Commit d2720c3d authored Aug 09, 2019 by Alexey Budankov Committed by Arnaldo Carvalho de Melo Aug 20, 2019

perf report: Dump LBR callstack data by -D jointly with thread stack



Make perf report -D command print captured LBR callstack chain when it is
collected together with raw thread stack data:

  2752673087247083 0x5d10 [0x548]: PERF_RECORD_SAMPLE(IP, 0x4002): 5841/5841: 0x40121f period: 1543862 addr: 0
  ... FP chain: nr:0
  ... branch callstack: nr:3
  .....  0: 00000000004011d0
  .....  1: 00007f393c388411
  .....  2: 0000000000401098
  ... user regs: mask 0xff0fff ABI 64-bit
  .... AX    0x34e7
  .... BX    0x7fff5f6dd3c0
  .... CX    0xffffffff
  .... DX    0x34e6
  .... SI    0x7f393c5268d0
  .... DI    0x0
  .... BP    0x401260
  .... SP    0x7fff5f6dd3c0
  .... IP    0x40121f
  .... FLAGS 0x29f
  .... CS    0x33
  .... SS    0x2b
  .... R8    0x7f393c526800
  .... R9    0x7f393c525da0
  .... R10   0xfffffffffffff70a
  .... R11   0x246
  .... R12   0x401070
  .... R13   0x7fff5f6ddcb0
  .... R14   0x0
  .... R15   0x0
  ... ustack: size 1024, offset 0x130
   . data_src: 0x5080021
   ... thread: stack_test:5841
   ...... dso: /root/abudanko/stacks/stack_test

Committer testing:

  # perf record -g --call-graph dwarf,1024 -j stack,u ls > /dev/null
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.042 MB perf.data (10 samples) ]
  #

Before:

  # perf report -D |& grep PERF_RECORD_SAMPLE -A28 | tail -29
  67538909824483 0xa7a0 [0x560]: PERF_RECORD_SAMPLE(IP, 0x4002): 9721/9721: 0x7f441b2b1e20 period: 1376095 addr: 0
  ... FP chain: nr:0
  ... user regs: mask 0xff0fff ABI 64-bit
  .... AX    0x7f441b2b1000
  .... BX    0x7f441b55b970
  .... CX    0x7fff6e2db218
  .... DX    0x7fff6e2db218
  .... SI    0x7fff6e2db208
  .... DI    0x1
  .... BP    0x1
  .... SP    0x7fff6e2db178
  .... IP    0x7f441b2b1e20
  .... FLAGS 0x20a
  .... CS    0x33
  .... SS    0x2b
  .... R8    0x1
  .... R9    0x7f441b371c18
  .... R10   0x7f441b5a5f10
  .... R11   0x202
  .... R12   0x7fff6e2db208
  .... R13   0x7fff6e2db218
  .... R14   0x7f441b5a7150
  .... R15   0x0
  ... ustack: size 1024, offset 0x148
   . data_src: 0x5080021
   ... thread: ls:9721
   ...... dso: /usr/lib64/libpthread-2.29.so

  0xad00 [0x60]: event: 10
  #

After:

  # perf report -D |& grep PERF_RECORD_SAMPLE -A31 | tail -32
  67538909824483 0xa7a0 [0x560]: PERF_RECORD_SAMPLE(IP, 0x4002): 9721/9721: 0x7f441b2b1e20 period: 1376095 addr: 0
  ... FP chain: nr:0
  ... branch callstack: nr:4
  .....  0: 00007f441b2b1e20
  .....  1: 00007f441b58af1a
  .....  2: 00007f441b58b0e1
  .....  3: 00007f441b57c145
  ... user regs: mask 0xff0fff ABI 64-bit
  .... AX    0x7f441b2b1000
  .... BX    0x7f441b55b970
  .... CX    0x7fff6e2db218
  .... DX    0x7fff6e2db218
  .... SI    0x7fff6e2db208
  .... DI    0x1
  .... BP    0x1
  .... SP    0x7fff6e2db178
  .... IP    0x7f441b2b1e20
  .... FLAGS 0x20a
  .... CS    0x33
  .... SS    0x2b
  .... R8    0x1
  .... R9    0x7f441b371c18
  .... R10   0x7f441b5a5f10
  .... R11   0x202
  .... R12   0x7fff6e2db208
  .... R13   0x7fff6e2db218
  .... R14   0x7f441b5a7150
  .... R15   0x0
  ... ustack: size 1024, offset 0x148
   . data_src: 0x5080021
   ... thread: ls:9721
   ...... dso: /usr/lib64/libpthread-2.29.so
  #

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/aa82e5dd-def2-0ca8-a064-db9e2e8ad076@linux.intel.com


Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

parent 25663496

tools/perf/util/session.c

+19 −12

Original line number	Diff line number	Diff line
		@@ -1051,15 +1051,18 @@ static void callchain__printf(struct evsel *evsel,
		i, callchain->ips[i]);
		}

		static void branch_stack__printf(struct perf_sample *sample)
		static void branch_stack__printf(struct perf_sample *sample, bool callstack)
		{
		uint64_t i;

		printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
		printf("%s: nr:%" PRIu64 "\n",
		!callstack ? "... branch stack" : "... branch callstack",
		sample->branch_stack->nr);

		for (i = 0; i < sample->branch_stack->nr; i++) {
		struct branch_entry *e = &sample->branch_stack->entries[i];

		if (!callstack) {
		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
		i, e->from, e->to,
		(unsigned short)e->flags.cycles,
		@@ -1068,6 +1071,10 @@ static void branch_stack__printf(struct perf_sample *sample)
		e->flags.abort ? "A" : " ",
		e->flags.in_tx ? "T" : " ",
		(unsigned)e->flags.reserved);
		} else {
		printf("..... %2"PRIu64": %016" PRIx64 "\n",
		i, i > 0 ? e->from : e->to);
		}
		}
		}

		@@ -1217,8 +1224,8 @@ static void dump_sample(struct evsel evsel, union perf_event event,
		if (evsel__has_callchain(evsel))
		callchain__printf(evsel, sample);

		if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel))
		branch_stack__printf(sample);
		if (sample_type & PERF_SAMPLE_BRANCH_STACK)
		branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));

		if (sample_type & PERF_SAMPLE_REGS_USER)
		regs_user__printf(sample);

Admin message