diff options
Diffstat (limited to 'drivers/gpu/drm/ttm')
22 files changed, 3929 insertions, 697 deletions
diff --git a/drivers/gpu/drm/ttm/Makefile b/drivers/gpu/drm/ttm/Makefile index dad298127226..40d07a35293a 100644 --- a/drivers/gpu/drm/ttm/Makefile +++ b/drivers/gpu/drm/ttm/Makefile @@ -4,7 +4,7 @@ ttm-y := ttm_tt.o ttm_bo.o ttm_bo_util.o ttm_bo_vm.o ttm_module.o \ ttm_execbuf_util.o ttm_range_manager.o ttm_resource.o ttm_pool.o \ - ttm_device.o ttm_sys_manager.o + ttm_device.o ttm_sys_manager.o ttm_backup.o ttm-$(CONFIG_AGP) += ttm_agp_backend.o obj-$(CONFIG_DRM_TTM) += ttm.o diff --git a/drivers/gpu/drm/ttm/tests/.kunitconfig b/drivers/gpu/drm/ttm/tests/.kunitconfig index 75fdce0cd98e..1ae1ffabd51e 100644 --- a/drivers/gpu/drm/ttm/tests/.kunitconfig +++ b/drivers/gpu/drm/ttm/tests/.kunitconfig @@ -1,4 +1,3 @@ CONFIG_KUNIT=y CONFIG_DRM=y -CONFIG_DRM_KUNIT_TEST_HELPERS=y CONFIG_DRM_TTM_KUNIT_TEST=y diff --git a/drivers/gpu/drm/ttm/tests/Makefile b/drivers/gpu/drm/ttm/tests/Makefile index 468535f7eed2..f3149de77541 100644 --- a/drivers/gpu/drm/ttm/tests/Makefile +++ b/drivers/gpu/drm/ttm/tests/Makefile @@ -6,4 +6,6 @@ obj-$(CONFIG_DRM_TTM_KUNIT_TEST) += \ ttm_resource_test.o \ ttm_tt_test.o \ ttm_bo_test.o \ + ttm_bo_validate_test.o \ + ttm_mock_manager.o \ ttm_kunit_helpers.o diff --git a/drivers/gpu/drm/ttm/tests/TODO b/drivers/gpu/drm/ttm/tests/TODO new file mode 100644 index 000000000000..45b03d184ccf --- /dev/null +++ b/drivers/gpu/drm/ttm/tests/TODO @@ -0,0 +1,27 @@ +TODO +===== + +- Add a test case where the only evictable BO is busy +- Update eviction tests so they use parametrized "from" memory type +- Improve mock manager's implementation, e.g. allocate a block of + dummy memory that can be used when testing page mapping functions +- Suggestion: Add test cases with external BOs +- Suggestion: randomize the number and size of tested buffers in + ttm_bo_validate() +- Agree on the naming convention +- Rewrite the mock manager: drop use_tt and manage mock memory using + drm_mm manager + +Notes and gotchas +================= + +- These tests are built and run with a UML kernel, because + 1) We are interested in hardware-independent testing + 2) We don't want to have actual DRM devices interacting with TTM + at the same time as the test one. Getting these to work in + parallel would require some time (...and that's a "todo" in itself!) +- Triggering ttm_bo_vm_ops callbacks from KUnit (i.e. kernel) might be + a challenge, but is worth trying. Look at selftests like + i915/gem/selftests/i915_gem_mman.c for inspiration +- The test suite uses UML where ioremap() call returns NULL, meaning that + ttm_bo_ioremap() can't be tested, unless we find a way to stub it diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c index 1f8a4f8adc92..560d12e50e9e 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c @@ -18,6 +18,12 @@ #define BO_SIZE SZ_8K +#ifdef CONFIG_PREEMPT_RT +#define ww_mutex_base_lock(b) rt_mutex_lock(b) +#else +#define ww_mutex_base_lock(b) mutex_lock(b) +#endif + struct ttm_bo_test_case { const char *description; bool interruptible; @@ -56,7 +62,7 @@ static void ttm_bo_reserve_optimistic_no_ticket(struct kunit *test) struct ttm_buffer_object *bo; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_bo_reserve(bo, params->interruptible, params->no_wait, NULL); KUNIT_ASSERT_EQ(test, err, 0); @@ -71,7 +77,7 @@ static void ttm_bo_reserve_locked_no_sleep(struct kunit *test) bool no_wait = true; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); /* Let's lock it beforehand */ dma_resv_lock(bo->base.resv, NULL); @@ -92,7 +98,7 @@ static void ttm_bo_reserve_no_wait_ticket(struct kunit *test) ww_acquire_init(&ctx, &reservation_ww_class); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_bo_reserve(bo, interruptible, no_wait, &ctx); KUNIT_ASSERT_EQ(test, err, -EBUSY); @@ -110,7 +116,7 @@ static void ttm_bo_reserve_double_resv(struct kunit *test) ww_acquire_init(&ctx, &reservation_ww_class); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_bo_reserve(bo, interruptible, no_wait, &ctx); KUNIT_ASSERT_EQ(test, err, 0); @@ -138,11 +144,11 @@ static void ttm_bo_reserve_deadlock(struct kunit *test) bool no_wait = false; int err; - bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE); - bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); ww_acquire_init(&ctx1, &reservation_ww_class); - mutex_lock(&bo2->base.resv->lock.base); + ww_mutex_base_lock(&bo2->base.resv->lock.base); /* The deadlock will be caught by WW mutex, don't warn about it */ lock_release(&bo2->base.resv->lock.base.dep_map, 1); @@ -195,7 +201,7 @@ static int threaded_ttm_bo_reserve(void *arg) err = ttm_bo_reserve(bo, interruptible, no_wait, &ctx); timer_delete_sync(&s_timer.timer); - destroy_timer_on_stack(&s_timer.timer); + timer_destroy_on_stack(&s_timer.timer); ww_acquire_fini(&ctx); @@ -208,7 +214,7 @@ static void ttm_bo_reserve_interrupted(struct kunit *test) struct task_struct *task; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); task = kthread_create(threaded_ttm_bo_reserve, bo, "ttm-bo-reserve"); @@ -237,7 +243,7 @@ static void ttm_bo_unreserve_basic(struct kunit *test) struct ttm_place *place; struct ttm_resource_manager *man; unsigned int bo_prio = TTM_MAX_BO_PRIORITY - 1; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; int err; place = ttm_place_kunit_init(test, mem_type, 0); @@ -249,23 +255,23 @@ static void ttm_bo_unreserve_basic(struct kunit *test) KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->priority = bo_prio; - err = ttm_resource_alloc(bo, place, &res1); + err = ttm_resource_alloc(bo, place, &res1, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res1; /* Add a dummy resource to populate LRU */ - ttm_resource_alloc(bo, place, &res2); + ttm_resource_alloc(bo, place, &res2, NULL); dma_resv_lock(bo->base.resv, NULL); ttm_bo_unreserve(bo); man = ttm_manager_type(priv->ttm_dev, mem_type); KUNIT_ASSERT_EQ(test, - list_is_last(&res1->lru, &man->lru[bo->priority]), 1); + list_is_last(&res1->lru.link, &man->lru[bo->priority]), 1); ttm_resource_free(bo, &res2); ttm_resource_free(bo, &res1); @@ -278,7 +284,7 @@ static void ttm_bo_unreserve_pinned(struct kunit *test) struct ttm_device *ttm_dev; struct ttm_resource *res1, *res2; struct ttm_place *place; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; int err; ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL); @@ -288,25 +294,25 @@ static void ttm_bo_unreserve_pinned(struct kunit *test) KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); place = ttm_place_kunit_init(test, mem_type, 0); dma_resv_lock(bo->base.resv, NULL); ttm_bo_pin(bo); - err = ttm_resource_alloc(bo, place, &res1); + err = ttm_resource_alloc(bo, place, &res1, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res1; /* Add a dummy resource to the pinned list */ - err = ttm_resource_alloc(bo, place, &res2); + err = ttm_resource_alloc(bo, place, &res2, NULL); KUNIT_ASSERT_EQ(test, err, 0); KUNIT_ASSERT_EQ(test, - list_is_last(&res2->lru, &priv->ttm_dev->pinned), 1); + list_is_last(&res2->lru.link, &priv->ttm_dev->unevictable), 1); ttm_bo_unreserve(bo); KUNIT_ASSERT_EQ(test, - list_is_last(&res1->lru, &priv->ttm_dev->pinned), 1); + list_is_last(&res1->lru.link, &priv->ttm_dev->unevictable), 1); ttm_resource_free(bo, &res1); ttm_resource_free(bo, &res2); @@ -321,7 +327,8 @@ static void ttm_bo_unreserve_bulk(struct kunit *test) struct ttm_resource *res1, *res2; struct ttm_device *ttm_dev; struct ttm_place *place; - uint32_t mem_type = TTM_PL_SYSTEM; + struct dma_resv *resv; + u32 mem_type = TTM_PL_SYSTEM; unsigned int bo_priority = 0; int err; @@ -332,18 +339,23 @@ static void ttm_bo_unreserve_bulk(struct kunit *test) ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, ttm_dev); + resv = kunit_kzalloc(test, sizeof(*resv), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, resv); + err = ttm_device_kunit_init(priv, ttm_dev, false, false); KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE); - bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + dma_resv_init(resv); + + bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, resv); + bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, resv); dma_resv_lock(bo1->base.resv, NULL); ttm_bo_set_bulk_move(bo1, &lru_bulk_move); dma_resv_unlock(bo1->base.resv); - err = ttm_resource_alloc(bo1, place, &res1); + err = ttm_resource_alloc(bo1, place, &res1, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo1->resource = res1; @@ -351,7 +363,7 @@ static void ttm_bo_unreserve_bulk(struct kunit *test) ttm_bo_set_bulk_move(bo2, &lru_bulk_move); dma_resv_unlock(bo2->base.resv); - err = ttm_resource_alloc(bo2, place, &res2); + err = ttm_resource_alloc(bo2, place, &res2, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo2->resource = res2; @@ -363,6 +375,8 @@ static void ttm_bo_unreserve_bulk(struct kunit *test) ttm_resource_free(bo1, &res1); ttm_resource_free(bo2, &res2); + + dma_resv_fini(resv); } static void ttm_bo_put_basic(struct kunit *test) @@ -372,7 +386,7 @@ static void ttm_bo_put_basic(struct kunit *test) struct ttm_resource *res; struct ttm_device *ttm_dev; struct ttm_place *place; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; int err; place = ttm_place_kunit_init(test, mem_type, 0); @@ -384,10 +398,10 @@ static void ttm_bo_put_basic(struct kunit *test) KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->type = ttm_bo_type_device; - err = ttm_resource_alloc(bo, place, &res); + err = ttm_resource_alloc(bo, place, &res, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res; @@ -445,7 +459,7 @@ static void ttm_bo_put_shared_resv(struct kunit *test) dma_fence_signal(fence); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->type = ttm_bo_type_device; bo->base.resv = external_resv; @@ -467,7 +481,7 @@ static void ttm_bo_pin_basic(struct kunit *test) KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); for (int i = 0; i < no_pins; i++) { dma_resv_lock(bo->base.resv, NULL); @@ -487,7 +501,7 @@ static void ttm_bo_pin_unpin_resource(struct kunit *test) struct ttm_resource *res; struct ttm_device *ttm_dev; struct ttm_place *place; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; unsigned int bo_priority = 0; int err; @@ -502,9 +516,9 @@ static void ttm_bo_pin_unpin_resource(struct kunit *test) KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); - err = ttm_resource_alloc(bo, place, &res); + err = ttm_resource_alloc(bo, place, &res, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res; @@ -538,7 +552,7 @@ static void ttm_bo_multiple_pin_one_unpin(struct kunit *test) struct ttm_resource *res; struct ttm_device *ttm_dev; struct ttm_place *place; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; unsigned int bo_priority = 0; int err; @@ -553,9 +567,9 @@ static void ttm_bo_multiple_pin_one_unpin(struct kunit *test) KUNIT_ASSERT_EQ(test, err, 0); priv->ttm_dev = ttm_dev; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); - err = ttm_resource_alloc(bo, place, &res); + err = ttm_resource_alloc(bo, place, &res, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res; @@ -619,4 +633,5 @@ static struct kunit_suite ttm_bo_test_suite = { kunit_test_suites(&ttm_bo_test_suite); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for ttm_bo APIs"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c new file mode 100644 index 000000000000..3148f5d3dbd6 --- /dev/null +++ b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c @@ -0,0 +1,1225 @@ +// SPDX-License-Identifier: GPL-2.0 AND MIT +/* + * Copyright © 2023 Intel Corporation + */ +#include <linux/delay.h> +#include <linux/kthread.h> + +#include <drm/ttm/ttm_resource.h> +#include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_tt.h> + +#include "ttm_kunit_helpers.h" +#include "ttm_mock_manager.h" + +#define BO_SIZE SZ_4K +#define MANAGER_SIZE SZ_1M + +static struct spinlock fence_lock; + +struct ttm_bo_validate_test_case { + const char *description; + enum ttm_bo_type bo_type; + u32 mem_type; + bool with_ttm; + bool no_gpu_wait; +}; + +static struct ttm_placement *ttm_placement_kunit_init(struct kunit *test, + struct ttm_place *places, + unsigned int num_places) +{ + struct ttm_placement *placement; + + placement = kunit_kzalloc(test, sizeof(*placement), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, placement); + + placement->num_placement = num_places; + placement->placement = places; + + return placement; +} + +static const char *fence_name(struct dma_fence *f) +{ + return "ttm-bo-validate-fence"; +} + +static const struct dma_fence_ops fence_ops = { + .get_driver_name = fence_name, + .get_timeline_name = fence_name, +}; + +static struct dma_fence *alloc_mock_fence(struct kunit *test) +{ + struct dma_fence *fence; + + fence = kunit_kzalloc(test, sizeof(*fence), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, fence); + + dma_fence_init(fence, &fence_ops, &fence_lock, 0, 0); + + return fence; +} + +static void dma_resv_kunit_active_fence_init(struct kunit *test, + struct dma_resv *resv, + enum dma_resv_usage usage) +{ + struct dma_fence *fence; + + fence = alloc_mock_fence(test); + dma_fence_enable_sw_signaling(fence); + + dma_resv_lock(resv, NULL); + dma_resv_reserve_fences(resv, 1); + dma_resv_add_fence(resv, fence, usage); + dma_resv_unlock(resv); +} + +static void ttm_bo_validate_case_desc(const struct ttm_bo_validate_test_case *t, + char *desc) +{ + strscpy(desc, t->description, KUNIT_PARAM_DESC_SIZE); +} + +static const struct ttm_bo_validate_test_case ttm_bo_type_cases[] = { + { + .description = "Buffer object for userspace", + .bo_type = ttm_bo_type_device, + }, + { + .description = "Kernel buffer object", + .bo_type = ttm_bo_type_kernel, + }, + { + .description = "Shared buffer object", + .bo_type = ttm_bo_type_sg, + }, +}; + +KUNIT_ARRAY_PARAM(ttm_bo_types, ttm_bo_type_cases, + ttm_bo_validate_case_desc); + +static void ttm_bo_init_reserved_sys_man(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + struct ttm_test_devices *priv = test->priv; + enum ttm_bo_type bo_type = params->bo_type; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + place = ttm_place_kunit_init(test, TTM_PL_SYSTEM, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, bo_type, placement, + PAGE_SIZE, &ctx, NULL, NULL, + &dummy_ttm_bo_destroy); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, kref_read(&bo->kref), 1); + KUNIT_EXPECT_PTR_EQ(test, bo->bdev, priv->ttm_dev); + KUNIT_EXPECT_EQ(test, bo->type, bo_type); + KUNIT_EXPECT_EQ(test, bo->page_alignment, PAGE_SIZE); + KUNIT_EXPECT_PTR_EQ(test, bo->destroy, &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, bo->pin_count, 0); + KUNIT_EXPECT_NULL(test, bo->bulk_move); + KUNIT_EXPECT_NOT_NULL(test, bo->ttm); + KUNIT_EXPECT_FALSE(test, ttm_tt_is_populated(bo->ttm)); + KUNIT_EXPECT_NOT_NULL(test, (void *)bo->base.resv->fences); + KUNIT_EXPECT_EQ(test, ctx.bytes_moved, size); + + if (bo_type != ttm_bo_type_kernel) + KUNIT_EXPECT_TRUE(test, + drm_mm_node_allocated(&bo->base.vma_node.vm_node)); + + ttm_resource_free(bo, &bo->resource); + ttm_bo_put(bo); +} + +static void ttm_bo_init_reserved_mock_man(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + enum ttm_bo_type bo_type = params->bo_type; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + struct ttm_placement *placement; + u32 mem_type = TTM_PL_VRAM; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, bo_type, placement, + PAGE_SIZE, &ctx, NULL, NULL, + &dummy_ttm_bo_destroy); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, kref_read(&bo->kref), 1); + KUNIT_EXPECT_PTR_EQ(test, bo->bdev, priv->ttm_dev); + KUNIT_EXPECT_EQ(test, bo->type, bo_type); + KUNIT_EXPECT_EQ(test, ctx.bytes_moved, size); + + if (bo_type != ttm_bo_type_kernel) + KUNIT_EXPECT_TRUE(test, + drm_mm_node_allocated(&bo->base.vma_node.vm_node)); + + ttm_resource_free(bo, &bo->resource); + ttm_bo_put(bo); + ttm_mock_manager_fini(priv->ttm_dev, mem_type); +} + +static void ttm_bo_init_reserved_resv(struct kunit *test) +{ + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + struct dma_resv resv; + int err; + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + place = ttm_place_kunit_init(test, TTM_PL_SYSTEM, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + dma_resv_init(&resv); + dma_resv_lock(&resv, NULL); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, bo_type, placement, + PAGE_SIZE, &ctx, NULL, &resv, + &dummy_ttm_bo_destroy); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_PTR_EQ(test, bo->base.resv, &resv); + + ttm_resource_free(bo, &bo->resource); + ttm_bo_put(bo); +} + +static void ttm_bo_validate_basic(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + u32 fst_mem = TTM_PL_SYSTEM, snd_mem = TTM_PL_VRAM; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + struct ttm_placement *fst_placement, *snd_placement; + struct ttm_test_devices *priv = test->priv; + struct ttm_place *fst_place, *snd_place; + u32 size = ALIGN(SZ_8K, PAGE_SIZE); + struct ttm_buffer_object *bo; + int err; + + ttm_mock_manager_init(priv->ttm_dev, snd_mem, MANAGER_SIZE); + + fst_place = ttm_place_kunit_init(test, fst_mem, 0); + fst_placement = ttm_placement_kunit_init(test, fst_place, 1); + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, params->bo_type, + fst_placement, PAGE_SIZE, &ctx_init, NULL, + NULL, &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + + snd_place = ttm_place_kunit_init(test, snd_mem, DRM_BUDDY_TOPDOWN_ALLOCATION); + snd_placement = ttm_placement_kunit_init(test, snd_place, 1); + + err = ttm_bo_validate(bo, snd_placement, &ctx_val); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, bo->base.size); + KUNIT_EXPECT_NOT_NULL(test, bo->ttm); + KUNIT_EXPECT_TRUE(test, ttm_tt_is_populated(bo->ttm)); + KUNIT_EXPECT_EQ(test, bo->resource->mem_type, snd_mem); + KUNIT_EXPECT_EQ(test, bo->resource->placement, + DRM_BUDDY_TOPDOWN_ALLOCATION); + + ttm_bo_put(bo); + ttm_mock_manager_fini(priv->ttm_dev, snd_mem); +} + +static void ttm_bo_validate_invalid_placement(struct kunit *test) +{ + enum ttm_bo_type bo_type = ttm_bo_type_device; + u32 unknown_mem_type = TTM_PL_PRIV + 1; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + place = ttm_place_kunit_init(test, unknown_mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); + bo->type = bo_type; + + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, -ENOMEM); + + ttm_bo_put(bo); +} + +static void ttm_bo_validate_failed_alloc(struct kunit *test) +{ + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + struct ttm_placement *placement; + u32 mem_type = TTM_PL_VRAM; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); + bo->type = bo_type; + + ttm_bad_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, -ENOMEM); + + ttm_bo_put(bo); + ttm_bad_manager_fini(priv->ttm_dev, mem_type); +} + +static void ttm_bo_validate_pinned(struct