4 files changed, 234 insertions, 152 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 5df596fb0280..9e07c3f75156 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -145,34 +145,12 @@ static inline uint32_t ttm_bo_type_flags(unsigned type)
 	return 1 << (type);
 }
 
-static void ttm_bo_release_list(struct kref *list_kref)
-{
-	struct ttm_buffer_object *bo =
-	    container_of(list_kref, struct ttm_buffer_object, list_kref);
-	size_t acc_size = bo->acc_size;
-
-	BUG_ON(kref_read(&bo->list_kref));
-	BUG_ON(kref_read(&bo->kref));
-	BUG_ON(bo->mem.mm_node != NULL);
-	BUG_ON(!list_empty(&bo->lru));
-	BUG_ON(!list_empty(&bo->ddestroy));
-	ttm_tt_destroy(bo->ttm);
-	atomic_dec(&ttm_bo_glob.bo_count);
-	dma_fence_put(bo->moving);
-	if (!ttm_bo_uses_embedded_gem_object(bo))
-		dma_resv_fini(&bo->base._resv);
-	bo->destroy(bo);
-	ttm_mem_global_free(&ttm_mem_glob, acc_size);
-}
-
 static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_type_manager *man;
 
-	dma_resv_assert_held(bo->base.resv);
-
 	if (!list_empty(&bo->lru))
 		return;
 
@@ -181,21 +159,14 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 
 	man = &bdev->man[mem->mem_type];
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
-	kref_get(&bo->list_kref);
 
 	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
 	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
 				     TTM_PAGE_FLAG_SWAPPED))) {
 		list_add_tail(&bo->swap, &ttm_bo_glob.swap_lru[bo->priority]);
-		kref_get(&bo->list_kref);
 	}
 }
 
-static void ttm_bo_ref_bug(struct kref *list_kref)
-{
-	BUG();
-}
-
 static void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -203,12 +174,10 @@ static void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 
 	if (!list_empty(&bo->swap)) {
 		list_del_init(&bo->swap);
-		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 		notify = true;
 	}
 	if (!list_empty(&bo->lru)) {
 		list_del_init(&bo->lru);
-		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 		notify = true;
 	}
 
@@ -372,14 +341,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	}
 
 moved:
-	if (bo->evicted) {
-		if (bdev->driver->invalidate_caches) {
-			ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
-			if (ret)
-				pr_err("Can not flush read caches\n");
-		}
-		bo->evicted = false;
-	}
+	bo->evicted = false;
 
 	if (bo->mem.mm_node)
 		bo->offset = (bo->mem.start << PAGE_SHIFT) +
@@ -428,92 +390,49 @@ static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo)
 	BUG_ON(!dma_resv_trylock(&bo->base._resv));
 
 	r = dma_resv_copy_fences(&bo->base._resv, bo->base.resv);
+	dma_resv_unlock(&bo->base._resv);
 	if (r)
-		dma_resv_unlock(&bo->base._resv);
+		return r;
+
+	if (bo->type != ttm_bo_type_sg) {
+		/* This works because the BO is about to be destroyed and nobody
+		 * reference it any more. The only tricky case is the trylock on
+		 * the resv object while holding the lru_lock.
+		 */
+		spin_lock(&ttm_bo_glob.lru_lock);
+		bo->base.resv = &bo->base._resv;
+		spin_unlock(&ttm_bo_glob.lru_lock);
+	}
 
 	return r;
 }
 
 static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo)
 {
+	struct dma_resv *resv = &bo->base._resv;
 	struct dma_resv_list *fobj;
 	struct dma_fence *fence;
 	int i;
 
