Merge branch 'perf/hw-branch-sampling' into perf/core

Merge reason: The 'perf record -b' hardware branch sampling feature is ready for upstream.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

17 files changed, 1023 insertions, 166 deletions

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index a5766b4b012..a1386b2fff0 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -152,6 +152,36 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
 corresponding events, i.e., they always refer to events defined earlier on the command
 line.
 
+-b::
+--branch-any::
+Enable taken branch stack sampling. Any type of taken branch may be sampled.
+This is a shortcut for --branch-filter any. See --branch-filter for more infos.
+
+-j::
+--branch-filter::
+Enable taken branch stack sampling. Each sample captures a series of consecutive
+taken branches. The number of branches captured with each sample depends on the
+underlying hardware, the type of branches of interest, and the executed code.
+It is possible to select the types of branches captured by enabling filters. The
+following filters are defined:
+
+        - any:  any type of branches
+        - any_call: any function call or system call
+        - any_ret: any function return or system call return
+        - any_ind: any indirect branch
+        - u:  only when the branch target is at the user level
+        - k: only when the branch target is in the kernel
+        - hv: only when the target is at the hypervisor level
+
++
+The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The privilege levels may be ommitted, in which case, the privilege levels of the associated
+event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
+levels are subject to permissions.  When sampling on multiple events, branch stack sampling
+is enabled for all the sampling events. The sampled branch type is the same for all events.
+The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
+Note that this feature may not be available on all processors.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9b430e98712..87feeee8b90 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -153,6 +153,16 @@ OPTIONS
 	information which may be very large and thus may clutter the display.
 	It currently includes: cpu and numa topology of the host system.
 
+-b::
+--branch-stack::
+	Use the addresses of sampled taken branches instead of the instruction
+	address to build the histograms. To generate meaningful output, the
+	perf.data file must have been obtained using perf record -b or
+	perf record --branch-filter xxx where xxx is a branch filter option.
+	perf report is able to auto-detect whether a perf.data file contains
+	branch stacks and it will automatically switch to the branch view mode,
+	unless --no-branch-stack is used.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 75d230fef20..be4e1eee782 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -473,6 +473,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	if (!have_tracepoints(&evsel_list->entries))
 		perf_header__clear_feat(&session->header, HEADER_TRACE_INFO);
 
+	if (!rec->opts.branch_stack)
+		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
 	if (!rec->file_new) {
 		err = perf_session__read_header(session, output);
 		if (err < 0)
@@ -638,6 +641,90 @@ out_delete_session:
 	return err;
 }
 
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_END
+};
+
+static int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice, -b + --branch-filter for instance
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -727,6 +814,14 @@ const struct option record_options[] = {
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
 	OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
+
+	OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
+		     "branch any", "sample any taken branches",
+		     parse_branch_stack),
+
+	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
+		     "branch filter mask", "branch stack filter modes",
+		     parse_branch_stack),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 25d34d483e4..8e91c6eba18 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -53,6 +53,82 @@ struct perf_report {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
+					struct addr_location *al,
+					struct perf_sample *sample,
+					struct perf_evsel *evsel,
+				      struct machine *machine)
+{
+	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct symbol *parent = NULL;
+	int err = 0;
+	unsigned i;
+	struct hist_entry *he;
+	struct branch_info *bi, *bx;
+
+	if ((sort__has_parent || symbol_conf.use_callchain)
+	    && sample->callchain) {
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample->callchain, &parent);
+		if (err)
+			return err;
+	}
+
+	bi = machine__resolve_bstack(machine, al->thread,
+				     sample->branch_stack);
+	if (!bi)
+		return -ENOMEM;
+
+	for (i = 0; i < sample->branch_stack->nr; i++) {
+		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+			continue;
+		/*
+		 * The report shows the percentage of total branches captured
+		 * and not events sampled. Thus we use a pseudo period of 1.
+		 */
+		he = __hists__add_branch_entry(&evsel->hists, al, parent,
+				&bi[i], 1);
+		if (he) {
+			struct annotation *notes;
+			err = -ENOMEM;
+			bx = he->branch_info;
+			if (bx->from.sym && use_browser > 0) {
+				notes = symbol__annotation(bx->from.sym);
+				if (!notes->src
+				    && symbol__alloc_hist(bx->from.sym) < 0)
+					goto out;
+
+				err = symbol__inc_addr_samples(bx->from.sym,
+							       bx->from.map,
+							       evsel->idx,
+							       bx->from.al_addr);
+				if (err)
+					goto out;
+			}
+
+			if (bx->to.sym && use_browser > 0) {
+				notes = symbol__annotation(bx->to.sym);
+				if (!notes->src
+				    && symbol__alloc_hist(bx->to.sym) < 0)
+					goto out;
+
+				err = symbol__inc_addr_samples(bx->to.sym,
+							       bx->to.map,
+							       evsel->idx,
+							       bx->to.al_addr);
+				if (err)
+					goto out;
+			}
+			evsel->hists.stats.total_period += 1;
+			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+			err = 0;
+		} else
+			return -ENOMEM;
+	}
+out:
+	return err;
+}
+
 static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 				      struct addr_location *al,
 				      struct perf_sample *sample,
@@ -126,14 +202,21 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (al.map != NULL)
-		al.map->dso->hit = 1;
+	if (sort__branch_mode == 1) {
+		if (perf_report__add_branch_hist_entry(tool, &al, sample,
+						       evsel, machine)) {
+			pr_debug("problem adding lbr entry, skipping event\n");
+			return -1;
+		}
+	} else {
+		if (al.map != NULL)
+			al.map->dso->hit = 1;
 