kunit *test) +{ + enum ttm_bo_type bo_type = ttm_bo_type_device; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + u32 mem_type = TTM_PL_SYSTEM; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); + bo->type = bo_type; + + ttm_bo_reserve(bo, false, false, NULL); + ttm_bo_pin(bo); + err = ttm_bo_validate(bo, placement, &ctx); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, -EINVAL); + + ttm_bo_reserve(bo, false, false, NULL); + ttm_bo_unpin(bo); + dma_resv_unlock(bo->base.resv); + + ttm_bo_put(bo); +} + +static const struct ttm_bo_validate_test_case ttm_mem_type_cases[] = { + { + .description = "System manager", + .mem_type = TTM_PL_SYSTEM, + }, + { + .description = "VRAM manager", + .mem_type = TTM_PL_VRAM, + }, +}; + +KUNIT_ARRAY_PARAM(ttm_bo_validate_mem, ttm_mem_type_cases, + ttm_bo_validate_case_desc); + +static void ttm_bo_validate_same_placement(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + place = ttm_place_kunit_init(test, params->mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + if (params->mem_type != TTM_PL_SYSTEM) + ttm_mock_manager_init(priv->ttm_dev, params->mem_type, MANAGER_SIZE); + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, params->bo_type, + placement, PAGE_SIZE, &ctx_init, NULL, + NULL, &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + + err = ttm_bo_validate(bo, placement, &ctx_val); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, 0); + + ttm_bo_put(bo); + + if (params->mem_type != TTM_PL_SYSTEM) + ttm_mock_manager_fini(priv->ttm_dev, params->mem_type); +} + +static void ttm_bo_validate_busy_placement(struct kunit *test) +{ + u32 fst_mem = TTM_PL_VRAM, snd_mem = TTM_PL_VRAM + 1; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + struct ttm_placement *placement_init, *placement_val; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_place *init_place, places[2]; + struct ttm_resource_manager *man; + struct ttm_buffer_object *bo; + int err; + + ttm_bad_manager_init(priv->ttm_dev, fst_mem, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, snd_mem, MANAGER_SIZE); + + init_place = ttm_place_kunit_init(test, TTM_PL_SYSTEM, 0); + placement_init = ttm_placement_kunit_init(test, init_place, 1); + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, bo_type, placement_init, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + + places[0] = (struct ttm_place){ .mem_type = fst_mem, .flags = TTM_PL_FLAG_DESIRED }; + places[1] = (struct ttm_place){ .mem_type = snd_mem, .flags = TTM_PL_FLAG_FALLBACK }; + placement_val = ttm_placement_kunit_init(test, places, 2); + + err = ttm_bo_validate(bo, placement_val, &ctx_val); + dma_resv_unlock(bo->base.resv); + + man = ttm_manager_type(priv->ttm_dev, snd_mem); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, bo->base.size); + 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_bad_manager_fini(priv->ttm_dev, fst_mem); + ttm_mock_manager_fini(priv->ttm_dev, snd_mem); +} + +static void ttm_bo_validate_multihop(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + struct ttm_placement *placement_init, *placement_val; + u32 fst_mem = TTM_PL_VRAM, tmp_mem = TTM_PL_TT, final_mem = TTM_PL_SYSTEM; + struct ttm_test_devices *priv = test->priv; + struct ttm_place *fst_place, *final_place; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_buffer_object *bo; + int err; + + ttm_mock_manager_init(priv->ttm_dev, fst_mem, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, tmp_mem, MANAGER_SIZE); + + fst_place = ttm_place_kunit_init(test, fst_mem, 0); + placement_init = ttm_placement_kunit_init(test, fst_place, 1); + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, params->bo_type, + placement_init, PAGE_SIZE, &ctx_init, NULL, + NULL, &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + + final_place = ttm_place_kunit_init(test, final_mem, 0); + placement_val = ttm_placement_kunit_init(test, final_place, 1); + + err = ttm_bo_validate(bo, placement_val, &ctx_val); + dma_resv_unlock(bo->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + 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_mock_manager_fini(priv->ttm_dev, fst_mem); + ttm_mock_manager_fini(priv->ttm_dev, tmp_mem); +} + +static const struct ttm_bo_validate_test_case ttm_bo_no_placement_cases[] = { + { + .description = "Buffer object in system domain, no page vector", + }, + { + .description = "Buffer object in system domain with an existing page vector", + .with_ttm = true, + }, +}; + +KUNIT_ARRAY_PARAM(ttm_bo_no_placement, ttm_bo_no_placement_cases, + ttm_bo_validate_case_desc); + +static void ttm_bo_validate_no_placement_signaled(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + u32 mem_type = TTM_PL_SYSTEM; + struct ttm_resource_manager *man; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + struct ttm_tt *old_tt; + u32 flags; + int err; + + place = ttm_place_kunit_init(test, mem_type, 0); + man = ttm_manager_type(priv->ttm_dev, mem_type); + + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); + bo->type = bo_type; + + if (params->with_ttm) { + old_tt = priv->ttm_dev->funcs->ttm_tt_create(bo, 0); + ttm_pool_alloc(&priv->ttm_dev->pool, old_tt, &ctx); + bo->ttm = old_tt; + } + + err = ttm_resource_alloc(bo, place, &bo->resource, NULL); + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_ASSERT_EQ(test, man->usage, size); + + placement = kunit_kzalloc(test, sizeof(*placement), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, placement); + + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx); + ttm_bo_unreserve(bo); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_ASSERT_EQ(test, man->usage, 0); + KUNIT_ASSERT_NOT_NULL(test, bo->ttm); + KUNIT_EXPECT_EQ(test, ctx.bytes_moved, 0); + + if (params->with_ttm) { + flags = bo->ttm->page_flags; + + KUNIT_ASSERT_PTR_EQ(test, bo->ttm, old_tt); + KUNIT_ASSERT_FALSE(test, flags & TTM_TT_FLAG_PRIV_POPULATED); + KUNIT_ASSERT_TRUE(test, flags & TTM_TT_FLAG_ZERO_ALLOC); + } + + ttm_bo_put(bo); +} + +static int threaded_dma_resv_signal(void *arg) +{ + struct ttm_buffer_object *bo = arg; + struct dma_resv *resv = bo->base.resv; + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + dma_fence_signal(fence); + } + dma_resv_iter_end(&cursor); + + return 0; +} + +static void ttm_bo_validate_no_placement_not_signaled(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + enum dma_resv_usage usage = DMA_RESV_USAGE_BOOKKEEP; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + u32 mem_type = TTM_PL_SYSTEM; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct task_struct *task; + struct ttm_place *place; + int err; + + place = ttm_place_kunit_init(test, mem_type, 0); + + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); + bo->type = params->bo_type; + + err = ttm_resource_alloc(bo, place, &bo->resource, NULL); + KUNIT_EXPECT_EQ(test, err, 0); + + placement = kunit_kzalloc(test, sizeof(*placement), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, placement); + + /* Create an active fence to simulate a non-idle resv object */ + spin_lock_init(&fence_lock); + dma_resv_kunit_active_fence_init(test, bo->base.resv, usage); + + task = kthread_create(threaded_dma_resv_signal, bo, "dma-resv-signal"); + if (IS_ERR(task)) + KUNIT_FAIL(test, "Couldn't create dma resv signal task\n"); + + wake_up_process(task); + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx); + ttm_bo_unreserve(bo); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_ASSERT_NOT_NULL(test, bo->ttm); + KUNIT_ASSERT_NULL(test, bo->resource); + KUNIT_ASSERT_NULL(test, bo->bulk_move); + KUNIT_EXPECT_EQ(test, ctx.bytes_moved, 0); + + if (bo->type != ttm_bo_type_sg) + KUNIT_ASSERT_PTR_EQ(test, bo->base.resv, &bo->base._resv); + + /* 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); +} + +static void ttm_bo_validate_move_fence_signaled(struct kunit *test) +{ + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_operation_ctx ctx = { }; + u32 mem_type = TTM_PL_SYSTEM; + struct ttm_resource_manager *man; + struct ttm_placement *placement; + struct ttm_buffer_object *bo; + struct ttm_place *place; + int err; + + man = ttm_manager_type(priv->ttm_dev, mem_type); + man->move = dma_fence_get_stub(); + + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); + bo->type = bo_type; + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx); + ttm_bo_unreserve(bo); + + KUNIT_EXPECT_EQ(test, err, 0); + 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); +} + +static const struct ttm_bo_validate_test_case ttm_bo_validate_wait_cases[] = { + { + .description = "Waits for GPU", + .no_gpu_wait = false, + }, + { + .description = "Tries to lock straight away", + .no_gpu_wait = true, + }, +}; + +KUNIT_ARRAY_PARAM(ttm_bo_validate_wait, ttm_bo_validate_wait_cases, + ttm_bo_validate_case_desc); + +static int threaded_fence_signal(void *arg) +{ + struct dma_fence *fence = arg; + + msleep(20); + + return dma_fence_signal(fence); +} + +static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test) +{ + const struct ttm_bo_validate_test_case *params = test->param_value; + struct ttm_operation_ctx ctx_init = { }, + ctx_val = { .no_wait_gpu = params->no_gpu_wait }; + u32 fst_mem = TTM_PL_VRAM, snd_mem = TTM_PL_VRAM + 1; + struct ttm_placement *placement_init, *placement_val; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + u32 size = ALIGN(BO_SIZE, PAGE_SIZE); + struct ttm_place *init_place, places[2]; + struct ttm_resource_manager *man; + struct ttm_buffer_object *bo; + struct task_struct *task; + int err; + + init_place = ttm_place_kunit_init(test, TTM_PL_SYSTEM, 0); + placement_init = ttm_placement_kunit_init(test, init_place, 1); + + bo = kunit_kzalloc(test, sizeof(*bo), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo); + + drm_gem_private_object_init(priv->drm, &bo->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo, bo_type, placement_init, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + + ttm_mock_manager_init(priv->ttm_dev, fst_mem, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, snd_mem, MANAGER_SIZE); + + places[0] = (struct ttm_place){ .mem_type = fst_mem, .flags = TTM_PL_FLAG_DESIRED }; + places[1] = (struct ttm_place){ .mem_type = snd_mem, .flags = TTM_PL_FLAG_FALLBACK }; + placement_val = ttm_placement_kunit_init(test, places, 2); + + spin_lock_init(&fence_lock); + man = ttm_manager_type(priv->ttm_dev, fst_mem); + man->move = alloc_mock_fence(test); + + task = kthread_create(threaded_fence_signal, man->move, "move-fence-signal"); + if (IS_ERR(task)) + KUNIT_FAIL(test, "Couldn't create move fence signal task\n"); + + wake_up_process(task); + 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); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, size); + + if (params->no_gpu_wait) + KUNIT_EXPECT_EQ(test, bo->resource->mem_type, snd_mem); + else + KUNIT_EXPECT_EQ(test, bo->resource->mem_type, fst_mem); + + ttm_bo_put(bo); + ttm_mock_manager_fini(priv->ttm_dev, fst_mem); + ttm_mock_manager_fini(priv->ttm_dev, snd_mem); +} + +static void ttm_bo_validate_swapout(struct kunit *test) +{ + unsigned long size_big, size = ALIGN(BO_SIZE, PAGE_SIZE); + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_buffer_object *bo_small, *bo_big; + struct ttm_test_devices *priv = test->priv; + struct ttm_operation_ctx ctx = { }; + struct ttm_placement *placement; + u32 mem_type = TTM_PL_TT; + struct ttm_place *place; + struct sysinfo si; + int err; + + si_meminfo(&si); + size_big = ALIGN(((u64)si.totalram * si.mem_unit / 2), PAGE_SIZE); + + ttm_mock_manager_init(priv->ttm_dev, mem_type, size_big + size); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo_small = kunit_kzalloc(test, sizeof(*bo_small), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_small); + + drm_gem_private_object_init(priv->drm, &bo_small->base, size); + + err = ttm_bo_init_reserved(priv->ttm_dev, bo_small, bo_type, placement, + PAGE_SIZE, &ctx, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + dma_resv_unlock(bo_small->base.resv); + + bo_big = ttm_bo_kunit_init(test, priv, size_big, NULL); + + dma_resv_lock(bo_big->base.resv, NULL); + err = ttm_bo_validate(bo_big, placement, &ctx); + dma_resv_unlock(bo_big->base.resv); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_NOT_NULL(test, bo_big->resource); + KUNIT_EXPECT_EQ(test, bo_big->resource->mem_type, mem_type); + KUNIT_EXPECT_EQ(test, bo_small->resource->mem_type, TTM_PL_SYSTEM); + KUNIT_EXPECT_TRUE(test, bo_small->ttm->page_flags & TTM_TT_FLAG_SWAPPED); + + ttm_bo_put(bo_big); + ttm_bo_put(bo_small); + + ttm_mock_manager_fini(priv->ttm_dev, mem_type); +} + +static void ttm_bo_validate_happy_evict(struct kunit *test) +{ + u32 mem_type = TTM_PL_VRAM, mem_multihop = TTM_PL_TT, + mem_type_evict = TTM_PL_SYSTEM; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + enum ttm_bo_type bo_type = ttm_bo_type_device; + u32 small = SZ_8K, medium = SZ_512K, + big = MANAGER_SIZE - (small + medium); + u32 bo_sizes[] = { small, medium, big }; + struct ttm_test_devices *priv = test->priv; + struct ttm_buffer_object *bos, *bo_val; + struct ttm_placement *placement; + struct ttm_place *place; + u32 bo_no = 3; + int i, err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, mem_multihop, MANAGER_SIZE); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bos = kunit_kmalloc_array(test, bo_no, sizeof(*bos), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bos); + + memset(bos, 0, sizeof(*bos) * bo_no); + for (i = 0; i < bo_no; i++) { + drm_gem_private_object_init(priv->drm, &bos[i].base, bo_sizes[i]); + err = ttm_bo_init_reserved(priv->ttm_dev, &bos[i], bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + dma_resv_unlock(bos[i].base.resv); + } + + bo_val = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo_val->type = bo_type; + + ttm_bo_reserve(bo_val, false, false, NULL); + err = ttm_bo_validate(bo_val, placement, &ctx_val); + ttm_bo_unreserve(bo_val); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, bos[0].resource->mem_type, mem_type_evict); + KUNIT_EXPECT_TRUE(test, bos[0].ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC); + KUNIT_EXPECT_TRUE(test, bos[0].ttm->page_flags & TTM_TT_FLAG_PRIV_POPULATED); + KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, small * 2 + BO_SIZE); + 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_mock_manager_fini(priv->ttm_dev, mem_type); + ttm_mock_manager_fini(priv->ttm_dev, mem_multihop); +} + +static void ttm_bo_validate_all_pinned_evict(struct kunit *test) +{ + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_buffer_object *bo_big, *bo_small; + struct ttm_test_devices *priv = test->priv; + struct ttm_placement *placement; + u32 mem_type = TTM_PL_VRAM, mem_multihop = TTM_PL_TT; + struct ttm_place *place; + int err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, mem_multihop, MANAGER_SIZE); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo_big = kunit_kzalloc(test, sizeof(*bo_big), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_big); + + drm_gem_private_object_init(priv->drm, &bo_big->base, MANAGER_SIZE); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_big, bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + + ttm_bo_pin(bo_big); + dma_resv_unlock(bo_big->base.resv); + + bo_small = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo_small->type = bo_type; + + ttm_bo_reserve(bo_small, false, false, NULL); + err = ttm_bo_validate(bo_small, placement, &ctx_val); + ttm_bo_unreserve(bo_small); + + KUNIT_EXPECT_EQ(test, err, -ENOMEM); + + ttm_bo_put(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_mock_manager_fini(priv->ttm_dev, mem_type); + ttm_mock_manager_fini(priv->ttm_dev, mem_multihop); +} + +static void ttm_bo_validate_allowed_only_evict(struct kunit *test) +{ + u32 mem_type = TTM_PL_VRAM, mem_multihop = TTM_PL_TT, + mem_type_evict = TTM_PL_SYSTEM; + struct ttm_buffer_object *bo, *bo_evictable, *bo_pinned; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + struct ttm_placement *placement; + struct ttm_place *place; + u32 size = SZ_512K; + int err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, mem_multihop, MANAGER_SIZE); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo_pinned = kunit_kzalloc(test, sizeof(*bo_pinned), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_pinned); + + drm_gem_private_object_init(priv->drm, &bo_pinned->base, size); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_pinned, bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + ttm_bo_pin(bo_pinned); + dma_resv_unlock(bo_pinned->base.resv); + + bo_evictable = kunit_kzalloc(test, sizeof(*bo_evictable), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_evictable); + + drm_gem_private_object_init(priv->drm, &bo_evictable->base, size); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_evictable, bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + dma_resv_unlock(bo_evictable->base.resv); + + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo->type = bo_type; + + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx_val); + ttm_bo_unreserve(bo); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, bo->resource->mem_type, mem_type); + KUNIT_EXPECT_EQ(test, bo_pinned->resource->mem_type, mem_type); + 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_reserve(bo_pinned, false, false, NULL); + ttm_bo_unpin(bo_pinned); + dma_resv_unlock(bo_pinned->base.resv); + ttm_bo_put(bo_pinned); + + ttm_mock_manager_fini(priv->ttm_dev, mem_type); + ttm_mock_manager_fini(priv->ttm_dev, mem_multihop); +} + +static void ttm_bo_validate_deleted_evict(struct kunit *test) +{ + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + u32 small = SZ_8K, big = MANAGER_SIZE - BO_SIZE; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_buffer_object *bo_big, *bo_small; + struct ttm_test_devices *priv = test->priv; + struct ttm_resource_manager *man; + u32 mem_type = TTM_PL_VRAM; + struct ttm_placement *placement; + struct ttm_place *place; + int err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + man = ttm_manager_type(priv->ttm_dev, mem_type); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo_big = kunit_kzalloc(test, sizeof(*bo_big), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_big); + + drm_gem_private_object_init(priv->drm, &bo_big->base, big); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_big, bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, ttm_resource_manager_usage(man), big); + + dma_resv_unlock(bo_big->base.resv); + bo_big->deleted = true; + + bo_small = ttm_bo_kunit_init(test, test->priv, small, NULL); + bo_small->type = bo_type; + + ttm_bo_reserve(bo_small, false, false, NULL); + err = ttm_bo_validate(bo_small, placement, &ctx_val); + ttm_bo_unreserve(bo_small); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, bo_small->resource->mem_type, mem_type); + KUNIT_EXPECT_EQ(test, ttm_resource_manager_usage(man), small); + 