1 files changed, 491 insertions, 264 deletions

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 41c9bde2fb6..25526d6eae5 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,25 +41,29 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
-
-static unsigned int	numcpus;
-static u64		min_freq;	/* Lowest CPU frequency seen */
-static u64		max_freq;	/* Highest CPU frequency seen */
-static u64		turbo_frequency;
-
-static u64		first_time, last_time;
-
-static bool		power_only;
-
-
 struct per_pid;
-struct per_pidcomm;
-
-struct cpu_sample;
 struct power_event;
 struct wake_event;
 
-struct sample_wrapper;
+struct timechart {
+	struct perf_tool	tool;
+	struct per_pid		*all_data;
+	struct power_event	*power_events;
+	struct wake_event	*wake_events;
+	int			proc_num;
+	unsigned int		numcpus;
+	u64			min_freq,	/* Lowest CPU frequency seen */
+				max_freq,	/* Highest CPU frequency seen */
+				turbo_frequency,
+				first_time, last_time;
+	bool			power_only,
+				tasks_only,
+				with_backtrace,
+				topology;
+};
+
+struct per_pidcomm;
+struct cpu_sample;
 
 /*
  * Datastructure layout:
@@ -124,10 +128,9 @@ struct cpu_sample {
 	u64 end_time;
 	int type;
 	int cpu;
+	const char *backtrace;
 };
 
-static struct per_pid *all_data;
-
 #define CSTATE 1
 #define PSTATE 2
 
@@ -145,12 +148,9 @@ 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;
@@ -160,9 +160,9 @@ struct process_filter {
 static struct process_filter *process_filter;
 
 
-static struct per_pid *find_create_pid(int pid)
+static struct per_pid *find_create_pid(struct timechart *tchart, int pid)
 {
-	struct per_pid *cursor = all_data;
+	struct per_pid *cursor = tchart->all_data;
 
 	while (cursor) {
 		if (cursor->pid == pid)
@@ -172,16 +172,16 @@ static struct per_pid *find_create_pid(int pid)
 	cursor = zalloc(sizeof(*cursor));
 	assert(cursor != NULL);
 	cursor->pid = pid;
-	cursor->next = all_data;
-	all_data = cursor;
+	cursor->next = tchart->all_data;
+	tchart->all_data = cursor;
 	return cursor;
 }
 
-static void pid_set_comm(int pid, char *comm)
+static void pid_set_comm(struct timechart *tchart, int pid, char *comm)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->all;
 	while (c) {
 		if (c->comm && strcmp(c->comm, comm) == 0) {
@@ -203,14 +203,14 @@ static void pid_set_comm(int pid, char *comm)
 	p->all = c;
 }
 
-static void pid_fork(int pid, int ppid, u64 timestamp)
+static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 {
 	struct per_pid *p, *pp;
-	p = find_create_pid(pid);
-	pp = find_create_pid(ppid);
+	p = find_create_pid(tchart, pid);
+	pp = find_create_pid(tchart, ppid);
 	p->ppid = ppid;
 	if (pp->current && pp->current->comm && !p->current)
-		pid_set_comm(pid, pp->current->comm);
+		pid_set_comm(tchart, pid, pp->current->comm);
 
 	p->start_time = timestamp;
 	if (p->current) {
@@ -219,23 +219,24 @@ static void pid_fork(int pid, int ppid, u64 timestamp)
 	}
 }
 
-static void pid_exit(int pid, u64 timestamp)
+static void pid_exit(struct timechart *tchart, int pid, u64 timestamp)
 {
 	struct per_pid *p;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	p->end_time = timestamp;
 	if (p->current)
 		p->current->end_time = timestamp;
 }
 
-static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
+static void pid_put_sample(struct timechart *tchart, int pid, int type,
+			   unsigned int cpu, u64 start, u64 end,
+			   const char *backtrace)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->current;
 	if (!c) {
 		c = zalloc(sizeof(*c));
@@ -252,6 +253,7 @@ 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) {
@@ -272,84 +274,47 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(struct perf_tool *tool __maybe_unused,
+static int process_comm_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_set_comm(event->comm.tid, event->comm.comm);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_set_comm(tchart, event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(struct perf_tool *tool __maybe_unused,
+static int process_fork_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_fork(tchart, event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(struct perf_tool *tool __maybe_unused,
+static int process_exit_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_exit(event->fork.pid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_exit(tchart, event->fork.pid, event->fork.time);
 	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;
 	cpus_cstate_state[cpu] = state;
 }
 
