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

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel side changes:

   - A couple of x86/cpu cleanups and changes were grandfathered in due
     to patch dependencies. These clean up the set of CPU model/family
     matching macros with a consistent namespace and C99 initializer
     style.

   - A bunch of updates to various low level PMU drivers:
       * AMD Family 19h L3 uncore PMU
       * Intel Tiger Lake uncore support
       * misc fixes to LBR TOS sampling

   - optprobe fixes

   - perf/cgroup: optimize cgroup event sched-in processing

   - misc cleanups and fixes

  Tooling side changes are to:

   - perf {annotate,expr,record,report,stat,test}

   - perl scripting

   - libapi, libperf and libtraceevent

   - vendor events on Intel and S390, ARM cs-etm

   - Intel PT updates

   - Documentation changes and updates to core facilities

   - misc cleanups, fixes and other enhancements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (89 commits)
  cpufreq/intel_pstate: Fix wrong macro conversion
  x86/cpu: Cleanup the now unused CPU match macros
  hwrng: via_rng: Convert to new X86 CPU match macros
  crypto: Convert to new CPU match macros
  ASoC: Intel: Convert to new X86 CPU match macros
  powercap/intel_rapl: Convert to new X86 CPU match macros
  PCI: intel-mid: Convert to new X86 CPU match macros
  mmc: sdhci-acpi: Convert to new X86 CPU match macros
  intel_idle: Convert to new X86 CPU match macros
  extcon: axp288: Convert to new X86 CPU match macros
  thermal: Convert to new X86 CPU match macros
  hwmon: Convert to new X86 CPU match macros
  platform/x86: Convert to new CPU match macros
  EDAC: Convert to new X86 CPU match macros
  cpufreq: Convert to new X86 CPU match macros
  ACPI: Convert to new X86 CPU match macros
  x86/platform: Convert to new CPU match macros
  x86/kernel: Convert to new CPU match macros
  x86/kvm: Convert to new CPU match macros
  x86/perf/events: Convert to new CPU match macros
  ...

32 files changed, 746 insertions, 400 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 07da6c790b63..c0cf8dff694e 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -121,7 +121,9 @@ perf-y += mem-events.o
 perf-y += vsprintf.o
 perf-y += units.o
 perf-y += time-utils.o
+perf-y += expr-flex.o
 perf-y += expr-bison.o
+perf-y += expr.o
 perf-y += branch.o
 perf-y += mem2node.o
 
@@ -189,9 +191,13 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
+$(OUTPUT)util/expr-flex.c: util/expr.l $(OUTPUT)util/expr-bison.c
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/expr-flex.h $(PARSER_DEBUG_FLEX) util/expr.l
+
 $(OUTPUT)util/expr-bison.c: util/expr.y
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
@@ -203,12 +209,14 @@ $(OUTPUT)util/pmu-bison.c: util/pmu.y
 
 CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
+CFLAGS_expr-flex.o          += -w
 CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 CFLAGS_expr-bison.o         += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
+$(OUTPUT)util/expr.o: $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-bison.c
 
 CFLAGS_bitmap.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
@@ -216,6 +224,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
+CFLAGS_expr.o          += -Wno-redundant-decls
 CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
 
 $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0ea95be84b3b..f1ea0d61eb5b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2611,8 +2611,6 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 
 		if (++al->jump_sources > notes->max_jump_sources)
 			notes->max_jump_sources = al->jump_sources;
-
-		++notes->nr_jumps;
 	}
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 001258601a37..07c775938d46 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -279,7 +279,6 @@ struct annotation {
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
 	int			nr_events;
-	int			nr_jumps;
 	int			max_jump_sources;
 	int			nr_entries;
 	int			nr_asm_entries;
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index fbbb6d640dad..423ec69bda6c 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -65,8 +65,7 @@ struct block_info *block_info__new(void)
 	return bi;
 }
 
-int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
-			struct hist_entry *left, struct hist_entry *right)
+int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	struct block_info *bi_l = left->block_info;
 	struct block_info *bi_r = right->block_info;
@@ -74,30 +73,27 @@ int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 
 	if (!bi_l->sym || !bi_r->sym) {
 		if (!bi_l->sym && !bi_r->sym)
-			return 0;
+			return -1;
 		else if (!bi_l->sym)
 			return -1;
 		else
 			return 1;
 	}
 
-	if (bi_l->sym == bi_r->sym) {
-		if (bi_l->start == bi_r->start) {
-			if (bi_l->end == bi_r->end)
-				return 0;
-			else
-				return (int64_t)(bi_r->end - bi_l->end);
-		} else
-			return (int64_t)(bi_r->start - bi_l->start);
-	} else {
-		cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+	cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+	if (cmp)
 		return cmp;
-	}
 
-	if (bi_l->sym->start != bi_r->sym->start)
-		return (int64_t)(bi_r->sym->start - bi_l->sym->start);
+	if (bi_l->start != bi_r->start)
+		return (int64_t)(bi_r->start - bi_l->start);
 
-	return (int64_t)(bi_r->sym->end - bi_l->sym->end);
+	return (int64_t)(bi_r->end - bi_l->end);
+}
+
+int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+			struct hist_entry *left, struct hist_entry *right)
+{
+	return __block_info__cmp(left, right);
 }
 
 static void init_block_info(struct block_info *bi, struct symbol *sym,
@@ -185,6 +181,17 @@ static int block_column_width(struct perf_hpp_fmt *fmt,
 	return block_fmt->width;
 }
 
+static int color_pct(struct perf_hpp *hpp, int width, double pct)
+{
+#ifdef HAVE_SLANG_SUPPORT
+	if (use_browser) {
+		return __hpp__slsmg_color_printf(hpp, "%*.2f%%",
+						 width - 1, pct);
+	}
+#endif
+	return hpp_color_scnprintf(hpp, "%*.2f%%", width - 1, pct);
+}
+
 static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 					struct perf_hpp *hpp,
 					struct hist_entry *he)
@@ -192,14 +199,11 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 	struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt);
 	struct block_info *bi = he->block_info;
 	double ratio = 0.0;
-	char buf[16];
 
 	if (block_fmt->total_cycles)
 		ratio = (double)bi->cycles / (double)block_fmt->total_cycles;
 
-	sprintf(buf, "%.2f%%", 100.0 * ratio);
-
-	return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+	return color_pct(hpp, block_fmt->width, 100.0 * ratio);
 }
 
 static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt,
@@ -252,16 +256,13 @@ static int block_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 	struct block_info *bi = he->block_info;
 	double ratio = 0.0;
 	u64 avg;
-	char buf[16];
 
 	if (block_fmt->block_cycles && bi->num_aggr) {
 		avg = bi->cycles_aggr / bi->num_aggr;
 		ratio = (double)avg / (double)block_fmt->block_cycles;
 	}
 
-	sprintf(buf, "%.2f%%", 100.0 * ratio);
-
-	return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+	return color_pct(hpp, block_fmt->width, 100.0 * ratio);
 }
 
 static int block_avg_cycles_entry(struct perf_hpp_fmt *fmt,
@@ -349,7 +350,7 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 
 	switch (idx) {
 	case PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT:
-		fmt->entry = block_total_cycles_pct_entry;
+		fmt->color = block_total_cycles_pct_entry;
 		fmt->cmp = block_info__cmp;
 		fmt->sort = block_total_cycles_pct_sort;
 		break;
@@ -357,7 +358,7 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 		fmt->entry = block_cycles_lbr_entry;
 		break;
 	case PERF_HPP_REPORT__BLOCK_CYCLES_PCT:
-		fmt->entry = block_cycles_pct_entry;
+		fmt->color = block_cycles_pct_entry;
 		break;
 	case PERF_HPP_REPORT__BLOCK_AVG_CYCLES:
 		fmt->entry = block_avg_cycles_entry;
@@ -377,33 +378,41 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 }
 
 static void register_block_columns(struct perf_hpp_list *hpp_list,
-				   struct block_fmt *block_fmts)
+				   struct block_fmt *block_fmts,
+				   int *block_hpps, int nr_hpps)
 {
-	for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++)
-		hpp_register(&block_fmts[i], i, hpp_list);
+	for (int i = 0; i < nr_hpps; i++)
+		hpp_register(&block_fmts[i], block_hpps[i], hpp_list);
 }
 
-static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts)
+static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts,
+			    int *block_hpps, int nr_hpps)
 {
 	__hists__init(&bh->block_hists, &bh->block_list);
 	perf_hpp_list__init(&bh->block_list);
 	bh->block_list.nr_header_lines = 1;
 
-	register_block_columns(&bh->block_list, block_fmts);
+	register_block_columns(&bh->block_list, block_fmts,
+			       block_hpps, nr_hpps);
 
-	perf_hpp_list__register_sort_field(&bh->block_list,
-		&block_fmts[PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT].fmt);
+	/* Sort by the first fmt */
+	perf_hpp_list__register_sort_field(&bh->block_list, &block_fmts[0].fmt);
 }
 
-static void process_block_report(struct hists *hists,
-				 struct block_report *block_report,
-				 u64 total_cycles)
+static int process_block_report(struct hists *hists,
+				struct block_report *block_report,
+				u64 total_cycles, int *block_hpps,
+				int nr_hpps)
 {
 	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct block_hist *bh = &block_report->hist;
 	struct hist_entry *he;
 
-	init_block_hist(bh, block_report->fmts);
+	if (nr_hpps > PERF_HPP_REPORT__BLOCK_MAX_INDEX)
+		return -1;
+
+	block_report->nr_fmts = nr_hpps;
+	init_block_hist(bh, block_report->fmts, block_hpps, nr_hpps);
 
 	while (next) {
 		he = rb_entry(next, struct hist_entry, rb_node);
@@ -412,16 +421,19 @@ static void process_block_report(struct hists *hists,
 		next = rb_next(&he->rb_node);
 	}
 
-	for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) {
+	for (int i = 0; i < nr_hpps; i++) {
 		block_report->fmts[i].total_cycles = total_cycles;
 		block_report->fmts[i].block_cycles = block_report->cycles;
 	}
 
 	hists__output_resort(&bh->block_hists, NULL);
+	return 0;
 }
 
 struct block_report *block_info__create_report(struct evlist *evlist,
-					       u64 total_cycles)
+					       u64 total_cycles,
+					       int *block_hpps, int nr_hpps,
+					       int *nr_reps)
 {
 	struct block_report *block_reports;
 	int nr_hists = evlist->core.nr_entries, i = 0;
@@ -434,13 +446,23 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 
-		process_block_report(hists, &block_reports[i], total_cycles);
+		process_block_report(hists, &block_reports[i], total_cycles,
+				     block_hpps, nr_hpps);
 		i++;
 	}
 
+	*nr_reps = nr_hists;
 	return block_reports;
 }
 
+void block_info__free_report(struct block_report *reps, int nr_reps)
+{
+	for (int i = 0; i < nr_reps; i++)
+		hists__delete_entries(&reps[i].hist.block_hists);
+
+	free(reps);
+}
+
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
 			       struct evsel *evsel, struct perf_env *env,
 			       struct annotation_options *annotation_opts)
@@ -452,13 +474,11 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent,
 		symbol_conf.report_individual_block = true;
 		hists__fprintf(&bh->block_hists, true, 0, 0, min_percent,
 			       stdout, true);
-		hists__delete_entries(&bh->block_hists);
 		return 0;
 	case 1:
 		symbol_conf.report_individual_block = true;
 		ret = block_hists_tui_browse(bh, evsel, min_percent,
 					     env, annotation_opts);
-		hists__delete_entries(&bh->block_hists);
 		return ret;
 	default:
 		return -1;
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index bef0d75e9819..42e9dcc4cf0a 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -45,6 +45,7 @@ struct block_report {
 	struct block_hist	hist;
 	u64			cycles;
 	struct block_fmt	fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX];
+	int			nr_fmts;
 };
 
 struct block_hist;
@@ -61,6 +62,8 @@ static inline void __block_info__zput(struct block_info **bi)
 
 #define block_info__zput(bi) __block_info__zput(&bi)
 
+int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right);
+
 int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			struct hist_entry *left, struct hist_entry *right);
 
@@ -68,7 +71,11 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 			    u64 *block_cycles_aggr, u64 total_cycles);
 
 struct block_report *block_info__create_report(struct evlist *evlist,
-					       u64 total_cycles);
+					       u64 total_cycles,
+					       int *block_hpps, int nr_hpps,
+					       int *nr_reps);
+
+void block_info__free_report(struct block_report *reps, int nr_reps);
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
 			       struct evsel *evsel, struct perf_env *env,
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 88e00d268f6f..154a05cd03af 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -12,6 +12,7 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include "event.h"
 
 struct branch_flags {
 	u64 mispred:1;
@@ -39,9 +40,30 @@ struct branch_entry {
 
 struct branch_stack {
 	u64			nr;
+	u64			hw_idx;
 	struct branch_entry	entries[0];
 };
 
+/*
+ * The hw_idx is only available when PERF_SAMPLE_BRANCH_HW_INDEX is applied.
+ * Otherwise, the output format of a sample with branch stack is
+ * struct branch_stack {
+ *	u64			nr;
+ *	struct branch_entry	entries[0];
+ * }
+ * Check whether the hw_idx is available,
+ * and return the corresponding pointer of entries[0].
+ */
+static inline struct branch_entry *perf_sample__branch_entries(struct perf_sample *sample)
+{
+	u64 *entry = (u64 *)sample->branch_stack;
+
+	entry++;
+	if (sample->no_hw_idx)
+		return (struct branch_entry *)entry;
+	return (struct branch_entry *)(++entry);
+}
+
 struct branch_type_stat {
 	bool	branch_to;
 	u64	counts[PERF_BR_MAX];
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 4881d4af3381..5bc9d3b01bd9 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -3,75 +3,16 @@
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
-#include <linux/stringify.h>
 #include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <stdlib.h>
 #include <string.h>
+#include <api/fs/fs.h>
 
 int nr_cgroups;
 
