Commit 75b5293a authored by Ingo Molnar's avatar Ingo Molnar
Browse files

Merge branch 'perf/core' of... 

Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core
parents 10a18d7d ce47dc56

include/linux/perf_event.h

+12 −1
Original line number Diff line number Diff line
@@ -215,8 +215,9 @@ struct perf_event_attr { 
				 */

				precise_ip     :  2, /* skid constraint       */

				mmap_data      :  1, /* non-exec mmap data    */

				sample_id_all  :  1, /* sample_type all events */



				__reserved_1   : 46;

				__reserved_1   : 45;



	union {

		__u32		wakeup_events;	  /* wakeup every n events */
@@ -327,6 +328,15 @@ struct perf_event_header { 
enum perf_event_type {



	/*

	 * If perf_event_attr.sample_id_all is set then all event types will

	 * have the sample_type selected fields related to where/when

	 * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)

	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after

	 * the perf_event_header and the fields already present for the existing

	 * fields, i.e. at the end of the payload. That way a newer perf.data

	 * file will be supported by older perf tools, with these new optional

	 * fields being ignored.

	 *

	 * The MMAP events record the PROT_EXEC mappings so that we can

	 * correlate userspace IPs to code. They have the following structure:

	 *
@@ -759,6 +769,7 @@ struct perf_event { 


	struct perf_event_attr		attr;

	u16				header_size;

	u16				id_header_size;

	u16				read_size;

	struct hw_perf_event		hw;

kernel/perf_event.c

+167 −67
Original line number Diff line number Diff line
@@ -133,6 +133,28 @@ static void unclone_ctx(struct perf_event_context *ctx) 
	}

}



static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)

{

	/*

	 * only top level events have the pid namespace they were created in

	 */

	if (event->parent)

		event = event->parent;



	return task_tgid_nr_ns(p, event->ns);

}



static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)

{

	/*

	 * only top level events have the pid namespace they were created in

	 */

	if (event->parent)

		event = event->parent;



	return task_pid_nr_ns(p, event->ns);

}



/*

 * If we inherit events we want to return the parent event id

 * to userspace.
@@ -351,15 +373,30 @@ static void perf_event__header_size(struct perf_event *event) 
	if (sample_type & PERF_SAMPLE_IP)

		size += sizeof(data->ip);



	if (sample_type & PERF_SAMPLE_ADDR)

		size += sizeof(data->addr);



	if (sample_type & PERF_SAMPLE_PERIOD)

		size += sizeof(data->period);



	if (sample_type & PERF_SAMPLE_READ)

		size += event->read_size;



	event->header_size = size;

}



static void perf_event__id_header_size(struct perf_event *event)

{

	struct perf_sample_data *data;

	u64 sample_type = event->attr.sample_type;

	u16 size = 0;



	if (sample_type & PERF_SAMPLE_TID)

		size += sizeof(data->tid_entry);



	if (sample_type & PERF_SAMPLE_TIME)

		size += sizeof(data->time);



	if (sample_type & PERF_SAMPLE_ADDR)

		size += sizeof(data->addr);



	if (sample_type & PERF_SAMPLE_ID)

		size += sizeof(data->id);
@@ -369,13 +406,7 @@ static void perf_event__header_size(struct perf_event *event) 
	if (sample_type & PERF_SAMPLE_CPU)

		size += sizeof(data->cpu_entry);



	if (sample_type & PERF_SAMPLE_PERIOD)

		size += sizeof(data->period);



	if (sample_type & PERF_SAMPLE_READ)

		size += event->read_size;



	event->header_size = size;

	event->id_header_size = size;

}



static void perf_group_attach(struct perf_event *event)
@@ -3357,6 +3388,73 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle, 
	} while (len);

}



static void __perf_event_header__init_id(struct perf_event_header *header,

					 struct perf_sample_data *data,

					 struct perf_event *event)

{

	u64 sample_type = event->attr.sample_type;



	data->type = sample_type;

	header->size += event->id_header_size;



	if (sample_type & PERF_SAMPLE_TID) {

		/* namespace issues */

		data->tid_entry.pid = perf_event_pid(event, current);

		data->tid_entry.tid = perf_event_tid(event, current);

