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 9287EC4332F for ; Tue, 31 Oct 2023 14:21:59 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 6227410E4FF; Tue, 31 Oct 2023 14:21:59 +0000 (UTC) Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.120]) by gabe.freedesktop.org (Postfix) with ESMTPS id 24FE310E4FE for ; Tue, 31 Oct 2023 14:21:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1698762106; x=1730298106; h=from:to:subject:date:message-id:in-reply-to:references: mime-version:content-transfer-encoding; bh=svPi0Jjf/qxZ1daN+g3aekJ5jB6SKVNElIg55czODi8=; b=D9DDu3ylTFugxxLem8oLVKLFWxNZosc2cxYAVsVyz+fbGc9KwfTalztj TXs/u9VfshYftlo68/DbTAlP0nq8YCya+MwRBQHKPPlc+gyvdvd6W5ZeU mRWgRP5MQSEp66ylPBlYm9rZDCKRZvSOLoGEug9Kkw/WZymbRwBGxPc0/ koXBSLX5FcMAyCyETRdxQqLVuahXiAwgGKDV2HkQOr8N04tlYR56aLWuH qUI318c42jmvwXZP387m2bxLQzyZBXoKKlyDjFs6ClIaYUfu2MzgeesZi /4p5KdDlBkWbxE9mlzjN14yYObGkMwtiiFiA/9XxBvgNRW7kdI0+l0QNR w==; X-IronPort-AV: E=McAfee;i="6600,9927,10880"; a="387183128" X-IronPort-AV: E=Sophos;i="6.03,265,1694761200"; d="scan'208";a="387183128" Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga104.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 31 Oct 2023 07:21:45 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10880"; a="934126060" X-IronPort-AV: E=Sophos;i="6.03,265,1694761200"; d="scan'208";a="934126060" Received: from olindum-mobl1.ger.corp.intel.com (HELO fedora..) ([10.249.254.59]) by orsmga005-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 31 Oct 2023 07:21:45 -0700 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= To: intel-xe@lists.freedesktop.org Date: Tue, 31 Oct 2023 15:21:24 +0100 Message-ID: <20231031142133.17129-2-thomas.hellstrom@linux.intel.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231031142133.17129-1-thomas.hellstrom@linux.intel.com> References: <20231031142133.17129-1-thomas.hellstrom@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Subject: [Intel-xe] [CI 02/11] drm/gpuvm: add common dma-resv per struct drm_gpuvm 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" From: Danilo Krummrich Provide a common dma-resv for GEM objects not being used outside of this GPU-VM. This is used in a subsequent patch to generalize dma-resv, external and evicted object handling and GEM validation. Reviewed-by: Thomas Hellström Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/drm_gpuvm.c | 53 ++++++++++++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_uvmm.c | 13 ++++++- include/drm/drm_gpuvm.h | 33 ++++++++++++++++ 3 files changed, 97 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index b378554b81ac..d4907aace831 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -61,6 +61,15 @@ * contained within struct drm_gpuva already. Hence, for inserting &drm_gpuva * entries from within dma-fence signalling critical sections it is enough to * pre-allocate the &drm_gpuva structures. + * + * &drm_gem_objects which are private to a single VM can share a common + * &dma_resv in order to improve locking efficiency (e.g. with &drm_exec). + * For this purpose drivers must pass a &drm_gem_object to drm_gpuvm_init(), in + * the following called 'resv object', which serves as the container of the + * GPUVM's shared &dma_resv. This resv object can be a driver specific + * &drm_gem_object, such as the &drm_gem_object containing the root page table, + * but it can also be a 'dummy' object, which can be allocated with + * drm_gpuvm_resv_object_alloc(). */ /** @@ -652,11 +661,49 @@ drm_gpuvm_range_valid(struct drm_gpuvm *gpuvm, !drm_gpuvm_in_kernel_node(gpuvm, addr, range); } +static void +drm_gpuvm_gem_object_free(struct drm_gem_object *obj) +{ + drm_gem_object_release(obj); + kfree(obj); +} + +static const struct drm_gem_object_funcs drm_gpuvm_object_funcs = { + .free = drm_gpuvm_gem_object_free, +}; + +/** + * drm_gpuvm_resv_object_alloc() - allocate a dummy &drm_gem_object + * @drm: the drivers &drm_device + * + * Allocates a dummy &drm_gem_object which can be passed to drm_gpuvm_init() in + * order to serve as root GEM object providing the &drm_resv shared across + * &drm_gem_objects local to a single GPUVM. + * + * Returns: the &drm_gem_object on success, NULL on failure + */ +struct drm_gem_object * +drm_gpuvm_resv_object_alloc(struct drm_device *drm) +{ + struct drm_gem_object *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) + return NULL; + + obj->funcs = &drm_gpuvm_object_funcs; + drm_gem_private_object_init(drm, obj, 0); + + return obj; +} +EXPORT_SYMBOL_GPL(drm_gpuvm_resv_object_alloc); + /** * drm_gpuvm_init() - initialize a &drm_gpuvm * @gpuvm: pointer to the &drm_gpuvm to initialize * @name: the name of the GPU VA space * @drm: the &drm_device this VM resides in + * @r_obj: the resv &drm_gem_object providing the GPUVM's common &dma_resv * @start_offset: the start offset of the GPU VA space * @range: the size of the GPU VA space * @reserve_offset: the start of the kernel reserved GPU VA area @@ -671,6 +718,7 @@ drm_gpuvm_range_valid(struct drm_gpuvm *gpuvm, void drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name, struct drm_device *drm, + struct drm_gem_object *r_obj, u64 start_offset, u64 range, u64 reserve_offset, u64 reserve_range, const struct drm_gpuvm_ops *ops) @@ -681,6 +729,9 @@ drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name, gpuvm->name = name ? name : "unknown"; gpuvm->ops = ops; gpuvm->drm = drm; + gpuvm->r_obj = r_obj; + + drm_gem_object_get(r_obj); drm_gpuvm_check_overflow(gpuvm, start_offset, range); gpuvm->mm_start = start_offset; @@ -715,6 +766,8 @@ drm_gpuvm_destroy(struct drm_gpuvm *gpuvm) drm_WARN(gpuvm->drm, !RB_EMPTY_ROOT(&gpuvm->rb.tree.rb_root), "GPUVA tree is not empty, potentially leaking memory.\n"); + + drm_gem_object_put(gpuvm->r_obj); } EXPORT_SYMBOL_GPL(drm_gpuvm_destroy); diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index aaf5d28bd587..b4e7d662961a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1809,8 +1809,9 @@ nouveau_uvmm_init(struct nouveau_uvmm *uvmm, struct nouveau_cli *cli, u64 kernel_managed_addr, u64 kernel_managed_size) { struct drm_device *drm = cli->drm->dev; - int ret; + struct drm_gem_object *r_obj; u64 kernel_managed_end = kernel_managed_addr + kernel_managed_size; + int ret; mutex_init(&uvmm->mutex); dma_resv_init(&uvmm->resv); @@ -1834,14 +1835,22 @@ nouveau_uvmm_init(struct nouveau_uvmm *uvmm, struct nouveau_cli *cli, goto out_unlock; } + r_obj = drm_gpuvm_resv_object_alloc(drm); + if (!r_obj) { + ret = -ENOMEM; + goto out_unlock; + } + uvmm->kernel_managed_addr = kernel_managed_addr; uvmm->kernel_managed_size = kernel_managed_size; - drm_gpuvm_init(&uvmm->base, cli->name, drm, + drm_gpuvm_init(&uvmm->base, cli->name, drm, r_obj, NOUVEAU_VA_SPACE_START, NOUVEAU_VA_SPACE_END, kernel_managed_addr, kernel_managed_size, NULL); + /* GPUVM takes care from here on. */ + drm_gem_object_put(r_obj); ret = nvif_vmm_ctor(&cli->mmu, "uvmm", cli->vmm.vmm.object.oclass, RAW, diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h index baa1a96c038c..54dc195a68ea 100644 --- a/include/drm/drm_gpuvm.h +++ b/include/drm/drm_gpuvm.h @@ -244,10 +244,16 @@ struct drm_gpuvm { * @ops: &drm_gpuvm_ops providing the split/merge steps to drivers */ const struct drm_gpuvm_ops *ops; + + /** + * @r_obj: Resv GEM object; representing the GPUVM's common &dma_resv. + */ + struct drm_gem_object *r_obj; }; void drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name, struct drm_device *drm, + struct drm_gem_object *r_obj, u64 start_offset, u64 range, u64 reserve_offset, u64 reserve_range, const struct drm_gpuvm_ops *ops); @@ -255,6 +261,33 @@ void drm_gpuvm_destroy(struct drm_gpuvm *gpuvm); bool drm_gpuvm_interval_empty(struct drm_gpuvm *gpuvm, u64 addr, u64 range); +struct drm_gem_object * +drm_gpuvm_resv_object_alloc(struct drm_device *drm); + +/** + * drm_gpuvm_resv() - returns the &drm_gpuvm's &dma_resv + * @gpuvm__: the &drm_gpuvm + * + * Returns: a pointer to the &drm_gpuvm's shared &dma_resv + */ +#define drm_gpuvm_resv(gpuvm__) ((gpuvm__)->r_obj->resv) + +/** + * drm_gpuvm_resv_obj() - returns the &drm_gem_object holding the &drm_gpuvm's + * &dma_resv + * @gpuvm__: the &drm_gpuvm + * + * Returns: a pointer to the &drm_gem_object holding the &drm_gpuvm's shared + * &dma_resv + */ +#define drm_gpuvm_resv_obj(gpuvm__) ((gpuvm__)->r_obj) + +#define drm_gpuvm_resv_held(gpuvm__) \ + dma_resv_held(drm_gpuvm_resv(gpuvm__)) + +#define drm_gpuvm_resv_assert_held(gpuvm__) \ + dma_resv_assert_held(drm_gpuvm_resv(gpuvm__)) + static inline struct drm_gpuva * __drm_gpuva_next(struct drm_gpuva *va) { -- 2.41.0