17 files changed, 248 insertions, 182 deletions

diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
index 6c77550c51af..d468f8322072 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
@@ -251,7 +251,7 @@ static void ttm_bo_unreserve_basic(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -290,7 +290,7 @@ static void ttm_bo_unreserve_pinned(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -342,7 +342,7 @@ static void ttm_bo_unreserve_bulk(struct kunit *test)
 	resv = kunit_kzalloc(test, sizeof(*resv), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, resv);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -379,7 +379,7 @@ static void ttm_bo_unreserve_bulk(struct kunit *test)
 	dma_resv_fini(resv);
 }
 
-static void ttm_bo_put_basic(struct kunit *test)
+static void ttm_bo_fini_basic(struct kunit *test)
 {
 	struct ttm_test_devices *priv = test->priv;
 	struct ttm_buffer_object *bo;
@@ -394,7 +394,7 @@ static void ttm_bo_put_basic(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -410,7 +410,7 @@ static void ttm_bo_put_basic(struct kunit *test)
 	dma_resv_unlock(bo->base.resv);
 	KUNIT_EXPECT_EQ(test, err, 0);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static const char *mock_name(struct dma_fence *f)
@@ -423,7 +423,7 @@ static const struct dma_fence_ops mock_fence_ops = {
 	.get_timeline_name = mock_name,
 };
 
-static void ttm_bo_put_shared_resv(struct kunit *test)
+static void ttm_bo_fini_shared_resv(struct kunit *test)
 {
 	struct ttm_test_devices *priv = test->priv;
 	struct ttm_buffer_object *bo;
@@ -437,7 +437,7 @@ static void ttm_bo_put_shared_resv(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -463,7 +463,7 @@ static void ttm_bo_put_shared_resv(struct kunit *test)
 	bo->type = ttm_bo_type_device;
 	bo->base.resv = external_resv;
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static void ttm_bo_pin_basic(struct kunit *test)
@@ -477,7 +477,7 @@ static void ttm_bo_pin_basic(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -512,7 +512,7 @@ static void ttm_bo_pin_unpin_resource(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -563,7 +563,7 @@ static void ttm_bo_multiple_pin_one_unpin(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 	priv->ttm_dev = ttm_dev;
 
@@ -616,8 +616,8 @@ static struct kunit_case ttm_bo_test_cases[] = {
 	KUNIT_CASE(ttm_bo_unreserve_basic),
 	KUNIT_CASE(ttm_bo_unreserve_pinned),
 	KUNIT_CASE(ttm_bo_unreserve_bulk),
-	KUNIT_CASE(ttm_bo_put_basic),
-	KUNIT_CASE(ttm_bo_put_shared_resv),
+	KUNIT_CASE(ttm_bo_fini_basic),
+	KUNIT_CASE(ttm_bo_fini_shared_resv),
 	KUNIT_CASE(ttm_bo_pin_basic),
 	KUNIT_CASE(ttm_bo_pin_unpin_resource),
 	KUNIT_CASE(ttm_bo_multiple_pin_one_unpin),
diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
index 1bcc67977f48..2eda87882e65 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
@@ -144,7 +144,7 @@ static void ttm_bo_init_reserved_sys_man(struct kunit *test)
 				  drm_mm_node_allocated(&bo->base.vma_node.vm_node));
 
 	ttm_resource_free(bo, &bo->resource);
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static void ttm_bo_init_reserved_mock_man(struct kunit *test)
@@ -186,7 +186,7 @@ static void ttm_bo_init_reserved_mock_man(struct kunit *test)
 				  drm_mm_node_allocated(&bo->base.vma_node.vm_node));
 
 	ttm_resource_free(bo, &bo->resource);
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 }
 
@@ -221,7 +221,7 @@ static void ttm_bo_init_reserved_resv(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, bo->base.resv, &resv);
 
 	ttm_resource_free(bo, &bo->resource);
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static void ttm_bo_validate_basic(struct kunit *test)
@@ -265,7 +265,7 @@ static void ttm_bo_validate_basic(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, bo->resource->placement,
 			DRM_BUDDY_TOPDOWN_ALLOCATION);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 	ttm_mock_manager_fini(priv->ttm_dev, snd_mem);
 }
 
@@ -292,7 +292,7 @@ static void ttm_bo_validate_invalid_placement(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, err, -ENOMEM);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static void ttm_bo_validate_failed_alloc(struct kunit *test)
@@ -321,7 +321,7 @@ static void ttm_bo_validate_failed_alloc(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, err, -ENOMEM);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 	ttm_bad_manager_fini(priv->ttm_dev, mem_type);
 }
 
@@ -353,7 +353,7 @@ static void ttm_bo_validate_pinned(struct kunit *test)
 	ttm_bo_unpin(bo);
 	dma_resv_unlock(bo->base.resv);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static const struct ttm_bo_validate_test_case ttm_mem_type_cases[] = {
@@ -403,7 +403,7 @@ static void ttm_bo_validate_same_placement(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, err, 0);
 	KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, 0);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 
 	if (params->mem_type != TTM_PL_SYSTEM)
 		ttm_mock_manager_fini(priv->ttm_dev, params->mem_type);
@@ -452,7 +452,7 @@ static void ttm_bo_validate_busy_placement(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, bo->resource->mem_type, snd_mem);
 	KUNIT_ASSERT_TRUE(test, list_is_singular(&man->lru[bo->priority]));
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 	ttm_bad_manager_fini(priv->ttm_dev, fst_mem);
 	ttm_mock_manager_fini(priv->ttm_dev, snd_mem);
 }
@@ -495,7 +495,7 @@ static void ttm_bo_validate_multihop(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, size * 2);
 	KUNIT_EXPECT_EQ(test, bo->resource->mem_type, final_mem);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 
 	ttm_mock_manager_fini(priv->ttm_dev, fst_mem);
 	ttm_mock_manager_fini(priv->ttm_dev, tmp_mem);
@@ -567,7 +567,7 @@ static void ttm_bo_validate_no_placement_signaled(struct kunit *test)
 		KUNIT_ASSERT_TRUE(test, flags & TTM_TT_FLAG_ZERO_ALLOC);
 	}
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static int threaded_dma_resv_signal(void *arg)
@@ -635,7 +635,7 @@ static void ttm_bo_validate_no_placement_not_signaled(struct kunit *test)
 	/* Make sure we have an idle object at this point */
 	dma_resv_wait_timeout(bo->base.resv, usage, false, MAX_SCHEDULE_TIMEOUT);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 }
 
