From patchwork Wed Jan 18 06:12:43 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Danilo Krummrich X-Patchwork-Id: 13105622 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 22F34C32793 for ; Wed, 18 Jan 2023 06:13:39 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id C799F10E682; Wed, 18 Jan 2023 06:13:32 +0000 (UTC) Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by gabe.freedesktop.org (Postfix) with ESMTPS id 24E4010E683 for ; Wed, 18 Jan 2023 06:13:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1674022410; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=leSDSUqYxgVrElrnUnSnvkj6D04l7A7PmoOZI2j6TnU=; b=HIMwOE19pLxBr3BvQfea21aNzgUgsOc1CL7/OBAFoDFez7zyK4zxjkHUXaxNeTu7LBOym+ N6dJQjw8R4q3/LTpT/AtRJfB9vLB4Xp9WwCKLcT96FHv/xxC69JW4IPMSArTbsJngkdpYn Jt+jGyy4EFHmoa6tlXJ5emouu2y2B8g= Received: from mail-ej1-f70.google.com (mail-ej1-f70.google.com [209.85.218.70]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_128_GCM_SHA256) id us-mta-441-r_HN9PU_Oy6jlewcWwmgtQ-1; Wed, 18 Jan 2023 01:13:29 -0500 X-MC-Unique: r_HN9PU_Oy6jlewcWwmgtQ-1 Received: by mail-ej1-f70.google.com with SMTP id du14-20020a17090772ce00b0087108bbcfa6so4963201ejc.7 for ; Tue, 17 Jan 2023 22:13:28 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=leSDSUqYxgVrElrnUnSnvkj6D04l7A7PmoOZI2j6TnU=; b=Ivy1mtevaPCmha0NW3YpTaqVdGcRdKmQ8F9mEbiE3ecWSFizSPLpL+/a6y5sOrxBS7 SRX02N8w5YGltQkdq+ZdFi+pC4u1wOnjaSUouPGUl1mvE73DM1pZoSL5GQgc8QTV+9lU 4hcnTMkIBGlObHd2/KhViLra/NFAYXWj6k7H7+07vxy/gD5+K/5CCah94glu/XZJkC5E dtQGtxYGJVJnjXFSGlKKYcl4iV9t5OzFE/IG8EsU3wC8bhi1g2zZIZuWQhBupjyNqDH8 mrujVyJPj3g4SoxDwxOqW2gaYBjQAIl+5/9rEZ5ePXb9ofNFfm3iWlUHnDCV64Mojc3u 77KQ== X-Gm-Message-State: AFqh2krWWXPeDWxzF2bgWRbwXa/0646lrJiPikMNmou2AQLVTTPdT54j YYDdoOq/tnKY7bInOs86+V0LKCd6mEj7lIcLCD8Nga0zG5pHxnapp8d31y1jfDHIKxSrECV+WS1 1SzcWBCBAdd5+NsV1UwSAqJw8guAk X-Received: by 2002:a05:6402:400a:b0:496:bdb5:572f with SMTP id d10-20020a056402400a00b00496bdb5572fmr7142137eda.31.1674022407649; Tue, 17 Jan 2023 22:13:27 -0800 (PST) X-Google-Smtp-Source: AMrXdXv9x/uCU2l/BfqsmNw5Er0rDnm8WHyxxdN/6twQiV98RGOqsa0cxK6o5UeSpYv4LaQR51egkQ== X-Received: by 2002:a05:6402:400a:b0:496:bdb5:572f with SMTP id d10-20020a056402400a00b00496bdb5572fmr7142114eda.31.1674022407317; Tue, 17 Jan 2023 22:13:27 -0800 (PST) Received: from cassiopeiae.. ([2a02:810d:4b3f:de78:642:1aff:fe31:a19f]) by smtp.gmail.com with ESMTPSA id r24-20020aa7da18000000b004704658abebsm13776387eds.54.2023.01.17.22.13.26 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 17 Jan 2023 22:13:26 -0800 (PST) From: Danilo Krummrich To: daniel@ffwll.ch, airlied@redhat.com, christian.koenig@amd.com, bskeggs@redhat.com, jason@jlekstrand.net, tzimmermann@suse.de, mripard@kernel.org, corbet@lwn.net Subject: [PATCH drm-next 01/14] drm: execution context for GEM buffers Date: Wed, 18 Jan 2023 07:12:43 +0100 Message-Id: <20230118061256.2689-2-dakr@redhat.com> X-Mailer: git-send-email 2.39.0 In-Reply-To: <20230118061256.2689-1-dakr@redhat.com> References: <20230118061256.2689-1-dakr@redhat.com> MIME-Version: 1.0 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: nouveau@lists.freedesktop.org, linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org, linux-doc@vger.kernel.org Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" From: Christian König This adds the infrastructure for an execution context for GEM buffers which is similar to the existinc TTMs execbuf util and intended to replace it in the long term. The basic functionality is that we abstracts the necessary loop to lock many different