Merge tag 'perf-core-for-mingo-5.7-20200310' 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:

perf stat:

Jin Yao:

- Show percore counts in per CPU output.

perf report:

Jin Yao:

- Allow selecting which block info columns to report and its order.

- Support color ops to print block percents in color.

- Fix wrong block address comparison in block_info__cmp().

perf annotate:

Ravi Bangoria:

- Get rid of annotation->nr_jumps, unused.

expr:

Jiri Olsa:

- Move expr lexer to flex.

llvm:

Arnaldo Carvalho de Melo:

- Add debug hint message about missing kernel-devel package.

core:

Kan Liang:

- Initial patches to support the recently added PERF_SAMPLE_BRANCH_HW_INDEX
kernel feature.

- Add check for unexpected use of reserved membrs in event attr, so that in
the future older perf tools will complain instead of silently try to process
unknown features.

libapi:

Namhyung Kim:

- Adopt cgroupsfs_find_mountpoint() from tools/perf/util/.

libperf:

Michael Petlan:

- Add counting example.

libtraceevent:

Steven Rostedt (VMware):

- Remove extra '\n' in print_event_time().

Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

tools/include/uapi/linux/perf_event.h

···
 
 	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
 
+	PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT	= 17, /* save low level index of raw branch records */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
···
 
 	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
 		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
+	PERF_SAMPLE_BRANCH_HW_INDEX	= 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
 
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
···
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 *
 	 *	{ u64                   nr;
-	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+	 *        { u64 from, to, flags } lbr[nr];
+	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
 	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER

tools/lib/api/fs/Build

···
 libapi-y += fs.o
 libapi-y += tracing_path.o
+libapi-y += cgroup.o

tools/lib/api/fs/cgroup.c

···
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "fs.h"
+
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
+{
+	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 (subsys && !strcmp(token, subsys)) {
+					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;
+}

tools/lib/api/fs/fs.h

···
 #undef FS
 
 
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys);
+
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
 int filename__read_xll(const char *filename, unsigned long long *value);

tools/lib/perf/Documentation/examples/counting.c

···
+#include <linux/perf_event.h>
+#include <perf/evlist.h>
+#include <perf/evsel.h>
+#include <perf/cpumap.h>
+#include <perf/threadmap.h>
+#include <perf/mmap.h>
+#include <perf/core.h>
+#include <perf/event.h>
+#include <stdio.h>
+#include <unistd.h>
+
+static int libperf_print(enum libperf_print_level level,
+                         const char *fmt, va_list ap)
+{
+	return vfprintf(stderr, fmt, ap);
+}
+
+int main(int argc, char **argv)
+{
+	int count = 100000, err = 0;
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct perf_thread_map *threads;
+	struct perf_counts_values counts;
+
+	struct perf_event_attr attr1 = {
+		.type        = PERF_TYPE_SOFTWARE,
+		.config      = PERF_COUNT_SW_CPU_CLOCK,
+		.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING,
+		.disabled    = 1,
+	};
+	struct perf_event_attr attr2 = {
+		.type        = PERF_TYPE_SOFTWARE,
+		.config      = PERF_COUNT_SW_TASK_CLOCK,
+		.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING,
+		.disabled    = 1,
+	};
+
+	libperf_init(libperf_print);
+	threads = perf_thread_map__new_dummy();
+	if (!threads) {
+		fprintf(stderr, "failed to create threads\n");
+		return -1;
+	}
+	perf_thread_map__set_pid(threads, 0, 0);
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		fprintf(stderr, "failed to create evlist\n");
+		goto out_threads;
+	}
+	evsel = perf_evsel__new(&attr1);
+	if (!evsel) {
+		fprintf(stderr, "failed to create evsel1\n");
+		goto out_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+	evsel = perf_evsel__new(&attr2);
+	if (!evsel) {
+		fprintf(stderr, "failed to create evsel2\n");
+		goto out_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+	perf_evlist__set_maps(evlist, NULL, threads);
+	err = perf_evlist__open(evlist);
+	if (err) {
+		fprintf(stderr, "failed to open evsel\n");
+		goto out_evlist;
+	}
+	perf_evlist__enable(evlist);
+	while (count--);
+	perf_evlist__disable(evlist);
+	perf_evlist__for_each_evsel(evlist, evsel) {
+		perf_evsel__read(evsel, 0, 0, &counts);
+		fprintf(stdout, "count %llu, enabled %llu, run %llu\n",
+				counts.val, counts.ena, counts.run);
+	}
+	perf_evlist__close(evlist);
+out_evlist:
+	perf_evlist__delete(evlist);
+out_threads:
+	perf_thread_map__put(threads);
+	return err;
+}