-	if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
-		pr_debug("problem incrementing symbol period, skipping event\n");
-		return -1;
+		if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+			pr_debug("problem incrementing symbol period, skipping event\n");
+			return -1;
+		}
 	}
-
 	return 0;
 }
 
@@ -188,6 +271,15 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 			}
 	}
 
+	if (sort__branch_mode == 1) {
+		if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+			fprintf(stderr, "selected -b but no branch data."
+					" Did you call perf record without"
+					" -b?\n");
+			return -1;
+		}
+	}
+
 	return 0;
 }
 
@@ -246,7 +338,7 @@ static int __cmd_report(struct perf_report *rep)
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
-	struct perf_session *session;
+	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
 	struct map *kernel_map;
 	struct kmap *kernel_kmap;
@@ -254,13 +346,6 @@ static int __cmd_report(struct perf_report *rep)
 
 	signal(SIGINT, sig_handler);
 
-	session = perf_session__new(rep->input_name, O_RDONLY,
-				    rep->force, false, &rep->tool);
-	if (session == NULL)
-		return -ENOMEM;
-
-	rep->session = session;
-
 	if (rep->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
 					       rep->cpu_bitmap);
@@ -427,9 +512,19 @@ setup:
 	return 0;
 }
 
+static int
+parse_branch_mode(const struct option *opt __used, const char *str __used, int unset)
+{
+	sort__branch_mode = !unset;
+	return 0;
+}
+
 int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
+	struct perf_session *session;
 	struct stat st;
+	bool has_br_stack = false;
+	int ret = -1;
 	char callchain_default_opt[] = "fractal,0.5,callee";
 	const char * const report_usage[] = {
 		"perf report [<options>]",
@@ -477,7 +572,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
+		   " dso_from, symbol_to, symbol_from, mispredict"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -517,6 +613,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
+		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_END()
 	};
 
@@ -536,11 +634,36 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		else
 			report.input_name = "perf.data";
 	}
+	session = perf_session__new(report.input_name, O_RDONLY,
+				    report.force, false, &report.tool);
+	if (session == NULL)
+		return -ENOMEM;
 
-	if (strcmp(report.input_name, "-") != 0)
+	report.session = session;
+
+	has_br_stack = perf_header__has_feat(&session->header,
+					     HEADER_BRANCH_STACK);
+
+	if (sort__branch_mode == -1 && has_br_stack)
+		sort__branch_mode = 1;
+
+	/* sort__branch_mode could be 0 if --no-branch-stack */
+	if (sort__branch_mode == 1) {
+		/*
+		 * if no sort_order is provided, then specify
+		 * branch-mode specific order
+		 */
+		if (sort_order == default_sort_order)
+			sort_order = "comm,dso_from,symbol_from,"
+				     "dso_to,symbol_to";
+
+	}
+
+	if (strcmp(report.input_name, "-") != 0) {
 		setup_browser(true);
-	else
+	} else {
 		use_browser = 0;
+	}
 
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
@@ -568,13 +691,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (symbol__init() < 0)
-		return -1;
+		goto error;
 
 	setup_sorting(report_usage, options);
 
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
-			return -1;
+			goto error;
 
 		/*
 		 * Only show the parent fields if we explicitly
@@ -592,9 +715,20 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	if (argc)
 		usage_with_options(report_usage, options);
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
 	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
 
