From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id BED68C7EE22 for ; Wed, 10 May 2023 08:15:39 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 4E6A610E459; Wed, 10 May 2023 08:15:39 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 447FD10E458 for ; Wed, 10 May 2023 08:15:37 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1683706537; x=1715242537; h=message-id:date:mime-version:subject:to:cc:references: from:in-reply-to:content-transfer-encoding; bh=TNUK830F+TN8NnOf/PocZlbE+2qrZUtAib/N5GDMB4A=; b=kyobgjOvdID6+xlPrZs2LEQroK/qQtJa32q64B6Ret1T+CZrlvSq/UVM HizG+8UiGtQhfMp/5F72o42+PGalY0GBQ1UCCMQxWJ3k11odQqCnhsTxU 9omZ8ZtqhDVF9NjB6LF3j31M+Lf2YA4Z902w3Cld5UZ65KNWVmwPoZ/65 l024xgMHna6KGT4lkS+ek+SVok9LVTV7FEGWwXh7l34cWeEU8MfJGs+bI bF1ipdTfAwZSTtqOc2zakObteP8pKxEPcS/RSvLs54hVt2v6t652eNKcT IHc9O7Wg5tNYdQC5MBKKWnUCkdEmEBzNucqrI5BqW8g2wSFsRfw67SpzH A==; X-IronPort-AV: E=McAfee;i="6600,9927,10705"; a="413448862" X-IronPort-AV: E=Sophos;i="5.99,264,1677571200"; d="scan'208";a="413448862" Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 10 May 2023 01:15:36 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10705"; a="1029123531" X-IronPort-AV: E=Sophos;i="5.99,264,1677571200"; d="scan'208";a="1029123531" Received: from aboreiko-mobl3.ger.corp.intel.com (HELO [10.249.254.114]) ([10.249.254.114]) by fmsmga005-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 10 May 2023 01:15:35 -0700 Message-ID: <1ef5e506-1e09-da16-4ad7-f983be5331d9@linux.intel.com> Date: Wed, 10 May 2023 10:15:33 +0200 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101 Thunderbird/102.8.0 Content-Language: en-US To: Matthew Brost References: <20230502001727.3211096-1-matthew.brost@intel.com> <20230502001727.3211096-6-matthew.brost@intel.com> <90b4e835-c21a-f9b3-4b22-aa59c911f54f@linux.intel.com> From: =?UTF-8?Q?Thomas_Hellstr=c3=b6m?= In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit Subject: Re: [Intel-xe] [PATCH v2 05/31] drm/xe: Long running job update X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: intel-xe@lists.freedesktop.org Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" On 5/10/23 00:16, Matthew Brost wrote: > On Tue, May 09, 2023 at 05:21:39PM +0200, Thomas Hellström wrote: >> On 5/9/23 16:56, Matthew Brost wrote: >>> On Mon, May 08, 2023 at 03:14:10PM +0200, Thomas Hellström wrote: >>>> Hi, Matthew >>>> >>>> In addition to Rodrigo's comments: >>>> >>>> On 5/2/23 02:17, Matthew Brost wrote: >>>>> Flow control + write ring in exec, return NULL in run_job, siganl >>>>> xe_hw_fence immediately, and override TDR for LR jobs. >>>>> >>>>> Signed-off-by: Matthew Brost >>>>> --- >>>>> drivers/gpu/drm/xe/xe_engine.c | 32 ++++++++ >>>>> drivers/gpu/drm/xe/xe_engine.h | 4 + >>>>> drivers/gpu/drm/xe/xe_exec.c | 8 ++ >>>>> drivers/gpu/drm/xe/xe_guc_engine_types.h | 2 + >>>>> drivers/gpu/drm/xe/xe_guc_submit.c | 95 +++++++++++++++++++++--- >>>>> drivers/gpu/drm/xe/xe_trace.h | 5 ++ >>>>> 6 files changed, 137 insertions(+), 9 deletions(-) >>>>> >>>>> diff --git a/drivers/gpu/drm/xe/xe_engine.c b/drivers/gpu/drm/xe/xe_engine.c >>>>> index 094ec17d3004..d1e84d7adbd4 