Messages in this thread Patch in this message | | | From | Andi Kleen <> | Subject | [PATCH 3/5] perf, tools: Disable branch flags/cycles for --callgraph lbr | Date | Tue, 20 Oct 2015 11:46:35 -0700 |
| |
From: Andi Kleen <ak@linux.intel.com>
Automatically disable collecting branch flags and cycles with --call-graph lbr. This allows avoiding a bunch of extra MSR reads in the PMI on Skylake.
When the kernel doesn't support the new flags they are automatically cleared in the fallback code.
v2: Switch to use branch_sample_type instead of sample_type. Adjust description. Fix the fallback logic. Signed-off-by: Andi Kleen <ak@linux.intel.com> --- tools/perf/util/evsel.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8be867c..e8724b4 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -36,6 +36,7 @@ static struct { bool cloexec; bool clockid; bool clockid_wrong; + bool lbr_flags; } perf_missing_features; static clockid_t clockid; @@ -573,7 +574,9 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel, } else { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER | - PERF_SAMPLE_BRANCH_CALL_STACK; + PERF_SAMPLE_BRANCH_CALL_STACK | + PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_NO_FLAGS; } } else pr_warning("Cannot use LBR callstack with branch stack. " @@ -1312,6 +1315,9 @@ fallback_missing_features: evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; + if (perf_missing_features.lbr_flags) + evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | + PERF_SAMPLE_BRANCH_NO_CYCLES); retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1414,6 +1420,12 @@ try_fallback: } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; goto retry_sample_id; + } else if (!perf_missing_features.lbr_flags && + (evsel->attr.branch_sample_type & + (PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_NO_FLAGS))) { + perf_missing_features.lbr_flags = true; + goto fallback_missing_features; } out_close: -- 2.4.3
| |