-static void c_state_end(int cpu, u64 timestamp)
+static void c_state_end(struct timechart *tchart, int cpu, u64 timestamp)
 {
 	struct power_event *pwr = zalloc(sizeof(*pwr));
 
@@ -361,12 +326,12 @@ static void c_state_end(int cpu, u64 timestamp)
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = CSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 }
 
-static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
+static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64 new_freq)
 {
 	struct power_event *pwr;
 
@@ -382,73 +347,78 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = PSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
 	if (!pwr->start_time)
-		pwr->start_time = first_time;
+		pwr->start_time = tchart->first_time;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 
 	cpus_pstate_state[cpu] = new_freq;
 	cpus_pstate_start_times[cpu] = timestamp;
 
-	if ((u64)new_freq > max_freq)
-		max_freq = new_freq;
+	if ((u64)new_freq > tchart->max_freq)
+		tchart->max_freq = new_freq;
 
-	if (new_freq < min_freq || min_freq == 0)
-		min_freq = new_freq;
+	if (new_freq < tchart->min_freq || tchart->min_freq == 0)
+		tchart->min_freq = new_freq;
 
-	if (new_freq == max_freq - 1000)
-			turbo_frequency = max_freq;
+	if (new_freq == tchart->max_freq - 1000)
+		tchart->turbo_frequency = tchart->max_freq;
 }
 
-static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
+static void sched_wakeup(struct timechart *tchart, 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->next = wake_events;
-	wake_events = we;
-	p = find_create_pid(we->wakee);
+	we->wakee = wakee;
+	we->next = tchart->wake_events;
+	tchart->wake_events = we;
+	p = find_create_pid(tchart, we->wakee);
 
 	if (p && p->current && p->current->state == TYPE_NONE) {
 		p->current->state_since = timestamp;
 		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(tchart, 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(struct timechart *tchart, 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(tchart, prev_pid);
 
-	prev_p = find_create_pid(sw->prev_pid);
-
-	p = find_create_pid(sw->next_pid);
+	p = find_create_pid(tchart, 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(tchart, 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(tchart, next_pid, p->current->state, cpu,
+				       p->current->state_since, timestamp,
+				       backtrace);
 
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_RUNNING;
@@ -457,109 +427,211 @@ 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;
 	}
 }
 
-typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
-				  struct perf_sample *sample);
+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.
+				 */
+				zfree(&p);
+				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 timechart *tchart,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  const char *backtrace);
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
-				struct machine *machine __maybe_unused)
+				struct machine *machine)
 {
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+
 	if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
-		if (!first_time || first_time > sample->time)
-			first_time = sample->time;
-		if (last_time < sample->time)
-			last_time = sample->time;
+		if (!tchart->first_time || tchart->first_time > sample->time)
+			tchart->first_time = sample->time;
+		if (tchart->last_time < sample->time)
+			tchart->last_time = sample->time;
 	}
 
-	if (sample->cpu > numcpus)
-		numcpus = sample->cpu;
-
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		return f(tchart, 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 timechart *tchart __maybe_unused,
+			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(tchart, 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 timechart *tchart,
+			     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(tchart, 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 timechart *tchart,
+			    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(tchart, 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 timechart *tchart,
+			    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(tchart, 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 timechart *tchart __maybe_unused,
+			   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)
+process_sample_power_end(struct timechart *tchart,
+			 struct perf_evsel *evsel __maybe_unused,
+			 struct perf_sample *sample,
+			 const char *backtrace __maybe_unused)
 {
-	c_state_end(sample->cpu, sample->time);
+	c_state_end(tchart, 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 timechart *tchart,
+			       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(tchart, cpu_id, sample->time, value);
 	return 0;
 }
 #endif /* SUPPORT_OLD_POWER_EVENTS */
@@ -568,12 +640,12 @@ process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
  */
-static void end_sample_processing(void)
+static void end_sample_processing(struct timechart *tchart)
 {
 	u64 cpu;
 	struct power_event *pwr;
 
-	for (cpu = 0; cpu <= numcpus; cpu++) {
+	for (cpu = 0; cpu <= tchart->numcpus; cpu++) {
 		/* C state */
 #if 0
 		pwr = zalloc(sizeof(*pwr));
@@ -582,12 +654,12 @@ static void end_sample_processing(void)
 
 		pwr->state = cpus_cstate_state[cpu];
 		pwr->start_time = cpus_cstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = CSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
-		power_events = pwr;
+		tchart->power_events = pwr;
 #endif
 		/* P state */
 
@@ -597,32 +669,32 @@ static void end_sample_processing(void)
 
 		pwr->state = cpus_pstate_state[cpu];
 		pwr->start_time = cpus_pstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = PSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
 		if (!pwr->start_time)
-			pwr->start_time = first_time;
+			pwr->start_time = tchart->first_time;
 		if (!pwr->state)
-			pwr->state = min_freq;
-		power_events = pwr;
+			pwr->state = tchart->min_freq;
+		tchart->power_events = pwr;
 	}
 }
 
 /*
  * Sort the pid datastructure
  */
-static void sort_pids(void)
+static void sort_pids(struct timechart *tchart)
 {
 	struct per_pid *new_list, *p, *cursor, *prev;
 	/* sort by ppid first, then by pid, lowest to highest */
 
 	new_list = NULL;
 
-	while (all_data) {
-		p = all_data;
-		all_data = p->next;
+	while (tchart->all_data) {
+		p = tchart->all_data;
+		tchart->all_data = p->next;
 		p->next = NULL;
 
 		if (new_list == NULL) {
@@ -655,14 +727,14 @@ static void sort_pids(void)
 				prev->next = p;
 		}
 	}
-	all_data = new_list;
+	tchart->all_data = new_list;
 }
 
 
-static void draw_c_p_states(void)
+static void draw_c_p_states(struct timechart *tchart)
 {
 	struct power_event *pwr;
-	pwr = power_events;
+	pwr = tchart->power_events;
 
 	/*
 	 * two pass drawing so that the P state bars are on top of the C state blocks
@@ -673,30 +745,30 @@ static void draw_c_p_states(void)
 		pwr = pwr->next;
 	}
 
-	pwr = power_events;
+	pwr = tchart->power_events;
 	while (pwr) {
 		if (pwr->type == PSTATE) {
 			if (!pwr->state)
-				pwr->state = min_freq;
+				pwr->state = tchart->min_freq;
 			svg_pstate(pwr->cpu, pwr->start_time, pwr->end_time, pwr->state);
 		}
 		pwr = pwr->next;
 	}
 }
 
-static void draw_wakeups(void)
+static void draw_wakeups(struct timechart *tchart)
 {
 	struct wake_event *we;
 	struct per_pid *p;
 	struct per_pidcomm *c;
 
-	we = wake_events;
+	we = tchart->wake_events;
 	while (we) {
 		int from = 0, to = 0;
 		char *task_from = NULL, *task_to = NULL;
 
 		/* locate the column of the waker and wakee */
-		p = all_data;
+		p = tchart->all_data;
 		while (p) {
 			if (p->pid == we->waker || p->pid == we->wakee) {
 				c = p->all;
@@ -739,11 +811,12 @@ 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);
@@ -751,19 +824,25 @@ static void draw_wakeups(void)
 	}
 }
 
-static void draw_cpu_usage(void)
+static void draw_cpu_usage(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
 			sample = c->samples;
 			while (sample) {
-				if (sample->type == TYPE_RUNNING)
-					svg_process(sample->cpu, sample->start_time, sample->end_time, "sample", c->comm);
+				if (sample->type == TYPE_RUNNING) {
+					svg_process(sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    p->pid,
+						    c->comm,
+						    sample->backtrace);
+				}
 
 				sample = sample->next;
 			}
@@ -773,16 +852,16 @@ static void draw_cpu_usage(void)
 	}
 }
 
-static void draw_process_bars(void)
+static void draw_process_bars(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 	int Y = 0;
 
-	Y = 2 * numcpus + 2;
+	Y = 2 * tchart->numcpus + 2;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
@@ -796,11 +875,20 @@ 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;
 			}
 
