Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

  * Make per-cpu mmaps the default in 'perf record', from Adrian Hunter.

  * Default -t/--thread 'perf record' option to no inheritance,
    from Adrian Hunter.

  * Make 'perf top -g' refer to callchains, for consistency with other tools,
    from David Ahern.

  * Skip ignored symbols while printing callchain, from David Ahern.

  * Print callchains and symbols if they exist in 'perf script',
    from David Ahern.

  * Remove thread summary coloring in 'perf trace', from Pekka Enberg.

  * zsh completion support, from Ramkumar Ramachandra.

  * 'perf timechart' improvements, including backtrace support,
    from Stanislav Fomichev.

  * Fix using kcore files stored in the buildid cache when doing report/annotate
    in non-live sessions, from Adrian Hunter

  * Minor 'timechart' cleanups.

  * Fix tags/TAGS targets rebuilding, from Jiri Olsa.

  * Add options to show comm, fork, exit and mmap PERF_RECORD_ events in
    'perf script', from Namhyung Kim.

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

28 files changed, 831 insertions, 234 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 217c82ee..900fca0 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4099,6 +4099,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 	unsigned long long val;
 	struct func_map *func;
 	const char *saveptr;
+	struct trace_seq p;
 	char *bprint_fmt = NULL;
 	char format[32];
 	int show_func;
@@ -4306,8 +4307,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				format[len] = 0;
 				if (!len_as_arg)
 					len_arg = -1;
-				print_str_arg(s, data, size, event,
+				/* Use helper trace_seq */
+				trace_seq_init(&p);
+				print_str_arg(&p, data, size, event,
 					      format, len_arg, arg);
+				trace_seq_terminate(&p);
+				trace_seq_puts(s, p.buffer);
 				arg = arg->next;
 				break;
 			default:
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 43b42c4..c407897 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -57,6 +57,8 @@ OPTIONS
 -t::
 --tid=::
         Record events on existing thread ID (comma separated list).
+        This option also disables inheritance by default.  Enable it by adding
+        --inherit.
 
 -u::
 --uid=::
@@ -201,11 +203,11 @@ abort events and some memory events in precise mode on modern Intel CPUs.
 --transaction::
 Record transaction flags for transaction related events.
 
---force-per-cpu::
-Force the use of per-cpu mmaps.  By default, when tasks are specified (i.e. -p,
--t or -u options) per-thread mmaps are created.  This option overrides that and
-forces per-cpu mmaps.  A side-effect of that is that inheritance is
-automatically enabled.  Add the -i option also to disable inheritance.
+--per-thread::
+Use per-thread mmaps.  By default per-cpu mmaps are created.  This option
+overrides that and uses per-thread mmaps.  A side-effect of that is that
+inheritance is automatically disabled.  --per-thread is ignored with a warning
+if combined with -a or -C options.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index e9cbfcd..cfdbb1e0 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -203,6 +203,12 @@ OPTIONS
 --show-kernel-path::
 	Try to resolve the path of [kernel.kallsyms]
 
+--show-task-events
+	Display task related events (e.g. FORK, COMM, EXIT).
+
+--show-mmap-events
+	Display mmap related events (e.g. MMAP, MMAP2).
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 3ff8bd4..271dd4e 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -8,8 +8,7 @@ perf-timechart - Tool to visualize total system behavior during a workload
 SYNOPSIS
 --------
 [verse]
-'perf timechart' record <command>
-'perf timechart' [<options>]
+'perf timechart' [<timechart options>] {record} [<record options>]
 
 DESCRIPTION
 -----------
@@ -21,8 +20,8 @@ There are two variants of perf timechart:
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
   that can be viewed with popular SVG viewers such as 'Inkscape'.
 
-OPTIONS
--------
+TIMECHART OPTIONS
+-----------------
 -o::
 --output=::
         Select the output file (default: output.svg)
@@ -35,6 +34,9 @@ OPTIONS
 -P::
 --power-only::
         Only output the CPU power section of the diagram
+-T::
+--tasks-only::
+        Don't output processor state transitions
 -p::
 --process::
         Select the processes to display, by name or PID
@@ -54,6 +56,22 @@ $ perf timechart
 
   Written 10.2 seconds of trace to output.svg.
 
+-n::
+--proc-num::
+        Print task info for at least given number of tasks.
+
+RECORD OPTIONS
+--------------
+-P::
+--power-only::
+        Record only power-related events
+-T::
+--tasks-only::
+        Record only tasks-related events
+-g::
+--callchain::
+        Do call-graph (stack chain/backtrace) recording
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 7de01dd..cdd8d49 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -50,7 +50,6 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
 	Only display functions with more events than this.
 
--g::
 --group::
         Put the counters into a counter group.
 
@@ -143,12 +142,12 @@ Default is to monitor all CPUS.
 --asm-raw::
 	Show raw instruction encoding of assembly instructions.
 
--G::
+-g::
 	Enables call-graph (stack chain/backtrace) recording.
 
 --call-graph::
 	Setup and enable call-graph (stack chain/backtrace) recording,
-	implies -G.
+	implies -g.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4835618..eefb9fb 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -60,8 +60,11 @@ endef
 
 #
 # Needed if no target specified:
+# (Except for tags and TAGS targets. The reason is that the
+# Makefile does not treat tags/TAGS as targets but as files
+# and thus won't rebuilt them once they are in place.)
 #
-all:
+all tags TAGS:
 	$(print_msg)
 	$(make)
 
@@ -77,3 +80,5 @@ clean:
 %:
 	$(print_msg)
 	$(make)
+
+.PHONY: tags TAGS
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7fc8f17..e416ccc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -840,9 +840,9 @@ ifndef NO_LIBPYTHON
 		$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
 		$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 endif
-	$(call QUIET_INSTALL, bash_completion-script) \
+	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
-		$(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7c8020a..65615a8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -800,6 +800,7 @@ static struct perf_record record = {
 		.freq		     = 4000,
 		.target		     = {
 			.uses_mmap   = true,
+			.default_per_cpu = true,
 		},
 	},
 };
@@ -842,8 +843,9 @@ const struct option record_options[] = {
 	OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
 	OPT_STRING('o', "output", &record.file.path, "file",
 		    "output file name"),
-	OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
-		    "child tasks do not inherit counters"),
+	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
+			&record.opts.no_inherit_set,
+			"child tasks do not inherit counters"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
 	OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
 		     "number of mmap data pages",
@@ -888,8 +890,8 @@ const struct option record_options[] = {
 		    "sample by weight (on special events only)"),
 	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
 		    "sample transaction flags (special events only)"),
-	OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
-		    "force the use of per-cpu mmaps"),
+	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
+		    "use per-thread mmaps"),
 	OPT_END()
 };
 
@@ -938,6 +940,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_symbol_exit;
 	}
 
+	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
+		rec->opts.no_inherit = true;
+
 	err = target__validate(&rec->opts.target);
 	if (err) {
 		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index baf1798..952dce9 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -280,6 +280,30 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	/*
+	 * set default for tracepoints to print symbols only
+	 * if callchains are present
+	 */
+	if (symbol_conf.use_callchain &&
+	    !output[PERF_TYPE_TRACEPOINT].user_set) {
+		struct perf_event_attr *attr;
+
+		j = PERF_TYPE_TRACEPOINT;
+		evsel = perf_session__find_first_evtype(session, j);
+		if (evsel == NULL)
+			goto out;
+
+		attr = &evsel->attr;
+
+		if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+			output[j].fields |= PERF_OUTPUT_IP;
+			output[j].fields |= PERF_OUTPUT_SYM;
+			output[j].fields |= PERF_OUTPUT_DSO;
+			set_print_ip_opts(attr);
+		}
+	}
+
+out:
 	return 0;
 }
 
@@ -288,7 +312,6 @@ static void print_sample_start(struct perf_sample *sample,
 			       struct perf_evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	const char *evname = NULL;
 	unsigned long secs;
 	unsigned long usecs;
 	unsigned long long nsecs;
@@ -323,11 +346,6 @@ static void print_sample_start(struct perf_sample *sample,
 		usecs = nsecs / NSECS_PER_USEC;
 		printf("%5lu.%06lu: ", secs, usecs);
 	}
-
-	if (PRINT_FIELD(EVNAME)) {
-		evname = perf_evsel__name(evsel);
-		printf("%s: ", evname ? evname : "[unknown]");
-	}
 }
 
 static bool is_bts_event(struct perf_event_attr *attr)
@@ -434,6 +452,11 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 
 	print_sample_start(sample, thread, evsel);
 
+	if (PRINT_FIELD(EVNAME)) {
+		const char *evname = perf_evsel__name(evsel);
+		printf("%s: ", evname ? evname : "[unknown]");
+	}
+
 	if (is_bts_event(attr)) {
 		print_sample_bts(event, sample, evsel, machine, thread);
 		return;
@@ -549,6 +572,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
+	bool			show_task_events;
+	bool			show_mmap_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -579,6 +604,163 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	return perf_evsel__check_attr(evsel, scr->session);
 }
 
+static int process_comm_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing COMM event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_comm(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+
+out:
+	return ret;
+}
+
+static int process_fork_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_fork(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing FORK event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = event->fork.time;
+		sample->tid = event->fork.tid;
+		sample->pid = event->fork.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+static int process_exit_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing EXIT event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	if (perf_event__process_exit(tool, event, sample, machine) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int process_mmap_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap.tid;
+		sample->pid = event->mmap.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
+static int process_mmap2_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP2 event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap2.tid;
+		sample->pid = event->mmap2.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -590,6 +772,17 @@ static int __cmd_script(struct perf_script *script)
 
 	signal(SIGINT, sig_handler);
 
+	/* override event processing functions */
+	if (script->show_task_events) {
+		script->tool.comm = process_comm_event;
+		script->tool.fork = process_fork_event;
+		script->tool.exit = process_exit_event;
+	}
+	if (script->show_mmap_events) {
+		script->tool.mmap = process_mmap_event;
+		script->tool.mmap2 = process_mmap2_event;
+	}
+
 	ret = perf_session__process_events(script->session, &script->tool);
 
 	if (debug_mode)
@@ -1352,6 +1545,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "display extended information from perf.data file"),
 	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
 		    "Show the path of [kernel.kallsyms]"),
+	OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
+		    "Show the fork/comm/exit events"),
+	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
+		    "Show the mmap events"),
 	OPT_END()
 	};
 	const char * const script_usage[] = {
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 41c9bde2..680632d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,6 +41,7 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
+static int proc_num = 15;
 
 static unsigned int	numcpus;
 static u64		min_freq;	/* Lowest CPU frequency seen */
@@ -50,16 +51,12 @@ static u64		turbo_frequency;
 static u64		first_time, last_time;
 
 static bool		power_only;
+static bool		tasks_only;
+static bool		with_backtrace;
 
 
-struct per_pid;
 struct per_pidcomm;
-
 struct cpu_sample;
-struct power_event;
-struct wake_event;
-
-struct sample_wrapper;
 
 /*
  * Datastructure layout:
@@ -124,6 +121,7 @@ struct cpu_sample {
 	u64 end_time;
 	int type;
 	int cpu;
+	const char *backtrace;
 };
 
 static struct per_pid *all_data;
@@ -145,12 +143,12 @@ struct wake_event {
 	int waker;
 	int wakee;
 	u64 time;
+	const char *backtrace;
 };
 
 static struct power_event    *power_events;
 static struct wake_event     *wake_events;
 