-	fobj = dma_resv_get_list(&bo->base._resv);
-	fence = dma_resv_get_excl(&bo->base._resv);
+	rcu_read_lock();
+	fobj = rcu_dereference(resv->fence);
+	fence = rcu_dereference(resv->fence_excl);
 	if (fence && !fence->ops->signaled)
 		dma_fence_enable_sw_signaling(fence);
 
 	for (i = 0; fobj && i < fobj->shared_count; ++i) {
-		fence = rcu_dereference_protected(fobj->shared[i],
-					dma_resv_held(bo->base.resv));
+		fence = rcu_dereference(fobj->shared[i]);
 
 		if (!fence->ops->signaled)
 			dma_fence_enable_sw_signaling(fence);
 	}
-}
-
-static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-	int ret;
-
-	ret = ttm_bo_individualize_resv(bo);
-	if (ret) {
-		/* Last resort, if we fail to allocate memory for the
-		 * fences block for the BO to become idle
-		 */
-		dma_resv_wait_timeout_rcu(bo->base.resv, true, false,
-						    30 * HZ);
-		spin_lock(&ttm_bo_glob.lru_lock);
-		goto error;
-	}
-
-	spin_lock(&ttm_bo_glob.lru_lock);
-	ret = dma_resv_trylock(bo->base.resv) ? 0 : -EBUSY;
-	if (!ret) {
-		if (dma_resv_test_signaled_rcu(&bo->base._resv, true)) {
-			ttm_bo_del_from_lru(bo);
-			spin_unlock(&ttm_bo_glob.lru_lock);
-			if (bo->base.resv != &bo->base._resv)
-				dma_resv_unlock(&bo->base._resv);
-
-			ttm_bo_cleanup_memtype_use(bo);
-			dma_resv_unlock(bo->base.resv);
-			return;
-		}
-
-		ttm_bo_flush_all_fences(bo);
-
-		/*
-		 * Make NO_EVICT bos immediately available to
-		 * shrinkers, now that they are queued for
-		 * destruction.
-		 */
-		if (bo->mem.placement & TTM_PL_FLAG_NO_EVICT) {
-			bo->mem.placement &= ~TTM_PL_FLAG_NO_EVICT;
-			ttm_bo_move_to_lru_tail(bo, NULL);
-		}
-
-		dma_resv_unlock(bo->base.resv);
-	}
-	if (bo->base.resv != &bo->base._resv)
-		dma_resv_unlock(&bo->base._resv);
-
-error:
-	kref_get(&bo->list_kref);
-	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
-	spin_unlock(&ttm_bo_glob.lru_lock);
-
-	schedule_delayed_work(&bdev->wq,
-			      ((HZ / 100) < 1) ? 1 : HZ / 100);
+	rcu_read_unlock();
 }
 
 /**
  * function ttm_bo_cleanup_refs
- * If bo idle, remove from delayed- and lru lists, and unref.
- * If not idle, do nothing.
+ * If bo idle, remove from lru lists, and unref.
+ * If not idle, block if possible.
  *
  * Must be called with lru_lock and reservation held, this function
  * will drop the lru lock and optionally the reservation lock before returning.
@@ -527,14 +446,9 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 			       bool interruptible, bool no_wait_gpu,
 			       bool unlock_resv)
 {
-	struct dma_resv *resv;
+	struct dma_resv *resv = &bo->base._resv;
 	int ret;
 
-	if (unlikely(list_empty(&bo->ddestroy)))
-		resv = bo->base.resv;
-	else
-		resv = &bo->base._resv;
-
 	if (dma_resv_test_signaled_rcu(resv, true))
 		ret = 0;
 	else
@@ -547,9 +461,8 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 			dma_resv_unlock(bo->base.resv);
 		spin_unlock(&ttm_bo_glob.lru_lock);
 
-		lret = dma_resv_wait_timeout_rcu(resv, true,
-							   interruptible,
-							   30 * HZ);
+		lret = dma_resv_wait_timeout_rcu(resv, true, interruptible,
+						 30 * HZ);
 
 		if (lret < 0)
 			return lret;
@@ -581,14 +494,14 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 
 	ttm_bo_del_from_lru(bo);
 	list_del_init(&bo->ddestroy);
-	kref_put(&bo->list_kref, ttm_bo_ref_bug);
-
 	spin_unlock(&ttm_bo_glob.lru_lock);
 	ttm_bo_cleanup_memtype_use(bo);
 
 	if (unlock_resv)
 		dma_resv_unlock(bo->base.resv);
 
+	ttm_bo_put(bo);
+
 	return 0;
 }
 
@@ -610,8 +523,9 @@ static bool ttm_bo_delayed_delete(struct ttm_bo_device *bdev, bool remove_all)
 
 		bo = list_first_entry(&bdev->ddestroy, struct ttm_buffer_object,
 				      ddestroy);
-		kref_get(&bo->list_kref);
 		list_move_tail(&bo->ddestroy, &removed);
+		if (!ttm_bo_get_unless_zero(bo))
+			continue;
 
 		if (remove_all || bo->base.resv != &bo->base._resv) {
 			spin_unlock(&glob->lru_lock);
@@ -626,7 +540,7 @@ static bool ttm_bo_delayed_delete(struct ttm_bo_device *bdev, bool remove_all)
 			spin_unlock(&glob->lru_lock);
 		}
 
-		kref_put(&bo->list_kref, ttm_bo_release_list);
+		ttm_bo_put(bo);
 		spin_lock(&glob->lru_lock);
 	}
 	list_splice_tail(&removed, &bdev->ddestroy);
@@ -652,16 +566,69 @@ static void ttm_bo_release(struct kref *kref)
 	    container_of(kref, struct ttm_buffer_object, kref);
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_type_manager *man = &bdev->man[bo->mem.mem_type];
+	size_t acc_size = bo->acc_size;
+	int ret;
 
-	if (bo->bdev->driver->release_notify)
-		bo->bdev->driver->release_notify(bo);
+	if (!bo->deleted) {
+		ret = ttm_bo_individualize_resv(bo);
+		if (ret) {
+			/* Last resort, if we fail to allocate memory for the
+			 * fences block for the BO to become idle
+			 */
+			dma_resv_wait_timeout_rcu(bo->base.resv, true, false,
+						  30 * HZ);
+		}
 
-	drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node);
-	ttm_mem_io_lock(man, false);
-	ttm_mem_io_free_vm(bo);
-	ttm_mem_io_unlock(man);
-	ttm_bo_cleanup_refs_or_queue(bo);
-	kref_put(&bo->list_kref, ttm_bo_release_list);
+		if (bo->bdev->driver->release_notify)
+			bo->bdev->driver->release_notify(bo);
+
+		drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node);
+		ttm_mem_io_lock(man, false);
+		ttm_mem_io_free_vm(bo);
+		ttm_mem_io_unlock(man);
+	}
+
+	if (!dma_resv_test_signaled_rcu(bo->base.resv, true)) {
+		/* The BO is not idle, resurrect it for delayed destroy */
+		ttm_bo_flush_all_fences(bo);
+		bo->deleted = true;
+
+		spin_lock(&ttm_bo_glob.lru_lock);
+
+		/*
+		 * Make NO_EVICT bos immediately available to
+		 * shrinkers, now that they are queued for
+		 * destruction.
+		 */
+		if (bo->mem.placement & TTM_PL_FLAG_NO_EVICT) {
+			bo->mem.placement &= ~TTM_PL_FLAG_NO_EVICT;
+			ttm_bo_del_from_lru(bo);
+			ttm_bo_add_mem_to_lru(bo, &bo->mem);
+		}
+
+		kref_init(&bo->kref);
+		list_add_tail(&bo->ddestroy, &bdev->ddestroy);
+		spin_unlock(&ttm_bo_glob.lru_lock);
+
+		schedule_delayed_work(&bdev->wq,
+				      ((HZ / 100) < 1) ? 1 : HZ / 100);
+		return;
+	}
+
+	spin_lock(&ttm_bo_glob.lru_lock);
+	ttm_bo_del_from_lru(bo);
+	list_del(&bo->ddestroy);
+	spin_unlock(&ttm_bo_glob.lru_lock);
+
+	ttm_bo_cleanup_memtype_use(bo);
+
+	BUG_ON(bo->mem.mm_node != NULL);
+	atomic_dec(&ttm_bo_glob.bo_count);
+	dma_fence_put(bo->moving);
+	if (!ttm_bo_uses_embedded_gem_object(bo))
+		dma_resv_fini(&bo->base._resv);
+	bo->destroy(bo);
+	ttm_mem_global_free(&ttm_mem_glob, acc_size);
 }
 
 void ttm_bo_put(struct ttm_buffer_object *bo)
@@ -764,8 +731,7 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo,
 
 	if (bo->base.resv == ctx->resv) {
 		dma_resv_assert_held(bo->base.resv);
-		if (ctx->flags & TTM_OPT_FLAG_ALLOW_RES_EVICT
-		    || !list_empty(&bo->ddestroy))
+		if (ctx->flags & TTM_OPT_FLAG_ALLOW_RES_EVICT)
 			ret = true;
 		*locked = false;
 		if (busy)
@@ -846,6 +812,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 					dma_resv_unlock(bo->base.resv);
 				continue;
 			}
+			if (!ttm_bo_get_unless_zero(bo)) {
+				if (locked)
+					dma_resv_unlock(bo->base.resv);
+				continue;
+			}
 			break;
 		}
 
@@ -857,21 +828,19 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	}
 
 	if (!bo) {
-		if (busy_bo)
-			kref_get(&busy_bo->list_kref);
+		if (busy_bo && !ttm_bo_get_unless_zero(busy_bo))
+			busy_bo = NULL;
 		spin_unlock(&ttm_bo_glob.lru_lock);
 		ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
 		if (busy_bo)
-			kref_put(&busy_bo->list_kref, ttm_bo_release_list);
+			ttm_bo_put(busy_bo);
 		return ret;
 	}
 
-	kref_get(&bo->list_kref);
-
-	if (!list_empty(&bo->ddestroy)) {
+	if (bo->deleted) {
 		ret = ttm_bo_cleanup_refs(bo, ctx->interruptible,
 					  ctx->no_wait_gpu, locked);
-		kref_put(&bo->list_kref, ttm_bo_release_list);
+		ttm_bo_put(bo);
 		return ret;
 	}
 
@@ -881,7 +850,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	if (locked)
 		ttm_bo_unreserve(bo);
 
-	kref_put(&bo->list_kref, ttm_bo_release_list);
+	ttm_bo_put(bo);
 	return ret;
 }
 
@@ -1226,6 +1195,18 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	uint32_t new_flags;
 
 	dma_resv_assert_held(bo->base.resv);
+
+	/*
+	 * Remove the backing store if no placement is given.
+	 */
+	if (!placement->num_placement && !placement->num_busy_placement) {
+		ret = ttm_bo_pipeline_gutting(bo);
+		if (ret)
+			return ret;
+
+		return ttm_tt_create(bo, false);
+	}
+
 	/*
 	 * Check whether we need to move buffer.
 	 */
@@ -1293,7 +1274,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	bo->destroy = destroy ? destroy : ttm_bo_default_destroy;
 
 	kref_init(&bo->kref);
-	kref_init(&bo->list_kref);
 	INIT_LIST_HEAD(&bo->lru);
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
@@ -1813,11 +1793,18 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
 	spin_lock(&glob->lru_lock);
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
 		list_for_each_entry(bo, &glob->swap_lru[i], swap) {
-			if (ttm_bo_evict_swapout_allowable(bo, ctx, &locked,
-							   NULL)) {
-				ret = 0;
-				break;
+			if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked,
+							    NULL))
+				continue;
+
+			if (!ttm_bo_get_unless_zero(bo)) {
+				if (locked)
+					dma_resv_unlock(bo->base.resv);
+				continue;
 			}
+
+			ret = 0;
+			break;
 		}
 		if (!ret)
 			break;
@@ -1828,11 +1815,9 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
 		return ret;
 	}
 