GEM buffers with automated deadlock and duplicate handling. v2: drop xarray and use dynamic resized array instead, the locking overhead is unecessary and measureable. Signed-off-by: Christian König --- Documentation/gpu/drm-mm.rst | 12 ++ drivers/gpu/drm/Kconfig | 6 + drivers/gpu/drm/Makefile | 2 + drivers/gpu/drm/amd/amdgpu/Kconfig | 1 + drivers/gpu/drm/drm_exec.c | 295 +++++++++++++++++++++++++++++ include/drm/drm_exec.h | 144 ++++++++++++++ 6 files changed, 460 insertions(+) create mode 100644 drivers/gpu/drm/drm_exec.c create mode 100644 include/drm/drm_exec.h diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index a79fd3549ff8..a52e6f4117d6 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -493,6 +493,18 @@ DRM Sync Objects .. kernel-doc:: drivers/gpu/drm/drm_syncobj.c :export: +DRM Execution context +===================== + +.. kernel-doc:: drivers/gpu/drm/drm_exec.c + :doc: Overview + +.. kernel-doc:: include/drm/drm_exec.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_exec.c + :export: + GPU Scheduler ============= diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 748b93d00184..05134256da59 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -200,6 +200,12 @@ config DRM_TTM GPU memory types. Will be enabled automatically if a device driver uses it. +config DRM_EXEC + tristate + depends on DRM + help + Execution context for command submissions + config DRM_BUDDY tristate depends on DRM diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 496fa5a6147a..4fe190aee584 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -78,6 +78,8 @@ obj-$(CONFIG_DRM_PANEL_ORIENTATION_QUIRKS) += drm_panel_orientation_quirks.o # # Memory-management helpers # +# +obj-$(CONFIG_DRM_EXEC) += drm_exec.o obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index 5341b6b242c3..279fb3bba810 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -11,6 +11,7 @@ config DRM_AMDGPU select DRM_SCHED select DRM_TTM select DRM_TTM_HELPER + select DRM_EXEC select POWER_SUPPLY select HWMON select I2C diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c new file mode 100644 index 000000000000..ed2106c22786 --- /dev/null +++ b/drivers/gpu/drm/drm_exec.c @@ -0,0 +1,295 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +#include +#include +#include + +/** + * DOC: Overview + * + * This component mainly abstracts the retry loop necessary for locking + * multiple GEM objects while preparing hardware operations (e.g. command + * submissions, page table updates etc..). + * + * If a contention is detected while locking a GEM object the cleanup procedure + * unlocks all previously locked GEM objects and locks the contended one first + * before locking any further objects. + * + * After an object is locked fences slots can optionally be reserved on the + * dma_resv object inside the GEM object. + * + * A typical usage pattern should look like this:: + * + * struct drm_gem_object *obj; + * struct drm_exec exec; + * unsigned long index; + * int ret; + * + * drm_exec_init(&exec, true); + * drm_exec_while_not_all_locked(&exec) { + * ret = drm_exec_prepare_obj(&exec, boA, 1); + * drm_exec_continue_on_contention(&exec); + * if (ret) + * goto error; + * + * ret = drm_exec_lock(&exec, boB, 1); + * drm_exec_continue_on_contention(&exec); + * if (ret) + * goto error; + * } + * + * drm_exec_for_each_locked_object(&exec, index, obj) { + * dma_resv_add_fence(obj->resv, fence, DMA_RESV_USAGE_READ); + * ... + * } + * drm_exec_fini(&exec); + * + * See struct dma_exec for more details. + */ + +/* Dummy value used to