Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull more perf updates from Ingo Molnar:
 "A second (and last) round of late coming fixes and changes, almost all
  of them in perf tooling:

  User visible tooling changes:

   - Add period data column and make it default in 'perf script' (Jiri
     Olsa)

   - Add a visual cue for toggle zeroing of samples in 'perf top'
     (Taeung Song)

   - Improve callchains when using libunwind (Namhyung Kim)

  Tooling fixes and infrastructure changes:

   - Fix for double free in 'perf stat' when using some specific invalid
     command line combo (Yasser Shalabi)

   - Fix off-by-one bugs in map->end handling (Stephane Eranian)

   - Fix off-by-one bug in maps__find(), also related to map->end
     handling (Namhyung Kim)

   - Make struct symbol->end be the first addr after the symbol range,
     to make it match the convention used for struct map->end.  (Arnaldo
     Carvalho de Melo)

   - Fix perf_evlist__add_pollfd() error handling in 'perf kvm stat
     live' (Jiri Olsa)

   - Fix python test build by moving callchain_param to an object linked
     into the python binding (Jiri Olsa)

   - Document sysfs events/ interfaces (Cody P Schafer)

   - Fix typos in perf/Documentation (Masanari Iida)

   - Add missing 'struct option' forward declaration (Arnaldo Carvalho
     de Melo)

   - Add option to copy events when queuing for sorting across cpu
     buffers and enable it for 'perf kvm stat live', to avoid having
     events left in the queue pointing to the ring buffer be rewritten
     in high volume sessions.  (Alexander Yarygin, improving work done
     by David Ahern):

   - Do not include a struct hists per perf_evsel, untangling the
     histogram code from perf_evsel, to pave the way for exporting a
     minimalistic tools/lib/api/perf/ library usable by tools/perf and
     initially by the rasd daemon being developed by Borislav Petkov,
     Robert Richter and Jean Pihet.  (Arnaldo Carvalho de Melo)

   - Make perf_evlist__open(evlist, NULL, NULL), i.e. without cpu and
     thread maps mean syswide monitoring, reducing the boilerplate for
     tools that only want system wide mode.  (Arnaldo Carvalho de Melo)

   - Move exit stuff from perf_evsel__delete to perf_evsel__exit, delete
     should be just a front end for exit + free (Arnaldo Carvalho de
     Melo)

   - Add support to new style format of kernel PMU event.  (Kan Liang)

  and other misc fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  perf script: Add period as a default output column
  perf script: Add period data column
  perf evsel: No need to drag util/cgroup.h
  perf evlist: Add missing 'struct option' forward declaration
  perf evsel: Move exit stuff from __delete to __exit
  kprobes/x86: Remove stale ARCH_SUPPORTS_KPROBES_ON_FTRACE define
  perf kvm stat live: Enable events copying
  perf session: Add option to copy events when queueing
  perf Documentation: Fix typos in perf/Documentation
  perf trace: Use thread_{,_set}_priv helpers
  perf kvm: Use thread_{,_set}_priv helpers
  perf callchain: Create an address space per thread
  perf report: Set callchain_param.record_mode for future use
  perf evlist: Fix for double free in tools/perf stat
  perf test: Add test case for pmu event new style format
  perf tools: Add support to new style format of kernel PMU event
  perf tools: Parse the pmu event prefix and suffix
  Revert "perf tools: Default to cpu// for events v5"
  perf Documentation: Remove Ruplicated docs for powerpc cpu specific events
  perf Documentation: sysfs events/ interfaces
  ...

33 files changed, 580 insertions, 196 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 36437527dbb3..7dabde14ea54 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -478,7 +478,7 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr < sym->start || addr > sym->end)
+	if (addr < sym->start || addr >= sym->end)
 		return -ERANGE;
 
 	offset = addr - sym->start;
@@ -836,7 +836,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 		    end = map__rip_2objdump(map, sym->end);
 
 		offset = line_ip - start;
-		if ((u64)line_ip < start || (u64)line_ip > end)
+		if ((u64)line_ip < start || (u64)line_ip >= end)
 			offset = -1;
 		else
 			parsed_line = tmp2 + 1;
@@ -966,7 +966,7 @@ fallback:
 		kce.kcore_filename = symfs_filename;
 		kce.addr = map__rip_2objdump(map, sym->start);
 		kce.offs = sym->start;
-		kce.len = sym->end + 1 - sym->start;
+		kce.len = sym->end - sym->start;
 		if (!kcore_extract__create(&kce)) {
 			delete_extract = true;
 			strlcpy(symfs_filename, kce.extract_filename,
@@ -987,7 +987,7 @@ fallback:
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
 		 map__rip_2objdump(map, sym->start),
-		 map__rip_2objdump(map, sym->end+1),
+		 map__rip_2objdump(map, sym->end),
 		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
 		 symbol_conf.annotate_src ? "-S" : "",
 		 symfs_filename, filename);
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 2a1f5a46543a..94cfefddf4db 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -65,6 +65,8 @@ struct callchain_param {
 	enum chain_key		key;
 };
 
+extern struct callchain_param callchain_param;
+
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7eb7107731ec..5699e7e2a790 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -190,6 +190,32 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_MAX
 };
 