100644 >>>>> --- a/drivers/gpu/drm/xe/xe_engine.c >>>>> +++ b/drivers/gpu/drm/xe/xe_engine.c >>>>> @@ -18,6 +18,7 @@ >>>>> #include "xe_macros.h" >>>>> #include "xe_migrate.h" >>>>> #include "xe_pm.h" >>>>> +#include "xe_ring_ops_types.h" >>>>> #include "xe_trace.h" >>>>> #include "xe_vm.h" >>>>> @@ -673,6 +674,37 @@ static void engine_kill_compute(struct xe_engine *e) >>>>> up_write(&e->vm->lock); >>>>> } >>>>> +/** >>>>> + * xe_engine_is_lr() - Whether an engine is long-running >>>>> + * @e: The engine >>>>> + * >>>>> + * Return: True if the engine is long-running, false otherwise. >>>>> + */ >>>>> +bool xe_engine_is_lr(struct xe_engine *e) >>>>> +{ >>>>> + return e->vm && xe_vm_no_dma_fences(e->vm) && >>>>> + !(e->flags & ENGINE_FLAG_VM); >>>>> +} >>>>> + >>>>> +static s32 xe_engine_num_job_inflight(struct xe_engine *e) >>>>> +{ >>>>> + return e->lrc->fence_ctx.next_seqno - xe_lrc_seqno(e->lrc) - 1; >>>>> +} >>>>> + >>>>> +/** >>>>> + * xe_engine_ring_full() - Whether an engine's ring is full >>>>> + * @e: The engine >>>>> + * >>>>> + * Return: True if the engine's ring is full, false otherwise. >>>>> + */ >>>>> +bool xe_engine_ring_full(struct xe_engine *e) >>>>> +{ >>>>> + struct xe_lrc *lrc = e->lrc; >>>>> + s32 max_job = lrc->ring.size / MAX_JOB_SIZE_BYTES; >>>>> + >>>>> + return xe_engine_num_job_inflight(e) >= max_job; >>>>> +} >>>>> + >>>>> /** >>>>> * xe_engine_is_idle() - Whether an engine is idle. >>>>> * @engine: The engine >>>>> diff --git a/drivers/gpu/drm/xe/xe_engine.h b/drivers/gpu/drm/xe/xe_engine.h >>>>> index a49cf2ab405e..2e60f6d90226 100644 >>>>> --- a/drivers/gpu/drm/xe/xe_engine.h >>>>> +++ b/drivers/gpu/drm/xe/xe_engine.h >>>>> @@ -42,6 +42,10 @@ static inline bool xe_engine_is_parallel(struct xe_engine *engine) >>>>> return engine->width > 1; >>>>> } >>>>> +bool xe_engine_is_lr(struct xe_engine *e); >>>>> + >>>>> +bool xe_engine_ring_full(struct xe_engine *e); >>>>> + >>>>> bool xe_engine_is_idle(struct xe_engine *engine); >>>>> void xe_engine_kill(struct xe_engine *e); >>>>> diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c >>>>> index ea869f2452ef..44ea9bcd0066 100644 >>>>> --- a/drivers/gpu/drm/xe/xe_exec.c >>>>> +++ b/drivers/gpu/drm/xe/xe_exec.c >>>>> @@ -13,6 +13,7 @@ >>>>> #include "xe_device.h" >>>>> #include "xe_engine.h" >>>>> #include "xe_macros.h" >>>>> +#include "xe_ring_ops_types.h" >>>>> #include "xe_sched_job.h" >>>>> #include "xe_sync.h" >>>>> #include "xe_vm.h" >>>>> @@ -277,6 +278,11 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) >>>>> goto err_engine_end; >>>>> } >>>>> + if (xe_engine_is_lr(engine) && xe_engine_ring_full(engine)) { >>>>> + err = -EWOULDBLOCK; >>>>> + goto err_engine_end; >>>>> + } >>>>> + >>>>> job = xe_sched_job_create(engine, xe_engine_is_parallel(engine) ? >>>>> addresses : &args->address); >>>>> if (IS_ERR(job)) { >>>>> @@ -363,6 +369,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) >>>>> xe_sync_entry_signal(&syncs[i], job, >>>>> &job->drm.s_fence->finished); >>>>> + if (xe_engine_is_lr(engine)) >>>>> + engine->ring_ops->emit_job(job); >>>>> xe_sched_job_push(job); >>>>> xe_vm_reactivate_rebind(vm); >>>>> diff --git a/drivers/gpu/drm/xe/xe_guc_engine_types.h b/drivers/gpu/drm/xe/xe_guc_engine_types.h >>>>> index cbfb13026ec1..5d83132034a6 100644 >>>>> --- a/drivers/gpu/drm/xe/xe_guc_engine_types.h >>>>> +++ b/drivers/gpu/drm/xe/xe_guc_engine_types.h >>>>> @@ -31,6 +31,8 @@ struct xe_guc_engine { >>>>> */ >>>>> #define MAX_STATIC_MSG_TYPE 3 >>>>> struct drm_sched_msg static_msgs[MAX_STATIC_MSG_TYPE]; >>>>> + /** @lr_tdr: long running TDR worker */ >>>>> + struct work_struct lr_tdr; >>>>> /** @fini_async: do final fini async from this worker */ >>>>> struct work_struct fini_async; >>>>> /** @resume_time: time of last resume */ >>>>> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c >>>>> index 68d09e7a4cc0..0a41f5d04f6d 100644 >>>>> --- a/drivers/gpu/drm/xe/xe_guc_submit.c >>>>> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c >>>>> @@ -500,6 +500,14 @@ static void register_engine(struct xe_engine *e) >>>>> parallel_write(xe, map, wq_desc.wq_status, WQ_STATUS_ACTIVE); >>>>> } >>>>> + /* >>>>> + * We must keep a reference for LR engines if engine is registered with >>>>> + * the GuC as jobs signal immediately and can't destroy an engine if the >>>>> + * GuC has a reference to it. >>>>> + */ >>>>> + if (xe_engine_is_lr(e)) >>>>> + xe_engine_get(e); >>>>> + >>>>> set_engine_registered(e); >>>>> trace_xe_engine_register(e); >>>>> if (xe_engine_is_parallel(e)) >>>>> @@ -662,6 +670,7 @@ guc_engine_run_job(struct drm_sched_job *drm_job) >>>>> { >>>>> struct xe_sched_job *job = to_xe_sched_job(drm_job); >>>>> struct xe_engine *e = job->engine; >>>>> + bool lr = xe_engine_is_lr(e); >>>>> XE_BUG_ON((engine_destroyed(e) || engine_pending_disable(e)) && >>>>> !engine_banned(e) && !engine_suspended(e)); >>>>> @@ -671,14 +680,19 @@ guc_engine_run_job(struct drm_sched_job *drm_job) >>>>> if (!engine_killed_or_banned(e) && !xe_sched_job_is_error(job)) { >>>>> if (!engine_registered(e)) >>>>> register_engine(e); >>>>> - e->ring_ops->emit_job(job); >>>>> + if (!lr) /* Written in IOCTL */ >>>> Hmm? What does "Written in IOCTL mean?" Could you rephrase to something more >>>> descriptive? >>>> >>> "LR jos are emitted in the IOCTL" >> Ah, I read it as "the lr variable was written in IOCTL." >> >> Perhaps LR jobs are already emitted at execbuf time? >> > I missed exec in my update. > > s/LR jos are emitted in the IOCTL/LR jos are emitted in the exec IOCTL/ Sounds good, with also s/jos/jobs/ /Thomas > > Matt > >> /Thomas >> >> >>> Does that work? >>> >>> Matt >>> >>>>> + e->ring_ops->emit_job(job); >>>>> submit_engine(e); >>>>> } >>>>> - if (test_and_set_bit(JOB_FLAG_SUBMIT, &job->fence->flags)) >>>>> + if (lr) { >>>>> + xe_sched_job_set_error(job, -ENOTSUPP); >>>>> + return NULL; >>>>> + } else if (test_and_set_bit(JOB_FLAG_SUBMIT, &job->fence->flags)) { >>>>> return job->fence; >>>>> - else >>>>> + } else { >>>>> return dma_fence_get(job->fence); >>>>> + } >>>>> } >>>>> static void guc_engine_free_job(struct drm_sched_job *drm_job) >>>>> @@ -782,6 +796,57 @@ static void simple_error_capture(struct xe_engine *e) >>>>> } >>>>> #endif >>>>> +static void xe_guc_engine_trigger_cleanup(struct