[PATCH v3] drm/xe/ufence: Flush xe ordered_wq in case of ufence timeout

[John Harrison]

On 10/28/2024 04:49, Nirmoy Das wrote:
> Flush xe ordered_wq in case of ufence timeout which is observed
> on LNL and that points to recent scheduling issue with E-cores.
>
> This is similar to the recent fix:
> commit e51527233804 ("drm/xe/guc/ct: Flush g2h worker in case of g2h
> response timeout") and should be removed once there is a E-core
> scheduling fix for LNL.
>
> v2: Add platform check(Himal)
>      s/__flush_workqueue/flush_workqueue(Jani)
> v3: Remove gfx platform check as the issue related to cpu
>      platform(John)
>
> Cc: Badal Nilawar <badal.nilawar at intel.com>
> Cc: Matthew Auld <matthew.auld at intel.com>
> Cc: John Harrison <John.C.Harrison at Intel.com>
> Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
> Cc: Lucas De Marchi <lucas.demarchi at intel.com>
> Cc: <stable at vger.kernel.org> # v6.11+
> Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2754
> Suggested-by: Matthew Brost <matthew.brost at intel.com>
> Signed-off-by: Nirmoy Das <nirmoy.das at intel.com>
> Reviewed-by: Matthew Brost <matthew.brost at intel.com>
> ---
>   drivers/gpu/drm/xe/xe_wait_user_fence.c | 11 +++++++++++
>   1 file changed, 11 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_wait_user_fence.c b/drivers/gpu/drm/xe/xe_wait_user_fence.c
> index f5deb81eba01..886c9862d89c 100644
> --- a/drivers/gpu/drm/xe/xe_wait_user_fence.c
> +++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c
> @@ -155,6 +155,17 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data,
>   		}
>   
>   		if (!timeout) {
> +			/*
> +			 * This is analogous to e51527233804 ("drm/xe/guc/ct: Flush g2h worker
> +			 * in case of g2h response timeout")
> +			 *
> +			 * TODO: Drop this change once workqueue scheduling delay issue is
> +			 * fixed on LNL Hybrid CPU.
> +			 */
> +			flush_workqueue(xe->ordered_wq);
I thought the plan was to make this a trackable macro used by all 
instances of this w/a - LNL_FLUSH_WORK|WORKQUEUE()? With a single, 
complete description of the problem attached to the macro rather than 
'this is similar to' comments scattered through the code.

There was also a request to add a dmesg print if the failing condition 
was met after doing the flush.

John.

> +			err = do_compare(addr, args->value, args->mask, args->op);
> +			if (err <= 0)
> +				break;
>   			err = -ETIME;
>   			break;
>   		}