[PATCH] tests/intel/xe_fault_injection: Ignore *ERROR* dmesg reports

[Michal Wajdeczko]

Hi,

On 03.06.2025 18:18, Jonathan Cavitt wrote:
> From: Satyanarayana K V P <satyanarayana.k.v.p at intel.com>

since this looks like a follow-up rev of the original patch, there was
no need to change subject and there should be a change log at the end

> 
> 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.
> 
> However, we can safely assert that all dmesg reports that contain
> *ERROR* in their message can be ignored, so add them to the dmesg ignore
> list.  This unfortunately does not include the device probe error
> itself, so that must be added separately.
> 
> While we're here, we should also assert that any errors we see are only
> coming from the target PCI device.
> 
> Fixes: 5dcf915415ee ("tests/intel/xe_fault_injection: Ignore expected errors")

I'm not sure it needs Fixes: tag as it wasn't badly broken

> Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p at intel.com>
> Signed-off-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
> Suggested-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
> Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
> Suggested-by: Lucas De Marchi <lucas.demarchi at intel.com>
> Cc: Francois Dugast <francois.dugast at intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
> Cc: John Harrison <john.c.harrison at intel.com>
> 
> ---
>  tests/intel/xe_fault_injection.c | 39 ++++++++++++--------------------
>  1 file changed, 15 insertions(+), 24 deletions(-)
> 
> diff --git a/tests/intel/xe_fault_injection.c b/tests/intel/xe_fault_injection.c
> index 9fe6bfe351..a4a08af5f7 100644
> --- a/tests/intel/xe_fault_injection.c
> +++ b/tests/intel/xe_fault_injection.c
> @@ -64,28 +64,19 @@ 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(int fd)

nit: this could be

	ignore_dmesg_errors_from_dut(fd)

and since it's quite generic maybe it could moved to lib/ near

	igt_emit_ignore_dmesg_regex(regex)
as
	igt_ignore_dmesg_errors_from_dut(fd)


>  {
> -	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.
> +	 * Driver probe is expected to fail in all cases, so ignore in igt_runner.
> +	 * Additionally, all error-level reports are expected, so ignore those as well.
>  	 */
> -	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");
> -	}
> +	char store[1024] = "probe with driver xe failed with error|\\*ERROR\\*";

	static const char store[] = ..

> +	char pci_slot[NAME_MAX];
> +	char regex[1024];
> +
> +	/* All dmesg reports should only target the pci slot of the given fd */
> +	igt_device_get_pci_slot_name(fd, pci_slot);
> +	snprintf(regex, 1024, "%s:.*(%s)", pci_slot, store);

	snprintf(regex, sizeof(regex), ...

>  
>  	igt_emit_ignore_dmesg_regex(regex);
>  }
> @@ -234,7 +225,7 @@ 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(fd);

not sure how this filtering really works, but maybe it will be
sufficient to call that once in the fixup ?

>  	injection_list_add(function_name);
>  	set_retval(function_name, INJECT_ERRNO);
>  
> @@ -299,7 +290,7 @@ 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(fd);
>  	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 +325,7 @@ 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(fd);
>  	injection_list_add(function_name);
>  	set_retval(function_name, INJECT_ERRNO);
>  	igt_assert(simple_vm_create(fd, flags) != 0);
> @@ -397,7 +388,7 @@ 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(fd);
>  	injection_list_add(function_name);
>  	set_retval(function_name, INJECT_ERRNO);
>  	igt_assert(simple_vm_bind(fd, vm) != 0);
> @@ -445,7 +436,7 @@ 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(fd);
>  	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);