-	return __cmd_report(&report);
+	if (sort__branch_mode == 1) {
+		sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
+		sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
+		sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
+		sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
+	} else {
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
+		sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
+	}
+
+	ret = __cmd_report(&report);
+error:
+	perf_session__delete(session);
+	return ret;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index f0227e93665..eec392e4806 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -179,6 +179,23 @@ struct ip_callchain {
 	u64 ips[0];
 };
 
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 reserved:62;
+};
+
+struct branch_entry {
+	u64				from;
+	u64				to;
+	struct branch_flags flags;
+};
+
+struct branch_stack {
+	u64				nr;
+	struct branch_entry	entries[0];
+};
+
 extern bool perf_host, perf_guest;
 extern const char perf_version_string[];
 
@@ -205,6 +222,7 @@ struct perf_record_opts {
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;
+	int	     branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
 	const char   *cpu_list;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index cbdeaad9c5e..1b197280c62 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -81,6 +81,7 @@ struct perf_sample {
 	u32 raw_size;
 	void *raw_data;
 	struct ip_callchain *callchain;
+	struct branch_stack *branch_stack;
 };
 
 #define BUILD_ID_SIZE 20
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 302d49a9f98..f421f7cbc0d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -126,6 +126,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
+	if (opts->branch_stack) {
+		attr->sample_type	|= PERF_SAMPLE_BRANCH_STACK;
+		attr->branch_sample_type = opts->branch_stack;
+	}
 
 	attr->mmap = track;
 	attr->comm = track;
@@ -576,6 +580,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 		data->raw_data = (void *) pdata;
 	}
 
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 sz;
+
+		data->branch_stack = (struct branch_stack *)array;
+		array++; /* nr */
+
+		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		sz /= sizeof(u64);
+		array += sz;
+	}
 	return 0;
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 9f867d96c6a..0d9b6da86a3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1023,6 +1023,12 @@ write_it:
 	return do_write_string(fd, buffer);
 }
 
+static int write_branch_stack(int fd __used, struct perf_header *h __used,
+		       struct perf_evlist *evlist __used)
+{
+	return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
 {
 	char *str = do_read_string(fd, ph);
@@ -1144,8 +1150,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	uint64_t id;
 	void *buf = NULL;
 	char *str;
-	u32 nre, sz, nr, i, j, msz;
-	int ret;
+	u32 nre, sz, nr, i, j;
+	ssize_t ret;
+	size_t msz;
 
 	/* number of events */
 	ret = read(fd, &nre, sizeof(nre));
@@ -1162,25 +1169,23 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	if (ph->needs_swap)
 		sz = bswap_32(sz);
 
-	/*
-	 * ensure it is at least to our ABI rev
-	 */
-	if (sz < (u32)sizeof(attr))
-		goto error;
-
 	memset(&attr, 0, sizeof(attr));
 
-	/* read entire region to sync up to next field */
+	/* buffer to hold on file attr struct */
 	buf = malloc(sz);
 	if (!buf)
 		goto error;
 
 	msz = sizeof(attr);
-	if (sz < msz)
+	if (sz < (ssize_t)msz)
 		msz = sz;
 
 	for (i = 0 ; i < nre; i++) {
 
+		/*
+		 * must read entire on-file attr struct to
+		 * sync up with layout.
+		 */
 		ret = read(fd, buf, sz);
 		if (ret != (ssize_t)sz)
 			goto error;
@@ -1316,6 +1321,12 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
 	free(str);
 }
 
+static void print_branch_stack(struct perf_header *ph __used, int fd __used,
+			       FILE *fp)
+{
+	fprintf(fp, "# contains samples with branch stack\n");
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -1520,6 +1531,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_CMDLINE,	cmdline),
 	FEAT_OPF(HEADER_CPU_TOPOLOGY,	cpu_topology),
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
+	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 };
 
 struct header_print_data {
@@ -1804,35 +1816,101 @@ out_free:
 	return err;
 }
 
-static int check_magic_endian(u64 *magic, struct perf_file_header *header,
-			      struct perf_header *ph)
+static const int attr_file_abi_sizes[] = {
+	[0] = PERF_ATTR_SIZE_VER0,
+	[1] = PERF_ATTR_SIZE_VER1,
+	0,
+};
+
+/*
+ * In the legacy file format, the magic number is not used to encode endianness.
+ * hdr_sz was used to encode endianness. But given that hdr_sz can vary based
+ * on ABI revisions, we need to try all combinations for all endianness to
+ * detect the endianness.
+ */
+static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph)
 {
-	int ret;
+	uint64_t ref_size, attr_size;
+	int i;
 
-	/* check for legacy format */
-	ret = memcmp(magic, __perf_magic1, sizeof(*magic));
-	if (ret == 0) {
-		pr_debug("legacy perf.data format\n");
-		if (!header)
-			return -1;
+	for (i = 0 ; attr_file_abi_sizes[i]; i++) {
+		ref_size = attr_file_abi_sizes[i]
+			 + sizeof(struct perf_file_section);
+		if (hdr_sz != ref_size) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != ref_size)
+				continue;
 
-		if (header->attr_size != sizeof(struct perf_file_attr)) {
-			u64 attr_size = bswap_64(header->attr_size);
+			ph->needs_swap = true;
+		}
+		pr_debug("ABI%d perf.data file detected, need_swap=%d\n",
+			 i,
+			 ph->needs_swap);
+		return 0;
+	}
+	/* could not determine endianness */
+	return -1;
+}
 
-			if (attr_size != sizeof(struct perf_file_attr))
-				return -1;
+#define PERF_PIPE_HDR_VER0	16
+
+static const size_t attr_pipe_abi_sizes[] = {
+	[0] = PERF_PIPE_HDR_VER0,
+	0,
+};
+
+/*
+ * In the legacy pipe format, there is an implicit assumption that endiannesss
+ * between host recording the samples, and host parsing the samples is the
+ * same. This is not always the case given that the pipe output may always be
+ * redirected into a file and analyzed on a different machine with possibly a
+ * different endianness and perf_event ABI revsions in the perf tool itself.
+ */
+static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph)
+{
+	u64 attr_size;
+	int i;
+
+	for (i = 0 ; attr_pipe_abi_sizes[i]; i++) {
+		if (hdr_sz != attr_pipe_abi_sizes[i]) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != hdr_sz)
+				continue;
 
 			ph->needs_swap = true;
 		}
+		pr_debug("Pipe ABI%d perf.data file detected\n", i);
 		return 0;
 	}
+	return -1;
+}
+
+static int check_magic_endian(u64 magic, uint64_t hdr_sz,
+			      bool is_pipe, struct perf_header *ph)
+{
+	int ret;
+
+	/* check for legacy format */
+	ret = memcmp(&magic, __perf_magic1, sizeof(magic));
+	if (ret == 0) {
+		pr_debug("legacy perf.data format\n");
+		if (is_pipe)
+			return try_all_pipe_abis(hdr_sz, ph);
+
+		return try_all_file_abis(hdr_sz, ph);
+	}
+	/*
+	 * the new magic number serves two purposes:
+	 * - unique number to identify actual perf.data files
+	 * - encode endianness of file
+	 */
 
-	/* check magic number with same endianness */
-	if (*magic == __perf_magic2)
+	/* check magic number with one endianness */
+	if (magic == __perf_magic2)
 		return 0;
 
-	/* check magic number but opposite endianness */
-	if (*magic != __perf_magic2_sw)
+	/* check magic number with opposite endianness */
+	if (magic != __perf_magic2_sw)
 		return -1;
 
 	ph->needs_swap = true;
@@ -1851,8 +1929,11 @@ int perf_file_header__read(struct perf_file_header *header,
 	if (ret <= 0)
 		return -1;
 
-	if (check_magic_endian(&header->magic, header, ph) < 0)
+	if (check_magic_endian(header->magic,
+			       header->attr_size, false, ph) < 0) {
+		pr_debug("magic/endian check failed\n");
 		return -1;
+	}
 
 	if (ph->needs_swap) {
 		mem_bswap_64(header, offsetof(struct perf_file_header,
@@ -1939,21 +2020,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 	if (ret <= 0)
 		return -1;
 
-	 if (check_magic_endian(&header->magic, NULL, ph) < 0)
+	if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+		pr_debug("endian/magic failed\n");
 		return -1;
+	}
+
+	if (ph->needs_swap)
+		header->size = bswap_64(header->size);
 
 	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
 		return -1;
 
-	if (header->size != sizeof(*header)) {
-		u64 size = bswap_64(header->size);
-
-		if (size != sizeof(*header))
-			return -1;
-
-		ph->needs_swap = true;
-	}
-
 	return 0;
 }
 
@@ -1973,6 +2050,52 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
 	return 0;
 }
 
