Show the branch speculation info if provided by the branch recording
hardware feature. This can be useful for optimizing code further.
The speculation info is appended to the end of the list of fields so any
existing tools that use "/" as a delimiter for access fields via an index
remain unaffected. Also show "-" instead of "N/A" when speculation info
is unavailable because "/" is used as the field separator.
E.g.
$ perf record -j any,u,save_type ./test_branch
$ perf script --fields brstacksym
Before:
[...]
check_match+0x60/strcmp+0x0/P/-/-/0/CALL
do_lookup_x+0x3c5/check_match+0x0/P/-/-/0/CALL
[...]
After:
[...]
check_match+0x60/strcmp+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH
do_lookup_x+0x3c5/check_match+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH
[...]
Signed-off-by: Sandipan Das <[email protected]>
---
tools/perf/builtin-script.c | 5 +++--
tools/perf/util/branch.c | 15 +++++++++++++++
tools/perf/util/branch.h | 5 ++++-
tools/perf/util/evsel.c | 15 ++++++++++++---
4 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 886f53cfa257..5b337f47a4be 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -877,12 +877,13 @@ mispred_str(struct branch_entry *br)
static int print_bstack_flags(FILE *fp, struct branch_entry *br)
{
- return fprintf(fp, "/%c/%c/%c/%d/%s ",
+ return fprintf(fp, "/%c/%c/%c/%d/%s/%s ",
mispred_str(br),
br->flags.in_tx ? 'X' : '-',
br->flags.abort ? 'A' : '-',
br->flags.cycles,
- get_branch_type(br));
+ get_branch_type(br),
+ br->flags.spec ? branch_spec_desc(br->flags.spec) : "-");
}
static int perf_sample__fprintf_brstack(struct perf_sample *sample,
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index 6d38238481d3..378f16a24751 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -212,3 +212,18 @@ int branch_type_str(struct branch_type_stat *st, char *bf, int size)
return printed;
}
+
+const char *branch_spec_desc(int spec)
+{
+ const char *branch_spec_outcomes[PERF_BR_SPEC_MAX] = {
+ "N/A",
+ "SPEC_WRONG_PATH",
+ "NON_SPEC_CORRECT_PATH",
+ "SPEC_CORRECT_PATH",
+ };
+
+ if (spec >= 0 && spec < PERF_BR_SPEC_MAX)
+ return branch_spec_outcomes[spec];
+
+ return NULL;
+}
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index f838b23db180..264817c96560 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -24,9 +24,10 @@ struct branch_flags {
u64 abort:1;
u64 cycles:16;
u64 type:4;
+ u64 spec:2;
u64 new_type:4;
u64 priv:3;
- u64 reserved:33;
+ u64 reserved:31;
};
};
};
@@ -90,4 +91,6 @@ const char *get_branch_type(struct branch_entry *e);
void branch_type_stat_display(FILE *fp, struct branch_type_stat *st);
int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize);
+const char *branch_spec_desc(int spec);
+
#endif /* _PERF_BRANCH_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5776bfa70f11..0266e885acb6 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2326,7 +2326,10 @@ u64 evsel__bitfield_swap_branch_flags(u64 value)
* abort:1 //transaction abort
* cycles:16 //cycle count to last branch
* type:4 //branch type
- * reserved:40
+ * spec:2 //branch speculation info
+ * new_type:4 //additional branch type
+ * priv:3 //privilege level
+ * reserved:31
* }
* }
*
@@ -2345,7 +2348,10 @@ u64 evsel__bitfield_swap_branch_flags(u64 value)
new_val |= bitfield_swap(value, 3, 1);
new_val |= bitfield_swap(value, 4, 16);
new_val |= bitfield_swap(value, 20, 4);
- new_val |= bitfield_swap(value, 24, 40);
+ new_val |= bitfield_swap(value, 24, 2);
+ new_val |= bitfield_swap(value, 26, 4);
+ new_val |= bitfield_swap(value, 30, 3);
+ new_val |= bitfield_swap(value, 33, 31);
} else {
new_val = bitfield_swap(value, 63, 1);
new_val |= bitfield_swap(value, 62, 1);
@@ -2353,7 +2359,10 @@ u64 evsel__bitfield_swap_branch_flags(u64 value)
new_val |= bitfield_swap(value, 60, 1);
new_val |= bitfield_swap(value, 44, 16);
new_val |= bitfield_swap(value, 40, 4);
- new_val |= bitfield_swap(value, 0, 40);
+ new_val |= bitfield_swap(value, 38, 2);
+ new_val |= bitfield_swap(value, 34, 4);
+ new_val |= bitfield_swap(value, 31, 3);
+ new_val |= bitfield_swap(value, 0, 31);
}
return new_val;
--
2.34.1