1 files changed, 85 insertions, 17 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 79eefdfd08a2..f10809115c56 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -107,34 +107,34 @@ nouveau_uvmm_vmm_sparse_unref(struct nouveau_uvmm *uvmm,
 
 static int
 nouveau_uvmm_vmm_get(struct nouveau_uvmm *uvmm,
-		     u64 addr, u64 range)
+		     u64 addr, u64 range, u8 page_shift)
 {
 	struct nvif_vmm *vmm = &uvmm->vmm.vmm;
 
-	return nvif_vmm_raw_get(vmm, addr, range, PAGE_SHIFT);
+	return nvif_vmm_raw_get(vmm, addr, range, page_shift);
 }
 
 static int
 nouveau_uvmm_vmm_put(struct nouveau_uvmm *uvmm,
-		     u64 addr, u64 range)
+		     u64 addr, u64 range, u8 page_shift)
 {
 	struct nvif_vmm *vmm = &uvmm->vmm.vmm;
 
-	return nvif_vmm_raw_put(vmm, addr, range, PAGE_SHIFT);
+	return nvif_vmm_raw_put(vmm, addr, range, page_shift);
 }
 
 static int
 nouveau_uvmm_vmm_unmap(struct nouveau_uvmm *uvmm,
-		       u64 addr, u64 range, bool sparse)
+		       u64 addr, u64 range, u8 page_shift, bool sparse)
 {
 	struct nvif_vmm *vmm = &uvmm->vmm.vmm;
 
-	return nvif_vmm_raw_unmap(vmm, addr, range, PAGE_SHIFT, sparse);
+	return nvif_vmm_raw_unmap(vmm, addr, range, page_shift, sparse);
 }
 
 static int
 nouveau_uvmm_vmm_map(struct nouveau_uvmm *uvmm,
-		     u64 addr, u64 range,
+		     u64 addr, u64 range, u8 page_shift,
 		     u64 bo_offset, u8 kind,
 		     struct nouveau_mem *mem)
 {
@@ -163,7 +163,7 @@ nouveau_uvmm_vmm_map(struct nouveau_uvmm *uvmm,
 		return -ENOSYS;
 	}
 
-	return nvif_vmm_raw_map(vmm, addr, range, PAGE_SHIFT,
+	return nvif_vmm_raw_map(vmm, addr, range, page_shift,
 				&args, argc,
 				&mem->mem, bo_offset);
 }
@@ -182,8 +182,9 @@ nouveau_uvma_vmm_put(struct nouveau_uvma *uvma)
 {
 	u64 addr = uvma->va.va.addr;
 	u64 range = uvma->va.va.range;
+	u8 page_shift = uvma->page_shift;
 
-	return nouveau_uvmm_vmm_put(to_uvmm(uvma), addr, range);
+	return nouveau_uvmm_vmm_put(to_uvmm(uvma), addr, range, page_shift);
 }
 
 static int
@@ -193,9 +194,11 @@ nouveau_uvma_map(struct nouveau_uvma *uvma,
 	u64 addr = uvma->va.va.addr;
 	u64 offset = uvma->va.gem.offset;
 	u64 range = uvma->va.va.range;
+	u8 page_shift = uvma->page_shift;
 
 	return nouveau_uvmm_vmm_map(to_uvmm(uvma), addr, range,
-				    offset, uvma->kind, mem);
+				    page_shift, offset, uvma->kind,
+				    mem);
 }
 
 static int
@@ -203,12 +206,13 @@ nouveau_uvma_unmap(struct nouveau_uvma *uvma)
 {
 	u64 addr = uvma->va.va.addr;
 	u64 range = uvma->va.va.range;
+	u8 page_shift = uvma->page_shift;
 	bool sparse = !!uvma->region;
 
 	if (drm_gpuva_invalidated(&uvma->va))
 		return 0;
 
-	return nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, sparse);
+	return nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, page_shift, sparse);
 }
 
 static int
@@ -450,6 +454,62 @@ 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 non_page_bits = (1ULL << page_shift) - 1;
+
+	return (op->va.addr & non_page_bits) == 0 &&
+	       (op->va.range & non_page_bits) == 0 &&
+	       (op->gem.offset & non_page_bits) == 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);
+
+	/* nouveau_bo_fixup_align() guarantees that the page size will be aligned
+	 * for most cases, but it can't handle cases where userspace allocates with
+	 * a size and then binds with a smaller granularity. So in order to avoid
+	 * breaking old userspace, we need to ensure that the VA is actually
+	 * aligned before using it, and if it isn't, then we downgrade to the first
+	 * granularity that will fit, which is optimal from a correctness and
+	 * performance perspective.
+	 */
+	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;
+
+	/* If the given granularity doesn't fit, let's find one 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.
+	 */
+	drm_WARN_ONCE(op->gem.obj->dev, 1, "Could not find an appropriate page size.\n");
+
+	return PAGE_SHIFT;
+}
+
 static void
 nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
 			       struct nouveau_uvma_prealloc *new,
@@ -501,7 +561,8 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
 
 			if (vmm_get_range)
 				nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
-						     vmm_get_range);
+						     vmm_get_range,
+						     select_page_shift(uvmm, &op->map));
 			break;
 		}
 		case DRM_GPUVA_OP_REMAP: {
@@ -528,6 +589,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
 			u64 ustart = va->va.addr;
 			u64 urange = va->va.range;
 			u64 uend = ustart + urange;
+			u8 page_shift = uvma_from_va(va)->page_shift;
 
 			/* Nothing to do for mappings we merge with. */
 			if (uend == vmm_get_start ||
@@ -538,7 +600,8 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
 				u64 vmm_get_range = ustart - vmm_get_start;
 
 				nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
-						     vmm_get_range);
+						     vmm_get_range,
+						     page_shift);
 			}
 			vmm_get_start = uend;
 			break;
@@ -592,6 +655,7 @@ op_map_prepare(struct nouveau_uvmm *uvmm,
 
 	uvma->region = args->region;
 	uvma->kind = args->kind;
+	uvma->page_shift = select_page_shift(uvmm, op);
 
 	drm_gpuva_map(&uvmm->base, &uvma->va, op);
 
@@ -633,7 +697,8 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
 
 			if (vmm_get_range) {
 				ret = nouveau_uvmm_vmm_get(uvmm, vmm_get_start,
-							   vmm_get_range);
+							   vmm_get_range,
+							   new->map->page_shift);
 				if (ret) {
 					op_map_prepare_unwind(new->map);
 					goto unwind;
@@ -689,6 +754,7 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
 			u64 ustart = va->va.addr;
 			u64 urange = va->va.range;
 			u64 uend = ustart + urange;
+			u8 page_shift = uvma_from_va(va)->page_shift;
 
 			op_unmap_prepare(u);
 
@@ -704,7 +770,7 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
 				u64 vmm_get_range = ustart - vmm_get_start;
 
 				ret = nouveau_uvmm_vmm_get(uvmm, vmm_get_start,
-							   vmm_get_range);
+							   vmm_get_range, page_shift);
 				if (ret) {
 					op_unmap_prepare_unwind(va);
 					goto unwind;
@@ -799,10 +865,11 @@ op_unmap_range(struct drm_gpuva_op_unmap *u,
 	       u64 addr, u64 range)
 {
 	struct nouveau_uvma *uvma = uvma_from_va(u->va);
+	u8 page_shift = uvma->page_shift;
 	bool sparse = !!uvma->region;
 
 	if (!drm_gpuva_invalidated(u->va))
-		nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, sparse);
+		nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, page_shift, sparse);
 }
 
 static void
@@ -882,6 +949,7 @@ nouveau_uvmm_sm_cleanup(struct nouveau_uvmm *uvmm,
 			struct drm_gpuva_op_map *n = r->next;
 			struct drm_gpuva *va = r->unmap->va;
 			struct nouveau_uvma *uvma = uvma_from_va(va);
+			u8 page_shift = uvma->page_shift;
 
 			if (unmap) {
 				u64 addr = va->va.addr;
@@ -893,7 +961,7 @@ nouveau_uvmm_sm_cleanup(struct nouveau_uvmm *uvmm,
 				if (n)
 					end = n->va.addr;
 
-				nouveau_uvmm_vmm_put(uvmm, addr, end - addr);
+				nouveau_uvmm_vmm_put(uvmm, addr, end - addr, page_shift);
 			}
 
 			nouveau_uvma_gem_put(uvma);