-static int
-cgroupfs_find_mountpoint(char *buf, size_t maxlen)
-{
-	FILE *fp;
-	char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
-	char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
-	char *token, *saved_ptr = NULL;
-
-	fp = fopen("/proc/mounts", "r");
-	if (!fp)
-		return -1;
-
-	/*
-	 * in order to handle split hierarchy, we need to scan /proc/mounts
-	 * and inspect every cgroupfs mount point to find one that has
-	 * perf_event subsystem
-	 */
-	path_v1[0] = '\0';
-	path_v2[0] = '\0';
-
-	while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
-				__stringify(PATH_MAX)"s %*d %*d\n",
-				mountpoint, type, tokens) == 3) {
-
-		if (!path_v1[0] && !strcmp(type, "cgroup")) {
-
-			token = strtok_r(tokens, ",", &saved_ptr);
-
-			while (token != NULL) {
-				if (!strcmp(token, "perf_event")) {
-					strcpy(path_v1, mountpoint);
-					break;
-				}
-				token = strtok_r(NULL, ",", &saved_ptr);
-			}
-		}
-
-		if (!path_v2[0] && !strcmp(type, "cgroup2"))
-			strcpy(path_v2, mountpoint);
-
-		if (path_v1[0] && path_v2[0])
-			break;
-	}
-	fclose(fp);
-
-	if (path_v1[0])
-		path = path_v1;
-	else if (path_v2[0])
-		path = path_v2;
-	else
-		return -1;
-
-	if (strlen(path) < maxlen) {
-		strcpy(buf, path);
-		return 0;
-	}
-	return -1;
-}
-
 static int open_cgroup(const char *name)
 {
 	char path[PATH_MAX + 1];
@@ -79,7 +20,7 @@ static int open_cgroup(const char *name)
 	int fd;
 
 
-	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
+	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event"))
 		return -1;
 
 	scnprintf(path, PATH_MAX, "%s/%s", mnt, name);
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5471045ebf5c..62d2f9b9ce1b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -363,6 +363,23 @@ struct cs_etm_packet_queue
 	return NULL;
 }
 
+static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
+				struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_packet *tmp;
+
+	if (etm->sample_branches || etm->synth_opts.last_branch ||
+	    etm->sample_instructions) {
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
+	}
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -945,7 +962,7 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
 	if (packet->isa == CS_ETM_ISA_T32) {
 		u64 addr = packet->start_addr;
 
-		while (offset > 0) {
+		while (offset) {
 			addr += cs_etm__t32_instr_size(etmq,
 						       trace_chan_id, addr);
 			offset--;
@@ -1134,10 +1151,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 
 	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
 
-	if (etm->synth_opts.last_branch) {
-		cs_etm__copy_last_branch_rb(etmq, tidq);
+	if (etm->synth_opts.last_branch)
 		sample.branch_stack = tidq->last_branch;
-	}
 
 	if (etm->synth_opts.inject) {
 		ret = cs_etm__inject_event(event, &sample,
@@ -1153,9 +1168,6 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 			"CS ETM Trace: failed to deliver instruction event, error %d\n",
 			ret);
 
-	if (etm->synth_opts.last_branch)
-		cs_etm__reset_last_branch_rb(tidq);
-
 	return ret;
 }
 
@@ -1172,6 +1184,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	union perf_event *event = tidq->event_buf;
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 	u64 ip;
@@ -1202,6 +1215,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	if (etm->synth_opts.last_branch) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,
@@ -1340,12 +1354,14 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 			  struct cs_etm_traceid_queue *tidq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 	int ret;
 	u8 trace_chan_id = tidq->trace_chan_id;
-	u64 instrs_executed = tidq->packet->instr_count;
+	u64 instrs_prev;
+
+	/* Get instructions remainder from previous packet */
+	instrs_prev = tidq->period_instructions;
 
-	tidq->period_instructions += instrs_executed;
+	tidq->period_instructions += tidq->packet->instr_count;
 
 	/*
 	 * Record a branch when the last instruction in
@@ -1363,26 +1379,80 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		 * TODO: allow period to be defined in cycles and clock time
 		 */
 
-		/* Get number of instructions executed after the sample point */
-		u64 instrs_over = tidq->period_instructions -
-			etm->instructions_sample_period;
+		/*
+		 * Below diagram demonstrates the instruction samples
+		 * generation flows:
+		 *
+		 *    Instrs     Instrs       Instrs       Instrs
+		 *   Sample(n)  Sample(n+1)  Sample(n+2)  Sample(n+3)
+		 *    |            |            |            |
+		 *    V            V            V            V
+		 *   --------------------------------------------------
+		 *            ^                                  ^
+		 *            |                                  |
+		 *         Period                             Period
+		 *    instructions(Pi)                   instructions(Pi')
+		 *
+		 *            |                                  |
+		 *            \---------------- -----------------/
+		 *                             V
+		 *                 tidq->packet->instr_count
+		 *
+		 * Instrs Sample(n...) are the synthesised samples occurring
+		 * every etm->instructions_sample_period instructions - as
+		 * defined on the perf command line.  Sample(n) is being the
+		 * last sample before the current etm packet, n+1 to n+3
+		 * samples are generated from the current etm packet.
+		 *
+		 * tidq->packet->instr_count represents the number of
+		 * instructions in the current etm packet.
+		 *
+		 * Period instructions (Pi) contains the the number of
+		 * instructions executed after the sample point(n) from the
+		 * previous etm packet.  This will always be less than
+		 * etm->instructions_sample_period.
+		 *
+		 * When generate new samples, it combines with two parts
+		 * instructions, one is the tail of the old packet and another
+		 * is the head of the new coming packet, to generate
+		 * sample(n+1); sample(n+2) and sample(n+3) consume the
+		 * instructions with sample period.  After sample(n+3), the rest
+		 * instructions will be used by later packet and it is assigned
+		 * to tidq->period_instructions for next round calculation.
+		 */
 
 		/*
-		 * Calculate the address of the sampled instruction (-1 as
-		 * sample is reported as though instruction has just been
-		 * executed, but PC has not advanced to next instruction)
+		 * Get the initial offset into the current packet instructions;
+		 * entry conditions ensure that instrs_prev is less than
+		 * etm->instructions_sample_period.
 		 */
-		u64 offset = (instrs_executed - instrs_over - 1);
-		u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
-					      tidq->packet, offset);
+		u64 offset = etm->instructions_sample_period - instrs_prev;
+		u64 addr;
 
-		ret = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr, etm->instructions_sample_period);
-		if (ret)
-			return ret;
+		/* Prepare last branches for instruction sample */
+		if (etm->synth_opts.last_branch)
+			cs_etm__copy_last_branch_rb(etmq, tidq);
 
-		/* Carry remaining instructions into next sample period */
-		tidq->period_instructions = instrs_over;
+		while (tidq->period_instructions >=
+				etm->instructions_sample_period) {
+			/*
+			 * Calculate the address of the sampled instruction (-1
+			 * as sample is reported as though instruction has just
+			 * been executed, but PC has not advanced to next
+			 * instruction)
+			 */
+			addr = cs_etm__instr_addr(etmq, trace_chan_id,
+						  tidq->packet, offset - 1);
+			ret = cs_etm__synth_instruction_sample(
+				etmq, tidq, addr,
+				etm->instructions_sample_period);
+			if (ret)
+				return ret;
+
+			offset += etm->instructions_sample_period;
+			tidq->period_instructions -=
+				etm->instructions_sample_period;
+		}
 	}
 
 	if (etm->sample_branches) {
@@ -1404,15 +1474,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		}
 	}
 
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
 
 	return 0;
 }
@@ -1441,7 +1503,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 {
 	int err = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 
 	/* Handle start tracing packet */
 	if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
@@ -1449,6 +1510,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Generate a last branch event for the branches left in the
 		 * circular buffer at the end of the trace.
@@ -1456,7 +1522,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		 * Use the address of the end of the last reported execution
 		 * range
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
@@ -1476,15 +1542,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 	}
 
 swap_packet:
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
+
+	/* Reset last branches after flush the trace */
+	if (etm->synth_opts.last_branch)
+		cs_etm__reset_last_branch_rb(tidq);
 
 	return err;
 }
@@ -1505,11 +1567,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 	 */
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Use the address of the end of the last reported execution
 		 * range.
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 85223159737c..3cda40a2fafc 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -139,6 +139,7 @@ struct perf_sample {
 	u16 insn_len;
 	u8  cpumode;
 	u16 misc;
+	bool no_hw_idx;		/* No hw_idx collected in branch_stack */
 	char insn[MAX_INSN];
 	void *raw_data;
 	struct ip_callchain *callchain;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c8dc4450884c..816d930d774e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -712,7 +712,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
 				attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
 							PERF_SAMPLE_BRANCH_CALL_STACK |
 							PERF_SAMPLE_BRANCH_NO_CYCLES |
-							PERF_SAMPLE_BRANCH_NO_FLAGS;
+							PERF_SAMPLE_BRANCH_NO_FLAGS |
+							PERF_SAMPLE_BRANCH_HW_INDEX;
 			}
 		} else
 			 pr_warning("Cannot use LBR callstack with branch stack. "
@@ -763,7 +764,8 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
 	if (param->record_mode == CALLCHAIN_LBR) {
 		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
-					      PERF_SAMPLE_BRANCH_CALL_STACK);
+					      PERF_SAMPLE_BRANCH_CALL_STACK |
+					      PERF_SAMPLE_BRANCH_HW_INDEX);
 	}
 	if (param->record_mode == CALLCHAIN_DWARF) {
 		perf_evsel__reset_sample_bit(evsel, REGS_USER);
@@ -1673,6 +1675,8 @@ fallback_missing_features:
 		evsel->core.attr.ksymbol = 0;
 	if (perf_missing_features.bpf)
 		evsel->core.attr.bpf_event = 0;
+	if (perf_missing_features.branch_hw_idx)
+		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_HW_INDEX;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->core.attr.sample_id_all = 0;
@@ -1784,7 +1788,12 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+	if (!perf_missing_features.branch_hw_idx &&
+	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
+		perf_missing_features.branch_hw_idx = true;
+		pr_debug2("switching off branch HW index support\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
 		perf_missing_features.aux_output = true;
 		pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n");
 		goto out_close;
@@ -2169,7 +2178,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 		if (data->branch_stack->nr > max_branch_nr)
 			return -EFAULT;
+
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		if (perf_evsel__has_branch_hw_idx(evsel))
+			sz += sizeof(u64);
+		else
+			data->no_hw_idx = true;
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
 	}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dc14f4a823cd..33804740e2ca 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -119,6 +119,7 @@ struct perf_missing_features {
 	bool ksymbol;
 	bool bpf;
 	bool aux_output;
+	bool branch_hw_idx;
 };
 
 extern struct perf_missing_features perf_missing_features;
@@ -389,6 +390,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
 	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
 
+static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+{
+	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
 static inline bool evsel__has_callchain(const struct evsel *evsel)
 {
 	return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
new file mode 100644
index 000000000000..fd192ddf93c1
--- /dev/null
+++ b/tools/perf/util/expr.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
+#include <assert.h>
+#include "expr.h"
+#include "expr-bison.h"
+#define YY_EXTRA_TYPE int
+#include "expr-flex.h"
+
+#ifdef PARSER_DEBUG
+extern int expr_debug;
+#endif
+
+/* Caller must make sure id is allocated */
+void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+{
+	int idx;
+
+	assert(ctx->num_ids < MAX_PARSE_ID);
+	idx = ctx->num_ids++;
+	ctx->ids[idx].name = name;
+	ctx->ids[idx].val = val;
+}
+
+void expr__ctx_init(struct parse_ctx *ctx)
+{
+	ctx->num_ids = 0;
+}
+
+static int
+__expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
+	      int start)
+{
+	YY_BUFFER_STATE buffer;
+	void *scanner;
+	int ret;
+
+	ret = expr_lex_init_extra(start, &scanner);
+	if (ret)
+		return ret;
+
+	buffer = expr__scan_string(expr, scanner);
+
+#ifdef PARSER_DEBUG
+	expr_debug = 1;
+#endif
+
+	ret = expr_parse(val, ctx, scanner);
+
+	expr__flush_buffer(buffer, scanner);
+	expr__delete_buffer(buffer, scanner);
+	expr_lex_destroy(scanner);
+	return ret;
+}
+
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr)
+{
+	return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
+}
+
+static bool
+already_seen(const char *val, const char *one, const char **other,
+	     int num_other)
+{
+	int i;
+
+	if (one && !strcasecmp(one, val))
+		return true;
+	for (i = 0; i < num_other; i++)
+		if (!strcasecmp(other[i], val))
+			return true;
+	return false;
+}
+
+int expr__find_other(const char *expr, const char *one, const char ***other,
+		     int *num_other)
+{
+	int err, i = 0, j = 0;
+	struct parse_ctx ctx;
+
+	expr__ctx_init(&ctx);
+	err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
+	if (err)
+		return -1;
+
+	*other = malloc((ctx.num_ids + 1) * sizeof(char *));
+	if (!*other)
+		return -ENOMEM;
+
+	for (i = 0, j = 0; i < ctx.num_ids; i++) {
+		const char *str = ctx.ids[i].name;
+
+		if (already_seen(str, one, *other, j))
+			continue;
+
+		str = strdup(str);
+		if (!str)
+			goto out;
+		(*other)[j++] = str;
+	}
+	(*other)[j] = NULL;
+
+out:
+	if (i != ctx.num_ids) {
+		while (--j)
+			free((char *) (*other)[i]);
+		free(*other);
+		err = -1;
+	}
+
+	*num_other = j;
+	return err;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 046160831f90..9377538f4097 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 15
+#define EXPR_MAX_OTHER 20
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct parse_id {
@@ -17,10 +17,8 @@ struct parse_ctx {
 