+/*
+ * The kernel collects the number of events it couldn't send in a stretch and
+ * when possible sends this number in a PERF_RECORD_LOST event. The number of
+ * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
+ * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
+ * the sum of all struct lost_event.lost fields reported.
+ *
+ * The total_period is needed because by default auto-freq is used, so
+ * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
+ * the total number of low level events, it is necessary to to sum all struct
+ * sample_event.period and stash the result in total_period.
+ */
+struct events_stats {
+	u64 total_period;
+	u64 total_non_filtered_period;
+	u64 total_lost;
+	u64 total_invalid_chains;
+	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_non_filtered_samples;
+	u32 nr_lost_warned;
+	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
+	u32 nr_unprocessable_samples;
+};
+
 struct attr_event {
 	struct perf_event_header header;
 	struct perf_event_attr attr;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3cebc9a8d52e..3c9e77d6b4c2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1003,6 +1003,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 
 out_delete_threads:
 	thread_map__delete(evlist->threads);
+	evlist->threads = NULL;
 	return -1;
 }
 
@@ -1175,11 +1176,51 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	}
 }
 
+static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
+{
+	int err = -ENOMEM;
+
+	/*
+	 * Try reading /sys/devices/system/cpu/online to get
+	 * an all cpus map.
+	 *
+	 * FIXME: -ENOMEM is the best we can do here, the cpu_map
+	 * code needs an overhaul to properly forward the
+	 * error, and we may not want to do that fallback to a
+	 * default cpu identity map :-\
+	 */
+	evlist->cpus = cpu_map__new(NULL);
+	if (evlist->cpus == NULL)
+		goto out;
+
+	evlist->threads = thread_map__new_dummy();
+	if (evlist->threads == NULL)
+		goto out_free_cpus;
+
+	err = 0;
+out:
+	return err;
+out_free_cpus:
+	cpu_map__delete(evlist->cpus);
+	evlist->cpus = NULL;
+	goto out;
+}
+
 int perf_evlist__open(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 	int err;
 
+	/*
+	 * Default: one fd per CPU, all threads, aka systemwide
+	 * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
+	 */
+	if (evlist->threads == NULL && evlist->cpus == NULL) {
+		err = perf_evlist__create_syswide_maps(evlist);
+		if (err < 0)
+			goto out_err;
+	}
+
 	perf_evlist__update_id_pos(evlist);
 
 	evlist__for_each(evlist, evsel) {
@@ -1276,8 +1317,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 		sigaction(SIGUSR1, &act, NULL);
 	}
 
-	if (target__none(target))
+	if (target__none(target)) {
+		if (evlist->threads == NULL) {
+			fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n",
+				__func__, __LINE__);
+			goto out_close_pipes;
+		}
 		evlist->threads->map[0] = evlist->workload.pid;
+	}
 
 	close(child_ready_pipe[1]);
 	close(go_pipe[0]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index bd312b01e876..649b0c597283 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -117,6 +117,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 						     void *ucontext));
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
+struct option;
+
 int perf_evlist__parse_mmap_pages(const struct option *opt,
 				  const char *str,
 				  int unset);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e0868a901c4a..2f9e68025ede 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,8 @@
 #include <linux/perf_event.h>
 #include <sys/resource.h>
 #include "asm/bug.h"
+#include "callchain.h"
+#include "cgroup.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -32,6 +34,48 @@ static struct {
 	bool cloexec;
 } perf_missing_features;
 
+static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
+{
+	return 0;
+}
+
+static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
+{
+}
+
+static struct {
+	size_t	size;
+	int	(*init)(struct perf_evsel *evsel);
+	void	(*fini)(struct perf_evsel *evsel);
+} perf_evsel__object = {
+	.size = sizeof(struct perf_evsel),
+	.init = perf_evsel__no_extra_init,
+	.fini = perf_evsel__no_extra_fini,
+};
+
+int perf_evsel__object_config(size_t object_size,
+			      int (*init)(struct perf_evsel *evsel),
+			      void (*fini)(struct perf_evsel *evsel))
+{
+
+	if (object_size == 0)
+		goto set_methods;
+
+	if (perf_evsel__object.size > object_size)
+		return -EINVAL;
+
+	perf_evsel__object.size = object_size;
+
+set_methods:
+	if (init != NULL)
+		perf_evsel__object.init = init;
+
+	if (fini != NULL)
+		perf_evsel__object.fini = fini;
+
+	return 0;
+}
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
 int __perf_evsel__sample_size(u64 sample_type)
@@ -116,16 +160,6 @@ void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
 	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
 }
 
-void hists__init(struct hists *hists)
-{
-	memset(hists, 0, sizeof(*hists));
-	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
-	hists->entries_in = &hists->entries_in_array[0];
-	hists->entries_collapsed = RB_ROOT;
-	hists->entries = RB_ROOT;
-	pthread_mutex_init(&hists->lock, NULL);
-}
-
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
 				  enum perf_event_sample_format bit)
 {
@@ -168,14 +202,14 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
 	INIT_LIST_HEAD(&evsel->node);
-	hists__init(&evsel->hists);
+	perf_evsel__object.init(evsel);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 	perf_evsel__calc_id_pos(evsel);
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
-	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
@@ -185,7 +219,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
-	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
 	if (evsel != NULL) {
 		struct perf_event_attr attr = {
@@ -692,7 +726,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	}
 }
 
