Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: Tomasz Lis <tomasz.lis@intel.com>
Cc: intel-xe@lists.freedesktop.org,
	"Michał Winiarski" <michal.winiarski@intel.com>,
	"Michał Wajdeczko" <michal.wajdeczko@intel.com>,
	"Piotr Piórkowski" <piotr.piorkowski@intel.com>
Subject: Re: [PATCH v3 4/4] drm/xe/vf: Redo LRC creation while in VF fixups
Date: Wed, 25 Feb 2026 17:49:31 -0800	[thread overview]
Message-ID: <aZ+mq7//0vNGe03S@lstrano-desk.jf.intel.com> (raw)
In-Reply-To: <20260225235447.2772383-5-tomasz.lis@intel.com>

On Thu, Feb 26, 2026 at 12:54:47AM +0100, Tomasz Lis wrote:
> If the xe module within a VM was creating a new LRC during save/
> restore, this LRC will be invalid. The fixups procedure may not
> be able to reach it, as there will be a race to add the new LRC
> reference to an exec queue.
> 
> Even if the new LRC which was being created during VM migration is
> added to EQ in time for fixups, said LRC may still remain damaged.
> In a small percentage of specially crafted test cases, the resulting
> LRC was still damaged and caused GPU hang.
> 
> Any LRC which could be created in such a situation, have to be
> re-created.
> 
> Due to VM having arbitrarily set amount of CPU cores, it is possible
> to limit the amount to 1. In such case, there is a possibility that
> kernel will switch CPU contexts in a way which allows to miss
> VF migration recovery running in parallel (by simply not switching
> to the LRC creation thread during recovery). Therefore checking
> if the migration is in progress just after LRC creation, is not
> enough to ensure detection.
> 
> Free the incorrectly created LRC, and trigger a re-run of the
> creation, but only after waiting for default LRC to get fixups.
> Use additional atomic value increased after fixups, to ensure any VF
> migration that avoided detection by just checking for recovery in
> progress, will be caught.
> 
> v2: Merge marker and wait for default LRC, reducing amount of calls
>   within xe_init_eq(). Alter the LRC creation loop to remove a race
>   with post-migration fixups worker.
> 
> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_exec_queue.c        | 29 ++++++++++++++++-------
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.c       | 25 +++++++++++++++++--
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.h       |  3 ++-
>  drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h |  2 ++
>  4 files changed, 47 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
> index 2cb37af42021..07c6d8bc3ad8 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -365,17 +365,28 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags)
>  	 * from the moment vCPU resumes execution.
>  	 */
>  	for (i = 0; i < q->width; ++i) {
> -		struct xe_lrc *lrc;
> +		struct xe_lrc *__lrc = NULL;
> +		int marker;
>  
> -		xe_gt_sriov_vf_wait_valid_ggtt(q->gt);
> -		lrc = xe_lrc_create(q->hwe, q->vm, q->replay_state,
> -				    xe_lrc_ring_size(), q->msix_vec, flags);
> -		if (IS_ERR(lrc)) {
> -			err = PTR_ERR(lrc);
> -			goto err_lrc;
> -		}
> +		do {
> +			struct xe_lrc *lrc;
> +
> +			marker = xe_gt_sriov_vf_wait_valid_ggtt(q->gt);
> +
> +			lrc = xe_lrc_create(q->hwe, q->vm, q->replay_state,
> +					    xe_lrc_ring_size(), q->msix_vec, flags);
> +			if (IS_ERR(lrc)) {
> +				err = PTR_ERR(lrc);
> +				goto err_lrc;
> +			}
> +
> +			xe_exec_queue_set_lrc(q, lrc, i);
> +
> +			if (__lrc)
> +				xe_lrc_put(__lrc);
> +			__lrc = lrc;
>  
> -		xe_exec_queue_set_lrc(q, lrc, i);
> +		} while (marker != xe_vf_migration_fixups_complete_count(q->gt));
>  	}
>  
>  	return 0;
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 7f83c0d3b099..3da38f2ee317 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -1277,6 +1277,8 @@ static int vf_post_migration_fixups(struct xe_gt *gt)
>  	if (err)
>  		return err;
>  
> +	atomic_inc(&gt->sriov.vf.migration.fixups_complete);
> +
>  	return 0;
>  }
>  
> @@ -1515,20 +1517,39 @@ static bool vf_valid_ggtt(struct xe_gt *gt)
>  	return true;
>  }
>  
> +int xe_vf_migration_fixups_complete_count(struct xe_gt *gt)

Kernel doc.

> +{
> +	if (!IS_SRIOV_VF(gt_to_xe(gt)) ||
> +	    !xe_sriov_vf_migration_supported(gt_to_xe(gt)))
> +		return 0;
> +
> +	/* should never match fixups_complete value */
> +	if (!vf_valid_ggtt(gt))
> +		return -1;
> +
> +	return atomic_read(&gt->sriov.vf.migration.fixups_complete);
> +}
> +
>  /**
>   * xe_gt_sriov_vf_wait_valid_ggtt() - wait for valid GGTT nodes and address refs
>   * @gt: the &xe_gt

Return: explain return value.

>   */
> -void xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt)
> +int xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt)
>  {
>  	int ret;
>  
> +	/*
> +	 * this condition shall identical to one in
> +	 * xe_vf_migration_fixups_complete_count()
> +	 */
>  	if (!IS_SRIOV_VF(gt_to_xe(gt)) ||
>  	    !xe_sriov_vf_migration_supported(gt_to_xe(gt)))
> -		return;
> +		return 0;
>  
>  	ret = wait_event_interruptible_timeout(gt->sriov.vf.migration.wq,
>  					       vf_valid_ggtt(gt),
>  					       HZ * 5);
>  	xe_gt_WARN_ON(gt, !ret);
> +
> +	return atomic_read(&gt->sriov.vf.migration.fixups_complete);
>  }
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> index 7d97189c2d3d..a6f7127521a5 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> @@ -39,6 +39,7 @@ void xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p);
>  void xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p);
>  void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p);
>  
> -void xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt);
> +int xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt);
> +int xe_vf_migration_fixups_complete_count(struct xe_gt *gt);
>  
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> index fca18be589db..0b397f259a26 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> @@ -54,6 +54,8 @@ struct xe_gt_sriov_vf_migration {
>  	wait_queue_head_t wq;
>  	/** @scratch: Scratch memory for VF recovery */
>  	void *scratch;
> +	/** @fixups_complete: Counts completed fixups stages */
> +	atomic_t fixups_complete;

Hate to nitpick names but fixups_complete_count?

Logic in patch LGTM.

Matt

>  	/** @debug: Debug hooks for delaying migration */
>  	struct {
>  		/**
> -- 
> 2.25.1
> 

  reply	other threads:[~2026-02-26  1:49 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-25 23:54 [PATCH v3 0/4] drm/xe/vf: Fix exec queue creation during post-migration recovery Tomasz Lis
2026-02-25 23:54 ` [PATCH v3 1/4] drm/xe/queue: Call fini on exec queue creation fail Tomasz Lis
2026-02-25 23:54 ` [PATCH v3 2/4] drm/xe/queue: Wrappers for setting and getting LRC references Tomasz Lis
2026-02-26  1:42   ` Matthew Brost
2026-02-26  1:57     ` Matthew Brost
2026-02-26 17:26       ` Lis, Tomasz
2026-02-26 17:30         ` Matthew Brost
2026-02-25 23:54 ` [PATCH v3 3/4] drm/xe/vf: Wait for all fixups before using default LRCs Tomasz Lis
2026-02-25 23:54 ` [PATCH v3 4/4] drm/xe/vf: Redo LRC creation while in VF fixups Tomasz Lis
2026-02-26  1:49   ` Matthew Brost [this message]
2026-02-26  1:24 ` ✓ CI.KUnit: success for drm/xe/vf: Fix exec queue creation during post-migration recovery (rev3) Patchwork
2026-02-26  2:02 ` ✓ Xe.CI.BAT: " Patchwork
2026-02-26  6:08 ` ✗ Xe.CI.FULL: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aZ+mq7//0vNGe03S@lstrano-desk.jf.intel.com \
    --to=matthew.brost@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=michal.wajdeczko@intel.com \
    --cc=michal.winiarski@intel.com \
    --cc=piotr.piorkowski@intel.com \
    --cc=tomasz.lis@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox