[PATCH linux-next] perf test: Skip failing 'perf test aslr' test case

[PATCH linux-next] perf test: Skip failing 'perf test aslr' test case

[Thomas Richter]

The test case 'perf test aslr' fails on s390. The root cause of the
failure is subtest test_callchain_aslr. This test invokes command

 # ./perf record -g -e task-clock:u -o /tmp/perf-test-aslr \
	-- perf test -w noploop 3

to generate a call stack using event task-clock:u. On s390 this defaults
to '--call-graph dwarf' whereas on x86_64 this defaults to framepointer
(fp) format. The command

 # ./perf inject --aslr -i /tmp/perf-test-aslr

now scans all SAMPLE entries recorded in the perf.data file to convert
possible addresses. This is done in aslr_tool__process_sample() looking
at sample_type bits PERF_SAMPLE_IP, PERF_SAMPLE_TID,
PERF_SAMPLE_TIME, PERF_SAMPLE_PERIOD, PERF_SAMPLE_CALLCHAIN,
PERF_SAMPLE_REGS_USER and PERF_SAMPLE_STACK_USER.
On s390 the samples do not contain FP entries
of type PERF_SAMPLE_CALLCHAIN (the bit is set in sample_type, but the
number of FP entries is 0).
The processing enters the PERF_SAMPLE_STACK_USER portion where the
data is copied to the newly constructed sample and then aborted with
this warning:

 /* TODO: can this be less conservative? */
 pr_debug("Dropping stack user sample as possible ASLR leak\n");

With command line option '--call-graph dwarf' the new output file
does not contain any samples at all. This leads to a missing $new_addr
value in the shell script and a failure.

Fix this and skip this subtest. Emit a hint that this subtest is
currently unsupported on all platform when option --call-graph dwarf
is selected.
Since one subtest is skipped, the complete test is reported as
skipped.

Fixes: 60bc9fbc0589 ("perf test: Add inject ASLR test")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/shell/inject_aslr.sh | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/inject_aslr.sh b/tools/perf/tests/shell/inject_aslr.sh
index c00461828ea7..7fdb43679dc8 100755
--- a/tools/perf/tests/shell/inject_aslr.sh
+++ b/tools/perf/tests/shell/inject_aslr.sh
@@ -135,8 +135,15 @@ test_callchain_aslr() {
     echo "Callchain ASLR test [Failed - no noploop samples in original file]"
     err=1
   elif [ -z "$new_addr" ]; then
-    echo "Callchain ASLR test [Failed - could not find remapped address]"
-    err=1
+    if perf evlist -v -i "${data}" | grep -q 'sample_type:.*STACK_USER'; then
+      echo "Dropping stack user sample as possible ASLR leak"
+      echo "Call-graph dwarf not supported with 'perf inject --aslr'"
+      echo "Callchain ASLR test [Skip]"
+      err=2
+    else
+      echo "Callchain ASLR test [Failed - could not find remapped address]"
+      err=1
+    fi
   elif [ "$orig_addr" = "$new_addr" ]; then
     echo "Callchain ASLR test [Failed - addresses are not remapped]"
     err=1
-- 
2.54.0

Re: [PATCH linux-next] perf test: Skip failing 'perf test aslr' test case

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Unconditionally setting `err=2` when skipping `test_callchain_aslr` masks prior test failures.
- [Medium] Skipping the test incorrectly triggers the test failure cleanup path, leaking the temporary directory in `/tmp/`.
--

commit d772895777a1677561d1802ac157c32ce73e1379
Author: Thomas Richter <tmricht@linux.ibm.com>

perf test: Skip failing 'perf test aslr' test case

The test case 'perf test aslr' fails on s390. This commit fixes the failure
by skipping the subtest test_callchain_aslr and emitting a hint when the
--call-graph dwarf option is selected.

Fixes: 60bc9fbc0589 ("perf test: Add inject ASLR test")

> diff --git a/tools/perf/tests/shell/inject_aslr.sh b/tools/perf/tests/shell/inject_aslr.sh
> index c00461828ea79..7fdb43679dc84 100755
> --- a/tools/perf/tests/shell/inject_aslr.sh
> +++ b/tools/perf/tests/shell/inject_aslr.sh
> @@ -135,8 +135,15 @@ test_callchain_aslr() {
>      echo "Callchain ASLR test [Failed - no noploop samples in original file]"
>      err=1
>    elif [ -z "$new_addr" ]; then
> -    echo "Callchain ASLR test [Failed - could not find remapped address]"
> -    err=1
> +    if perf evlist -v -i "${data}" | grep -q 'sample_type:.*STACK_USER'; then
> +      echo "Dropping stack user sample as possible ASLR leak"
> +      echo "Call-graph dwarf not supported with 'perf inject --aslr'"
> +      echo "Callchain ASLR test [Skip]"
> +      err=2

[Severity: Medium]
Does unconditionally setting err=2 here mask prior test failures?

If an earlier subtest fails, the global err variable is set to 1. When
test_callchain_aslr() decides to skip and assigns err=2, it overwrites
this previous failure state.

Since the perf test framework treats an exit code of 2 as a SKIP, the test
suite will report the entire script as skipped, completely hiding the
actual failure from the prior subtest.

[Severity: Medium]
Will skipping this test inadvertently trigger the test failure cleanup path
and leak the temporary directory?

The cleanup() function in tools/perf/tests/shell/inject_aslr.sh explicitly
aborts deletion if the exit code or err is non-zero:

cleanup() {
  if [ "${exit_code}" -ne 0 ] || [ "${err}" -ne 0 ]; then
    echo "Test failed! Preserving temp directory: ${temp_dir}"
    return
  fi
  ...
}

Because cleanup() was not updated to handle the new skip state, it
mistakenly treats err=2 as a test failure. This unconditionally leaves
behind the /tmp/perf-test-aslr.XXXXXX directory every time the test skips.

> +    else
> +      echo "Callchain ASLR test [Failed - could not find remapped address]"
> +      err=1
> +    fi
>    elif [ "$orig_addr" = "$new_addr" ]; then
>      echo "Callchain ASLR test [Failed - addresses are not remapped]"
>      err=1

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619093531.4038655-1-tmricht@linux.ibm.com?part=1