-	kref_get(&bo->list_kref);
-
-	if (!list_empty(&bo->ddestroy)) {
+	if (bo->deleted) {
 		ret = ttm_bo_cleanup_refs(bo, false, false, locked);
-		kref_put(&bo->list_kref, ttm_bo_release_list);
+		ttm_bo_put(bo);
 		return ret;
 	}
 
@@ -1886,7 +1871,7 @@ out:
 	 */
 	if (locked)
 		dma_resv_unlock(bo->base.resv);
-	kref_put(&bo->list_kref, ttm_bo_release_list);
+	ttm_bo_put(bo);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_swapout);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 953c82a4f573..52d2b71f1588 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -507,11 +507,10 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
 
-	kref_init(&fbo->base.list_kref);
 	kref_init(&fbo->base.kref);
 	fbo->base.destroy = &ttm_transfered_destroy;
 	fbo->base.acc_size = 0;
-	if (bo->base.resv == &bo->base._resv)
+	if (bo->type != ttm_bo_type_sg)
 		fbo->base.base.resv = &fbo->base.base._resv;
 
 	dma_resv_init(&fbo->base.base._resv);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 389128b8c4dd..0ad30b112982 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -59,9 +59,10 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 
 	/*
 	 * If possible, avoid waiting for GPU with mmap_sem
-	 * held.
+	 * held.  We only do this if the fault allows retry and this
+	 * is the first attempt.
 	 */
-	if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+	if (fault_flag_allow_retry_first(vmf->flags)) {
 		ret = VM_FAULT_RETRY;
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_unlock;
@@ -135,7 +136,12 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 	 * for the buffer to become unreserved.
 	 */
 	if (unlikely(!dma_resv_trylock(bo->base.resv))) {
-		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+		/*
+		 * If the fault allows retry and this is the first
+		 * fault attempt, we try to release the mmap_sem
+		 * before waiting
+		 */
+		if (fault_flag_allow_retry_first(vmf->flags)) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
 				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
@@ -156,6 +162,89 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_vm_reserve);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/**
+ * ttm_bo_vm_insert_huge - Insert a pfn for PUD or PMD faults
+ * @vmf: Fault data
+ * @bo: The buffer object
+ * @page_offset: Page offset from bo start
+ * @fault_page_size: The size of the fault in pages.
+ * @pgprot: The page protections.
+ * Does additional checking whether it's possible to insert a PUD or PMD
+ * pfn and performs the insertion.
+ *
+ * Return: VM_FAULT_NOPAGE on successful insertion, VM_FAULT_FALLBACK if
+ * a huge fault was not possible, or on insertion error.
+ */
+static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
+					struct ttm_buffer_object *bo,
+					pgoff_t page_offset,
+					pgoff_t fault_page_size,
+					pgprot_t pgprot)
+{
+	pgoff_t i;
+	vm_fault_t ret;
+	unsigned long pfn;
+	pfn_t pfnt;
+	struct ttm_tt *ttm = bo->ttm;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	/* Fault should not cross bo boundary. */
+	page_offset &= ~(fault_page_size - 1);
+	if (page_offset + fault_page_size > bo->num_pages)
+		goto out_fallback;
+
+	if (bo->mem.bus.is_iomem)
+		pfn = ttm_bo_io_mem_pfn(bo, page_offset);
+	else
+		pfn = page_to_pfn(ttm->pages[page_offset]);
+
+	/* pfn must be fault_page_size aligned. */
+	if ((pfn & (fault_page_size - 1)) != 0)
+		goto out_fallback;
+
+	/* Check that memory is contiguous. */
+	if (!bo->mem.bus.is_iomem) {
+		for (i = 1; i < fault_page_size; ++i) {
+			if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i)
+				goto out_fallback;
+		}
+	} else if (bo->bdev->driver->io_mem_pfn) {
+		for (i = 1; i < fault_page_size; ++i) {
+			if (ttm_bo_io_mem_pfn(bo, page_offset + i) != pfn + i)
+				goto out_fallback;
+		}
+	}
+
+	pfnt = __pfn_to_pfn_t(pfn, PFN_DEV);
+	if (fault_page_size == (HPAGE_PMD_SIZE >> PAGE_SHIFT))
+		ret = vmf_insert_pfn_pmd_prot(vmf, pfnt, pgprot, write);
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	else if (fault_page_size == (HPAGE_PUD_SIZE >> PAGE_SHIFT))
+		ret = vmf_insert_pfn_pud_prot(vmf, pfnt, pgprot, write);
+#endif
+	else
+		WARN_ON_ONCE(ret = VM_FAULT_FALLBACK);
+
+	if (ret != VM_FAULT_NOPAGE)
+		goto out_fallback;
+
+	return VM_FAULT_NOPAGE;
+out_fallback:
+	count_vm_event(THP_FAULT_FALLBACK);
+	return VM_FAULT_FALLBACK;
+}
+#else
+static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
+					struct ttm_buffer_object *bo,
+					pgoff_t page_offset,
+					pgoff_t fault_page_size,
+					pgprot_t pgprot)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif
+
 /**
  * ttm_bo_vm_fault_reserved - TTM fault helper
  * @vmf: The struct vm_fault given as argument to the fault callback
@@ -163,6 +252,7 @@ EXPORT_SYMBOL(ttm_bo_vm_reserve);
  * @num_prefault: Maximum number of prefault pages. The caller may want to
  * specify this based on madvice settings and the size of the GPU object
  * backed by the memory.
+ * @fault_page_size: The size of the fault in pages.
  *
  * This function inserts one or more page table entries pointing to the
  * memory backing the buffer object, and then returns a return code
@@ -176,7 +266,8 @@ EXPORT_SYMBOL(ttm_bo_vm_reserve);
  */
 vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 				    pgprot_t prot,
-				    pgoff_t num_prefault)
+				    pgoff_t num_prefault,
+				    pgoff_t fault_page_size)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
@@ -268,6 +359,13 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		prot = pgprot_decrypted(prot);
 	}
 
+	/* We don't prefault on huge faults. Yet. */
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1) {
+		ret = ttm_bo_vm_insert_huge(vmf, bo, page_offset,
+					    fault_page_size, prot);
+		goto out_io_unlock;
+	}
+
 	/*
 	 * Speculatively prefault a number of pages. Only error on
 	 * first page.
@@ -334,7 +432,7 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		return ret;
 
 	prot = vma->vm_page_prot;
-	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
+	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1);
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
 
@@ -445,7 +543,7 @@ static const struct vm_operations_struct ttm_bo_vm_ops = {
 	.fault = ttm_bo_vm_fault,
 	.open = ttm_bo_vm_open,
 	.close = ttm_bo_vm_close,
-	.access = ttm_bo_vm_access
+	.access = ttm_bo_vm_access,
 };
 
 static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev,
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index bf876faea592..faefaaef7909 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -604,7 +604,7 @@ static struct dma_pool *ttm_dma_pool_init(struct device *dev, gfp_t flags,
 	p = pool->name;
 	for (i = 0; i < ARRAY_SIZE(t); i++) {
 		if (type & t[i]) {
-			p += snprintf(p, sizeof(pool->name) - (p - pool->name),
+			p += scnprintf(p, sizeof(pool->name) - (p - pool->name),
 				      "%s", n[i]);
 		}
 	}