+static int read_attr(int fd, struct perf_header *ph,
+		     struct perf_file_attr *f_attr)
+{
+	struct perf_event_attr *attr = &f_attr->attr;
+	size_t sz, left;
+	size_t our_sz = sizeof(f_attr->attr);
+	int ret;
+
+	memset(f_attr, 0, sizeof(*f_attr));
+
+	/* read minimal guaranteed structure */
+	ret = readn(fd, attr, PERF_ATTR_SIZE_VER0);
+	if (ret <= 0) {
+		pr_debug("cannot read %d bytes of header attr\n",
+			 PERF_ATTR_SIZE_VER0);
+		return -1;
+	}
+
+	/* on file perf_event_attr size */
+	sz = attr->size;
+
+	if (ph->needs_swap)
+		sz = bswap_32(sz);
+
+	if (sz == 0) {
+		/* assume ABI0 */
+		sz =  PERF_ATTR_SIZE_VER0;
+	} else if (sz > our_sz) {
+		pr_debug("file uses a more recent and unsupported ABI"
+			 " (%zu bytes extra)\n", sz - our_sz);
+		return -1;
+	}
+	/* what we have not yet read and that we know about */
+	left = sz - PERF_ATTR_SIZE_VER0;
+	if (left) {
+		void *ptr = attr;
+		ptr += PERF_ATTR_SIZE_VER0;
+
+		ret = readn(fd, ptr, left);
+	}
+	/* read perf_file_section, ids are read in caller */
+	ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids));
+
+	return ret <= 0 ? -1 : 0;
+}
+
 int perf_session__read_header(struct perf_session *session, int fd)
 {
 	struct perf_header *header = &session->header;
@@ -1988,19 +2111,17 @@ int perf_session__read_header(struct perf_session *session, int fd)
 	if (session->fd_pipe)
 		return perf_header__read_pipe(session, fd);
 
-	if (perf_file_header__read(&f_header, header, fd) < 0) {
-		pr_debug("incompatible file format\n");
+	if (perf_file_header__read(&f_header, header, fd) < 0)
 		return -EINVAL;
-	}
 
-	nr_attrs = f_header.attrs.size / sizeof(f_attr);
+	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
 	for (i = 0; i < nr_attrs; i++) {
 		struct perf_evsel *evsel;
 		off_t tmp;
 
-		if (readn(fd, &f_attr, sizeof(f_attr)) <= 0)
+		if (read_attr(fd, header, &f_attr) < 0)
 			goto out_errno;
 
 		if (header->needs_swap)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e68f617d082..21a6be09c12 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -27,7 +27,7 @@ enum {
 	HEADER_EVENT_DESC,
 	HEADER_CPU_TOPOLOGY,
 	HEADER_NUMA_TOPOLOGY,
-
+	HEADER_BRANCH_STACK,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6f505d1abac..8380c3db1c9 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -50,21 +50,25 @@ static void hists__reset_col_len(struct hists *hists)
 		hists__set_col_len(hists, col, 0);
 }
 
+static void hists__set_unres_dso_col_len(struct hists *hists, int dso)
+{
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+	if (hists__col_len(hists, dso) < unresolved_col_width &&
+	    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+	    !symbol_conf.dso_list)
+		hists__set_col_len(hists, dso, unresolved_col_width);
+}
+
 static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 {
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
 	u16 len;
 
 	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen);
-	else {
-		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-		if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width &&
-		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-		    !symbol_conf.dso_list)
-			hists__set_col_len(hists, HISTC_DSO,
-					   unresolved_col_width);
-	}
+		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
+	else
+		hists__set_unres_dso_col_len(hists, HISTC_DSO);
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -74,6 +78,37 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		len = dso__name_len(h->ms.map->dso);
 		hists__new_col_len(hists, HISTC_DSO, len);
 	}
+
+	if (h->branch_info) {
+		int symlen;
+		/*
+		 * +4 accounts for '[x] ' priv level info
+		 * +2 account of 0x prefix on raw addresses
+		 */
+		if (h->branch_info->from.sym) {
+			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+
+			symlen = dso__name_len(h->branch_info->from.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_FROM, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
+		}
+
+		if (h->branch_info->to.sym) {
+			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+
+			symlen = dso__name_len(h->branch_info->to.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_TO, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
+		}
+	}
 }
 
 static void hist_entry__add_cpumode_period(struct hist_entry *he,
@@ -195,26 +230,14 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
+static struct hist_entry *add_hist_entry(struct hists *hists,
+				      struct hist_entry *entry,
 				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+				      u64 period)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	struct hist_entry entry = {
-		.thread	= al->thread,
-		.ms = {
-			.map	= al->map,