initially enter the retry loop */ +#define DRM_EXEC_DUMMY (void*)~0 + +/* Initialize the drm_exec_objects container */ +static void drm_exec_objects_init(struct drm_exec_objects *container) +{ + container->objects = kmalloc(PAGE_SIZE, GFP_KERNEL); + + /* If allocation here fails, just delay that till the first use */ + container->max_objects = container->objects ? + PAGE_SIZE / sizeof(void *) : 0; + container->num_objects = 0; +} + +/* Cleanup the drm_exec_objects container */ +static void drm_exec_objects_fini(struct drm_exec_objects *container) +{ + kvfree(container->objects); +} + +/* Make sure we have enough room and add an object the container */ +static int drm_exec_objects_add(struct drm_exec_objects *container, + struct drm_gem_object *obj) +{ + if (unlikely(container->num_objects == container->max_objects)) { + size_t size = container->max_objects * sizeof(void *); + void *tmp; + + tmp = kvrealloc(container->objects, size, size + PAGE_SIZE, + GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + container->objects = tmp; + container->max_objects += PAGE_SIZE / sizeof(void *); + } + drm_gem_object_get(obj); + container->objects[container->num_objects++] = obj; + return 0; +} + +/* Unlock all objects and drop references */ +static void drm_exec_unlock_all(struct drm_exec *exec) +{ + struct drm_gem_object *obj; + unsigned long index; + + drm_exec_for_each_duplicate_object(exec, index, obj) + drm_gem_object_put(obj); + + drm_exec_for_each_locked_object(exec, index, obj) { + dma_resv_unlock(obj->resv); + drm_gem_object_put(obj); + } +} + +/** + * drm_exec_init - initialize a drm_exec object + * @exec: the drm_exec object to initialize + * @interruptible: if locks should be acquired interruptible + * + * Initialize the object and make sure that we can track locked and duplicate + * objects. + */ +void drm_exec_init(struct drm_exec *exec, bool interruptible) +{ + exec->interruptible = interruptible; + drm_exec_objects_init(&exec->locked); + drm_exec_objects_init(&exec->duplicates); + exec->contended = DRM_EXEC_DUMMY; +} +EXPORT_SYMBOL(drm_exec_init); + +/** + * drm_exec_fini - finalize a drm_exec object + * @exec: the drm_exec object to finilize + * + * Unlock all locked objects, drop the references to objects and free all memory + * used for tracking the state. + */ +void drm_exec_fini(struct drm_exec *exec) +{ + drm_exec_unlock_all(exec); + drm_exec_objects_fini(&exec->locked); + drm_exec_objects_fini(&exec->duplicates); + if (exec->contended != DRM_EXEC_DUMMY) { + drm_gem_object_put(exec->contended); + ww_acquire_fini(&exec->ticket); + } +} +EXPORT_SYMBOL(drm_exec_fini); + +/** + * drm_exec_cleanup - cleanup when contention is detected + * @exec: the drm_exec object to cleanup + * + * Cleanup the current state and return true if we should stay inside the retry + * loop, false if there wasn't any contention detected and we can keep the + * objects locked. + */ +bool drm_exec_cleanup(struct drm_exec *exec) +{ + if (likely(!exec->contended)) { + ww_acquire_done(&exec->ticket); + return false; + } + + if (likely(exec->contended == DRM_EXEC_DUMMY)) { + exec->contended = NULL; + ww_acquire_init(&exec->ticket, &reservation_ww_class); + return true; + } + + drm_exec_unlock_all(exec); + exec->locked.num_objects = 0; + exec->duplicates.num_objects = 0; + return true; +} +EXPORT_SYMBOL(drm_exec_cleanup); + +/* Track the locked object in the xa and reserve fences */ +static int drm_exec_obj_locked(struct drm_exec_objects *container, + struct drm_gem_object *obj, + unsigned int num_fences) +{ + int