-int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
 
@@ -780,13 +814,13 @@ int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_fd(struct perf_evsel *evsel)
+static void perf_evsel__free_fd(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->fd);
 	evsel->fd = NULL;
 }
 
-void perf_evsel__free_id(struct perf_evsel *evsel)
+static void perf_evsel__free_id(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
@@ -817,16 +851,17 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	assert(list_empty(&evsel->node));
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
-}
-
-void perf_evsel__delete(struct perf_evsel *evsel)
-{
-	perf_evsel__exit(evsel);
 	close_cgroup(evsel->cgrp);
 	zfree(&evsel->group_name);
 	if (evsel->tp_format)
 		pevent_free_format(evsel->tp_format);
 	zfree(&evsel->name);
+	perf_evsel__object.fini(evsel);
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+	perf_evsel__exit(evsel);
 	free(evsel);
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 7bc314be6a7b..163c5604e5d1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -7,8 +7,6 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 #include "xyarray.h"
-#include "cgroup.h"
-#include "hist.h"
 #include "symbol.h"
 
 struct perf_counts_values {
@@ -43,6 +41,8 @@ struct perf_sample_id {
 	u64			period;
 };
 
+struct cgroup_sel;
+
 /** struct perf_evsel - event selector
  *
  * @name - Can be set to retain the original event name passed by the user,
@@ -66,7 +66,6 @@ struct perf_evsel {
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
-	struct hists		hists;
 	char			*name;
 	double			scale;
 	const char		*unit;
@@ -100,13 +99,16 @@ union u64_swap {
 	u32 val32[2];
 };
 
-#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
-
 struct cpu_map;
+struct target;
 struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+int perf_evsel__object_config(size_t object_size,
+			      int (*init)(struct perf_evsel *evsel),
+			      void (*fini)(struct perf_evsel *evsel));
+
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
 static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
@@ -153,12 +155,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel);
 const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
-int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_fd(struct perf_evsel *evsel);
-void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
@@ -281,8 +280,6 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-void hists__init(struct hists *hists);
-
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *sample);
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 86569fa3651d..6e88b9e395df 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,6 +3,7 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
 #include <math.h>
@@ -14,13 +15,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
 
-struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_REL,
-	.min_percent = 0.5,
-	.order  = ORDER_CALLEE,
-	.key	= CCKEY_FUNCTION
-};
-
 u16 hists__col_len(struct hists *hists, enum hist_column col)
 {
 	return hists->col_len[col];
@@ -516,6 +510,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 {
 	u64 cost;
 	struct mem_info *mi = iter->priv;
+	struct hists *hists = evsel__hists(iter->evsel);
 	struct hist_entry *he;
 
 	if (mi == NULL)
@@ -532,7 +527,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 	 * and this is indirectly achieved by passing period=weight here
 	 * and the he_stat__add_period() function.
 	 */
-	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+	he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
 				cost, cost, 0, true);
 	if (!he)
 		return -ENOMEM;
@@ -546,13 +541,14 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 		      struct addr_location *al __maybe_unused)
 {
 	struct perf_evsel *evsel = iter->evsel;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he = iter->he;
 	int err = -EINVAL;
 
 	if (he == NULL)
 		goto out;
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(hists, he->filtered);
 
 	err = hist_entry__append_callchain(he, iter->sample);
 
@@ -618,6 +614,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 {
 	struct branch_info *bi;
 	struct perf_evsel *evsel = iter->evsel;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he = NULL;
 	int i = iter->curr;
 	int err = 0;
@@ -631,12 +628,12 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	 * The report shows the percentage of total branches captured
 	 * and not events sampled. Thus we use a pseudo period of 1.
 	 */
-	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
 				1, 1, 0, true);
 	if (he == NULL)
 		return -ENOMEM;
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(hists, he->filtered);
 
 out:
 	iter->he = he;
@@ -668,7 +665,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
 
-	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
 				sample->transaction, true);
 	if (he == NULL)
@@ -691,7 +688,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter,
 
 	iter->he = NULL;
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(evsel__hists(evsel), he->filtered);
 
 	return hist_entry__append_callchain(he, sample);
 }
@@ -724,12 +721,13 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 				 struct addr_location *al)
 {
 	struct perf_evsel *evsel = iter->evsel;
+	struct hists *hists = evsel__hists(evsel);
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry **he_cache = iter->priv;
 	struct hist_entry *he;
 	int err = 0;
 
-	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
 				sample->transaction, true);
 	if (he == NULL)
@@ -746,7 +744,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	 */
 	callchain_cursor_commit(&callchain_cursor);
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(hists, he->filtered);
 
 	return err;
 }
@@ -802,7 +800,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 		}
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
 				sample->transaction, false);
 	if (he == NULL)
@@ -1408,6 +1406,21 @@ int hists__link(struct hists *leader, struct hists *other)
 	return 0;
 }
 
