evlist->mmap[thread].base, evlist->mmap_len);
+			evlist->mmap[thread].base = NULL;
+		}
+	}
+	return -1;
+}
+
 /** perf_evlist__mmap - Create per cpu maps to receive events
  *
  * @evlist - list of events
@@ -282,11 +368,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 {
 	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-	int mask = pages * page_size - 1, cpu;
-	struct perf_evsel *first_evsel, *evsel;
+	int mask = pages * page_size - 1;
+	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
 
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
@@ -296,42 +382,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 
 	evlist->overwrite = overwrite;
 	evlist->mmap_len = (pages + 1) * page_size;
-	first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
 		    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
 			return -ENOMEM;
-
-		for (cpu = 0; cpu < cpus->nr; cpu++) {
-			for (thread = 0; thread < threads->nr; thread++) {
-				int fd = FD(evsel, cpu, thread);
-
-				if (evsel->idx || thread) {
-					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
-						  FD(first_evsel, cpu, 0)) != 0)
-						goto out_unmap;
-				} else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
-					goto out_unmap;
-
-				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-					goto out_unmap;
-			}
-		}
 	}
 
-	return 0;
+	if (evlist->cpus->map[0] == -1)
+		return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
-out_unmap:
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
-		}
-	}
-	return -1;
+	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
@@ -342,7 +404,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target_tid != -1)
+	if (cpu_list == NULL && target_tid != -1)
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(cpu_list);
@@ -392,3 +454,47 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_type != pos->attr.sample_type)
+			return false;
+	}
+
+	return true;
+}
+
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_type;
+}
+
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_id_all != pos->attr.sample_id_all)
+			return false;
+	}
+
+	return true;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_id_all;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8b1cb7a4c5f..b2b862374f3 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -17,6 +17,7 @@ struct perf_evlist {
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
 	int		 nr_fds;
+	int		 nr_mmaps;
 	int		 mmap_len;
 	bool		 overwrite;
 	union perf_event event_copy;
@@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
@@ -65,4 +66,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
+
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596afd7f..0239eb87b23 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,22 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+int __perf_evsel__sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1ULL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
@@ -35,7 +51,17 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	int cpu, thread;
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+	if (evsel->fd) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			for (thread = 0; thread < nthreads; thread++) {
+				FD(evsel, cpu, thread) = -1;
+			}
+		}
+	}
+
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
@@ -175,7 +201,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group, bool inherit)
+			      struct thread_map *threads, bool group)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
@@ -192,19 +218,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		int group_fd = -1;
-		/*
-		 * Don't allow mmap() of inherited per-task counters. This
-		 * would create a performance issue due to all children writing
-		 * to the same buffer.
-		 *
-		 * FIXME:
-		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-		 * but a 'flags' parameter, with 'group' folded there as well,
-		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-		 * set. Lets go for the minimal fix first tho.
-		 */
-		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -253,7 +266,7 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit)
+		     struct thread_map *threads, bool group)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -263,19 +276,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+	return __perf_evsel__open(evsel, cpus, threads, group);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit)
+			     struct cpu_map *cpus, bool group)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit)
+				struct thread_map *threads, bool group)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
@@ -316,8 +329,20 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
 	return 0;
 }
 
+static bool sample_overlap(const union perf_event *event,
+			   const void *offset, u64 size)
+{
+	const void *base = event;
+
+	if (offset + size > base + event->header.size)
+		return true;
+
+	return false;
+}
+
 int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     bool sample_id_all, struct perf_sample *data)
+			     int sample_size, bool sample_id_all,
+			     struct perf_sample *data)
 {
 	const u64 *array;
 
@@ -332,6 +357,9 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 
 	array = event->sample.array;
 
+	if (sample_size + sizeof(event->header) > event->header.size)
+		return -EFAULT;
+
 	if (type & PERF_SAMPLE_IP) {
 		data->ip = event->ip.ip;
 		array++;
@@ -382,14 +410,29 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CALLCHAIN) {
+		if (sample_overlap(event, array, sizeof(data->callchain->nr)))
+			return -EFAULT;
+
 		data->callchain = (struct ip_callchain *)array;
+
+		if (sample_overlap(event, array, data->callchain->nr))
+			return -EFAULT;
+
 		array += 1 + data->callchain->nr;
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
 		u32 *p = (u32 *)array;
+
+		if (sample_overlap(event, array, sizeof(u32)))
+			return -EFAULT;
+
 		data->raw_size = *p;
 		p++;
+
+		if (sample_overlap(event, p, data->raw_size))
+			return -EFAULT;
+
 		data->raw_data = p;
 	}
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab53834..7e9366e4490 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@ void perf_evsel__free_id(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, bool group, bool inherit);
+			     struct cpu_map *cpus, bool group);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit);
+				struct thread_map *threads, bool group);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit);
+		     struct thread_map *threads, bool group);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
@@ -149,4 +149,11 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
+int __perf_evsel__sample_size(u64 sample_type);
+
+static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
+{
+	return __perf_evsel__sample_size(evsel->attr.sample_type);
+}
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 93862a8027e..afb0849fe53 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -193,9 +193,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
-	if (is_kallsyms)
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			return 0;
+		}
 		realname = (char *)name;
-	else
+	} else
 		realname = realpath(name, NULL);
 
