Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Auld <matthew.auld@intel.com>
To: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Matthew Brost" <matthew.brost@intel.com>,
	"Himal Prasad Ghimiray" <himal.prasad.ghimiray@intel.com>,
	"Stuart Summers" <stuart.summers@intel.com>
Cc: intel-xe@lists.freedesktop.org
Subject: Re: [PATCH 2/5] drm/xe: Requeue the rebind worker instead of retrying in-line on -EAGAIN
Date: Thu, 19 Nov 2026 17:38:13 +0000	[thread overview]
Message-ID: <2059a86f-e6c6-49d1-aa8d-79af1852204a@intel.com> (raw)
In-Reply-To: <90e8b4228e4233d89c5295fec195f804a8a487de.camel@linux.intel.com>

On 19/11/2026 17:26, Thomas Hellström wrote:
> On Thu, 2026-11-19 at 16:29 +0000, Matthew Auld wrote:
>> On 19/11/2026 12:51, Thomas Hellström wrote:
>>> On Thu, 2026-11-19 at 11:14 +0000, Matthew Auld wrote:
>>>> From: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>>>>
>>>> When the preempt rebind worker needs to retry, it currently jumps
>>>> back
>>>> and keeps holding vm->lock in write mode across the retry. Only
>>>> VFs
>>>> with migration support drop the lock and requeue the worker.
>>>>
>>>> Holding the vm lock across retries needlessly blocks other users
>>>> of
>>>> the
>>>> lock and other work on the ordered workqueue, and makes the retry
>>>> unfit
>>>> for conditions that may last for a while, like repeatedly
>>>> invalidated
>>>> userptrs.
>>>>
>>>> Always drop the vm lock and requeue the worker on -EAGAIN. This
>>>> also
>>>> fixes a leak of the preempt fences allocated in the failed
>>>> attempt on
>>>> the existing VF path.
>>>
>>> Do we need a Fixes: here?
>>
>> Yeah, should I also split out the leak fix? Feels like a separate
>> change?
> 
> Yes please do.
> 
>> And do we want a fixes tag also for the new requeue behaviour?
> 
> Hm. You mean if we want to backport the whole series to fix the
> timeout?

Just for the requeue patch here, I wasn't sure if you meant to also 
consider that as a fixes or not, or just a fixes for the leak angle 
(once split out). I assume we don't want to backport the entire series here?

> 
> /Thomas
> 
> 
>>
>>>
>>> Also needs a separate reviewer.
>>
>> I don't think I touched anything other than adding my sob:
>>
>> Reviewed-by: Matthew Auld <matthew.auld@intel.com>
>>
>>>
>>>>
>>>> The userptr invalidation injection state that forces one retry
>>>> per
>>>> rebind sequence was a local variable that would be reset by a
>>>> requeue.
>>>> Move it to the vm.
>>>>
>>>> Signed-off-by: Thomas Hellström
>>>> <thomas.hellstrom@linux.intel.com>
>>>> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
>>>> ---
>>>>    drivers/gpu/drm/xe/xe_vm.c       | 59
>>>> ++++++++++++++++++++++++++----
>>>> ----------
>>>>    drivers/gpu/drm/xe/xe_vm_types.h |  8 ++++++
>>>>    2 files changed, 46 insertions(+), 21 deletions(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/xe/xe_vm.c
>>>> b/drivers/gpu/drm/xe/xe_vm.c
>>>> index 75be5e5329bd..ff8d355728fc 100644
>>>> --- a/drivers/gpu/drm/xe/xe_vm.c
>>>> +++ b/drivers/gpu/drm/xe/xe_vm.c
>>>> @@ -542,6 +542,31 @@ void xe_vm_resume_rebind_worker(struct xe_vm
>>>> *vm)
>>>>    	queue_work(vm->xe->ordered_wq, &vm-
>>>>> preempt.rebind_work);
>>>>    }
>>>>    
>>>> +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
>>>> +/*
>>>> + * Force one retry per rebind sequence. The sequence spans
>>>> requeues
>>>> of the
>>>> + * worker, so the state must live in the vm.