-struct process_filter;
 struct process_filter {
 	char			*name;
 	int			pid;
@@ -229,7 +227,8 @@ static void pid_exit(int pid, u64 timestamp)
 }
 
 static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
+pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end,
+	       const char *backtrace)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
@@ -252,6 +251,7 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
 	sample->type = type;
 	sample->next = c->samples;
 	sample->cpu = cpu;
+	sample->backtrace = backtrace;
 	c->samples = sample;
 
 	if (sample->type == TYPE_RUNNING && end > start && start > 0) {
@@ -299,50 +299,10 @@ static int process_exit_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-struct trace_entry {
-	unsigned short		type;
-	unsigned char		flags;
-	unsigned char		preempt_count;
-	int			pid;
-	int			lock_depth;
-};
-
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int use_old_power_events;
-struct power_entry_old {
-	struct trace_entry te;
-	u64	type;
-	u64	value;
-	u64	cpu_id;
-};
 #endif
 
-struct power_processor_entry {
-	struct trace_entry te;
-	u32	state;
-	u32	cpu_id;
-};
-
-#define TASK_COMM_LEN 16
-struct wakeup_entry {
-	struct trace_entry te;
-	char comm[TASK_COMM_LEN];
-	int   pid;
-	int   prio;
-	int   success;
-};
-
-struct sched_switch {
-	struct trace_entry te;
-	char prev_comm[TASK_COMM_LEN];
-	int  prev_pid;
-	int  prev_prio;
-	long prev_state; /* Arjan weeps. */
-	char next_comm[TASK_COMM_LEN];
-	int  next_pid;
-	int  next_prio;
-};
-
 static void c_state_start(int cpu, u64 timestamp, int state)
 {
 	cpus_cstate_start_times[cpu] = timestamp;
@@ -402,23 +362,23 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 			turbo_frequency = max_freq;
 }
 
-static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
+static void sched_wakeup(int cpu, u64 timestamp, int waker, int wakee,
+			 u8 flags, const char *backtrace)
 {
 	struct per_pid *p;
-	struct wakeup_entry *wake = (void *)te;
 	struct wake_event *we = zalloc(sizeof(*we));
 
 	if (!we)
 		return;
 
 	we->time = timestamp;
-	we->waker = pid;
+	we->waker = waker;
+	we->backtrace = backtrace;
 
-	if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
+	if ((flags & TRACE_FLAG_HARDIRQ) || (flags & TRACE_FLAG_SOFTIRQ))
 		we->waker = -1;
 
-	we->wakee = wake->pid;
+	we->wakee = wakee;
 	we->next = wake_events;
 	wake_events = we;
 	p = find_create_pid(we->wakee);
@@ -428,27 +388,31 @@ sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
 		p->current->state = TYPE_WAITING;
 	}
 	if (p && p->current && p->current->state == TYPE_BLOCKED) {
-		pid_put_sample(p->pid, p->current->state, cpu, p->current->state_since, timestamp);
+		pid_put_sample(p->pid, p->current->state, cpu,
+			       p->current->state_since, timestamp, NULL);
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 }
 
-static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
+static void sched_switch(int cpu, u64 timestamp, int prev_pid, int next_pid,
+			 u64 prev_state, const char *backtrace)
 {
 	struct per_pid *p = NULL, *prev_p;
-	struct sched_switch *sw = (void *)te;
 
+	prev_p = find_create_pid(prev_pid);
 
-	prev_p = find_create_pid(sw->prev_pid);
-
-	p = find_create_pid(sw->next_pid);
+	p = find_create_pid(next_pid);
 
 	if (prev_p->current && prev_p->current->state != TYPE_NONE)
-		pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu, prev_p->current->state_since, timestamp);
+		pid_put_sample(prev_pid, TYPE_RUNNING, cpu,
+			       prev_p->current->state_since, timestamp,
+			       backtrace);
 	if (p && p->current) {
 		if (p->current->state != TYPE_NONE)
-			pid_put_sample(sw->next_pid, p->current->state, cpu, p->current->state_since, timestamp);
+			pid_put_sample(next_pid, p->current->state, cpu,
+				       p->current->state_since, timestamp,
+				       backtrace);
 
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_RUNNING;
@@ -457,18 +421,97 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 	if (prev_p->current) {
 		prev_p->current->state = TYPE_NONE;
 		prev_p->current->state_since = timestamp;
-		if (sw->prev_state & 2)
+		if (prev_state & 2)
 			prev_p->current->state = TYPE_BLOCKED;
-		if (sw->prev_state == 0)
+		if (prev_state == 0)
 			prev_p->current->state = TYPE_WAITING;
 	}
 }
 
+static const char *cat_backtrace(union perf_event *event,
+				 struct perf_sample *sample,
+				 struct machine *machine)
+{
+	struct addr_location al;
+	unsigned int i;
+	char *p = NULL;
+	size_t p_len;
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	struct addr_location tal;
+	struct ip_callchain *chain = sample->callchain;
+	FILE *f = open_memstream(&p, &p_len);
+
+	if (!f) {
+		perror("open_memstream error");
+		return NULL;
+	}
+
+	if (!chain)
+		goto exit;
+
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+			event->header.type);
+		goto exit;
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip;
+
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				free(p);
+				p = NULL;
+				goto exit;
+			}
+			continue;
+		}
+
+		tal.filtered = false;
+		thread__find_addr_location(al.thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &tal);
+
+		if (tal.sym)
+			fprintf(f, "..... %016" PRIx64 " %s\n", ip,
+				tal.sym->name);
+		else
+			fprintf(f, "..... %016" PRIx64 "\n", ip);
+	}
+
+exit:
+	fclose(f);
+
+	return p;
+}
+
 typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
-				  struct perf_sample *sample);
+				  struct perf_sample *sample,
+				  const char *backtrace);
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
+				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
 				struct machine *machine __maybe_unused)
@@ -485,81 +528,97 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		return f(evsel, sample, cat_backtrace(event, sample, machine));
 	}
 
