Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 3efa1cc9 authored by Ingo Molnar's avatar Ingo Molnar
Browse files

perf record/report: Add call graph / call chain profiling 



Add the first steps of call-graph profiling:

 - add the -c (--call-graph) option to perf record
 - parse the call-graph record and printout out under -D (--dump-trace)

The call-graph data is not put into the histogram yet, but it
can be seen that it's being processed correctly:

0x3ce0 [0x38]: event: 35
.
. ... raw event: size 56 bytes
.  0000:  23 00 00 00 05 00 38 00 d4 df 0e 81 ff ff ff ff  #.....8........
.  0010:  60 0b 00 00 60 0b 00 00 03 00 00 00 01 00 02 00  `...`..........
.  0020:  d4 df 0e 81 ff ff ff ff a0 61 ed 41 36 00 00 00  .........a.A6..
.  0030:  04 92 e6 41 36 00 00 00                          .a.A6..
.
0x3ce0 [0x38]: PERF_EVENT (IP, 5): 2912: 0xffffffff810edfd4 period: 1
... chain: u:2, k:1, nr:3
.....  0: 0xffffffff810edfd4
.....  1: 0x3641ed61a0
.....  2: 0x3641e69204
 ... thread: perf:2912
 ...... dso: [kernel]

This shows a 3-entry call-graph: with 1 kernel-space and two user-space
entries

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent 8465b050

tools/perf/builtin-record.c

+8 −0
Original line number Original line Diff line number Diff line
@@ -37,6 +37,7 @@ static pid_t target_pid = -1; 
static int			inherit				= 1;

static int			inherit				= 1;

static int			force				= 0;

static int			force				= 0;

static int			append_file			= 0;

static int			append_file			= 0;

static int			call_graph			= 0;

static int			verbose				= 0;

static int			verbose				= 0;





static long			samples;

static long			samples;
@@ -351,11 +352,16 @@ static void create_counter(int counter, int cpu, pid_t pid) 
	int track = 1;

	int track = 1;





	attr->sample_type	= PERF_SAMPLE_IP | PERF_SAMPLE_TID;

	attr->sample_type	= PERF_SAMPLE_IP | PERF_SAMPLE_TID;



	if (freq) {

	if (freq) {

		attr->sample_type	|= PERF_SAMPLE_PERIOD;

		attr->sample_type	|= PERF_SAMPLE_PERIOD;

		attr->freq		= 1;

		attr->freq		= 1;

		attr->sample_freq	= freq;

		attr->sample_freq	= freq;

	}

	}



	if (call_graph)

		attr->sample_type	|= PERF_SAMPLE_CALLCHAIN;



	attr->mmap		= track;

	attr->mmap		= track;

	attr->comm		= track;

	attr->comm		= track;

	attr->inherit		= (cpu < 0) && inherit;

	attr->inherit		= (cpu < 0) && inherit;
@@ -555,6 +561,8 @@ static const struct option options[] = { 
		    "profile at this frequency"),

		    "profile at this frequency"),

	OPT_INTEGER('m', "mmap-pages", &mmap_pages,

	OPT_INTEGER('m', "mmap-pages", &mmap_pages,

		    "number of mmap data pages"),

		    "number of mmap data pages"),

	OPT_BOOLEAN('g', "call-graph", &call_graph,

		    "do call-graph (stack chain/backtrace) recording"),

	OPT_BOOLEAN('v', "verbose", &verbose,

	OPT_BOOLEAN('v', "verbose", &verbose,

		    "be more verbose (show counter open errors, etc)"),

		    "be more verbose (show counter open errors, etc)"),

	OPT_END()

	OPT_END()

tools/perf/builtin-report.c

+45 −12
Original line number Original line Diff line number Diff line
@@ -36,6 +36,7 @@ static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; 




static int		dump_trace = 0;

static int		dump_trace = 0;

#define dprintf(x...)	do { if (dump_trace) printf(x); } while (0)

#define dprintf(x...)	do { if (dump_trace) printf(x); } while (0)

#define cdprintf(x...)	do { if (dump_trace) color_fprintf(stdout, color, x); } while (0)





static int		verbose;

static int		verbose;

static int		full_paths;

static int		full_paths;
@@ -43,11 +44,19 @@ static int full_paths; 
static unsigned long	page_size;

static unsigned long	page_size;

static unsigned long	mmap_window = 32;

static unsigned long	mmap_window = 32;





struct ip_chain_event {

	__u16 nr;

	__u16 hv;

	__u16 kernel;

	__u16 user;

	__u64 ips[];

};



struct ip_event {

struct ip_event {

	struct perf_event_header header;

	struct perf_event_header header;

	__u64 ip;

	__u64 ip;

	__u32 pid, tid;

	__u32 pid, tid;

	__u64 period;

	unsigned char __more_data[];

};

};





struct mmap_event {

struct mmap_event {
@@ -944,9 +953,13 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head) 
	__u64 ip = event->ip.ip;

	__u64 ip = event->ip.ip;

	__u64 period = 1;

	__u64 period = 1;

	struct map *map = NULL;

	struct map *map = NULL;

	void *more_data = event->ip.__more_data;

	struct ip_chain_event *chain;





	if (event->header.type & PERF_SAMPLE_PERIOD)

	if (event->header.type & PERF_SAMPLE_PERIOD) {

		period = event->ip.period;

		period = *(__u64 *)more_data;

		more_data += sizeof(__u64);

	}





	dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n",

	dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n",

		(void *)(offset + head),

		(void *)(offset + head),
@@ -956,6 +969,22 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head) 
		(void *)(long)ip,

		(void *)(long)ip,

		(long long)period);

		(long long)period);





	if (event->header.type & PERF_SAMPLE_CALLCHAIN) {

		int i;



		chain = (void *)more_data;



		if (dump_trace) {

			dprintf("... chain: u:%d, k:%d, nr:%d\n",

				chain->user,

				chain->kernel,

				chain->nr);



			for (i = 0; i < chain->nr; i++)

				dprintf("..... %2d: %p\n", i, (void *)chain->ips[i]);

		}

	}



	dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid);

	dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid);





	if (thread == NULL) {

	if (thread == NULL) {
@@ -1098,30 +1127,34 @@ process_period_event(event_t *event, unsigned long offset, unsigned long head) 
static void trace_event(event_t *event)

static void trace_event(event_t *event)

{

{

	unsigned char *raw_event = (void *)event;

	unsigned char *raw_event = (void *)event;

	char *color = PERF_COLOR_BLUE;

	int i, j;

	int i, j;





	if (!dump_trace)

	if (!dump_trace)

		return;

		return;





	dprintf(".\n. ... raw event: size %d bytes\n", event->header.size);

	dprintf(".");

	cdprintf("\n. ... raw event: size %d bytes\n", event->header.size);





	for (i = 0; i < event->header.size; i++) {

	for (i = 0; i < event->header.size; i++) {

		if ((i & 15) == 0)

		if ((i & 15) == 0) {

			dprintf(".  %04x: ", i);

			dprintf(".");

			cdprintf("  %04x: ", i);

		}





		dprintf(" %02x", raw_event[i]);

		cdprintf(" %02x", raw_event[i]);





		if (((i & 15) == 15) || i == event->header.size-1) {

		if (((i & 15) == 15) || i == event->header.size-1) {

			dprintf("  ");

			cdprintf("  ");

			for (j = 0; j < 15-(i & 15); j++)

			for (j = 0; j < 15-(i & 15); j++)

				dprintf("   ");

				cdprintf("   ");

			for (j = 0; j < (i & 15); j++) {

			for (j = 0; j < (i & 15); j++) {

				if (isprint(raw_event[i-15+j]))

				if (isprint(raw_event[i-15+j]))

					dprintf("%c", raw_event[i-15+j]);

					cdprintf("%c", raw_event[i-15+j]);

				else

				else

					dprintf(".");

					cdprintf(".");

			}

			}

			dprintf("\n");

			cdprintf("\n");

		}

		}

	}

	}

	dprintf(".\n");

	dprintf(".\n");