ret; + + if (container) { + ret = drm_exec_objects_add(container, obj); + if (ret) + return ret; + } + + if (num_fences) { + ret = dma_resv_reserve_fences(obj->resv, num_fences); + if (ret) + goto error_erase; + } + + return 0; + +error_erase: + if (container) { + --container->num_objects; + drm_gem_object_put(obj); + } + return ret; +} + +/* Make sure the contended object is locked first */ +static int drm_exec_lock_contended(struct drm_exec *exec) +{ + struct drm_gem_object *obj = exec->contended; + int ret; + + if (likely(!obj)) + return 0; + + if (exec->interruptible) { + ret = dma_resv_lock_slow_interruptible(obj->resv, + &exec->ticket); + if (unlikely(ret)) + goto error_dropref; + } else { + dma_resv_lock_slow(obj->resv, &exec->ticket); + } + + ret = drm_exec_obj_locked(&exec->locked, obj, 0); + if (unlikely(ret)) + dma_resv_unlock(obj->resv); + +error_dropref: + /* Always cleanup the contention so that error handling can kick in */ + drm_gem_object_put(obj); + exec->contended = NULL; + return ret; +} + +/** + * drm_exec_prepare_obj - prepare a GEM object for use + * @exec: the drm_exec object with the state + * @obj: the GEM object to prepare + * @num_fences: how many fences to reserve + * + * Prepare a GEM object for use by locking it and reserving fence slots. All + * succesfully locked objects are put into the locked container. Duplicates + * detected as well and automatically moved into the duplicates container. + * + * Returns: -EDEADLK if a contention is detected, -ENOMEM when memory + * allocation failed and zero for success. + */ +int drm_exec_prepare_obj(struct drm_exec *exec, struct drm_gem_object *obj, + unsigned int num_fences) +{ + int ret; + + ret = drm_exec_lock_contended(exec); + if (unlikely(ret)) + return ret; + + if (exec->interruptible) + ret = dma_resv_lock_interruptible(obj->resv, &exec->ticket); + else + ret = dma_resv_lock(obj->resv, &exec->ticket); + + if (unlikely(ret == -EDEADLK)) { + drm_gem_object_get(obj); + exec->contended = obj; + return -EDEADLK; + } + + if (unlikely(ret == -EALREADY)) { + struct drm_exec_objects *container = &exec->duplicates; + + /* + * If this is the first locked GEM object it was most likely + * just contended. So don't add it to the duplicates, just + * reserve the fence slots. + */ + if (exec->locked.num_objects && exec->locked.objects[0] == obj) + container = NULL; + + ret = drm_exec_obj_locked(container, obj, num_fences); + if (ret) + return ret; + + } else if (unlikely(ret)) { + return ret; + + } else { + ret = drm_exec_obj_locked(&exec->locked, obj, num_fences); + if (ret) + goto error_unlock; + } + + drm_gem_object_get(obj); + return 0; + +error_unlock: + dma_resv_unlock(obj->resv); + return ret; +} +EXPORT_SYMBOL(drm_exec_prepare_obj); + +MODULE_DESCRIPTION("DRM execution context"); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h new file mode 100644 index 000000000000..f73981c6292e --- /dev/null +++ b/include/drm/drm_exec.h @@ -0,0 +1,144 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +#ifndef __DRM_EXEC_H__ +#define __DRM_EXEC_H__ + +#include + +struct drm_gem_object; + +/** + * struct drm_exec_objects - Container for GEM objects in a drm_exec + */ +struct drm_exec_objects { + unsigned int num_objects; + unsigned int max_objects; + struct drm_gem_object **objects; +}; + +/** + * drm_exec_objects_for_each - iterate over all the objects inside the container + */ +#define drm_exec_objects_for_each(array, index, obj) \ + for (index = 0, obj = (array)->objects[0]; \ + index < (array)->num_objects; \ + ++index, obj = (array)->objects[index]) + +/** + * struct drm_exec - Execution context + */ +struct drm_exec { + /** + * @interruptible: If locks should be taken interruptible + */ + bool interruptible; + + /** + * @ticket: WW ticket used for acquiring locks + */ + struct ww_acquire_ctx ticket; + + /** + * @locked: container for the locked GEM objects + */ + struct drm_exec_objects locked; + + /** + * @duplicates: container for the duplicated GEM objects + */ + struct drm_exec_objects duplicates; + + /** + * @contended: contended GEM object we backet of for. + */ + struct drm_gem_object *contended; +}; + +/** + * drm_exec_for_each_locked_object - iterate over all the locked objects + * @exec: drm_exec object + * @index: unsigned long index for the iteration + * @obj: the current GEM object + * + * Iterate over all the locked GEM objects inside the drm_exec object. + */ +#define drm_exec_for_each_locked_object(exec, index, obj) \ + drm_exec_objects_for_each(&(exec)->locked, index, obj) + +/** + * drm_exec_for_each_duplicate_object - iterate over all the duplicate objects + * @exec: drm_exec object + * @index: unsigned long index for the iteration + * @obj: the current GEM object + * + * Iterate over all the duplicate GEM objects inside the drm_exec object. + */ +#define drm_exec_for_each_duplicate_object(exec, index, obj) \ + drm_exec_objects_for_each(&(exec)->duplicates, index, obj) + +/** + * drm_exec_while_not_all_locked - loop until all GEM objects are prepared + * @exec: drm_exec object + * + * Core functionality of the drm_exec object. Loops until all GEM objects are + * prepared and no more contention exists. + * + * At the beginning of the loop it is guaranteed that no GEM object is locked. + */ +#define drm_exec_while_not_all_locked(exec) \ + while (drm_exec_cleanup(exec)) + +/** + * drm_exec_continue_on_contention - continue the loop when we need to cleanup + * @exec: drm_exec object + * + * Control flow helper to continue when a contention was detected and we need to + * clean up and re-start the loop to prepare all GEM objects. + */ +#define drm_exec_continue_on_contention(exec) \ + if (unlikely(drm_exec_is_contended(exec))) \ + continue + +/** + * drm_exec_break_on_contention - break a subordinal loop on contention + * @exec: drm_exec object + * + * Control flow helper to break a subordinal loop when a contention was detected + * and we need to clean up and re-start the loop to prepare all GEM objects. + */ +#define drm_exec_break_on_contention(exec) \ + if (unlikely(drm_exec_is_contended(exec))) \ + break + +/** + * drm_exec_is_contended - check for contention + * @exec: drm_exec object + * + * Returns true if the drm_exec object has run into some contention while + * locking a GEM object and needs to clean up. + */ +static inline bool drm_exec_is_contended(struct drm_exec *exec) +{ + return !!exec->contended; +} + +/** + * drm_exec_has_duplicates - check for duplicated GEM object + * @exec: drm_exec object + * + * Return true if the drm_exec object has encountered some already locked GEM + * objects while trying to lock them. This can happen if multiple GEM objects + * share the same underlying resv object. + */ +static inline bool drm_exec_has_duplicates(struct drm_exec *exec) +{ + return exec->duplicates.num_objects > 0; +} + +void drm_exec_init(struct drm_exec *exec, bool interruptible); +void drm_exec_fini(struct drm_exec *exec); +bool drm_exec_cleanup(struct drm_exec *exec); +int drm_exec_prepare_obj(struct drm_exec *exec, struct drm_gem_object *obj, + unsigned int num_fences); + +#endif