tools/lib/traceevent/event-parse.c

···
 	if (p10 > 1 && p10 < time)
 		trace_seq_printf(s, "%5llu.%0*llu", time / p10, prec, time % p10);
 	else
-		trace_seq_printf(s, "%12llu\n", time);
+		trace_seq_printf(s, "%12llu", time);
 }
 
 struct print_event_type {

tools/perf/Documentation/perf-stat.txt

···
 --all-user::
 Configure all used events to run in user space.
 
+--percore-show-thread::
+The event modifier "percore" has supported to sum up the event counts
+for all hardware threads in a core and show the counts per core.
+
+This option with event modifier "percore" enabled also sums up the event
+counts for all hardware threads in a core but show the sum counts per
+hardware thread. This is essentially a replacement for the any bit and
+convenient for post processing.
+
 EXAMPLES
 --------
 

tools/perf/builtin-diff.c

···
 	bh->valid = true;
 }
 
-static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
-{
-	struct block_info *bi_a = a->block_info;
-	struct block_info *bi_b = b->block_info;
-	int cmp;
-
-	if (!bi_a->sym || !bi_b->sym)
-		return -1;
-
-	cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
-
-	if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
-		return 0;
-
-	return -1;
-}
-
 static struct hist_entry *get_block_pair(struct hist_entry *he,
 					 struct hists *hists_pair)
 {
 	struct rb_root_cached *root = hists_pair->entries_in;
 	struct rb_node *next = rb_first_cached(root);
-	int cmp;
+	int64_t cmp;
 
 	while (next != NULL) {
 		struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
···
 
 		next = rb_next(&he_pair->rb_node_in);
 
-		cmp = block_pair_cmp(he_pair, he);
+		cmp = __block_info__cmp(he_pair, he);
 		if (!cmp)
 			return he_pair;
 	}
···
 	end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
 				he->ms.sym);
 
-	if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+	if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+	    (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
 		scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
 			  start_line, end_line, block_he->diff.cycles);
 	} else {

tools/perf/builtin-report.c

···
 	bool			symbol_ipc;
 	bool			total_cycles_mode;
 	struct block_report	*block_reports;
+	int			nr_block_reports;
 };
 
 static int report__config(const char *var, const char *value, void *cb)
···
 	report__output_resort(rep);
 
 	if (rep->total_cycles_mode) {
+		int block_hpps[6] = {
+			PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT,
+			PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
+			PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
+			PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
+			PERF_HPP_REPORT__BLOCK_RANGE,
+			PERF_HPP_REPORT__BLOCK_DSO,
+		};
+
 		rep->block_reports = block_info__create_report(session->evlist,
-							       rep->total_cycles);
+							       rep->total_cycles,
+							       block_hpps, 6,
+							       &rep->nr_block_reports);
 		if (!rep->block_reports)
 			return -1;
 	}
···
 		zfree(&report.ptime_range);
 	}
 
-	if (report.block_reports)
-		zfree(&report.block_reports);
+	if (report.block_reports) {
+		block_info__free_report(report.block_reports,
+					report.nr_block_reports);
+		report.block_reports = NULL;
+	}
 