	}



	if (sample_type & PERF_SAMPLE_TIME)

		data->time = perf_clock();



	if (sample_type & PERF_SAMPLE_ID)

		data->id = primary_event_id(event);



	if (sample_type & PERF_SAMPLE_STREAM_ID)

		data->stream_id = event->id;



	if (sample_type & PERF_SAMPLE_CPU) {

		data->cpu_entry.cpu	 = raw_smp_processor_id();

		data->cpu_entry.reserved = 0;

	}

}



static void perf_event_header__init_id(struct perf_event_header *header,

				       struct perf_sample_data *data,

				       struct perf_event *event)

{

	if (event->attr.sample_id_all)

		__perf_event_header__init_id(header, data, event);

}



static void __perf_event__output_id_sample(struct perf_output_handle *handle,

					   struct perf_sample_data *data)

{

	u64 sample_type = data->type;



	if (sample_type & PERF_SAMPLE_TID)

		perf_output_put(handle, data->tid_entry);



	if (sample_type & PERF_SAMPLE_TIME)

		perf_output_put(handle, data->time);



	if (sample_type & PERF_SAMPLE_ID)

		perf_output_put(handle, data->id);



	if (sample_type & PERF_SAMPLE_STREAM_ID)

		perf_output_put(handle, data->stream_id);



	if (sample_type & PERF_SAMPLE_CPU)

		perf_output_put(handle, data->cpu_entry);

}



static void perf_event__output_id_sample(struct perf_event *event,

					 struct perf_output_handle *handle,

					 struct perf_sample_data *sample)

{

	if (event->attr.sample_id_all)

		__perf_event__output_id_sample(handle, sample);

}



int perf_output_begin(struct perf_output_handle *handle,

		      struct perf_event *event, unsigned int size,

		      int nmi, int sample)
@@ -3364,6 +3462,7 @@ int perf_output_begin(struct perf_output_handle *handle, 
	struct perf_buffer *buffer;

	unsigned long tail, offset, head;

	int have_lost;

	struct perf_sample_data sample_data;

	struct {

		struct perf_event_header header;

		u64			 id;
@@ -3390,8 +3489,12 @@ int perf_output_begin(struct perf_output_handle *handle, 
		goto out;



	have_lost = local_read(&buffer->lost);

	if (have_lost)

		size += sizeof(lost_event);

	if (have_lost) {

		lost_event.header.size = sizeof(lost_event);

		perf_event_header__init_id(&lost_event.header, &sample_data,

					   event);

		size += lost_event.header.size;

	}



	perf_output_get_handle(handle);
@@ -3422,11 +3525,11 @@ int perf_output_begin(struct perf_output_handle *handle, 
	if (have_lost) {

		lost_event.header.type = PERF_RECORD_LOST;

		lost_event.header.misc = 0;

		lost_event.header.size = sizeof(lost_event);

		lost_event.id          = event->id;

		lost_event.lost        = local_xchg(&buffer->lost, 0);



		perf_output_put(handle, lost_event);

		perf_event__output_id_sample(event, handle, &sample_data);

	}



	return 0;
@@ -3459,28 +3562,6 @@ void perf_output_end(struct perf_output_handle *handle) 
	rcu_read_unlock();

}



static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)

{

	/*

	 * only top level events have the pid namespace they were created in

	 */

	if (event->parent)

		event = event->parent;



	return task_tgid_nr_ns(p, event->ns);

}



static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)

{

	/*

	 * only top level events have the pid namespace they were created in

	 */

	if (event->parent)

		event = event->parent;



	return task_pid_nr_ns(p, event->ns);

}



static void perf_output_read_one(struct perf_output_handle *handle,

				 struct perf_event *event,

				 u64 enabled, u64 running)
@@ -3655,37 +3736,17 @@ void perf_prepare_sample(struct perf_event_header *header, 
{

	u64 sample_type = event->attr.sample_type;



	data->type = sample_type;



	header->type = PERF_RECORD_SAMPLE;

	header->size = sizeof(*header) + event->header_size;



	header->misc = 0;

	header->misc |= perf_misc_flags(regs);