@@ -853,21 +941,21 @@ static int passes_filter(struct per_pid *p, struct per_pidcomm *c)
 	return 0;
 }
 
-static int determine_display_tasks_filtered(void)
+static int determine_display_tasks_filtered(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
+			p->end_time = tchart->last_time;
 
 		c = p->all;
 
@@ -875,7 +963,7 @@ static int determine_display_tasks_filtered(void)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
 			if (passes_filter(p, c)) {
 				c->display = 1;
@@ -884,7 +972,7 @@ static int determine_display_tasks_filtered(void)
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -893,25 +981,25 @@ static int determine_display_tasks_filtered(void)
 	return count;
 }
 
-static int determine_display_tasks(u64 threshold)
+static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
 	if (process_filter)
-		return determine_display_tasks_filtered();
+		return determine_display_tasks_filtered(tchart);
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* 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)
+			p->end_time = tchart->last_time;
+		if (p->total_time >= threshold)
 			p->display = 1;
 
 		c = p->all;
@@ -920,15 +1008,15 @@ static int determine_display_tasks(u64 threshold)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
-			if (c->total_time >= threshold && !power_only) {
+			if (c->total_time >= threshold) {
 				c->display = 1;
 				count++;
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -941,45 +1029,77 @@ static int determine_display_tasks(u64 threshold)
 
 #define TIME_THRESH 10000000
 
-static void write_svg_file(const char *filename)
+static void write_svg_file(struct timechart *tchart, const char *filename)
 {
 	u64 i;
 	int count;
+	int thresh = TIME_THRESH;
 
-	numcpus++;
+	if (tchart->power_only)
+		tchart->proc_num = 0;
 
+	/* We'd like to show at least proc_num tasks;
+	 * be less picky if we have fewer */
+	do {
+		count = determine_display_tasks(tchart, thresh);
+		thresh /= 10;
+	} while (!process_filter && thresh && count < tchart->proc_num);
 
-	count = determine_display_tasks(TIME_THRESH);
+	if (!tchart->proc_num)
+		count = 0;
 
-	/* 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);
-
-	open_svg(filename, numcpus, count, first_time, last_time);
+	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
 	svg_time_grid();
 	svg_legenda();
 
-	for (i = 0; i < numcpus; i++)
-		svg_cpu_box(i, max_freq, turbo_frequency);
+	for (i = 0; i < tchart->numcpus; i++)
+		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
 
-	draw_cpu_usage();
-	draw_process_bars();
-	draw_c_p_states();
-	draw_wakeups();
+	draw_cpu_usage(tchart);
+	if (tchart->proc_num)
+		draw_process_bars(tchart);
+	if (!tchart->tasks_only)
+		draw_c_p_states(tchart);
+	if (tchart->proc_num)
+		draw_wakeups(tchart);
 
 	svg_close();
 }
 
-static int __cmd_timechart(const char *output_name)
+static int process_header(struct perf_file_section *section __maybe_unused,
+			  struct perf_header *ph,
+			  int feat,
+			  int fd __maybe_unused,
+			  void *data)
+{
+	struct timechart *tchart = data;
+
+	switch (feat) {
+	case HEADER_NRCPUS:
+		tchart->numcpus = ph->env.nr_cpus_avail;
+		break;
+
+	case HEADER_CPU_TOPOLOGY:
+		if (!tchart->topology)
+			break;
+
+		if (svg_build_topology_map(ph->env.sibling_cores,
+					   ph->env.nr_sibling_cores,
+					   ph->env.sibling_threads,
+					   ph->env.nr_sibling_threads))
+			fprintf(stderr, "problem building topology\n");
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 {
-	struct perf_tool perf_timechart = {
-		.comm		 = process_comm_event,
-		.fork		 = process_fork_event,
-		.exit		 = process_exit_event,
-		.sample		 = process_sample_event,
-		.ordered_samples = true,
-	};
 	const struct perf_evsel_str_handler power_tracepoints[] = {
 		{ "power:cpu_idle",		process_sample_cpu_idle },
 		{ "power:cpu_frequency",	process_sample_cpu_frequency },
@@ -997,12 +1117,17 @@ static int __cmd_timechart(const char *output_name)
 	};
 
 	struct perf_session *session = perf_session__new(&file, false,
-							 &perf_timechart);
+							 &tchart->tool);
 	int ret = -EINVAL;
 
 	if (session == NULL)
 		return -ENOMEM;
 
