[PATCH i-g-t 1/3] tests/intel/xe_wedged: Introduce a new test for Xe device wedged state

[Ghimiray, Himal Prasad]

On 10-04-2024 03:49, Rodrigo Vivi wrote:
> Let's inject a gt_reset failure that will put Xe device in the
> new wedged state, then we confirm the IOCTL is blocked and we
> reload the driver to get back to a clean state for other test
> execution, since wedged state in Xe is a final state that can only
> be cleared with a device rebind/reprobe.
>
> The fault injection of this test is entirely based on xe_uevent
> provided by Himal.
>
> v2: Use rebind instead of module reload (Lucas)
>      And other improvements also pointed out by Lucas.
>
> Cc: Lucas De Marchi <lucas.demarchi at intel.com>
> Cc:  Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>   tests/intel/xe_wedged.c | 108 ++++++++++++++++++++++++++++++++++++++++
>   tests/meson.build       |   1 +
>   2 files changed, 109 insertions(+)
>   create mode 100644 tests/intel/xe_wedged.c
>
> diff --git a/tests/intel/xe_wedged.c b/tests/intel/xe_wedged.c
> new file mode 100644
> index 000000000..f2587cc43
> --- /dev/null
> +++ b/tests/intel/xe_wedged.c
> @@ -0,0 +1,108 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2024 Intel Corporation
> + */
> +
> +/**
> + * TEST: cause fake gt reset failure which put Xe device in wedged state
> + * Category: Software building block
> + * Sub-category: driver
> + * Functionality: wedged
> + * Test category: functionality test
> + */
> +
> +#include <limits.h>
> +#include <dirent.h>
> +
> +#include "igt.h"
> +#include "igt_device.h"
> +#include "igt_kmod.h"
> +#include "igt_sysfs.h"
> +
> +#include "xe/xe_ioctl.h"
> +
> +static void force_wedged(int fd)
> +{
> +	igt_debugfs_write(fd, "fail_gt_reset/probability", "100");
> +	igt_debugfs_write(fd, "fail_gt_reset/times", "2");
> +
> +	xe_force_gt_reset(fd, 0);
> +	sleep(1);
> +}
> +
> +static int rebind_xe(int fd)
> +{
> +	char pci_slot[NAME_MAX];
> +	int sysfs;
> +
> +	igt_device_get_pci_slot_name(fd, pci_slot);
> +
> +	sysfs = open("/sys/bus/pci/drivers/xe", O_DIRECTORY);
> +	igt_assert(sysfs);
> +
> +        igt_assert(igt_sysfs_set(sysfs, "unbind", pci_slot));
> +
> +	/*
> +	 * We need to close the client for a proper release, before
> +	 * binding back again.
> +	 */
> +	close(fd);
> +
> +        igt_assert(igt_sysfs_set(sysfs, "bind", pci_slot));
> +	close(sysfs);
> +
> +	/* Renew the client connection */
> +	fd = drm_open_driver(DRIVER_XE);
> +	igt_assert(fd);
> +
> +	return fd;
> +}
> +
> +static int simple_ioctl(int fd)
> +{
> +	int ret;
> +
> +	struct drm_xe_vm_create create = {
> +		.extensions = 0,
> +		.flags = 0,
> +	};
> +
> +	ret = igt_ioctl(fd, DRM_IOCTL_XE_VM_CREATE, &create);
> +
> +	if (ret == 0)
> +		xe_vm_destroy(fd, create.vm_id);
> +
> +	return ret;
> +}
> +
> +/**
> + * SUBTEST: basic-wedged
> + * Description: Force Xe device wedged after injecting a failure in GT reset
> + */
> +igt_main
> +{
> +	int fd;
> +
> +	igt_fixture {
> +		fd = drm_open_driver(DRIVER_XE);
> +	}
> +
> +	igt_subtest("basic-wedged") {
> +		igt_require(igt_debugfs_exists(fd, "fail_gt_reset/probability",
> +					       O_RDWR));
> +
> +		igt_assert_eq(simple_ioctl(fd), 0);
> +		force_wedged(fd);
> +		igt_assert_neq(simple_ioctl(fd), 0);
> +		fd = rebind_xe(fd);
> +		igt_assert_eq(simple_ioctl(fd), 0);
> +	}
> +
> +	igt_fixture {
> +		if (igt_debugfs_exists(fd, "fail_gt_reset/probability", O_RDWR)) {
> +			igt_debugfs_write(fd, "fail_gt_reset/probability", "0");
> +			igt_debugfs_write(fd, "fail_gt_reset/times", "1");
> +		}
> +		drm_close_driver(fd);
> +	}
> +}


Patch LGTM.

Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>


> diff --git a/tests/meson.build b/tests/meson.build
> index a856510fc..65b8bf23b 100644
> --- a/tests/meson.build
> +++ b/tests/meson.build
> @@ -274,6 +274,7 @@ intel_kms_progs = [
>   ]
>   
>   intel_xe_progs = [
> +	'xe_wedged',
>   	'xe_ccs',
>   	'xe_create',
>   	'xe_compute',