[PATCH v2 3/3] drm/panthor: Report innocent group kill

[Steven Price]

On 28/10/2024 11:48, Boris Brezillon 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.

Sadly I don't see any code to return that new flag... Shouldn't there be
a change to panthor_get_get_state()?

> 
> Bump the minor driver version to reflect the uAPI change.
> 
> Changes in v2:
> - New patch
> 
> Signed-off-by: Boris Brezillon <boris.brezillon at collabora.com>
> ---
>  drivers/gpu/drm/panthor/panthor_drv.c   |  2 +-
>  drivers/gpu/drm/panthor/panthor_sched.c | 16 ++++++++++++++++
>  include/uapi/drm/panthor_drm.h          |  9 +++++++++
>  3 files changed, 26 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
> index ac7e53f6e3f0..f1dff7e0173d 100644
> --- a/drivers/gpu/drm/panthor/panthor_drv.c
> +++ b/drivers/gpu/drm/panthor/panthor_drv.c
> @@ -1507,7 +1507,7 @@ 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..bb4a8c522fdc 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.
>  			 */
> 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,
>  };
>  
>  /**