linux-kernel - [PATCH v15 10/10] perf test: Add direct off-cpu test

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250213230009.1450907-11-howardchu95@gmail.com>
Date: Thu, 13 Feb 2025 15:00:09 -0800
From: Howard Chu <howardchu95@...il.com>
To: acme@...nel.org
Cc: namhyung@...nel.org,
	jolsa@...nel.org,
	irogers@...gle.com,
	adrian.hunter@...el.com,
	linux-perf-users@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Howard Chu <howardchu95@...il.com>,
	Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
	Ingo Molnar <mingo@...hat.com>,
	James Clark <james.clark@...aro.org>,
	Kan Liang <kan.liang@...ux.intel.com>,
	Mark Rutland <mark.rutland@....com>,
	Peter Zijlstra <peterz@...radead.org>,
	Arnaldo Carvalho de Melo <acme@...hat.com>
Subject: [PATCH v15 10/10] perf test: Add direct off-cpu test

Why is there a --off-cpu-thresh 2000?

We collect an off-cpu period __ONLY ONCE__, either in direct sample form,
or in accumulated form (in BPF stack trace map).

If I don't add --off-cpu-thresh 2000, the sample in the original test
goes into the ring buffer instead of the BPF stack trace map.

Additionally, when using -e dummy, the ring buffer is not open, causing
us to lose a sample.

Signed-off-by: Howard Chu <howardchu95@...il.com>
Cc: Adrian Hunter <adrian.hunter@...el.com>
Cc: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Cc: Ian Rogers <irogers@...gle.com>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: James Clark <james.clark@...aro.org>
Cc: Jiri Olsa <jolsa@...nel.org>
Cc: Kan Liang <kan.liang@...ux.intel.com>
Cc: Mark Rutland <mark.rutland@....com>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Link: https://lore.kernel.org/r/20241108204137.2444151-11-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
---
 tools/perf/tests/shell/record_offcpu.sh | 71 +++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index 678947fe69ee..c5d6cae94c65 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -7,6 +7,9 @@ set -e
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 
+ts=$(printf "%u" $((~0 << 32))) # OFF_CPU_TIMESTAMP
+dummy_timestamp=${ts%???} # remove the last 3 digits to match perf script
+
 cleanup() {
   rm -f ${perfdata}
   rm -f ${perfdata}.old
@@ -19,6 +22,9 @@ trap_cleanup() {
 }
 trap trap_cleanup EXIT TERM INT
 
+test_over_thresh="Threshold test (over threshold)"
+test_below_thresh="Threshold test (below threshold)"
+
 test_offcpu_priv() {
   echo "Checking off-cpu privilege"
 
@@ -88,6 +94,63 @@ test_offcpu_child() {
   echo "Child task off-cpu test [Success]"
 }
 
+# task blocks longer than the --off-cpu-thresh, perf should collect a direct sample
+test_offcpu_over_thresh() {
+  echo "${test_over_thresh}"
+
+  # collect direct off-cpu samples for tasks blocked for more than 999ms
+  if ! perf record -e dummy --off-cpu --off-cpu-thresh 999 -o ${perfdata} -- sleep 1 2> /dev/null
+  then
+    echo "${test_over_thresh} [Failed record]"
+    err=1
+    return
+  fi
+  # direct sample's timestamp should be lower than the dummy_timestamp of the at-the-end sample
+  # check if a direct sample exists
+  if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q "offcpu-time"
+  then
+    echo "${test_over_thresh} [Failed missing direct samples]"
+    err=1
+    return
+  fi
+  # there should only be one direct sample, and its period should be higher than off-cpu-thresh
+  if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F period | \
+       awk '{ if (int($1) > 999000000) exit 0; else exit 1; }'
+  then
+    echo "${test_over_thresh} [Failed off-cpu time too short]"
+    err=1
+    return
+  fi
+  echo "${test_over_thresh} [Success]"
+}
+
+# task blocks shorter than the --off-cpu-thresh, perf should collect an at-the-end sample
+test_offcpu_below_thresh() {
+  echo "${test_below_thresh}"
+
+  # collect direct off-cpu samples for tasks blocked for more than 1.2s
+  if ! perf record -e dummy --off-cpu --off-cpu-thresh 12000 -o ${perfdata} -- sleep 1 2> /dev/null
+  then
+    echo "${test_below_thresh} [Failed record]"
+    err=1
+    return
+  fi
+  # see if there's an at-the-end sample
+  if ! perf script --time "${dummy_timestamp}," -i ${perfdata} -F event | grep -q 'offcpu-time'
+  then
+    echo "${test_below_thresh} [Failed at-the-end samples cannot be found]"
+    err=1
+    return
+  fi
+  # plus there shouldn't be any direct samples
+  if perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q 'offcpu-time'
+  then
+    echo "${test_below_thresh} [Failed direct samples are found when they shouldn't be]"
+    err=1
+    return
+  fi
+  echo "${test_below_thresh} [Success]"
+}
 
 test_offcpu_priv
 
@@ -99,5 +162,13 @@ if [ $err = 0 ]; then
   test_offcpu_child
 fi
 
+if [ $err = 0 ]; then
+  test_offcpu_over_thresh
+fi
+
+if [ $err = 0 ]; then
+  test_offcpu_below_thresh
+fi
+
 cleanup
 exit $err
-- 
2.45.2