 void expr__ctx_init(struct parse_ctx *ctx);
 void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
-#ifndef IN_EXPR_Y
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp);
-#endif
-int expr__find_other(const char *p, const char *one, const char ***other,
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
+int expr__find_other(const char *expr, const char *one, const char ***other,
 		int *num_other);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
new file mode 100644
index 000000000000..eaad29243c23
--- /dev/null
+++ b/tools/perf/util/expr.l
@@ -0,0 +1,114 @@
+%option prefix="expr_"
+%option reentrant
+%option bison-bridge
+
+%{
+#include <linux/compiler.h>
+#include "expr.h"
+#include "expr-bison.h"
+
+char *expr_get_text(yyscan_t yyscanner);
+YYSTYPE *expr_get_lval(yyscan_t yyscanner);
+
+static int __value(YYSTYPE *yylval, char *str, int base, int token)
+{
+	u64 num;
+
+	errno = 0;
+	num = strtoull(str, NULL, base);
+	if (errno)
+		return EXPR_ERROR;
+
+	yylval->num = num;
+	return token;
+}
+
+static int value(yyscan_t scanner, int base)
+{
+	YYSTYPE *yylval = expr_get_lval(scanner);
+	char *text = expr_get_text(scanner);
+
+	return __value(yylval, text, base, NUMBER);
+}
+
+/*
+ * Allow @ instead of / to be able to specify pmu/event/ without
+ * conflicts with normal division.
+ */
+static char *normalize(char *str)
+{
+	char *ret = str;
+	char *dst = str;
+
+	while (*str) {
+		if (*str == '@')
+			*dst++ = '/';
+		else if (*str == '\\')
+			*dst++ = *++str;
+		else
+			*dst++ = *str;
+		str++;
+	}
+
+	*dst = 0x0;
+	return ret;
+}
+
+static int str(yyscan_t scanner, int token)
+{
+	YYSTYPE *yylval = expr_get_lval(scanner);
+	char *text = expr_get_text(scanner);
+
+	yylval->str = normalize(strdup(text));
+	if (!yylval->str)
+		return EXPR_ERROR;
+
+	yylval->str = normalize(yylval->str);
+	return token;
+}
+%}
+
+number		[0-9]+
+
+sch		[-,=]
+spec		\\{sch}
+sym		[0-9a-zA-Z_\.:@]+
+symbol		{spec}*{sym}*{spec}*{sym}*
+
+%%
+	{
+		int start_token;
+
+		start_token = expr_get_extra(yyscanner);
+
+		if (start_token) {
+			expr_set_extra(NULL, yyscanner);
+			return start_token;
+		}
+	}
+
+max		{ return MAX; }
+min		{ return MIN; }
+if		{ return IF; }
+else		{ return ELSE; }
+#smt_on		{ return SMT_ON; }
+{number}	{ return value(yyscanner, 10); }
+{symbol}	{ return str(yyscanner, ID); }
+"|"		{ return '|'; }
+"^"		{ return '^'; }
+"&"		{ return '&'; }
+"-"		{ return '-'; }
+"+"		{ return '+'; }
+"*"		{ return '*'; }
+"/"		{ return '/'; }
+"%"		{ return '%'; }
+"("		{ return '('; }
+")"		{ return ')'; }
+","		{ return ','; }
+.		{ }
+%%
+
+int expr_wrap(void *scanner __maybe_unused)
+{
+	return 1;
+}
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 7d226241f1d7..4720cbe79357 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -1,31 +1,32 @@
 /* Simple expression parser */
 %{
+#define YYDEBUG 1
+#include <stdio.h>
 #include "util.h"
 #include "util/debug.h"
 #include <stdlib.h> // strtod()
 #define IN_EXPR_Y 1
 #include "expr.h"
 #include "smt.h"
-#include <assert.h>
 #include <string.h>
 
-#define MAXIDLEN 256
 %}
 
 %define api.pure full
 
 %parse-param { double *final_val }
 %parse-param { struct parse_ctx *ctx }
-%parse-param { const char **pp }
-%lex-param { const char **pp }
+%parse-param {void *scanner}
+%lex-param {void* scanner}
 
 %union {
-	double num;
-	char id[MAXIDLEN+1];
+	double	 num;
+	char	*str;
 }
 
+%token EXPR_PARSE EXPR_OTHER EXPR_ERROR
 %token <num> NUMBER
-%token <id> ID
+%token <str> ID
 %token MIN MAX IF ELSE SMT_ON
 %left MIN MAX IF
 %left '|'
@@ -37,11 +38,9 @@
 %type <num> expr if_expr
 
 %{
-static int expr__lex(YYSTYPE *res, const char **pp);
-
-static void expr__error(double *final_val __maybe_unused,
+static void expr_error(double *final_val __maybe_unused,
 		       struct parse_ctx *ctx __maybe_unused,
-		       const char **pp __maybe_unused,
+		       void *scanner,
 		       const char *s)
 {
 	pr_debug("%s\n", s);
@@ -63,6 +62,27 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
 %}
 %%
 
+start:
+EXPR_PARSE all_expr
+|
+EXPR_OTHER all_other
+
+all_other: all_other other
+|
+
+other: ID
+{
+	if (ctx->num_ids + 1 >= EXPR_MAX_OTHER) {
+		pr_err("failed: way too many variables");
+		YYABORT;
+	}
+
+	ctx->ids[ctx->num_ids++].name = $1;
+}
+|
+MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')'
+
+
 all_expr: if_expr			{ *final_val = $1; }
 	;
 
@@ -93,146 +113,3 @@ expr:	  NUMBER
 	;
 
 %%
-
-static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
-{
-	char *dst = res->id;
-	const char *s = p;
-
-	if (*p == '#')
-		*dst++ = *p++;
-
-	while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') {
-		if (p - s >= MAXIDLEN)
-			return -1;
-		/*
-		 * Allow @ instead of / to be able to specify pmu/event/ without
-		 * conflicts with normal division.
-		 */
-		if (*p == '@')
-			*dst++ = '/';
-		else if (*p == '\\')
-			*dst++ = *++p;
-		else
-			*dst++ = *p;
-		p++;
-	}
-	*dst = 0;
-	*pp = p;
-	dst = res->id;
-	switch (dst[0]) {
-	case 'm':
-		if (!strcmp(dst, "min"))
-			return MIN;
-		if (!strcmp(dst, "max"))
-			return MAX;
-		break;
-	case 'i':
-		if (!strcmp(dst, "if"))
-			return IF;
-		break;
-	case 'e':
-		if (!strcmp(dst, "else"))
-			return ELSE;
-		break;
-	case '#':
-		if (!strcasecmp(dst, "#smt_on"))
-			return SMT_ON;
-		break;
-	}
-	return ID;
-}
-
-static int expr__lex(YYSTYPE *res, const char **pp)
-{
-	int tok;
-	const char *s;
-	const char *p = *pp;
-
-	while (isspace(*p))
-		p++;
-	s = p;
-	switch (*p++) {
-	case '#':
-	case 'a' ... 'z':
-	case 'A' ... 'Z':
-		return expr__symbol(res, p - 1, pp);
-	case '0' ... '9': case '.':
-		res->num = strtod(s, (char **)&p);
-		tok = NUMBER;
-		break;
-	default:
-		tok = *s;
-		break;
-	}
-	*pp = p;
-	return tok;
-}
-
-/* Caller must make sure id is allocated */
-void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
-{
-	int idx;
-	assert(ctx->num_ids < MAX_PARSE_ID);
-	idx = ctx->num_ids++;
-	ctx->ids[idx].name = name;
-	ctx->ids[idx].val = val;
-}
-
-void expr__ctx_init(struct parse_ctx *ctx)
-{
-	ctx->num_ids = 0;
-}
-
-static bool already_seen(const char *val, const char *one, const char **other,
-			 int num_other)
-{
-	int i;
-
-	if (one && !strcasecmp(one, val))
-		return true;
-	for (i = 0; i < num_other; i++)
-		if (!strcasecmp(other[i], val))
-			return true;
-	return false;
-}
-
-int expr__find_other(const char *p, const char *one, const char ***other,
-		     int *num_otherp)
-{
-	const char *orig = p;
-	int err = -1;
-	int num_other;
-
-	*other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *));
-	if (!*other)
-		return -1;
-
-	num_other = 0;
-	for (;;) {
-		YYSTYPE val;
-		int tok = expr__lex(&val, &p);
-		if (tok == 0) {
-			err = 0;
-			break;
-		}
-		if (tok == ID && !already_seen(val.id, one, *other, num_other)) {
-			if (num_other >= EXPR_MAX_OTHER - 1) {
-				pr_debug("Too many extra events in %s\n", orig);
-				break;
-			}
-			(*other)[num_other] = strdup(val.id);
-			if (!(*other)[num_other])
-				return -1;
-			num_other++;
-		}
-	}
-	(*other)[num_other] = NULL;
-	*num_otherp = num_other;
-	if (err) {
-		*num_otherp = 0;
-		free(*other);
-		*other = NULL;
-	}
-	return err;
-}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4246e7447e54..acbd046bf95c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1590,6 +1590,40 @@ static void free_event_desc(struct evsel *events)
 	free(events);
 }
 
