[i-g-t,v4,2/3] tests/intel/xe_fault_injection: Inject errors during xe_guc_ct_send_recv & xe_guc_mmio_send_recv.

[Laguna, Lukasz]

On 3/28/2025 12:15, Satyanarayana K V P wrote:
> Use the kernel fault injection infrastructure to test error handling
> of xe during driver probe when executing xe_guc_ct_send_recv() /
> xe_guc_mmio_send_recv() so that more code paths are tested, such as
> error handling and unwinding.
>
> All xe_init() kind of functions are called just once during driver probe,
> so it is sufficient to fail first/all calls to them. Driver communicates
> with the GuC multiple times, and the real failure can happen at different
> call, hence the need to inject failure in GuC communication functions,
> like guc_mmio_send() or guc_ct_send(), but it can't be just first call or
> all calls, but we need to be able to select specific iteration to fail.
>
> To address this problem, the environmental variable IGT_FAULT_INJECT_ITERATION

I think it'd be better to use test parameter instead of environment 
variable. Please check igt_main_args() and consider using it.

> is used. If the IGT_FAULT_INJECT_ITERATION is not exported, an error will
> be injected in every possible function call starting from first up to the
> max number of iteration defined by INJECT_ITERATIONS, currently hardcoded
> as 100. Also, using IGT_FAULT_INJECT_ITERATION, an error can be injected at
> specific function call.
>
> Error can be injected using:
> igt at xe_fault_injection@probe-fail-guc-xe_guc_ct_send_recv
> igt at xe_fault_injection@probe-fail-guc-xe_guc_mmio_send_recv
>
> Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p at intel.com>
> Cc: Michał Wajdeczko <michal.wajdeczko at intel.com>
> Cc: Francois Dugast <francois.dugast at intel.com>
> Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com>
> ---
>   tests/intel/xe_fault_injection.c | 61 ++++++++++++++++++++++++++++++++
>   1 file changed, 61 insertions(+)
>
> diff --git a/tests/intel/xe_fault_injection.c b/tests/intel/xe_fault_injection.c
> index 1325a1716..a49070b4d 100644
> --- a/tests/intel/xe_fault_injection.c
> +++ b/tests/intel/xe_fault_injection.c
> @@ -26,6 +26,7 @@
>   #define INJECT_ERRNO	-ENOMEM
>   #define BO_ADDR		0x1a0000
>   #define BO_SIZE		(1024*1024)
> +#define INJECT_ITERATIONS	100
>   
>   enum injection_list_action {
>   	INJECTION_LIST_ADD,
> @@ -43,6 +44,24 @@ struct fault_injection_params {
>   	uint32_t space;
>   };
>   
> +/**
> + *  Introduce a new environmental variable IGT_FAULT_INJECT_ITERATION
> + *  using which an error can be injected at specific function call.
> + *  When unset test will run for INJECT_ITERATIONS iterations.
> + *  When set to <=0 or malformed - same as unset.
> + *  When set to >0 it will run single n-th iteration only.
> + */
> +static int get_fault_inject_iter(void)
> +{
> +	const char *env = getenv("IGT_FAULT_INJECT_ITERATION");
> +
> +	/* Return 0 if not exported / -ve value */
> +	if (!env || atoi(env) <= 0)
> +		return 0;
> +
> +	return atoi(env);
> +}
> +
>   static int fail_function_open(void)
>   {
>   	int debugfs_fail_function_dir_fd;
> @@ -228,6 +247,34 @@ inject_fault_probe(int fd, char pci_slot[], const char function_name[])
>   	injection_list_do(INJECTION_LIST_REMOVE, function_name);
>   }
>   
> +/**
> + * SUBTEST: probe-fail-guc-%s
> + * Description: inject an error in the injectable function %arg[1] then reprobe driver
> + * Functionality: fault
> + *
> + * arg[1]:
> + * @xe_guc_mmio_send_recv:     Inject an error when calling xe_guc_mmio_send_recv
> + * @xe_guc_ct_send_recv:       Inject an error when calling xe_guc_ct_send_recv
> + */
> +static void probe_fail_guc(int fd, char pci_slot[], const char function_name[],
> +               struct fault_injection_params *fault_params)
> +{
> +	int iter_start = 0, iter_end = 0, iter = 0;
> +
> +	igt_assert(fault_params);
> +
> +	/* Get the iteration count from environment */
> +	iter = get_fault_inject_iter();
> +	iter_start = iter ? : 0;

Can't it be just iter_start = iter; ?

> +	iter_end = iter ? iter + 1 : INJECT_ITERATIONS;
> +	for (int i = iter_start; i < iter_end; i++) {
> +		fault_params->space = i;
> +		setup_injection_fault(fault_params);
> +		inject_fault_probe(fd, pci_slot, function_name);
> +		igt_kmod_unbind("xe", pci_slot);
> +	}
> +}
> +
>   /**
>    * SUBTEST: exec-queue-create-fail-%s
>    * Description: inject an error in function %arg[1] used in exec queue create IOCTL to make it fail
> @@ -406,6 +453,7 @@ igt_main
>   {
>   	int fd, sysfs;
>   	struct drm_xe_engine_class_instance *hwe;
> +	struct fault_injection_params fault_params;
>   	static uint32_t devid;
>   	char pci_slot[NAME_MAX];
>   	const struct section {
> @@ -463,6 +511,12 @@ igt_main
>   		{ }
>   	};
>   
> +	const struct section guc_fail_functions[] = {
> +		{ "xe_guc_mmio_send_recv" },
> +		{ "xe_guc_ct_send_recv" },
> +		{ }
> +	};
> +
>   	igt_fixture {
>   		igt_require(fail_function_injection_enabled());
>   		fd = drm_open_driver(DRIVER_XE);
> @@ -505,6 +559,13 @@ igt_main
>   		igt_subtest_f("inject-fault-probe-function-%s", s->name)
>   			inject_fault_probe(fd, pci_slot, s->name);
>   
> +   for (const struct section *s = guc_fail_functions; s->name; s++)
> +       igt_subtest_f("probe-fail-guc-%s", s->name) {
> +           memcpy(&fault_params, &default_fault_params,
> +                   sizeof(struct fault_injection_params));
> +           probe_fail_guc(fd, pci_slot, s->name, &fault_params);
> +       }
> +
>   	igt_fixture {
>   		close(sysfs);
>   		drm_close_driver(fd);