perf script: Show branch speculation info

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
  [...]

The bitfield swapping scheme used duing sample parsing has changed
because of the addition of new branch flags, namely "spec", "new_type"
and "priv". Earlier, these were all part of the "reserved" field but
now, each of these fields get swapped separately. Change the expected
flag values accordingly for the test to pass.

E.g.

  $ perf test -v 27

Before:

   27: Sample parsing                                                  :
  --- start ---
  test child forked, pid 61979
  parsing failed for sample_type 0x800
  test child finished with -1
  ---- end ----
  Sample parsing: FAILED!

After:

   27: Sample parsing                                                  :
  --- start ---
  test child forked, pid 63293
  test child finished with 0
  ---- end ----
  Sample parsing: Ok

Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: x86@kernel.org
Link: https://lore.kernel.org/r/56e272583552526e999ba0b536ac009ae3613966.1675333809.git.sandipan.das@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index cb6b34da4eefb9070be051887f9e2a0d00e333ed..339b441015eb7697faf0c5932fe043cf8d431469 100644 (file)
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -889,12 +889,13 @@ 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/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 927c7f0cc4ccc8e48699f9e52e36f6c19b8c0835..25a3f6cece50549b32c1267b7249a934ec2c5e28 100644 (file)
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -37,7 +37,7 @@
  * in branch_stack variable.
  */
 #define BS_EXPECTED_BE 0xa000d00000000000
-#define BS_EXPECTED_LE 0xd5000000
+#define BS_EXPECTED_LE 0x1aa00000000
 #define FLAG(s)        s->branch_stack->entries[i].flags
 
 static bool samples_same(const struct perf_sample *s1,

diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index 6d38238481d327d00b5e13fa6171f387e4d50d16..378f16a247511820ea93d0c13a6c5c14ced0e73e 100644 (file)
--- 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 3ed792db11255e6e954e7437fa999898086b68ae..e41bfffe22170b076b9f52096bc9b1ff27d463b4 100644 (file)
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -89,4 +89,6 @@ 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 8550638587e506f8845bd255c938284ad869e6e7..019e53db03b3291066428e3a3f914ee594b41750 100644 (file)
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2319,7 +2319,10 @@ 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
         *      }
         * }
         *
@@ -2335,7 +2338,10 @@ 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);
@@ -2343,7 +2349,10 @@ 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;