	__perf_event_header__init_id(header, data, event);



	if (sample_type & PERF_SAMPLE_IP)

		data->ip = perf_instruction_pointer(regs);



	if (sample_type & PERF_SAMPLE_TID) {

		/* namespace issues */

		data->tid_entry.pid = perf_event_pid(event, current);

		data->tid_entry.tid = perf_event_tid(event, current);

	}



	if (sample_type & PERF_SAMPLE_TIME)

		data->time = perf_clock();



	if (sample_type & PERF_SAMPLE_ID)

		data->id = primary_event_id(event);



	if (sample_type & PERF_SAMPLE_STREAM_ID)

		data->stream_id = event->id;



	if (sample_type & PERF_SAMPLE_CPU) {

		data->cpu_entry.cpu		= raw_smp_processor_id();

		data->cpu_entry.reserved	= 0;

	}



	if (sample_type & PERF_SAMPLE_CALLCHAIN) {

		int size = 1;
@@ -3749,6 +3810,7 @@ perf_event_read_event(struct perf_event *event, 
			struct task_struct *task)

{

	struct perf_output_handle handle;

	struct perf_sample_data sample;

	struct perf_read_event read_event = {

		.header = {

			.type = PERF_RECORD_READ,
@@ -3760,12 +3822,14 @@ perf_event_read_event(struct perf_event *event, 
	};

	int ret;



	perf_event_header__init_id(&read_event.header, &sample, event);

	ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);

	if (ret)

		return;



	perf_output_put(&handle, read_event);

	perf_output_read(&handle, event);

	perf_event__output_id_sample(event, &handle, &sample);



	perf_output_end(&handle);

}
@@ -3795,14 +3859,16 @@ static void perf_event_task_output(struct perf_event *event, 
				     struct perf_task_event *task_event)

{

	struct perf_output_handle handle;

	struct perf_sample_data	sample;

	struct task_struct *task = task_event->task;

	int size, ret;

	int ret, size = task_event->event_id.header.size;



	size  = task_event->event_id.header.size;

	ret = perf_output_begin(&handle, event, size, 0, 0);

	perf_event_header__init_id(&task_event->event_id.header, &sample, event);



	ret = perf_output_begin(&handle, event,

				task_event->event_id.header.size, 0, 0);

	if (ret)

		return;

		goto out;



	task_event->event_id.pid = perf_event_pid(event, task);

	task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3812,7 +3878,11 @@ static void perf_event_task_output(struct perf_event *event, 


	perf_output_put(&handle, task_event->event_id);



	perf_event__output_id_sample(event, &handle, &sample);



	perf_output_end(&handle);

out:

	task_event->event_id.header.size = size;

}



static int perf_event_task_match(struct perf_event *event)
@@ -3925,11 +3995,16 @@ static void perf_event_comm_output(struct perf_event *event, 
				     struct perf_comm_event *comm_event)

{

	struct perf_output_handle handle;

	struct perf_sample_data sample;

	int size = comm_event->event_id.header.size;

	int ret = perf_output_begin(&handle, event, size, 0, 0);

	int ret;



	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);

	ret = perf_output_begin(&handle, event,

				comm_event->event_id.header.size, 0, 0);



	if (ret)

		return;

		goto out;



	comm_event->event_id.pid = perf_event_pid(event, comm_event->task);

	comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
@@ -3937,7 +4012,12 @@ static void perf_event_comm_output(struct perf_event *event, 
	perf_output_put(&handle, comm_event->event_id);

	perf_output_copy(&handle, comm_event->comm,

				   comm_event->comm_size);



	perf_event__output_id_sample(event, &handle, &sample);



	perf_output_end(&handle);

out:

	comm_event->event_id.header.size = size;

}



static int perf_event_comm_match(struct perf_event *event)
@@ -3982,7 +4062,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) 
	comm_event->comm_size = size;



	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;



	rcu_read_lock();

	list_for_each_entry_rcu(pmu, &pmus, entry) {

		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
@@ -4061,11 +4140,15 @@ static void perf_event_mmap_output(struct perf_event *event, 
				     struct perf_mmap_event *mmap_event)

{

	struct perf_output_handle handle;

	struct perf_sample_data sample;

	int size = mmap_event->event_id.header.size;

	int ret = perf_output_begin(&handle, event, size, 0, 0);

	int ret;