+static bool perf_attr_check(struct perf_event_attr *attr)
+{
+	if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3) {
+		pr_warning("Reserved bits are set unexpectedly. "
+			   "Please update perf tool.\n");
+		return false;
+	}
+
+	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) {
+		pr_warning("Unknown sample type (0x%llx) is detected. "
+			   "Please update perf tool.\n",
+			   attr->sample_type);
+		return false;
+	}
+
+	if (attr->read_format & ~(PERF_FORMAT_MAX-1)) {
+		pr_warning("Unknown read format (0x%llx) is detected. "
+			   "Please update perf tool.\n",
+			   attr->read_format);
+		return false;
+	}
+
+	if ((attr->sample_type & PERF_SAMPLE_BRANCH_STACK) &&
+	    (attr->branch_sample_type & ~(PERF_SAMPLE_BRANCH_MAX-1))) {
+		pr_warning("Unknown branch sample type (0x%llx) is detected. "
+			   "Please update perf tool.\n",
+			   attr->branch_sample_type);
+
+		return false;
+	}
+
+	return true;
+}
+
 static struct evsel *read_event_desc(struct feat_fd *ff)
 {
 	struct evsel *evsel, *events = NULL;
@@ -1634,6 +1668,9 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
 
 		memcpy(&evsel->core.attr, buf, msz);
 
+		if (!perf_attr_check(&evsel->core.attr))
+			goto error;
+
 		if (do_read_u32(ff, &nr))
 			goto error;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index ca5a8f4d007e..e74a5acf66d9 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2584,9 +2584,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  u64 *total_cycles)
 {
 	struct branch_info *bi;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 
 	/* If we have branch cycles always annotate them. */
-	if (bs && bs->nr && bs->entries[0].flags.cycles) {
+	if (bs && bs->nr && entries[0].flags.cycles) {
 		int i;
 
 		bi = sample__resolve_bstack(sample, al);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 33cf8928cf05..23c8289c2472 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1295,6 +1295,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	struct perf_sample sample = { .ip = 0, };
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 
@@ -1316,6 +1317,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index b5af680fc667..dbdffb6673fe 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -265,6 +265,8 @@ static int detect_kbuild_dir(char **kbuild_dir)
 			return -ENOMEM;
 		return 0;
 	}
+	pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n",
+		 __func__, autoconf_path);
 	free(autoconf_path);
 	return -ENOENT;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb5c2cd44d30..fd14f1489802 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2081,15 +2081,16 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 {
 	unsigned int i;
 	const struct branch_stack *bs = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
 	if (!bi)
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
-		bi[i].flags = bs->entries[i].flags;
+		ip__resolve_ams(al->thread, &bi[i].to, entries[i].to);
+		ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
+		bi[i].flags = entries[i].flags;
 	}
 	return bi;
 }
@@ -2185,6 +2186,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	/* LBR only affects the user callchain */
 	if (i != chain_nr) {
 		struct branch_stack *lbr_stack = sample->branch_stack;
+		struct branch_entry *entries = perf_sample__branch_entries(sample);
 		int lbr_nr = lbr_stack->nr, j, k;
 		bool branch;
 		struct branch_flags *flags;
@@ -2210,31 +2212,29 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = chain->ips[j];
 				else if (j > i + 1) {
 					k = j - i - 2;
-					ip = lbr_stack->entries[k].from;
+					ip = entries[k].from;
 					branch = true;
-					flags = &lbr_stack->entries[k].flags;
+					flags = &entries[k].flags;
 				} else {
-					ip = lbr_stack->entries[0].to;
+					ip = entries[0].to;
 					branch = true;
-					flags = &lbr_stack->entries[0].flags;
-					branch_from =
-						lbr_stack->entries[0].from;
+					flags = &entries[0].flags;
+					branch_from = entries[0].from;
 				}
 			} else {
 				if (j < lbr_nr) {
 					k = lbr_nr - j - 1;
-					ip = lbr_stack->entries[k].from;
+					ip = entries[k].from;
 					branch = true;
-					flags = &lbr_stack->entries[k].flags;
+					flags = &entries[k].flags;
 				}
 				else if (j > lbr_nr)
 					ip = chain->ips[i + 1 - (j - lbr_nr)];
 				else {
-					ip = lbr_stack->entries[0].to;
+					ip = entries[0].to;
 					branch = true;
-					flags = &lbr_stack->entries[0].flags;
-					branch_from =
-						lbr_stack->entries[0].from;
+					flags = &entries[0].flags;
+					branch_from = entries[0].from;
 				}
 			}
 
@@ -2281,6 +2281,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 					    int max_stack)
 {
 	struct branch_stack *branch = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = 0;
 	u8 cpumode = PERF_RECORD_MISC_USER;
@@ -2328,7 +2329,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 
 		for (i = 0; i < nr; i++) {
 			if (callchain_param.order == ORDER_CALLEE) {
-				be[i] = branch->entries[i];
+				be[i] = entries[i];
 
 				if (chain == NULL)
 					continue;
@@ -2347,7 +2348,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 				    be[i].from >= chain->ips[first_call] - 8)
 					first_call++;
 			} else
-				be[i] = branch->entries[branch->nr - i - 1];
+				be[i] = entries[branch->nr - i - 1];
 		}
 
 		memset(iter, 0, sizeof(struct iterations) * nr);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b342f744b1fc..53d96611e6a6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -44,8 +44,8 @@ static inline int is_no_dso_memory(const char *filename)
 
 static inline int is_android_lib(const char *filename)
 {
-	return !strncmp(filename, "/data/app-lib", 13) ||
-	       !strncmp(filename, "/system/lib", 11);
+	return strstarts(filename, "/data/app-lib/") ||
+	       strstarts(filename, "/system/lib/");
 }
 
 static inline bool replace_android_lib(const char *filename, char *newfilename)
@@ -65,7 +65,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 
 	app_abi_length = strlen(app_abi);
 
-	if (!strncmp(filename, "/data/app-lib", 13)) {
+	if (strstarts(filename, "/data/app-lib/")) {
 		char *apk_path;
 
 		if (!app_abi_length)
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 12)) {
+	if (strstarts(filename, "/system/lib/")) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 02aee946b6c1..c3a8c701609a 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -22,6 +22,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
+#include <api/fs/fs.h>
+#include "util.h"
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 struct evsel *evsel,
@@ -399,13 +401,85 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	strlist__delete(metriclist);
 }
 
+static void metricgroup__add_metric_weak_group(struct strbuf *events,
+					       const char **ids,
+					       int idnum)
+{
+	bool no_group = false;
+	int i;
+
+	for (i = 0; i < idnum; i++) {
+		pr_debug("found event %s\n", ids[i]);
+		/*
+		 * Duration time maps to a software event and can make
+		 * groups not count. Always use it outside a
+		 * group.
+		 */
+		if (!strcmp(ids[i], "duration_time")) {
+			if (i > 0)
+				strbuf_addf(events, "}:W,");
+			strbuf_addf(events, "duration_time");
+			no_group = true;
+			continue;
+		}
+		strbuf_addf(events, "%s%s",
+			i == 0 || no_group ? "{" : ",",
+			ids[i]);
+		no_group = false;
+	}
+	if (!no_group)
+		strbuf_addf(events, "}:W");
+}
+
+static void metricgroup__add_metric_non_group(struct strbuf *events,
+					      const char **ids,
+					      int idnum)
+{
+	int i;
+
+	for (i = 0; i < idnum; i++)
+		strbuf_addf(events, ",%s", ids[i]);
+}
+
+static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
+{
+	static bool violate_nmi_constraint;
+
+	if (!foot) {
+		pr_warning("Splitting metric group %s into standalone metrics.\n", name);
+		violate_nmi_constraint = true;
+		return;
+	}
+
+	if (!violate_nmi_constraint)
+		return;
+
+	pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n"
+		   "    echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+		   "    perf stat ...\n"
+		   "    echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+static bool metricgroup__has_constraint(struct pmu_event *pe)
+{
+	if (!pe->metric_constraint)
+		return false;
+
+	if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") &&
+	    sysctl__nmi_watchdog_enabled()) {
+		metricgroup___watchdog_constraint_hint(pe->metric_name, false);
+		return true;
+	}
+
+	return false;
+}
+
 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(NULL);
 	struct pmu_event *pe;
-	int ret = -EINVAL;
-	int i, j;
+	int i, ret = -EINVAL;
 
 	if (!map)
 		return 0;
@@ -422,7 +496,6 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			const char **ids;
 			int idnum;
 			struct egroup *eg;
-			bool no_group = false;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
@@ -431,27 +504,11 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				continue;
 			if (events->len > 0)
 				strbuf_addf(events, ",");
-			for (j = 0; j < idnum; j++) {
-				pr_debug("found event %s\n", ids[j]);
-				/*
-				 * Duration time maps to a software event and can make
-				 * groups not count. Always use it outside a
-				 * group.
-				 */
-				if (!strcmp(ids[j], "duration_time")) {
-					if (j > 0)
-						strbuf_addf(events, "}:W,");
-					strbuf_addf(events, "duration_time");
-					no_group = true;
-					continue;
-				}
-				strbuf_addf(events, "%s%s",
-					j == 0 || no_group ? "{" : ",",
-					ids[j]);
-				no_group = false;
-			}
-			if (!no_group)
-				strbuf_addf(events, "}:W");
+
+			if (metricgroup__has_constraint(pe))
+				metricgroup__add_metric_non_group(events, ids, idnum);
+			else
+				metricgroup__add_metric_weak_group(events, ids, idnum);
 
 			eg = malloc(sizeof(struct egroup));
 			if (!eg) {
@@ -493,6 +550,10 @@ static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
 		}
 	}
 	free(nlist);
+
+	if (!ret)
+		metricgroup___watchdog_constraint_hint(NULL, true);
+
 	return ret;
 }
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3b664fa673a6..ab7108d22428 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -98,20 +98,29 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
 {
 	void *data;
 	size_t mmap_len;
-	unsigned long node_mask;
+	unsigned long *node_mask;
+	unsigned long node_index;
+	int err = 0;
 
 	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
 		data = map->aio.data[idx];
 		mmap_len = mmap__mmap_len(map);
-		node_mask = 1UL << cpu__get_node(cpu);
-		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
-			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
-				data, data + mmap_len, cpu__get_node(cpu));
+		node_index = cpu__get_node(cpu);
+		node_mask = bitmap_alloc(node_index + 1);
+		if (!node_mask) {
+			pr_err("Failed to allocate node mask for mbind: error %m\n");
 			return -1;
 		}
+		set_bit(node_index, node_mask);
+		if (mbind(data, mmap_len, MPOL_BIND, node_mask, node_index + 1 + 1, 0)) {
+			pr_err("Failed to bind [%p-%p] AIO buffer to node %lu: error %m\n",
+				data, data + mmap_len, node_index);
+			err = -1;
+		}
+		bitmap_free(node_mask);
 	}
 
-	return 0;
+	return err;
 }
 #else /* !HAVE_LIBNUMA_SUPPORT */
 static int perf_mmap__aio_alloc(struct mmap *map, int idx)
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 651203126c71..355d3458d4e6 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -50,6 +50,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
 		bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+		bit_name(HW_INDEX),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 80ca5d0ab7fe..8c1b27cd8b99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -464,6 +464,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 					struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 
@@ -484,28 +485,28 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 			Py_FatalError("couldn't create Python dictionary");
 
 		pydict_set_item_string_decref(pyelem, "from",
-		    PyLong_FromUnsignedLongLong(br->entries[i].from));
+		    PyLong_FromUnsignedLongLong(entries[i].from));
 		pydict_set_item_string_decref(pyelem, "to",
-		    PyLong_FromUnsignedLongLong(br->entries[i].to));
+		    PyLong_FromUnsignedLongLong(entries[i].to));
 		pydict_set_item_string_decref(pyelem, "mispred",
-		    PyBool_FromLong(br->entries[i].flags.mispred));
+		    PyBool_FromLong(entries[i].flags.mispred));
 		pydict_set_item_string_decref(pyelem, "predicted",
-		    PyBool_FromLong(br->entries[i].flags.predicted));
+		    PyBool_FromLong(entries[i].flags.predicted));
 		pydict_set_item_string_decref(pyelem, "in_tx",
-		    PyBool_FromLong(br->entries[i].flags.in_tx));
+		    PyBool_FromLong(entries[i].flags.in_tx));
 		pydict_set_item_string_decref(pyelem, "abort",
-		    PyBool_FromLong(br->entries[i].flags.abort));
+		    PyBool_FromLong(entries[i].flags.abort));
 		pydict_set_item_string_decref(pyelem, "cycles",
-		    PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
+		    PyLong_FromUnsignedLongLong(entries[i].flags.cycles));
 
 		thread__find_map_fb(thread, sample->cpumode,
-				    br->entries[i].from, &al);
+				    entries[i].from, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "from_dsoname",
 					      _PyUnicode_FromString(dsoname));
 
 		thread__find_map_fb(thread, sample->cpumode,
-				    br->entries[i].to, &al);
+				    entries[i].to, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "to_dsoname",
 					      _PyUnicode_FromString(dsoname));
@@ -561,6 +562,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 					   struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 	char bf[512];
@@ -581,22 +583,22 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 			Py_FatalError("couldn't create Python dictionary");
 
 		thread__find_symbol_fb(thread, sample->cpumode,
-				       br->entries[i].from, &al);
+				       entries[i].from, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "from",
 					      _PyUnicode_FromString(bf));
 
 		thread__find_symbol_fb(thread, sample->cpumode,
-				       br->entries[i].to, &al);
+				       entries[i].to, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "to",
 					      _PyUnicode_FromString(bf));
 