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);

tools/perf/builtin-script.c

···
 					struct perf_event_attr *attr, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct addr_location alf, alt;
 	u64 i, from, to;
 	int printed = 0;
···
 		return 0;
 
 	for (i = 0; i < br->nr; i++) {
-		from = br->entries[i].from;
-		to   = br->entries[i].to;
+		from = entries[i].from;
+		to   = entries[i].to;
 
 		if (PRINT_FIELD(DSO)) {
 			memset(&alf, 0, sizeof(alf));
···
 		}
 
 		printed += fprintf(fp, "/%c/%c/%c/%d ",
-			mispred_str( br->entries + i),
-			br->entries[i].flags.in_tx? 'X' : '-',
-			br->entries[i].flags.abort? 'A' : '-',
-			br->entries[i].flags.cycles);
+			mispred_str(entries + i),
+			entries[i].flags.in_tx ? 'X' : '-',
+			entries[i].flags.abort ? 'A' : '-',
+			entries[i].flags.cycles);
 	}
 
 	return printed;
···
 					   struct perf_event_attr *attr, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct addr_location alf, alt;
 	u64 i, from, to;
 	int printed = 0;
···
 
 		memset(&alf, 0, sizeof(alf));
 		memset(&alt, 0, sizeof(alt));
-		from = br->entries[i].from;
-		to   = br->entries[i].to;
+		from = entries[i].from;
+		to   = entries[i].to;
 
 		thread__find_symbol_fb(thread, sample->cpumode, from, &alf);
 		thread__find_symbol_fb(thread, sample->cpumode, to, &alt);
···
 			printed += fprintf(fp, ")");
 		}
 		printed += fprintf(fp, "/%c/%c/%c/%d ",
-			mispred_str( br->entries + i),
-			br->entries[i].flags.in_tx? 'X' : '-',
-			br->entries[i].flags.abort? 'A' : '-',
-			br->entries[i].flags.cycles);
+			mispred_str(entries + i),
+			entries[i].flags.in_tx ? 'X' : '-',
+			entries[i].flags.abort ? 'A' : '-',
+			entries[i].flags.cycles);
 	}
 
 	return printed;
···
 					   struct perf_event_attr *attr, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct addr_location alf, alt;
 	u64 i, from, to;
 	int printed = 0;
···
 
 		memset(&alf, 0, sizeof(alf));
 		memset(&alt, 0, sizeof(alt));
-		from = br->entries[i].from;
-		to   = br->entries[i].to;
+		from = entries[i].from;
+		to   = entries[i].to;
 
 		if (thread__find_map_fb(thread, sample->cpumode, from, &alf) &&
 		    !alf.map->dso->adjust_symbols)
···
 			printed += fprintf(fp, ")");
 		}
 		printed += fprintf(fp, "/%c/%c/%c/%d ",
-			mispred_str(br->entries + i),
-			br->entries[i].flags.in_tx ? 'X' : '-',
-			br->entries[i].flags.abort ? 'A' : '-',
-			br->entries[i].flags.cycles);
+			mispred_str(entries + i),
+			entries[i].flags.in_tx ? 'X' : '-',
+			entries[i].flags.abort ? 'A' : '-',
+			entries[i].flags.cycles);
 	}
 
 	return printed;
···
 					    struct machine *machine, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	u64 start, end;
 	int i, insn, len, nr, ilen, printed = 0;
 	struct perf_insn x;
···
 	printed += fprintf(fp, "%c", '\n');
 
 	/* Handle first from jump, of which we don't know the entry. */
-	len = grab_bb(buffer, br->entries[nr-1].from,
-			br->entries[nr-1].from,
+	len = grab_bb(buffer, entries[nr-1].from,
+			entries[nr-1].from,
 			machine, thread, &x.is64bit, &x.cpumode, false);
 	if (len > 0) {
-		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+		printed += ip__fprintf_sym(entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
-		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+		printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
 					    &x, buffer, len, 0, fp, &total_cycles);
 		if (PRINT_FIELD(SRCCODE))
-			printed += print_srccode(thread, x.cpumode, br->entries[nr - 1].from);
+			printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
 	}
 
