Merge tag 'perf-core-for-mingo' 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:

  - Accept a zero --itrace period, meaning "as often as possible".  In the case
    of Intel PT that is the same as a period of 1 and a unit of 'instructions'
    (i.e.  --itrace=i1i). (Adrian Hunter)

  - Harmonize itrace's synthesized callchains with the existing --max-stack
    tool option. (Adrian Hunter)

  - Allow time to be displayed in nanoseconds in 'perf script'. (Adrian Hunter)

  - Fix potential infinite loop when handling Intel PT timestamps. (Adrian Hunter)

  - Slighly improve Intel PT debug logging. (Adrian Hunter)

  - Warn when AUX data has been lost, just like when processing PERF_RECORD_LOST.
    (Adrian Hunter)

  - Further document export-to-postgresql.py script. (Adrian Hunter)

  - Add option to synthesize branch stack from auxtrace data. (Adrian Hunter)

  - Use equivalent logic to avoid using dso->kernel. (Arnaldo Carvalho de Melo)

  - Show proper error messages when parsing bad terms for hw/sw events. (He Kuang)

  - Tracepoint event parsing improvements. (He Kuang)

  - Store tracing mountpoint for better error message. (Jiri Olsa)

  - Add fixdep to tools/build, bringing it closer to the kernel counterpart, from
    where it is being lifted. (Jiri Olsa)

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

20 files changed, 428 insertions, 94 deletions

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a980e7c50ee0..7f10430af39c 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -926,6 +926,8 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool,
 #define PERF_ITRACE_DEFAULT_PERIOD		100000
 #define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ	16
 #define PERF_ITRACE_MAX_CALLCHAIN_SZ		1024
+#define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
+#define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
 void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 {
@@ -936,6 +938,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
 	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 }
 
 /*
@@ -950,6 +953,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 	const char *p;
 	char *endptr;
 	bool period_type_set = false;
+	bool period_set = false;
 
 	synth_opts->set = true;
 
@@ -971,6 +975,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				p += 1;
 			if (isdigit(*p)) {
 				synth_opts->period = strtoull(p, &endptr, 10);
+				period_set = true;
 				p = endptr;
 				while (*p == ' ' || *p == ',')
 					p += 1;
@@ -1041,6 +1046,23 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->callchain_sz = val;
 			}
 			break;
+		case 'l':
+			synth_opts->last_branch = true;
+			synth_opts->last_branch_sz =
+					PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				unsigned int val;
+
+				val = strtoul(p, &endptr, 10);
+				p = endptr;
+				if (!val ||
+				    val > PERF_ITRACE_MAX_LAST_BRANCH_SZ)
+					goto out_err;
+				synth_opts->last_branch_sz = val;
+			}
+			break;
 		case ' ':
 		case ',':
 			break;
@@ -1053,7 +1075,7 @@ out:
 		if (!period_type_set)
 			synth_opts->period_type =
 					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-		if (!synth_opts->period)
+		if (!period_set)
 			synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
 	}
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bf72b77a588a..b86f90db1352 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -63,7 +63,9 @@ enum itrace_period_type {
  * @calls: limit branch samples to calls (can be combined with @returns)
  * @returns: limit branch samples to returns (can be combined with @calls)
  * @callchain: add callchain to 'instructions' events
+ * @last_branch: add branch context to 'instruction' events
  * @callchain_sz: maximum callchain size
+ * @last_branch_sz: branch context size
  * @period: 'instructions' events period
  * @period_type: 'instructions' events period type
  */
@@ -79,7 +81,9 @@ struct itrace_synth_opts {
 	bool			calls;
 	bool			returns;
 	bool			callchain;
+	bool			last_branch;
 	unsigned int		callchain_sz;
+	unsigned int		last_branch_sz;
 	unsigned long long	period;
 	enum itrace_period_type	period_type;
 };
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6214ad47d554..b1bb348ec3b6 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -378,7 +378,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
 
-		if (pos->dso->kernel)
+		if (__map__is_kernel(pos))
 			continue;
 