	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);

	ret = perf_output_begin(&handle, event,

				mmap_event->event_id.header.size, 0, 0);

	if (ret)

		return;

		goto out;



	mmap_event->event_id.pid = perf_event_pid(event, current);

	mmap_event->event_id.tid = perf_event_tid(event, current);
@@ -4073,7 +4156,12 @@ static void perf_event_mmap_output(struct perf_event *event, 
	perf_output_put(&handle, mmap_event->event_id);

	perf_output_copy(&handle, mmap_event->file_name,

				   mmap_event->file_size);



	perf_event__output_id_sample(event, &handle, &sample);



	perf_output_end(&handle);

out:

	mmap_event->event_id.header.size = size;

}



static int perf_event_mmap_match(struct perf_event *event,
@@ -4226,6 +4314,7 @@ void perf_event_mmap(struct vm_area_struct *vma) 
static void perf_log_throttle(struct perf_event *event, int enable)

{

	struct perf_output_handle handle;

	struct perf_sample_data sample;

	int ret;



	struct {
@@ -4247,11 +4336,15 @@ static void perf_log_throttle(struct perf_event *event, int enable) 
	if (enable)

		throttle_event.header.type = PERF_RECORD_UNTHROTTLE;



	ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0);

	perf_event_header__init_id(&throttle_event.header, &sample, event);



	ret = perf_output_begin(&handle, event,

				throttle_event.header.size, 1, 0);

	if (ret)

		return;



	perf_output_put(&handle, throttle_event);

	perf_event__output_id_sample(event, &handle, &sample);

	perf_output_end(&handle);

}
@@ -5745,6 +5838,7 @@ SYSCALL_DEFINE5(perf_event_open, 
	 * Precalculate sample_data sizes

	 */

	perf_event__header_size(event);

	perf_event__id_header_size(event);



	/*

	 * Drop the reference on the group_event after placing the
@@ -6098,6 +6192,12 @@ inherit_event(struct perf_event *parent_event, 
	child_event->ctx = child_ctx;

	child_event->overflow_handler = parent_event->overflow_handler;



	/*

	 * Precalculate sample_data sizes

	 */

	perf_event__header_size(child_event);

	perf_event__id_header_size(child_event);



	/*

	 * Link it up in the child's context:

	 */

tools/perf/Documentation/perf-record.txt

+5 −0
Original line number Diff line number Diff line
@@ -108,6 +108,11 @@ OPTIONS 
--data::

	Sample addresses.



-T::

--timestamp::

	Sample timestamps. Use it with 'perf report -D' to see the timestamps,

	for instance.



-n::

--no-samples::

	Don't sample.

tools/perf/builtin-annotate.c

+3 −3
Original line number Diff line number Diff line
@@ -58,12 +58,12 @@ static int hists__add_entry(struct hists *self, struct addr_location *al) 
	return hist_entry__inc_addr_samples(he, al->addr);

}



static int process_sample_event(event_t *event, struct perf_session *session)

static int process_sample_event(event_t *event, struct sample_data *sample,

				struct perf_session *session)

{

	struct addr_location al;

	struct sample_data data;



	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {

	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {

		pr_warning("problem processing %d event, skipping it.\n",

			   event->header.type);

		return -1;

tools/perf/builtin-diff.c

+6 −5
Original line number Diff line number Diff line
@@ -30,12 +30,13 @@ static int hists__add_entry(struct hists *self, 
	return -ENOMEM;

}



static int diff__process_sample_event(event_t *event, struct perf_session *session)

static int diff__process_sample_event(event_t *event,

				      struct sample_data *sample,

				      struct perf_session *session)

{

	struct addr_location al;

	struct sample_data data = { .period = 1, };



	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {

	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {

		pr_warning("problem processing %d event, skipping it.\n",

			   event->header.type);

		return -1;
@@ -44,12 +45,12 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi 
	if (al.filtered || al.sym == NULL)

		return 0;



	if (hists__add_entry(&session->hists, &al, data.period)) {

	if (hists__add_entry(&session->hists, &al, sample->period)) {

		pr_warning("problem incrementing symbol period, skipping event\n");

		return -1;

	}



	session->hists.stats.total_period += data.period;

	session->hists.stats.total_period += sample->period;

	return 0;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE