Merge tag 'perf-core-for-mingo-4.16-20171206' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Improve build messages for files needed by Intel-PT, originally copied
  from the kernel sources, that drifted from its original (Adrian Hunter)

- Allow computing 'perf stat' style metrics in 'perf script' (Andi Kleen)

- Fix 'perf report -D' output for user metadata events (Arnaldo Carvalho de Melo)

- Add feature test for pthread_barrier_t availability (Arnaldo Carvalho de Melo)

- Allow again using x86's asm.h when building for the 'bpf' clang target,
  making some 'perf test' LLVM/BPF entries work again (Arnaldo Carvalho de Melo)

- Use cpumaps in 'perf bench futex', eliminating some code duplication
  (Davidlohr Bueso)

- Improve PMU infrastructure to support amp64's ThunderX2 implementation
  defined core events (Ganapatrao Kulkarni)

- Add hint about how to add USDT probes for Node.js (Hansuk Hong)

- s/390 needs -fPIC to be incrementally linked or linked to shared
  libraries (Hendrik Brueckner)

- Use pthread_barrier to synch 'perf bench futex wake-parallel' waker
  threads (James Yang)

- Fix up build in hardened environments, such as Fedora 27 (Jiri Olsa)

- Add a tip about cacheline events in 'perf c2c' (Sangwon Hong)

- Set browser mode right before setup_browser(), because we may have
  errors printed before that, which were getting lost (Seokho Song)

- s390x doesn't support PERF_TYPE_BREAKPOINT, so disable 'perf test'
  cases 19 and 20 on s390x, that tests that feature (Thomas Richter)

- Fix unnecessary memory allocation for s390x 'perf annotate' objdump
  parsing, which could lead to thousands of needless entries in the
  instruction handling array (Thomas Richter)

- Fix objdump comment parsing for Intel mov dissassembly (Thomas Richter)

- Clarify usage of 'overwrite' and 'backward' in the evlist/mmap code,
  removing the 'overwrite' parameter from several functions as it was
  always used it as 'false' (Wang Nan)

- Fix 'perf record' backward recording, it wasn't doing what was
  expected: overwriting records when the ring buffer gets full (Wang Nan)

- Use more flexible pattern matching for CPU identification for perf
  vendor event's mapfile.csv, removing the need for a new perf binary
  for a sligthly different chip revision that shares the same set of
  counters (William Cohen)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 275 insertions, 128 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 22ea7936d92f..facad1e279a8 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -322,6 +322,8 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 		return 0;
 
 	*addrp = strtoull(comment, &endptr, 16);
+	if (endptr == comment)
+		return 0;
 	name = strchr(endptr, '<');
 	if (name == NULL)
 		return -1;
@@ -435,8 +437,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 		return 0;
 
 	comment = ltrim(comment);
-	comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name);
-	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
 	return 0;
 
@@ -480,7 +482,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 		return 0;
 
 	comment = ltrim(comment);
-	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
 	return 0;
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 199bb82efbcd..3570355bcf39 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
-	zfree(&evlist->backward_mmap);
+	zfree(&evlist->overwrite_mmap);
 	fdarray__exit(&evlist->pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
 	int i;
 
-	if (!evlist->backward_mmap)
+	if (!evlist->overwrite_mmap)
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		int fd = evlist->backward_mmap[i].fd;
+		int fd = evlist->overwrite_mmap[i].fd;
 		int err;
 
 		if (fd < 0)
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
 	 * No need for read-write ring buffer: kernel stop outputting when
 	 * it hit md->prev (perf_mmap__consume()).
 	 */
-	return perf_mmap__read_forward(md, evlist->overwrite);
+	return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
@@ -738,7 +738,7 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-	perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
+	perf_mmap__consume(&evlist->mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -749,16 +749,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 		for (i = 0; i < evlist->nr_mmaps; i++)
 			perf_mmap__munmap(&evlist->mmap[i]);
 
-	if (evlist->backward_mmap)
+	if (evlist->overwrite_mmap)
 		for (i = 0; i < evlist->nr_mmaps; i++)
-			perf_mmap__munmap(&evlist->backward_mmap[i]);
+			perf_mmap__munmap(&evlist->overwrite_mmap[i]);
 }
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
 	perf_evlist__munmap_nofree(evlist);
 	zfree(&evlist->mmap);
-	zfree(&evlist->backward_mmap);
+	zfree(&evlist->overwrite_mmap);
 }
 
 static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
@@ -800,7 +800,7 @@ perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 				       struct mmap_params *mp, int cpu_idx,
-				       int thread, int *_output, int *_output_backward)
+				       int thread, int *_output, int *_output_overwrite)
 {
 	struct perf_evsel *evsel;
 	int revent;
@@ -812,18 +812,20 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		int fd;
 		int cpu;
 
+		mp->prot = PROT_READ | PROT_WRITE;
 		if (evsel->attr.write_backward) {
-			output = _output_backward;
-			maps = evlist->backward_mmap;
+			output = _output_overwrite;
+			maps = evlist->overwrite_mmap;
 
 			if (!maps) {
 				maps = perf_evlist__alloc_mmap(evlist);
 				if (!maps)
 					return -1;
-				evlist->backward_mmap = maps;
+				evlist->overwrite_mmap = maps;
 				if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
 					perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
 			}
+			mp->prot &= ~PROT_WRITE;
 		}
 
 		if (evsel->system_wide && thread)
@@ -884,14 +886,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
-		int output_backward = -1;
+		int output_overwrite = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
 					      true);
 
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-							thread, &output, &output_backward))
+							thread, &output, &output_overwrite))
 				goto out_unmap;
 		}
 	}
@@ -912,13 +914,13 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
-		int output_backward = -1;
+		int output_overwrite = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
 					      false);
 
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-						&output, &output_backward))
+						&output, &output_overwrite))
 			goto out_unmap;
 	}
 
@@ -1052,15 +1054,18 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-			 bool overwrite, unsigned int auxtrace_pages,
+			 unsigned int auxtrace_pages,
 			 bool auxtrace_overwrite)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	struct mmap_params mp = {
-		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
-	};
+	/*
+	 * Delay setting mp.prot: set it before calling perf_mmap__mmap.
+	 * Its value is decided by evsel's write_backward.
+	 * So &mp should not be passed through const pointer.
+	 */
+	struct mmap_params mp;
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist);
@@ -1070,7 +1075,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
-	evlist->overwrite = overwrite;
 	evlist->mmap_len = perf_evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
 	mp.mask = evlist->mmap_len - page_size - 1;
@@ -1091,10 +1095,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite)
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
@@ -1750,7 +1753,7 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 		RESUME,
 	} action = NONE;
 
-	if (!evlist->backward_mmap)
+	if (!evlist->overwrite_mmap)
 		return;
 
 	switch (old_state) {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4e8131dacbd7..75160666d305 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -31,7 +31,6 @@ struct perf_evlist {
 	int		 nr_entries;
 	int		 nr_groups;
 	int		 nr_mmaps;
-	bool		 overwrite;
 	bool		 enabled;
 	bool		 has_user_cpus;
 	size_t		 mmap_len;
@@ -45,7 +44,7 @@ struct perf_evlist {
 	} workload;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
-	struct perf_mmap *backward_mmap;
+	struct perf_mmap *overwrite_mmap;
 	struct thread_map *threads;
 	struct cpu_map	  *cpus;
 	struct perf_evsel *selected;
@@ -169,10 +168,9 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-			 bool overwrite, unsigned int auxtrace_pages,
+			 unsigned int auxtrace_pages,
 			 bool auxtrace_overwrite);
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite);
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 size_t perf_evlist__mmap_size(unsigned long pages);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 7c0e9d587bfa..5890e08e0754 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3258,6 +3258,74 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	return err;
 }
 