 	if (realname == NULL || filename == NULL || linkname == NULL)
@@ -934,37 +938,6 @@ out_delete_evlist:
 	return -ENOMEM;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
-{
-	struct perf_evsel *pos;
-	u64 type = 0;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (!type)
-			type = pos->attr.sample_type;
-		else if (type != pos->attr.sample_type)
-			die("non matching sample_type");
-	}
-
-	return type;
-}
-
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
-{
-	bool value = false, first = true;
-	struct perf_evsel *pos;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (first) {
-			value = pos->attr.sample_id_all;
-			first = false;
-		} else if (value != pos->attr.sample_id_all)
-			die("non matching sample_id_all");
-	}
-
-	return value;
-}
-
 int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 				perf_event__handler_t process,
 				struct perf_session *session)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 456661d7f10..1886256768a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -64,8 +64,6 @@ int perf_header__write_pipe(int fd);
 int perf_header__push_event(u64 id, const char *name);
 char *perf_header__find_event(u64 id);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
 void perf_header__set_feat(struct perf_header *header, int feat);
 void perf_header__clear_feat(struct perf_header *header, int feat);
 bool perf_header__has_feat(const struct perf_header *header, int feat);
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
new file mode 100644
index 00000000000..6789d788d49
--- /dev/null
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
+#define _PERF_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define altinstruction_entry #
+
+#endif
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 00000000000..1b476c9ae64
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 356c7e467b8..1d928a0ce99 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,4 +1,6 @@
 #include <linux/kernel.h>
+#include <linux/prefetch.h>
+
 #include "../../../../include/linux/list.h"
 
 #ifndef PERF_LIST_H
@@ -23,5 +25,5 @@ static inline void list_del_range(struct list_head *begin,
  * @head: the head for your list.
  */
 #define list_for_each_from(pos, head) \
-	for (; prefetch(pos->next), pos != (head); pos = pos->next)
+	for (; pos != (head); pos = pos->next)
 #endif
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 952b4ae3d95..41982c373fa 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -31,34 +31,36 @@ char debugfs_path[MAXPATHLEN];
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
 
 static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),		"cpu-cycles",		"cycles"	},
-  { CHW(INSTRUCTIONS),		"instructions",		""		},
-  { CHW(CACHE_REFERENCES),	"cache-references",	""		},
-  { CHW(CACHE_MISSES),		"cache-misses",		""		},
-  { CHW(BRANCH_INSTRUCTIONS),	"branch-instructions",	"branches"	},
-  { CHW(BRANCH_MISSES),		"branch-misses",	""		},
-  { CHW(BUS_CYCLES),		"bus-cycles",		""		},
-
-  { CSW(CPU_CLOCK),		"cpu-clock",		""		},
-  { CSW(TASK_CLOCK),		"task-clock",		""		},
-  { CSW(PAGE_FAULTS),		"page-faults",		"faults"	},
-  { CSW(PAGE_FAULTS_MIN),	"minor-faults",		""		},
-  { CSW(PAGE_FAULTS_MAJ),	"major-faults",		""		},
-  { CSW(CONTEXT_SWITCHES),	"context-switches",	"cs"		},
-  { CSW(CPU_MIGRATIONS),	"cpu-migrations",	"migrations"	},
-  { CSW(ALIGNMENT_FAULTS),	"alignment-faults",	""		},
-  { CSW(EMULATION_FAULTS),	"emulation-faults",	""		},
+  { CHW(CPU_CYCLES),			"cpu-cycles",			"cycles"		},
+  { CHW(STALLED_CYCLES_FRONTEND),	"stalled-cycles-frontend",	"idle-cycles-frontend"	},
+  { CHW(STALLED_CYCLES_BACKEND),	"stalled-cycles-backend",	"idle-cycles-backend"	},
+  { CHW(INSTRUCTIONS),			"instructions",			""			},
+  { CHW(CACHE_REFERENCES),		"cache-references",		""			},
+  { CHW(CACHE_MISSES),			"cache-misses",			""			},
+  { CHW(BRANCH_INSTRUCTIONS),		"branch-instructions",		"branches"		},
+  { CHW(BRANCH_MISSES),			"branch-misses",		""			},
+  { CHW(BUS_CYCLES),			"bus-cycles",			""			},
+
+  { CSW(CPU_CLOCK),			"cpu-clock",			""			},
+  { CSW(TASK_CLOCK),			"task-clock",			""			},
+  { CSW(PAGE_FAULTS),			"page-faults",			"faults"		},
+  { CSW(PAGE_FAULTS_MIN),		"minor-faults",			""			},
+  { CSW(PAGE_FAULTS_MAJ),		"major-faults",			""			},
+  { CSW(CONTEXT_SWITCHES),		"context-switches",		"cs"			},
+  { CSW(CPU_MIGRATIONS),		"cpu-migrations",		"migrations"		},
+  { CSW(ALIGNMENT_FAULTS),		"alignment-faults",		""			},
+  { CSW(EMULATION_FAULTS),		"emulation-faults",		""			},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
 	((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
 