 		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index be5cbc7be889..a0dbcbd4f6d8 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -257,6 +257,7 @@ struct events_stats {
 	u64 total_non_filtered_period;
 	u64 total_lost;
 	u64 total_lost_samples;
+	u64 total_aux_lost;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a8643735dcea..89546228b8ed 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -165,6 +165,13 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 	__perf_evlist__propagate_maps(evlist, entry);
 }
 
+void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel)
+{
+	evsel->evlist = NULL;
+	list_del_init(&evsel->node);
+	evlist->nr_entries -= 1;
+}
+
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 				   struct list_head *list)
 {
@@ -617,6 +624,21 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
+struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
+						u64 id)
+{
+	struct perf_sample_id *sid;
+
+	if (!id)
+		return NULL;
+
+	sid = perf_evlist__id2sid(evlist, id);
+	if (sid)
+		return sid->evsel;
+
+	return NULL;
+}
+
 static int perf_evlist__event2id(struct perf_evlist *evlist,
 				 union perf_event *event, u64 *id)
 {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 115d8b53c601..66bc9d4c0869 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -73,6 +73,7 @@ void perf_evlist__exit(struct perf_evlist *evlist);
 void perf_evlist__delete(struct perf_evlist *evlist);
 
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
+void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel);
 int perf_evlist__add_default(struct perf_evlist *evlist);
 int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
 				     struct perf_event_attr *attrs, size_t nr_attrs);
@@ -104,6 +105,8 @@ int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mas
 int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
+struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
+						u64 id);
 
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b3567a25f0c4..0cad9e07c5b4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -695,7 +695,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter,
 }
 
 static int
-iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
 			      struct addr_location *al __maybe_unused)
 {
 	struct hist_entry **he_cache;
@@ -707,7 +707,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
 	 * cumulated only one time to prevent entries more than 100%
 	 * overhead.
 	 */
-	he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+	he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1));
 	if (he_cache == NULL)
 		return -ENOMEM;
 
@@ -868,6 +868,8 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (err)
 		return err;
 
+	iter->max_stack = max_stack_depth;
+
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4d6aa1dbdaee..8c20a8f6b214 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -90,6 +90,7 @@ struct hist_entry_iter {
 	int curr;
 
 	bool hide_unresolved;
+	int max_stack;
 
 	struct perf_evsel *evsel;
 	struct perf_sample *sample;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 22ba50224319..9409d014b46c 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -650,7 +650,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 		if (data->from_mtc && timestamp < data->timestamp &&
 		    data->timestamp - timestamp < decoder->tsc_slip)
 			return 1;
-		while (timestamp < data->timestamp)
+		if (timestamp < data->timestamp)
 			timestamp += (1ULL << 56);
 		if (pkt_info->last_packet_type != INTEL_PT_CYC) {
 			if (data->from_mtc)
@@ -1191,7 +1191,7 @@ static void intel_pt_calc_tsc_timestamp(struct intel_pt_decoder *decoder)
 					timestamp);
 			timestamp = decoder->timestamp;
 		}
-		while (timestamp < decoder->timestamp) {
+		if (timestamp < decoder->timestamp) {
 			intel_pt_log_to("Wraparound timestamp", timestamp);
 			timestamp += (1ULL << 56);
 			decoder->tsc_timestamp = timestamp;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
index d09c7d9f9050..319bef33a64b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -29,18 +29,18 @@
 
 static FILE *f;
 static char log_name[MAX_LOG_NAME];
-static bool enable_logging;
+bool intel_pt_enable_logging;
 
 void intel_pt_log_enable(void)
 {
-	enable_logging = true;
+	intel_pt_enable_logging = true;
 }
 
 void intel_pt_log_disable(void)
 {
 	if (f)
 		fflush(f);
-	enable_logging = false;
+	intel_pt_enable_logging = false;
 }
 
 void intel_pt_log_set_name(const char *name)
@@ -80,7 +80,7 @@ static void intel_pt_print_no_data(uint64_t pos, int indent)
 
 static int intel_pt_log_open(void)
 {
-	if (!enable_logging)
+	if (!intel_pt_enable_logging)
 		return -1;
 
 	if (f)
@@ -91,15 +91,15 @@ static int intel_pt_log_open(void)
 
 	f = fopen(log_name, "w+");
 	if (!f) {
-		enable_logging = false;
+		intel_pt_enable_logging = false;
 		return -1;
 	}
 
 	return 0;
 }
 
-void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
-			 uint64_t pos, const unsigned char *buf)
+void __intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
+			   uint64_t pos, const unsigned char *buf)
 {
 	char desc[INTEL_PT_PKT_DESC_MAX];
 
@@ -111,7 +111,7 @@ void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
 	fprintf(f, "%s\n", desc);
 }
 
-void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 {
 	char desc[INTEL_PT_INSN_DESC_MAX];
 	size_t len = intel_pt_insn->length;
@@ -128,7 +128,8 @@ void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 		fprintf(f, "Bad instruction!\n");
 }
 
-void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
+				 uint64_t ip)
 {
 	char desc[INTEL_PT_INSN_DESC_MAX];
 
@@ -142,7 +143,7 @@ void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 		fprintf(f, "Bad instruction!\n");
 }
 
-void intel_pt_log(const char *fmt, ...)
+void __intel_pt_log(const char *fmt, ...)
 {
 	va_list args;
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index db3942f83677..debe751dc3d6 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -25,20 +25,46 @@ void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);
 
-void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
-			 uint64_t pos, const unsigned char *buf);
+void __intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
+			   uint64_t pos, const unsigned char *buf);
 
 struct intel_pt_insn;
 
-void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip);
-void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
-			       uint64_t ip);
+void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip);
+void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
+				 uint64_t ip);
 
 __attribute__((format(printf, 1, 2)))
-void intel_pt_log(const char *fmt, ...);
+void __intel_pt_log(const char *fmt, ...);
+
+#define intel_pt_log(fmt, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log(fmt, ##__VA_ARGS__); \
+	} while (0)
+
+#define intel_pt_log_packet(arg, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log_packet(arg, ##__VA_ARGS__); \
+	} while (0)
+
+#define intel_pt_log_insn(arg, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log_insn(arg, ##__VA_ARGS__); \
+	} while (0)
+
+#define intel_pt_log_insn_no_data(arg, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log_insn_no_data(arg, ##__VA_ARGS__); \
+	} while (0)
 
 #define x64_fmt "0x%" PRIx64
 
+extern bool intel_pt_enable_logging;
+
 static inline void intel_pt_log_at(const char *msg, uint64_t u)
 {
 	intel_pt_log("%s at " x64_fmt "\n", msg, u);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 38942e1eac8f..03ff072b5993 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -22,6 +22,7 @@
 #include "../perf.h"
 #include "session.h"
 #include "machine.h"
+#include "sort.h"
 #include "tool.h"
 #include "event.h"
 #include "evlist.h"
@@ -63,6 +64,7 @@ struct intel_pt {
 	bool data_queued;
 	bool est_tsc;
 	bool sync_switch;
+	bool mispred_all;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -115,6 +117,9 @@ struct intel_pt_queue {
 	void *decoder;
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
+	struct branch_stack *last_branch;
+	struct branch_stack *last_branch_rb;
+	size_t last_branch_pos;
 	union perf_event *event_buf;
 	bool on_heap;
 	bool stop;
@@ -675,6 +680,19 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 			goto out_free;
 	}
 
+	if (pt->synth_opts.last_branch) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += pt->synth_opts.last_branch_sz *
+		      sizeof(struct branch_entry);
+		ptq->last_branch = zalloc(sz);
+		if (!ptq->last_branch)
+			goto out_free;
+		ptq->last_branch_rb = zalloc(sz);
+		if (!ptq->last_branch_rb)
+			goto out_free;
+	}
+
 	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
 	if (!ptq->event_buf)
 		goto out_free;
@@ -720,7 +738,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 
 		if (!params.period) {
 			params.period_type = INTEL_PT_PERIOD_INSTRUCTIONS;
-			params.period = 1000;
+			params.period = 1;
 		}
 	}
 