>>>> + */
>>>> +static bool xe_vm_rebind_worker_inject_retry(struct xe_vm *vm)
>>>> +{
>>>> +	return !vm->preempt.inval_inject_tries++;
>>>> +}
>>>> +
>>>> +static void xe_vm_rebind_worker_reset_inject(struct xe_vm *vm)
>>>> +{
>>>> +	vm->preempt.inval_inject_tries = 0;
>>>> +}
>>>> +#else
>>>> +static bool xe_vm_rebind_worker_inject_retry(struct xe_vm *vm)
>>>> +{
>>>> +	return false;
>>>> +}
>>>> +
>>>> +static void xe_vm_rebind_worker_reset_inject(struct xe_vm *vm)
>>>> +{
>>>> +}
>>>> +#endif
>>>> +
>>>>    static void preempt_rebind_work_func(struct work_struct *w)
>>>>    {
>>>>    	struct xe_vm *vm = container_of(w, struct xe_vm,
>>>> preempt.rebind_work);
>>>> @@ -551,7 +576,6 @@ static void preempt_rebind_work_func(struct
>>>> work_struct *w)
>>>>    	LIST_HEAD(preempt_fences);
>>>>    	int err = 0;
>>>>    	long wait;
>>>> -	int __maybe_unused tries = 0;
>>>>    
>>>>    	xe_assert(vm->xe, xe_vm_in_preempt_fence_mode(vm));
>>>>    	trace_xe_vm_rebind_worker_enter(vm);
>>>> @@ -564,7 +588,6 @@ static void preempt_rebind_work_func(struct
>>>> work_struct *w)
>>>>    		return;
>>>>    	}
>>>>    
>>>> -retry:
>>>>    	if (!try_wait_for_completion(&vm->xe->pm_block) &&
>>>> vm_suspend_rebind_worker(vm)) {
>>>>    		up_write(&vm->lock);
>>>>    		/* We don't actually block but don't make
>>>> progress.
>>>> */
>>>> @@ -614,20 +637,14 @@ static void preempt_rebind_work_func(struct
>>>> work_struct *w)
>>>>    		goto out_unlock;
>>>>    	}
>>>>    
>>>> -#define retry_required(__tries, __vm) \
>>>> -	(IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) ? \
>>>> -	(!(__tries)++ || __xe_vm_userptr_needs_repin(__vm)) : \
>>>> -	__xe_vm_userptr_needs_repin(__vm))
>>>> -
>>>>    	xe_svm_notifier_lock(vm);
>>>> -	if (retry_required(tries, vm)) {
>>>> +	if (xe_vm_rebind_worker_inject_retry(vm) ||
>>>> +	    __xe_vm_userptr_needs_repin(vm)) {
>>>>    		xe_svm_notifier_unlock(vm);
>>>>    		err = -EAGAIN;
>>>>    		goto out_unlock;
>>>>    	}
>>>>    
>>>> -#undef retry_required
>>>> -
>>>>    	xe_vm_bump_lru(vm, &exec);
>>>>    
>>>>    	/* Point of no return. */
>>>> @@ -642,20 +659,20 @@ static void preempt_rebind_work_func(struct
>>>> work_struct *w)
>>>>    		trace_xe_vm_rebind_worker_retry(vm);
>>>>    
>>>>    		/*
>>>> -		 * We can't block in workers on a VF which
>>>> supports
>>>> migration
>>>> -		 * given this can block the VF post-migration
>>>> workers from
>>>> -		 * getting scheduled.
>>>> +		 * Drop all locks and requeue rather than
>>>> retrying
>>>> in-line.
>>>> +		 * This avoids blocking other work items, such
>>>> as VF
>>>> +		 * post-migration workers, and lets other users
>>>> of
>>>> the vm
>>>> +		 * lock make progress between attempts.