+static bool has_unit(struct perf_evsel *counter)
+{
+	return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+	return counter->scale != 1;
+}
+
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+				      struct perf_evlist *evsel_list,
+				      perf_event__handler_t process,
+				      bool is_pipe)
+{
+	struct perf_evsel *counter;
+	int err;
+
+	/*
+	 * Synthesize other events stuff not carried within
+	 * attr event - unit, scale, name
+	 */
+	evlist__for_each_entry(evsel_list, counter) {
+		if (!counter->supported)
+			continue;
+
+		/*
+		 * Synthesize unit and scale only if it's defined.
+		 */
+		if (has_unit(counter)) {
+			err = perf_event__synthesize_event_update_unit(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel unit.\n");
+				return err;
+			}
+		}
+
+		if (has_scale(counter)) {
+			err = perf_event__synthesize_event_update_scale(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel counter.\n");
+				return err;
+			}
+		}
+
+		if (counter->own_cpus) {
+			err = perf_event__synthesize_event_update_cpus(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel cpus.\n");
+				return err;
+			}
+		}
+
+		/*
+		 * Name is needed only for pipe output,
+		 * perf.data carries event names.
+		 */
+		if (is_pipe) {
+			err = perf_event__synthesize_event_update_name(tool, counter, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel name.\n");
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
 int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_evlist **pevlist)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 29ccbfdf8724..317fb901e47f 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "env.h"
+#include "pmu.h"
 
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
@@ -107,6 +108,11 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 				    struct perf_evlist *evlist,
 				    perf_event__handler_t process);
 
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+				      struct perf_evlist *evsel_list,
+				      perf_event__handler_t process,
+				      bool is_pipe);
+
 int perf_event__process_feature(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_session *session);
@@ -166,5 +172,5 @@ int write_padded(struct feat_fd *fd, const void *bf,
  */
 int get_cpuid(char *buffer, size_t sz);
 
-char *get_cpuid_str(void);
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 10e0814bb8d2..1b704fbea9de 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -11,15 +11,21 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
-	test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
-	diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
-	diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
-	diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
-	diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
-	|| echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true
+	test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \
+	((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \
+	((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \
+	((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \
+	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 0ddd9c199227..e48410c99b39 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -38,6 +38,10 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 	struct metric_event me = {
 		.evsel = evsel
 	};
+
+	if (!metric_events)
+		return NULL;
+
 	nd = rblist__find(metric_events, &me);
 	if (nd)
 		return container_of(nd, struct metric_event, nd);
@@ -270,7 +274,7 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
 void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 			bool raw)
 {
-	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
 	int i;
 	struct rblist groups;
@@ -368,7 +372,7 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
-	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
 	int ret = -EINVAL;
 	int i, j;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c7d577..05076e683938 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -21,33 +21,13 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map, bool check_messup,
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
 					 u64 start, u64 end, u64 *prev)
 {
 	unsigned char *data = map->base + page_size;
 	union perf_event *event = NULL;
 	int diff = end - start;
 
-	if (check_messup) {
-		/*
-		 * If we're further behind than half the buffer, there's a chance
-		 * the writer will bite our tail and mess up the samples under us.
-		 *
-		 * If we somehow ended up ahead of the 'end', we got messed up.
-		 *
-		 * In either case, truncate and restart at 'end'.
-		 */
-		if (diff > map->mask / 2 || diff < 0) {
-			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-			/*
-			 * 'end' points to a known good entry, start there.
-			 */
-			start = end;
-			diff = 0;
-		}
-	}
-
 	if (diff >= (int)sizeof(event->header)) {
 		size_t size;
 
@@ -89,7 +69,7 @@ broken_event:
 	return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
 	u64 head;
 	u64 old = map->prev;
@@ -102,7 +82,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_mess
 
 	head = perf_mmap__read_head(map);
 
-	return perf_mmap__read(map, check_messup, old, head, &map->prev);
+	return perf_mmap__read(map, old, head, &map->prev);
 }
 
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
@@ -138,7 +118,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
 	else
 		end = head + map->mask + 1;
 
-	return perf_mmap__read(map, false, start, end, &map->prev);
+	return perf_mmap__read(map, start, end, &map->prev);
 }
 
 void perf_mmap__read_catchup(struct perf_mmap *map)
@@ -254,18 +234,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
 	return 0;
 }
 
-static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 {
 	struct perf_event_header *pheader;
 	u64 evt_head = head;
 	int size = mask + 1;
 
-	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+	pr_debug2("overwrite_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
 	pheader = (struct perf_event_header *)(buf + (head & mask));
 	*start = head;
 	while (true) {
 		if (evt_head - head >= (unsigned int)size) {
-			pr_debug("Finished reading backward ring buffer: rewind\n");
+			pr_debug("Finished reading overwrite ring buffer: rewind\n");
 			if (evt_head - head > (unsigned int)size)
 				evt_head -= pheader->size;
 			*end = evt_head;
@@ -275,7 +255,7 @@ static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64
 		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
 
 		if (pheader->size == 0) {
-			pr_debug("Finished reading backward ring buffer: get start\n");
+			pr_debug("Finished reading overwrite ring buffer: get start\n");
 			*end = evt_head;
 			return 0;
 		}
@@ -287,19 +267,7 @@ static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64
 	return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-			 u64 *start, u64 *end, bool backward)
-{
-	if (!backward) {
-		*start = old;
-		*end = head;
-		return 0;
-	}
-
-	return backward_rb_find_range(data, mask, head, start, end);
-}
-
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 		    void *to, int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
@@ -310,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
 	void *buf;
 	int rc = 0;
 
-	if (rb_find_range(data, md->mask, head, old, &start, &end, backward))
-		return -1;
+	start = overwrite ? head : old;
+	end = overwrite ? old : head;
 
 	if (start == end)
 		return 0;
 
 	size = end - start;
 	if (size > (unsigned long)(md->mask) + 1) {
-		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+		if (!overwrite) {
+			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
-		md->prev = head;
-		perf_mmap__consume(md, overwrite || backward);
-		return 0;
+			md->prev = head;
+			perf_mmap__consume(md, overwrite);
+			return 0;
+		}
+
+		/*
+		 * Backward ring buffer is full. We still have a chance to read
+		 * most of data from it.
+		 */
+		if (overwrite_rb_find_range(data, md->mask, head, &start, &end))
+			return -1;
 	}
 
 	if ((start & md->mask) + size != (end & md->mask)) {
@@ -346,7 +323,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, overwrite || backward);
+	perf_mmap__consume(md, overwrite);
 out:
 	return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index efd78b827b05..d640273b7762 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -86,10 +86,10 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 	pc->data_tail = tail;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
 		    void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 80fb1593913a..57e38fdf0b34 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -12,6 +12,7 @@
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
+#include <regex.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
@@ -537,17 +538,45 @@ static bool pmu_is_uncore(const char *name)
 }
 
 /*
+ *  PMU CORE devices have different name other than cpu in sysfs on some
+ *  platforms. looking for possible sysfs files to identify as core device.
+ */
+static int is_pmu_core(const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return 0;
+
+	/* Look for cpu sysfs (x86 and others) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
+	if ((stat(path, &st) == 0) &&
+			(strncmp(name, "cpu", strlen("cpu")) == 0))
+		return 1;
+
+	/* Look for cpu sysfs (specific to arm) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
+				sysfs, name);
+	if (stat(path, &st) == 0)
+		return 1;
+
+	return 0;
+}
+
+/*
  * Return the CPU id as a raw string.
  *
  * Each architecture should provide a more precise id string that
  * can be use to match the architecture's "mapfile".
  */
-char * __weak get_cpuid_str(void)
+char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	return NULL;
 }
 