@@ -732,6 +750,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 
 out_free:
 	zfree(&ptq->event_buf);
+	zfree(&ptq->last_branch);
+	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 	return NULL;
@@ -746,6 +766,8 @@ static void intel_pt_free_queue(void *priv)
 	thread__zput(ptq->thread);
 	intel_pt_decoder_free(ptq->decoder);
 	zfree(&ptq->event_buf);
+	zfree(&ptq->last_branch);
+	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 }
@@ -876,6 +898,58 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
 	return 0;
 }
 
+static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
+{
+	struct branch_stack *bs_src = ptq->last_branch_rb;
+	struct branch_stack *bs_dst = ptq->last_branch;
+	size_t nr = 0;
+
+	bs_dst->nr = bs_src->nr;
+
+	if (!bs_src->nr)
+		return;
+
+	nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
+	memcpy(&bs_dst->entries[0],
+	       &bs_src->entries[ptq->last_branch_pos],
+	       sizeof(struct branch_entry) * nr);
+
+	if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
+		memcpy(&bs_dst->entries[nr],
+		       &bs_src->entries[0],
+		       sizeof(struct branch_entry) * ptq->last_branch_pos);
+	}
+}
+
+static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
+{
+	ptq->last_branch_pos = 0;
+	ptq->last_branch_rb->nr = 0;
+}
+
+static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
+{
+	const struct intel_pt_state *state = ptq->state;
+	struct branch_stack *bs = ptq->last_branch_rb;
+	struct branch_entry *be;
+
+	if (!ptq->last_branch_pos)
+		ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
+
+	ptq->last_branch_pos -= 1;
+
+	be              = &bs->entries[ptq->last_branch_pos];
+	be->from        = state->from_ip;
+	be->to          = state->to_ip;
+	be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
+	be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
+	/* No support for mispredict */
+	be->flags.mispred = ptq->pt->mispred_all;
+
+	if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
+		bs->nr += 1;
+}
+
 static int intel_pt_inject_event(union perf_event *event,
 				 struct perf_sample *sample, u64 type,
 				 bool swapped)
@@ -890,6 +964,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
 	struct perf_sample sample = { .ip = 0, };
+	struct dummy_branch_stack {
+		u64			nr;
+		struct branch_entry	entries;
+	} dummy_bs;
+
+	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
+		return 0;
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
@@ -909,8 +990,20 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	sample.flags = ptq->flags;
 	sample.insn_len = ptq->insn_len;
 
-	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
-		return 0;
+	/*
+	 * perf report cannot handle events without a branch stack when using
+	 * SORT_MODE__BRANCH so make a dummy one.
+	 */
+	if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
+		dummy_bs = (struct dummy_branch_stack){
+			.nr = 1,
+			.entries = {
+				.from = sample.ip,
+				.to = sample.addr,
+			},
+		};
+		sample.branch_stack = (struct branch_stack *)&dummy_bs;
+	}
 
 	if (pt->synth_opts.inject) {
 		ret = intel_pt_inject_event(event, &sample,
@@ -961,6 +1054,11 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 		sample.callchain = ptq->chain;
 	}
 
+	if (pt->synth_opts.last_branch) {
+		intel_pt_copy_last_branch_rb(ptq);
+		sample.branch_stack = ptq->last_branch;
+	}
+
 	if (pt->synth_opts.inject) {
 		ret = intel_pt_inject_event(event, &sample,
 					    pt->instructions_sample_type,
@@ -974,6 +1072,9 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 		pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n",
 		       ret);
 
+	if (pt->synth_opts.last_branch)
+		intel_pt_reset_last_branch_rb(ptq);
+
 	return ret;
 }
 
@@ -1008,6 +1109,11 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 		sample.callchain = ptq->chain;
 	}
 
+	if (pt->synth_opts.last_branch) {
+		intel_pt_copy_last_branch_rb(ptq);
+		sample.branch_stack = ptq->last_branch;
+	}
+
 	if (pt->synth_opts.inject) {
 		ret = intel_pt_inject_event(event, &sample,
 					    pt->transactions_sample_type,
@@ -1021,6 +1127,9 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 		pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
 		       ret);
 
