Show the branch speculation info if provided by the branch recording
hardware feature. This can be useful for purposes of code optimization.
E.g.
$ perf record -j any,u ./test_branch
$ perf report --dump-raw-trace
Before:
[...]
8380958377610 0x40b178 [0x1b0]: PERF_RECORD_SAMPLE(IP, 0x2): 7952/7952: 0x4f851a period: 48973 addr: 0
... branch stack: nr:16
..... 0: 00000000004b52fd -> 00000000004f82c0 0 cycles P 0
..... 1: ffffffff8220137c -> 00000000004b52f0 0 cycles M 0
..... 2: 000000000041d1c4 -> 00000000004b52f0 0 cycles P 0
..... 3: 00000000004e7ead -> 000000000041d1b0 0 cycles M 0
..... 4: 00000000004e7f91 -> 00000000004e7ead 0 cycles P 0
..... 5: 00000000004e7ea8 -> 00000000004e7f70 0 cycles P 0
..... 6: 00000000004e7e52 -> 00000000004e7e98 0 cycles M 0
..... 7: 00000000004e7e1f -> 00000000004e7e40 0 cycles M 0
..... 8: 00000000004e7f60 -> 00000000004e7df0 0 cycles P 0
..... 9: 00000000004e7f58 -> 00000000004e7f60 0 cycles M 0
..... 10: 000000000041d85d -> 00000000004e7f50 0 cycles P 0
..... 11: 000000000043306a -> 000000000041d840 0 cycles P 0
..... 12: ffffffff8220137c -> 0000000000433040 0 cycles M 0
..... 13: 000000000041e4a1 -> 0000000000433040 0 cycles P 0
..... 14: ffffffff8220137c -> 000000000041e490 0 cycles M 0
..... 15: 000000000041d89b -> 000000000041e487 0 cycles P 0
... thread: test_branch:7952
...... dso: /data/sandipan/test_branch
[...]
After:
[...]
8380958377610 0x40b178 [0x1b0]: PERF_RECORD_SAMPLE(IP, 0x2): 7952/7952: 0x4f851a period: 48973 addr: 0
... branch stack: nr:16
..... 0: 00000000004b52fd -> 00000000004f82c0 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 1: ffffffff8220137c -> 00000000004b52f0 0 cycles M 0 NON_SPEC_CORRECT_PATH
..... 2: 000000000041d1c4 -> 00000000004b52f0 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 3: 00000000004e7ead -> 000000000041d1b0 0 cycles M 0 NON_SPEC_CORRECT_PATH
..... 4: 00000000004e7f91 -> 00000000004e7ead 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 5: 00000000004e7ea8 -> 00000000004e7f70 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 6: 00000000004e7e52 -> 00000000004e7e98 0 cycles M 0 SPEC_CORRECT_PATH
..... 7: 00000000004e7e1f -> 00000000004e7e40 0 cycles M 0 NON_SPEC_CORRECT_PATH
..... 8: 00000000004e7f60 -> 00000000004e7df0 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 9: 00000000004e7f58 -> 00000000004e7f60 0 cycles M 0 NON_SPEC_CORRECT_PATH
..... 10: 000000000041d85d -> 00000000004e7f50 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 11: 000000000043306a -> 000000000041d840 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 12: ffffffff8220137c -> 0000000000433040 0 cycles M 0 NON_SPEC_CORRECT_PATH
..... 13: 000000000041e4a1 -> 0000000000433040 0 cycles P 0 NON_SPEC_CORRECT_PATH
..... 14: ffffffff8220137c -> 000000000041e490 0 cycles M 0 NON_SPEC_CORRECT_PATH
..... 15: 000000000041d89b -> 000000000041e487 0 cycles P 0 NON_SPEC_CORRECT_PATH
... thread: test_branch:7952
...... dso: /data/sandipan/test_branch
[...]
Signed-off-by: Sandipan Das <[email protected]>
---
tools/perf/util/session.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1a4f10de29ff..71951db535f8 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1177,7 +1177,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
struct branch_entry *e = &entries[i];
if (!callstack) {
- printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s\n",
+ printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s %s\n",
i, e->from, e->to,
(unsigned short)e->flags.cycles,
e->flags.mispred ? "M" : " ",
@@ -1185,7 +1185,8 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
e->flags.abort ? "A" : " ",
e->flags.in_tx ? "T" : " ",
(unsigned)e->flags.reserved,
- get_branch_type(e));
+ get_branch_type(e),
+ e->flags.spec ? branch_spec_desc(e->flags.spec) : "");
} else {
if (i == 0) {
printf("..... %2"PRIu64": %016" PRIx64 "\n"
--
2.34.1