linux-kernel - [PATCH 2/5] drm/nouveau/uvmm: Allow larger pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251006191329.277485-3-mohamedahmedegypt2001@gmail.com>
Date: Mon,  6 Oct 2025 22:13:25 +0300
From: Mohamed Ahmed <mohamedahmedegypt2001@...il.com>
To: linux-kernel@...r.kernel.org
Cc: dri-devel@...ts.freedesktop.org,
	Mary Guillemard <mary@...y.zone>,
	Faith Ekstrand <faith.ekstrand@...labora.com>,
	Mohamed Ahmed <mohamedahmedegypt2001@...il.com>,
	Lyude Paul <lyude@...hat.com>,
	Danilo Krummrich <dakr@...nel.org>,
	Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
	Maxime Ripard <mripard@...nel.org>,
	Thomas Zimmermann <tzimmermann@...e.de>,
	David Airlie <airlied@...il.com>,
	Simona Vetter <simona@...ll.ch>,
	nouveau@...ts.freedesktop.org
Subject: [PATCH 2/5] drm/nouveau/uvmm: Allow larger pages

From: Mary Guillemard <mary@...y.zone>

Now that everything in UVMM knows about the variable page shift, we can
select larger values.

The proposed approach rely on nouveau_bo::page unless it would cause
alignment issues (in which case we fall back to searching an appropriate
shift)

Co-developed-by: Mohamed Ahmed <mohamedahmedegypt2001@...il.com>
Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001@...il.com>
Signed-off-by: Mary Guillemard <mary@...y.zone>
---
 drivers/gpu/drm/nouveau/nouveau_uvmm.c | 55 +++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index a92c729600d6..c336a121e320 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -454,6 +454,56 @@ op_unmap_prepare_unwind(struct drm_gpuva *va)
 	drm_gpuva_insert(va->vm, va);
 }
 
+static bool
+op_map_aligned_to_page_shift(const struct drm_gpuva_op_map *op, u8 page_shift)
+{
+	u64 page_size = 1ULL << page_shift;
+
+	return op->va.addr % page_size == 0 && op->va.range % page_size == 0 &&
+		   op->gem.offset % page_size == 0;
+}
+
+static u8
+select_page_shift(struct nouveau_uvmm *uvmm, struct drm_gpuva_op_map *op)
+{
+	struct nouveau_bo *nvbo = nouveau_gem_object(op->gem.obj);
+
+	if (nvbo) {
+		/* If the BO preferred page shift already fits, use it. */
+		if (op_map_aligned_to_page_shift(op, nvbo->page))
+			return nvbo->page;
+
+		struct nouveau_mem *mem = nouveau_mem(nvbo->bo.resource);
+		struct nvif_vmm *vmm = &uvmm->vmm.vmm;
+		int i;
+
+		/* Otherwise let's find a granuality that will fit. */
+		for (i = 0; i < vmm->page_nr; i++) {
+			/* Ignore anything that is bigger or identical to the BO preference. */
+			if (vmm->page[i].shift >= nvbo->page)
+				continue;
+
+			/* Skip incompatible domains. */
+			if ((mem->mem.type & NVIF_MEM_VRAM) && !vmm->page[i].vram)
+				continue;
+			if ((mem->mem.type & NVIF_MEM_HOST) &&
+			    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
+				continue;
+
+			/* If it fits, return the proposed shift. */
+			if (op_map_aligned_to_page_shift(op, vmm->page[i].shift))
+				return vmm->page[i].shift;
+		}
+
+		/* If we get here then nothing can reconcile the requirements. This should never
+		 * happen.
+		 */
+		WARN_ON(1);
+	}
+
+	return PAGE_SHIFT;
+}
+
 static void
 nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
 			       struct nouveau_uvma_prealloc *new,
@@ -506,7 +556,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
 			if (vmm_get_range)
 				nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
 						     vmm_get_range,
-						     PAGE_SHIFT);
+						     select_page_shift(uvmm, &op->map));
 			break;
 		}
 		case DRM_GPUVA_OP_REMAP: {
@@ -636,7 +686,8 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
 		case DRM_GPUVA_OP_MAP: {
 			u64 vmm_get_range = vmm_get_end - vmm_get_start;
 
-			ret = op_map_prepare(uvmm, &new->map, &op->map, args, PAGE_SHIFT);
+			ret = op_map_prepare(uvmm, &new->map, &op->map, args,
+					     select_page_shift(uvmm, &op->map));
 			if (ret)
 				goto unwind;
 
-- 
2.51.0