+
+size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
+{
+	struct perf_evsel *pos;
+	size_t ret = 0;
+
+	evlist__for_each(evlist, pos) {
+		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
+		ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
+	}
+
+	return ret;
+}
+
+
 u64 hists__total_period(struct hists *hists)
 {
 	return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
@@ -1434,3 +1447,31 @@ int perf_hist_config(const char *var, const char *value)
 
 	return 0;
 }
+
+static int hists_evsel__init(struct perf_evsel *evsel)
+{
+	struct hists *hists = evsel__hists(evsel);
+
+	memset(hists, 0, sizeof(*hists));
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in = &hists->entries_in_array[0];
+	hists->entries_collapsed = RB_ROOT;
+	hists->entries = RB_ROOT;
+	pthread_mutex_init(&hists->lock, NULL);
+	return 0;
+}
+
+/*
+ * XXX We probably need a hists_evsel__exit() to free the hist_entries
+ * stored in the rbtree...
+ */
+
+int hists__init(void)
+{
+	int err = perf_evsel__object_config(sizeof(struct hists_evsel),
+					    hists_evsel__init, NULL);
+	if (err)
+		fputs("FATAL ERROR: Couldn't setup hists class\n", stderr);
+
+	return err;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 8c9c70e18cbb..d0ef9a19a744 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -4,12 +4,11 @@
 #include <linux/types.h>
 #include <pthread.h>
 #include "callchain.h"
+#include "evsel.h"
 #include "header.h"
 #include "color.h"
 #include "ui/progress.h"
 
-extern struct callchain_param callchain_param;
-
 struct hist_entry;
 struct addr_location;
 struct symbol;
@@ -23,32 +22,6 @@ enum hist_filter {
 	HIST_FILTER__HOST,
 };
 
-/*
- * The kernel collects the number of events it couldn't send in a stretch and
- * when possible sends this number in a PERF_RECORD_LOST event. The number of
- * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
- * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
- * the sum of all struct lost_event.lost fields reported.
- *
- * The total_period is needed because by default auto-freq is used, so
- * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
- * the total number of low level events, it is necessary to to sum all struct
- * sample_event.period and stash the result in total_period.
- */
-struct events_stats {
-	u64 total_period;
-	u64 total_non_filtered_period;
-	u64 total_lost;
-	u64 total_invalid_chains;
-	u32 nr_events[PERF_RECORD_HEADER_MAX];
-	u32 nr_non_filtered_samples;
-	u32 nr_lost_warned;
-	u32 nr_unknown_events;
-	u32 nr_invalid_chains;
-	u32 nr_unknown_id;
-	u32 nr_unprocessable_samples;
-};
-
 enum hist_column {
 	HISTC_SYMBOL,
 	HISTC_DSO,
@@ -165,6 +138,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp);
+size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
@@ -185,6 +159,25 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
 void hists__match(struct hists *leader, struct hists *other);
 int hists__link(struct hists *leader, struct hists *other);
 
+struct hists_evsel {
+	struct perf_evsel evsel;
+	struct hists	  hists;
+};
+
+static inline struct perf_evsel *hists_to_evsel(struct hists *hists)
+{
+	struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists);
+	return &hevsel->evsel;
+}
+
+static inline struct hists *evsel__hists(struct perf_evsel *evsel)
+{
+	struct hists_evsel *hevsel = (struct hists_evsel *)evsel;
+	return &hevsel->hists;
+}
+
+int hists__init(void);
+
 struct perf_hpp {
 	char *buf;
 	size_t size;
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 97a800738226..6f19c548ecc0 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1,4 +1,3 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
-int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b7d477fbda02..34fc7c8672e4 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -13,12 +13,18 @@
 #include <symbol/kallsyms.h>
 #include "unwind.h"
 
+static void dsos__init(struct dsos *dsos)
+{
+	INIT_LIST_HEAD(&dsos->head);
+	dsos->root = RB_ROOT;
+}
+
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
 	map_groups__init(&machine->kmaps);
 	RB_CLEAR_NODE(&machine->rb_node);
-	INIT_LIST_HEAD(&machine->user_dsos.head);
-	INIT_LIST_HEAD(&machine->kernel_dsos.head);
+	dsos__init(&machine->user_dsos);
+	dsos__init(&machine->kernel_dsos);
 
 	machine->threads = RB_ROOT;
 	INIT_LIST_HEAD(&machine->dead_threads);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b7090596ac50..2137c4596ec7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -556,7 +556,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 {
-	if (ams->addr < ams->map->start || ams->addr > ams->map->end) {
+	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
 		if (ams->map->groups == NULL)
 			return -1;
 		ams->map = map_groups__find(ams->map->groups, ams->map->type,
@@ -664,7 +664,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				goto move_map;
 			}
 
-			before->end = map->start - 1;
+			before->end = map->start;
 			map_groups__insert(mg, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
@@ -678,7 +678,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				goto move_map;
 			}
 
-			after->start = map->end + 1;
+			after->start = map->end;
 			map_groups__insert(mg, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
@@ -752,7 +752,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 		m = rb_entry(parent, struct map, rb_node);
 		if (ip < m->start)
 			p = &(*p)->rb_left;
-		else if (ip > m->end)
+		else if (ip >= m->end)
 			p = &(*p)->rb_right;
 		else
 			return m;
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 706ce1a66169..fd4be94125fb 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -1,5 +1,6 @@
 #include <linux/list.h>
 #include <linux/compiler.h>
+#include <linux/string.h>
 #include "ordered-events.h"
 #include "evlist.h"
 #include "session.h"
@@ -57,11 +58,45 @@ static void queue_event(struct ordered_events *oe, struct ordered_event *new)
 	}
 }
 
+static union perf_event *__dup_event(struct ordered_events *oe,
+				     union perf_event *event)
+{
+	union perf_event *new_event = NULL;
+
+	if (oe->cur_alloc_size < oe->max_alloc_size) {
+		new_event = memdup(event, event->header.size);
+		if (new_event)
+			oe->cur_alloc_size += event->header.size;
+	}
+
+	return new_event;
+}
+
+static union perf_event *dup_event(struct ordered_events *oe,
+				   union perf_event *event)
+{
+	return oe->copy_on_queue ? __dup_event(oe, event) : event;
+}
+
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue) {
+		oe->cur_alloc_size -= event->header.size;
+		free(event);
+	}
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
-static struct ordered_event *alloc_event(struct ordered_events *oe)
+static struct ordered_event *alloc_event(struct ordered_events *oe,
+					 union perf_event *event)
 {
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
+	union perf_event *new_event;
+
+	new_event = dup_event(oe, event);
+	if (!new_event)
+		return NULL;
 
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
@@ -74,8 +109,10 @@ static struct ordered_event *alloc_event(struct ordered_events *oe)
 		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
 
 		oe->buffer = malloc(size);
-		if (!oe->buffer)
+		if (!oe->buffer) {
+			free_dup_event(oe, new_event);
 			return NULL;
+		}
 
 		pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
 		   oe->cur_alloc_size, size, oe->max_alloc_size);
@@ -90,15 +127,17 @@ static struct ordered_event *alloc_event(struct ordered_events *oe)
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
 	}
 
+	new->event = new_event;
 	return new;
 }
 
 struct ordered_event *
-ordered_events__new(struct ordered_events *oe, u64 timestamp)
+ordered_events__new(struct ordered_events *oe, u64 timestamp,
+		    union perf_event *event)
 {
 	struct ordered_event *new;
 
-	new = alloc_event(oe);
+	new = alloc_event(oe, event);
 	if (new) {
 		new->timestamp = timestamp;
 		queue_event(oe, new);
@@ -111,6 +150,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 {
 	list_move(&event->list, &oe->cache);
 	oe->nr_events--;
+	free_dup_event(oe, event->event);
 }
 
 static int __ordered_events__flush(struct perf_session *s,
@@ -240,6 +280,7 @@ void ordered_events__free(struct ordered_events *oe)
 
 		event = list_entry(oe->to_free.next, struct ordered_event, list);
 		list_del(&event->list);
+		free_dup_event(oe, event->event);
 		free(event);
 	}
 }
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 3b2f20542a01..7b8f9b011f38 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -34,9 +34,11 @@ struct ordered_events {
 	int			buffer_idx;
 	unsigned int		nr_events;
 	enum oe_flush		last_flush_type;
+	bool                    copy_on_queue;
 };
 
-struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp,
+					  union perf_event *event);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
 			  enum oe_flush how);
@@ -48,4 +50,10 @@ void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
 {
 	oe->max_alloc_size = size;
 }
+
+static inline
+void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy)
+{
+	oe->copy_on_queue = copy;
+}
 #endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d76aa30cb1fb..c659a3ca1283 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -6,7 +6,7 @@
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "linux/string.h"
+#include "string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
@@ -30,6 +30,15 @@ extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
 
+static struct perf_pmu_event_symbol *perf_pmu_events_list;
+/*
+ * The variable indicates the number of supported pmu event symbols.
+ * 0 means not initialized and ready to init
+ * -1 means failed to init, don't try anymore
+ * >0 is the number of supported pmu event symbols
+ */
+static int perf_pmu_events_list_num;
+
 static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
 		.symbol = "cpu-cycles",
@@ -863,30 +872,111 @@ int parse_events_name(struct list_head *list, char *name)
 	return 0;
 }
 
-static int parse_events__scanner(const char *str, void *data, int start_token);
+static int
+comp_pmu(const void *p1, const void *p2)
+{
+	struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1;
+	struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2;
 
-static int parse_events_fixup(int ret, const char *str, void *data,
-			      int start_token)
+	return strcmp(pmu1->symbol, pmu2->symbol);
+}
+
+static void perf_pmu__parse_cleanup(void)
 {
-	char *o = strdup(str);
-	char *s = NULL;
-	char *t = o;
-	char *p;
+	if (perf_pmu_events_list_num > 0) {
+		struct perf_pmu_event_symbol *p;
+		int i;
+
+		for (i = 0; i < perf_pmu_events_list_num; i++) {
+			p = perf_pmu_events_list + i;
+			free(p->symbol);
+		}
+		free(perf_pmu_events_list);
+		perf_pmu_events_list = NULL;
+		perf_pmu_events_list_num = 0;
+	}
+}
+
+#define SET_SYMBOL(str, stype)		\
+do {					\
+	p->symbol = str;		\
+	if (!p->symbol)			\
+		goto err;		\
+	p->type = stype;		\
+} while (0)
+
+/*
+ * Read the pmu events list from sysfs
+ * Save it into perf_pmu_events_list
+ */
+static void perf_pmu__parse_init(void)
+{
+
+	struct perf_pmu *pmu = NULL;
+	struct perf_pmu_alias *alias;
 	int len = 0;
 
-	if (!o)
-		return ret;
-	while ((p = strsep(&t, ",")) != NULL) {
-		if (s)
-			str_append(&s, &len, ",");
-		str_append(&s, &len, "cpu/");
-		str_append(&s, &len, p);
-		str_append(&s, &len, "/");
+	pmu = perf_pmu__find("cpu");
+	if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+		perf_pmu_events_list_num = -1;
+		return;
 	}
-	free(o);
-	if (!s)
-		return -ENOMEM;
-	return parse_events__scanner(s, data, start_token);
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (strchr(alias->name, '-'))
+			len++;
+		len++;
+	}
+	perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
+	if (!perf_pmu_events_list)
+		return;
+	perf_pmu_events_list_num = len;
+
+	len = 0;
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+		char *tmp = strchr(alias->name, '-');
+
+		if (tmp != NULL) {
+			SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+					PMU_EVENT_SYMBOL_PREFIX);
+			p++;
+			SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+			len += 2;
+		} else {
+			SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+			len++;
+		}
+	}
+	qsort(perf_pmu_events_list, len,
+		sizeof(struct perf_pmu_event_symbol), comp_pmu);
+
+	return;
+err:
+	perf_pmu__parse_cleanup();
+}
+
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name)
+{
+	struct perf_pmu_event_symbol p, *r;
+
+	/* scan kernel pmu events from sysfs if needed */
+	if (perf_pmu_events_list_num == 0)
+		perf_pmu__parse_init();
+	/*
+	 * name "cpu" could be prefix of cpu-cycles or cpu// events.
+	 * cpu-cycles has been handled by hardcode.
+	 * So it must be cpu// events, not kernel pmu event.
+	 */
+	if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu"))
+		return PMU_EVENT_SYMBOL_ERR;
+
+	p.symbol = strdup(name);
+	r = bsearch(&p, perf_pmu_events_list,
+			(size_t) perf_pmu_events_list_num,
+			sizeof(struct perf_pmu_event_symbol), comp_pmu);
+	free(p.symbol);
+	return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
 static int parse_events__scanner(const char *str, void *data, int start_token)
@@ -909,8 +999,6 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
 	parse_events__flush_buffer(buffer, scanner);
 	parse_events__delete_buffer(buffer, scanner);
 	parse_events_lex_destroy(scanner);
-	if (ret && !strchr(str, '/'))
-		ret = parse_events_fixup(ret, str, data, start_token);
 	return ret;
 }
 
@@ -945,6 +1033,7 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	int ret;
 
 	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+	perf_pmu__parse_cleanup();
 	if (!ret) {
 		int entries = data.idx - evlist->nr_entries;
 		perf_evlist__splice_list_tail(evlist, &data.list, entries);
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index df094b4ed5ed..db2cf78ff0f3 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -35,6 +35,18 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum perf_pmu_event_symbol_type {
+	PMU_EVENT_SYMBOL_ERR,		/* not a PMU EVENT */
+	PMU_EVENT_SYMBOL,		/* normal style PMU event */
+	PMU_EVENT_SYMBOL_PREFIX,	/* prefix of pre-suf style event */
+	PMU_EVENT_SYMBOL_SUFFIX,	/* suffix of pre-suf style event */
+};
+
+struct perf_pmu_event_symbol {
+	char	*symbol;
+	enum perf_pmu_event_symbol_type	type;
+};
+
 enum {
 	PARSE_EVENTS__TERM_TYPE_NUM,
 	PARSE_EVENTS__TERM_TYPE_STR,
@@ -95,6 +107,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type);
 int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *pmu , struct list_head *head_config);
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 343299575b30..906630bbf8eb 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -51,6 +51,24 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+static int pmu_str_check(yyscan_t scanner)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	yylval->str = strdup(text);
+	switch (perf_pmu__parse_check(text)) {
+		case PMU_EVENT_SYMBOL_PREFIX:
+			return PE_PMU_EVENT_PRE;
+		case PMU_EVENT_SYMBOL_SUFFIX:
+			return PE_PMU_EVENT_SUF;
+		case PMU_EVENT_SYMBOL:
+			return PE_KERNEL_PMU_EVENT;
+		default:
+			return PE_NAME;
+	}
+}
+
 static int sym(yyscan_t scanner, int type, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -178,6 +196,16 @@ alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 
+	/*
+	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
+	 * Because the prefix cycles is mixed up with cpu-cycles.
+	 * loads and stores are mixed up with cache event
+	 */
+cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+cycles-t					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-loads					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-stores					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|
 LLC|L2					|
@@ -199,7 +227,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{name}			{ return str(yyscanner, PE_NAME); }
+{name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }
 ,			{ BEGIN(event); return ','; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 55fab6ad609a..93c4c9fbc922 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -47,6 +47,7 @@ static inc_group_count(struct list_head *list,
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
+%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -58,6 +59,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
+%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
 %type <term> event_term
@@ -220,6 +222,44 @@ PE_NAME '/' '/'
 	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
 	$$ = list;
 }
+|
+PE_KERNEL_PMU_EVENT sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+
+	ALLOC_LIST(head);
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, 1));
+	list_add_tail(&term->list, head);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	parse_events__free_terms(head);
+	$$ = list;
+}
+|
+PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+	char pmu_name[128];
+	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+
+	ALLOC_LIST(head);
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					&pmu_name, 1));
+	list_add_tail(&term->list, head);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	parse_events__free_terms(head);
+	$$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 93a41ca96b8e..e243ad962a4d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -12,16 +12,6 @@
 #include "parse-events.h"
 #include "cpumap.h"
 
