[PATCH v4 37/39] perf record: Enable defer_callchain for user callchains

From: Namhyung Kim <[email protected]>

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 <[email protected]>
Signed-off-by: Josh Poimboeuf <[email protected]>
---
 tools/perf/util/evsel.c | 24 ++++++++++++++++++++++++
 tools/perf/util/evsel.h |  1 +
 2 files changed, 25 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 09b9735f2fb1..e3be3cc7632d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -998,6 +998,14 @@ 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;
@@ -2038,6 +2046,8 @@ 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.inherit_sample_read && evsel->core.attr.inherit &&
 	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ))
 		evsel->core.attr.inherit = 0;
@@ -2244,6 +2254,15 @@ static bool evsel__detect_missing_features(struct evsel *evsel)
 
 	/* Please add new feature detection here. */
 
+	attr.defer_callchain = true;
+	attr.sample_type = PERF_SAMPLE_CALLCHAIN;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.defer_callchain = true;
+	pr_debug2("switching off deferred callchain support\n");
+	attr.defer_callchain = false;
+	attr.sample_type = 0;
+
 	attr.inherit = true;
 	attr.sample_type = PERF_SAMPLE_READ;
 	if (has_attr_feature(&attr, /*flags=*/0))
@@ -2355,6 +2374,11 @@ static bool evsel__detect_missing_features(struct evsel *evsel)
 	errno = old_errno;
 
 check:
+	if (evsel->core.attr.defer_callchain &&
+	    evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN &&
+	    perf_missing_features.defer_callchain)
+		return true;
+
 	if (evsel->core.attr.inherit &&
 	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ) &&
 	    perf_missing_features.inherit_sample_read)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 04934a7af174..b90a970f9a30 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -206,6 +206,7 @@ struct perf_missing_features {
 	bool read_lost;
 	bool branch_counters;
 	bool inherit_sample_read;
+	bool defer_callchain;
 };
 
 extern struct perf_missing_features perf_missing_features;
-- 
2.48.1