[PATCH v7 4/4] tools/perf: Allow inherit + PERF_SAMPLE_READ when opening events
From: Ben Gainey
Date: Thu Jun 06 2024 - 11:07:22 EST
The 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@xxxxxxx>
---
tools/perf/tests/attr/README | 2 +
.../tests/attr/test-record-group-sampling | 3 +-
.../tests/attr/test-record-group-sampling1 | 51 ++++++++++++++++
.../tests/attr/test-record-group-sampling2 | 61 +++++++++++++++++++
tools/perf/tests/attr/test-record-group2 | 1 +
...{test-record-group2 => test-record-group3} | 10 +--
tools/perf/util/evsel.c | 19 +++++-
tools/perf/util/evsel.h | 1 +
8 files changed, 141 insertions(+), 7 deletions(-)
create mode 100644 tools/perf/tests/attr/test-record-group-sampling1
create mode 100644 tools/perf/tests/attr/test-record-group-sampling2
copy tools/perf/tests/attr/{test-record-group2 => test-record-group3} (81%)
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 4066fec7180a..67c4ca76b85d 100644
--- 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-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 97e7e64a38f0..c32ceb156226 100644
--- 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 = 6.10
[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
index 000000000000..db6404c1ef78
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling1
@@ -0,0 +1,51 @@
+[config]
+command = record
+args = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret = 1
+kernel_since = 6.10
+
+[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
index 000000000000..32884df78c95
--- /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 = 6.10
+
+[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 cebdaa8e64e4..8fe6c679618c 100644
--- 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 = 6.10
[event-1:base-record]
fd=1
diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group3
similarity index 81%
copy from tools/perf/tests/attr/test-record-group2
copy to tools/perf/tests/attr/test-record-group3
index cebdaa8e64e4..72e6a9ee2f60 100644
--- a/tools/perf/tests/attr/test-record-group2
+++ b/tools/perf/tests/attr/test-record-group3
@@ -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_since = 6.10
[event-1:base-record]
fd=1
@@ -9,8 +10,9 @@ group_fd=-1
config=0|1
sample_period=1234000
sample_type=87
-read_format=12|28
-inherit=0
+read_format=28|31
+disabled=1
+inherit=1
freq=0
[event-2:base-record]
@@ -19,9 +21,9 @@ group_fd=1
config=0|1
sample_period=6789000
sample_type=87
-read_format=12|28
+read_format=28|31
disabled=0
-inherit=0
+inherit=1
mmap=0
comm=0
freq=0
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4f818ab6b662..66b782811997 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1162,7 +1162,15 @@ 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;
}
}
@@ -1838,6 +1846,8 @@ 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)
@@ -1893,7 +1903,12 @@ 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 375a38e15cd9..911c2fd42c6d 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -192,6 +192,7 @@ 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;
--
2.45.2