 	return 0;
 }
 
 static int
-process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
-			struct perf_sample *sample)
+process_sample_cpu_idle(struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			const char *backtrace __maybe_unused)
 {
-	struct power_processor_entry *ppe = sample->raw_data;
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	if (ppe->state == (u32) PWR_EVENT_EXIT)
-		c_state_end(ppe->cpu_id, sample->time);
+	if (state == (u32)PWR_EVENT_EXIT)
+		c_state_end(cpu_id, sample->time);
 	else
-		c_state_start(ppe->cpu_id, sample->time, ppe->state);
+		c_state_start(cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
-			     struct perf_sample *sample)
+process_sample_cpu_frequency(struct perf_evsel *evsel,
+			     struct perf_sample *sample,
+			     const char *backtrace __maybe_unused)
 {
-	struct power_processor_entry *ppe = sample->raw_data;
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	p_state_change(ppe->cpu_id, sample->time, ppe->state);
+	p_state_change(cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
-			    struct perf_sample *sample)
+process_sample_sched_wakeup(struct perf_evsel *evsel,
+			    struct perf_sample *sample,
+			    const char *backtrace)
 {
-	struct trace_entry *te = sample->raw_data;
+	u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
+	int waker = perf_evsel__intval(evsel, sample, "common_pid");
+	int wakee = perf_evsel__intval(evsel, sample, "pid");
 
-	sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+	sched_wakeup(sample->cpu, sample->time, waker, wakee, flags, backtrace);
 	return 0;
 }
 
 static int
-process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
-			    struct perf_sample *sample)
+process_sample_sched_switch(struct perf_evsel *evsel,
+			    struct perf_sample *sample,
+			    const char *backtrace)
 {
-	struct trace_entry *te = sample->raw_data;
+	int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
+	int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 
-	sched_switch(sample->cpu, sample->time, te);
+	sched_switch(sample->cpu, sample->time, prev_pid, next_pid, prev_state,
+		     backtrace);
 	return 0;
 }
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int
-process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
-			   struct perf_sample *sample)
+process_sample_power_start(struct perf_evsel *evsel,
+			   struct perf_sample *sample,
+			   const char *backtrace __maybe_unused)
 {
-	struct power_entry_old *peo = sample->raw_data;
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	c_state_start(peo->cpu_id, sample->time, peo->value);
+	c_state_start(cpu_id, sample->time, value);
 	return 0;
 }
 
 static int
 process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
-			 struct perf_sample *sample)
+			 struct perf_sample *sample,
+			 const char *backtrace __maybe_unused)
 {
 	c_state_end(sample->cpu, sample->time);
 	return 0;
 }
 
 static int
-process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
-			       struct perf_sample *sample)
+process_sample_power_frequency(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       const char *backtrace __maybe_unused)
 {
-	struct power_entry_old *peo = sample->raw_data;
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	p_state_change(peo->cpu_id, sample->time, peo->value);
+	p_state_change(cpu_id, sample->time, value);
 	return 0;
 }
 #endif /* SUPPORT_OLD_POWER_EVENTS */
@@ -739,11 +798,12 @@ static void draw_wakeups(void)
 		}
 
 		if (we->waker == -1)
-			svg_interrupt(we->time, to);
+			svg_interrupt(we->time, to, we->backtrace);
 		else if (from && to && abs(from - to) == 1)
-			svg_wakeline(we->time, from, to);
+			svg_wakeline(we->time, from, to, we->backtrace);
 		else
-			svg_partial_wakeline(we->time, from, task_from, to, task_to);
+			svg_partial_wakeline(we->time, from, task_from, to,
+					     task_to, we->backtrace);
 		we = we->next;
 
 		free(task_from);
@@ -796,11 +856,20 @@ static void draw_process_bars(void)
 			sample = c->samples;
 			while (sample) {
 				if (sample->type == TYPE_RUNNING)
-					svg_sample(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_running(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_BLOCKED)
-					svg_box(Y, sample->start_time, sample->end_time, "blocked");
+					svg_blocked(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_WAITING)
-					svg_waiting(Y, sample->start_time, sample->end_time);
+					svg_waiting(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				sample = sample->next;
 			}
 
@@ -911,7 +980,7 @@ static int determine_display_tasks(u64 threshold)
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
 			p->end_time = last_time;
-		if (p->total_time >= threshold && !power_only)
+		if (p->total_time >= threshold)
 			p->display = 1;
 
 		c = p->all;
@@ -922,7 +991,7 @@ static int determine_display_tasks(u64 threshold)
 			if (c->start_time == 1)
 				c->start_time = first_time;
 
-			if (c->total_time >= threshold && !power_only) {
+			if (c->total_time >= threshold) {
 				c->display = 1;
 				count++;
 			}
@@ -945,15 +1014,19 @@ static void write_svg_file(const char *filename)
 {
 	u64 i;
 	int count;
+	int thresh = TIME_THRESH;
 
 	numcpus++;
 
+	if (power_only)
+		proc_num = 0;
 
-	count = determine_display_tasks(TIME_THRESH);
-
-	/* We'd like to show at least 15 tasks; be less picky if we have fewer */
-	if (count < 15)
-		count = determine_display_tasks(TIME_THRESH / 10);
+	/* We'd like to show at least proc_num tasks;
+	 * be less picky if we have fewer */
+	do {
+		count = determine_display_tasks(thresh);
+		thresh /= 10;
+	} while (!process_filter && thresh && count < proc_num);
 
 	open_svg(filename, numcpus, count, first_time, last_time);
 