-#define UNIT_MAX_LEN	31 /* max length for event unit name */
-
-struct perf_pmu_alias {
-	char *name;
-	struct list_head terms; /* HEAD struct parse_events_term -> list */
-	struct list_head list;  /* ELEM */
-	char unit[UNIT_MAX_LEN+1];
-	double scale;
-};
-
 struct perf_pmu_format {
 	char *name;
 	int value;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fe90a012c003..fe9dfbee8eed 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -30,6 +30,16 @@ struct perf_pmu_info {
 	double scale;
 };
 
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
+struct perf_pmu_alias {
+	char *name;
+	struct list_head terms; /* HEAD struct parse_events_term -> list */
+	struct list_head list;  /* ELEM */
+	char unit[UNIT_MAX_LEN+1];
+	double scale;
+};
+
 struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 56ba07cce549..496f21cadd97 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -28,6 +28,7 @@
 
 #include "../../perf.h"
 #include "../debug.h"
+#include "../callchain.h"
 #include "../evsel.h"
 #include "../util.h"
 #include "../event.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 883406f4b381..6702ac28754b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -532,17 +532,16 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
 			return -EINVAL;
 	}
 
-	new = ordered_events__new(oe, timestamp);
+	new = ordered_events__new(oe, timestamp, event);
 	if (!new) {
 		ordered_events__flush(s, tool, OE_FLUSH__HALF);
-		new = ordered_events__new(oe, timestamp);
+		new = ordered_events__new(oe, timestamp, event);
 	}
 
 	if (!new)
 		return -ENOMEM;
 
 	new->file_offset = file_offset;
-	new->event = event;
 	return 0;
 }
 
@@ -813,22 +812,6 @@ int perf_session__deliver_event(struct perf_session *session,
 	dump_event(session, event, file_offset, sample);
 
 	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
-		/*
-		 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
-		 * because the tools right now may apply filters, discarding
-		 * some of the samples. For consistency, in the future we
-		 * should have something like nr_filtered_samples and remove
-		 * the sample->period from total_sample_period, etc, KISS for
-		 * now tho.
-		 *
-		 * Also testing against NULL allows us to handle files without
-		 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
-		 * future probably it'll be a good idea to restrict event
-		 * processing via perf_session to files with both set.
-		 */
-		hists__inc_nr_events(&evsel->hists, event->header.type);
-	}
 
 	machine = perf_session__find_machine_for_cpumode(session, event,
 							 sample);
@@ -1391,16 +1374,9 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-	struct perf_evsel *pos;
 	size_t ret = fprintf(fp, "Aggregated stats:\n");
 
 	ret += events_stats__fprintf(&session->stats, fp);
-
-	evlist__for_each(session->evlist, pos) {
-		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
-		ret += events_stats__fprintf(&pos->hists.stats, fp);
-	}
-
 	return ret;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index ffb440462008..a4be851f1a90 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -2,7 +2,6 @@
 #define __PERF_SESSION_H
 
 #include "trace-event.h"
-#include "hist.h"
 #include "event.h"
 #include "header.h"
 #include "machine.h"
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 289df9d1e65a..4906cd81cb56 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1218,7 +1218,7 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
 
 	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
@@ -1233,7 +1233,7 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
 
 	return len;
 }
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d87767f76903..6afd6106ceb5 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -357,27 +357,3 @@ void *memdup(const void *src, size_t len)
 
 	return p;
 }
-
-/**
- * str_append - reallocate string and append another
- * @s: pointer to string pointer
- * @len: pointer to len (initialized)
- * @a: string to append.
- */
-int str_append(char **s, int *len, const char *a)
-{
-	int olen = *s ? strlen(*s) : 0;
-	int nlen = olen + strlen(a) + 1;
-	if (*len < nlen) {
-		*len = *len * 2;
-		if (*len < nlen)
-			*len = nlen;
-		*s = realloc(*s, *len);
-		if (!*s)
-			return -ENOMEM;
-		if (olen == 0)
-			**s = 0;
-	}
-	strcat(*s, a);
-	return 0;
-}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index be84f7a9838b..078331140d8c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -186,7 +186,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start - 1;
+			prev->end = curr->start;
 	}
 
 	/* Last entry */
@@ -207,7 +207,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
 		prev = curr;
 		curr = rb_entry(nd, struct map, rb_node);
-		prev->end = curr->start - 1;
+		prev->end = curr->start;
 	}
 
 	/*
@@ -229,7 +229,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 		sym = ((void *)sym) + symbol_conf.priv_size;
 
 	sym->start   = start;
-	sym->end     = len ? start + len - 1 : start;
+	sym->end     = len ? start + len : start;
 	sym->binding = binding;
 	sym->namelen = namelen - 1;
 
@@ -325,7 +325,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 
 		if (ip < s->start)
 			n = n->rb_left;
-		else if (ip > s->end)
+		else if (ip >= s->end)
 			n = n->rb_right;
 		else
 			return s;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bec4b7bd09de..eb2c19bf8d90 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -95,7 +95,7 @@ void symbols__delete(struct rb_root *symbols);
 
 static inline size_t symbol__size(const struct symbol *sym)
 {
-	return sym->end - sym->start + 1;
+	return sym->end - sym->start;
 }
 
 struct strlist;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index a9df7f2c6dc9..2b7b2d91c016 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,7 @@
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
+#include "unwind.h"
 
 int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
@@ -37,6 +38,9 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->comm_list);
 
+		if (unwind__prepare_access(thread) < 0)
+			goto err_thread;
+
 		comm_str = malloc(32);
 		if (!comm_str)
 			goto err_thread;
@@ -48,6 +52,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
+
 	}
 
 	return thread;
@@ -69,6 +74,7 @@ void thread__delete(struct thread *thread)
 		list_del(&comm->list);
 		comm__free(comm);
 	}
+	unwind__finish_access(thread);
 
 	free(thread);
 }
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5d3215912105..f93b9734735b 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -214,6 +214,17 @@ out_free_threads:
 	goto out;
 }
 
+struct thread_map *thread_map__new_dummy(void)
+{
+	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+	if (threads != NULL) {
+		threads->map[0]	= -1;
+		threads->nr	= 1;
+	}
+	return threads;
+}
+
 static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 {
 	struct thread_map *threads = NULL, *nt;
@@ -224,14 +235,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 	struct strlist *slist;
 
 	/* perf-stat expects threads to be generated even if tid not given */
-	if (!tid_str) {
-		threads = malloc(sizeof(*threads) + sizeof(pid_t));
-		if (threads != NULL) {
-			threads->map[0] = -1;
-			threads->nr	= 1;
-		}
-		return threads;
-	}
+	if (!tid_str)
+		return thread_map__new_dummy();
 
 	slist = strlist__new(false, tid_str);
 	if (!slist)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0cd8b3108084..95313f43cc0f 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -9,6 +9,7 @@ struct thread_map {
 	pid_t map[];
 };
 
+struct thread_map *thread_map__new_dummy(void);
 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_by_uid(uid_t uid);
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 92b56db52471..e060386165c5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -24,6 +24,7 @@
 #include <linux/list.h>
 #include <libunwind.h>
 #include <libunwind-ptrace.h>
+#include "callchain.h"
 #include "thread.h"
 #include "session.h"
 #include "perf_regs.h"
@@ -525,12 +526,12 @@ static unw_accessors_t accessors = {
 	.get_proc_name		= get_proc_name,
 };
 
-static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-		       void *arg, int max_stack)
+int unwind__prepare_access(struct thread *thread)
 {
 	unw_addr_space_t addr_space;
-	unw_cursor_t c;
-	int ret;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return 0;
 
 	addr_space = unw_create_addr_space(&accessors, 0);
 	if (!addr_space) {
@@ -538,6 +539,33 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		return -ENOMEM;
 	}
 
+	thread__set_priv(thread, addr_space);
+
+	return 0;
+}
+
+void unwind__finish_access(struct thread *thread)
+{
+	unw_addr_space_t addr_space;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	addr_space = thread__priv(thread);
+	unw_destroy_addr_space(addr_space);
+}
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+		       void *arg, int max_stack)
+{
+	unw_addr_space_t addr_space;
+	unw_cursor_t c;
+	int ret;
+
+	addr_space = thread__priv(ui->thread);
+	if (addr_space == NULL)
+		return -1;
+
 	ret = unw_init_remote(&c, addr_space, ui);
 	if (ret)
 		display_error(ret);
@@ -549,7 +577,6 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
 	}
 
-	unw_destroy_addr_space(addr_space);
 	return ret;
 }
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f03061260b4e..c17c4855bdbc 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "symbol.h"
+#include "thread.h"
 
 struct unwind_entry {
 	struct map	*map;
@@ -21,6 +22,15 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
+int unwind__prepare_access(struct thread *thread);
+void unwind__finish_access(struct thread *thread);
+#else
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+	return 0;
+}
+
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else
 static inline int
@@ -33,5 +43,12 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 {
 	return 0;
 }
+
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+	return 0;
+}
+
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 24e8d871b74e..d5eab3f3323f 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,14 @@
 #include <byteswap.h>
 #include <linux/kernel.h>
 #include <unistd.h>
+#include "callchain.h"
+
+struct callchain_param	callchain_param = {
+	.mode	= CHAIN_GRAPH_REL,
+	.min_percent = 0.5,
+	.order  = ORDER_CALLEE,
+	.key	= CCKEY_FUNCTION
+};
 
 /*
  * XXX We need to find a better place for these things...