[PATCH 1/4] drm/xe: Introduce a simple wedged state

[Ghimiray, Himal Prasad]

On 10-04-2024 03:45, Rodrigo Vivi wrote:
> Introduce a very simple 'wedged' state where any attempt
> to access the GPU is entirely blocked.
>
> On some critical cases, like on gt_reset failure, we need to
> block any other attempt to use the GPU. Otherwise we are at
> a risk of reaching cases that would force us to reboot the machine.
>
> So, when this cases are identified we corner and block any GPU
> access. No IOCTL and not even another GT reset should be attempted.
>
> The 'wedged' state in Xe is an end state with no way back.
> Only a device "re-probe" (unbind + bind) can restore the GPU access.
>
> v2: - s/wedged/busted (Lucas)
>      - use unbind+bind instead of module reload (Lucas)
>      - added more info on unbind operations and instruction on bug report
>      - only print the message once.
>
> v3: - s/busted/wedged (Ashutosh, Tvrtko, Thomas)
>      - don't assume user has sudo and tee available (Lucas)
>
> v4: - remove unnecessary cases around ct communication or migration.
>
> Cc: Ashutosh Dixit <ashutosh.dixit at intel.com>
> Cc: Tvrtko Ursulin <tursulin at ursulin.net>
> Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> Cc: Lucas De Marchi <lucas.demarchi at intel.com>
> Cc: Anshuman Gupta <anshuman.gupta at intel.com>
> Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com> #v2
RB is valid for this patch too.
> Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com> #v2
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>   drivers/gpu/drm/xe/xe_device.c       |  6 ++++++
>   drivers/gpu/drm/xe/xe_device.h       | 20 ++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_device_types.h |  3 +++
>   drivers/gpu/drm/xe/xe_gt.c           |  5 ++++-
>   drivers/gpu/drm/xe/xe_guc_pc.c       |  3 +++
>   5 files changed, 36 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index 9083f5e02dd9..67de795e43b3 100644
> --- a/drivers/gpu/drm/xe/xe_device.c
> +++ b/drivers/gpu/drm/xe/xe_device.c
> @@ -142,6 +142,9 @@ static long xe_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
>   	struct xe_device *xe = to_xe_device(file_priv->minor->dev);
>   	long ret;
>   
> +	if (xe_device_wedged(xe))
> +		return -ECANCELED;
> +
>   	ret = xe_pm_runtime_get_ioctl(xe);
>   	if (ret >= 0)
>   		ret = drm_ioctl(file, cmd, arg);
> @@ -157,6 +160,9 @@ static long xe_drm_compat_ioctl(struct file *file, unsigned int cmd, unsigned lo
>   	struct xe_device *xe = to_xe_device(file_priv->minor->dev);
>   	long ret;
>   
> +	if (xe_device_wedged(xe))
> +		return -ECANCELED;
> +
>   	ret = xe_pm_runtime_get_ioctl(xe);
>   	if (ret >= 0)
>   		ret = drm_compat_ioctl(file, cmd, arg);
> diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
> index d413bc2c6be5..c532209c5bbd 100644
> --- a/drivers/gpu/drm/xe/xe_device.h
> +++ b/drivers/gpu/drm/xe/xe_device.h
> @@ -176,4 +176,24 @@ void xe_device_snapshot_print(struct xe_device *xe, struct drm_printer *p);
>   u64 xe_device_canonicalize_addr(struct xe_device *xe, u64 address);
>   u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address);
>   
> +static inline bool xe_device_wedged(struct xe_device *xe)
> +{
> +	return atomic_read(&xe->wedged);
> +}
> +
> +static inline void xe_device_declare_wedged(struct xe_device *xe)
> +{
> +	if (!atomic_xchg(&xe->wedged, 1)) {
> +		xe->needs_flr_on_fini = true;
> +		drm_err(&xe->drm,
> +			"CRITICAL: Xe has declared device %s as wedged.\n"
> +			"IOCTLs and executions are blocked until device is probed again with unbind and bind operations:\n"
> +			"echo '%s' > /sys/bus/pci/drivers/xe/unbind\n"
> +			"echo '%s' > /sys/bus/pci/drivers/xe/bind\n"
> +			"Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/xe/kernel/issues/new\n",
> +			dev_name(xe->drm.dev), dev_name(xe->drm.dev),
> +			dev_name(xe->drm.dev));
> +	}
> +}
> +
>   #endif
> diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
> index faa32407efa5..b9ef60f21750 100644
> --- a/drivers/gpu/drm/xe/xe_device_types.h
> +++ b/drivers/gpu/drm/xe/xe_device_types.h
> @@ -458,6 +458,9 @@ struct xe_device {
>   	/** @needs_flr_on_fini: requests function-reset on fini */
>   	bool needs_flr_on_fini;
>   
> +	/** @wedged: Xe device faced a critical error and is now blocked. */
> +	atomic_t wedged;
> +
>   	/* private: */
>   
>   #if IS_ENABLED(CONFIG_DRM_XE_DISPLAY)
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index cfa5da900461..0844081b88ef 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -633,6 +633,9 @@ static int gt_reset(struct xe_gt *gt)
>   {
>   	int err;
>   
> +	if (xe_device_wedged(gt_to_xe(gt)))
> +		return -ECANCELED;
> +
>   	/* We only support GT resets with GuC submission */
>   	if (!xe_device_uc_enabled(gt_to_xe(gt)))
>   		return -ENODEV;
> @@ -685,7 +688,7 @@ static int gt_reset(struct xe_gt *gt)
>   err_fail:
>   	xe_gt_err(gt, "reset failed (%pe)\n", ERR_PTR(err));
>   
> -	gt_to_xe(gt)->needs_flr_on_fini = true;
> +	xe_device_declare_wedged(gt_to_xe(gt));
>   
>   	return err;
>   }
> diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
> index 521ae24f2314..f4663f1b0a80 100644
> --- a/drivers/gpu/drm/xe/xe_guc_pc.c
> +++ b/drivers/gpu/drm/xe/xe_guc_pc.c
> @@ -902,6 +902,9 @@ static void xe_guc_pc_fini(struct drm_device *drm, void *arg)
>   		return;
>   	}
>   
> +	if (xe_device_wedged(xe))
> +		return;
> +
>   	XE_WARN_ON(xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL));
>   	XE_WARN_ON(xe_guc_pc_gucrc_disable(pc));
>   	XE_WARN_ON(xe_guc_pc_stop(pc));