[PATCH v1 05/12] perf tests: Skip metrics validation if system-wide recording lacks permission

[Ian Rogers <irogers@google.com>]

The metrics value validation test requires system-wide recording (`-a`),
which can fail on systems without root permissions or where paranoid
levels restrict tracing. Add a check to skip the test if `-a` is not
supported.

Also fix false negatives during validation by updating parse error string
patterns and resolving issues in metric list generation.

Fixes: 3ad7092f5145 ("perf test: Add metric value validation test")
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../tests/shell/lib/perf_metric_validation.py | 11 ++--
 tools/perf/tests/shell/stat_all_metrics.sh    | 63 ++++++++++---------
 tools/perf/tests/shell/stat_metrics_values.sh |  7 +++
 3 files changed, 48 insertions(+), 33 deletions(-)

diff --git a/tools/perf/tests/shell/lib/perf_metric_validation.py b/tools/perf/tests/shell/lib/perf_metric_validation.py
index dea8ef1977bf..3d52f94f22b9 100644
--- a/tools/perf/tests/shell/lib/perf_metric_validation.py
+++ b/tools/perf/tests/shell/lib/perf_metric_validation.py
@@ -383,10 +383,13 @@ class Validator:
         wl = workload.split()
         command.extend(wl)
         print(" ".join(command))
-        cmd = subprocess.run(command, stderr=subprocess.PIPE, encoding='utf-8')
-        data = [x+'}' for x in cmd.stderr.split('}\n') if x]
-        if data[0][0] != '{':
-            data[0] = data[0][data[0].find('{'):]
+        cmd = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, encoding='utf-8')
+        lines = cmd.stderr.splitlines() + cmd.stdout.splitlines()
+        data = []
+        for line in lines:
+            line = line.strip()
+            if line.startswith('{') and line.endswith('}'):
+                data.append(line)
         return data
 
     def collect_perf(self, workload: str):
diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh
index b582d23f28c9..5ee869452ee7 100755
--- a/tools/perf/tests/shell/stat_all_metrics.sh
+++ b/tools/perf/tests/shell/stat_all_metrics.sh
@@ -12,38 +12,53 @@ system_wide_flag="-a"
 if ParanoidAndNotRoot 0
 then
   system_wide_flag=""
-  test_prog="perf test -w noploop"
+  test_prog="perf test -w noploop 0.01"
 fi
 
+check_metric() {
+  local output="$1"
+  local status="$2"
+  local metric="$3"
+
+  if [[ $status -ne 0 || ! "$output" =~ ${metric:0:50} ]]; then
+    return 1
+  fi
+
+  if [[ "$output" =~ "<not counted>" || "$output" =~ "<not supported>" ]]; then
+    return 1
+  fi
+
+  return 0
+}
+
 skip=0
 err=3
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
   result=$(perf stat -M "$m" $system_wide_flag -- $test_prog 2>&1)
   result_err=$?
-  if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
-  then
-    # No error result and metric shown.
+
+  if check_metric "$result" $result_err "$m"; then
     if [[ "$err" -ne 1 ]]
     then
       err=0
     fi
     continue
   fi
-  if [[ "$result" =~ "Cannot resolve IDs for" || "$result" =~ "No supported events found" ]]
-  then
-    if [[ $(perf list --raw-dump $m) == "Default"* ]]
+
+  result=$(perf stat -M "$m" $system_wide_flag -- perf test -w noploop 0.1 2>&1)
+  result_err=$?
+
+  if check_metric "$result" $result_err "$m"; then
+    if [[ "$err" -ne 1 ]]
     then
-      echo "[Ignored $m] failed but as a Default metric this can be expected"
-      echo $result
-      continue
+      err=0
     fi
-    echo "[Failed $m] Metric contains missing events"
-    echo $result
-    err=1 # Fail
     continue
-  elif [[ "$result" =~ \
-        "Access to performance monitoring and observability operations is limited" ]]
+  fi
+
+  # If retry also failed, determine if we skip, ignore, or fail
+  if [[ "$result" =~ "Access to performance monitoring and observability operations is limited" ]]
   then
     echo "[Skipped $m] Permission failure"
     echo $result
@@ -61,7 +76,9 @@ for m in $(perf list --raw-dump metrics); do
       skip=1
     fi
     continue
-  elif [[ "$result" =~ "<not supported>" ]]
+  elif [[ "$result" =~ "<not supported>" || \
+          "$result" =~ "Cannot resolve IDs for" || \
+          "$result" =~ "No supported events found" ]]
   then
     if [[ $(perf list --raw-dump $m) == "Default"* ]]
     then
@@ -105,19 +122,7 @@ for m in $(perf list --raw-dump metrics); do
     continue
   fi
 
-  # Failed, possibly the workload was too small so retry with something longer.
-  result=$(perf stat -M "$m" $system_wide_flag -- perf bench internals synthesize 2>&1)
-  result_err=$?
-  if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
-  then
-    # No error result and metric shown.
-    if [[ "$err" -ne 1 ]]
-    then
-      err=0
-    fi
-    continue
-  fi
-  echo "[Failed $m] has non-zero error '$result_err' or not printed in:"
+  echo "[Failed $m] has non-zero error '$result_err' or not printed/counted in:"
   echo "$result"
   err=1
 done
diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh
index 30566f0b5427..76f1e99d1273 100755
--- a/tools/perf/tests/shell/stat_metrics_values.sh
+++ b/tools/perf/tests/shell/stat_metrics_values.sh
@@ -8,6 +8,13 @@ shelldir=$(dirname "$0")
 
 grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; }
 
+# Skip if no permission to record system-wide events
+if ! perf stat -a -e instructions sleep 0.01 >/dev/null 2>&1; then
+  echo "Skipping: no permission to record system-wide events (-a)"
+  exit 2
+fi
+
+
 pythonvalidator=$(dirname $0)/lib/perf_metric_validation.py
 rulefile=$(dirname $0)/lib/perf_metric_validation_rules.json
 tmpdir=$(mktemp -d /tmp/__perf_test.program.XXXXX)
-- 
2.54.0.1136.gdb2ca164c4-goog