 	/* Print all blocks */
 	for (i = nr - 2; i >= 0; i--) {
-		if (br->entries[i].from || br->entries[i].to)
+		if (entries[i].from || entries[i].to)
 			pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
-				 br->entries[i].from,
-				 br->entries[i].to);
-		start = br->entries[i + 1].to;
-		end   = br->entries[i].from;
+				 entries[i].from,
+				 entries[i].to);
+		start = entries[i + 1].to;
+		end   = entries[i].from;
 
 		len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
 		/* Patch up missing kernel transfers due to ring filters */
 		if (len == -ENXIO && i > 0) {
-			end = br->entries[--i].from;
+			end = entries[--i].from;
 			pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
 			len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
 		}
···
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,
+				printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
 							    &total_cycles);
 				if (PRINT_FIELD(SRCCODE))
 					printed += print_srccode(thread, x.cpumode, ip);
···
 	 * Hit the branch? In this case we are already done, and the target
 	 * has not been executed yet.
 	 */
-	if (br->entries[0].from == sample->ip)
+	if (entries[0].from == sample->ip)
 		goto out;
-	if (br->entries[0].flags.abort)
+	if (entries[0].flags.abort)
 		goto out;
 
 	/*
···
 	 * between final branch and sample. When this happens just
 	 * continue walking after the last TO until we hit a branch.
 	 */
-	start = br->entries[0].to;
+	start = entries[0].to;
 	end = sample->ip;
 	if (end < start) {
 		/* Missing jump. Scan 128 bytes for the next branch */

tools/perf/builtin-stat.c

···
 	OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user,
 			 "Configure all used events to run in user space.",
 			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN(0, "percore-show-thread", &stat_config.percore_show_thread,
+		    "Use with 'percore' event qualifier to show the event "
+		    "counts of one hardware thread by sum up total hardware "
+		    "threads of same physical core"),
 	OPT_END()
 };
 

tools/perf/tests/expr.c

···
 {
 	double val;
 
-	if (expr__parse(&val, ctx, &e))
+	if (expr__parse(&val, ctx, e))
 		TEST_ASSERT_VAL("parse test failed", 0);
 	TEST_ASSERT_VAL("unexpected value", val == val2);
 	return 0;
···
 		return ret;
 
 	p = "FOO/0";
-	ret = expr__parse(&val, &ctx, &p);
-	TEST_ASSERT_VAL("division by zero", ret == 1);
+	ret = expr__parse(&val, &ctx, p);
+	TEST_ASSERT_VAL("division by zero", ret == -1);
 
 	p = "BAR/";
-	ret = expr__parse(&val, &ctx, &p);
-	TEST_ASSERT_VAL("missing operand", ret == 1);
+	ret = expr__parse(&val, &ctx, p);
+	TEST_ASSERT_VAL("missing operand", ret == -1);
 
 	TEST_ASSERT_VAL("find other",
 			expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);

tools/perf/tests/sample-parsing.c

···
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		COMP(branch_stack->nr);
+		COMP(branch_stack->hw_idx);
 		for (i = 0; i < s1->branch_stack->nr; i++)
 			MCOMP(branch_stack->entries[i]);
 	}
···
 		u64 data[64];
 	} branch_stack = {
 		/* 1 branch_entry */
-		.data = {1, 211, 212, 213},
+		.data = {1, -1ULL, 211, 212, 213},
 	};
 	u64 regs[64];
 	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
···
 		.transaction	= 112,
 		.raw_data	= (void *)raw_data,
 		.callchain	= &callchain.callchain,
+		.no_hw_idx      = false,
 		.branch_stack	= &branch_stack.branch_stack,
 		.user_regs	= {
 			.abi	= PERF_SAMPLE_REGS_ABI_64,
···
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR)
 		evsel.core.attr.sample_regs_intr = sample_regs;
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		evsel.core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
 
 	for (i = 0; i < sizeof(regs); i++)
 		*(i + (u8 *)regs) = i & 0xfe;

tools/perf/util/Build

···
 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
 
···
 	$(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)
···
 
 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))"
···
 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

tools/perf/util/annotate.c

···
 
 		if (++al->jump_sources > notes->max_jump_sources)
 			notes->max_jump_sources = al->jump_sources;
-
-		++notes->nr_jumps;
 	}
 }
 

tools/perf/util/annotate.h

···
 	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;

tools/perf/util/block-info.c

···
 	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;
···
 
 	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,
···
 	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)
···
 	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,
···
 	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,
···
 	end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
 				he->ms.sym);
 
-	if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+	if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+	    (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
 		scnprintf(buf, sizeof(buf), "[%s -> %s]",
 			  start_line, end_line);
 	} else {
···
 
 	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;
···
 		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;
···
 }
 