>>>>    		 */
>>>> -		if (IS_SRIOV_VF(vm->xe) &&
>>>> -		    xe_sriov_vf_migration_supported(vm->xe)) {
>>>> -			up_write(&vm->lock);
>>>> -			xe_vm_queue_rebind_worker(vm);
>>>> -			return;
>>>> -		}
>>>> -
>>>> -		goto retry;
>>>> +		up_write(&vm->lock);
>>>> +		free_preempt_fences(&preempt_fences);
>>>> +		xe_vm_queue_rebind_worker(vm);
>>>> +		trace_xe_vm_rebind_worker_exit(vm);
>>>> +		return;
>>>>    	}
>>>>    
>>>> +	xe_vm_rebind_worker_reset_inject(vm);
>>>> +
>>>>    	if (err) {
>>>>    		drm_warn(&vm->xe->drm, "VM worker error: %d\n",
>>>> err);
>>>>    		xe_vm_kill(vm, true);
>>>> diff --git a/drivers/gpu/drm/xe/xe_vm_types.h
>>>> b/drivers/gpu/drm/xe/xe_vm_types.h
>>>> index fb9305124679..756cf2dbee8a 100644
>>>> --- a/drivers/gpu/drm/xe/xe_vm_types.h
>>>> +++ b/drivers/gpu/drm/xe/xe_vm_types.h
>>>> @@ -350,6 +350,14 @@ struct xe_vm {
>>>>    		 * kicked on resume.
>>>>    		 */
>>>>    		struct list_head pm_activate_link;
>>>> +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
>>>> +		/**
>>>> +		 * @inval_inject_tries: Number of rebind
>>>> attempts in
>>>> the
>>>> +		 * current rebind sequence. Used to force a
>>>> retry
>>>> for testing.
>>>> +		 * Protected by @lock.
>>>> +		 */
>>>> +		unsigned int inval_inject_tries;
>>>> +#endif
>>>>    	} preempt;
>>>>    
>>>>    	/** @exec_queues: Manages list of exec queues attached
>>>> to
>>>> this VM, protected by lock. */


  reply	other threads:[~2026-11-19 17:38 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 11:14 [PATCH 0/5] Non-fatal repin retries and NUMA-local rebind worker Matthew Auld
2026-11-19 11:14 ` [PATCH 1/5] drm/xe/vm: restore userptr invalidations on VMA op unwind Matthew Auld
2026-11-19 12:48   ` Thomas Hellström
2026-11-19 16:35   ` Himal prasad Ghimiray
2026-11-19 11:14 ` [PATCH 2/5] drm/xe: Requeue the rebind worker instead of retrying in-line on -EAGAIN Matthew Auld
2026-11-19 12:51   ` Thomas Hellström
2026-11-19 16:29     ` Matthew Auld
2026-11-19 17:26       ` Thomas Hellström
2026-11-19 17:38         ` Matthew Auld [this message]
2026-11-19 16:36   ` Himal prasad Ghimiray
2026-11-19 11:14 ` [PATCH 3/5] drm/xe: Add a userptr repin timeout sysfs attribute Matthew Auld
2026-11-19 16:38   ` Himal prasad Ghimiray
2026-11-19 11:14 ` [PATCH 4/5] drm/xe/userptr: Make the repin retry loop non-fatal Matthew Auld
2026-11-19 13:03   ` Thomas Hellström
2026-11-19 17:10   ` Himal prasad Ghimiray
2026-11-19 11:14 ` [PATCH 5/5] drm/xe: run compute rebind worker on device NUMA node Matthew Auld
2026-11-19 13:11   ` Thomas Hellström
2026-11-19 13:38     ` Matthew Auld
2026-11-19 13:16 ` ✓ CI.KUnit: success for Non-fatal repin retries and NUMA-local rebind worker Patchwork
2026-11-19 13:54 ` ✓ Xe.CI.BAT: " 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=2059a86f-e6c6-49d1-aa8d-79af1852204a@intel.com \
    --to=matthew.auld@intel.com \
    --cc=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=stuart.summers@intel.com \
    --cc=thomas.hellstrom@linux.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