Re: [PATCH v4] drm/panthor: Report innocent group kill

[Boris Brezillon <boris.brezillon@collabora.com>]

On Wed, 11 Dec 2024 09:05:00 +0100
Boris Brezillon <boris.brezillon@collabora.com> wrote:

> Groups can be killed during a reset even though they did nothing wrong.
> That usually happens when the FW is put in a bad state by other groups,
> resulting in group suspension failures when the reset happens.
> 
> If we end up in that situation, flag the group innocent and report
> innocence through a new DRM_PANTHOR_GROUP_STATE flag.
> 
> Bump the minor driver version to reflect the uAPI change.
> 
> Changes in v4:
> - Add an entry to the driver version changelog
> - Add R-bs
> 
> Changes in v3:
> - Actually report innocence to userspace
> 
> Changes in v2:
> - New patch
> 
> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
> Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
> Reviewed-by: Steven Price <steven.price@arm.com>

Queued to drm-misc-next.

> ---
>  drivers/gpu/drm/panthor/panthor_drv.c   |  3 ++-
>  drivers/gpu/drm/panthor/panthor_sched.c | 18 ++++++++++++++++++
>  include/uapi/drm/panthor_drm.h          |  9 +++++++++
>  3 files changed, 29 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
> index ac7e53f6e3f0..1498c97b4b85 100644
> --- a/drivers/gpu/drm/panthor/panthor_drv.c
> +++ b/drivers/gpu/drm/panthor/panthor_drv.c
> @@ -1493,6 +1493,7 @@ static void panthor_debugfs_init(struct drm_minor *minor)
>   * - 1.1 - adds DEV_QUERY_TIMESTAMP_INFO query
>   * - 1.2 - adds DEV_QUERY_GROUP_PRIORITIES_INFO query
>   *       - adds PANTHOR_GROUP_PRIORITY_REALTIME priority
> + * - 1.3 - adds DRM_PANTHOR_GROUP_STATE_INNOCENT flag
>   */
>  static const struct drm_driver panthor_drm_driver = {
>  	.driver_features = DRIVER_RENDER | DRIVER_GEM | DRIVER_SYNCOBJ |
> @@ -1507,7 +1508,7 @@ static const struct drm_driver panthor_drm_driver = {
>  	.desc = "Panthor DRM driver",
>  	.date = "20230801",
>  	.major = 1,
> -	.minor = 2,
> +	.minor = 3,
>  
>  	.gem_create_object = panthor_gem_create_object,
>  	.gem_prime_import_sg_table = drm_gem_shmem_prime_import_sg_table,
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
> index ef4bec7ff9c7..97ed5fe5a191 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.c
> +++ b/drivers/gpu/drm/panthor/panthor_sched.c
> @@ -610,6 +610,16 @@ struct panthor_group {
>  	 */
>  	bool timedout;
>  
> +	/**
> +	 * @innocent: True when the group becomes unusable because the group suspension
> +	 * failed during a reset.
> +	 *
> +	 * Sometimes the FW was put in a bad state by other groups, causing the group
> +	 * suspension happening in the reset path to fail. In that case, we consider the
> +	 * group innocent.
> +	 */
> +	bool innocent;
> +
>  	/**
>  	 * @syncobjs: Pool of per-queue synchronization objects.
>  	 *
> @@ -2690,6 +2700,12 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
>  			u32 csg_id = ffs(slot_mask) - 1;
>  			struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id];
>  
> +			/* If the group was still usable before that point, we consider
> +			 * it innocent.
> +			 */
> +			if (group_can_run(csg_slot->group))
> +				csg_slot->group->innocent = true;
> +
>  			/* We consider group suspension failures as fatal and flag the
>  			 * group as unusable by setting timedout=true.
>  			 */
> @@ -3570,6 +3586,8 @@ int panthor_group_get_state(struct panthor_file *pfile,
>  		get_state->state |= DRM_PANTHOR_GROUP_STATE_FATAL_FAULT;
>  		get_state->fatal_queues = group->fatal_queues;
>  	}
> +	if (group->innocent)
> +		get_state->state |= DRM_PANTHOR_GROUP_STATE_INNOCENT;
>  	mutex_unlock(&sched->lock);
>  
>  	group_put(group);
> diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h
> index 87c9cb555dd1..b99763cbae48 100644
> --- a/include/uapi/drm/panthor_drm.h
> +++ b/include/uapi/drm/panthor_drm.h
> @@ -923,6 +923,15 @@ enum drm_panthor_group_state_flags {
>  	 * When a group ends up with this flag set, no jobs can be submitted to its queues.
>  	 */
>  	DRM_PANTHOR_GROUP_STATE_FATAL_FAULT = 1 << 1,
> +
> +	/**
> +	 * @DRM_PANTHOR_GROUP_STATE_INNOCENT: Group was killed during a reset caused by other
> +	 * groups.
> +	 *
> +	 * This flag can only be set if DRM_PANTHOR_GROUP_STATE_TIMEDOUT is set and
> +	 * DRM_PANTHOR_GROUP_STATE_FATAL_FAULT is not.
> +	 */
> +	DRM_PANTHOR_GROUP_STATE_INNOCENT = 1 << 2,
>  };
>  
>  /**