@@ -964,9 +1037,12 @@ static void write_svg_file(const char *filename)
 		svg_cpu_box(i, max_freq, turbo_frequency);
 
 	draw_cpu_usage();
-	draw_process_bars();
-	draw_c_p_states();
-	draw_wakeups();
+	if (proc_num)
+		draw_process_bars();
+	if (!tasks_only)
+		draw_c_p_states();
+	if (proc_num)
+		draw_wakeups();
 
 	svg_close();
 }
@@ -1031,50 +1107,92 @@ out_delete:
 
 static int __cmd_record(int argc, const char **argv)
 {
-#ifdef SUPPORT_OLD_POWER_EVENTS
-	const char * const record_old_args[] = {
+	unsigned int rec_argc, i, j;
+	const char **rec_argv;
+	const char **p;
+	unsigned int record_elems;
+
+	const char * const common_args[] = {
 		"record", "-a", "-R", "-c", "1",
+	};
+	unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+	const char * const backtrace_args[] = {
+		"-g",
+	};
+	unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
+
+	const char * const power_args[] = {
+		"-e", "power:cpu_frequency",
+		"-e", "power:cpu_idle",
+	};
+	unsigned int power_args_nr = ARRAY_SIZE(power_args);
+
+	const char * const old_power_args[] = {
+#ifdef SUPPORT_OLD_POWER_EVENTS
 		"-e", "power:power_start",
 		"-e", "power:power_end",
 		"-e", "power:power_frequency",
-		"-e", "sched:sched_wakeup",
-		"-e", "sched:sched_switch",
-	};
 #endif
-	const char * const record_new_args[] = {
-		"record", "-a", "-R", "-c", "1",
-		"-e", "power:cpu_frequency",
-		"-e", "power:cpu_idle",
+	};
+	unsigned int old_power_args_nr = ARRAY_SIZE(old_power_args);
+
+	const char * const tasks_args[] = {
 		"-e", "sched:sched_wakeup",
 		"-e", "sched:sched_switch",
 	};
-	unsigned int rec_argc, i, j;
-	const char **rec_argv;
-	const char * const *record_args = record_new_args;
-	unsigned int record_elems = ARRAY_SIZE(record_new_args);
+	unsigned int tasks_args_nr = ARRAY_SIZE(tasks_args);
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 	if (!is_valid_tracepoint("power:cpu_idle") &&
 	    is_valid_tracepoint("power:power_start")) {
 		use_old_power_events = 1;
-		record_args = record_old_args;
-		record_elems = ARRAY_SIZE(record_old_args);
+		power_args_nr = 0;
+	} else {
+		old_power_args_nr = 0;
 	}
 #endif
 
-	rec_argc = record_elems + argc - 1;
+	if (power_only)
+		tasks_args_nr = 0;
+
+	if (tasks_only) {
+		power_args_nr = 0;
+		old_power_args_nr = 0;
+	}
+
+	if (!with_backtrace)
+		backtrace_args_no = 0;
+
+	record_elems = common_args_nr + tasks_args_nr +
+		power_args_nr + old_power_args_nr + backtrace_args_no;
+
+	rec_argc = record_elems + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
 		return -ENOMEM;
 
-	for (i = 0; i < record_elems; i++)
-		rec_argv[i] = strdup(record_args[i]);
+	p = rec_argv;
+	for (i = 0; i < common_args_nr; i++)
+		*p++ = strdup(common_args[i]);
 
-	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	for (i = 0; i < backtrace_args_no; i++)
+		*p++ = strdup(backtrace_args[i]);
 
-	return cmd_record(i, rec_argv, NULL);
+	for (i = 0; i < tasks_args_nr; i++)
+		*p++ = strdup(tasks_args[i]);
+
+	for (i = 0; i < power_args_nr; i++)
+		*p++ = strdup(power_args[i]);
+
+	for (i = 0; i < old_power_args_nr; i++)
+		*p++ = strdup(old_power_args[i]);
+
+	for (j = 1; j < (unsigned int)argc; j++)
+		*p++ = argv[j];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
 }
 
 static int
@@ -1090,16 +1208,20 @@ int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
 	const char *output_name = "output.svg";
-	const struct option options[] = {
+	const struct option timechart_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
 	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
+		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
+	OPT_INTEGER('n', "proc-num", &proc_num,
+		    "min. number of tasks to print"),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
@@ -1107,15 +1229,39 @@ int cmd_timechart(int argc, const char **argv,
 		NULL
 	};
 
-	argc = parse_options(argc, argv, options, timechart_usage,
+	const struct option record_options[] = {
+	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
+		    "output processes data only"),
+	OPT_BOOLEAN('g', "callchain", &with_backtrace, "record callchain"),
+	OPT_END()
+	};
+	const char * const record_usage[] = {
+		"perf timechart record [<options>]",
+		NULL
+	};
+	argc = parse_options(argc, argv, timechart_options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (power_only && tasks_only) {
+		pr_err("-P and -T options cannot be used at the same time.\n");
+		return -1;
+	}
+
 	symbol__init();
 
-	if (argc && !strncmp(argv[0], "rec", 3))
+	if (argc && !strncmp(argv[0], "rec", 3)) {
+		argc = parse_options(argc, argv, record_options, record_usage,
+				     PARSE_OPT_STOP_AT_NON_OPTION);
+
+		if (power_only && tasks_only) {
+			pr_err("-P and -T options cannot be used at the same time.\n");
+			return -1;
+		}
+
 		return __cmd_record(argc, argv);
-	else if (argc)
-		usage_with_options(timechart_usage, options);
+	} else if (argc)
+		usage_with_options(timechart_usage, timechart_options);
 
 	setup_pager();
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 71e6402..03d37a7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -634,26 +634,9 @@ repeat:
 	return NULL;
 }
 
-/* Tag samples to be skipped. */
-static const char *skip_symbols[] = {
-	"intel_idle",
-	"default_idle",
-	"native_safe_halt",
-	"cpu_idle",
-	"enter_idle",
-	"exit_idle",
-	"mwait_idle",
-	"mwait_idle_with_hints",
-	"poll_idle",
-	"ppc64_runlatch_off",
-	"pseries_dedicated_idle_sleep",
-	NULL
-};
-
 static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
 	const char *name = sym->name;
-	int i;
 
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the
@@ -671,12 +654,8 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	    strstr(name, "_text_end"))
 		return 1;
 
-	for (i = 0; skip_symbols[i]; i++) {
-		if (!strcmp(skip_symbols[i], name)) {
-			sym->ignore = true;
-			break;
-		}
-	}
+	if (symbol__is_idle(sym))
+		sym->ignore = true;
 
 	return 0;
 }
@@ -1084,7 +1063,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "dump the symbol table used for profiling"),
 	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
-	OPT_BOOLEAN('g', "group", &opts->group,
+	OPT_BOOLEAN(0, "group", &opts->group,
 			    "put the counters into a counter group"),
 	OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
 		    "child tasks do not inherit counters"),
@@ -1105,7 +1084,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		   " abort, in_tx, transaction"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+	OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
 			   NULL, "enables call-graph recording",
 			   &callchain_opt),
 	OPT_CALLBACK(0, "call-graph", &top.record_opts,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8be17fc..e9f345e2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2158,7 +2158,6 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	size_t printed = data->printed;
 	struct trace *trace = data->trace;
 	struct thread_trace *ttrace = thread->priv;
-	const char *color;
 	double ratio;
 
 	if (ttrace == NULL)
@@ -2166,17 +2165,9 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 
 	ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
 
-	color = PERF_COLOR_NORMAL;
-	if (ratio > 50.0)
-		color = PERF_COLOR_RED;
-	else if (ratio > 25.0)
-		color = PERF_COLOR_GREEN;
-	else if (ratio > 5.0)
-		color = PERF_COLOR_YELLOW;
-
-	printed += color_fprintf(fp, color, " %s (%d), ", thread__comm_str(thread), thread->tid);
+	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
 	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
-	printed += color_fprintf(fp, color, "%.1f%%", ratio);
+	printed += fprintf(fp, "%.1f%%", ratio);
 	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
 	printed += thread__dump_stats(ttrace, trace, fp);
 
diff --git a/tools/perf/bash_completion b/tools/perf/perf-completion.sh
index 62e157db..4949488 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/perf-completion.sh
@@ -1,4 +1,4 @@
-# perf completion
+# perf bash and zsh completion
 
 # Taken from git.git's completion script.
 __my_reassemble_comp_words_by_ref()
@@ -89,37 +89,113 @@ __ltrim_colon_completions()
 	fi
 }
 
-type perf &>/dev/null &&
-_perf()
+__perfcomp ()
 {
-	local cur words cword prev cmd
+	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
+}
 
-	COMPREPLY=()
-	_get_comp_words_by_ref -n =: cur words cword prev
+__perfcomp_colon ()
+{
+	__perfcomp "$1" "$2"
+	__ltrim_colon_completions $cur
+}
+
+__perf_main ()
+{
+	local cmd
 
 	cmd=${words[0]}
+	COMPREPLY=()
 
 	# List perf subcommands or long options
 	if [ $cword -eq 1 ]; then
 		if [[ $cur == --* ]]; then
-			COMPREPLY=( $( compgen -W '--help --version \
+			__perfcomp '--help --version \
 			--exec-path --html-path --paginate --no-pager \
-			--perf-dir --work-tree --debugfs-dir' -- "$cur" ) )
+			--perf-dir --work-tree --debugfs-dir' -- "$cur"
 		else
 			cmds=$($cmd --list-cmds)
-			COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+			__perfcomp "$cmds" "$cur"
 		fi
 	# List possible events for -e option
 	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
 		evts=$($cmd list --raw-dump)
-		COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
-		__ltrim_colon_completions $cur
+		__perfcomp_colon "$evts" "$cur"
 	# List long option names
 	elif [[ $cur == --* ]];  then
 		subcmd=${words[1]}
 		opts=$($cmd $subcmd --list-opts)
-		COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
+		__perfcomp "$opts" "$cur"
 	fi
+}
+
+if [[ -n ${ZSH_VERSION-} ]]; then
+	autoload -U +X compinit && compinit
+
+	__perfcomp ()
+	{
+		emulate -L zsh
+
+		local c IFS=$' \t\n'
+		local -a array
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[${#array[@]}+1]="$c"
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	__perfcomp_colon ()
+	{
+		emulate -L zsh
+
+		local cur_="${2-$cur}"
+		local c IFS=$' \t\n'
+		local -a array
+
+		if [[ "$cur_" == *:* ]]; then
+			local colon_word=${cur_%"${cur_##*:}"}
+		fi
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[$#array+1]=${c#"$colon_word"}
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	_perf ()
+	{
+		local _ret=1 cur cword prev
+		cur=${words[CURRENT]}
+		prev=${words[CURRENT-1]}
+		let cword=CURRENT-1
+		emulate ksh -c __perf_main
+		let _ret && _default && _ret=0
+		return _ret
+	}
+
+	compdef _perf perf
+	return
+fi
+
+type perf &>/dev/null &&
+_perf()
+{
+	local cur words cword prev
+	_get_comp_words_by_ref -n =: cur words cword prev
+	__perf_main
 } &&
 
 complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b079304..b23fed5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -254,6 +254,7 @@ struct perf_record_opts {
 	bool	     inherit_stat;
 	bool	     no_delay;
 	bool	     no_inherit;
+	bool	     no_inherit_set;
 	bool	     no_samples;
 	bool	     raw_samples;
 	bool	     sample_address;
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 9079a25..44edcb2 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -3,5 +3,5 @@ command = record
 args    = -i kill >/dev/null 2>&1
 