 static void ttm_bo_validate_move_fence_signaled(struct kunit *test)
@@ -652,7 +652,7 @@ static void ttm_bo_validate_move_fence_signaled(struct kunit *test)
 	int err;
 
 	man = ttm_manager_type(priv->ttm_dev, mem_type);
-	man->move = dma_fence_get_stub();
+	man->eviction_fences[0] = dma_fence_get_stub();
 
 	bo = ttm_bo_kunit_init(test, test->priv, size, NULL);
 	bo->type = bo_type;
@@ -668,8 +668,8 @@ static void ttm_bo_validate_move_fence_signaled(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, bo->resource->mem_type, mem_type);
 	KUNIT_EXPECT_EQ(test, ctx.bytes_moved, size);
 
-	ttm_bo_put(bo);
-	dma_fence_put(man->move);
+	ttm_bo_fini(bo);
+	dma_fence_put(man->eviction_fences[0]);
 }
 
 static const struct ttm_bo_validate_test_case ttm_bo_validate_wait_cases[] = {
@@ -733,9 +733,9 @@ static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test)
 
 	spin_lock_init(&fence_lock);
 	man = ttm_manager_type(priv->ttm_dev, fst_mem);
-	man->move = alloc_mock_fence(test);
+	man->eviction_fences[0] = alloc_mock_fence(test);
 
-	task = kthread_create(threaded_fence_signal, man->move, "move-fence-signal");
+	task = kthread_create(threaded_fence_signal, man->eviction_fences[0], "move-fence-signal");
 	if (IS_ERR(task))
 		KUNIT_FAIL(test, "Couldn't create move fence signal task\n");
 
@@ -743,7 +743,8 @@ static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test)
 	err = ttm_bo_validate(bo, placement_val, &ctx_val);
 	dma_resv_unlock(bo->base.resv);
 
-	dma_fence_wait_timeout(man->move, false, MAX_SCHEDULE_TIMEOUT);
+	dma_fence_wait_timeout(man->eviction_fences[0], false, MAX_SCHEDULE_TIMEOUT);
+	man->eviction_fences[0] = NULL;
 
 	KUNIT_EXPECT_EQ(test, err, 0);
 	KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, size);
@@ -753,7 +754,7 @@ static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test)
 	else
 		KUNIT_EXPECT_EQ(test, bo->resource->mem_type, fst_mem);
 
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo);
 	ttm_mock_manager_fini(priv->ttm_dev, fst_mem);
 	ttm_mock_manager_fini(priv->ttm_dev, snd_mem);
 }
@@ -807,8 +808,8 @@ static void ttm_bo_validate_happy_evict(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, bos[1].resource->mem_type, mem_type);
 
 	for (i = 0; i < bo_no; i++)
-		ttm_bo_put(&bos[i]);
-	ttm_bo_put(bo_val);
+		ttm_bo_fini(&bos[i]);
+	ttm_bo_fini(bo_val);
 
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 	ttm_mock_manager_fini(priv->ttm_dev, mem_multihop);
@@ -852,12 +853,12 @@ static void ttm_bo_validate_all_pinned_evict(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, err, -ENOMEM);
 
-	ttm_bo_put(bo_small);
+	ttm_bo_fini(bo_small);
 
 	ttm_bo_reserve(bo_big, false, false, NULL);
 	ttm_bo_unpin(bo_big);
 	dma_resv_unlock(bo_big->base.resv);
-	ttm_bo_put(bo_big);
+	ttm_bo_fini(bo_big);
 
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 	ttm_mock_manager_fini(priv->ttm_dev, mem_multihop);
@@ -916,13 +917,13 @@ static void ttm_bo_validate_allowed_only_evict(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, bo_evictable->resource->mem_type, mem_type_evict);
 	KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, size * 2 + BO_SIZE);
 
-	ttm_bo_put(bo);
-	ttm_bo_put(bo_evictable);
+	ttm_bo_fini(bo);
+	ttm_bo_fini(bo_evictable);
 
 	ttm_bo_reserve(bo_pinned, false, false, NULL);
 	ttm_bo_unpin(bo_pinned);
 	dma_resv_unlock(bo_pinned->base.resv);
-	ttm_bo_put(bo_pinned);
+	ttm_bo_fini(bo_pinned);
 
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 	ttm_mock_manager_fini(priv->ttm_dev, mem_multihop);
@@ -973,8 +974,8 @@ static void ttm_bo_validate_deleted_evict(struct kunit *test)
 	KUNIT_EXPECT_NULL(test, bo_big->ttm);
 	KUNIT_EXPECT_NULL(test, bo_big->resource);
 
-	ttm_bo_put(bo_small);
-	ttm_bo_put(bo_big);
+	ttm_bo_fini(bo_small);
+	ttm_bo_fini(bo_big);
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 }
 
@@ -995,7 +996,7 @@ static void ttm_bo_validate_busy_domain_evict(struct kunit *test)
 	 */
 	ttm_device_fini(priv->ttm_dev);
 
-	err = ttm_device_kunit_init_bad_evict(test->priv, priv->ttm_dev, false, false);
+	err = ttm_device_kunit_init_bad_evict(test->priv, priv->ttm_dev);
 	KUNIT_ASSERT_EQ(test, err, 0);
 
 	ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE);
@@ -1025,8 +1026,8 @@ static void ttm_bo_validate_busy_domain_evict(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, bo_init->resource->mem_type, mem_type);
 	KUNIT_EXPECT_NULL(test, bo_val->resource);
 
-	ttm_bo_put(bo_init);
-	ttm_bo_put(bo_val);
+	ttm_bo_fini(bo_init);
+	ttm_bo_fini(bo_val);
 
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 	ttm_bad_manager_fini(priv->ttm_dev, mem_type_evict);
@@ -1070,8 +1071,8 @@ static void ttm_bo_validate_evict_gutting(struct kunit *test)
 	KUNIT_ASSERT_NULL(test, bo_evict->resource);
 	KUNIT_ASSERT_TRUE(test, bo_evict->ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC);
 
-	ttm_bo_put(bo_evict);
-	ttm_bo_put(bo);
+	ttm_bo_fini(bo_evict);
+	ttm_bo_fini(bo);
 
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 }
@@ -1128,9 +1129,9 @@ static void ttm_bo_validate_recrusive_evict(struct kunit *test)
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
 	ttm_mock_manager_fini(priv->ttm_dev, mem_type_evict);
 
-	ttm_bo_put(bo_val);
-	ttm_bo_put(bo_tt);
-	ttm_bo_put(bo_mock);
+	ttm_bo_fini(bo_val);
+	ttm_bo_fini(bo_tt);
+	ttm_bo_fini(bo_mock);
 }
 
 static struct kunit_case ttm_bo_validate_test_cases[] = {
diff --git a/drivers/gpu/drm/ttm/tests/ttm_device_test.c b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
index 1621903818e5..2d55ad34fe48 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_device_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
@@ -7,11 +7,11 @@
 #include <drm/ttm/ttm_placement.h>
 
 #include "ttm_kunit_helpers.h"
+#include "../ttm_pool_internal.h"
 
 struct ttm_device_test_case {
 	const char *description;
-	bool use_dma_alloc;
-	bool use_dma32;
+	unsigned int alloc_flags;
 	bool pools_init_expected;
 };
 
@@ -25,7 +25,7 @@ static void ttm_device_init_basic(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 
 	KUNIT_EXPECT_PTR_EQ(test, ttm_dev->funcs, &ttm_dev_funcs);
@@ -55,7 +55,7 @@ static void ttm_device_init_multiple(struct kunit *test)
 	KUNIT_ASSERT_NOT_NULL(test, ttm_devs);
 
 	for (i = 0; i < num_dev; i++) {
-		err = ttm_device_kunit_init(priv, &ttm_devs[i], false, false);
+		err = ttm_device_kunit_init(priv, &ttm_devs[i], 0);
 		KUNIT_ASSERT_EQ(test, err, 0);
 
 		KUNIT_EXPECT_PTR_EQ(test, ttm_devs[i].dev_mapping,
@@ -81,7 +81,7 @@ static void ttm_device_fini_basic(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 
 	man = ttm_manager_type(ttm_dev, TTM_PL_SYSTEM);
@@ -109,7 +109,7 @@ static void ttm_device_init_no_vma_man(struct kunit *test)
 	vma_man = drm->vma_offset_manager;
 	drm->vma_offset_manager = NULL;
 
-	err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+	err = ttm_device_kunit_init(priv, ttm_dev, 0);
 	KUNIT_EXPECT_EQ(test, err, -EINVAL);
 
 	/* Bring the manager back for a graceful cleanup */
@@ -119,26 +119,22 @@ static void ttm_device_init_no_vma_man(struct kunit *test)
 static const struct ttm_device_test_case ttm_device_cases[] = {
 	{
 		.description = "No DMA allocations, no DMA32 required",
-		.use_dma_alloc = false,
-		.use_dma32 = false,
 		.pools_init_expected = false,
 	},
 	{
 		.description = "DMA allocations, DMA32 required",
-		.use_dma_alloc = true,
-		.use_dma32 = true,
+		.alloc_flags = TTM_ALLOCATION_POOL_USE_DMA_ALLOC |
+			       TTM_ALLOCATION_POOL_USE_DMA32,
 		.pools_init_expected = true,
 	},
 	{
 		.description = "No DMA allocations, DMA32 required",
-		.use_dma_alloc = false,
-		.use_dma32 = true,
+		.alloc_flags = TTM_ALLOCATION_POOL_USE_DMA32,
 		.pools_init_expected = false,
 	},
 	{
 		.description = "DMA allocations, no DMA32 required",
-		.use_dma_alloc = true,
-		.use_dma32 = false,
+		.alloc_flags = TTM_ALLOCATION_POOL_USE_DMA_ALLOC,
 		.pools_init_expected = true,
 	},
 };
@@ -162,16 +158,13 @@ static void ttm_device_init_pools(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(priv, ttm_dev,
-				    params->use_dma_alloc,
-				    params->use_dma32);
+	err = ttm_device_kunit_init(priv, ttm_dev, params->alloc_flags);
 	KUNIT_ASSERT_EQ(test, err, 0);
 
 	pool = &ttm_dev->pool;
 	KUNIT_ASSERT_NOT_NULL(test, pool);
 	KUNIT_EXPECT_PTR_EQ(test, pool->dev, priv->dev);
-	KUNIT_EXPECT_EQ(test, pool->use_dma_alloc, params->use_dma_alloc);
-	KUNIT_EXPECT_EQ(test, pool->use_dma32, params->use_dma32);
+	KUNIT_EXPECT_EQ(test, pool->alloc_flags, params->alloc_flags);
 
 	if (params->pools_init_expected) {
 		for (int i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
@@ -181,7 +174,7 @@ static void ttm_device_init_pools(struct kunit *test)
 				KUNIT_EXPECT_EQ(test, pt.caching, i);
 				KUNIT_EXPECT_EQ(test, pt.order, j);
 
