[PATCH i-g-t] tests/intel/xe_fault_injection: Ignore all errors while injecting fault

[Daniele Ceraolo Spurio]

On 5/29/2025 6:31 AM, Satyanarayana K V P wrote:
> Currently, numerous fault messages have been included in the dmesg ignore list,
> and this list continues to expand. Each time a new fault injection point is
> introduced or a new feature is activated, additional fault messages appear,
> making it cumbersome to manage the dmesg ignore list.
>
> This new patch automatically ignores all error messages from dmesg, eliminating
> the need to add or maintain a dmesg ignore message list.

This would make the test almost meaningless. If the test finds an actual 
bug (i.e., an error we didn't expect), how would CI detect and report it 
if all errors are ignored? The only situations we would still fail on is 
when the kernel just dies.

Daniele

>
> Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p at intel.com>
> ---
> Cc: Michal Wajdeczko <michal.wajdeczko at intel.com>
> Cc: Francois Dugast <francois.dugast at intel.com>
> Cc: Jonathan Cavitt <jonathan.cavitt at intel.com>
> Cc: John Harrison <John.C.Harrison at Intel.com>
> ---
>   tests/intel/xe_fault_injection.c | 35 +++++++-------------------------
>   1 file changed, 7 insertions(+), 28 deletions(-)
>
> diff --git a/tests/intel/xe_fault_injection.c b/tests/intel/xe_fault_injection.c
> index f9bd5c761..0dffbe5da 100644
> --- a/tests/intel/xe_fault_injection.c
> +++ b/tests/intel/xe_fault_injection.c
> @@ -64,30 +64,9 @@ static int fail_function_open(void)
>   	return debugfs_fail_function_dir_fd;
>   }
>   
> -static bool function_is_part_of_guc(const char function_name[])
> +static void ignore_faults_in_dmesg(void)
>   {
> -	return strstr(function_name, "_guc_") != NULL ||
> -	       strstr(function_name, "_uc_") != NULL ||
> -	       strstr(function_name, "_wopcm_") != NULL;
> -}
> -
> -static void ignore_faults_in_dmesg(const char function_name[])
> -{
> -	/* Driver probe is expected to fail in all cases, so ignore in igt_runner */
> -	char regex[1024] = "probe with driver xe failed with error -12";
> -
> -	/*
> -	 * If GuC module fault is injected, GuC is expected to fail,
> -	 * so also ignore GuC init failures in igt_runner.
> -	 */
> -	if (function_is_part_of_guc(function_name)) {
> -		strcat(regex, "|GT[0-9a-fA-F]*: GuC init failed with -ENOMEM");
> -		strcat(regex, "|GT[0-9a-fA-F]*: Failed to initialize uC .-ENOMEM");
> -		strcat(regex, "|GT[0-9a-fA-F]*: Failed to enable GuC CT	.-ENOMEM");
> -		strcat(regex, "|GT[0-9a-fA-F]*: GuC PC query task state failed:	-ENOMEM");
> -	}
> -
> -	igt_emit_ignore_dmesg_regex(regex);
> +	igt_emit_ignore_dmesg_regex(".*");
>   }
>   
>   /*
> @@ -234,7 +213,7 @@ inject_fault_probe(int fd, char pci_slot[], const char function_name[])
>   	igt_info("Injecting error \"%s\" (%d) in function \"%s\"\n",
>   		 strerror(-INJECT_ERRNO), INJECT_ERRNO, function_name);
>   
> -	ignore_faults_in_dmesg(function_name);
> +	ignore_faults_in_dmesg();
>   	injection_list_add(function_name);
>   	set_retval(function_name, INJECT_ERRNO);
>   
> @@ -299,7 +278,7 @@ exec_queue_create_fail(int fd, struct drm_xe_engine_class_instance *instance,
>   	igt_assert_eq(__xe_exec_queue_create(fd, vm, 1, 1, instance, 0, &exec_queue_id), 0);
>   	xe_exec_queue_destroy(fd, exec_queue_id);
>   
> -	ignore_faults_in_dmesg(function_name);
> +	ignore_faults_in_dmesg();
>   	injection_list_add(function_name);
>   	set_retval(function_name, INJECT_ERRNO);
>   	igt_assert(__xe_exec_queue_create(fd, vm, 1, 1, instance, 0, &exec_queue_id) != 0);
> @@ -334,7 +313,7 @@ vm_create_fail(int fd, const char function_name[], unsigned int flags)
>   {
>   	igt_assert_eq(simple_vm_create(fd, flags), 0);
>   
> -	ignore_faults_in_dmesg(function_name);
> +	ignore_faults_in_dmesg();
>   	injection_list_add(function_name);
>   	set_retval(function_name, INJECT_ERRNO);
>   	igt_assert(simple_vm_create(fd, flags) != 0);
> @@ -397,7 +376,7 @@ vm_bind_fail(int fd, const char function_name[])
>   
>   	igt_assert_eq(simple_vm_bind(fd, vm), 0);
>   
> -	ignore_faults_in_dmesg(function_name);
> +	ignore_faults_in_dmesg();
>   	injection_list_add(function_name);
>   	set_retval(function_name, INJECT_ERRNO);
>   	igt_assert(simple_vm_bind(fd, vm) != 0);
> @@ -445,7 +424,7 @@ oa_add_config_fail(int fd, int sysfs, int devid, const char function_name[])
>   	igt_assert(igt_sysfs_scanf(sysfs, path, "%" PRIu64, &config_id) == 1);
>   	igt_assert_eq(intel_xe_perf_ioctl(fd, DRM_XE_OBSERVATION_OP_REMOVE_CONFIG, &config_id), 0);
>   
> -	ignore_faults_in_dmesg(function_name);
> +	ignore_faults_in_dmesg();
>   	injection_list_add(function_name);
>   	set_retval(function_name, INJECT_ERRNO);
>   	igt_assert_lt(intel_xe_perf_ioctl(fd, DRM_XE_OBSERVATION_OP_ADD_CONFIG, &config), 0);