+	if (pt->synth_opts.callchain)
+		intel_pt_reset_last_branch_rb(ptq);
+
 	return ret;
 }
 
@@ -1116,6 +1225,9 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
+	if (pt->synth_opts.last_branch)
+		intel_pt_update_last_branch_rb(ptq);
+
 	if (!pt->sync_switch)
 		return 0;
 
@@ -1763,6 +1875,8 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		pt->instructions_sample_period = attr.sample_period;
 		if (pt->synth_opts.callchain)
 			attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+		if (pt->synth_opts.last_branch)
+			attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
 		pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
 			 id, (u64)attr.sample_type);
 		err = intel_pt_synth_event(session, &attr, id);
@@ -1782,6 +1896,8 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		attr.sample_period = 1;
 		if (pt->synth_opts.callchain)
 			attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+		if (pt->synth_opts.last_branch)
+			attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
 		pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
 			 id, (u64)attr.sample_type);
 		err = intel_pt_synth_event(session, &attr, id);
@@ -1808,6 +1924,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		attr.sample_period = 1;
 		attr.sample_type |= PERF_SAMPLE_ADDR;
 		attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN;
+		attr.sample_type &= ~(u64)PERF_SAMPLE_BRANCH_STACK;
 		pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
 			 id, (u64)attr.sample_type);
 		err = intel_pt_synth_event(session, &attr, id);
@@ -1852,6 +1969,16 @@ static bool intel_pt_find_switch(struct perf_evlist *evlist)
 	return false;
 }
 
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt *pt = data;
+
+	if (!strcmp(var, "intel-pt.mispred-all"))
+		pt->mispred_all = perf_config_bool(var, value);
+
+	return 0;
+}
+
 static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
 	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
@@ -1896,6 +2023,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (!pt)
 		return -ENOMEM;
 
+	perf_config(intel_pt_perf_config, pt);
+
 	err = auxtrace_queues__init(&pt->queues);
 	if (err)
 		goto err_free;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 61c2bc20926d..5ffb356cbcc6 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -27,6 +27,8 @@
 extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
+static int get_config_terms(struct list_head *head_config,
+			    struct list_head *head_terms __maybe_unused);
 
 static struct perf_pmu_event_symbol *perf_pmu_events_list;
 /*
@@ -416,7 +418,8 @@ static void tracepoint_error(struct parse_events_error *error, int err,
 
 static int add_tracepoint(struct list_head *list, int *idx,
 			  char *sys_name, char *evt_name,
-			  struct parse_events_error *error __maybe_unused)
+			  struct parse_events_error *error __maybe_unused,
+			  struct list_head *head_config)
 {
 	struct perf_evsel *evsel;
 
@@ -426,13 +429,22 @@ static int add_tracepoint(struct list_head *list, int *idx,
 		return PTR_ERR(evsel);
 	}
 
+	if (head_config) {
+		LIST_HEAD(config_terms);
+
+		if (get_config_terms(head_config, &config_terms))
+			return -ENOMEM;
+		list_splice(&config_terms, &evsel->config_terms);
+	}
+
 	list_add_tail(&evsel->node, list);
 	return 0;
 }
 
 static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 				      char *sys_name, char *evt_name,
-				      struct parse_events_error *error)
+				      struct parse_events_error *error,
+				      struct list_head *head_config)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
@@ -456,7 +468,8 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		if (!strglobmatch(evt_ent->d_name, evt_name))
 			continue;
 
