tools/perf: Allow inherit + PERF_SAMPLE_READ when opening events

The "perf record" tool will now default to this new mode if the user
specifies a sampling group when not in system-wide mode, and when
"--no-inherit" is not specified.

This change updates evsel to allow the combination of inherit
and PERF_SAMPLE_READ.

A fallback is implemented for kernel versions where this feature is not
supported.

Signed-off-by: Ben Gainey <ben.gainey@arm.com>
Cc: james.clark@arm.com
Link: https://lore.kernel.org/r/20241001121505.1009685-3-ben.gainey@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 4066fec7180a8eaa362874f4a33678abaf681007..67c4ca76b85d5611bbe45ee2eeb9c34c28a0828d 100644 (file)
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -51,6 +51,8 @@ Following tests are defined (with perf commands):
   perf record --call-graph fp kill              (test-record-graph-fp-aarch64)
   perf record -e '{cycles,instructions}' kill   (test-record-group1)
   perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
+  perf record -e '{cycles,cache-misses}:S' kill (test-record-group-sampling1)
+  perf record -c 10000 -e '{cycles,cache-misses}:S' kill (test-record-group-sampling2)
   perf record -D kill                           (test-record-no-delay)
   perf record -i kill                           (test-record-no-inherit)
   perf record -n kill                           (test-record-no-samples)

diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
index 198e8429a1bf85af56be904ac20abeafcee83ef1..1049ac8b52f27f6341fb3d035c9088dde5626e2e 100644 (file)
--- a/tools/perf/tests/attr/test-record-C0
+++ b/tools/perf/tests/attr/test-record-C0
@@ -18,5 +18,7 @@ sample_type=65927
 mmap=0
 comm=0
 task=0
+inherit=0
 
 [event:system-wide-dummy]
+inherit=0

diff --git a/tools/perf/tests/attr/test-record-dummy-C0 b/tools/perf/tests/attr/test-record-dummy-C0
index 576ec48b3aafaa6a783e3e58f3ecd72cc927521b..3050298bd6140d64999c2d3db51f20103544901b 100644 (file)
--- a/tools/perf/tests/attr/test-record-dummy-C0
+++ b/tools/perf/tests/attr/test-record-dummy-C0
@@ -19,7 +19,7 @@ sample_period=4000
 sample_type=391
 read_format=4|20
 disabled=0
-inherit=1
+inherit=0
 pinned=0
 exclusive=0
 exclude_user=0

diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 97e7e64a38f07f682d05b1d8a6257e92bdc07867..86a940d7895d740457116d029b7ed8a5e1df44af 100644 (file)
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -2,6 +2,7 @@
 command = record
 args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
+kernel_until = 6.12
 
 [event-1:base-record]
 fd=1
@@ -18,7 +19,7 @@ group_fd=1
 type=0
 config=3
 
-# default | PERF_SAMPLE_READ
+# default | PERF_SAMPLE_READ | PERF_SAMPLE_PERIOD
 sample_type=343
 
 # PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST

diff --git a/tools/perf/tests/attr/test-record-group-sampling1 b/tools/perf/tests/attr/test-record-group-sampling1
new file mode 100644 (file)
index 0000000..4748ab7
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling1
@@ -0,0 +1,50 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret     = 1
+kernel_since = 6.12
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+
+# cycles
+type=0
+config=0
+
+# default | PERF_SAMPLE_READ | PERF_SAMPLE_PERIOD
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=1
+mmap=1
+comm=1
+enable_on_exec=1
+disabled=1
+
+# inherit is enabled for group sampling
+inherit=1
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ | PERF_SAMPLE_PERIOD
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=0
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+freq=0
+
+# inherit is enabled for group sampling
+inherit=1

diff --git a/tools/perf/tests/attr/test-record-group-sampling2 b/tools/perf/tests/attr/test-record-group-sampling2
new file mode 100644 (file)
index 0000000..e043224
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling2
@@ -0,0 +1,61 @@
+[config]
+command = record
+args    = --no-bpf-event -c 10000 -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret     = 1
+kernel_since = 6.12
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+
+# cycles
+type=0
+config=0
+
+# default | PERF_SAMPLE_READ
+sample_type=87
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=1
+mmap=1
+comm=1
+enable_on_exec=1
+disabled=1
+
+# inherit is enabled for group sampling
+inherit=1
+
+# sampling disabled
+sample_freq=0
+sample_period=10000
+freq=0
+write_backward=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ
+sample_type=87
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST | PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING
+read_format=28|31
+task=0
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+
+# inherit is enabled for group sampling
+inherit=1
+
+# sampling disabled
+sample_freq=0
+sample_period=0
+freq=0
+write_backward=0

diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2
index cebdaa8e64e474715035629e5b6d32cd54518ec3..891d41a7bddf785a8de3c6be5ba2fd3f099f5a14 100644 (file)
--- a/tools/perf/tests/attr/test-record-group2
+++ b/tools/perf/tests/attr/test-record-group2
@@ -2,6 +2,7 @@
 command = record
 args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
 ret     = 1
+kernel_until = 6.12
 
 [event-1:base-record]
 fd=1

diff --git a/tools/perf/tests/attr/test-record-group3 b/tools/perf/tests/attr/test-record-group3
new file mode 100644 (file)
index 0000000..249be88
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group3
@@ -0,0 +1,31 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+ret     = 1
+kernel_since = 6.12
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+config=0|1
+sample_period=1234000
+sample_type=87
+read_format=28|31
+disabled=1
+inherit=1
+freq=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=0|1
+sample_period=6789000
+sample_type=87
+read_format=28|31
+disabled=0
+inherit=1
+mmap=0
+comm=0
+freq=0
+enable_on_exec=0
+task=0

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index da0bada62140d9b013bc66937746818942196750..b221459439b8868ffdca704d1c9e8bbd7f42d014 100644 (file)
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1148,7 +1148,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
        bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
        attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
-       attr->inherit       = !opts->no_inherit;
+       attr->inherit       = target__has_cpu(&opts->target) ? 0 : !opts->no_inherit;
        attr->write_backward = opts->overwrite ? 1 : 0;
        attr->read_format   = PERF_FORMAT_LOST;
 
@@ -1170,7 +1170,15 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
                 */
                if (leader->core.nr_members > 1) {
                        attr->read_format |= PERF_FORMAT_GROUP;
-                       attr->inherit = 0;
+               }
+
+               /*
+                * Inherit + SAMPLE_READ requires SAMPLE_TID in the read_format
+                */
+               if (attr->inherit) {
+                       evsel__set_sample_bit(evsel, TID);
+                       evsel->core.attr.read_format |=
+                               PERF_FORMAT_ID;
                }
        }
 
@@ -2104,6 +2112,8 @@ 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.inherit_sample_read)
+               evsel->core.attr.inherit = 0;
        if (perf_missing_features.branch_counters)
                evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
        if (perf_missing_features.read_lost)
@@ -2159,7 +2169,12 @@ 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.inherit_sample_read &&
+           evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ)) {
+               perf_missing_features.inherit_sample_read = true;
+               pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\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 3e751ea769ac4d3a15a9d1235ad7485a6cf0406a..bd08d94d3f8ab67b36e41dfa8eda0963cdbb3123 100644 (file)
--- 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 inherit_sample_read;
 };
 
 extern struct perf_missing_features perf_missing_features;