-				if (params->use_dma_alloc)
+				if (ttm_pool_uses_dma_alloc(pool))
 					KUNIT_ASSERT_FALSE(test,
 							   list_empty(&pt.pages));
 			}
diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
index 7aaf0d1395ff..7b533e4e1e04 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
@@ -117,8 +117,7 @@ static void bad_evict_flags(struct ttm_buffer_object *bo,
 
 static int ttm_device_kunit_init_with_funcs(struct ttm_test_devices *priv,
 					    struct ttm_device *ttm,
-					    bool use_dma_alloc,
-					    bool use_dma32,
+					    unsigned int alloc_flags,
 					    struct ttm_device_funcs *funcs)
 {
 	struct drm_device *drm = priv->drm;
@@ -127,7 +126,7 @@ static int ttm_device_kunit_init_with_funcs(struct ttm_test_devices *priv,
 	err = ttm_device_init(ttm, funcs, drm->dev,
 			      drm->anon_inode->i_mapping,
 			      drm->vma_offset_manager,
-			      use_dma_alloc, use_dma32);
+			      alloc_flags);
 
 	return err;
 }
@@ -143,11 +142,10 @@ EXPORT_SYMBOL_GPL(ttm_dev_funcs);
 
 int ttm_device_kunit_init(struct ttm_test_devices *priv,
 			  struct ttm_device *ttm,
-			  bool use_dma_alloc,
-			  bool use_dma32)
+			  unsigned int alloc_flags)
 {
-	return ttm_device_kunit_init_with_funcs(priv, ttm, use_dma_alloc,
-						use_dma32, &ttm_dev_funcs);
+	return ttm_device_kunit_init_with_funcs(priv, ttm, alloc_flags,
+						&ttm_dev_funcs);
 }
 EXPORT_SYMBOL_GPL(ttm_device_kunit_init);
 
@@ -161,12 +159,10 @@ struct ttm_device_funcs ttm_dev_funcs_bad_evict = {
 EXPORT_SYMBOL_GPL(ttm_dev_funcs_bad_evict);
 
 int ttm_device_kunit_init_bad_evict(struct ttm_test_devices *priv,
-				    struct ttm_device *ttm,
-				    bool use_dma_alloc,
-				    bool use_dma32)
+				    struct ttm_device *ttm)
 {
-	return ttm_device_kunit_init_with_funcs(priv, ttm, use_dma_alloc,
-						use_dma32, &ttm_dev_funcs_bad_evict);
+	return ttm_device_kunit_init_with_funcs(priv, ttm, 0,
+						&ttm_dev_funcs_bad_evict);
 }
 EXPORT_SYMBOL_GPL(ttm_device_kunit_init_bad_evict);
 
@@ -252,7 +248,7 @@ struct ttm_test_devices *ttm_test_devices_all(struct kunit *test)
 	ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
 
-	err = ttm_device_kunit_init(devs, ttm_dev, false, false);
+	err = ttm_device_kunit_init(devs, ttm_dev, 0);
 	KUNIT_ASSERT_EQ(test, err, 0);
 
 	devs->ttm_dev = ttm_dev;
diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h
index c7da23232ffa..f8402b979d05 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h
+++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h
@@ -28,12 +28,9 @@ struct ttm_test_devices {
 /* Building blocks for test-specific init functions */
 int ttm_device_kunit_init(struct ttm_test_devices *priv,
 			  struct ttm_device *ttm,
-			  bool use_dma_alloc,
-			  bool use_dma32);
+			  unsigned int alloc_flags);
 int ttm_device_kunit_init_bad_evict(struct ttm_test_devices *priv,
-				    struct ttm_device *ttm,
-				    bool use_dma_alloc,
-				    bool use_dma32);
+				    struct ttm_device *ttm);
 struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test,
 					    struct ttm_test_devices *devs,
 					    size_t size,
diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
index d7eb6471f2ed..dd395229e388 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/module.h>
 
 #include <drm/ttm/ttm_resource.h>
 #include <drm/ttm/ttm_device.h>
diff --git a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
index 8ade53371f72..11c92bd75779 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
@@ -8,11 +8,12 @@
 #include <drm/ttm/ttm_pool.h>
 
 #include "ttm_kunit_helpers.h"
+#include "../ttm_pool_internal.h"
 
 struct ttm_pool_test_case {
 	const char *description;
 	unsigned int order;
-	bool use_dma_alloc;
+	unsigned int alloc_flags;
 };
 
 struct ttm_pool_test_priv {
@@ -86,7 +87,7 @@ static struct ttm_pool *ttm_pool_pre_populated(struct kunit *test,
 	pool = kunit_kzalloc(test, sizeof(*pool), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, pool);
 
-	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, true, false);
+	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, TTM_ALLOCATION_POOL_USE_DMA_ALLOC);
 
 	err = ttm_pool_alloc(pool, tt, &simple_ctx);
 	KUNIT_ASSERT_EQ(test, err, 0);
@@ -113,12 +114,12 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	{
 		.description = "One page, with coherent DMA mappings enabled",
 		.order = 0,
-		.use_dma_alloc = true,
+		.alloc_flags = TTM_ALLOCATION_POOL_USE_DMA_ALLOC,
 	},
 	{
 		.description = "Above the allocation limit, with coherent DMA mappings enabled",
 		.order = MAX_PAGE_ORDER + 1,
-		.use_dma_alloc = true,
+		.alloc_flags = TTM_ALLOCATION_POOL_USE_DMA_ALLOC,
 	},
 };
 
@@ -150,12 +151,11 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 	pool = kunit_kzalloc(test, sizeof(*pool), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, pool);
 
-	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, params->use_dma_alloc,
-		      false);
+	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, params->alloc_flags);
 
 	KUNIT_ASSERT_PTR_EQ(test, pool->dev, devs->dev);
 	KUNIT_ASSERT_EQ(test, pool->nid, NUMA_NO_NODE);
-	KUNIT_ASSERT_EQ(test, pool->use_dma_alloc, params->use_dma_alloc);
+	KUNIT_ASSERT_EQ(test, pool->alloc_flags, params->alloc_flags);
 
 	err = ttm_pool_alloc(pool, tt, &simple_ctx);
 	KUNIT_ASSERT_EQ(test, err, 0);
@@ -165,14 +165,14 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 	last_page = tt->pages[tt->num_pages - 1];
 
 	if (params->order <= MAX_PAGE_ORDER) {
-		if (params->use_dma_alloc) {
+		if (ttm_pool_uses_dma_alloc(pool)) {
 			KUNIT_ASSERT_NOT_NULL(test, (void *)fst_page->private);
 			KUNIT_ASSERT_NOT_NULL(test, (void *)last_page->private);
 		} else {
 			KUNIT_ASSERT_EQ(test, fst_page->private, params->order);
 		}
 	} else {
-		if (params->use_dma_alloc) {
+		if (ttm_pool_uses_dma_alloc(pool)) {
 			KUNIT_ASSERT_NOT_NULL(test, (void *)fst_page->private);
 			KUNIT_ASSERT_NULL(test, (void *)last_page->private);
 		} else {
@@ -218,7 +218,7 @@ static void ttm_pool_alloc_basic_dma_addr(struct kunit *test)
 	pool = kunit_kzalloc(test, sizeof(*pool), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, pool);
 
-	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, true, false);
+	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, TTM_ALLOCATION_POOL_USE_DMA_ALLOC);
 
 	err = ttm_pool_alloc(pool, tt, &simple_ctx);
 	KUNIT_ASSERT_EQ(test, err, 0);
@@ -348,7 +348,7 @@ static void ttm_pool_free_dma_alloc(struct kunit *test)
 	pool = kunit_kzalloc(test, sizeof(*pool), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, pool);
 
-	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, true, false);
+	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, TTM_ALLOCATION_POOL_USE_DMA_ALLOC);
 	ttm_pool_alloc(pool, tt, &simple_ctx);
 
 	pt = &pool->caching[caching].orders[order];
@@ -379,7 +379,7 @@ static void ttm_pool_free_no_dma_alloc(struct kunit *test)
 	pool = kunit_kzalloc(test, sizeof(*pool), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, pool);
 
-	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, false, false);
+	ttm_pool_init(pool, devs->dev, NUMA_NO_NODE, 0);
 	ttm_pool_alloc(pool, tt, &simple_ctx);
 
 	pt = &pool->caching[caching].orders[order];
diff --git a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
index e6ea2bd01f07..c0e4e35e0442 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
@@ -207,6 +207,7 @@ static void ttm_resource_manager_init_basic(struct kunit *test)
 	struct ttm_resource_test_priv *priv = test->priv;
 	struct ttm_resource_manager *man;
 	size_t size = SZ_16K;
+	int i;
 
 	man = kunit_kzalloc(test, sizeof(*man), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, man);
@@ -216,8 +217,8 @@ static void ttm_resource_manager_init_basic(struct kunit *test)
 	KUNIT_ASSERT_PTR_EQ(test, man->bdev, priv->devs->ttm_dev);
 	KUNIT_ASSERT_EQ(test, man->size, size);
 	KUNIT_ASSERT_EQ(test, man->usage, 0);
-	KUNIT_ASSERT_NULL(test, man->move);
-	KUNIT_ASSERT_NOT_NULL(test, &man->move_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++)
+		KUNIT_ASSERT_NULL(test, man->eviction_fences[i]);
 
 	for (int i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
 		KUNIT_ASSERT_TRUE(test, list_empty(&man->lru[i]));
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 29423ceeec5c..bd27607f8076 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -31,6 +31,8 @@
 
 #define pr_fmt(fmt) "[TTM] " fmt
 
+#include <drm/drm_print.h>
+#include <drm/ttm/ttm_allocation.h>
 #include <drm/ttm/ttm_bo.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_tt.h>
@@ -318,18 +320,17 @@ static void ttm_bo_release(struct kref *kref)
 	bo->destroy(bo);
 }
 
-/**
- * ttm_bo_put
- *
- * @bo: The buffer object.
- *
- * Unreference a buffer object.
- */
+/* TODO: remove! */
 void ttm_bo_put(struct ttm_buffer_object *bo)
 {
 	kref_put(&bo->kref, ttm_bo_release);
 }
-EXPORT_SYMBOL(ttm_bo_put);
+
+void ttm_bo_fini(struct ttm_buffer_object *bo)
+{
+	ttm_bo_put(bo);
+}
+EXPORT_SYMBOL(ttm_bo_fini);
 
 static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo,
 				     struct ttm_operation_ctx *ctx,
@@ -658,34 +659,35 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo)
 EXPORT_SYMBOL(ttm_bo_unpin);
 
 /*
- * Add the last move fence to the BO as kernel dependency and reserve a new
- * fence slot.
+ * Add the pipelined eviction fencesto the BO as kernel dependency and reserve new
+ * fence slots.
  */
-static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
-				 struct ttm_resource_manager *man,
-				 bool no_wait_gpu)
+static int ttm_bo_add_pipelined_eviction_fences(struct ttm_buffer_object *bo,
+						struct ttm_resource_manager *man,
+						bool no_wait_gpu)
 {
 	struct dma_fence *fence;
-	int ret;
+	int i;
 
-	spin_lock(&man->move_lock);
-	fence = dma_fence_get(man->move);
-	spin_unlock(&man->move_lock);
-
-	if (!fence)
-		return 0;
+	spin_lock(&man->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
+		fence = man->eviction_fences[i];
+		if (!fence)
+			continue;
 
-	if (no_wait_gpu) {
-		ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
-		dma_fence_put(fence);
-		return ret;
+		if (no_wait_gpu) {
+			if (!dma_fence_is_signaled(fence)) {
+				spin_unlock(&man->eviction_lock);
+				return -EBUSY;
+			}
+		} else {
+			dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL);
+		}
 	}
+	spin_unlock(&man->eviction_lock);
 
-	dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL);
-
-	ret = dma_resv_reserve_fences(bo->base.resv, 1);
-	dma_fence_put(fence);
-	return ret;
+	/* TODO: this call should be removed. */
+	return dma_resv_reserve_fences(bo->base.resv, 1);
 }
 
 /**
@@ -718,7 +720,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo,
 	int i, ret;
 
 	ticket = dma_resv_locking_ctx(bo->base.resv);
-	ret = dma_resv_reserve_fences(bo->base.resv, 1);
+	ret = dma_resv_reserve_fences(bo->base.resv, TTM_NUM_MOVE_FENCES);
 	if (unlikely(ret))
 		return ret;
 
@@ -757,7 +759,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo,
 				return ret;
 		}
 
-		ret = ttm_bo_add_move_fence(bo, man, ctx->no_wait_gpu);
+		ret = ttm_bo_add_pipelined_eviction_fences(bo, man, ctx->no_wait_gpu);
 		if (unlikely(ret)) {
 			ttm_resource_free(bo, res);
 			if (ret == -EBUSY)
@@ -878,7 +880,8 @@ bounce:
 
 	/* For backward compatibility with userspace */
 	if (ret == -ENOSPC)
-		return -ENOMEM;
+		return bo->bdev->alloc_flags & TTM_ALLOCATION_PROPAGATE_ENOSPC ?
+		       ret : -ENOMEM;
 
 	/*
 	 * We might need to add a TTM.
diff --git a/drivers/gpu/drm/ttm/ttm_bo_internal.h b/drivers/gpu/drm/ttm/ttm_bo_internal.h
index 9d8b747a34db..e0d48eac74b0 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_internal.h
+++ b/drivers/gpu/drm/ttm/ttm_bo_internal.h
@@ -55,4 +55,6 @@ ttm_bo_get_unless_zero(struct ttm_buffer_object *bo)
 	return bo;
 }
 
+void ttm_bo_put(struct ttm_buffer_object *bo);
+
 #endif
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index acbbca9d5c92..2ff35d55e462 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -258,7 +258,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
-	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
+	ret = dma_resv_reserve_fences(&fbo->base.base._resv, TTM_NUM_MOVE_FENCES);
 	if (ret) {
 		dma_resv_unlock(&fbo->base.base._resv);
 		kfree(fbo);
@@ -646,20 +646,44 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo,
 {
 	struct ttm_device *bdev = bo->bdev;
 	struct ttm_resource_manager *from;
+	struct dma_fence *tmp;
+	int i;
 
 	from = ttm_manager_type(bdev, bo->resource->mem_type);
 
 	/**
 	 * BO doesn't have a TTM we need to bind/unbind. Just remember
-	 * this eviction and free up the allocation
+	 * this eviction and free up the allocation.
+	 * The fence will be saved in the first free slot or in the slot
+	 * already used to store a fence from the same context. Since
+	 * drivers can't use more than TTM_NUM_MOVE_FENCES contexts for
+	 * evictions we should always find a slot to use.
 	 */
-	spin_lock(&from->move_lock);
-	if (!from->move || dma_fence_is_later(fence, from->move)) {
-		dma_fence_put(from->move);
-		from->move = dma_fence_get(fence);
+	spin_lock(&from->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
+		tmp = from->eviction_fences[i];
+		if (!tmp)
+			break;
+		if (fence->context != tmp->context)
+			continue;
+		if (dma_fence_is_later(fence, tmp)) {
+			dma_fence_put(tmp);
+			break;
+		}
+		goto unlock;
+	}
+	if (i < TTM_NUM_MOVE_FENCES) {
+		from->eviction_fences[i] = dma_fence_get(fence);
+	} else {
+		WARN(1, "not enough fence slots for all fence contexts");
+		spin_unlock(&from->eviction_lock);
+		dma_fence_wait(fence, false);
+		goto end;
 	}
-	spin_unlock(&from->move_lock);
 
+unlock:
+	spin_unlock(&from->eviction_lock);
+end:
 	ttm_resource_free(bo, &bo->resource);
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index c3e2fcbdd2cc..9a51afaf0749 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -31,6 +31,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 
+#include <drm/ttm/ttm_allocation.h>
 #include <drm/ttm/ttm_bo.h>
 #include <drm/ttm/ttm_device.h>
 #include <drm/ttm/ttm_tt.h>
@@ -198,8 +199,7 @@ EXPORT_SYMBOL(ttm_device_swapout);
  * @dev: The core kernel device pointer for DMA mappings and allocations.
  * @mapping: The address space to use for this bo.
  * @vma_manager: A pointer to a vma manager.
- * @use_dma_alloc: If coherent DMA allocation API should be used.
- * @use_dma32: If we should use GFP_DMA32 for device memory allocations.
+ * @alloc_flags: TTM_ALLOCATION_* flags.
  *
  * Initializes a struct ttm_device:
  * Returns:
@@ -208,7 +208,7 @@ EXPORT_SYMBOL(ttm_device_swapout);
 int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *funcs,
 		    struct device *dev, struct address_space *mapping,
 		    struct drm_vma_offset_manager *vma_manager,
-		    bool use_dma_alloc, bool use_dma32)
+		    unsigned int alloc_flags)
 {
 	struct ttm_global *glob = &ttm_glob;
 	int ret, nid;
@@ -227,6 +227,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 		return -ENOMEM;
 	}
 
+	bdev->alloc_flags = alloc_flags;
 	bdev->funcs = funcs;
 
 	ttm_sys_man_init(bdev);
@@ -236,7 +237,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 	else
 		nid = NUMA_NO_NODE;
 
-	ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
+	ttm_pool_init(&bdev->pool, dev, nid, alloc_flags);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c
index b3fffe7b5062..aa137ead5cc5 100644
--- a/drivers/gpu/drm/ttm/ttm_module.c
+++ b/drivers/gpu/drm/ttm/ttm_module.c
@@ -74,7 +74,8 @@ pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp)
 #endif /* CONFIG_UML */
 #endif /* __i386__ || __x86_64__ */
 #if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
-	defined(__powerpc__) || defined(__mips__) || defined(__loongarch__)
+	defined(__powerpc__) || defined(__mips__) || defined(__loongarch__) || \
+	defined(__riscv)
 	if (caching == ttm_write_combined)
 		tmp = pgprot_writecombine(tmp);
 	else
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index baf27c70a419..18b6db015619 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -48,6 +48,7 @@
 #include <drm/ttm/ttm_bo.h>
 
 #include "ttm_module.h"
+#include "ttm_pool_internal.h"
 