-static char *perf_pmu__getcpuid(void)
+static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
 	char *cpuid;
 	static bool printed;
@@ -556,7 +585,7 @@ static char *perf_pmu__getcpuid(void)
 	if (cpuid)
 		cpuid = strdup(cpuid);
 	if (!cpuid)
-		cpuid = get_cpuid_str();
+		cpuid = get_cpuid_str(pmu);
 	if (!cpuid)
 		return NULL;
 
@@ -567,22 +596,45 @@ static char *perf_pmu__getcpuid(void)
 	return cpuid;
 }
 
-struct pmu_events_map *perf_pmu__find_map(void)
+struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
 {
 	struct pmu_events_map *map;
-	char *cpuid = perf_pmu__getcpuid();
+	char *cpuid = perf_pmu__getcpuid(pmu);
 	int i;
 
+	/* on some platforms which uses cpus map, cpuid can be NULL for
+	 * PMUs other than CORE PMUs.
+	 */
+	if (!cpuid)
+		return NULL;
+
 	i = 0;
 	for (;;) {
+		regex_t re;
+		regmatch_t pmatch[1];
+		int match;
+
 		map = &pmu_events_map[i++];
 		if (!map->table) {
 			map = NULL;
 			break;
 		}
 
-		if (!strcmp(map->cpuid, cpuid))
+		if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
+			/* Warn unable to generate match particular string. */
+			pr_info("Invalid regular expression %s\n", map->cpuid);
 			break;
+		}
+
+		match = !regexec(&re, cpuid, 1, pmatch, 0);
+		regfree(&re);
+		if (match) {
+			size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+			/* Verify the entire string matched. */
+			if (match_len == strlen(cpuid))
+				break;
+		}
 	}
 	free(cpuid);
 	return map;
@@ -593,13 +645,14 @@ struct pmu_events_map *perf_pmu__find_map(void)
  * to the current running CPU. Then, add all PMU events from that table
  * as aliases.
  */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 {
 	int i;
 	struct pmu_events_map *map;
 	struct pmu_event *pe;
+	const char *name = pmu->name;
 
-	map = perf_pmu__find_map();
+	map = perf_pmu__find_map(pmu);
 	if (!map)
 		return;
 
@@ -608,7 +661,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 	 */
 	i = 0;
 	while (1) {
-		const char *pname;
 
 		pe = &map->table[i++];
 		if (!pe->name) {
@@ -617,9 +669,13 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 			break;
 		}
 
-		pname = pe->pmu ? pe->pmu : "cpu";
-		if (strncmp(pname, name, strlen(pname)))
-			continue;
+		if (!is_pmu_core(name)) {
+			/* check for uncore devices */
+			if (pe->pmu == NULL)
+				continue;
+			if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+				continue;
+		}
 
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
@@ -661,21 +717,20 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	if (pmu_aliases(name, &aliases))
 		return NULL;
 
-	pmu_add_cpu_aliases(&aliases, name);
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
 		return NULL;
 
 	pmu->cpus = pmu_cpumask(name);
-
+	pmu->name = strdup(name);
+	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(name);
+	pmu_add_cpu_aliases(&aliases, pmu);
 
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
 	list_splice(&aliases, &pmu->aliases);
-	pmu->name = strdup(name);
-	pmu->type = type;
 	list_add_tail(&pmu->list, &pmus);
 
 	pmu->default_config = perf_pmu__get_default_config(pmu);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 27c75e635866..76fecec7b3f9 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -92,6 +92,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
-struct pmu_events_map *perf_pmu__find_map(void);
+struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 8e49d9cafcfc..b1e999bd21ef 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -864,7 +864,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
 					 &pages, &overwrite))
 		return NULL;
 
