Hi Janusz,
On 2026-01-13 at 16:59:36 +0100, Janusz Krzysztofik wrote:
> The smem-oom subtest can expectedly result in oom-killer being triggered,
> which then dumps a call trace from a process that triggered it.  If that
> happens to be a process that executes drm or i915 functions then the call
> trace dump contains lines recognized by igt_runner running in piglit mode
> as potential warnings.  If severity of the call trace dump messages is
> NOTICE or higher, which isn't unlikely, then a dmesg-warn result is
> reported despite successful completion of the subtest.
> 
> Fortunately, severity of those call trace dump messages depends on kernel
> default log level which can be controlled from user space over sysctl.
> 
> To avoid false failure reports, relax kernel default log level to INFO so
> those log lines are ignored by igt_runner in piglit mode at an expense of
> call traces from real issues potentially detected by the subtest not
> contributing to the igt_runner reported result.  Since those call traces
> are still available to developers, only submitted with reduced severity,
> that shouldn't hurt as long as the igt_runner still abandons further
> execution and reports an abort result on a kernel taint.
> 
> v3: Move cleanup to an exit handler in case we are killed (Kamil).
> v2: Move default log level setup inside subtest smem-oom (Kamil),
>   - move cleanup there as well.
> 
> Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5493
> Cc: Kamil Konieczny <[email protected]>
> Signed-off-by: Janusz Krzysztofik <[email protected]>
> ---
>  tests/intel/gem_lmem_swapping.c | 61 +++++++++++++++++++++++++++++++--
>  1 file changed, 59 insertions(+), 2 deletions(-)
> 
> diff --git a/tests/intel/gem_lmem_swapping.c b/tests/intel/gem_lmem_swapping.c
> index adae26716c..e68d318fd0 100644
> --- a/tests/intel/gem_lmem_swapping.c
> +++ b/tests/intel/gem_lmem_swapping.c
> @@ -661,6 +661,21 @@ static void gem_leak(int fd, uint64_t alloc)
>       gem_madvise(fd, handle, I915_MADV_DONTNEED);
>  }
>  
> +static FILE *printk;
> +static int console_log_level, default_log_level;
> +
> +static void printk_exit_handler(int sig)
> +{
> +     if (printk) {
> +             rewind(printk);
> +             igt_debug_on(fprintf(printk, "%d %d",
> +                                  console_log_level,
> +                                  default_log_level) != 3);
> +             fclose(printk);
> +             printk = NULL;
> +     }
> +}
> +

I would prefer just using write() with already prepared buf,
not fprintf, as this is for at_exit path and should be fast,
but this is maybe a matter of style.

Reviewed-by: Kamil Konieczny <[email protected]>

Regards,
Kamil

>  static int *lmem_done;
>  
>  static void smem_oom_exit_handler(int sig)
> @@ -861,8 +876,50 @@ int igt_main_args("", long_options, help_str, 
> opt_handler, NULL)
>       }
>  
>       igt_describe("Exercise local memory swapping during exhausting system 
> memory");
> -     dynamic_lmem_subtest(region, regions, "smem-oom")
> -             test_smem_oom(i915, ctx, region);
> +     igt_subtest_with_dynamic("smem-oom") {
> +             unsigned int i;
> +
> +             /*
> +              * This subtest can result in oom-killer being triggered, which
> +              * then dumps a call trace from a process that triggered it.
> +              * If that happens to be a process that executes drm or i915
> +              * functions then the call trace dump contains lines recognized
> +              * by igt_runner as warnings and a dmesg-warn result is
> +              * reported.  To avoid false failure reports, relax kernel
> +              * default log level to INFO for those lines to be ignored by
> +              * igt_runner in piglit mode, at an expense of call traces from
> +              * potential real issues not contributing to the igt_runner
> +              * reported result.  Since those call traces are still available
> +              * to developers, only displayed with relaxed severity, that
> +              * shouldn't hurt as long as igt_runner still abandons further
> +              * execution and reports an abort result on a kernel taint.
> +              */
> +             printk = fopen("/proc/sys/kernel/printk", "r+");
> +             if (!igt_debug_on(!printk)) {
> +                     if (!igt_debug_on(fscanf(printk, "%d %d",
> +                                              &console_log_level,
> +                                              &default_log_level) != 2) &&
> +                         default_log_level < 6) {
> +                             igt_install_exit_handler(printk_exit_handler);
> +
> +                             rewind(printk);
> +                             igt_debug_on(fprintf(printk, "%d 6",
> +                                                  console_log_level) != 3);
> +                     } else {
> +                             fclose(printk);
> +                             printk = NULL;
> +                     }
> +             }
> +
> +             for (i = 0; i < regions->num_regions; i++) {
> +                     region = &regions->regions[i];
> +                     if (region->region.memory_class == 
> I915_MEMORY_CLASS_DEVICE)
> +                             igt_dynamic_f("lmem%u", 
> region->region.memory_instance)
> +                                     test_smem_oom(i915, ctx, region);
> +             }
> +
> +             printk_exit_handler(0);
> +     }
>  
>       igt_fixture() {
>               intel_allocator_multiprocess_stop();
> -- 
> 2.52.0
> 

Reply via email to