+	(void)perf_header__process_sections(&session->header,
+					    perf_data_file__fd(session->file),
+					    tchart,
+					    process_header);
+
 	if (!perf_session__has_traces(session, "timechart record"))
 		goto out_delete;
 
@@ -1012,69 +1137,111 @@ static int __cmd_timechart(const char *output_name)
 		goto out_delete;
 	}
 
-	ret = perf_session__process_events(session, &perf_timechart);
+	ret = perf_session__process_events(session, &tchart->tool);
 	if (ret)
 		goto out_delete;
 
-	end_sample_processing();
+	end_sample_processing(tchart);
 
-	sort_pids();
+	sort_pids(tchart);
 
-	write_svg_file(output_name);
+	write_svg_file(tchart, output_name);
 
 	pr_info("Written %2.1f seconds of trace to %s.\n",
-		(last_time - first_time) / 1000000000.0, output_name);
+		(tchart->last_time - tchart->first_time) / 1000000000.0, output_name);
 out_delete:
 	perf_session__delete(session);
 	return ret;
 }
 
-static int __cmd_record(int argc, const char **argv)
+static int timechart__record(struct timechart *tchart, 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 (tchart->power_only)
+		tasks_args_nr = 0;
+
+	if (tchart->tasks_only) {
+		power_args_nr = 0;
+		old_power_args_nr = 0;
+	}
+
+	if (!tchart->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 (i = 0; i < backtrace_args_no; i++)
+		*p++ = strdup(backtrace_args[i]);
+
+	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 (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	for (i = 0; i < old_power_args_nr; i++)
+		*p++ = strdup(old_power_args[i]);
 
-	return cmd_record(i, rec_argv, NULL);
+	for (j = 1; j < (unsigned int)argc; j++)
+		*p++ = argv[j];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
 }
 
 static int
@@ -1086,20 +1253,56 @@ parse_process(const struct option *opt __maybe_unused, const char *arg,
 	return 0;
 }
 
+static int
+parse_highlight(const struct option *opt __maybe_unused, const char *arg,
+		int __maybe_unused unset)
+{
+	unsigned long duration = strtoul(arg, NULL, 0);
+
+	if (svg_highlight || svg_highlight_name)
+		return -1;
+
+	if (duration)
+		svg_highlight = duration;
+	else
+		svg_highlight_name = strdup(arg);
+
+	return 0;
+}
+
 int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
+	struct timechart tchart = {
+		.tool = {
+			.comm		 = process_comm_event,
+			.fork		 = process_fork_event,
+			.exit		 = process_exit_event,
+			.sample		 = process_sample_event,
+			.ordered_samples = true,
+		},
+		.proc_num = 15,
+	};
 	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_CALLBACK(0, "highlight", NULL, "duration or task name",
+		      "highlight tasks. Pass duration in ns or process name.",
+		       parse_highlight),
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.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", &tchart.proc_num,
+		    "min. number of tasks to print"),
+	OPT_BOOLEAN('t', "topology", &tchart.topology,
+		    "sort CPUs according to topology"),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
@@ -1107,17 +1310,41 @@ 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", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+		    "output processes data only"),
+	OPT_BOOLEAN('g', "callchain", &tchart.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 (tchart.power_only && tchart.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))
-		return __cmd_record(argc, argv);
-	else if (argc)
-		usage_with_options(timechart_usage, options);
+	if (argc && !strncmp(argv[0], "rec", 3)) {
+		argc = parse_options(argc, argv, record_options, record_usage,
+				     PARSE_OPT_STOP_AT_NON_OPTION);
+
+		if (tchart.power_only && tchart.tasks_only) {
+			pr_err("-P and -T options cannot be used at the same time.\n");
+			return -1;
+		}
+
+		return timechart__record(&tchart, argc, argv);
+	} else if (argc)
+		usage_with_options(timechart_usage, timechart_options);
 
 	setup_pager();
 
-	return __cmd_timechart(output_name);
+	return __cmd_timechart(&tchart, output_name);
 }