-	if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+	if (perf_evlist__mmap(evlist, pages) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
index 0dfe27d99458..0efc3258c648 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -101,16 +101,21 @@ void rblist__init(struct rblist *rblist)
 	return;
 }
 
+void rblist__exit(struct rblist *rblist)
+{
+	struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+	while (next) {
+		pos = next;
+		next = rb_next(pos);
+		rblist__remove_node(rblist, pos);
+	}
+}
+
 void rblist__delete(struct rblist *rblist)
 {
 	if (rblist != NULL) {
-		struct rb_node *pos, *next = rb_first(&rblist->entries);
-
-		while (next) {
-			pos = next;
-			next = rb_next(pos);
-			rblist__remove_node(rblist, pos);
-		}
+		rblist__exit(rblist);
 		free(rblist);
 	}
 }
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index 4c8638a22571..76df15c27f5f 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -29,6 +29,7 @@ struct rblist {
 };
 
 void rblist__init(struct rblist *rblist);
+void rblist__exit(struct rblist *rblist);
 void rblist__delete(struct rblist *rblist);
 int rblist__add_node(struct rblist *rblist, const void *new_entry);
 void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index df2857137908..54e30f1bcbd7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1348,10 +1348,11 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
+	struct perf_sample sample = { .time = 0, };
 	int fd = perf_data__fd(session->data);
 	int err;
 
-	dump_event(session->evlist, event, file_offset, NULL);
+	dump_event(session->evlist, event, file_offset, &sample);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 855e35cbb1dc..57ec22513971 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -87,6 +87,16 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
 	return &nd->rb_node;
 }
 
+static void saved_value_delete(struct rblist *rblist __maybe_unused,
+			       struct rb_node *rb_node)
+{
+	struct saved_value *v;
+
+	BUG_ON(!rb_node);
+	v = container_of(rb_node, struct saved_value, rb_node);
+	free(v);
+}
+
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
 					      int cpu,
 					      bool create)
@@ -114,7 +124,7 @@ void perf_stat__init_shadow_stats(void)
 	rblist__init(&runtime_saved_values);
 	runtime_saved_values.node_cmp = saved_value_cmp;
 	runtime_saved_values.node_new = saved_value_new;
-	/* No delete for now */
+	runtime_saved_values.node_delete = saved_value_delete;
 }
 
 static int evsel_context(struct perf_evsel *evsel)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index be0d5a736dea..2b653853eec2 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -92,7 +92,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	return threads;
 }
 
-struct thread_map *thread_map__new_by_uid(uid_t uid)
+static struct thread_map *__thread_map__new_all_cpus(uid_t uid)
 {
 	DIR *proc;
 	int max_threads = 32, items, i;
@@ -113,7 +113,6 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
-		struct stat st;
 		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
@@ -121,11 +120,12 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 
 		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
-		if (stat(path, &st) != 0)
-			continue;
+		if (uid != UINT_MAX) {
+			struct stat st;
 
-		if (st.st_uid != uid)
-			continue;
+			if (stat(path, &st) != 0 || st.st_uid != uid)
+				continue;
+		}
 
 		snprintf(path, sizeof(path), "/proc/%d/task", pid);
 		items = scandir(path, &namelist, filter, NULL);
@@ -178,6 +178,16 @@ out_free_closedir:
 	goto out_closedir;
 }
 
+struct thread_map *thread_map__new_all_cpus(void)
+{
+	return __thread_map__new_all_cpus(UINT_MAX);
+}
+
+struct thread_map *thread_map__new_by_uid(uid_t uid)
+{
+	return __thread_map__new_all_cpus(uid);
+}
+
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
 {
 	if (pid != -1)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index f15803985435..07a765fb22bb 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -23,6 +23,7 @@ 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);
+struct thread_map *thread_map__new_all_cpus(void);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 struct thread_map *thread_map__new_event(struct thread_map_event *event);