 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);
···
 		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;
···
 	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,
···
 		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;

tools/perf/util/block-info.h

···
 	struct block_hist	hist;
 	u64			cycles;
 	struct block_fmt	fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX];
+	int			nr_fmts;
 };
 
 struct block_hist;
···
 
 #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);
 
···
 			    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,

tools/perf/util/branch.h

···
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include "event.h"
 
 struct branch_flags {
 	u64 mispred:1;
···
 
 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;

tools/perf/util/cgroup.c

···
 #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)
 {
···
 	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);

tools/perf/util/cs-etm.c

···
 	union perf_event *event = tidq->event_buf;
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 	u64 ip;
···
 	if (etm->synth_opts.last_branch) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,

tools/perf/util/event.h

···
 	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;

tools/perf/util/evsel.c

···
 				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. "
···
 	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);
···
 		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;
···
 	 * 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;
···
 
 		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;
 	}

tools/perf/util/evsel.h

···
 	bool ksymbol;
 	bool bpf;
 	bool aux_output;
+	bool branch_hw_idx;
 };
 
 extern struct perf_missing_features perf_missing_features;
···
 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)

tools/perf/util/expr.c

···
+// 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;
+}

tools/perf/util/expr.h

···
 #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 {
···
 
 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

tools/perf/util/expr.l

···
+%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 = parse_events_get_extra(yyscanner);
+
+		if (start_token) {
+			parse_events_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;
+}

tools/perf/util/expr.y

···
 /* 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 '|'
···
 %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);
···
 
 %}
 %%
+
+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; }
 	;
···
 	;
 
 %%
-
-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;
-}

tools/perf/util/header.c

···
 	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;
···
 			perf_event__attr_swap(buf);
 
 		memcpy(&evsel->core.attr, buf, msz);
+
+		if (!perf_attr_check(&evsel->core.attr))
+			goto error;
 
 		if (do_read_u32(ff, &nr))
 			goto error;

tools/perf/util/hist.c

···
 			  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);

tools/perf/util/intel-pt.c

···
 	struct perf_sample sample = { .ip = 0, };
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 
···
 	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,

tools/perf/util/llvm-utils.c

···
 			return -ENOMEM;
 		return 0;
 	}
+	pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n",
+		 __func__, autoconf_path);
 	free(autoconf_path);
 	return -ENOENT;
 }

tools/perf/util/machine.c

···
 {
 	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;
 }
···
 	/* 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;
···
 					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;
 				}
 			}
 
···
 					    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;
···
 
 		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;
···
 				    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);

tools/perf/util/map.c

···
 
 	if (map && map->dso) {
 		char *srcline = map__srcline(map, addr, NULL);
-		if (srcline != SRCLINE_UNKNOWN)
+		if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);
 	}

tools/perf/util/perf_event_attr_fprintf.c

···
 		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

tools/perf/util/scripting-engines/trace-event-python.c

···
 					struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 
···
 			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));
···
 					   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];
···
 			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 {
···
 					      _PyUnicode_FromString("-"));
 		}
 
-		if (br->entries[i].flags.abort) {
+		if (entries[i].flags.abort) {
 			pydict_set_item_string_decref(pyelem, "abort",
 					      _PyUnicode_FromString("A"));
 		} else {

tools/perf/util/session.c

···
 {
 	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;
 
···
 			       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);
 	}
 }
 
···
 
 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",
···
 		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",

tools/perf/util/stat-display.c

···
 			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),
···
 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;
···
 		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);
···
 		evlist__for_each_entry(evlist, counter) {
 			print_counter_aggrdata(config, counter, s,
 					       prefix, metric_only,
-					       &first);
+					       &first, -1);
 		}
 		if (metric_only)
 			fputc('\n', output);
···
 			"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)
 {
···
 	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)

tools/perf/util/stat-shadow.c

···
 	}
 
 	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];
 

tools/perf/util/stat.h

···
 	bool			 walltime_run_table;
 	bool			 all_kernel;
 	bool			 all_user;
+	bool			 percore_show_thread;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;

tools/perf/util/synthetic-events.c

···
 
 	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;
 	}
 
···
 
 	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;
 	}