-#define PERF_EVENT_RAW(config)	__PERF_EVENT_FIELD(config, RAW)
+#define PERF_EVENT_RAW(config)		__PERF_EVENT_FIELD(config, RAW)
 #define PERF_EVENT_CONFIG(config)	__PERF_EVENT_FIELD(config, CONFIG)
-#define PERF_EVENT_TYPE(config)	__PERF_EVENT_FIELD(config, TYPE)
+#define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-static const char *hw_event_names[] = {
+static const char *hw_event_names[PERF_COUNT_HW_MAX] = {
 	"cycles",
 	"instructions",
 	"cache-references",
@@ -66,11 +68,13 @@ static const char *hw_event_names[] = {
 	"branches",
 	"branch-misses",
 	"bus-cycles",
+	"stalled-cycles-frontend",
+	"stalled-cycles-backend",
 };
 
-static const char *sw_event_names[] = {
-	"cpu-clock-msecs",
-	"task-clock-msecs",
+static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
+	"cpu-clock",
+	"task-clock",
 	"page-faults",
 	"context-switches",
 	"CPU-migrations",
@@ -307,7 +311,7 @@ const char *__event_name(int type, u64 config)
 
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
-		if (config < PERF_COUNT_HW_MAX)
+		if (config < PERF_COUNT_HW_MAX && hw_event_names[config])
 			return hw_event_names[config];
 		return "unknown-hardware";
 
@@ -333,7 +337,7 @@ const char *__event_name(int type, u64 config)
 	}
 
 	case PERF_TYPE_SOFTWARE:
-		if (config < PERF_COUNT_SW_MAX)
+		if (config < PERF_COUNT_SW_MAX && sw_event_names[config])
 			return sw_event_names[config];
 		return "unknown-software";
 
@@ -648,13 +652,15 @@ static int check_events(const char *str, unsigned int i)
 	int n;
 
 	n = strlen(event_symbols[i].symbol);
-	if (!strncmp(str, event_symbols[i].symbol, n))
+	if (!strncasecmp(str, event_symbols[i].symbol, n))
 		return n;
 
 	n = strlen(event_symbols[i].alias);
-	if (n)
-		if (!strncmp(str, event_symbols[i].alias, n))
+	if (n) {
+		if (!strncasecmp(str, event_symbols[i].alias, n))
 			return n;
+	}
+
 	return 0;
 }
 
@@ -718,15 +724,22 @@ parse_numeric_event(const char **strp, struct perf_event_attr *attr)
 	return EVT_FAILED;
 }
 
-static enum event_result
+static int
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
 	const char *str = *strp;
 	int exclude = 0;
 	int eu = 0, ek = 0, eh = 0, precise = 0;
 
-	if (*str++ != ':')
+	if (!*str)
+		return 0;
+
+	if (*str == ',')
 		return 0;
+
+	if (*str++ != ':')
+		return -1;
+
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -747,14 +760,16 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 
 		++str;
 	}
-	if (str >= *strp + 2) {
-		*strp = str;
-		attr->exclude_user   = eu;
-		attr->exclude_kernel = ek;
-		attr->exclude_hv     = eh;
-		attr->precise_ip     = precise;
-		return 1;
-	}
+	if (str < *strp + 2)
+		return -1;
+
+	*strp = str;
+
+	attr->exclude_user   = eu;
+	attr->exclude_kernel = ek;
+	attr->exclude_hv     = eh;
+	attr->precise_ip     = precise;
+
 	return 0;
 }
 
@@ -797,7 +812,12 @@ parse_event_symbols(const struct option *opt, const char **str,
 	return EVT_FAILED;
 
 modifier:
-	parse_event_modifier(str, attr);
+	if (parse_event_modifier(str, attr) < 0) {
+		fprintf(stderr, "invalid event modifier: '%s'\n", *str);
+		fprintf(stderr, "Run 'perf list' for a list of valid events and modifiers\n");
+
+		return EVT_FAILED;
+	}
 
 	return ret;
 }
@@ -912,7 +932,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent.d_name, evt_dirent.d_name);
-			printf("  %-42s [%s]\n", evt_path,
+			printf("  %-50s [%s]\n", evt_path,
 				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
 		}
 		closedir(evt_dir);
@@ -977,7 +997,7 @@ void print_events_type(u8 type)
 		else
 			snprintf(name, sizeof(name), "%s", syms->symbol);
 
-		printf("  %-42s [%s]\n", name,
+		printf("  %-50s [%s]\n", name,
 			event_type_descriptors[type]);