 [event:base-record]
-sample_type=259
+sample_type=263
 inherit=0
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bb788c1..c77814b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -732,8 +732,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	if (thread == NULL)
 		return -1;
 
-	if (symbol_conf.comm_list &&
-	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread)))
+	if (thread__is_filtered(thread))
 		goto out_filtered;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bbc746a..76fa764 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -819,8 +819,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target->force_per_cpu)
-		evlist->cpus = cpu_map__new(target->cpu_list);
+	if (target->default_per_cpu)
+		evlist->cpus = target->per_thread ?
+					cpu_map__dummy_new() :
+					cpu_map__new(target->cpu_list);
 	else if (target__has_task(target))
 		evlist->cpus = cpu_map__dummy_new();
 	else if (!target__has_cpu(target) && !target->uses_mmap)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dad6492..b5fe7f9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -574,6 +574,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
+	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
@@ -647,7 +648,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		}
 	}
 
-	if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
+	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
@@ -655,7 +656,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target) || opts->target.force_per_cpu))
+	     target__has_cpu(&opts->target) || per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 31f404a..d22e3f80 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -78,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 
 	case OPTION_BOOLEAN:
 		*(bool *)opt->value = unset ? false : true;
+		if (opt->set)
+			*(bool *)opt->set = true;
 		return 0;
 
 	case OPTION_INCR:
@@ -224,6 +226,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
 			return 0;
 		}
 		if (!rest) {
+			if (!prefixcmp(options->long_name, "no-")) {
+				/*
+				 * The long name itself starts with "no-", so
+				 * accept the option without "no-" so that users
+				 * do not have to enter "no-no-" to get the
+				 * negation.
+				 */
+				rest = skip_prefix(arg, options->long_name + 3);
+				if (rest) {
+					flags |= OPT_UNSET;
+					goto match;
+				}
+				/* Abbreviated case */
+				if (!prefixcmp(options->long_name + 3, arg)) {
+					flags |= OPT_UNSET;
+					goto is_abbreviated;
+				}
+			}
 			/* abbreviated? */
 			if (!strncmp(options->long_name, arg, arg_end - arg)) {
 is_abbreviated:
@@ -259,6 +279,7 @@ is_abbreviated:
 			if (!rest)
 				continue;
 		}
+match:
 		if (*rest) {
 			if (*rest != '=')
 				continue;
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b0241e2..cbf0149 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
  *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
+ *
+ * `set`::
+ *   whether an option was set by the user
  */
 struct option {
 	enum parse_opt_type type;
@@ -94,6 +97,7 @@ struct option {
 	int flags;
 	parse_opt_cb *callback;
 	intptr_t defval;
+	bool *set;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -103,6 +107,10 @@ struct option {
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
 #define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
 #define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_BOOLEAN_SET(s, l, v, os, h) \
+	{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
+	.value = check_vtype(v, bool *), .help = (h), \
+	.set = check_vtype(os, bool *)}
 #define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f36d24a..b0b15e2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1522,6 +1522,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!node)
 				break;
 
+			if (node->sym && node->sym->ignore)
+				goto next;
+
 			if (print_ip)
 				printf("%c%16" PRIx64, s, node->ip);
 
@@ -1544,12 +1547,15 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!print_oneline)
 				printf("\n");
 
-			callchain_cursor_advance(&callchain_cursor);
-
 			stack_depth--;
+next:
+			callchain_cursor_advance(&callchain_cursor);
 		}
 
 	} else {
+		if (al.sym && al.sym->ignore)
+			return;
+
 		if (print_ip)
 			printf("%16" PRIx64, sample->ip);
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96c8660..8b79d3a 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -95,6 +95,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
 	total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
 	fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
+	fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n");
 	fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
 	fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
@@ -128,12 +129,33 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
-void svg_sample(int Yslot, int cpu, u64 start, u64 end)
+static char *time_to_string(u64 duration);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
+{
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
+		time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace);
+	svg_box(Yslot, start, end, "blocked");
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	double text_size;
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>#%d running %s</title>\n",
+		cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
 
@@ -148,6 +170,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end)
 		fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
 			time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *time_to_string(u64 duration)
@@ -168,7 +191,7 @@ static char *time_to_string(u64 duration)
 	return text;
 }
 
-void svg_waiting(int Yslot, u64 start, u64 end)
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	char *text;
 	const char *style;
@@ -192,6 +215,9 @@ void svg_waiting(int Yslot, u64 start, u64 end)
 	font_size = round_text_size(font_size);
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
@@ -242,6 +268,8 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	max_freq = __max_freq;
 	turbo_frequency = __turbo_freq;
 
+	fprintf(svgfile, "<g>\n");
+
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
 		time2pixels(first_time),
 		time2pixels(last_time)-time2pixels(first_time),
@@ -253,6 +281,8 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 
 	fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
@@ -264,6 +294,7 @@ void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name
 
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+	fprintf(svgfile, "<title>%s %s</title>\n", name, time_to_string(end - start));
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
@@ -288,6 +319,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
 	if (type > 6)
 		type = 6;
 	sprintf(style, "c%i", type);
@@ -306,6 +339,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 	if (width > MIN_TEXT_SIZE)
 		fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
 			time2pixels(start), cpu2y(cpu)+width, width, type);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *HzToHuman(unsigned long hz)
@@ -339,6 +374,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
 	if (max_freq)
 		height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
 	height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
@@ -347,10 +384,11 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
 		time2pixels(start), height+0.9, HzToHuman(freq));
 
+	fprintf(svgfile, "</g>\n");
 }
 
 
-void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2)
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace)
 {
 	double height;
 
