On 02/05/2024 19:38, Boris Brezillon wrote:
> We need to undo what was done in panthor_sched_pre_reset() even if the
> reset failed. We just flag all previously running groups as terminated
> when that happens to unblock things.
>
> Signed-off-by: Boris Brezillon <boris.brezillon@xxxxxxxxxxxxx>
Seems reasonable, although I hope this case doesn't happen in practice ;)
Reviewed-by: Steven Price <steven.price@xxxxxxx>
> ---
> drivers/gpu/drm/panthor/panthor_device.c | 7 +------
> drivers/gpu/drm/panthor/panthor_sched.c | 19 ++++++++++++++-----
> drivers/gpu/drm/panthor/panthor_sched.h | 2 +-
> 3 files changed, 16 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
> index 4c5b54e7abb7..4082c8f2951d 100644
> --- a/drivers/gpu/drm/panthor/panthor_device.c
> +++ b/drivers/gpu/drm/panthor/panthor_device.c
> @@ -129,13 +129,8 @@ static void panthor_device_reset_work(struct work_struct *work)
> panthor_gpu_l2_power_on(ptdev);
> panthor_mmu_post_reset(ptdev);
> ret = panthor_fw_post_reset(ptdev);
> - if (ret)
> - goto out_dev_exit;
> -
> atomic_set(&ptdev->reset.pending, 0);
> - panthor_sched_post_reset(ptdev);
> -
> -out_dev_exit:
> + panthor_sched_post_reset(ptdev, ret != 0);
> drm_dev_exit(cookie);
>
> if (ret) {
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
> index 6ea094b00cf9..fc43ff62c77d 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.c
> +++ b/drivers/gpu/drm/panthor/panthor_sched.c
> @@ -2728,15 +2728,22 @@ void panthor_sched_pre_reset(struct panthor_device *ptdev)
> mutex_unlock(&sched->reset.lock);
> }
>
> -void panthor_sched_post_reset(struct panthor_device *ptdev)
> +void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed)
> {
> struct panthor_scheduler *sched = ptdev->scheduler;
> struct panthor_group *group, *group_tmp;
>
> mutex_lock(&sched->reset.lock);
>
> - list_for_each_entry_safe(group, group_tmp, &sched->reset.stopped_groups, run_node)
> + list_for_each_entry_safe(group, group_tmp, &sched->reset.stopped_groups, run_node) {
> + /* Consider all previously running group as terminated if the
> + * reset failed.
> + */
> + if (reset_failed)
> + group->state = PANTHOR_CS_GROUP_TERMINATED;
> +
> panthor_group_start(group);
> + }
>
> /* We're done resetting the GPU, clear the reset.in_progress bit so we can
> * kick the scheduler.
> @@ -2744,9 +2751,11 @@ void panthor_sched_post_reset(struct panthor_device *ptdev)
> atomic_set(&sched->reset.in_progress, false);
> mutex_unlock(&sched->reset.lock);
>
> - sched_queue_delayed_work(sched, tick, 0);
> -
> - sched_queue_work(sched, sync_upd);
> + /* No need to queue a tick and update syncs if the reset failed. */
> + if (!reset_failed) {
> + sched_queue_delayed_work(sched, tick, 0);
> + sched_queue_work(sched, sync_upd);
> + }
> }
>
> static void group_sync_upd_work(struct work_struct *work)
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.h b/drivers/gpu/drm/panthor/panthor_sched.h
> index 66438b1f331f..3a30d2328b30 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.h
> +++ b/drivers/gpu/drm/panthor/panthor_sched.h
> @@ -40,7 +40,7 @@ void panthor_group_pool_destroy(struct panthor_file *pfile);
> int panthor_sched_init(struct panthor_device *ptdev);
> void panthor_sched_unplug(struct panthor_device *ptdev);
> void panthor_sched_pre_reset(struct panthor_device *ptdev);
> -void panthor_sched_post_reset(struct panthor_device *ptdev);
> +void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed);
> void panthor_sched_suspend(struct panthor_device *ptdev);
> void panthor_sched_resume(struct panthor_device *ptdev);
>