 #ifdef CONFIG_FAULT_INJECTION
 #include <linux/fault-inject.h>
@@ -135,6 +136,7 @@ static DECLARE_RWSEM(pool_shrink_rwsem);
 static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
 					unsigned int order)
 {
+	const unsigned int beneficial_order = ttm_pool_beneficial_order(pool);
 	unsigned long attr = DMA_ATTR_FORCE_CONTIGUOUS;
 	struct ttm_pool_dma *dma;
 	struct page *p;
@@ -148,7 +150,14 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
 		gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN |
 			__GFP_THISNODE;
 
-	if (!pool->use_dma_alloc) {
+	/*
+	 * Do not add latency to the allocation path for allocations orders
+	 * device tolds us do not bring them additional performance gains.
+	 */
+	if (beneficial_order && order > beneficial_order)
+		gfp_flags &= ~__GFP_DIRECT_RECLAIM;
+
+	if (!ttm_pool_uses_dma_alloc(pool)) {
 		p = alloc_pages_node(pool->nid, gfp_flags, order);
 		if (p)
 			p->private = order;
@@ -200,7 +209,7 @@ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching,
 		set_pages_wb(p, 1 << order);
 #endif
 
-	if (!pool || !pool->use_dma_alloc) {
+	if (!pool || !ttm_pool_uses_dma_alloc(pool)) {
 		__free_pages(p, order);
 		return;
 	}
@@ -243,7 +252,7 @@ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order,
 {
 	dma_addr_t addr;
 
-	if (pool->use_dma_alloc) {
+	if (ttm_pool_uses_dma_alloc(pool)) {
 		struct ttm_pool_dma *dma = (void *)p->private;
 
 		addr = dma->addr;
@@ -265,7 +274,7 @@ static void ttm_pool_unmap(struct ttm_pool *pool, dma_addr_t dma_addr,
 			   unsigned int num_pages)
 {
 	/* Unmapped while freeing the page */
-	if (pool->use_dma_alloc)
+	if (ttm_pool_uses_dma_alloc(pool))
 		return;
 
 	dma_unmap_page(pool->dev, dma_addr, (long)num_pages << PAGE_SHIFT,
@@ -339,7 +348,7 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
 						  enum ttm_caching caching,
 						  unsigned int order)
 {
-	if (pool->use_dma_alloc)
+	if (ttm_pool_uses_dma_alloc(pool))
 		return &pool->caching[caching].orders[order];
 
 #ifdef CONFIG_X86
@@ -348,7 +357,7 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
 		if (pool->nid != NUMA_NO_NODE)
 			return &pool->caching[caching].orders[order];
 
-		if (pool->use_dma32)
+		if (ttm_pool_uses_dma32(pool))
 			return &global_dma32_write_combined[order];
 
 		return &global_write_combined[order];
@@ -356,7 +365,7 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
 		if (pool->nid != NUMA_NO_NODE)
 			return &pool->caching[caching].orders[order];
 
-		if (pool->use_dma32)
+		if (ttm_pool_uses_dma32(pool))
 			return &global_dma32_uncached[order];
 
 		return &global_uncached[order];
@@ -396,7 +405,7 @@ static unsigned int ttm_pool_shrink(void)
 /* Return the allocation order based for a page */
 static unsigned int ttm_pool_page_order(struct ttm_pool *pool, struct page *p)
 {
-	if (pool->use_dma_alloc) {
+	if (ttm_pool_uses_dma_alloc(pool)) {
 		struct ttm_pool_dma *dma = (void *)p->private;
 
 		return dma->vaddr & ~PAGE_MASK;
@@ -719,7 +728,7 @@ static int __ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	if (ctx->gfp_retry_mayfail)
 		gfp_flags |= __GFP_RETRY_MAYFAIL;
 
-	if (pool->use_dma32)
+	if (ttm_pool_uses_dma32(pool))
 		gfp_flags |= GFP_DMA32;
 	else
 		gfp_flags |= GFP_HIGHUSER;
@@ -977,7 +986,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
 		return -EINVAL;
 
 	if ((!ttm_backup_bytes_avail() && !flags->purge) ||
-	    pool->use_dma_alloc || ttm_tt_is_backed_up(tt))
+	    ttm_pool_uses_dma_alloc(pool) || ttm_tt_is_backed_up(tt))
 		return -EBUSY;
 
 #ifdef CONFIG_X86
@@ -1014,7 +1023,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
 	if (flags->purge)
 		return shrunken;
 
-	if (pool->use_dma32)
+	if (ttm_pool_uses_dma32(pool))
 		gfp = GFP_DMA32;
 	else
 		gfp = GFP_HIGHUSER;
@@ -1058,22 +1067,20 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
  * @pool: the pool to initialize
  * @dev: device for DMA allocations and mappings
  * @nid: NUMA node to use for allocations
- * @use_dma_alloc: true if coherent DMA alloc should be used
- * @use_dma32: true if GFP_DMA32 should be used
+ * @alloc_flags: TTM_ALLOCATION_POOL_* flags
  *
  * Initialize the pool and its pool types.
  */
 void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
-		   int nid, bool use_dma_alloc, bool use_dma32)
+		   int nid, unsigned int alloc_flags)
 {
 	unsigned int i, j;
 
-	WARN_ON(!dev && use_dma_alloc);
+	WARN_ON(!dev && ttm_pool_uses_dma_alloc(pool));
 
 	pool->dev = dev;
 	pool->nid = nid;
-	pool->use_dma_alloc = use_dma_alloc;
-	pool->use_dma32 = use_dma32;
+	pool->alloc_flags = alloc_flags;
 
 	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
 		for (j = 0; j < NR_PAGE_ORDERS; ++j) {
@@ -1239,7 +1246,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 {
 	unsigned int i;
 
