From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1DC73606A320 for ; Thu, 19 Nov 2026 17:38:29 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.a=rsa-sha256 header.s=Intel header.b=LsJIfIbA Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id BE0D310F026; Thu, 19 Nov 2026 17:38:23 +0000 (UTC) Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) by gabe.freedesktop.org (Postfix) with ESMTPS id 4A9FF10F026 for ; Thu, 19 Nov 2026 17:38:17 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1795109897; x=1826645897; h=message-id:date:mime-version:subject:to:cc:references: from:in-reply-to:content-transfer-encoding; bh=DQxonPiFf1cR2L0FNd1tPp2Kr00Es851ePcuG+m7fow=; b=LsJIfIbAiOWin877BKpCYrKhadmdIrzXhBaIIrCPZR3NhmmIy+q6ZVBE kUsOIpSPf6BCMuntgsi00psz6pcGYdXcWe1bjyxayZd3qRa4c/A+bqG7P RsXB3hSZuzMKI0vB0PHPyhHpWP+b3gRd7y/dDa9/k44X4rO+daikhsQxK TE00n3qMzgPJ7KdXS/mIL4rkNX5KU0Y/H6wkpLyMngTpjJR6zVX3zYdAd feJ561z4UqlKeEkfDm2I2l58Rlf6wfbyyVfXzJFqNBDt+5BViy+BGYv+m auolWNiTGDUdGmyXzMaFFJTqX8Rg8TjdkuizSvayodkEQttdAD7diLSUH g==; X-CSE-ConnectionGUID: /eKAmLxoTue3sFOel0gWLg== X-CSE-MsgGUID: ih4j0dC3SpetX1iFhO+D5g== X-IronPort-AV: E=McAfee;i="6800,10657,11971"; a="3859326" X-IronPort-AV: E=Sophos;i="6.27,221,1787036400"; d="scan'208";a="3859326" Received: from fmviesa011.fm.intel.com ([10.60.135.151]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 19 Nov 2026 09:38:17 -0800 X-CSE-ConnectionGUID: qNT6NtheT/+0gU1NJl+BJg== X-CSE-MsgGUID: qXGUZ9aHT/Sk6w7B45ivZw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.27,221,1787036400"; d="scan'208";a="12331510" Received: from ettammin-mobl3.ger.corp.intel.com (HELO [10.245.245.108]) ([10.245.245.108]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 19 Nov 2026 09:38:15 -0800 Message-ID: <2059a86f-e6c6-49d1-aa8d-79af1852204a@intel.com> Date: Thu, 19 Nov 2026 17:38:13 +0000 X-Archived-By: MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH 2/5] drm/xe: Requeue the rebind worker instead of retrying in-line on -EAGAIN To: =?UTF-8?Q?Thomas_Hellstr=C3=B6m?= , Matthew Brost , Himal Prasad Ghimiray , Stuart Summers Cc: intel-xe@lists.freedesktop.org References: <20261119-userptr-repin-v1-0-af2e327833a9@intel.com> <20261119-userptr-repin-v1-2-af2e327833a9@intel.com> <90e8b4228e4233d89c5295fec195f804a8a487de.camel@linux.intel.com> Content-Language: en-GB From: Matthew Auld In-Reply-To: <90e8b4228e4233d89c5295fec195f804a8a487de.camel@linux.intel.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Intel-xe" X-Spam-Status: No, score=-17.3 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE, SPF_PASS,USER_AGENT_SANE_1 autolearn=ham autolearn_force=no version=4.0.1 X-Spam-Checker-Version: SpamAssassin 4.0.1 (2024-03-26) on aws-us-west-2-korg-listserv-alma10-1 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 >>>> >>>> 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 >> >>> >>>> >>>> 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 >>>> >>>> Signed-off-by: Matthew Auld >>>> --- >>>>   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. */