@@ -358,6 +396,15 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>%s wakes up %s</title>\n",
+		desc1 ? desc1 : "?",
+		desc2 ? desc2 : "?");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2) {
 		if (row1) {
 			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
@@ -395,9 +442,11 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	if (row1)
 		fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_wakeline(u64 start, int row1, int row2)
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 {
 	double height;
 
@@ -405,6 +454,11 @@ void svg_wakeline(u64 start, int row1, int row2)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2)
 		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
@@ -417,17 +471,28 @@ void svg_wakeline(u64 start, int row1, int row2)
 		height += SLOT_HEIGHT;
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_interrupt(u64 start, int row)
+void svg_interrupt(u64 start, int row, const char *backtrace)
 {
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_text(int Yslot, u64 start, const char *text)
@@ -455,6 +520,7 @@ void svg_legenda(void)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
 	svg_legenda_box(0,	"Running", "sample");
 	svg_legenda_box(100,	"Idle","c1");
 	svg_legenda_box(200,	"Deeper Idle", "c3");
@@ -462,6 +528,7 @@ void svg_legenda(void)
 	svg_legenda_box(550,	"Sleeping", "process2");
 	svg_legenda_box(650,	"Waiting for cpu", "waiting");
 	svg_legenda_box(800,	"Blocked on IO", "blocked");
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_time_grid(void)
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e078198..fad79ce 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -5,8 +5,9 @@
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_sample(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_waiting(int Yslot, u64 start, u64 end);
+extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
@@ -17,9 +18,9 @@ extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 extern void svg_time_grid(void);
 extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2);
-extern void svg_interrupt(u64 start, int row);
+extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+extern void svg_interrupt(u64 start, int row, const char *backtrace);
 extern void svg_text(int Yslot, u64 start, const char *text);
 extern void svg_close(void);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c0c3696..360eefe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -573,6 +573,36 @@ static u8 kallsyms2elf_type(char type)
 	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
 }
 
+bool symbol__is_idle(struct symbol *sym)
+{
+	const char * const idle_symbols[] = {
+		"cpu_idle",
+		"intel_idle",
+		"default_idle",
+		"native_safe_halt",
+		"enter_idle",
+		"exit_idle",
+		"mwait_idle",
+		"mwait_idle_with_hints",
+		"poll_idle",
+		"ppc64_runlatch_off",
+		"pseries_dedicated_idle_sleep",
+		NULL
+	};
+
+	int i;
+
+	if (!sym)
+		return false;
+
+	for (i = 0; idle_symbols[i]; i++) {
+		if (!strcmp(idle_symbols[i], sym->name))
+			return true;
+	}
+
+	return false;
+}
+
 static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {
@@ -1496,14 +1526,15 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
+	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
+		  sbuild_id);
+
 	/* Use /proc/kallsyms if possible */
 	if (is_host) {
 		DIR *d;
 		int fd;
 
 		/* If no cached kcore go with /proc/kallsyms */
-		scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
-			  buildid_dir, sbuild_id);
 		d = opendir(path);
 		if (!d)
 			goto proc_kallsyms;
@@ -1528,6 +1559,10 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 		goto proc_kallsyms;
 	}
 
+	/* Find kallsyms in build-id cache with kcore */
+	if (!find_matching_kcore(map, path, sizeof(path)))
+		return strdup(path);
+
 	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
 		  buildid_dir, sbuild_id);
 
@@ -1719,7 +1754,7 @@ out_fail:
 	return -1;
 }
 
-static int setup_list(struct strlist **list, const char *list_str,
+int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
 	if (list_str == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 07de8fe..f1031a1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -240,6 +240,7 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
+bool symbol__is_idle(struct symbol *sym);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
@@ -273,4 +274,7 @@ void kcore_extract__delete(struct kcore_extract *kce);
 int kcore_copy(const char *from_dir, const char *to_dir);
 int compare_proc_modules(const char *from, const char *to);
 
+int setup_list(struct strlist **list, const char *list_str,
+	       const char *list_name);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3c778a0..e74c596 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
 			ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
 	}
 
+	/* THREAD and SYSTEM/CPU are mutually exclusive */
+	if (target->per_thread && (target->system_wide || target->cpu_list)) {
+		target->per_thread = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+	}
+
 	return ret;
 }
 
@@ -100,6 +107,7 @@ static const char *target__error_str[] = {
 	"UID switch overriding CPU",
 	"PID/TID switch overriding SYSTEM",
 	"UID switch overriding SYSTEM",
+	"SYSTEM/CPU switch overriding PER-THREAD",
 	"Invalid User: %s",
 	"Problems obtaining information for user %s",
 };
@@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
 	msg = target__error_str[idx];
 
 	switch (errnum) {
-	case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
+	case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+	     TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
 		snprintf(buf, buflen, "%s", msg);
 		break;
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 2d0c506..31dd2e9 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,7 +12,8 @@ struct target {
 	uid_t	     uid;
 	bool	     system_wide;
 	bool	     uses_mmap;
-	bool	     force_per_cpu;
+	bool	     default_per_cpu;
+	bool	     per_thread;
 };
 
 enum target_errno {
@@ -33,6 +34,7 @@ enum target_errno {
 	TARGET_ERRNO__UID_OVERRIDE_CPU,
 	TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
 	TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
+	TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
 
 	/* for target__parse_uid() */
 	TARGET_ERRNO__INVALID_UID,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 897c1b2..5b856bf 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include "symbol.h"
+#include <strlist.h>
 
 struct thread {
 	union {
@@ -66,4 +67,15 @@ static inline void thread__set_priv(struct thread *thread, void *p)
 {
 	thread->priv = p;
 }
+
+static inline bool thread__is_filtered(struct thread *thread)
+{
+	if (symbol_conf.comm_list &&
+	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
+		return true;
+	}
+
+	return false;
+}
+
 #endif	/* __PERF_THREAD_H */