-	if (!pool->use_dma_alloc && pool->nid == NUMA_NO_NODE) {
+	if (!ttm_pool_uses_dma_alloc(pool) && pool->nid == NUMA_NO_NODE) {
 		seq_puts(m, "unused\n");
 		return 0;
 	}
@@ -1250,7 +1257,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
 		if (!ttm_pool_select_type(pool, i, 0))
 			continue;
-		if (pool->use_dma_alloc)
+		if (ttm_pool_uses_dma_alloc(pool))
 			seq_puts(m, "DMA ");
 		else
 			seq_printf(m, "N%d ", pool->nid);
diff --git a/drivers/gpu/drm/ttm/ttm_pool_internal.h b/drivers/gpu/drm/ttm/ttm_pool_internal.h
new file mode 100644
index 000000000000..82c4b7e56a99
--- /dev/null
+++ b/drivers/gpu/drm/ttm/ttm_pool_internal.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright (c) 2025 Valve Corporation */
+
+#ifndef _TTM_POOL_INTERNAL_H_
+#define _TTM_POOL_INTERNAL_H_
+
+#include <drm/ttm/ttm_allocation.h>
+#include <drm/ttm/ttm_pool.h>
+
+static inline bool ttm_pool_uses_dma_alloc(struct ttm_pool *pool)
+{
+	return pool->alloc_flags & TTM_ALLOCATION_POOL_USE_DMA_ALLOC;
+}
+
+static inline bool ttm_pool_uses_dma32(struct ttm_pool *pool)
+{
+	return pool->alloc_flags & TTM_ALLOCATION_POOL_USE_DMA32;
+}
+
+static inline bool ttm_pool_beneficial_order(struct ttm_pool *pool)
+{
+	return pool->alloc_flags & 0xff;
+}
+
+#endif
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index e2c82ad07eb4..f5aa29dc6ec0 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -34,6 +34,7 @@
 #include <drm/ttm/ttm_resource.h>
 #include <drm/ttm/ttm_tt.h>
 
+#include <drm/drm_print.h>
 #include <drm/drm_util.h>
 
 /* Detach the cursor from the bulk move list*/
@@ -523,14 +524,15 @@ void ttm_resource_manager_init(struct ttm_resource_manager *man,
 {
 	unsigned i;
 
-	spin_lock_init(&man->move_lock);
 	man->bdev = bdev;
 	man->size = size;
 	man->usage = 0;
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
 		INIT_LIST_HEAD(&man->lru[i]);
-	man->move = NULL;
+	spin_lock_init(&man->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++)
+		man->eviction_fences[i] = NULL;
 }
 EXPORT_SYMBOL(ttm_resource_manager_init);
 
@@ -551,7 +553,7 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 		.no_wait_gpu = false,
 	};
 	struct dma_fence *fence;
-	int ret;
+	int ret, i;
 
 	do {
 		ret = ttm_bo_evict_first(bdev, man, &ctx);
@@ -561,18 +563,24 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 	if (ret && ret != -ENOENT)
 		return ret;
 
-	spin_lock(&man->move_lock);
-	fence = dma_fence_get(man->move);
-	spin_unlock(&man->move_lock);
-
-	if (fence) {
-		ret = dma_fence_wait(fence, false);
-		dma_fence_put(fence);
-		if (ret)
-			return ret;
+	ret = 0;
+
+	spin_lock(&man->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
+		fence = man->eviction_fences[i];
+		if (fence && !dma_fence_is_signaled(fence)) {
+			dma_fence_get(fence);
+			spin_unlock(&man->eviction_lock);
+			ret = dma_fence_wait(fence, false);
+			dma_fence_put(fence);
+			if (ret)
+				return ret;
+			spin_lock(&man->eviction_lock);
+		}
 	}
+	spin_unlock(&man->eviction_lock);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(ttm_resource_manager_evict_all);
 
@@ -587,6 +595,9 @@ uint64_t ttm_resource_manager_usage(struct ttm_resource_manager *man)
 {
 	uint64_t usage;
 
+	if (WARN_ON_ONCE(!man->bdev))
+		return 0;
+
 	spin_lock(&man->bdev->lru_lock);
 	usage = man->usage;
 	spin_unlock(&man->bdev->lru_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 506e257dfba8..611d20ab966d 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -40,12 +40,14 @@
 #include <linux/shmem_fs.h>
 #include <drm/drm_cache.h>
 #include <drm/drm_device.h>
+#include <drm/drm_print.h>
 #include <drm/drm_util.h>
 #include <drm/ttm/ttm_backup.h>
 #include <drm/ttm/ttm_bo.h>
 #include <drm/ttm/ttm_tt.h>
 
 #include "ttm_module.h"
+#include "ttm_pool_internal.h"
 
 static unsigned long ttm_pages_limit;
 
@@ -93,7 +95,8 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
 	 * mapped TT pages need to be decrypted or otherwise the drivers
 	 * will end up sending encrypted mem to the gpu.
 	 */
-	if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
+	if (ttm_pool_uses_dma_alloc(&bdev->pool) &&
+	    cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
 		page_flags |= TTM_TT_FLAG_DECRYPTED;
 		drm_info_once(ddev, "TT memory decryption enabled.");
 	}
@@ -378,7 +381,7 @@ int ttm_tt_populate(struct ttm_device *bdev,
 
 	if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) {
 		atomic_long_add(ttm->num_pages, &ttm_pages_allocated);
-		if (bdev->pool.use_dma32)
+		if (ttm_pool_uses_dma32(&bdev->pool))
 			atomic_long_add(ttm->num_pages,
 					&ttm_dma32_pages_allocated);
 	}
@@ -416,7 +419,7 @@ int ttm_tt_populate(struct ttm_device *bdev,
 error:
 	if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) {
 		atomic_long_sub(ttm->num_pages, &ttm_pages_allocated);
-		if (bdev->pool.use_dma32)
+		if (ttm_pool_uses_dma32(&bdev->pool))
 			atomic_long_sub(ttm->num_pages,
 					&ttm_dma32_pages_allocated);
 	}
@@ -439,7 +442,7 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm)
 
 	if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) {
 		atomic_long_sub(ttm->num_pages, &ttm_pages_allocated);
-		if (bdev->pool.use_dma32)
+		if (ttm_pool_uses_dma32(&bdev->pool))
 			atomic_long_sub(ttm->num_pages,
 					&ttm_dma32_pages_allocated);
 	}