From patchwork Sun Nov 13 07:57:21 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Niranjana Vishwanathapura X-Patchwork-Id: 13041485 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 B426FC433FE for ; Sun, 13 Nov 2022 07:59:36 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id CA07610E228; Sun, 13 Nov 2022 07:58:41 +0000 (UTC) Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by gabe.freedesktop.org (Postfix) with ESMTPS id B835610E1F1; Sun, 13 Nov 2022 07:57:42 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1668326262; x=1699862262; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=EbWPB/++PrwuOGFA6RFX8Aam7nLHSJp+9xBpt66TdFs=; b=YFIPUfk+xBPcx14b9L1tl2AJAej9nFeJrn+O6xBBOgC38zvLaSRMwo8k MGsLo0fL7Te4ne6rDFXxX1W3ScWQ2wju/XTdTShlRsDvJbwtkJJ3lglZk anP+NNPMn1lnVu5V1tNZni2It/TUdisENqohYah42uGhz7TD7AbUhQ1lV Fovi3FosfSY/9+gTuK/y1KFNN18TcOyxmR4r1+zlnoeardaY45FluZ+Jx OgUndyAsxKZYsB/Ygv5gTshETGsnI5UWuIZC7lajwLNaCprlEyJtz/UEq pJbjC81Y0M36bWHikeb+RGSj7G1iHPwjptt+7qeoNaypuLW8NVG86dtuR A==; X-IronPort-AV: E=McAfee;i="6500,9779,10529"; a="312936336" X-IronPort-AV: E=Sophos;i="5.96,161,1665471600"; d="scan'208";a="312936336" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga102.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 12 Nov 2022 23:57:42 -0800 X-IronPort-AV: E=McAfee;i="6500,9779,10529"; a="669235714" X-IronPort-AV: E=Sophos;i="5.96,161,1665471600"; d="scan'208";a="669235714" Received: from nvishwa1-desk.sc.intel.com ([172.25.29.76]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 12 Nov 2022 23:57:41 -0800 From: Niranjana Vishwanathapura To: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org Subject: [PATCH v7 09/20] drm/i915/vm_bind: Add out fence support Date: Sat, 12 Nov 2022 23:57:21 -0800 Message-Id: <20221113075732.32100-10-niranjana.vishwanathapura@intel.com> X-Mailer: git-send-email 2.21.0.rc0.32.g243a4c7e27 In-Reply-To: <20221113075732.32100-1-niranjana.vishwanathapura@intel.com> References: <20221113075732.32100-1-niranjana.vishwanathapura@intel.com> MIME-Version: 1.0 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: matthew.brost@intel.com, paulo.r.zanoni@intel.com, tvrtko.ursulin@intel.com, jani.nikula@intel.com, lionel.g.landwerlin@intel.com, thomas.hellstrom@intel.com, matthew.auld@intel.com, jason@jlekstrand.net, andi.shyti@linux.intel.com, daniel.vetter@intel.com, christian.koenig@amd.com Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" Add support for handling out fence for vm_bind call. v2: Reset vma->vm_bind_fence.syncobj to NULL at the end of vm_bind call. v3: Remove vm_unbind out fence uapi which is not supported yet. v4: Return error if I915_TIMELINE_FENCE_WAIT fence flag is set. Wait for bind to complete iff I915_TIMELINE_FENCE_SIGNAL is not specified. v5: Ensure __I915_TIMELINE_FENCE_UNKNOWN_FLAGS are not set. Reviewed-by: Matthew Auld Signed-off-by: Niranjana Vishwanathapura Signed-off-by: Andi Shyti --- drivers/gpu/drm/i915/gem/i915_gem_vm_bind.h | 4 + .../drm/i915/gem/i915_gem_vm_bind_object.c | 98 ++++++++++++++++++- drivers/gpu/drm/i915/i915_vma.c | 7 +- drivers/gpu/drm/i915/i915_vma_types.h | 7 ++ include/uapi/drm/i915_drm.h | 58 ++++++++++- 5 files changed, 165 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_vm_bind.h b/drivers/gpu/drm/i915/gem/i915_gem_vm_bind.h index 36262a6357b5..b70e900e35ab 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_vm_bind.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_vm_bind.h @@ -8,6 +8,7 @@ #include +struct dma_fence; struct drm_device; struct drm_file; struct i915_address_space; @@ -23,4 +24,7 @@ int i915_gem_vm_unbind_ioctl(struct drm_device *dev, void *data, void i915_gem_vm_unbind_all(struct i915_address_space *vm); +void i915_vm_bind_signal_fence(struct i915_vma *vma, + struct dma_fence * const fence); + #endif /* __I915_GEM_VM_BIND_H */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c b/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c index 6cfbce2a4a9b..cce663a1b409 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c @@ -7,6 +7,8 @@ #include +#include + #include "gem/i915_gem_context.h" #include "gem/i915_gem_vm_bind.h" @@ -101,6 +103,77 @@ static void i915_gem_vm_bind_remove(struct i915_vma *vma, bool release_obj) i915_gem_object_put(vma->obj); } +static int i915_vm_bind_add_fence(struct drm_file *file, struct i915_vma *vma, + u32 handle, u64 point) +{ + struct drm_syncobj *syncobj; + + syncobj = drm_syncobj_find(file, handle); + if (!syncobj) { + drm_dbg(&vma->vm->i915->drm, + "Invalid syncobj handle provided\n"); + return -ENOENT; + } + + /* + * For timeline syncobjs we need to preallocate chains for + * later signaling. + */ + if (point) { + vma->vm_bind_fence.chain_fence = dma_fence_chain_alloc(); + if (!vma->vm_bind_fence.chain_fence) { + drm_syncobj_put(syncobj); + return -ENOMEM; + } + } else { + vma->vm_bind_fence.chain_fence = NULL; + } + vma->vm_bind_fence.syncobj = syncobj; + vma->vm_bind_fence.value = point; + + return 0; +} + +static void i915_vm_bind_put_fence(struct i915_vma *vma) +{ + if (!vma->vm_bind_fence.syncobj) + return; + + drm_syncobj_put(vma->vm_bind_fence.syncobj); + dma_fence_chain_free(vma->vm_bind_fence.chain_fence); + vma->vm_bind_fence.syncobj = NULL; +} + +/** + * i915_vm_bind_signal_fence() - Add fence to vm_bind syncobj + * @vma: vma mapping requiring signaling + * @fence: fence to be added + * + * Associate specified @fence with the @vma's syncobj to be + * signaled after the @fence work completes. + */ +void i915_vm_bind_signal_fence(struct i915_vma *vma, + struct dma_fence * const fence) +{ + struct drm_syncobj *syncobj = vma->vm_bind_fence.syncobj; + + if (!syncobj) + return; + + if (vma->vm_bind_fence.chain_fence) { + drm_syncobj_add_point(syncobj, + vma->vm_bind_fence.chain_fence, + fence, vma->vm_bind_fence.value); + /* + * The chain's ownership is transferred to the + * timeline. + */ + vma->vm_bind_fence.chain_fence = NULL; + } else { + drm_syncobj_replace_fence(syncobj, fence); + } +} + static int i915_gem_vm_unbind_vma(struct i915_address_space *vm, struct drm_i915_gem_vm_unbind *va) { @@ -206,6 +279,11 @@ static int i915_gem_vm_bind_obj(struct i915_address_space *vm, if (!va->length || !IS_ALIGNED(va->start, I915_GTT_PAGE_SIZE)) ret = -EINVAL; + /* In fences are not supported */ + if ((va->fence.flags & I915_TIMELINE_FENCE_WAIT) || + (va->fence.flags & __I915_TIMELINE_FENCE_UNKNOWN_FLAGS)) + ret = -EINVAL; + obj = i915_gem_object_lookup(file, va->handle); if (!obj) return -ENOENT; @@ -238,6 +316,13 @@ static int i915_gem_vm_bind_obj(struct i915_address_space *vm, goto unlock_vm; } + if (va->fence.flags & I915_TIMELINE_FENCE_SIGNAL) { + ret = i915_vm_bind_add_fence(file, vma, va->fence.handle, + va->fence.value); + if (ret) + goto put_vma; + } + pin_flags = va->start | PIN_OFFSET_FIXED | PIN_USER | PIN_VALIDATE | PIN_NOEVICT; @@ -250,10 +335,12 @@ static int i915_gem_vm_bind_obj(struct i915_address_space *vm, if (ret) continue; - /* Wait for bind to complete */ - ret = i915_vma_wait_for_bind(vma); - if (ret) - continue; + /* If out fence is not requested, wait for bind to complete */ + if (!(va->fence.flags & I915_TIMELINE_FENCE_SIGNAL)) { + ret = i915_vma_wait_for_bind(vma); + if (ret) + continue; + } list_add_tail(&vma->vm_bind_link, &vm->vm_bound_list); i915_vm_bind_it_insert(vma, &vm->va); @@ -265,6 +352,9 @@ static int i915_gem_vm_bind_obj(struct i915_address_space *vm, i915_gem_object_get(vma->obj); } + if (va->fence.flags & I915_TIMELINE_FENCE_SIGNAL) + i915_vm_bind_put_fence(vma); +put_vma: if (ret) i915_vma_destroy(vma); unlock_vm: diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 3c2ee29536d4..6d929791d33d 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -29,6 +29,7 @@ #include "display/intel_frontbuffer.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_tiling.h" +#include "gem/i915_gem_vm_bind.h" #include "gt/intel_engine.h" #include "gt/intel_engine_heartbeat.h" #include "gt/intel_gt.h" @@ -1569,8 +1570,12 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, err_vma_res: i915_vma_resource_free(vma_res); err_fence: - if (work) + if (work) { + if (i915_vma_is_persistent(vma)) + i915_vm_bind_signal_fence(vma, &work->base.dma); + dma_fence_work_commit_imm(&work->base); + } err_rpm: if (wakeref) intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h index 61d0ec1a4e18..7c8c293ddfcb 100644 --- a/drivers/gpu/drm/i915/i915_vma_types.h +++ b/drivers/gpu/drm/i915/i915_vma_types.h @@ -308,6 +308,13 @@ struct i915_vma { /** @vm_rebind_link: link to vm_rebind_list and protected by vm_rebind_lock */ struct list_head vm_rebind_link; /* Link in vm_rebind_list */ + /** Timeline fence for vm_bind completion notification */ + struct { + struct dma_fence_chain *chain_fence; + struct drm_syncobj *syncobj; + u64 value; + } vm_bind_fence; + /** Interval tree structures for persistent vma */ /** @rb: node for the interval tree of vm for persistent vmas */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 1a87fc2985c9..2ad8ced69691 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1533,6 +1533,41 @@ struct drm_i915_gem_execbuffer2 { #define i915_execbuffer2_get_context_id(eb2) \ ((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK) +/** + * struct drm_i915_gem_timeline_fence - An input or output timeline fence. + * + * The operation will wait for input fence to signal. + * + * The returned output fence will be signaled after the completion of the + * operation. + */ +struct drm_i915_gem_timeline_fence { + /** @handle: User's handle for a drm_syncobj to wait on or signal. */ + __u32 handle; + + /** + * @flags: Supported flags are: + * + * I915_TIMELINE_FENCE_WAIT: + * Wait for the input fence before the operation. + * + * I915_TIMELINE_FENCE_SIGNAL: + * Return operation completion fence as output. + */ + __u32 flags; +#define I915_TIMELINE_FENCE_WAIT (1 << 0) +#define I915_TIMELINE_FENCE_SIGNAL (1 << 1) +#define __I915_TIMELINE_FENCE_UNKNOWN_FLAGS (-(I915_TIMELINE_FENCE_SIGNAL << 1)) + + /** + * @value: A point in the timeline. + * Value must be 0 for a binary drm_syncobj. A Value of 0 for a + * timeline drm_syncobj is invalid as it turns a drm_syncobj into a + * binary one. + */ + __u64 value; +}; + struct drm_i915_gem_pin { /** Handle of the buffer to be pinned. */ __u32 handle; @@ -3785,7 +3820,8 @@ struct drm_i915_gem_create_ext_vm_private { * -ENOSPC will be returned if the VA range specified can't be reserved. * * VM_BIND/UNBIND ioctl calls executed on different CPU threads concurrently - * are not ordered. + * are not ordered. Furthermore, parts of the VM_BIND operation can be done + * asynchronously, if valid @fence is specified. */ struct drm_i915_gem_vm_bind { /** @vm_id: VM (address space) id to bind */ @@ -3803,14 +3839,28 @@ struct drm_i915_gem_vm_bind { /** @length: Length of mapping to bind */ __u64 length; - /** @flags: Currently reserved, MBZ. */ + /** + * @flags: Currently reserved, MBZ. + * + * Note that @fence carries its own flags. + */ __u64 flags; /** @rsvd: Reserved, MBZ */ __u64 rsvd[2]; - /** @rsvd2: Reserved for timeline fence */ - __u64 rsvd2[2]; + /** + * @fence: Timeline fence for bind completion signaling. + * + * Timeline fence is of format struct drm_i915_gem_timeline_fence. + * + * It is an out fence, hence using I915_TIMELINE_FENCE_WAIT flag + * is invalid, and an error will be returned. + * + * If I915_TIMELINE_FENCE_SIGNAL flag is not set, then out fence + * is not requested and binding is completed synchronously. + */ + struct drm_i915_gem_timeline_fence fence; /** * @extensions: Zero-terminated chain of extensions.