166f10836a: perf-sanity-tests.Object_code_reading.fail
kernel test robot
build botHello,
kernel test robot noticed "perf-sanity-tests.Object_code_reading.fail" on:
commit: 166f10836a653dfa280d4335603b52f685b8b1ef ("perf/core: Fix kernel register info leak via hardware skid") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
[test failed on linux-next/master 68142f986ff04b2b70b31db00f719bf690f64a9a]
in testcase: perf-sanity-tests
with following parameters:
perf_compiler: gcc group: group-00
config: x86_64-rhel-9.4-bpf
compiler: gcc-14
test machine: 20 threads 1 sockets (Commet Lake) with 16G memory
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-lkp/[email protected]
2026-09-14 10:03:47 sudo ASAN_OPTIONS=fast_unwind_on_malloc=0 /usr/src/linux-perf-x86_64-rhel-9.4-bpf-166f10836a653dfa280d4335603b52f685b8b1ef/tools/perf/perf test 23 -v 23: Object code reading : Running (1 active)
---- start ----
...
Reading object code for memory address: 0x7f6d46bf44de File is: /usr/lib/x86_64-linux-gnu/libc.so.6
Already tested /usr/lib/x86_64-linux-gnu/libc.so.6 @ 0xff4de - skipping Reading object code for memory address: 0x7f6d46bf44de File is: /usr/lib/x86_64-linux-gnu/libc.so.6 Already tested /usr/lib/x86_64-linux-gnu/libc.so.6 @ 0xff4de - skipping Reading object code for memory address: 0 thread__find_map failed
---- end(-1) ----
23: Object code reading : FAILED!
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260915/[email protected]
This defect was originally reported on the perf/core branch (see https://lore.kernel.org/oe-lkp/[email protected]/). Since the culprit patch has now been merged into the mainline kernel, we have re-submitted the report to ensure proper tracking.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Thanks, this looks the same issue with
https://lore.kernel.org/oe-lkp/[email protected]/.
To avoid the kernel address leakage, perf clears the kernel address to 0 if only user space SAMPLE_IP is required.
The proper fix could need to refine the test case and filter out these 0 IP addresses. The fix is in progress and would be posted later.
Quoted 43 lines · kernel test robot
Hello,
kernel test robot noticed "perf-sanity-tests.Object_code_reading.fail" on:
commit:
166f10836a653dfa280d4335603b52f685b8b1ef("perf/core: Fix kernel register info leak via hardware skid") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master[test failed on linux-next/master
68142f986ff04b2b70b31db00f719bf690f64a9a]in testcase: perf-sanity-tests
with following parameters:perf_compiler: gcc group: group-00config: x86_64-rhel-9.4-bpf
compiler: gcc-14
test machine: 20 threads 1 sockets (Commet Lake) with 16G memoryIf you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-lkp/[email protected]2026-09-14 10:03:47 sudo ASAN_OPTIONS=fast_unwind_on_malloc=0 /usr/src/linux-perf-x86_64-rhel-9.4-bpf-166f10836a653dfa280d4335603b52f685b8b1ef/tools/perf/perf test 23 -v 23: Object code reading : Running (1 active)---- start ----
...
Reading object code for memory address:0x7f6d46bf44deFile is:/usr/lib/x86_64-linux-gnu/libc.so.6
Already tested/usr/lib/x86_64-linux-gnu/libc.so.6@0xff4de- skipping Reading object code for memory address:0x7f6d46bf44deFile is:/usr/lib/x86_64-linux-gnu/libc.so.6Already tested/usr/lib/x86_64-linux-gnu/libc.so.6@0xff4de- skipping Reading object code for memory address: 0thread__find_mapfailed
---- end(-1) ----
23: Object code reading : FAILED!The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260915/[email protected]This defect was originally reported on the perf/core branch (see https://lore.kernel.org/oe-lkp/[email protected]/). Since the culprit patch has now been merged into the mainline kernel, we have re-submitted the report to ensure proper tracking.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki