Re: [PATCH i-g-t 4/4] tests/intel/xe_fault_injection: Inject errors during xe_guc_ct_send_recv & xe_guc_mmio_send_recv.

[Francois Dugast <francois.dugast@intel.com>]

On Fri, Feb 07, 2025 at 12:59:02PM +0530, 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.
> 
> Error can be injected using:
> igt@xe_fault_injection@probe-fail-guc-xe_guc_ct_send_recv
> igt@xe_fault_injection@probe-fail-guc-xe_guc_mmio_send_recv
> 
> Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
> Cc: Michał Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Francois Dugast <francois.dugast@intel.com>
> ---
>  tests/intel/xe_fault_injection.c | 41 ++++++++++++++++++++++++++++++++
>  1 file changed, 41 insertions(+)
> 
> diff --git a/tests/intel/xe_fault_injection.c b/tests/intel/xe_fault_injection.c
> index 9432828c2..288a5c384 100644
> --- a/tests/intel/xe_fault_injection.c
> +++ b/tests/intel/xe_fault_injection.c
> @@ -231,6 +231,34 @@ inject_fault_probe(int fd, char pci_slot[], const char function_name[])
>  	xe_sysfs_driver_do(fd, pci_slot, XE_SYSFS_DRIVER_TRY_UNBIND);
>  }
>  
> +/**
> + * 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;
> +	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);
> +	}

This loop is specific to the guc test, it is not present for other tests.
What is different about this test, why do we need to inject a fault at a
given iteration?

In case IGT_FAULT_INJECT_ITERATION is not set, why running
inject_fault_probe() 100 times instead of just once like with existing
tests during probe?

> +}
> +
>  static int
>  simple_vm_create(int fd, unsigned int flags)
>  {
> @@ -330,6 +358,7 @@ igt_main
>  {
>  	int fd;
>  	char pci_slot[NAME_MAX];
> +	struct fault_injection_params fault_params;

This struct is used only in probe_fail_guc() so it could be local to that
function, along with the memcpy() below.

Francois

>  	const struct section {
>  		const char *name;
>  		unsigned int flags;
> @@ -363,6 +392,11 @@ igt_main
>  		{ "xe_vma_ops_alloc" },
>  		{ }
>  	};
> +	const struct section guc_fail_functions[] = {
> +		{ "xe_guc_mmio_send_recv" },
> +		{ "xe_guc_ct_send_recv" },
> +		{ }
> +	};
>  
>  	igt_fixture {
>  		igt_require(fail_function_injection_enabled());
> @@ -387,6 +421,13 @@ 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 {
>  		drm_close_driver(fd);
>  		xe_sysfs_driver_do(fd, pci_slot, XE_SYSFS_DRIVER_BIND);
> -- 
> 2.35.3
>