-		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name, error);
+		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name,
+				     error, head_config);
 	}
 
 	closedir(evt_dir);
@@ -465,16 +478,20 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 
 static int add_tracepoint_event(struct list_head *list, int *idx,
 				char *sys_name, char *evt_name,
-				struct parse_events_error *error)
+				struct parse_events_error *error,
+				struct list_head *head_config)
 {
 	return strpbrk(evt_name, "*?") ?
-	       add_tracepoint_multi_event(list, idx, sys_name, evt_name, error) :
-	       add_tracepoint(list, idx, sys_name, evt_name, error);
+	       add_tracepoint_multi_event(list, idx, sys_name, evt_name,
+					  error, head_config) :
+	       add_tracepoint(list, idx, sys_name, evt_name,
+			      error, head_config);
 }
 
 static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 				    char *sys_name, char *evt_name,
-				    struct parse_events_error *error)
+				    struct parse_events_error *error,
+				    struct list_head *head_config)
 {
 	struct dirent *events_ent;
 	DIR *events_dir;
@@ -498,23 +515,13 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 			continue;
 
 		ret = add_tracepoint_event(list, idx, events_ent->d_name,
-					   evt_name, error);
+					   evt_name, error, head_config);
 	}
 
 	closedir(events_dir);
 	return ret;
 }
 
-int parse_events_add_tracepoint(struct list_head *list, int *idx,
-				char *sys, char *event,
-				struct parse_events_error *error)
-{
-	if (strpbrk(sys, "*?"))
-		return add_tracepoint_multi_sys(list, idx, sys, event, error);
-	else
-		return add_tracepoint_event(list, idx, sys, event, error);
-}
-
 static int
 parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
@@ -599,9 +606,13 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-static int config_term(struct perf_event_attr *attr,
-		       struct parse_events_term *term,
-		       struct parse_events_error *err)
+typedef int config_term_func_t(struct perf_event_attr *attr,
+			       struct parse_events_term *term,
+			       struct parse_events_error *err);
+
+static int config_term_common(struct perf_event_attr *attr,
+			      struct parse_events_term *term,
+			      struct parse_events_error *err)
 {
 #define CHECK_TYPE_VAL(type)						   \
 do {									   \
@@ -610,12 +621,6 @@ do {									   \
 } while (0)
 
 	switch (term->type_term) {
-	case PARSE_EVENTS__TERM_TYPE_USER:
-		/*
-		 * Always succeed for sysfs terms, as we dont know
-		 * at this point what type they need to have.
-		 */
-		return 0;
 	case PARSE_EVENTS__TERM_TYPE_CONFIG:
 		CHECK_TYPE_VAL(NUM);
 		attr->config = term->val.num;
@@ -658,6 +663,9 @@ do {									   \
 		CHECK_TYPE_VAL(STR);
 		break;
 	default:
+		err->str = strdup("unknown term");
+		err->idx = term->err_term;
+		err->help = parse_events_formats_error_string(NULL);
 		return -EINVAL;
 	}
 
@@ -665,9 +673,44 @@ do {									   \
 #undef CHECK_TYPE_VAL
 }
 
+static int config_term_pmu(struct perf_event_attr *attr,
+			   struct parse_events_term *term,
+			   struct parse_events_error *err)
+{
+	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER)
+		/*
+		 * Always succeed for sysfs terms, as we dont know
+		 * at this point what type they need to have.
+		 */
+		return 0;
+	else
+		return config_term_common(attr, term, err);
+}
+
+static int config_term_tracepoint(struct perf_event_attr *attr,
+				  struct parse_events_term *term,
+				  struct parse_events_error *err)
+{
+	switch (term->type_term) {
+	case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
+	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
+		return config_term_common(attr, term, err);
+	default:
+		if (err) {
+			err->idx = term->err_term;
+			err->str = strdup("unknown term");
+			err->help = strdup("valid terms: call-graph,stack-size\n");
+		}
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int config_attr(struct perf_event_attr *attr,
 		       struct list_head *head,
-		       struct parse_events_error *err)
+		       struct parse_events_error *err,
+		       config_term_func_t config_term)
 {
 	struct parse_events_term *term;
 
@@ -722,6 +765,27 @@ do {								\
 	return 0;
 }
 
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event,
+				struct parse_events_error *error,
+				struct list_head *head_config)
+{
+	if (head_config) {
+		struct perf_event_attr attr;
+
+		if (config_attr(&attr, head_config, error,
+				config_term_tracepoint))
+			return -EINVAL;
+	}
+
+	if (strpbrk(sys, "*?"))
+		return add_tracepoint_multi_sys(list, idx, sys, event,
+						error, head_config);
+	else
+		return add_tracepoint_event(list, idx, sys, event,
+					    error, head_config);
+}
+
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
@@ -735,7 +799,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 	attr.config = config;
 
 	if (head_config) {
-		if (config_attr(&attr, head_config, data->error))
+		if (config_attr(&attr, head_config, data->error,
+				config_term_common))
 			return -EINVAL;
 
 		if (get_config_terms(head_config, &config_terms))
@@ -795,7 +860,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 	 * Configure hardcoded terms first, no need to check
 	 * return value when called with fail == 0 ;)
 	 */
-	if (config_attr(&attr, head_config, data->error))
+	if (config_attr(&attr, head_config, data->error, config_term_pmu))
 		return -EINVAL;
 
 	if (get_config_terms(head_config, &config_terms))
@@ -1861,3 +1926,29 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 	err->str = strdup(str);
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
+
+/*
+ * Return string contains valid config terms of an event.
+ * @additional_terms: For terms such as PMU sysfs terms.
+ */
+char *parse_events_formats_error_string(char *additional_terms)
+{
+	char *str;
+	static const char *static_terms = "config,config1,config2,name,"
+					  "period,freq,branch_type,time,"
+					  "call-graph,stack-size\n";
+
+	/* valid terms */
+	if (additional_terms) {
+		if (!asprintf(&str, "valid terms: %s,%s",
+			      additional_terms, static_terms))
+			goto fail;
+	} else {
+		if (!asprintf(&str, "valid terms: %s", static_terms))
+			goto fail;
+	}
+	return str;
+
+fail:
+	return NULL;
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index ffee7ece75a6..f13d3ccda444 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -119,7 +119,8 @@ int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				char *sys, char *event,
-				struct parse_events_error *error);
+				struct parse_events_error *error,
+				struct list_head *head_config);
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
@@ -156,5 +157,6 @@ int print_hwcache_events(const char *event_glob, bool name_only);
 extern int is_valid_tracepoint(const char *event_string);
 
 int valid_event_mount(const char *eventfs);
+char *parse_events_formats_error_string(char *additional_terms);
 
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 936d566f48d8..c29832bce496 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -174,7 +174,7 @@ modifier_bp	[rwx]{1,3}
 
 <config>{
 	/*
-	 * Please update formats_error_string any time
+	 * Please update parse_events_formats_error_string any time
 	 * new static term is added.
 	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 8bcc45868457..ae6af269f9c9 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -67,6 +67,7 @@ static inc_group_count(struct list_head *list,
 %type <head> event_legacy_cache
 %type <head> event_legacy_mem
 %type <head> event_legacy_tracepoint
+%type <tracepoint_name> tracepoint_name
 %type <head> event_legacy_numeric
 %type <head> event_legacy_raw
 %type <head> event_def
@@ -84,6 +85,10 @@ static inc_group_count(struct list_head *list,
 	u64 num;
 	struct list_head *head;
 	struct parse_events_term *term;
+	struct tracepoint_name {
+		char *sys;
+		char *event;
+	} tracepoint_name;
 }
 %%
 
@@ -368,38 +373,60 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-PE_NAME '-' PE_NAME ':' PE_NAME
+tracepoint_name
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
-	char sys_name[128];
-	snprintf(&sys_name, 128, "%s-%s", $1, $3);
 
 	ALLOC_LIST(list);
-	if (parse_events_add_tracepoint(list, &data->idx, &sys_name, $5, error)) {
-		if (error)
-			error->idx = @1.first_column;
+	if (error)
+		error->idx = @1.first_column;
+
+	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
+					error, NULL))
 		return -1;
-	}
+
 	$$ = list;
 }
 |
-PE_NAME ':' PE_NAME
+tracepoint_name '/' event_config '/'
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	if (parse_events_add_tracepoint(list, &data->idx, $1, $3, error)) {
-		if (error)
-			error->idx = @1.first_column;
+	if (error)
+		error->idx = @1.first_column;
+
+	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
+					error, $3))
 		return -1;
-	}
+
 	$$ = list;
 }
 
