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

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

1 files changed, 121 insertions, 31 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 227b6ae99785..be4e1eee782e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -44,6 +44,7 @@ struct perf_record {
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
 	const char		*progname;
+	const char		*uid_str;
 	int			output;
 	unsigned int		page_size;
 	int			realtime_prio;
@@ -208,7 +209,7 @@ fallback_missing_features:
 		if (opts->exclude_guest_missing)
 			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-		attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+		attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
 				     opts->group, group_fd) < 0) {
@@ -227,11 +228,11 @@ try_again:
 						 "guest or host samples.\n");
 					opts->exclude_guest_missing = true;
 					goto fallback_missing_features;
-				} else if (opts->sample_id_all_avail) {
+				} else if (!opts->sample_id_all_missing) {
 					/*
 					 * Old kernel, no attr->sample_id_type_all field
 					 */
-					opts->sample_id_all_avail = false;
+					opts->sample_id_all_missing = true;
 					if (!opts->sample_time && !opts->raw_samples && !time_needed)
 						attr->sample_type &= ~PERF_SAMPLE_TIME;
 
@@ -396,7 +397,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 {
 	struct stat st;
 	int flags;
-	int err, output;
+	int err, output, feat;
 	unsigned long waking = 0;
 	const bool forks = argc > 0;
 	struct machine *machine;
@@ -463,8 +464,17 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
 	rec->session = session;
 
-	if (!rec->no_buildid)
-		perf_header__set_feat(&session->header, HEADER_BUILD_ID);
+	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+		perf_header__set_feat(&session->header, feat);
+
+	if (rec->no_buildid)
+		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+
+	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);
@@ -472,22 +482,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 			goto out_delete_session;
 	}
 
-	if (have_tracepoints(&evsel_list->entries))
-		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
-
-	perf_header__set_feat(&session->header, HEADER_HOSTNAME);
-	perf_header__set_feat(&session->header, HEADER_OSRELEASE);
-	perf_header__set_feat(&session->header, HEADER_ARCH);
-	perf_header__set_feat(&session->header, HEADER_CPUDESC);
-	perf_header__set_feat(&session->header, HEADER_NRCPUS);
-	perf_header__set_feat(&session->header, HEADER_EVENT_DESC);
-	perf_header__set_feat(&session->header, HEADER_CMDLINE);
-	perf_header__set_feat(&session->header, HEADER_VERSION);
-	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
-	perf_header__set_feat(&session->header, HEADER_TOTAL_MEM);
-	perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY);
-	perf_header__set_feat(&session->header, HEADER_CPUID);
-
 	if (forks) {
 		err = perf_evlist__prepare_workload(evsel_list, opts, argv);
 		if (err < 0) {
@@ -647,6 +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>]",
@@ -665,13 +743,10 @@ static const char * const record_usage[] = {
  */
 static struct perf_record record = {
 	.opts = {
-		.target_pid	     = -1,
-		.target_tid	     = -1,
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
 		.freq		     = 1000,
-		.sample_id_all_avail = true,
 	},
 	.write_mode = WRITE_FORCE,
 	.file_new   = true,
@@ -690,9 +765,9 @@ const struct option record_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
 		     "event filter", parse_filter),
-	OPT_INTEGER('p', "pid", &record.opts.target_pid,
+	OPT_STRING('p', "pid", &record.opts.target_pid, "pid",
 		    "record events on existing process id"),
-	OPT_INTEGER('t', "tid", &record.opts.target_tid,
+	OPT_STRING('t', "tid", &record.opts.target_tid, "tid",
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &record.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
@@ -738,6 +813,15 @@ const struct option record_options[] = {
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "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()
 };
 
@@ -758,8 +842,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 &&
-		!rec->opts.system_wide && !rec->opts.cpu_list)
+	if (!argc && !rec->opts.target_pid && !rec->opts.target_tid &&
+		!rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str)
 		usage_with_options(record_usage, record_options);
 
 	if (rec->force && rec->append_file) {
@@ -799,11 +883,17 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		goto out_symbol_exit;
 	}
 
-	if (rec->opts.target_pid != -1)
+	rec->opts.uid = parse_target_uid(rec->uid_str, rec->opts.target_tid,
+					 rec->opts.target_pid);
+	if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1)
+		goto out_free_fd;
+
+	if (rec->opts.target_pid)
 		rec->opts.target_tid = rec->opts.target_pid;
 
 	if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,
-				     rec->opts.target_tid, rec->opts.cpu_list) < 0)
+				     rec->opts.target_tid, rec->opts.uid,
+				     rec->opts.cpu_list) < 0)
 		usage_with_options(record_usage, record_options);
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {