[PATCH v3 17/19] perf record: Enable defer_callchain for user callchains

Josh Poimboeuf posted 19 patches 3 weeks, 6 days ago
[PATCH v3 17/19] perf record: Enable defer_callchain for user callchains
Posted by Josh Poimboeuf 3 weeks, 6 days ago
From: Namhyung Kim <namhyung@kernel.org>

And add the missing feature detection logic to clear the flag on old
kernels.

  $ perf record -g -vv true
  ...
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|CALLCHAIN|PERIOD
    read_format                      ID|LOST
    disabled                         1
    inherit                          1
    mmap                             1
    comm                             1
    freq                             1
    enable_on_exec                   1
    task                             1
    sample_id_all                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
    bpf_event                        1
    defer_callchain                  1
  ------------------------------------------------------------
  sys_perf_event_open: pid 162755  cpu 0  group_fd -1  flags 0x8
  sys_perf_event_open failed, error -22
  switching off deferred callchain support

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/perf/util/evsel.c | 17 ++++++++++++++++-
 tools/perf/util/evsel.h |  1 +
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 701092d6b1b6..ad89644b32f2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -912,6 +912,14 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 		}
 	}
 
+	if (param->record_mode == CALLCHAIN_FP && !attr->exclude_callchain_user) {
+		/*
+		 * Enable deferred callchains optimistically.  It'll be switched
+		 * off later if the kernel doesn't support it.
+		 */
+		attr->defer_callchain = 1;
+	}
+
 	if (function) {
 		pr_info("Disabling user space callchains for function trace event.\n");
 		attr->exclude_callchain_user = 1;
@@ -2089,6 +2097,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.defer_callchain)
+		evsel->core.attr.defer_callchain = 0;
 	if (perf_missing_features.branch_counters)
 		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
 	if (perf_missing_features.read_lost)
@@ -2144,7 +2154,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.branch_counters &&
+	if (!perf_missing_features.defer_callchain &&
+	    evsel->core.attr.defer_callchain) {
+		perf_missing_features.defer_callchain = true;
+		pr_debug2("switching off deferred callchain support\n");
+		return true;
+	} else if (!perf_missing_features.branch_counters &&
 	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
 		perf_missing_features.branch_counters = true;
 		pr_debug2("switching off branch counters support\n");
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 15e745a9a798..f0a1e1d78942 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -221,6 +221,7 @@ struct perf_missing_features {
 	bool weight_struct;
 	bool read_lost;
 	bool branch_counters;
+	bool defer_callchain;
 };
 
 extern struct perf_missing_features perf_missing_features;
-- 
2.47.0