xe_engine *e) >>>>> +{ >>>>> + struct xe_guc *guc = engine_to_guc(e); >>>>> + >>>>> + if (xe_engine_is_lr(e)) >>>>> + queue_work(guc_to_gt(guc)->ordered_wq, &e->guc->lr_tdr); >>>>> + else >>>>> + drm_sched_set_timeout(&e->guc->sched, MIN_SCHED_TIMEOUT); >>>>> +} >>>>> + >>>>> +static void xe_guc_engine_lr_cleanup(struct work_struct *w) >>>>> +{ >>>>> + struct xe_guc_engine *ge = >>>>> + container_of(w, struct xe_guc_engine, lr_tdr); >>>>> + struct xe_engine *e = ge->engine; >>>>> + struct drm_gpu_scheduler *sched = &ge->sched; >>>>> + >>>>> + XE_BUG_ON(!xe_engine_is_lr(e)); >>>>> + trace_xe_engine_lr_cleanup(e); >>>>> + >>>>> + /* Kill the run_job / process_msg entry points */ >>>>> + drm_sched_run_wq_stop(sched); >>>>> + >>>>> + /* Engine state now stable, disable scheduling / deregister if needed */ >>>>> + if (engine_registered(e)) { >>>>> + struct xe_guc *guc = engine_to_guc(e); >>>>> + int ret; >>>>> + >>>>> + set_engine_banned(e); >>>>> + xe_engine_get(e); >>>>> + disable_scheduling_deregister(guc, e); >>>>> + >>>>> + /* >>>>> + * Must wait for scheduling to be disabled before signalling >>>>> + * any fences, if GT broken the GT reset code should signal us. >>>>> + */ >>>>> + smp_rmb(); >>>> wait_event() paired with wake_up() family of functions typically set the >>>> necessary barriers to make sure anything written prior to wake_up() is seen >>>> in wait_event(). So that smp_rmb() is most likely not needed. If it still >>>> is, its pairing smp_wmb() should be documented and pointed to as well. See >>>> documentation of set_current_state() vs __set_current_state(). >>>> >>>>> + ret = wait_event_timeout(guc->ct.wq, >>>>> + !engine_pending_disable(e) || >>>>> + guc_read_stopped(guc), HZ * 5); >>>>> + if (!ret) { >>>>> + XE_WARN_ON("Schedule disable failed to respond"); >>>>> + drm_sched_run_wq_start(sched); >>>>> + xe_gt_reset_async(e->gt); >>>>> + return; >>>>> + } >>>>> + } >>>>> + >>>>> + drm_sched_run_wq_start(sched); >>>>> +} >>>>> + >>>>> static enum drm_gpu_sched_stat >>>>> guc_engine_timedout_job(struct drm_sched_job *drm_job) >>>>> { >>>>> @@ -832,7 +897,7 @@ guc_engine_timedout_job(struct drm_sched_job *drm_job) >>>>> err = -EIO; >>>>> set_engine_banned(e); >>>>> xe_engine_get(e); >>>>> - disable_scheduling_deregister(engine_to_guc(e), e); >>>>> + disable_scheduling_deregister(guc, e); >>>>> /* >>>>> * Must wait for scheduling to be disabled before signalling >>>>> @@ -865,7 +930,7 @@ guc_engine_timedout_job(struct drm_sched_job *drm_job) >>>>> */ >>>>> list_add(&drm_job->list, &sched->pending_list); >>>>> drm_sched_run_wq_start(sched); >>>>> - drm_sched_set_timeout(&e->guc->sched, MIN_SCHED_TIMEOUT); >>>>> + xe_guc_engine_trigger_cleanup(e); >>>>> /* Mark all outstanding jobs as bad, thus completing them */ >>>>> spin_lock(&sched->job_list_lock); >>>>> @@ -889,6 +954,8 @@ static void __guc_engine_fini_async(struct work_struct *w) >>>>> trace_xe_engine_destroy(e); >>>>> + if (xe_engine_is_lr(e)) >>>>> + cancel_work_sync(&ge->lr_tdr); >>>>> if (e->flags & ENGINE_FLAG_PERSISTENT) >>>>> xe_device_remove_persistent_engines(gt_to_xe(e->gt), e); >>>>> release_guc_id(guc, e); >>>>> @@ -906,7 +973,7 @@ static void guc_engine_fini_async(struct xe_engine *e) >>>>> bool kernel = e->flags & ENGINE_FLAG_KERNEL; >>>>> INIT_WORK(&e->guc->fini_async, __guc_engine_fini_async); >>>>> - queue_work(system_unbound_wq, &e->guc->fini_async); >>>>> + queue_work(system_wq, &e->guc->fini_async); >>>>> /* We must block on kernel engines so slabs are empty on driver unload */ >>>>> if (kernel) { >>>>> @@ -1089,12 +1156,16 @@ static int guc_engine_init(struct xe_engine *e) >>>>> if (err) >>>>> goto err_free; >>>>> + >>>> Unrelated whitespace? >>>> >>>> >>>>> sched = &ge->sched; >>>>> err = drm_sched_entity_init(&ge->entity, DRM_SCHED_PRIORITY_NORMAL, >>>>> &sched, 1, NULL); >>>>> if (err) >>>>> goto err_sched; >>>>> + if (xe_engine_is_lr(e)) >>>>> + INIT_WORK(&e->guc->lr_tdr, xe_guc_engine_lr_cleanup); >>>>> + >>>>> mutex_lock(&guc->submission_state.lock); >>>>> err = alloc_guc_id(guc, e); >>>>> @@ -1146,7 +1217,7 @@ static void guc_engine_kill(struct xe_engine *e) >>>>> { >>>>> trace_xe_engine_kill(e); >>>>> set_engine_killed(e); >>>>> - drm_sched_set_timeout(&e->guc->sched, MIN_SCHED_TIMEOUT); >>>>> + xe_guc_engine_trigger_cleanup(e); >>>>> } >>>>> static void guc_engine_add_msg(struct xe_engine *e, struct drm_sched_msg *msg, >>>>> @@ -1296,6 +1367,9 @@ static void guc_engine_stop(struct xe_guc *guc, struct xe_engine *e) >>>>> /* Stop scheduling + flush any DRM scheduler operations */ >>>>> drm_sched_run_wq_stop(sched); >>>>> + if (engine_registered(e) && xe_engine_is_lr(e)) >>>>> + xe_engine_put(e); >>>>> + >>>>> /* Clean up lost G2H + reset engine state */ >>>>> if (engine_destroyed(e) && engine_registered(e)) { >>>>> if (engine_banned(e)) >>>>> @@ -1520,6 +1594,9 @@ int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len) >>>>> trace_xe_engine_deregister_done(e); >>>>> clear_engine_registered(e); >>>>> + if (xe_engine_is_lr(e)) >>>>> + xe_engine_put(e); >>>>> + >>>>> if (engine_banned(e)) >>>>> xe_engine_put(e); >>>>> else >>>>> @@ -1557,7 +1634,7 @@ int xe_guc_engine_reset_handler(struct xe_guc *guc, u32 *msg, u32 len) >>>>> */ >>>>> set_engine_reset(e); >>>>> if (!engine_banned(e)) >>>>> - drm_sched_set_timeout(&e->guc->sched, MIN_SCHED_TIMEOUT); >>>>> + xe_guc_engine_trigger_cleanup(e); >>>>> return 0; >>>>> } >>>>> @@ -1584,7 +1661,7 @@ int xe_guc_engine_memory_cat_error_handler(struct xe_guc *guc, u32 *msg, >>>>> /* Treat the same as engine reset */ >>>>> set_engine_reset(e); >>>>> if (!engine_banned(e)) >>>>> - drm_sched_set_timeout(&e->guc->sched, MIN_SCHED_TIMEOUT); >>>>> + xe_guc_engine_trigger_cleanup(e); >>>>> return 0; >>>>> } >>>>> diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h >>>>> index 2f8eb7ebe9a7..02861c26e145 100644 >>>>> --- a/drivers/gpu/drm/xe/xe_trace.h >>>>> +++ b/drivers/gpu/drm/xe/xe_trace.h >>>>> @@ -219,6 +219,11 @@ DEFINE_EVENT(xe_engine, xe_engine_resubmit, >>>>> TP_ARGS(e) >>>>> ); >>>>> +DEFINE_EVENT(xe_engine, xe_engine_lr_cleanup, >>>>> + TP_PROTO(struct xe_engine *e), >>>>> + TP_ARGS(e) >>>>> +); >>>>> + >>>>> DECLARE_EVENT_CLASS(xe_sched_job, >>>>> TP_PROTO(struct xe_sched_job *job), >>>>> TP_ARGS(job),