-		get_br_mspred(&br->entries[i].flags, bf, sizeof(bf));
+		get_br_mspred(&entries[i].flags, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "pred",
 					      _PyUnicode_FromString(bf));
 
-		if (br->entries[i].flags.in_tx) {
+		if (entries[i].flags.in_tx) {
 			pydict_set_item_string_decref(pyelem, "in_tx",
 					      _PyUnicode_FromString("X"));
 		} else {
@@ -604,7 +606,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 					      _PyUnicode_FromString("-"));
 		}
 
-		if (br->entries[i].flags.abort) {
+		if (entries[i].flags.abort) {
 			pydict_set_item_string_decref(pyelem, "abort",
 					      _PyUnicode_FromString("A"));
 		} else {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d0d7d25b23e3..055b00abd56d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1007,6 +1007,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
 {
 	struct ip_callchain *callchain = sample->callchain;
 	struct branch_stack *lbr_stack = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	u64 kernel_callchain_nr = callchain->nr;
 	unsigned int i;
 
@@ -1043,10 +1044,10 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
 			       i, callchain->ips[i]);
 
 		printf("..... %2d: %016" PRIx64 "\n",
-		       (int)(kernel_callchain_nr), lbr_stack->entries[0].to);
+		       (int)(kernel_callchain_nr), entries[0].to);
 		for (i = 0; i < lbr_stack->nr; i++)
 			printf("..... %2d: %016" PRIx64 "\n",
-			       (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from);
+			       (int)(i + kernel_callchain_nr + 1), entries[i].from);
 	}
 }
 
@@ -1068,6 +1069,7 @@ static void callchain__printf(struct evsel *evsel,
 
 static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 {
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
 	printf("%s: nr:%" PRIu64 "\n",
@@ -1075,7 +1077,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 		sample->branch_stack->nr);
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
-		struct branch_entry *e = &sample->branch_stack->entries[i];
+		struct branch_entry *e = &entries[i];
 
 		if (!callstack) {
 			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bc31fccc0057..76c6052b12e2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include "cgroup.h"
 #include <api/fs/fs.h>
+#include "util.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -110,7 +111,7 @@ static void aggr_printout(struct perf_stat_config *config,
 			config->csv_sep);
 			break;
 	case AGGR_NONE:
-		if (evsel->percore) {
+		if (evsel->percore && !config->percore_show_thread) {
 			fprintf(config->output, "S%d-D%d-C%*d%s",
 				cpu_map__id_to_socket(id),
 				cpu_map__id_to_die(id),
@@ -628,7 +629,7 @@ static void aggr_cb(struct perf_stat_config *config,
 static void print_counter_aggrdata(struct perf_stat_config *config,
 				   struct evsel *counter, int s,
 				   char *prefix, bool metric_only,
-				   bool *first)
+				   bool *first, int cpu)
 {
 	struct aggr_data ad;
 	FILE *output = config->output;
@@ -654,7 +655,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = val * counter->scale;
-	printout(config, id, nr, counter, uval, prefix,
+	printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix,
 		 run, ena, 1.0, &rt_stat);
 	if (!metric_only)
 		fputc('\n', output);
@@ -687,7 +688,7 @@ static void print_aggr(struct perf_stat_config *config,
 		evlist__for_each_entry(evlist, counter) {
 			print_counter_aggrdata(config, counter, s,
 					       prefix, metric_only,
-					       &first);
+					       &first, -1);
 		}
 		if (metric_only)
 			fputc('\n', output);
@@ -1097,7 +1098,6 @@ static void print_footer(struct perf_stat_config *config)
 {
 	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = config->output;
-	int n;
 
 	if (!config->null_run)
 		fprintf(output, "\n");
@@ -1131,9 +1131,7 @@ static void print_footer(struct perf_stat_config *config)
 	}
 	fprintf(output, "\n\n");
 
-	if (config->print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
+	if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
@@ -1146,6 +1144,26 @@ static void print_footer(struct perf_stat_config *config)
 			"the same PMU. Try reorganizing the group.\n");
 }
 
+static void print_percore_thread(struct perf_stat_config *config,
+				 struct evsel *counter, char *prefix)
+{
+	int s, s2, id;
+	bool first = true;
+
+	for (int i = 0; i < perf_evsel__nr_cpus(counter); i++) {
+		s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+		for (s = 0; s < config->aggr_map->nr; s++) {
+			id = config->aggr_map->map[s];
+			if (s2 == id)
+				break;
+		}
+
+		print_counter_aggrdata(config, counter, s,
+				       prefix, false,
+				       &first, i);
+	}
+}
+
 static void print_percore(struct perf_stat_config *config,
 			  struct evsel *counter, char *prefix)
 {
@@ -1157,13 +1175,16 @@ static void print_percore(struct perf_stat_config *config,
 	if (!(config->aggr_map || config->aggr_get_id))
 		return;
 
+	if (config->percore_show_thread)
+		return print_percore_thread(config, counter, prefix);
+
 	for (s = 0; s < config->aggr_map->nr; s++) {
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
 		print_counter_aggrdata(config, counter, s,
 				       prefix, metric_only,
-				       &first);
+				       &first, -1);
 	}
 
 	if (metric_only)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 90d23cc3c8d4..0fd713d3674f 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -777,9 +777,7 @@ static void generic_metric(struct perf_stat_config *config,
 	}
 
 	if (!metric_events[i]) {
-		const char *p = metric_expr;
-
-		if (expr__parse(&ratio, &pctx, &p) == 0) {
+		if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
 			char *unit;
 			char metric_bf[64];
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index fb990efa54a8..b4fdfaa7f2c0 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -109,6 +109,7 @@ struct perf_stat_config {
 	bool			 walltime_run_table;
 	bool			 all_kernel;
 	bool			 all_user;
+	bool			 percore_show_thread;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index c423298fe62d..3f28af39f9c6 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -345,6 +345,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			continue;
 
 		event->mmap2.ino = (u64)ino;
+		event->mmap2.ino_generation = 0;
 
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
@@ -1183,7 +1184,8 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
+		/* nr, hw_idx */
+		sz += 2 * sizeof(u64);
 		result += sz;
 	}
 
@@ -1344,7 +1346,8 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
+		/* nr, hw_idx */
+		sz += 2 * sizeof(u64);
 		memcpy(array, sample->branch_stack, sz);
 		array = (void *)array + sz;
 	}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 969ae560dad9..d707c9624dd9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -55,6 +55,24 @@ int sysctl__max_stack(void)
 	return sysctl_perf_event_max_stack;
 }
 
+bool sysctl__nmi_watchdog_enabled(void)
+{
+	static bool cached;
+	static bool nmi_watchdog;
+	int value;
+
+	if (cached)
+		return nmi_watchdog;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &value) < 0)
+		return false;
+
+	nmi_watchdog = (value > 0) ? true : false;
+	cached = true;
+
+	return nmi_watchdog;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9969b8b46f7c..f486fdd3a538 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -29,6 +29,8 @@ size_t hex_width(u64 v);
 
 int sysctl__max_stack(void);
 
+bool sysctl__nmi_watchdog_enabled(void);
+
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
 #define KVER_VERSION(x)		(((x) >> 16) & 0xff)