+tracepoint_name:
+PE_NAME '-' PE_NAME ':' PE_NAME
+{
+	char sys_name[128];
+	struct tracepoint_name tracepoint;
+
+	snprintf(&sys_name, 128, "%s-%s", $1, $3);
+	tracepoint.sys = &sys_name;
+	tracepoint.event = $5;
+
+	$$ = tracepoint;
+}
+|
+PE_NAME ':' PE_NAME
+{
+	struct tracepoint_name tracepoint = {$1, $3};
+
+	$$ = tracepoint;
+}
+
 event_legacy_numeric:
 PE_VALUE ':' PE_VALUE
 {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 89c91a1a67e7..ac42c97be9e4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -626,38 +626,26 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	return -1;
 }
 
-static char *formats_error_string(struct list_head *formats)
+static char *pmu_formats_string(struct list_head *formats)
 {
 	struct perf_pmu_format *format;
-	char *err, *str;
-	static const char *static_terms = "config,config1,config2,name,"
-					  "period,freq,branch_type,time,"
-					  "call-graph,stack-size\n";
+	char *str;
+	struct strbuf buf;
 	unsigned i = 0;
 
-	if (!asprintf(&str, "valid terms:"))
+	if (!formats)
 		return NULL;
 
+	strbuf_init(&buf, 0);
 	/* sysfs exported terms */
-	list_for_each_entry(format, formats, list) {
-		char c = i++ ? ',' : ' ';
-
-		err = str;
-		if (!asprintf(&str, "%s%c%s", err, c, format->name))
-			goto fail;
-		free(err);
-	}
+	list_for_each_entry(format, formats, list)
+		strbuf_addf(&buf, i++ ? ",%s" : "%s",
+			    format->name);
 
-	/* static terms */
-	err = str;
-	if (!asprintf(&str, "%s,%s", err, static_terms))
-		goto fail;
+	str = strbuf_detach(&buf, NULL);
+	strbuf_release(&buf);
 
-	free(err);
 	return str;
-fail:
-	free(err);
-	return NULL;
 }
 
 /*
@@ -693,9 +681,12 @@ static int pmu_config_term(struct list_head *formats,
 		if (verbose)
 			printf("Invalid event/parameter '%s'\n", term->config);
 		if (err) {
+			char *pmu_term = pmu_formats_string(formats);
+
 			err->idx  = term->err_term;
 			err->str  = strdup("unknown term");
-			err->help = formats_error_string(formats);
+			err->help = parse_events_formats_error_string(pmu_term);
+			free(pmu_term);
 		}
 		return -EINVAL;
 	}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index aa9e1257c1ee..a8e825fca42a 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -319,7 +319,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 
 	if (thread__resolve_callchain(al->thread, evsel,
 				      sample, NULL, NULL,
-				      PERF_MAX_STACK_DEPTH) != 0) {
+				      scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f5e000030a5e..84a02eae4394 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1101,6 +1101,9 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	case PERF_RECORD_AUX:
+		if (tool->aux == perf_event__process_aux &&
+		    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
+			evlist->stats.total_aux_lost += 1;
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
@@ -1346,6 +1349,13 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 		}
 	}
 
+	if (session->tool->aux == perf_event__process_aux &&
+	    stats->total_aux_lost != 0) {
+		ui__warning("AUX data lost %" PRIu64 " times out of %u!\n\n",
+			    stats->total_aux_lost,
+			    stats->nr_events[PERF_RECORD_AUX]);
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
@@ -1790,7 +1800,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 
 		if (thread__resolve_callchain(al->thread, evsel,
 					      sample, NULL, NULL,
-					      PERF_MAX_STACK_DEPTH) != 0) {
+					      stack_depth) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index da6cc4cc2a4f..b85ee55cca0c 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -78,6 +78,8 @@ struct scripting_ops {
 	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
+extern unsigned int scripting_max_stack;
+
 int script_spec_register(const char *spec, struct scripting_ops *ops);
 
 void setup_perl_scripting(void);