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 C706FC001B2 for ; Tue, 7 Nov 2023 05:26:06 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id F06E510E4C2; Tue, 7 Nov 2023 05:26:04 +0000 (UTC) Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.136]) by gabe.freedesktop.org (Postfix) with ESMTPS id 7436010E4B1 for ; Tue, 7 Nov 2023 05:25:58 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1699334758; x=1730870758; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=hBlT/yMKNzXKHSkv/plJ8JxnfWMhaYB6Uo4orTw0rbg=; b=YG7cv5tihcr07zgT6QvSta+D/xq1L1u9vFnGx7SjDuX5NYrSjZKXVNah PHTnofskZnd7RCJghEJjyX6VBeUXggBbd0r6ZbskxBwAzgb1yjHCM9rOp e5Rpmyy8RSuHBITBx0NqYGvUvEjRPC1EpYpHaA1IkYO5xjty5U+oH3jlU YApxI0Q7Z6F4bjn1qArkalc9OXhGQtwu4QHuIeWUs88L8r8kfugWpIhWu GnIxRDgyctJ82B7CmqqlDDR57NHckZXeRxLKblG7FjU/r0Nc7HknW36aI M1QPSe+s251NwCVUu0OgRRfrBlLkNACxujGLiuOfw/TGCQg9zQfZen1Hp g==; X-IronPort-AV: E=McAfee;i="6600,9927,10886"; a="368769539" X-IronPort-AV: E=Sophos;i="6.03,282,1694761200"; d="scan'208";a="368769539" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga106.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Nov 2023 21:25:58 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10886"; a="791689896" X-IronPort-AV: E=Sophos;i="6.03,282,1694761200"; d="scan'208";a="791689896" Received: from lstrano-desk.jf.intel.com ([10.54.39.91]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Nov 2023 21:25:56 -0800 From: Matthew Brost To: Date: Mon, 6 Nov 2023 21:26:03 -0800 Message-Id: <20231107052603.124361-28-matthew.brost@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20231107052603.124361-1-matthew.brost@intel.com> References: <20231107052603.124361-1-matthew.brost@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Subject: [Intel-xe] [PATCH v2 27/27] drm/xe/uapi: Make sync vs async VM bind operations per IOCTL rather than queue 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: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" Making sync vs async per IOCTL simplifies the uAPI while also making it more flexible. Adjust the uAPI accordingly. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_exec_queue.c | 7 +--- drivers/gpu/drm/xe/xe_exec_queue_types.h | 2 - drivers/gpu/drm/xe/xe_vm.c | 53 ++++++++---------------- drivers/gpu/drm/xe/xe_vm_types.h | 15 +++---- include/uapi/drm/xe_drm.h | 6 +-- 5 files changed, 28 insertions(+), 55 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 6d142fb75dfc..57a4b688505f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -625,10 +625,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (XE_IOCTL_DBG(xe, eci[0].gt_id >= xe->info.gt_count)) return -EINVAL; - if (eci[0].engine_class >= DRM_XE_ENGINE_CLASS_VM_BIND_ASYNC) { - bool sync = eci[0].engine_class == - DRM_XE_ENGINE_CLASS_VM_BIND_SYNC; - + if (eci[0].engine_class == DRM_XE_ENGINE_CLASS_VM_BIND) { for_each_gt(gt, xe, id) { struct xe_exec_queue *new; @@ -654,8 +651,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, args->width, hwe, EXEC_QUEUE_FLAG_PERSISTENT | EXEC_QUEUE_FLAG_VM | - (sync ? 0 : - EXEC_QUEUE_FLAG_VM_ASYNC) | (id ? EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD : 0)); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 35ffe7c55f25..91c1f243aad4 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -71,8 +71,6 @@ struct xe_exec_queue { #define EXEC_QUEUE_FLAG_VM BIT(4) /* child of VM queue for multi-tile VM jobs */ #define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD BIT(5) -/* VM jobs for this queue are asynchronous */ -#define EXEC_QUEUE_FLAG_VM_ASYNC BIT(6) /** * @flags: flags for this exec queue, should statically setup aside from ban diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 52f563580fc3..9ec0896e5ac6 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -827,7 +827,8 @@ int xe_vm_userptr_check_repin(struct xe_vm *vm) static void xe_vma_ops_init(struct xe_vma_ops *vops, struct xe_vm *vm, struct xe_exec_queue *q, - struct xe_sync_entry *syncs, u32 num_syncs) + struct xe_sync_entry *syncs, u32 num_syncs, + bool async) { memset(vops, 0, sizeof(*vops)); INIT_LIST_HEAD(&vops->list); @@ -835,6 +836,7 @@ static void xe_vma_ops_init(struct xe_vma_ops *vops, struct xe_vm *vm, vops->q = q; vops->syncs = syncs; vops->num_syncs = num_syncs; + vops->async = async; } static int xe_vma_ops_alloc(struct xe_vma_ops *vops) @@ -1431,7 +1433,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) init_rwsem(&vm->lock); - xe_vma_ops_init(&vm->dummy_ops.vops, vm, NULL, NULL, 0); + xe_vma_ops_init(&vm->dummy_ops.vops, vm, NULL, NULL, 0, false); INIT_LIST_HEAD(&vm->dummy_ops.op.link); list_add(&vm->dummy_ops.op.link, &vm->dummy_ops.vops.list); for (i = 0; i < XE_MAX_TILES_PER_DEVICE; ++i) @@ -1517,9 +1519,6 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) struct xe_gt *gt = tile->primary_gt; struct xe_vm *migrate_vm; struct xe_exec_queue *q; - u32 create_flags = EXEC_QUEUE_FLAG_VM | - ((flags & XE_VM_FLAG_ASYNC_DEFAULT) ? - EXEC_QUEUE_FLAG_VM_ASYNC : 0); if (!vm->pt_root[id]) continue; @@ -1527,7 +1526,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) migrate_vm = xe_migrate_get_vm(tile->migrate); q = xe_exec_queue_create_class(xe, gt, migrate_vm, XE_ENGINE_CLASS_COPY, - create_flags); + EXEC_QUEUE_FLAG_VM); xe_vm_put(migrate_vm); if (IS_ERR(q)) { xe_vm_close_and_put(vm); @@ -1767,15 +1766,8 @@ to_wait_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) return q ? q : vm->q[0]; } -static bool xe_vm_sync_mode(struct xe_vm *vm, struct xe_exec_queue *q) -{ - return q ? !(q->flags & EXEC_QUEUE_FLAG_VM_ASYNC) : - !(vm->flags & XE_VM_FLAG_ASYNC_DEFAULT); -} - #define ALL_DRM_XE_VM_CREATE_FLAGS (DRM_XE_VM_CREATE_SCRATCH_PAGE | \ DRM_XE_VM_CREATE_COMPUTE_MODE | \ - DRM_XE_VM_CREATE_ASYNC_DEFAULT | \ DRM_XE_VM_CREATE_FAULT_MODE) int xe_vm_create_ioctl(struct drm_device *dev, void *data, @@ -1829,8 +1821,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, flags |= XE_VM_FLAG_SCRATCH_PAGE; if (args->flags & DRM_XE_VM_CREATE_COMPUTE_MODE) flags |= XE_VM_FLAG_COMPUTE_MODE; - if (args->flags & DRM_XE_VM_CREATE_ASYNC_DEFAULT) - flags |= XE_VM_FLAG_ASYNC_DEFAULT; if (args->flags & DRM_XE_VM_CREATE_FAULT_MODE) flags |= XE_VM_FLAG_FAULT_MODE; @@ -2605,12 +2595,13 @@ struct dma_fence *xe_vm_ops_execute(struct xe_vm *vm, struct xe_vma_ops *vops) return fence; } -static void vm_bind_ioctl_ops_install_fences(struct xe_vm *vm, - struct xe_vma_ops *vops, - struct dma_fence *fence) +static int vm_bind_ioctl_ops_install_fences(struct xe_vm *vm, + struct xe_vma_ops *vops, + struct dma_fence *fence) { struct xe_exec_queue *wait_exec_queue = to_wait_exec_queue(vm, vops->q); struct xe_vma_op *op; + long timeout = 0; int i; list_for_each_entry(op, &vops->list, link) { @@ -2623,9 +2614,13 @@ static void vm_bind_ioctl_ops_install_fences(struct xe_vm *vm, for (i = 0; i < vops->num_syncs; i++) xe_sync_entry_signal(vops->syncs + i, NULL, fence); xe_exec_queue_last_fence_set(wait_exec_queue, vm, fence); - if (xe_vm_sync_mode(vm, vops->q)) - dma_fence_wait(fence, true); + if (!vops->async) + timeout = dma_fence_wait(fence, true); dma_fence_put(fence); + + if (timeout < 0) + return -EINTR; + return 0; } static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, @@ -2648,7 +2643,7 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, if (IS_ERR(fence)) return PTR_ERR(fence); - vm_bind_ioctl_ops_install_fences(vm, vops, fence); + err = vm_bind_ioctl_ops_install_fences(vm, vops, fence); } drm_exec_fini(&exec); @@ -2805,12 +2800,6 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) err = -EINVAL; goto put_exec_queue; } - - if (XE_IOCTL_DBG(xe, args->num_binds && async != - !!(q->flags & EXEC_QUEUE_FLAG_VM_ASYNC))) { - err = -EINVAL; - goto put_exec_queue; - } } vm = xe_vm_lookup(xef, args->vm_id); @@ -2819,14 +2808,6 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto put_exec_queue; } - if (!args->exec_queue_id) { - if (XE_IOCTL_DBG(xe, args->num_binds && async != - !!(vm->flags & XE_VM_FLAG_ASYNC_DEFAULT))) { - err = -EINVAL; - goto put_vm; - } - } - err = down_write_killable(&vm->lock); if (err) goto put_vm; @@ -2928,7 +2909,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto free_syncs; } - xe_vma_ops_init(&vops, vm, q, syncs, num_syncs); + xe_vma_ops_init(&vops, vm, q, syncs, num_syncs, async); for (i = 0; i < args->num_binds; ++i) { u64 range = bind_ops[i].range; u64 addr = bind_ops[i].addr; diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index adbd8199aa8b..2ff904edb583 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -217,6 +217,8 @@ struct xe_vma_ops { struct xe_sync_entry *syncs; /** @num_syncs: number of syncs */ u32 num_syncs; + /** @async: VMA operations are asynchronous */ + bool async; /** @pt_update_ops: page table update operations */ struct xe_vm_pgtable_update_ops pt_update_ops[XE_MAX_TILES_PER_DEVICE]; }; @@ -252,13 +254,12 @@ struct xe_vm { */ #define XE_VM_FLAG_64K BIT(0) #define XE_VM_FLAG_COMPUTE_MODE BIT(1) -#define XE_VM_FLAG_ASYNC_DEFAULT BIT(2) -#define XE_VM_FLAG_MIGRATION BIT(3) -#define XE_VM_FLAG_SCRATCH_PAGE BIT(4) -#define XE_VM_FLAG_FAULT_MODE BIT(5) -#define XE_VM_FLAG_BANNED BIT(6) -#define XE_VM_FLAG_TILE_ID(flags) FIELD_GET(GENMASK(8, 7), flags) -#define XE_VM_FLAG_SET_TILE_ID(tile) FIELD_PREP(GENMASK(8, 7), (tile)->id) +#define XE_VM_FLAG_MIGRATION BIT(2) +#define XE_VM_FLAG_SCRATCH_PAGE BIT(3) +#define XE_VM_FLAG_FAULT_MODE BIT(4) +#define XE_VM_FLAG_BANNED BIT(5) +#define XE_VM_FLAG_TILE_ID(flags) FIELD_GET(GENMASK(7, 6), flags) +#define XE_VM_FLAG_SET_TILE_ID(tile) FIELD_PREP(GENMASK(7, 6), (tile)->id) unsigned long flags; /** @composite_fence_ctx: context composite fence */ diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 9bd7092a7ea4..78a346960240 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -137,8 +137,7 @@ struct drm_xe_engine_class_instance { * Kernel only classes (not actual hardware engine class). Used for * creating ordered queues of VM bind operations. */ -#define DRM_XE_ENGINE_CLASS_VM_BIND_ASYNC 5 -#define DRM_XE_ENGINE_CLASS_VM_BIND_SYNC 6 +#define DRM_XE_ENGINE_CLASS_VM_BIND 5 __u16 engine_class; __u16 engine_instance; @@ -597,8 +596,7 @@ struct drm_xe_vm_create { #define DRM_XE_VM_CREATE_SCRATCH_PAGE (0x1 << 0) #define DRM_XE_VM_CREATE_COMPUTE_MODE (0x1 << 1) -#define DRM_XE_VM_CREATE_ASYNC_DEFAULT (0x1 << 2) -#define DRM_XE_VM_CREATE_FAULT_MODE (0x1 << 3) +#define DRM_XE_VM_CREATE_FAULT_MODE (0x1 << 2) /** @flags: Flags */ __u32 flags; -- 2.34.1