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_mock_manager_fini(priv->ttm_dev, mem_type); +} + +static void ttm_bo_validate_busy_domain_evict(struct kunit *test) +{ + u32 mem_type = TTM_PL_VRAM, mem_type_evict = TTM_PL_MOCK1; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + struct ttm_buffer_object *bo_init, *bo_val; + struct ttm_placement *placement; + struct ttm_place *place; + int err; + + /* + * Drop the default device and setup a new one that points to busy + * thus unsuitable eviction domain + */ + ttm_device_fini(priv->ttm_dev); + + err = ttm_device_kunit_init_bad_evict(test->priv, priv->ttm_dev, false, false); + KUNIT_ASSERT_EQ(test, err, 0); + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + ttm_busy_manager_init(priv->ttm_dev, mem_type_evict, MANAGER_SIZE); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo_init = kunit_kzalloc(test, sizeof(*bo_init), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_init); + + drm_gem_private_object_init(priv->drm, &bo_init->base, MANAGER_SIZE); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_init, bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + dma_resv_unlock(bo_init->base.resv); + + bo_val = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo_val->type = bo_type; + + ttm_bo_reserve(bo_val, false, false, NULL); + err = ttm_bo_validate(bo_val, placement, &ctx_val); + ttm_bo_unreserve(bo_val); + + KUNIT_EXPECT_EQ(test, err, -ENOMEM); + 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_mock_manager_fini(priv->ttm_dev, mem_type); + ttm_bad_manager_fini(priv->ttm_dev, mem_type_evict); +} + +static void ttm_bo_validate_evict_gutting(struct kunit *test) +{ + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + struct ttm_buffer_object *bo, *bo_evict; + u32 mem_type = TTM_PL_MOCK1; + struct ttm_placement *placement; + struct ttm_place *place; + int err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + + place = ttm_place_kunit_init(test, mem_type, 0); + placement = ttm_placement_kunit_init(test, place, 1); + + bo_evict = kunit_kzalloc(test, sizeof(*bo_evict), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_evict); + + drm_gem_private_object_init(priv->drm, &bo_evict->base, MANAGER_SIZE); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_evict, bo_type, placement, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + dma_resv_unlock(bo_evict->base.resv); + + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo->type = bo_type; + + ttm_bo_reserve(bo, false, false, NULL); + err = ttm_bo_validate(bo, placement, &ctx_val); + ttm_bo_unreserve(bo); + + KUNIT_EXPECT_EQ(test, err, 0); + KUNIT_EXPECT_EQ(test, bo->resource->mem_type, mem_type); + 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_mock_manager_fini(priv->ttm_dev, mem_type); +} + +static void ttm_bo_validate_recrusive_evict(struct kunit *test) +{ + u32 mem_type = TTM_PL_TT, mem_type_evict = TTM_PL_MOCK2; + struct ttm_operation_ctx ctx_init = { }, ctx_val = { }; + struct ttm_placement *placement_tt, *placement_mock; + struct ttm_buffer_object *bo_tt, *bo_mock, *bo_val; + enum ttm_bo_type bo_type = ttm_bo_type_device; + struct ttm_test_devices *priv = test->priv; + struct ttm_place *place_tt, *place_mock; + int err; + + ttm_mock_manager_init(priv->ttm_dev, mem_type, MANAGER_SIZE); + ttm_mock_manager_init(priv->ttm_dev, mem_type_evict, MANAGER_SIZE); + + place_tt = ttm_place_kunit_init(test, mem_type, 0); + place_mock = ttm_place_kunit_init(test, mem_type_evict, 0); + + placement_tt = ttm_placement_kunit_init(test, place_tt, 1); + placement_mock = ttm_placement_kunit_init(test, place_mock, 1); + + bo_tt = kunit_kzalloc(test, sizeof(*bo_tt), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_tt); + + bo_mock = kunit_kzalloc(test, sizeof(*bo_mock), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, bo_mock); + + drm_gem_private_object_init(priv->drm, &bo_tt->base, MANAGER_SIZE); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_tt, bo_type, placement_tt, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + dma_resv_unlock(bo_tt->base.resv); + + drm_gem_private_object_init(priv->drm, &bo_mock->base, MANAGER_SIZE); + err = ttm_bo_init_reserved(priv->ttm_dev, bo_mock, bo_type, placement_mock, + PAGE_SIZE, &ctx_init, NULL, NULL, + &dummy_ttm_bo_destroy); + KUNIT_EXPECT_EQ(test, err, 0); + dma_resv_unlock(bo_mock->base.resv); + + bo_val = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + bo_val->type = bo_type; + + ttm_bo_reserve(bo_val, false, false, NULL); + err = ttm_bo_validate(bo_val, placement_tt, &ctx_val); + ttm_bo_unreserve(bo_val); + + KUNIT_EXPECT_EQ(test, err, 0); + + 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); +} + +static struct kunit_case ttm_bo_validate_test_cases[] = { + KUNIT_CASE_PARAM(ttm_bo_init_reserved_sys_man, ttm_bo_types_gen_params), + KUNIT_CASE_PARAM(ttm_bo_init_reserved_mock_man, ttm_bo_types_gen_params), + KUNIT_CASE(ttm_bo_init_reserved_resv), + KUNIT_CASE_PARAM(ttm_bo_validate_basic, ttm_bo_types_gen_params), + KUNIT_CASE(ttm_bo_validate_invalid_placement), + KUNIT_CASE_PARAM(ttm_bo_validate_same_placement, + ttm_bo_validate_mem_gen_params), + KUNIT_CASE(ttm_bo_validate_failed_alloc), + KUNIT_CASE(ttm_bo_validate_pinned), + KUNIT_CASE(ttm_bo_validate_busy_placement), + KUNIT_CASE_PARAM(ttm_bo_validate_multihop, ttm_bo_types_gen_params), + KUNIT_CASE_PARAM(ttm_bo_validate_no_placement_signaled, + ttm_bo_no_placement_gen_params), + KUNIT_CASE_PARAM(ttm_bo_validate_no_placement_not_signaled, + ttm_bo_types_gen_params), + KUNIT_CASE(ttm_bo_validate_move_fence_signaled), + KUNIT_CASE_PARAM(ttm_bo_validate_move_fence_not_signaled, + ttm_bo_validate_wait_gen_params), + KUNIT_CASE(ttm_bo_validate_swapout), + KUNIT_CASE(ttm_bo_validate_happy_evict), + KUNIT_CASE(ttm_bo_validate_all_pinned_evict), + KUNIT_CASE(ttm_bo_validate_allowed_only_evict), + KUNIT_CASE(ttm_bo_validate_deleted_evict), + KUNIT_CASE(ttm_bo_validate_busy_domain_evict), + KUNIT_CASE(ttm_bo_validate_evict_gutting), + KUNIT_CASE(ttm_bo_validate_recrusive_evict), + {} +}; + +static struct kunit_suite ttm_bo_validate_test_suite = { + .name = "ttm_bo_validate", + .init = ttm_test_devices_all_init, + .exit = ttm_test_devices_fini, + .test_cases = ttm_bo_validate_test_cases, +}; + +kunit_test_suites(&ttm_bo_validate_test_suite); + +MODULE_DESCRIPTION("KUnit tests for ttm_bo APIs"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_device_test.c b/drivers/gpu/drm/ttm/tests/ttm_device_test.c index 19eaff22e6ae..1621903818e5 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_device_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_device_test.c @@ -209,4 +209,5 @@ static struct kunit_suite ttm_device_test_suite = { kunit_test_suites(&ttm_device_test_suite); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for ttm_device APIs"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c index 7b7c1fa805fc..b91c13f46225 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c +++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c @@ -6,8 +6,43 @@ #include "ttm_kunit_helpers.h" -static struct ttm_tt *ttm_tt_simple_create(struct ttm_buffer_object *bo, - uint32_t page_flags) +static const struct ttm_place sys_place = { + .fpfn = 0, + .lpfn = 0, + .mem_type = TTM_PL_SYSTEM, + .flags = TTM_PL_FLAG_FALLBACK, +}; + +static const struct ttm_place mock1_place = { + .fpfn = 0, + .lpfn = 0, + .mem_type = TTM_PL_MOCK1, + .flags = TTM_PL_FLAG_FALLBACK, +}; + +static const struct ttm_place mock2_place = { + .fpfn = 0, + .lpfn = 0, + .mem_type = TTM_PL_MOCK2, + .flags = TTM_PL_FLAG_FALLBACK, +}; + +static struct ttm_placement sys_placement = { + .num_placement = 1, + .placement = &sys_place, +}; + +static struct ttm_placement bad_placement = { + .num_placement = 1, + .placement = &mock1_place, +}; + +static struct ttm_placement mock_placement = { + .num_placement = 1, + .placement = &mock2_place, +}; + +static struct ttm_tt *ttm_tt_simple_create(struct ttm_buffer_object *bo, u32 page_flags) { struct ttm_tt *tt; @@ -22,13 +57,84 @@ static void ttm_tt_simple_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) kfree(ttm); } -static void dummy_ttm_bo_destroy(struct ttm_buffer_object *bo) +static int mock_move(struct ttm_buffer_object *bo, bool evict, + struct ttm_operation_ctx *ctx, + struct ttm_resource *new_mem, + struct ttm_place *hop) +{ + struct ttm_resource *old_mem = bo->resource; + + if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM && !bo->ttm)) { + ttm_bo_move_null(bo, new_mem); + return 0; + } + + if (bo->resource->mem_type == TTM_PL_VRAM && + new_mem->mem_type == TTM_PL_SYSTEM) { + hop->mem_type = TTM_PL_TT; + hop->flags = TTM_PL_FLAG_TEMPORARY; + hop->fpfn = 0; + hop->lpfn = 0; + return -EMULTIHOP; + } + + if ((old_mem->mem_type == TTM_PL_SYSTEM && + new_mem->mem_type == TTM_PL_TT) || + (old_mem->mem_type == TTM_PL_TT && + new_mem->mem_type == TTM_PL_SYSTEM)) { + ttm_bo_move_null(bo, new_mem); + return 0; + } + + return ttm_bo_move_memcpy(bo, ctx, new_mem); +} + +static void mock_evict_flags(struct ttm_buffer_object *bo, + struct ttm_placement *placement) { + switch (bo->resource->mem_type) { + case TTM_PL_VRAM: + case TTM_PL_SYSTEM: + *placement = sys_placement; + break; + case TTM_PL_TT: + *placement = mock_placement; + break; + case TTM_PL_MOCK1: + /* Purge objects coming from this domain */ + break; + } +} + +static void bad_evict_flags(struct ttm_buffer_object *bo, + struct ttm_placement *placement) +{ + *placement = bad_placement; +} + +static int ttm_device_kunit_init_with_funcs(struct ttm_test_devices *priv, + struct ttm_device *ttm, + bool use_dma_alloc, + bool use_dma32, + struct ttm_device_funcs *funcs) +{ + struct drm_device *drm = priv->drm; + int err; + + err = ttm_device_init(ttm, funcs, drm->dev, + drm->anon_inode->i_mapping, + drm->vma_offset_manager, + use_dma_alloc, use_dma32); + + return err; } struct ttm_device_funcs ttm_dev_funcs = { .ttm_tt_create = ttm_tt_simple_create, .ttm_tt_destroy = ttm_tt_simple_destroy, + .move = mock_move, + .eviction_valuable = ttm_bo_eviction_valuable, + .evict_flags = mock_evict_flags, }; EXPORT_SYMBOL_GPL(ttm_dev_funcs); @@ -37,21 +143,34 @@ int ttm_device_kunit_init(struct ttm_test_devices *priv, bool use_dma_alloc, bool use_dma32) { - struct drm_device *drm = priv->drm; - int err; + return ttm_device_kunit_init_with_funcs(priv, ttm, use_dma_alloc, + use_dma32, &ttm_dev_funcs); +} +EXPORT_SYMBOL_GPL(ttm_device_kunit_init); - err = ttm_device_init(ttm, &ttm_dev_funcs, drm->dev, - drm->anon_inode->i_mapping, - drm->vma_offset_manager, - use_dma_alloc, use_dma32); +struct ttm_device_funcs ttm_dev_funcs_bad_evict = { + .ttm_tt_create = ttm_tt_simple_create, + .ttm_tt_destroy = ttm_tt_simple_destroy, + .move = mock_move, + .eviction_valuable = ttm_bo_eviction_valuable, + .evict_flags = bad_evict_flags, +}; +EXPORT_SYMBOL_GPL(ttm_dev_funcs_bad_evict); - return err; +int ttm_device_kunit_init_bad_evict(struct ttm_test_devices *priv, + struct ttm_device *ttm, + bool use_dma_alloc, + bool use_dma32) +{ + return ttm_device_kunit_init_with_funcs(priv, ttm, use_dma_alloc, + use_dma32, &ttm_dev_funcs_bad_evict); } -EXPORT_SYMBOL_GPL(ttm_device_kunit_init); +EXPORT_SYMBOL_GPL(ttm_device_kunit_init_bad_evict); struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test, struct ttm_test_devices *devs, - size_t size) + size_t size, + struct dma_resv *obj) { struct drm_gem_object gem_obj = { }; struct ttm_buffer_object *bo; @@ -61,6 +180,10 @@ struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test, KUNIT_ASSERT_NOT_NULL(test, bo); bo->base = gem_obj; + + if (obj) + bo->base.resv = obj; + err = drm_gem_object_init(devs->drm, &bo->base, size); KUNIT_ASSERT_EQ(test, err, 0); @@ -73,8 +196,7 @@ struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test, } EXPORT_SYMBOL_GPL(ttm_bo_kunit_init); -struct ttm_place *ttm_place_kunit_init(struct kunit *test, - uint32_t mem_type, uint32_t flags) +struct ttm_place *ttm_place_kunit_init(struct kunit *test, u32 mem_type, u32 flags) { struct ttm_place *place; @@ -88,6 +210,12 @@ struct ttm_place *ttm_place_kunit_init(struct kunit *test, } EXPORT_SYMBOL_GPL(ttm_place_kunit_init); +void dummy_ttm_bo_destroy(struct ttm_buffer_object *bo) +{ + drm_gem_object_release(&bo->base); +} +EXPORT_SYMBOL_GPL(dummy_ttm_bo_destroy); + struct ttm_test_devices *ttm_test_devices_basic(struct kunit *test) { struct ttm_test_devices *devs; @@ -98,6 +226,9 @@ struct ttm_test_devices *ttm_test_devices_basic(struct kunit *test) devs->dev = drm_kunit_helper_alloc_device(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, devs->dev); + /* Set mask for alloc_coherent mappings to enable ttm_pool_alloc testing */ + devs->dev->coherent_dma_mask = -1; + devs->drm = __drm_kunit_helper_alloc_drm_device(test, devs->dev, sizeof(*devs->drm), 0, DRIVER_GEM); @@ -150,10 +281,25 @@ int ttm_test_devices_init(struct kunit *test) } EXPORT_SYMBOL_GPL(ttm_test_devices_init); +int ttm_test_devices_all_init(struct kunit *test) +{ + struct ttm_test_devices *priv; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, priv); + + priv = ttm_test_devices_all(test); + test->priv = priv; + + return 0; +} +EXPORT_SYMBOL_GPL(ttm_test_devices_all_init); + void ttm_test_devices_fini(struct kunit *test) { ttm_test_devices_put(test, test->priv); } EXPORT_SYMBOL_GPL(ttm_test_devices_fini); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("TTM KUnit test helper functions"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h index 2f51c833a536..c7da23232ffa 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h +++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h @@ -13,7 +13,11 @@ #include <drm/drm_kunit_helpers.h> #include <kunit/test.h> +#define TTM_PL_MOCK1 (TTM_PL_PRIV + 1) +#define TTM_PL_MOCK2 (TTM_PL_PRIV + 2) + extern struct ttm_device_funcs ttm_dev_funcs; +extern struct ttm_device_funcs ttm_dev_funcs_bad_evict; struct ttm_test_devices { struct drm_device *drm; @@ -26,11 +30,17 @@ int ttm_device_kunit_init(struct ttm_test_devices *priv, struct ttm_device *ttm, bool use_dma_alloc, bool use_dma32); +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_buffer_object *ttm_bo_kunit_init(struct kunit *test, struct ttm_test_devices *devs, - size_t size); -struct ttm_place *ttm_place_kunit_init(struct kunit *test, - uint32_t mem_type, uint32_t flags); + size_t size, + struct dma_resv *obj); +struct ttm_place *ttm_place_kunit_init(struct kunit *test, u32 mem_type, + u32 flags); +void dummy_ttm_bo_destroy(struct ttm_buffer_object *bo); struct ttm_test_devices *ttm_test_devices_basic(struct kunit *test); struct ttm_test_devices *ttm_test_devices_all(struct kunit *test); @@ -39,6 +49,7 @@ void ttm_test_devices_put(struct kunit *test, struct ttm_test_devices *devs); /* Generic init/fini for tests that only need DRM/TTM devices */ int ttm_test_devices_init(struct kunit *test); +int ttm_test_devices_all_init(struct kunit *test); void ttm_test_devices_fini(struct kunit *test); #endif // TTM_KUNIT_HELPERS_H diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c new file mode 100644 index 000000000000..f6d1c8a2845d --- /dev/null +++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 AND MIT +/* + * Copyright © 2023 Intel Corporation + */ +#include <drm/ttm/ttm_resource.h> +#include <drm/ttm/ttm_device.h> +#include <drm/ttm/ttm_placement.h> + +#include "ttm_mock_manager.h" + +static inline struct ttm_mock_manager * +to_mock_mgr(struct ttm_resource_manager *man) +{ + return container_of(man, struct ttm_mock_manager, man); +} + +static inline struct ttm_mock_resource * +to_mock_mgr_resource(struct ttm_resource *res) +{ + return container_of(res, struct ttm_mock_resource, base); +} + +static int ttm_mock_manager_alloc(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + struct ttm_mock_manager *manager = to_mock_mgr(man); + struct ttm_mock_resource *mock_res; + struct drm_buddy *mm = &manager->mm; + u64 lpfn, fpfn, alloc_size; + int err; + + mock_res = kzalloc(sizeof(*mock_res), GFP_KERNEL); + + if (!mock_res) + return -ENOMEM; + + fpfn = 0; + lpfn = man->size; + + ttm_resource_init(bo, place, &mock_res->base); + INIT_LIST_HEAD(&mock_res->blocks); + + if (place->flags & TTM_PL_FLAG_TOPDOWN) + mock_res->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION; + + if (place->flags & TTM_PL_FLAG_CONTIGUOUS) + mock_res->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION; + + alloc_size = (uint64_t)mock_res->base.size; + mutex_lock(&manager->lock); + err = drm_buddy_alloc_blocks(mm, fpfn, lpfn, alloc_size, + manager->default_page_size, + &mock_res->blocks, + mock_res->flags); + + if (err) + goto error_free_blocks; + mutex_unlock(&manager->lock); + + *res = &mock_res->base; + return 0; + +error_free_blocks: + drm_buddy_free_list(mm, &mock_res->blocks, 0); + ttm_resource_fini(man, &mock_res->base); + mutex_unlock(&manager->lock); + + return err; +} + +static void ttm_mock_manager_free(struct ttm_resource_manager *man, + struct ttm_resource *res) +{ + struct ttm_mock_manager *manager = to_mock_mgr(man); + struct ttm_mock_resource *mock_res = to_mock_mgr_resource(res); + struct drm_buddy *mm = &manager->mm; + + mutex_lock(&manager->lock); + drm_buddy_free_list(mm, &mock_res->blocks, 0); + mutex_unlock(&manager->lock); + + ttm_resource_fini(man, res); + kfree(mock_res); +} + +static const struct ttm_resource_manager_func ttm_mock_manager_funcs = { + .alloc = ttm_mock_manager_alloc, + .free = ttm_mock_manager_free, +}; + +int ttm_mock_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size) +{ + struct ttm_mock_manager *manager; + struct ttm_resource_manager *base; + int err; + + manager = kzalloc(sizeof(*manager), GFP_KERNEL); + if (!manager) + return -ENOMEM; + + mutex_init(&manager->lock); + + err = drm_buddy_init(&manager->mm, size, PAGE_SIZE); + + if (err) { + kfree(manager); + return err; + } + + manager->default_page_size = PAGE_SIZE; + base = &manager->man; + base->func = &ttm_mock_manager_funcs; + base->use_tt = true; + + ttm_resource_manager_init(base, bdev, size); + ttm_set_driver_manager(bdev, mem_type, base); + ttm_resource_manager_set_used(base, true); + + return 0; +} +EXPORT_SYMBOL_GPL(ttm_mock_manager_init); + +void ttm_mock_manager_fini(struct ttm_device *bdev, u32 mem_type) +{ + struct ttm_resource_manager *man; + struct ttm_mock_manager *mock_man; + int err; + + man = ttm_manager_type(bdev, mem_type); + mock_man = to_mock_mgr(man); + + err = ttm_resource_manager_evict_all(bdev, man); + if (err) + return; + + ttm_resource_manager_set_used(man, false); + + mutex_lock(&mock_man->lock); + drm_buddy_fini(&mock_man->mm); + mutex_unlock(&mock_man->lock); + + ttm_set_driver_manager(bdev, mem_type, NULL); +} +EXPORT_SYMBOL_GPL(ttm_mock_manager_fini); + +static int ttm_bad_manager_alloc(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + return -ENOSPC; +} + +static int ttm_busy_manager_alloc(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + return -EBUSY; +} + +static void ttm_bad_manager_free(struct ttm_resource_manager *man, + struct ttm_resource *res) +{ +} + +static bool ttm_bad_manager_compatible(struct ttm_resource_manager *man, + struct ttm_resource *res, + const struct ttm_place *place, + size_t size) +{ + return true; +} + +static const struct ttm_resource_manager_func ttm_bad_manager_funcs = { + .alloc = ttm_bad_manager_alloc, + .free = ttm_bad_manager_free, + .compatible = ttm_bad_manager_compatible +}; + +static const struct ttm_resource_manager_func ttm_bad_busy_manager_funcs = { + .alloc = ttm_busy_manager_alloc, + .free = ttm_bad_manager_free, + .compatible = ttm_bad_manager_compatible +}; + +int ttm_bad_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size) +{ + struct ttm_resource_manager *man; + + man = kzalloc(sizeof(*man), GFP_KERNEL); + if (!man) + return -ENOMEM; + + man->func = &ttm_bad_manager_funcs; + + ttm_resource_manager_init(man, bdev, size); + ttm_set_driver_manager(bdev, mem_type, man); + ttm_resource_manager_set_used(man, true); + + return 0; +} +EXPORT_SYMBOL_GPL(ttm_bad_manager_init); + +int ttm_busy_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size) +{ + struct ttm_resource_manager *man; + + ttm_bad_manager_init(bdev, mem_type, size); + man = ttm_manager_type(bdev, mem_type); + + man->func = &ttm_bad_busy_manager_funcs; + + return 0; +} +EXPORT_SYMBOL_GPL(ttm_busy_manager_init); + +void ttm_bad_manager_fini(struct ttm_device *bdev, uint32_t mem_type) +{ + struct ttm_resource_manager *man; + + man = ttm_manager_type(bdev, mem_type); + + ttm_resource_manager_set_used(man, false); + ttm_set_driver_manager(bdev, mem_type, NULL); + + kfree(man); +} +EXPORT_SYMBOL_GPL(ttm_bad_manager_fini); + +MODULE_DESCRIPTION("KUnit tests for ttm with mock resource managers"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h new file mode 100644 index 000000000000..e4c95f86a467 --- /dev/null +++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 AND MIT */ +/* + * Copyright © 2023 Intel Corporation + */ +#ifndef TTM_MOCK_MANAGER_H +#define TTM_MOCK_MANAGER_H + +#include <drm/drm_buddy.h> + +struct ttm_mock_manager { + struct ttm_resource_manager man; + struct drm_buddy mm; + u64 default_page_size; + /* protects allocations of mock buffer objects */ + struct mutex lock; +}; + +struct ttm_mock_resource { + struct ttm_resource base; + struct list_head blocks; + unsigned long flags; +}; + +int ttm_mock_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size); +int ttm_bad_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size); +int ttm_busy_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size); +void ttm_mock_manager_fini(struct ttm_device *bdev, u32 mem_type); +void ttm_bad_manager_fini(struct ttm_device *bdev, u32 mem_type); + +#endif // TTM_MOCK_MANAGER_H diff --git a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c index 0a3fede84da9..8ade53371f72 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c @@ -48,7 +48,7 @@ static void ttm_pool_test_fini(struct kunit *test) } static struct ttm_tt *ttm_tt_kunit_init(struct kunit *test, - uint32_t page_flags, + u32 page_flags, enum ttm_caching caching, size_t size) { @@ -57,7 +57,7 @@ static struct ttm_tt *ttm_tt_kunit_init(struct kunit *test, struct ttm_tt *tt; int err; - bo = ttm_bo_kunit_init(test, priv->devs, size); + bo = ttm_bo_kunit_init(test, priv->devs, size, NULL); KUNIT_ASSERT_NOT_NULL(test, bo); priv->mock_bo = bo; @@ -209,7 +209,7 @@ static void ttm_pool_alloc_basic_dma_addr(struct kunit *test) tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, devs, size); + bo = ttm_bo_kunit_init(test, devs, size, NULL); KUNIT_ASSERT_NOT_NULL(test, bo); err = ttm_sg_tt_init(tt, bo, 0, caching); @@ -433,4 +433,5 @@ static struct kunit_suite ttm_pool_test_suite = { kunit_test_suites(&ttm_pool_test_suite); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for ttm_pool APIs"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c index 029e1f094bb0..e6ea2bd01f07 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c @@ -11,8 +11,8 @@ struct ttm_resource_test_case { const char *description; - uint32_t mem_type; - uint32_t flags; + u32 mem_type; + u32 flags; }; struct ttm_resource_test_priv { @@ -47,20 +47,20 @@ static void ttm_resource_test_fini(struct kunit *test) static void ttm_init_test_mocks(struct kunit *test, struct ttm_resource_test_priv *priv, - uint32_t mem_type, uint32_t flags) + u32 mem_type, u32 flags) { size_t size = RES_SIZE; /* Make sure we have what we need for a good BO mock */ KUNIT_ASSERT_NOT_NULL(test, priv->devs->ttm_dev); - priv->bo = ttm_bo_kunit_init(test, priv->devs, size); + priv->bo = ttm_bo_kunit_init(test, priv->devs, size, NULL); priv->place = ttm_place_kunit_init(test, mem_type, flags); } static void ttm_init_test_manager(struct kunit *test, struct ttm_resource_test_priv *priv, - uint32_t mem_type) + u32 mem_type) { struct ttm_device *ttm_dev = priv->devs->ttm_dev; struct ttm_resource_manager *man; @@ -112,7 +112,7 @@ static void ttm_resource_init_basic(struct kunit *test) struct ttm_buffer_object *bo; struct ttm_place *place; struct ttm_resource_manager *man; - uint64_t expected_usage; + u64 expected_usage; ttm_init_test_mocks(test, priv, params->mem_type, params->flags); bo = priv->bo; @@ -164,18 +164,18 @@ static void ttm_resource_init_pinned(struct kunit *test) res = kunit_kzalloc(test, sizeof(*res), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, res); - KUNIT_ASSERT_TRUE(test, list_empty(&bo->bdev->pinned)); + KUNIT_ASSERT_TRUE(test, list_empty(&bo->bdev->unevictable)); dma_resv_lock(bo->base.resv, NULL); ttm_bo_pin(bo); ttm_resource_init(bo, place, res); - KUNIT_ASSERT_TRUE(test, list_is_singular(&bo->bdev->pinned)); + KUNIT_ASSERT_TRUE(test, list_is_singular(&bo->bdev->unevictable)); ttm_bo_unpin(bo); ttm_resource_fini(man, res); dma_resv_unlock(bo->base.resv); - KUNIT_ASSERT_TRUE(test, list_empty(&bo->bdev->pinned)); + KUNIT_ASSERT_TRUE(test, list_empty(&bo->bdev->unevictable)); } static void ttm_resource_fini_basic(struct kunit *test) @@ -198,7 +198,7 @@ static void ttm_resource_fini_basic(struct kunit *test) ttm_resource_init(bo, place, res); ttm_resource_fini(man, res); - KUNIT_ASSERT_TRUE(test, list_empty(&res->lru)); + KUNIT_ASSERT_TRUE(test, list_empty(&res->lru.link)); KUNIT_ASSERT_EQ(test, man->usage, 0); } @@ -230,7 +230,7 @@ static void ttm_resource_manager_usage_basic(struct kunit *test) struct ttm_buffer_object *bo; struct ttm_place *place; struct ttm_resource_manager *man; - uint64_t actual_usage; + u64 actual_usage; ttm_init_test_mocks(test, priv, TTM_PL_SYSTEM, TTM_PL_FLAG_TOPDOWN); bo = priv->bo; @@ -268,7 +268,7 @@ static void ttm_sys_man_alloc_basic(struct kunit *test) struct ttm_buffer_object *bo; struct ttm_place *place; struct ttm_resource *res; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; int ret; ttm_init_test_mocks(test, priv, mem_type, 0); @@ -293,7 +293,7 @@ static void ttm_sys_man_free_basic(struct kunit *test) struct ttm_buffer_object *bo; struct ttm_place *place; struct ttm_resource *res; - uint32_t mem_type = TTM_PL_SYSTEM; + u32 mem_type = TTM_PL_SYSTEM; ttm_init_test_mocks(test, priv, mem_type, 0); bo = priv->bo; @@ -302,7 +302,7 @@ static void ttm_sys_man_free_basic(struct kunit *test) res = kunit_kzalloc(test, sizeof(*res), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, res); - ttm_resource_alloc(bo, place, &res); + ttm_resource_alloc(bo, place, &res, NULL); man = ttm_manager_type(priv->devs->ttm_dev, mem_type); man->func->free(man, res); @@ -332,4 +332,5 @@ static struct kunit_suite ttm_resource_test_suite = { kunit_test_suites(&ttm_resource_test_suite); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for ttm_resource and ttm_sys_man APIs"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/tests/ttm_tt_test.c b/drivers/gpu/drm/ttm/tests/ttm_tt_test.c index fd4502c18de6..61ec6f580b62 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_tt_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_tt_test.c @@ -11,23 +11,10 @@ struct ttm_tt_test_case { const char *description; - uint32_t size; - uint32_t extra_pages_num; + u32 size; + u32 extra_pages_num; }; -static int ttm_tt_test_init(struct kunit *test) -{ - struct ttm_test_devices *priv; - - priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); - KUNIT_ASSERT_NOT_NULL(test, priv); - - priv = ttm_test_devices_all(test); - test->priv = priv; - - return 0; -} - static const struct ttm_tt_test_case ttm_tt_init_basic_cases[] = { { .description = "Page-aligned size", @@ -54,16 +41,16 @@ static void ttm_tt_init_basic(struct kunit *test) const struct ttm_tt_test_case *params = test->param_value; struct ttm_buffer_object *bo; struct ttm_tt *tt; - uint32_t page_flags = TTM_TT_FLAG_ZERO_ALLOC; + u32 page_flags = TTM_TT_FLAG_ZERO_ALLOC; enum ttm_caching caching = ttm_cached; - uint32_t extra_pages = params->extra_pages_num; + u32 extra_pages = params->extra_pages_num; int num_pages = params->size >> PAGE_SHIFT; int err; tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, test->priv, params->size); + bo = ttm_bo_kunit_init(test, test->priv, params->size, NULL); err = ttm_tt_init(tt, bo, page_flags, caching, extra_pages); KUNIT_ASSERT_EQ(test, err, 0); @@ -82,14 +69,14 @@ static void ttm_tt_init_misaligned(struct kunit *test) struct ttm_buffer_object *bo; struct ttm_tt *tt; enum ttm_caching caching = ttm_cached; - uint32_t size = SZ_8K; + u32 size = SZ_8K; int num_pages = (size + SZ_4K) >> PAGE_SHIFT; int err; tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, test->priv, size); + bo = ttm_bo_kunit_init(test, test->priv, size, NULL); /* Make the object size misaligned */ bo->base.size += 1; @@ -110,7 +97,7 @@ static void ttm_tt_fini_basic(struct kunit *test) tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_tt_init(tt, bo, 0, caching, 0); KUNIT_ASSERT_EQ(test, err, 0); @@ -130,7 +117,7 @@ static void ttm_tt_fini_sg(struct kunit *test) tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_sg_tt_init(tt, bo, 0, caching); KUNIT_ASSERT_EQ(test, err, 0); @@ -151,7 +138,7 @@ static void ttm_tt_fini_shmem(struct kunit *test) tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_tt_init(tt, bo, 0, caching, 0); KUNIT_ASSERT_EQ(test, err, 0); @@ -168,7 +155,7 @@ static void ttm_tt_create_basic(struct kunit *test) struct ttm_buffer_object *bo; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->type = ttm_bo_type_device; dma_resv_lock(bo->base.resv, NULL); @@ -187,7 +174,7 @@ static void ttm_tt_create_invalid_bo_type(struct kunit *test) struct ttm_buffer_object *bo; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->type = ttm_bo_type_sg + 1; dma_resv_lock(bo->base.resv, NULL); @@ -208,7 +195,7 @@ static void ttm_tt_create_ttm_exists(struct kunit *test) tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, tt); - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); err = ttm_tt_init(tt, bo, 0, caching, 0); KUNIT_ASSERT_EQ(test, err, 0); @@ -224,7 +211,7 @@ static void ttm_tt_create_ttm_exists(struct kunit *test) } static struct ttm_tt *ttm_tt_null_create(struct ttm_buffer_object *bo, - uint32_t page_flags) + u32 page_flags) { return NULL; } @@ -239,7 +226,7 @@ static void ttm_tt_create_failed(struct kunit *test) struct ttm_buffer_object *bo; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); /* Update ttm_device_funcs so we don't alloc ttm_tt */ devs->ttm_dev->funcs = &ttm_dev_empty_funcs; @@ -257,7 +244,7 @@ static void ttm_tt_destroy_basic(struct kunit *test) struct ttm_buffer_object *bo; int err; - bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE); + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); dma_resv_lock(bo->base.resv, NULL); err = ttm_tt_create(bo, false); @@ -269,6 +256,120 @@ static void ttm_tt_destroy_basic(struct kunit *test) ttm_tt_destroy(devs->ttm_dev, bo->ttm); } +static void ttm_tt_populate_null_ttm(struct kunit *test) +{ + const struct ttm_test_devices *devs = test->priv; + struct ttm_operation_ctx ctx = { }; + int err; + + err = ttm_tt_populate(devs->ttm_dev, NULL, &ctx); + KUNIT_ASSERT_EQ(test, err, -EINVAL); +} + +static void ttm_tt_populate_populated_ttm(struct kunit *test) +{ + const struct ttm_test_devices *devs = test->priv; + struct ttm_operation_ctx ctx = { }; + struct ttm_buffer_object *bo; + struct ttm_tt *tt; + struct page *populated_page; + int err; + + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + + tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, tt); + + err = ttm_tt_init(tt, bo, 0, ttm_cached, 0); + KUNIT_ASSERT_EQ(test, err, 0); + + err = ttm_tt_populate(devs->ttm_dev, tt, &ctx); + KUNIT_ASSERT_EQ(test, err, 0); + populated_page = *tt->pages; + + err = ttm_tt_populate(devs->ttm_dev, tt, &ctx); + KUNIT_ASSERT_PTR_EQ(test, populated_page, *tt->pages); +} + +static void ttm_tt_unpopulate_basic(struct kunit *test) +{ + const struct ttm_test_devices *devs = test->priv; + struct ttm_operation_ctx ctx = { }; + struct ttm_buffer_object *bo; + struct ttm_tt *tt; + int err; + + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + + tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, tt); + + err = ttm_tt_init(tt, bo, 0, ttm_cached, 0); + KUNIT_ASSERT_EQ(test, err, 0); + + err = ttm_tt_populate(devs->ttm_dev, tt, &ctx); + KUNIT_ASSERT_EQ(test, err, 0); + KUNIT_ASSERT_TRUE(test, ttm_tt_is_populated(tt)); + + ttm_tt_unpopulate(devs->ttm_dev, tt); + KUNIT_ASSERT_FALSE(test, ttm_tt_is_populated(tt)); +} + +static void ttm_tt_unpopulate_empty_ttm(struct kunit *test) +{ + const struct ttm_test_devices *devs = test->priv; + struct ttm_buffer_object *bo; + struct ttm_tt *tt; + int err; + + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + + tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, tt); + + err = ttm_tt_init(tt, bo, 0, ttm_cached, 0); + KUNIT_ASSERT_EQ(test, err, 0); + + ttm_tt_unpopulate(devs->ttm_dev, tt); + /* Expect graceful handling of unpopulated TTs */ +} + +static void ttm_tt_swapin_basic(struct kunit *test) +{ + const struct ttm_test_devices *devs = test->priv; + int expected_num_pages = BO_SIZE >> PAGE_SHIFT; + struct ttm_operation_ctx ctx = { }; + struct ttm_buffer_object *bo; + struct ttm_tt *tt; + int err, num_pages; + + bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); + + tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, tt); + + err = ttm_tt_init(tt, bo, 0, ttm_cached, 0); + KUNIT_ASSERT_EQ(test, err, 0); + + err = ttm_tt_populate(devs->ttm_dev, tt, &ctx); + KUNIT_ASSERT_EQ(test, err, 0); + KUNIT_ASSERT_TRUE(test, ttm_tt_is_populated(tt)); + + num_pages = ttm_tt_swapout(devs->ttm_dev, tt, GFP_KERNEL); + KUNIT_ASSERT_EQ(test, num_pages, expected_num_pages); + KUNIT_ASSERT_NOT_NULL(test, tt->swap_storage); + KUNIT_ASSERT_TRUE(test, tt->page_flags & TTM_TT_FLAG_SWAPPED); + + /* Swapout depopulates TT, allocate pages and then swap them in */ + err = ttm_pool_alloc(&devs->ttm_dev->pool, tt, &ctx); + KUNIT_ASSERT_EQ(test, err, 0); + + err = ttm_tt_swapin(tt); + KUNIT_ASSERT_EQ(test, err, 0); + KUNIT_ASSERT_NULL(test, tt->swap_storage); + KUNIT_ASSERT_FALSE(test, tt->page_flags & TTM_TT_FLAG_SWAPPED); +} + static struct kunit_case ttm_tt_test_cases[] = { KUNIT_CASE_PARAM(ttm_tt_init_basic, ttm_tt_init_basic_gen_params), KUNIT_CASE(ttm_tt_init_misaligned), @@ -280,16 +381,22 @@ static struct kunit_case ttm_tt_test_cases[] = { KUNIT_CASE(ttm_tt_create_ttm_exists), KUNIT_CASE(ttm_tt_create_failed), KUNIT_CASE(ttm_tt_destroy_basic), + KUNIT_CASE(ttm_tt_populate_null_ttm), + KUNIT_CASE(ttm_tt_populate_populated_ttm), + KUNIT_CASE(ttm_tt_unpopulate_basic), + KUNIT_CASE(ttm_tt_unpopulate_empty_ttm), + KUNIT_CASE(ttm_tt_swapin_basic), {} }; static struct kunit_suite ttm_tt_test_suite = { .name = "ttm_tt", - .init = ttm_tt_test_init, + .init = ttm_test_devices_all_init, .exit = ttm_test_devices_fini, .test_cases = ttm_tt_test_cases, }; kunit_test_suites(&ttm_tt_test_suite); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for ttm_tt APIs"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c new file mode 100644 index 000000000000..ffaab68bd5dd --- /dev/null +++ b/drivers/gpu/drm/ttm/ttm_backup.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include <drm/ttm/ttm_backup.h> +#include <linux/page-flags.h> +#include <linux/swap.h> + +/* + * Need to map shmem indices to handle since a handle value + * of 0 means error, following the swp_entry_t convention. + */ +static unsigned long ttm_backup_shmem_idx_to_handle(pgoff_t idx) +{ + return (unsigned long)idx + 1; +} + +static pgoff_t ttm_backup_handle_to_shmem_idx(pgoff_t handle) +{ + return handle - 1; +} + +/** + * ttm_backup_drop() - release memory associated with a handle + * @backup: The struct backup pointer used to obtain the handle + * @handle: The handle obtained from the @backup_page function. + */ +void ttm_backup_drop(struct file *backup, pgoff_t handle) +{ + loff_t start = ttm_backup_handle_to_shmem_idx(handle); + + start <<= PAGE_SHIFT; + shmem_truncate_range(file_inode(backup), start, + start + PAGE_SIZE - 1); +} + +/** + * ttm_backup_copy_page() - Copy the contents of a previously backed + * up page + * @backup: The struct backup pointer used to back up the page. + * @dst: The struct page to copy into. + * @handle: The handle returned when the page was backed up. + * @intr: Try to perform waits interruptible or at least killable. + * + * Return: 0 on success, Negative error code on failure, notably + * -EINTR if @intr was set to true and a signal is pending. + */ +int ttm_backup_copy_page(struct file *backup, struct page *dst, + pgoff_t handle, bool intr) +{ + struct address_space *mapping = backup->f_mapping; + struct folio *from_folio; + pgoff_t idx = ttm_backup_handle_to_shmem_idx(handle); + + from_folio = shmem_read_folio(mapping, idx); + if (IS_ERR(from_folio)) + return PTR_ERR(from_folio); + + copy_highpage(dst, folio_file_page(from_folio, idx)); + folio_put(from_folio); + + return 0; +} + +/** + * ttm_backup_backup_page() - Backup a page + * @backup: The struct backup pointer to use. + * @page: The page to back up. + * @writeback: Whether to perform immediate writeback of the page. + * This may have performance implications. + * @idx: A unique integer for each page and each struct backup. + * This allows the backup implementation to avoid managing + * its address space separately. + * @page_gfp: The gfp value used when the page was allocated. + * This is used for accounting purposes. + * @alloc_gfp: The gfp to be used when allocating memory. + * + * Context: If called from reclaim context, the caller needs to + * assert that the shrinker gfp has __GFP_FS set, to avoid + * deadlocking on lock_page(). If @writeback is set to true and + * called from reclaim context, the caller also needs to assert + * that the shrinker gfp has __GFP_IO set, since without it, + * we're not allowed to start backup IO. + * + * Return: A handle on success. Negative error code on failure. + * + * Note: This function could be extended to back up a folio and + * implementations would then split the folio internally if needed. + * Drawback is that the caller would then have to keep track of + * the folio size- and usage. + */ +s64 +ttm_backup_backup_page(struct file *backup, struct page *page, + bool writeback, pgoff_t idx, gfp_t page_gfp, + gfp_t alloc_gfp) +{ + struct address_space *mapping = backup->f_mapping; + unsigned long handle = 0; + struct folio *to_folio; + int ret; + + to_folio = shmem_read_folio_gfp(mapping, idx, alloc_gfp); + if (IS_ERR(to_folio)) + return PTR_ERR(to_folio); + + folio_mark_accessed(to_folio); + folio_lock(to_folio); + folio_mark_dirty(to_folio); + copy_highpage(folio_file_page(to_folio, idx), page); + handle = ttm_backup_shmem_idx_to_handle(idx); + + if (writeback && !folio_mapped(to_folio) && + folio_clear_dirty_for_io(to_folio)) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = SWAP_CLUSTER_MAX, + .range_start = 0, + .range_end = LLONG_MAX, + .for_reclaim = 1, + }; + folio_set_reclaim(to_folio); + ret = shmem_writeout(to_folio, &wbc); + if (!folio_test_writeback(to_folio)) + folio_clear_reclaim(to_folio); + /* + * If writeout succeeds, it unlocks the folio. errors + * are otherwise dropped, since writeout is only best + * effort here. + */ + if (ret) + folio_unlock(to_folio); + } else { + folio_unlock(to_folio); + } + + folio_put(to_folio); + + return handle; +} + +/** + * ttm_backup_fini() - Free the struct backup resources after last use. + * @backup: Pointer to the struct backup whose resources to free. + * + * After a call to this function, it's illegal to use the @backup pointer. + */ +void ttm_backup_fini(struct file *backup) +{ + fput(backup); +} + +/** + * ttm_backup_bytes_avail() - Report the approximate number of bytes of backup space + * left for backup. + * + * This function is intended also for driver use to indicate whether a + * backup attempt is meaningful. + * + * Return: An approximate size of backup space available. + */ +u64 ttm_backup_bytes_avail(void) +{ + /* + * The idea behind backing up to shmem is that shmem objects may + * eventually be swapped out. So no point swapping out if there + * is no or low swap-space available. But the accuracy of this + * number also depends on shmem actually swapping out backed-up + * shmem objects without too much buffering. + */ + return (u64)get_nr_swap_pages() << PAGE_SHIFT; +} +EXPORT_SYMBOL_GPL(ttm_backup_bytes_avail); + +/** + * ttm_backup_shmem_create() - Create a shmem-based struct backup. + * @size: The maximum size (in bytes) to back up. + * + * Create a backup utilizing shmem objects. + * + * Return: A pointer to a struct file on success, + * an error pointer on error. + */ +struct file *ttm_backup_shmem_create(loff_t size) +{ + return shmem_file_setup("ttm shmem backup", size, 0); +} diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 96a724e8f3ff..08a23ab037cb 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -42,6 +42,7 @@ #include <linux/file.h> #include <linux/module.h> #include <linux/atomic.h> +#include <linux/cgroup_dmem.h> #include <linux/dma-resv.h> #include "ttm_module.h" @@ -139,7 +140,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, goto out_err; if (mem->mem_type != TTM_PL_SYSTEM) { - ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx); + ret = ttm_bo_populate(bo, ctx); if (ret) goto out_err; } @@ -224,80 +225,6 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) dma_resv_iter_end(&cursor); } -/** - * ttm_bo_cleanup_refs - * 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. - * - * @bo: The buffer object to clean-up - * @interruptible: Any sleeps should occur interruptibly. - * @no_wait_gpu: Never wait for gpu. Return -EBUSY instead. - * @unlock_resv: Unlock the reservation lock as well. - */ - -static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, - bool interruptible, bool no_wait_gpu, - bool unlock_resv) -{ - struct dma_resv *resv = &bo->base._resv; - int ret; - - if (dma_resv_test_signaled(resv, DMA_RESV_USAGE_BOOKKEEP)) - ret = 0; - else - ret = -EBUSY; - - if (ret && !no_wait_gpu) { - long lret; - - if (unlock_resv) - dma_resv_unlock(bo->base.resv); - spin_unlock(&bo->bdev->lru_lock); - - lret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, - interruptible, - 30 * HZ); - - if (lret < 0) - return lret; - else if (lret == 0) - return -EBUSY; - - spin_lock(&bo->bdev->lru_lock); - if (unlock_resv && !dma_resv_trylock(bo->base.resv)) { - /* - * We raced, and lost, someone else holds the reservation now, - * and is probably busy in ttm_bo_cleanup_memtype_use. - * - * Even if it's not the case, because we finished waiting any - * delayed destruction would succeed, so just return success - * here. - */ - spin_unlock(&bo->bdev->lru_lock); - return 0; - } - ret = 0; - } - - if (ret) { - if (unlock_resv) - dma_resv_unlock(bo->base.resv); - spin_unlock(&bo->bdev->lru_lock); - return ret; - } - - spin_unlock(&bo->bdev->lru_lock); - ttm_bo_cleanup_memtype_use(bo); - - if (unlock_resv) - dma_resv_unlock(bo->base.resv); - - return 0; -} - /* * Block for the dma_resv object to become idle, lock the buffer and clean up * the resource and tt object. @@ -308,7 +235,7 @@ static void ttm_bo_delayed_delete(struct work_struct *work) bo = container_of(work, typeof(*bo), delayed_delete); - dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, false, + dma_resv_wait_timeout(&bo->base._resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); dma_resv_lock(bo->base.resv, NULL); ttm_bo_cleanup_memtype_use(bo); @@ -343,9 +270,10 @@ static void ttm_bo_release(struct kref *kref) drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node); ttm_mem_io_free(bdev, bo->resource); - if (!dma_resv_test_signaled(bo->base.resv, + if (!dma_resv_test_signaled(&bo->base._resv, DMA_RESV_USAGE_BOOKKEEP) || (want_init_on_free() && (bo->ttm != NULL)) || + bo->type == ttm_bo_type_sg || !dma_resv_trylock(bo->base.resv)) { /* The BO is not idle, resurrect it for delayed destroy */ ttm_bo_flush_all_fences(bo); @@ -402,7 +330,6 @@ void ttm_bo_put(struct ttm_buffer_object *bo) EXPORT_SYMBOL(ttm_bo_put); static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, - struct ttm_resource **mem, struct ttm_operation_ctx *ctx, struct ttm_place *hop) { @@ -469,7 +396,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, if (ret != -EMULTIHOP) break; - ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop); + ret = ttm_bo_bounce_temp_buffer(bo, ctx, &hop); } while (!ret); if (ret) { @@ -506,150 +433,182 @@ bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_eviction_valuable); -/* - * Check the target bo is allowable to be evicted or swapout, including cases: - * - * a. if share same reservation object with ctx->resv, have assumption - * reservation objects should already be locked, so not lock again and - * return true directly when either the opreation allow_reserved_eviction - * or the target bo already is in delayed free list; +/** + * ttm_bo_evict_first() - Evict the first bo on the manager's LRU list. + * @bdev: The ttm device. + * @man: The manager whose bo to evict. + * @ctx: The TTM operation ctx governing the eviction. * - * b. Otherwise, trylock it. + * Return: 0 if successful or the resource disappeared. Negative error code on error. */ -static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, - struct ttm_operation_ctx *ctx, - const struct ttm_place *place, - bool *locked, bool *busy) +int ttm_bo_evict_first(struct ttm_device *bdev, struct ttm_resource_manager *man, + struct ttm_operation_ctx *ctx) { - bool ret = false; + struct ttm_resource_cursor cursor; + struct ttm_buffer_object *bo; + struct ttm_resource *res; + unsigned int mem_type; + int ret = 0; - if (bo->pin_count) { - *locked = false; - if (busy) - *busy = false; - return false; + spin_lock(&bdev->lru_lock); + ttm_resource_cursor_init(&cursor, man); + res = ttm_resource_manager_first(&cursor); + ttm_resource_cursor_fini(&cursor); + if (!res) { + ret = -ENOENT; + goto out_no_ref; } + bo = res->bo; + if (!ttm_bo_get_unless_zero(bo)) + goto out_no_ref; + mem_type = res->mem_type; + spin_unlock(&bdev->lru_lock); + ret = ttm_bo_reserve(bo, ctx->interruptible, ctx->no_wait_gpu, NULL); + if (ret) + goto out_no_lock; + if (!bo->resource || bo->resource->mem_type != mem_type) + goto out_bo_moved; - if (bo->base.resv == ctx->resv) { - dma_resv_assert_held(bo->base.resv); - if (ctx->allow_res_evict) - ret = true; - *locked = false; - if (busy) - *busy = false; + if (bo->deleted) { + ret = ttm_bo_wait_ctx(bo, ctx); + if (!ret) + ttm_bo_cleanup_memtype_use(bo); } else { - ret = dma_resv_trylock(bo->base.resv); - *locked = ret; - if (busy) - *busy = !ret; - } - - if (ret && place && (bo->resource->mem_type != place->mem_type || - !bo->bdev->funcs->eviction_valuable(bo, place))) { - ret = false; - if (*locked) { - dma_resv_unlock(bo->base.resv); - *locked = false; - } + ret = ttm_bo_evict(bo, ctx); } +out_bo_moved: + dma_resv_unlock(bo->base.resv); +out_no_lock: + ttm_bo_put(bo); + return ret; +out_no_ref: + spin_unlock(&bdev->lru_lock); return ret; } /** - * ttm_mem_evict_wait_busy - wait for a busy BO to become available - * - * @busy_bo: BO which couldn't be locked with trylock - * @ctx: operation context - * @ticket: acquire ticket - * - * Try to lock a busy buffer object to avoid failing eviction. + * struct ttm_bo_evict_walk - Parameters for the evict walk. */ -static int ttm_mem_evict_wait_busy(struct ttm_buffer_object *busy_bo, - struct ttm_operation_ctx *ctx, - struct ww_acquire_ctx *ticket) +struct ttm_bo_evict_walk { + /** @walk: The walk base parameters. */ + struct ttm_lru_walk walk; + /** @place: The place passed to the resource allocation. */ + const struct ttm_place *place; + /** @evictor: The buffer object we're trying to make room for. */ + struct ttm_buffer_object *evictor; + /** @res: The allocated resource if any. */ + struct ttm_resource **res; + /** @evicted: Number of successful evictions. */ + unsigned long evicted; + + /** @limit_pool: Which pool limit we should test against */ + struct dmem_cgroup_pool_state *limit_pool; + /** @try_low: Whether we should attempt to evict BO's with low watermark threshold */ + bool try_low; + /** @hit_low: If we cannot evict a bo when @try_low is false (first pass) */ + bool hit_low; +}; + +static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) { - int r; + struct ttm_bo_evict_walk *evict_walk = + container_of(walk, typeof(*evict_walk), walk); + s64 lret; - if (!busy_bo || !ticket) - return -EBUSY; + if (!dmem_cgroup_state_evict_valuable(evict_walk->limit_pool, bo->resource->css, + evict_walk->try_low, &evict_walk->hit_low)) + return 0; - if (ctx->interruptible) - r = dma_resv_lock_interruptible(busy_bo->base.resv, - ticket); - else - r = dma_resv_lock(busy_bo->base.resv, ticket); + if (bo->pin_count || !bo->bdev->funcs->eviction_valuable(bo, evict_walk->place)) + return 0; - /* - * TODO: It would be better to keep the BO locked until allocation is at - * least tried one more time, but that would mean a much larger rework - * of TTM. - */ - if (!r) - dma_resv_unlock(busy_bo->base.resv); + if (bo->deleted) { + lret = ttm_bo_wait_ctx(bo, walk->ctx); + if (!lret) + ttm_bo_cleanup_memtype_use(bo); + } else { + lret = ttm_bo_evict(bo, walk->ctx); + } - return r == -EDEADLK ? -EBUSY : r; -} + if (lret) + goto out; -int ttm_mem_evict_first(struct ttm_device *bdev, - struct ttm_resource_manager *man, - const struct ttm_place *place, - struct ttm_operation_ctx *ctx, - struct ww_acquire_ctx *ticket) -{ - struct ttm_buffer_object *bo = NULL, *busy_bo = NULL; - struct ttm_resource_cursor cursor; - struct ttm_resource *res; - bool locked = false; - int ret; + evict_walk->evicted++; + if (evict_walk->res) + lret = ttm_resource_alloc(evict_walk->evictor, evict_walk->place, + evict_walk->res, NULL); + if (lret == 0) + return 1; +out: + /* Errors that should terminate the walk. */ + if (lret == -ENOSPC) + return -EBUSY; - spin_lock(&bdev->lru_lock); - ttm_resource_manager_for_each_res(man, &cursor, res) { - bool busy; - - if (!ttm_bo_evict_swapout_allowable(res->bo, ctx, place, - &locked, &busy)) { - if (busy && !busy_bo && ticket != - dma_resv_locking_ctx(res->bo->base.resv)) - busy_bo = res->bo; - continue; - } + return lret; +} - if (ttm_bo_get_unless_zero(res->bo)) { - bo = res->bo; - break; - } - if (locked) - dma_resv_unlock(res->bo->base.resv); +static const struct ttm_lru_walk_ops ttm_evict_walk_ops = { + .process_bo = ttm_bo_evict_cb, +}; + +static int ttm_bo_evict_alloc(struct ttm_device *bdev, + struct ttm_resource_manager *man, + const struct ttm_place *place, + struct ttm_buffer_object *evictor, + struct ttm_operation_ctx *ctx, + struct ww_acquire_ctx *ticket, + struct ttm_resource **res, + struct dmem_cgroup_pool_state *limit_pool) +{ + struct ttm_bo_evict_walk evict_walk = { + .walk = { + .ops = &ttm_evict_walk_ops, + .ctx = ctx, + .ticket = ticket, + }, + .place = place, + .evictor = evictor, + .res = res, + .limit_pool = limit_pool, + }; + s64 lret; + + evict_walk.walk.trylock_only = true; + lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1); + + /* One more attempt if we hit low limit? */ + if (!lret && evict_walk.hit_low) { + evict_walk.try_low = true; + lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1); } + if (lret || !ticket) + goto out; - if (!bo) { - if (busy_bo && !ttm_bo_get_unless_zero(busy_bo)) - busy_bo = NULL; - spin_unlock(&bdev->lru_lock); - ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket); - if (busy_bo) - ttm_bo_put(busy_bo); - return ret; - } + /* Reset low limit */ + evict_walk.try_low = evict_walk.hit_low = false; + /* If ticket-locking, repeat while making progress. */ + evict_walk.walk.trylock_only = false; - if (bo->deleted) { - ret = ttm_bo_cleanup_refs(bo, ctx->interruptible, - ctx->no_wait_gpu, locked); - ttm_bo_put(bo); - return ret; +retry: + do { + /* The walk may clear the evict_walk.walk.ticket field */ + evict_walk.walk.ticket = ticket; + evict_walk.evicted = 0; + lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1); + } while (!lret && evict_walk.evicted); + + /* We hit the low limit? Try once more */ + if (!lret && evict_walk.hit_low && !evict_walk.try_low) { + evict_walk.try_low = true; + goto retry; } - - spin_unlock(&bdev->lru_lock); - - ret = ttm_bo_evict(bo, ctx); - if (locked) - ttm_bo_unreserve(bo); - else - ttm_bo_move_to_lru_tail_unlocked(bo); - - ttm_bo_put(bo); - return ret; +out: + if (lret < 0) + return lret; + if (lret == 0) + return -EBUSY; + return 0; } /** @@ -666,7 +625,8 @@ void ttm_bo_pin(struct ttm_buffer_object *bo) spin_lock(&bo->bdev->lru_lock); if (bo->resource) ttm_resource_del_bulk_move(bo->resource, bo); - ++bo->pin_count; + if (!bo->pin_count++ && bo->resource) + ttm_resource_move_to_lru_tail(bo->resource); spin_unlock(&bo->bdev->lru_lock); } EXPORT_SYMBOL(ttm_bo_pin); @@ -685,9 +645,10 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo) return; spin_lock(&bo->bdev->lru_lock); - --bo->pin_count; - if (bo->resource) + if (!--bo->pin_count && bo->resource) { ttm_resource_add_bulk_move(bo->resource, bo); + ttm_resource_move_to_lru_tail(bo->resource); + } spin_unlock(&bo->bdev->lru_lock); } EXPORT_SYMBOL(ttm_bo_unpin); @@ -698,7 +659,6 @@ EXPORT_SYMBOL(ttm_bo_unpin); */ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, struct ttm_resource_manager *man, - struct ttm_resource *mem, bool no_wait_gpu) { struct dma_fence *fence; @@ -724,164 +684,117 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, return ret; } -/* - * Repeatedly evict memory from the LRU for @mem_type until we create enough - * space, or we've evicted everything and there isn't enough space. - */ -static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx) -{ - struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - struct ww_acquire_ctx *ticket; - int ret; - - man = ttm_manager_type(bdev, place->mem_type); - ticket = dma_resv_locking_ctx(bo->base.resv); - do { - ret = ttm_resource_alloc(bo, place, mem); - if (likely(!ret)) - break; - if (unlikely(ret != -ENOSPC)) - return ret; - ret = ttm_mem_evict_first(bdev, man, place, ctx, - ticket); - if (unlikely(ret != 0)) - return ret; - } while (1); - - return ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); -} - /** - * ttm_bo_mem_space + * ttm_bo_alloc_resource - Allocate backing store for a BO * - * @bo: Pointer to a struct ttm_buffer_object. the data of which - * we want to allocate space for. - * @placement: Proposed new placement for the buffer object. - * @mem: A struct ttm_resource. + * @bo: Pointer to a struct ttm_buffer_object of which we want a resource for + * @placement: Proposed new placement for the buffer object * @ctx: if and how to sleep, lock buffers and alloc memory + * @force_space: If we should evict buffers to force space + * @res: The resulting struct ttm_resource. * - * Allocate memory space for the buffer object pointed to by @bo, using - * the placement flags in @placement, potentially evicting other idle buffer objects. - * This function may sleep while waiting for space to become available. + * Allocates a resource for the buffer object pointed to by @bo, using the + * placement flags in @placement, potentially evicting other buffer objects when + * @force_space is true. + * This function may sleep while waiting for resources to become available. * Returns: - * -EBUSY: No space available (only if no_wait == 1). + * -EBUSY: No space available (only if no_wait == true). * -ENOSPC: Could not allocate space for the buffer object, either due to * fragmentation or concurrent allocators. * -ERESTARTSYS: An interruptible sleep was interrupted by a signal. */ -int ttm_bo_mem_space(struct ttm_buffer_object *bo, - struct ttm_placement *placement, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx) +static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_operation_ctx *ctx, + bool force_space, + struct ttm_resource **res) { struct ttm_device *bdev = bo->bdev; - bool type_found = false; + struct ww_acquire_ctx *ticket; int i, ret; + ticket = dma_resv_locking_ctx(bo->base.resv); ret = dma_resv_reserve_fences(bo->base.resv, 1); if (unlikely(ret)) return ret; for (i = 0; i < placement->num_placement; ++i) { const struct ttm_place *place = &placement->placement[i]; + struct dmem_cgroup_pool_state *limit_pool = NULL; struct ttm_resource_manager *man; - - if (place->flags & TTM_PL_FLAG_FALLBACK) - continue; + bool may_evict; man = ttm_manager_type(bdev, place->mem_type); if (!man || !ttm_resource_manager_used(man)) continue; - type_found = true; - ret = ttm_resource_alloc(bo, place, mem); - if (ret == -ENOSPC) + if (place->flags & (force_space ? TTM_PL_FLAG_DESIRED : + TTM_PL_FLAG_FALLBACK)) continue; - if (unlikely(ret)) - goto error; - ret = ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); + may_evict = (force_space && place->mem_type != TTM_PL_SYSTEM); + ret = ttm_resource_alloc(bo, place, res, force_space ? &limit_pool : NULL); + if (ret) { + if (ret != -ENOSPC && ret != -EAGAIN) { + dmem_cgroup_pool_state_put(limit_pool); + return ret; + } + if (!may_evict) { + dmem_cgroup_pool_state_put(limit_pool); + continue; + } + + ret = ttm_bo_evict_alloc(bdev, man, place, bo, ctx, + ticket, res, limit_pool); + dmem_cgroup_pool_state_put(limit_pool); + if (ret == -EBUSY) + continue; + if (ret) + return ret; + } + + ret = ttm_bo_add_move_fence(bo, man, ctx->no_wait_gpu); if (unlikely(ret)) { - ttm_resource_free(bo, mem); + ttm_resource_free(bo, res); if (ret == -EBUSY) continue; - goto error; + return ret; } return 0; } - for (i = 0; i < placement->num_placement; ++i) { - const struct ttm_place *place = &placement->placement[i]; - struct ttm_resource_manager *man; - - if (place->flags & TTM_PL_FLAG_DESIRED) - continue; - - man = ttm_manager_type(bdev, place->mem_type); - if (!man || !ttm_resource_manager_used(man)) - continue; - - type_found = true; - ret = ttm_bo_mem_force_space(bo, place, mem, ctx); - if (likely(!ret)) - return 0; - - if (ret && ret != -EBUSY) - goto error; - } - - ret = -ENOSPC; - if (!type_found) { - pr_err(TTM_PFX "No compatible memory type found\n"); - ret = -EINVAL; - } - -error: - return ret; + return -ENOSPC; } -EXPORT_SYMBOL(ttm_bo_mem_space); -static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, - struct ttm_placement *placement, - struct ttm_operation_ctx *ctx) +/* + * ttm_bo_mem_space - Wrapper around ttm_bo_alloc_resource + * + * @bo: Pointer to a struct ttm_buffer_object of which we want a resource for + * @placement: Proposed new placement for the buffer object + * @res: The resulting struct ttm_resource. + * @ctx: if and how to sleep, lock buffers and alloc memory + * + * Tries both idle allocation and forcefully eviction of buffers. See + * ttm_bo_alloc_resource for details. + */ +int ttm_bo_mem_space(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_resource **res, + struct ttm_operation_ctx *ctx) { - struct ttm_resource *mem; - struct ttm_place hop; + bool force_space = false; int ret; - dma_resv_assert_held(bo->base.resv); + do { + ret = ttm_bo_alloc_resource(bo, placement, ctx, + force_space, res); + force_space = !force_space; + } while (ret == -ENOSPC && force_space); - /* - * Determine where to move the buffer. - * - * If driver determines move is going to need - * an extra step then it will return -EMULTIHOP - * and the buffer will be moved to the temporary - * stop and the driver will be called to make - * the second hop. - */ - ret = ttm_bo_mem_space(bo, placement, &mem, ctx); - if (ret) - return ret; -bounce: - ret = ttm_bo_handle_move_mem(bo, mem, false, ctx, &hop); - if (ret == -EMULTIHOP) { - ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop); - if (ret) - goto out; - /* try and move to final place now. */ - goto bounce; - } -out: - if (ret) - ttm_resource_free(bo, &mem); return ret; } +EXPORT_SYMBOL(ttm_bo_mem_space); /** * ttm_bo_validate @@ -902,6 +815,9 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx) { + struct ttm_resource *res; + struct ttm_place hop; + bool force_space; int ret; dma_resv_assert_held(bo->base.resv); @@ -912,20 +828,53 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, if (!placement->num_placement) return ttm_bo_pipeline_gutting(bo); - /* Check whether we need to move buffer. */ - if (bo->resource && ttm_resource_compatible(bo->resource, placement)) - return 0; + force_space = false; + do { + /* Check whether we need to move buffer. */ + if (bo->resource && + ttm_resource_compatible(bo->resource, placement, + force_space)) + return 0; + + /* Moving of pinned BOs is forbidden */ + if (bo->pin_count) + return -EINVAL; + + /* + * Determine where to move the buffer. + * + * If driver determines move is going to need + * an extra step then it will return -EMULTIHOP + * and the buffer will be moved to the temporary + * stop and the driver will be called to make + * the second hop. + */ + ret = ttm_bo_alloc_resource(bo, placement, ctx, force_space, + &res); + force_space = !force_space; + if (ret == -ENOSPC) + continue; + if (ret) + return ret; - /* Moving of pinned BOs is forbidden */ - if (bo->pin_count) - return -EINVAL; +bounce: + ret = ttm_bo_handle_move_mem(bo, res, false, ctx, &hop); + if (ret == -EMULTIHOP) { + ret = ttm_bo_bounce_temp_buffer(bo, ctx, &hop); + /* try and move to final place now. */ + if (!ret) + goto bounce; + } + if (ret) { + ttm_resource_free(bo, &res); + return ret; + } + + } while (ret && force_space); - ret = ttm_bo_move_buffer(bo, placement, ctx); /* For backward compatibility with userspace */ if (ret == -ENOSPC) return -ENOMEM; - if (ret) - return ret; /* * We might need to add a TTM. @@ -1136,12 +1085,27 @@ int ttm_bo_wait_ctx(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) } EXPORT_SYMBOL(ttm_bo_wait_ctx); -int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - gfp_t gfp_flags) +/** + * struct ttm_bo_swapout_walk - Parameters for the swapout walk + */ +struct ttm_bo_swapout_walk { + /** @walk: The walk base parameters. */ + struct ttm_lru_walk walk; + /** @gfp_flags: The gfp flags to use for ttm_tt_swapout() */ + gfp_t gfp_flags; + /** @hit_low: Whether we should attempt to swap BO's with low watermark threshold */ + /** @evict_low: If we cannot swap a bo when @try_low is false (first pass) */ + bool hit_low, evict_low; +}; + +static s64 +ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) { - struct ttm_place place; - bool locked; - long ret; + struct ttm_place place = {.mem_type = bo->resource->mem_type}; + struct ttm_bo_swapout_walk *swapout_walk = + container_of(walk, typeof(*swapout_walk), walk); + struct ttm_operation_ctx *ctx = walk->ctx; + s64 ret; /* * While the bo may already reside in SYSTEM placement, set @@ -1149,28 +1113,29 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, * The driver may use the fact that we're moving from SYSTEM * as an indication that we're about to swap out. */ - memset(&place, 0, sizeof(place)); - place.mem_type = bo->resource->mem_type; - if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) - return -EBUSY; + if (bo->pin_count || !bo->bdev->funcs->eviction_valuable(bo, &place)) { + ret = -EBUSY; + goto out; + } if (!bo->ttm || !ttm_tt_is_populated(bo->ttm) || bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL || - bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED || - !ttm_bo_get_unless_zero(bo)) { - if (locked) - dma_resv_unlock(bo->base.resv); - return -EBUSY; + bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED) { + ret = -EBUSY; + goto out; } if (bo->deleted) { - ret = ttm_bo_cleanup_refs(bo, false, false, locked); - ttm_bo_put(bo); - return ret == -EBUSY ? -ENOSPC : ret; - } + pgoff_t num_pages = bo->ttm->num_pages; - /* TODO: Cleanup the locking */ - spin_unlock(&bo->bdev->lru_lock); + ret = ttm_bo_wait_ctx(bo, ctx); + if (ret) + goto out; + + ttm_bo_cleanup_memtype_use(bo); + ret = num_pages; + goto out; + } /* * Move to system cached @@ -1181,13 +1146,14 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, memset(&hop, 0, sizeof(hop)); place.mem_type = TTM_PL_SYSTEM; - ret = ttm_resource_alloc(bo, &place, &evict_mem); - if (unlikely(ret)) + ret = ttm_resource_alloc(bo, &place, &evict_mem, NULL); + if (ret) goto out; ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); - if (unlikely(ret != 0)) { - WARN(ret == -EMULTIHOP, "Unexpected multihop in swaput - likely driver bug.\n"); + if (ret) { + WARN(ret == -EMULTIHOP, + "Unexpected multihop in swapout - likely driver bug.\n"); ttm_resource_free(bo, &evict_mem); goto out; } @@ -1197,30 +1163,65 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, * Make sure BO is idle. */ ret = ttm_bo_wait_ctx(bo, ctx); - if (unlikely(ret != 0)) + if (ret) goto out; ttm_bo_unmap_virtual(bo); - - /* - * Swap out. Buffer will be swapped in again as soon as - * anyone tries to access a ttm page. - */ if (bo->bdev->funcs->swap_notify) bo->bdev->funcs->swap_notify(bo); - if (ttm_tt_is_populated(bo->ttm)) - ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); + if (ttm_tt_is_populated(bo->ttm)) { + spin_lock(&bo->bdev->lru_lock); + ttm_resource_del_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); + + ret = ttm_tt_swapout(bo->bdev, bo->ttm, swapout_walk->gfp_flags); + + spin_lock(&bo->bdev->lru_lock); + if (ret) + ttm_resource_add_bulk_move(bo->resource, bo); + ttm_resource_move_to_lru_tail(bo->resource); + spin_unlock(&bo->bdev->lru_lock); + } + out: + /* Consider -ENOMEM and -ENOSPC non-fatal. */ + if (ret == -ENOMEM || ret == -ENOSPC) + ret = -EBUSY; - /* - * Unreserve without putting on LRU to avoid swapping out an - * already swapped buffer. - */ - if (locked) - dma_resv_unlock(bo->base.resv); - ttm_bo_put(bo); - return ret == -EBUSY ? -ENOSPC : ret; + return ret; +} + +const struct ttm_lru_walk_ops ttm_swap_ops = { + .process_bo = ttm_bo_swapout_cb, +}; + +/** + * ttm_bo_swapout() - Swap out buffer objects on the LRU list to shmem. + * @bdev: The ttm device. + * @ctx: The ttm_operation_ctx governing the swapout operation. + * @man: The resource manager whose resources / buffer objects are + * goint to be swapped out. + * @gfp_flags: The gfp flags used for shmem page allocations. + * @target: The desired number of bytes to swap out. + * + * Return: The number of bytes actually swapped out, or negative error code + * on error. + */ +s64 ttm_bo_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, + struct ttm_resource_manager *man, gfp_t gfp_flags, + s64 target) +{ + struct ttm_bo_swapout_walk swapout_walk = { + .walk = { + .ops = &ttm_swap_ops, + .ctx = ctx, + .trylock_only = true, + }, + .gfp_flags = gfp_flags, + }; + + return ttm_lru_walk_for_evict(&swapout_walk.walk, bdev, man, target); } void ttm_bo_tt_destroy(struct ttm_buffer_object *bo) @@ -1232,3 +1233,47 @@ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo) ttm_tt_destroy(bo->bdev, bo->ttm); bo->ttm = NULL; } + +/** + * ttm_bo_populate() - Ensure that a buffer object has backing pages + * @bo: The buffer object + * @ctx: The ttm_operation_ctx governing the operation. + * + * For buffer objects in a memory type whose manager uses + * struct ttm_tt for backing pages, ensure those backing pages + * are present and with valid content. The bo's resource is also + * placed on the correct LRU list if it was previously swapped + * out. + * + * Return: 0 if successful, negative error code on failure. + * Note: May return -EINTR or -ERESTARTSYS if @ctx::interruptible + * is set to true. + */ +int ttm_bo_populate(struct ttm_buffer_object *bo, + struct ttm_operation_ctx *ctx) +{ + struct ttm_tt *tt = bo->ttm; + bool swapped; + int ret; + + dma_resv_assert_held(bo->base.resv); + + if (!tt) + return 0; + + swapped = ttm_tt_is_swapped(tt); + ret = ttm_tt_populate(bo->bdev, tt, ctx); + if (ret) + return ret; + + if (swapped && !ttm_tt_is_swapped(tt) && !bo->pin_count && + bo->resource) { + spin_lock(&bo->bdev->lru_lock); + ttm_resource_add_bulk_move(bo->resource, bo); + ttm_resource_move_to_lru_tail(bo->resource); + spin_unlock(&bo->bdev->lru_lock); + } + + return 0; +} +EXPORT_SYMBOL(ttm_bo_populate); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 0b3f4267130c..15cab9bda17f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -28,7 +28,7 @@ /* * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ - +#include <linux/swap.h> #include <linux/vmalloc.h> #include <drm/ttm/ttm_bo.h> @@ -163,7 +163,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, src_man = ttm_manager_type(bdev, src_mem->mem_type); if (ttm && ((ttm->page_flags & TTM_TT_FLAG_SWAPPED) || dst_man->use_tt)) { - ret = ttm_tt_populate(bdev, ttm, ctx); + ret = ttm_bo_populate(bo, ctx); if (ret) return ret; } @@ -350,7 +350,7 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo, BUG_ON(!ttm); - ret = ttm_tt_populate(bo->bdev, ttm, &ctx); + ret = ttm_bo_populate(bo, &ctx); if (ret) return ret; @@ -507,7 +507,7 @@ int ttm_bo_vmap(struct ttm_buffer_object *bo, struct iosys_map *map) pgprot_t prot; void *vaddr; - ret = ttm_tt_populate(bo->bdev, ttm, &ctx); + ret = ttm_bo_populate(bo, &ctx); if (ret) return ret; @@ -768,3 +768,392 @@ error_destroy_tt: ttm_tt_destroy(bo->bdev, ttm); return ret; } + +static bool ttm_lru_walk_trylock(struct ttm_operation_ctx *ctx, + struct ttm_buffer_object *bo, + bool *needs_unlock) +{ + *needs_unlock = false; + + if (dma_resv_trylock(bo->base.resv)) { + *needs_unlock = true; + return true; + } + + if (bo->base.resv == ctx->resv && ctx->allow_res_evict) { + dma_resv_assert_held(bo->base.resv); + return true; + } + + return false; +} + +static int ttm_lru_walk_ticketlock(struct ttm_lru_walk *walk, + struct ttm_buffer_object *bo, + bool *needs_unlock) +{ + struct dma_resv *resv = bo->base.resv; + int ret; + + if (walk->ctx->interruptible) + ret = dma_resv_lock_interruptible(resv, walk->ticket); + else + ret = dma_resv_lock(resv, walk->ticket); + + if (!ret) { + *needs_unlock = true; + /* + * Only a single ticketlock per loop. Ticketlocks are prone + * to return -EDEADLK causing the eviction to fail, so + * after waiting for the ticketlock, revert back to + * trylocking for this walk. + */ + walk->ticket = NULL; + } else if (ret == -EDEADLK) { + /* Caller needs to exit the ww transaction. */ + ret = -ENOSPC; + } + + return ret; +} + +static void ttm_lru_walk_unlock(struct ttm_buffer_object *bo, bool locked) +{ + if (locked) + dma_resv_unlock(bo->base.resv); +} + +/** + * ttm_lru_walk_for_evict() - Perform a LRU list walk, with actions taken on + * valid items. + * @walk: describe the walks and actions taken + * @bdev: The TTM device. + * @man: The struct ttm_resource manager whose LRU lists we're walking. + * @target: The end condition for the walk. + * + * The LRU lists of @man are walk, and for each struct ttm_resource encountered, + * the corresponding ttm_buffer_object is locked and taken a reference on, and + * the LRU lock is dropped. the LRU lock may be dropped before locking and, in + * that case, it's verified that the item actually remains on the LRU list after + * the lock, and that the buffer object didn't switch resource in between. + * + * With a locked object, the actions indicated by @walk->process_bo are + * performed, and after that, the bo is unlocked, the refcount dropped and the + * next struct ttm_resource is processed. Here, the walker relies on + * TTM's restartable LRU list implementation. + * + * Typically @walk->process_bo() would return the number of pages evicted, + * swapped or shrunken, so that when the total exceeds @target, or when the + * LRU list has been walked in full, iteration is terminated. It's also terminated + * on error. Note that the definition of @target is done by the caller, it + * could have a different meaning than the number of pages. + * + * Note that the way dma_resv individualization is done, locking needs to be done + * either with the LRU lock held (trylocking only) or with a reference on the + * object. + * + * Return: The progress made towards target or negative error code on error. + */ +s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev, + struct ttm_resource_manager *man, s64 target) +{ + struct ttm_resource_cursor cursor; + struct ttm_resource *res; + s64 progress = 0; + s64 lret; + + spin_lock(&bdev->lru_lock); + ttm_resource_cursor_init(&cursor, man); + ttm_resource_manager_for_each_res(&cursor, res) { + struct ttm_buffer_object *bo = res->bo; + bool bo_needs_unlock = false; + bool bo_locked = false; + int mem_type; + + /* + * Attempt a trylock before taking a reference on the bo, + * since if we do it the other way around, and the trylock fails, + * we need to drop the lru lock to put the bo. + */ + if (ttm_lru_walk_trylock(walk->ctx, bo, &bo_needs_unlock)) + bo_locked = true; + else if (!walk->ticket || walk->ctx->no_wait_gpu || + walk->trylock_only) + continue; + + if (!ttm_bo_get_unless_zero(bo)) { + ttm_lru_walk_unlock(bo, bo_needs_unlock); + continue; + } + + mem_type = res->mem_type; + spin_unlock(&bdev->lru_lock); + + lret = 0; + if (!bo_locked) + lret = ttm_lru_walk_ticketlock(walk, bo, &bo_needs_unlock); + + /* + * Note that in between the release of the lru lock and the + * ticketlock, the bo may have switched resource, + * and also memory type, since the resource may have been + * freed and allocated again with a different memory type. + * In that case, just skip it. + */ + if (!lret && bo->resource && bo->resource->mem_type == mem_type) + lret = walk->ops->process_bo(walk, bo); + + ttm_lru_walk_unlock(bo, bo_needs_unlock); + ttm_bo_put(bo); + if (lret == -EBUSY || lret == -EALREADY) + lret = 0; + progress = (lret < 0) ? lret : progress + lret; + + spin_lock(&bdev->lru_lock); + if (progress < 0 || progress >= target) + break; + } + ttm_resource_cursor_fini(&cursor); + spin_unlock(&bdev->lru_lock); + + return progress; +} +EXPORT_SYMBOL(ttm_lru_walk_for_evict); + +static void ttm_bo_lru_cursor_cleanup_bo(struct ttm_bo_lru_cursor *curs) +{ + struct ttm_buffer_object *bo = curs->bo; + + if (bo) { + if (curs->needs_unlock) + dma_resv_unlock(bo->base.resv); + ttm_bo_put(bo); + curs->bo = NULL; + } +} + +/** + * ttm_bo_lru_cursor_fini() - Stop using a struct ttm_bo_lru_cursor + * and clean up any iteration it was used for. + * @curs: The cursor. + */ +void ttm_bo_lru_cursor_fini(struct ttm_bo_lru_cursor *curs) +{ + spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock; + + ttm_bo_lru_cursor_cleanup_bo(curs); + spin_lock(lru_lock); + ttm_resource_cursor_fini(&curs->res_curs); + spin_unlock(lru_lock); +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_fini); + +/** + * ttm_bo_lru_cursor_init() - Initialize a struct ttm_bo_lru_cursor + * @curs: The ttm_bo_lru_cursor to initialize. + * @man: The ttm resource_manager whose LRU lists to iterate over. + * @ctx: The ttm_operation_ctx to govern the locking. + * + * Initialize a struct ttm_bo_lru_cursor. Currently only trylocking + * or prelocked buffer objects are available as detailed by + * @ctx::resv and @ctx::allow_res_evict. Ticketlocking is not + * supported. + * + * Return: Pointer to @curs. The function does not fail. + */ +struct ttm_bo_lru_cursor * +ttm_bo_lru_cursor_init(struct ttm_bo_lru_cursor *curs, + struct ttm_resource_manager *man, + struct ttm_operation_ctx *ctx) +{ + memset(curs, 0, sizeof(*curs)); + ttm_resource_cursor_init(&curs->res_curs, man); + curs->ctx = ctx; + + return curs; +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_init); + +static struct ttm_buffer_object * +ttm_bo_from_res_reserved(struct ttm_resource *res, struct ttm_bo_lru_cursor *curs) +{ + struct ttm_buffer_object *bo = res->bo; + + if (!ttm_lru_walk_trylock(curs->ctx, bo, &curs->needs_unlock)) + return NULL; + + if (!ttm_bo_get_unless_zero(bo)) { + if (curs->needs_unlock) + dma_resv_unlock(bo->base.resv); + return NULL; + } + + curs->bo = bo; + return bo; +} + +/** + * ttm_bo_lru_cursor_next() - Continue iterating a manager's LRU lists + * to find and lock buffer object. + * @curs: The cursor initialized using ttm_bo_lru_cursor_init() and + * ttm_bo_lru_cursor_first(). + * + * Return: A pointer to a locked and reference-counted buffer object, + * or NULL if none could be found and looping should be terminated. + */ +struct ttm_buffer_object *ttm_bo_lru_cursor_next(struct ttm_bo_lru_cursor *curs) +{ + spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock; + struct ttm_resource *res = NULL; + struct ttm_buffer_object *bo; + + ttm_bo_lru_cursor_cleanup_bo(curs); + + spin_lock(lru_lock); + for (;;) { + res = ttm_resource_manager_next(&curs->res_curs); + if (!res) + break; + + bo = ttm_bo_from_res_reserved(res, curs); + if (bo) + break; + } + + spin_unlock(lru_lock); + return res ? bo : NULL; +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_next); + +/** + * ttm_bo_lru_cursor_first() - Start iterating a manager's LRU lists + * to find and lock buffer object. + * @curs: The cursor initialized using ttm_bo_lru_cursor_init(). + * + * Return: A pointer to a locked and reference-counted buffer object, + * or NULL if none could be found and looping should be terminated. + */ +struct ttm_buffer_object *ttm_bo_lru_cursor_first(struct ttm_bo_lru_cursor *curs) +{ + spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock; + struct ttm_buffer_object *bo; + struct ttm_resource *res; + + spin_lock(lru_lock); + res = ttm_resource_manager_first(&curs->res_curs); + if (!res) { + spin_unlock(lru_lock); + return NULL; + } + + bo = ttm_bo_from_res_reserved(res, curs); + spin_unlock(lru_lock); + + return bo ? bo : ttm_bo_lru_cursor_next(curs); +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_first); + +/** + * ttm_bo_shrink() - Helper to shrink a ttm buffer object. + * @ctx: The struct ttm_operation_ctx used for the shrinking operation. + * @bo: The buffer object. + * @flags: Flags governing the shrinking behaviour. + * + * The function uses the ttm_tt_back_up functionality to back up or + * purge a struct ttm_tt. If the bo is not in system, it's first + * moved there. + * + * Return: The number of pages shrunken or purged, or + * negative error code on failure. + */ +long ttm_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, + const struct ttm_bo_shrink_flags flags) +{ + static const struct ttm_place sys_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .mem_type = TTM_PL_SYSTEM, + .flags = 0, + }; + static struct ttm_placement sys_placement = { + .num_placement = 1, + .placement = &sys_placement_flags, + }; + struct ttm_tt *tt = bo->ttm; + long lret; + + dma_resv_assert_held(bo->base.resv); + + if (flags.allow_move && bo->resource->mem_type != TTM_PL_SYSTEM) { + int ret = ttm_bo_validate(bo, &sys_placement, ctx); + + /* Consider -ENOMEM and -ENOSPC non-fatal. */ + if (ret) { + if (ret == -ENOMEM || ret == -ENOSPC) + ret = -EBUSY; + return ret; + } + } + + ttm_bo_unmap_virtual(bo); + lret = ttm_bo_wait_ctx(bo, ctx); + if (lret < 0) + return lret; + + if (bo->bulk_move) { + spin_lock(&bo->bdev->lru_lock); + ttm_resource_del_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); + } + + lret = ttm_tt_backup(bo->bdev, tt, (struct ttm_backup_flags) + {.purge = flags.purge, + .writeback = flags.writeback}); + + if (lret <= 0 && bo->bulk_move) { + spin_lock(&bo->bdev->lru_lock); + ttm_resource_add_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); + } + + if (lret < 0 && lret != -EINTR) + return -EBUSY; + + return lret; +} +EXPORT_SYMBOL(ttm_bo_shrink); + +/** + * ttm_bo_shrink_suitable() - Whether a bo is suitable for shinking + * @ctx: The struct ttm_operation_ctx governing the shrinking. + * @bo: The candidate for shrinking. + * + * Check whether the object, given the information available to TTM, + * is suitable for shinking, This function can and should be used + * before attempting to shrink an object. + * + * Return: true if suitable. false if not. + */ +bool ttm_bo_shrink_suitable(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) +{ + return bo->ttm && ttm_tt_is_populated(bo->ttm) && !bo->pin_count && + (!ctx->no_wait_gpu || + dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP)); +} +EXPORT_SYMBOL(ttm_bo_shrink_suitable); + +/** + * ttm_bo_shrink_avoid_wait() - Whether to avoid waiting for GPU + * during shrinking + * + * In some situations, like direct reclaim, waiting (in particular gpu waiting) + * should be avoided since it may stall a system that could otherwise make progress + * shrinking something else less time consuming. + * + * Return: true if gpu waiting should be avoided, false if not. + */ +bool ttm_bo_shrink_avoid_wait(void) +{ + return !current_is_kswapd(); +} +EXPORT_SYMBOL(ttm_bo_shrink_avoid_wait); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 4212b8c91dd4..bdfa6ecfef05 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -58,13 +58,13 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo, if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; - ttm_bo_get(bo); + drm_gem_object_get(&bo->base); mmap_read_unlock(vmf->vma->vm_mm); (void)dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_KERNEL, true, MAX_SCHEDULE_TIMEOUT); dma_resv_unlock(bo->base.resv); - ttm_bo_put(bo); + drm_gem_object_put(&bo->base); return VM_FAULT_RETRY; } @@ -130,12 +130,12 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, */ if (fault_flag_allow_retry_first(vmf->flags)) { if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { - ttm_bo_get(bo); + drm_gem_object_get(&bo->base); mmap_read_unlock(vmf->vma->vm_mm); if (!dma_resv_lock_interruptible(bo->base.resv, NULL)) dma_resv_unlock(bo->base.resv); - ttm_bo_put(bo); + drm_gem_object_put(&bo->base); } return VM_FAULT_RETRY; @@ -220,11 +220,10 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, struct ttm_operation_ctx ctx = { .interruptible = true, .no_wait_gpu = false, - .force_alloc = true }; ttm = bo->ttm; - err = ttm_tt_populate(bdev, bo->ttm, &ctx); + err = ttm_bo_populate(bo, &ctx); if (err) { if (err == -EINTR || err == -ERESTARTSYS || err == -EAGAIN) @@ -353,7 +352,7 @@ void ttm_bo_vm_open(struct vm_area_struct *vma) WARN_ON(bo->bdev->dev_mapping != vma->vm_file->f_mapping); - ttm_bo_get(bo); + drm_gem_object_get(&bo->base); } EXPORT_SYMBOL(ttm_bo_vm_open); @@ -361,7 +360,7 @@ void ttm_bo_vm_close(struct vm_area_struct *vma) { struct ttm_buffer_object *bo = vma->vm_private_data; - ttm_bo_put(bo); + drm_gem_object_put(&bo->base); vma->vm_private_data = NULL; } EXPORT_SYMBOL(ttm_bo_vm_close); @@ -405,13 +404,25 @@ static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo, return len; } -int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, - void *buf, int len, int write) +/** + * ttm_bo_access - Helper to access a buffer object + * + * @bo: ttm buffer object + * @offset: access offset into buffer object + * @buf: pointer to caller memory to read into or write from + * @len: length of access + * @write: write access + * + * Utility function to access a buffer object. Useful when buffer object cannot + * be easily mapped (non-contiguous, non-visible, etc...). Should not directly + * be exported to user space via a peak / poke interface. + * + * Returns: + * @len if successful, negative error code on failure. + */ +int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset, + void *buf, int len, int write) { - struct ttm_buffer_object *bo = vma->vm_private_data; - unsigned long offset = (addr) - vma->vm_start + - ((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node)) - << PAGE_SHIFT); int ret; if (len < 1 || (offset + len) > bo->base.size) @@ -429,8 +440,8 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, break; default: if (bo->bdev->funcs->access_memory) - ret = bo->bdev->funcs->access_memory( - bo, offset, buf, len, write); + ret = bo->bdev->funcs->access_memory + (bo, offset, buf, len, write); else ret = -EIO; } @@ -439,6 +450,18 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, return ret; } +EXPORT_SYMBOL(ttm_bo_access); + +int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + struct ttm_buffer_object *bo = vma->vm_private_data; + unsigned long offset = (addr) - vma->vm_start + + ((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node)) + << PAGE_SHIFT); + + return ttm_bo_access(bo, offset, buf, len, write); +} EXPORT_SYMBOL(ttm_bo_vm_access); static const struct vm_operations_struct ttm_bo_vm_ops = { @@ -462,7 +485,7 @@ int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo) if (is_cow_mapping(vma->vm_flags)) return -EINVAL; - ttm_bo_get(bo); + drm_gem_object_get(&bo->base); /* * Drivers may want to override the vm_ops field. Otherwise we diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 76027960054f..02e797fd1891 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -27,6 +27,7 @@ #define pr_fmt(fmt) "[TTM DEVICE] " fmt +#include <linux/debugfs.h> #include <linux/mm.h> #include <drm/ttm/ttm_bo.h> @@ -147,35 +148,20 @@ int ttm_global_swapout(struct ttm_operation_ctx *ctx, gfp_t gfp_flags) int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, gfp_t gfp_flags) { - struct ttm_resource_cursor cursor; struct ttm_resource_manager *man; - struct ttm_resource *res; unsigned i; - int ret; + s64 lret; - spin_lock(&bdev->lru_lock); for (i = TTM_PL_SYSTEM; i < TTM_NUM_MEM_TYPES; ++i) { man = ttm_manager_type(bdev, i); if (!man || !man->use_tt) continue; - ttm_resource_manager_for_each_res(man, &cursor, res) { - struct ttm_buffer_object *bo = res->bo; - uint32_t num_pages; - - if (!bo || bo->resource != res) - continue; - - num_pages = PFN_UP(bo->base.size); - ret = ttm_bo_swapout(bo, ctx, gfp_flags); - /* ttm_bo_swapout has dropped the lru_lock */ - if (!ret) - return num_pages; - if (ret != -EBUSY) - return ret; - } + lret = ttm_bo_swapout(bdev, ctx, man, gfp_flags, 1); + /* Can be both positive (num_pages) and negative (error) */ + if (lret) + return lret; } - spin_unlock(&bdev->lru_lock); return 0; } EXPORT_SYMBOL(ttm_device_swapout); @@ -230,7 +216,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func bdev->vma_manager = vma_manager; spin_lock_init(&bdev->lru_lock); - INIT_LIST_HEAD(&bdev->pinned); + INIT_LIST_HEAD(&bdev->unevictable); bdev->dev_mapping = mapping; mutex_lock(&ttm_global_mutex); list_add_tail(&bdev->device_list, &glob->device_list); @@ -273,14 +259,14 @@ static void ttm_device_clear_lru_dma_mappings(struct ttm_device *bdev, struct ttm_resource *res; spin_lock(&bdev->lru_lock); - while ((res = list_first_entry_or_null(list, typeof(*res), lru))) { + while ((res = ttm_lru_first_res_or_null(list))) { struct ttm_buffer_object *bo = res->bo; /* Take ref against racing releases once lru_lock is unlocked */ if (!ttm_bo_get_unless_zero(bo)) continue; - list_del_init(&res->lru); + list_del_init(&bo->resource->lru.link); spin_unlock(&bdev->lru_lock); if (bo->ttm) @@ -297,7 +283,7 @@ void ttm_device_clear_dma_mappings(struct ttm_device *bdev) struct ttm_resource_manager *man; unsigned int i, j; - ttm_device_clear_lru_dma_mappings(bdev, &bdev->pinned); + ttm_device_clear_lru_dma_mappings(bdev, &bdev->unevictable); for (i = TTM_PL_SYSTEM; i < TTM_NUM_MEM_TYPES; ++i) { man = ttm_manager_type(bdev, i); diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 6e1fd6985ffc..c2ea865be657 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -41,12 +41,20 @@ #include <asm/set_memory.h> #endif +#include <drm/ttm/ttm_backup.h> #include <drm/ttm/ttm_pool.h> #include <drm/ttm/ttm_tt.h> #include <drm/ttm/ttm_bo.h> #include "ttm_module.h" +#ifdef CONFIG_FAULT_INJECTION +#include <linux/fault-inject.h> +static DECLARE_FAULT_ATTR(backup_fault_inject); +#else +#define should_fail(...) false +#endif + /** * struct ttm_pool_dma - Helper object for coherent DMA mappings * @@ -58,6 +66,52 @@ struct ttm_pool_dma { unsigned long vaddr; }; +/** + * struct ttm_pool_alloc_state - Current state of the tt page allocation process + * @pages: Pointer to the next tt page pointer to populate. + * @caching_divide: Pointer to the first page pointer whose page has a staged but + * not committed caching transition from write-back to @tt_caching. + * @dma_addr: Pointer to the next tt dma_address entry to populate if any. + * @remaining_pages: Remaining pages to populate. + * @tt_caching: The requested cpu-caching for the pages allocated. + */ +struct ttm_pool_alloc_state { + struct page **pages; + struct page **caching_divide; + dma_addr_t *dma_addr; + pgoff_t remaining_pages; + enum ttm_caching tt_caching; +}; + +/** + * struct ttm_pool_tt_restore - State representing restore from backup + * @pool: The pool used for page allocation while restoring. + * @snapshot_alloc: A snapshot of the most recent struct ttm_pool_alloc_state. + * @alloced_page: Pointer to the page most recently allocated from a pool or system. + * @first_dma: The dma address corresponding to @alloced_page if dma_mapping + * is requested. + * @alloced_pages: The number of allocated pages present in the struct ttm_tt + * page vector from this restore session. + * @restored_pages: The number of 4K pages restored for @alloced_page (which + * is typically a multi-order page). + * @page_caching: The struct ttm_tt requested caching + * @order: The order of @alloced_page. + * + * Recovery from backup might fail when we've recovered less than the + * full ttm_tt. In order not to loose any data (yet), keep information + * around that allows us to restart a failed ttm backup recovery. + */ +struct ttm_pool_tt_restore { + struct ttm_pool *pool; + struct ttm_pool_alloc_state snapshot_alloc; + struct page *alloced_page; + dma_addr_t first_dma; + pgoff_t alloced_pages; + pgoff_t restored_pages; + enum ttm_caching page_caching; + unsigned int order; +}; + static unsigned long page_pool_size; MODULE_PARM_DESC(page_pool_size, "Number of pages in the WC/UC/DMA pool"); @@ -91,7 +145,7 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, */ if (order) gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | - __GFP_KSWAPD_RECLAIM; + __GFP_THISNODE; if (!pool->use_dma_alloc) { p = alloc_pages_node(pool->nid, gfp_flags, order); @@ -160,34 +214,33 @@ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching, kfree(dma); } -/* Apply a new caching to an array of pages */ -static int ttm_pool_apply_caching(struct page **first, struct page **last, - enum ttm_caching caching) +/* Apply any cpu-caching deferred during page allocation */ +static int ttm_pool_apply_caching(struct ttm_pool_alloc_state *alloc) { #ifdef CONFIG_X86 - unsigned int num_pages = last - first; + unsigned int num_pages = alloc->pages - alloc->caching_divide; if (!num_pages) return 0; - switch (caching) { + switch (alloc->tt_caching) { case ttm_cached: break; case ttm_write_combined: - return set_pages_array_wc(first, num_pages); + return set_pages_array_wc(alloc->caching_divide, num_pages); case ttm_uncached: - return set_pages_array_uc(first, num_pages); + return set_pages_array_uc(alloc->caching_divide, num_pages); } #endif + alloc->caching_divide = alloc->pages; return 0; } -/* Map pages of 1 << order size and fill the DMA address array */ +/* DMA Map pages of 1 << order size and return the resulting dma_address. */ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order, - struct page *p, dma_addr_t **dma_addr) + struct page *p, dma_addr_t *dma_addr) { dma_addr_t addr; - unsigned int i; if (pool->use_dma_alloc) { struct ttm_pool_dma *dma = (void *)p->private; @@ -201,10 +254,7 @@ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order, return -EFAULT; } - for (i = 1 << order; i ; --i) { - *(*dma_addr)++ = addr; - addr += PAGE_SIZE; - } + *dma_addr = addr; return 0; } @@ -354,24 +404,235 @@ static unsigned int ttm_pool_page_order(struct ttm_pool *pool, struct page *p) return p->private; } -/* Called when we got a page, either from a pool or newly allocated */ +/* + * Split larger pages so that we can free each PAGE_SIZE page as soon + * as it has been backed up, in order to avoid memory pressure during + * reclaim. + */ +static void ttm_pool_split_for_swap(struct ttm_pool *pool, struct page *p) +{ + unsigned int order = ttm_pool_page_order(pool, p); + pgoff_t nr; + + if (!order) + return; + + split_page(p, order); + nr = 1UL << order; + while (nr--) + (p++)->private = 0; +} + +/** + * DOC: Partial backup and restoration of a struct ttm_tt. + * + * Swapout using ttm_backup_backup_page() and swapin using + * ttm_backup_copy_page() may fail. + * The former most likely due to lack of swap-space or memory, the latter due + * to lack of memory or because of signal interruption during waits. + * + * Backup failure is easily handled by using a ttm_tt pages vector that holds + * both backup handles and page pointers. This has to be taken into account when + * restoring such a ttm_tt from backup, and when freeing it while backed up. + * When restoring, for simplicity, new pages are actually allocated from the + * pool and the contents of any old pages are copied in and then the old pages + * are released. + * + * For restoration failures, the struct ttm_pool_tt_restore holds sufficient state + * to be able to resume an interrupted restore, and that structure is freed once + * the restoration is complete. If the struct ttm_tt is destroyed while there + * is a valid struct ttm_pool_tt_restore attached, that is also properly taken + * care of. + */ + +/* Is restore ongoing for the currently allocated page? */ +static bool ttm_pool_restore_valid(const struct ttm_pool_tt_restore *restore) +{ + return restore && restore->restored_pages < (1 << restore->order); +} + +/* DMA unmap and free a multi-order page, either to the relevant pool or to system. */ +static pgoff_t ttm_pool_unmap_and_free(struct ttm_pool *pool, struct page *page, + const dma_addr_t *dma_addr, enum ttm_caching caching) +{ + struct ttm_pool_type *pt = NULL; + unsigned int order; + pgoff_t nr; + + if (pool) { + order = ttm_pool_page_order(pool, page); + nr = (1UL << order); + if (dma_addr) + ttm_pool_unmap(pool, *dma_addr, nr); + + pt = ttm_pool_select_type(pool, caching, order); + } else { + order = page->private; + nr = (1UL << order); + } + + if (pt) + ttm_pool_type_give(pt, page); + else + ttm_pool_free_page(pool, caching, order, page); + + return nr; +} + +/* Populate the page-array using the most recent allocated multi-order page. */ +static void ttm_pool_allocated_page_commit(struct page *allocated, + dma_addr_t first_dma, + struct ttm_pool_alloc_state *alloc, + pgoff_t nr) +{ + pgoff_t i; + + for (i = 0; i < nr; ++i) + *alloc->pages++ = allocated++; + + alloc->remaining_pages -= nr; + + if (!alloc->dma_addr) + return; + + for (i = 0; i < nr; ++i) { + *alloc->dma_addr++ = first_dma; + first_dma += PAGE_SIZE; + } +} + +/* + * When restoring, restore backed-up content to the newly allocated page and + * if successful, populate the page-table and dma-address arrays. + */ +static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore, + struct file *backup, + const struct ttm_operation_ctx *ctx, + struct ttm_pool_alloc_state *alloc) + +{ + pgoff_t i, nr = 1UL << restore->order; + struct page **first_page = alloc->pages; + struct page *p; + int ret = 0; + + for (i = restore->restored_pages; i < nr; ++i) { + p = first_page[i]; + if (ttm_backup_page_ptr_is_handle(p)) { + unsigned long handle = ttm_backup_page_ptr_to_handle(p); + + if (IS_ENABLED(CONFIG_FAULT_INJECTION) && ctx->interruptible && + should_fail(&backup_fault_inject, 1)) { + ret = -EINTR; + break; + } + + if (handle == 0) { + restore->restored_pages++; + continue; + } + + ret = ttm_backup_copy_page(backup, restore->alloced_page + i, + handle, ctx->interruptible); + if (ret) + break; + + ttm_backup_drop(backup, handle); + } else if (p) { + /* + * We could probably avoid splitting the old page + * using clever logic, but ATM we don't care, as + * we prioritize releasing memory ASAP. Note that + * here, the old retained page is always write-back + * cached. + */ + ttm_pool_split_for_swap(restore->pool, p); + copy_highpage(restore->alloced_page + i, p); + __free_pages(p, 0); + } + + restore->restored_pages++; + first_page[i] = ttm_backup_handle_to_page_ptr(0); + } + + if (ret) { + if (!restore->restored_pages) { + dma_addr_t *dma_addr = alloc->dma_addr ? &restore->first_dma : NULL; + + ttm_pool_unmap_and_free(restore->pool, restore->alloced_page, + dma_addr, restore->page_caching); + restore->restored_pages = nr; + } + return ret; + } + + ttm_pool_allocated_page_commit(restore->alloced_page, restore->first_dma, + alloc, nr); + if (restore->page_caching == alloc->tt_caching || PageHighMem(restore->alloced_page)) + alloc->caching_divide = alloc->pages; + restore->snapshot_alloc = *alloc; + restore->alloced_pages += nr; + + return 0; +} + +/* If restoring, save information needed for ttm_pool_restore_commit(). */ +static void +ttm_pool_page_allocated_restore(struct ttm_pool *pool, unsigned int order, + struct page *p, + enum ttm_caching page_caching, + dma_addr_t first_dma, + struct ttm_pool_tt_restore *restore, + const struct ttm_pool_alloc_state *alloc) +{ + restore->pool = pool; + restore->order = order; + restore->restored_pages = 0; + restore->page_caching = page_caching; + restore->first_dma = first_dma; + restore->alloced_page = p; + restore->snapshot_alloc = *alloc; +} + +/* + * Called when we got a page, either from a pool or newly allocated. + * if needed, dma map the page and populate the dma address array. + * Populate the page address array. + * If the caching is consistent, update any deferred caching. Otherwise + * stage this page for an upcoming deferred caching update. + */ static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order, - struct page *p, dma_addr_t **dma_addr, - unsigned long *num_pages, - struct page ***pages) + struct page *p, enum ttm_caching page_caching, + struct ttm_pool_alloc_state *alloc, + struct ttm_pool_tt_restore *restore) { - unsigned int i; - int r; + bool caching_consistent; + dma_addr_t first_dma; + int r = 0; + + caching_consistent = (page_caching == alloc->tt_caching) || PageHighMem(p); - if (*dma_addr) { - r = ttm_pool_map(pool, order, p, dma_addr); + if (caching_consistent) { + r = ttm_pool_apply_caching(alloc); if (r) return r; } - *num_pages -= 1 << order; - for (i = 1 << order; i; --i, ++(*pages), ++p) - **pages = p; + if (alloc->dma_addr) { + r = ttm_pool_map(pool, order, p, &first_dma); + if (r) + return r; + } + + if (restore) { + ttm_pool_page_allocated_restore(pool, order, p, page_caching, + first_dma, restore, alloc); + } else { + ttm_pool_allocated_page_commit(p, first_dma, alloc, 1UL << order); + + if (caching_consistent) + alloc->caching_divide = alloc->pages; + } return 0; } @@ -394,53 +655,62 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt, pgoff_t start_page, pgoff_t end_page) { struct page **pages = &tt->pages[start_page]; - unsigned int order; + struct file *backup = tt->backup; pgoff_t i, nr; for (i = start_page; i < end_page; i += nr, pages += nr) { - struct ttm_pool_type *pt = NULL; + struct page *p = *pages; - order = ttm_pool_page_order(pool, *pages); - nr = (1UL << order); - if (tt->dma_address) - ttm_pool_unmap(pool, tt->dma_address[i], nr); + nr = 1; + if (ttm_backup_page_ptr_is_handle(p)) { + unsigned long handle = ttm_backup_page_ptr_to_handle(p); - pt = ttm_pool_select_type(pool, caching, order); - if (pt) - ttm_pool_type_give(pt, *pages); - else - ttm_pool_free_page(pool, caching, order, *pages); + if (handle != 0) + ttm_backup_drop(backup, handle); + } else if (p) { + dma_addr_t *dma_addr = tt->dma_address ? + tt->dma_address + i : NULL; + + nr = ttm_pool_unmap_and_free(pool, p, dma_addr, caching); + } } } -/** - * ttm_pool_alloc - Fill a ttm_tt object - * - * @pool: ttm_pool to use - * @tt: ttm_tt object to fill - * @ctx: operation context - * - * Fill the ttm_tt object with pages and also make sure to DMA map them when - * necessary. - * - * Returns: 0 on successe, negative error code otherwise. +static void ttm_pool_alloc_state_init(const struct ttm_tt *tt, + struct ttm_pool_alloc_state *alloc) +{ + alloc->pages = tt->pages; + alloc->caching_divide = tt->pages; + alloc->dma_addr = tt->dma_address; + alloc->remaining_pages = tt->num_pages; + alloc->tt_caching = tt->caching; +} + +/* + * Find a suitable allocation order based on highest desired order + * and number of remaining pages */ -int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, - struct ttm_operation_ctx *ctx) +static unsigned int ttm_pool_alloc_find_order(unsigned int highest, + const struct ttm_pool_alloc_state *alloc) +{ + return min_t(unsigned int, highest, __fls(alloc->remaining_pages)); +} + +static int __ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx, + struct ttm_pool_alloc_state *alloc, + struct ttm_pool_tt_restore *restore) { - pgoff_t num_pages = tt->num_pages; - dma_addr_t *dma_addr = tt->dma_address; - struct page **caching = tt->pages; - struct page **pages = tt->pages; enum ttm_caching page_caching; gfp_t gfp_flags = GFP_USER; pgoff_t caching_divide; unsigned int order; + bool allow_pools; struct page *p; int r; - WARN_ON(!num_pages || ttm_tt_is_populated(tt)); - WARN_ON(dma_addr && !pool->dev); + WARN_ON(!alloc->remaining_pages || ttm_tt_is_populated(tt)); + WARN_ON(alloc->dma_addr && !pool->dev); if (tt->page_flags & TTM_TT_FLAG_ZERO_ALLOC) gfp_flags |= __GFP_ZERO; @@ -453,86 +723,155 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, else gfp_flags |= GFP_HIGHUSER; - for (order = min_t(unsigned int, MAX_PAGE_ORDER, __fls(num_pages)); - num_pages; - order = min_t(unsigned int, order, __fls(num_pages))) { + page_caching = tt->caching; + allow_pools = true; + for (order = ttm_pool_alloc_find_order(MAX_PAGE_ORDER, alloc); + alloc->remaining_pages; + order = ttm_pool_alloc_find_order(order, alloc)) { struct ttm_pool_type *pt; - page_caching = tt->caching; - pt = ttm_pool_select_type(pool, tt->caching, order); - p = pt ? ttm_pool_type_take(pt) : NULL; - if (p) { - r = ttm_pool_apply_caching(caching, pages, - tt->caching); - if (r) - goto error_free_page; - - caching = pages; - do { - r = ttm_pool_page_allocated(pool, order, p, - &dma_addr, - &num_pages, - &pages); - if (r) - goto error_free_page; - - caching = pages; - if (num_pages < (1 << order)) - break; - - p = ttm_pool_type_take(pt); - } while (p); - } - - page_caching = ttm_cached; - while (num_pages >= (1 << order) && - (p = ttm_pool_alloc_page(pool, gfp_flags, order))) { - - if (PageHighMem(p)) { - r = ttm_pool_apply_caching(caching, pages, - tt->caching); - if (r) - goto error_free_page; - caching = pages; - } - r = ttm_pool_page_allocated(pool, order, p, &dma_addr, - &num_pages, &pages); - if (r) - goto error_free_page; - if (PageHighMem(p)) - caching = pages; + /* First, try to allocate a page from a pool if one exists. */ + p = NULL; + pt = ttm_pool_select_type(pool, page_caching, order); + if (pt && allow_pools) + p = ttm_pool_type_take(pt); + /* + * If that fails or previously failed, allocate from system. + * Note that this also disallows additional pool allocations using + * write-back cached pools of the same order. Consider removing + * that behaviour. + */ + if (!p) { + page_caching = ttm_cached; + allow_pools = false; + p = ttm_pool_alloc_page(pool, gfp_flags, order); } - + /* If that fails, lower the order if possible and retry. */ if (!p) { if (order) { --order; + page_caching = tt->caching; + allow_pools = true; continue; } r = -ENOMEM; goto error_free_all; } + r = ttm_pool_page_allocated(pool, order, p, page_caching, alloc, + restore); + if (r) + goto error_free_page; + + if (ttm_pool_restore_valid(restore)) { + r = ttm_pool_restore_commit(restore, tt->backup, ctx, alloc); + if (r) + goto error_free_all; + } } - r = ttm_pool_apply_caching(caching, pages, tt->caching); + r = ttm_pool_apply_caching(alloc); if (r) goto error_free_all; + kfree(tt->restore); + tt->restore = NULL; + return 0; error_free_page: ttm_pool_free_page(pool, page_caching, order, p); error_free_all: - num_pages = tt->num_pages - num_pages; - caching_divide = caching - tt->pages; + if (tt->restore) + return r; + + caching_divide = alloc->caching_divide - tt->pages; ttm_pool_free_range(pool, tt, tt->caching, 0, caching_divide); - ttm_pool_free_range(pool, tt, ttm_cached, caching_divide, num_pages); + ttm_pool_free_range(pool, tt, ttm_cached, caching_divide, + tt->num_pages - alloc->remaining_pages); return r; } + +/** + * ttm_pool_alloc - Fill a ttm_tt object + * + * @pool: ttm_pool to use + * @tt: ttm_tt object to fill + * @ctx: operation context + * + * Fill the ttm_tt object with pages and also make sure to DMA map them when + * necessary. + * + * Returns: 0 on successe, negative error code otherwise. + */ +int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + struct ttm_operation_ctx *ctx) +{ + struct ttm_pool_alloc_state alloc; + + if (WARN_ON(ttm_tt_is_backed_up(tt))) + return -EINVAL; + + ttm_pool_alloc_state_init(tt, &alloc); + + return __ttm_pool_alloc(pool, tt, ctx, &alloc, NULL); +} EXPORT_SYMBOL(ttm_pool_alloc); /** + * ttm_pool_restore_and_alloc - Fill a ttm_tt, restoring previously backed-up + * content. + * + * @pool: ttm_pool to use + * @tt: ttm_tt object to fill + * @ctx: operation context + * + * Fill the ttm_tt object with pages and also make sure to DMA map them when + * necessary. Read in backed-up content. + * + * Returns: 0 on successe, negative error code otherwise. + */ +int ttm_pool_restore_and_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx) +{ + struct ttm_pool_alloc_state alloc; + + if (WARN_ON(!ttm_tt_is_backed_up(tt))) + return -EINVAL; + + if (!tt->restore) { + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + + ttm_pool_alloc_state_init(tt, &alloc); + if (ctx->gfp_retry_mayfail) + gfp |= __GFP_RETRY_MAYFAIL; + + tt->restore = kzalloc(sizeof(*tt->restore), gfp); + if (!tt->restore) + return -ENOMEM; + + tt->restore->snapshot_alloc = alloc; + tt->restore->pool = pool; + tt->restore->restored_pages = 1; + } else { + struct ttm_pool_tt_restore *restore = tt->restore; + int ret; + + alloc = restore->snapshot_alloc; + if (ttm_pool_restore_valid(tt->restore)) { + ret = ttm_pool_restore_commit(restore, tt->backup, ctx, &alloc); + if (ret) + return ret; + } + if (!alloc.remaining_pages) + return 0; + } + + return __ttm_pool_alloc(pool, tt, ctx, &alloc, tt->restore); +} + +/** * ttm_pool_free - Free the backing pages from a ttm_tt object * * @pool: Pool to give pages back to. @@ -550,6 +889,169 @@ void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt) EXPORT_SYMBOL(ttm_pool_free); /** + * ttm_pool_drop_backed_up() - Release content of a swapped-out struct ttm_tt + * @tt: The struct ttm_tt. + * + * Release handles with associated content or any remaining pages of + * a backed-up struct ttm_tt. + */ +void ttm_pool_drop_backed_up(struct ttm_tt *tt) +{ + struct ttm_pool_tt_restore *restore; + pgoff_t start_page = 0; + + WARN_ON(!ttm_tt_is_backed_up(tt)); + + restore = tt->restore; + + /* + * Unmap and free any uncommitted restore page. + * any tt page-array backup entries already read back has + * been cleared already + */ + if (ttm_pool_restore_valid(restore)) { + dma_addr_t *dma_addr = tt->dma_address ? &restore->first_dma : NULL; + + ttm_pool_unmap_and_free(restore->pool, restore->alloced_page, + dma_addr, restore->page_caching); + restore->restored_pages = 1UL << restore->order; + } + + /* + * If a restore is ongoing, part of the tt pages may have a + * caching different than writeback. + */ + if (restore) { + pgoff_t mid = restore->snapshot_alloc.caching_divide - tt->pages; + + start_page = restore->alloced_pages; + WARN_ON(mid > start_page); + /* Pages that might be dma-mapped and non-cached */ + ttm_pool_free_range(restore->pool, tt, tt->caching, + 0, mid); + /* Pages that might be dma-mapped but cached */ + ttm_pool_free_range(restore->pool, tt, ttm_cached, + mid, restore->alloced_pages); + kfree(restore); + tt->restore = NULL; + } + + ttm_pool_free_range(NULL, tt, ttm_cached, start_page, tt->num_pages); +} + +/** + * ttm_pool_backup() - Back up or purge a struct ttm_tt + * @pool: The pool used when allocating the struct ttm_tt. + * @tt: The struct ttm_tt. + * @flags: Flags to govern the backup behaviour. + * + * Back up or purge a struct ttm_tt. If @purge is true, then + * all pages will be freed directly to the system rather than to the pool + * they were allocated from, making the function behave similarly to + * ttm_pool_free(). If @purge is false the pages will be backed up instead, + * exchanged for handles. + * A subsequent call to ttm_pool_restore_and_alloc() will then read back the content and + * a subsequent call to ttm_pool_drop_backed_up() will drop it. + * If backup of a page fails for whatever reason, @ttm will still be + * partially backed up, retaining those pages for which backup fails. + * In that case, this function can be retried, possibly after freeing up + * memory resources. + * + * Return: Number of pages actually backed up or freed, or negative + * error code on error. + */ +long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_backup_flags *flags) +{ + struct file *backup = tt->backup; + struct page *page; + unsigned long handle; + gfp_t alloc_gfp; + gfp_t gfp; + int ret = 0; + pgoff_t shrunken = 0; + pgoff_t i, num_pages; + + if (WARN_ON(ttm_tt_is_backed_up(tt))) + return -EINVAL; + + if ((!ttm_backup_bytes_avail() && !flags->purge) || + pool->use_dma_alloc || ttm_tt_is_backed_up(tt)) + return -EBUSY; + +#ifdef CONFIG_X86 + /* Anything returned to the system needs to be cached. */ + if (tt->caching != ttm_cached) + set_pages_array_wb(tt->pages, tt->num_pages); +#endif + + if (tt->dma_address || flags->purge) { + for (i = 0; i < tt->num_pages; i += num_pages) { + unsigned int order; + + page = tt->pages[i]; + if (unlikely(!page)) { + num_pages = 1; + continue; + } + + order = ttm_pool_page_order(pool, page); + num_pages = 1UL << order; + if (tt->dma_address) + ttm_pool_unmap(pool, tt->dma_address[i], + num_pages); + if (flags->purge) { + shrunken += num_pages; + page->private = 0; + __free_pages(page, order); + memset(tt->pages + i, 0, + num_pages * sizeof(*tt->pages)); + } + } + } + + if (flags->purge) + return shrunken; + + if (pool->use_dma32) + gfp = GFP_DMA32; + else + gfp = GFP_HIGHUSER; + + alloc_gfp = GFP_KERNEL | __GFP_HIGH | __GFP_NOWARN | __GFP_RETRY_MAYFAIL; + + num_pages = tt->num_pages; + + /* Pretend doing fault injection by shrinking only half of the pages. */ + if (IS_ENABLED(CONFIG_FAULT_INJECTION) && should_fail(&backup_fault_inject, 1)) + num_pages = DIV_ROUND_UP(num_pages, 2); + + for (i = 0; i < num_pages; ++i) { + s64 shandle; + + page = tt->pages[i]; + if (unlikely(!page)) + continue; + + ttm_pool_split_for_swap(pool, page); + + shandle = ttm_backup_backup_page(backup, page, flags->writeback, i, + gfp, alloc_gfp); + if (shandle < 0) { + /* We allow partially shrunken tts */ + ret = shandle; + break; + } + handle = shandle; + tt->pages[i] = ttm_backup_handle_to_page_ptr(handle); + put_page(page); + shrunken++; + } + + return shrunken ? shrunken : ret; +} + +/** * ttm_pool_init - Initialize a pool * * @pool: the pool to initialize @@ -810,6 +1312,10 @@ int ttm_pool_mgr_init(unsigned long num_pages) &ttm_pool_debugfs_globals_fops); debugfs_create_file("page_pool_shrink", 0400, ttm_debugfs_root, NULL, &ttm_pool_debugfs_shrink_fops); +#ifdef CONFIG_FAULT_INJECTION + fault_create_debugfs_attr("backup_fault_inject", ttm_debugfs_root, + &backup_fault_inject); +#endif #endif mm_shrinker = shrinker_alloc(0, "drm-ttm_pool"); diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index fb14f7716cf8..769b0ca9be47 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -22,16 +22,98 @@ * Authors: Christian König */ -#include <linux/iosys-map.h> +#include <linux/debugfs.h> #include <linux/io-mapping.h> +#include <linux/iosys-map.h> #include <linux/scatterlist.h> +#include <linux/cgroup_dmem.h> #include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_resource.h> +#include <drm/ttm/ttm_tt.h> #include <drm/drm_util.h> +/* Detach the cursor from the bulk move list*/ +static void +ttm_resource_cursor_clear_bulk(struct ttm_resource_cursor *cursor) +{ + lockdep_assert_held(&cursor->man->bdev->lru_lock); + + cursor->bulk = NULL; + list_del_init(&cursor->bulk_link); +} + +/* Move the cursor to the end of the bulk move list it's in */ +static void ttm_resource_cursor_move_bulk_tail(struct ttm_lru_bulk_move *bulk, + struct ttm_resource_cursor *cursor) +{ + struct ttm_lru_bulk_move_pos *pos; + + lockdep_assert_held(&cursor->man->bdev->lru_lock); + + if (WARN_ON_ONCE(bulk != cursor->bulk)) { + list_del_init(&cursor->bulk_link); + return; + } + + pos = &bulk->pos[cursor->mem_type][cursor->priority]; + if (pos->last) + list_move(&cursor->hitch.link, &pos->last->lru.link); + ttm_resource_cursor_clear_bulk(cursor); +} + +/* Move all cursors attached to a bulk move to its end */ +static void ttm_bulk_move_adjust_cursors(struct ttm_lru_bulk_move *bulk) +{ + struct ttm_resource_cursor *cursor, *next; + + list_for_each_entry_safe(cursor, next, &bulk->cursor_list, bulk_link) + ttm_resource_cursor_move_bulk_tail(bulk, cursor); +} + +/* Remove a cursor from an empty bulk move list */ +static void ttm_bulk_move_drop_cursors(struct ttm_lru_bulk_move *bulk) +{ + struct ttm_resource_cursor *cursor, *next; + + list_for_each_entry_safe(cursor, next, &bulk->cursor_list, bulk_link) + ttm_resource_cursor_clear_bulk(cursor); +} + +/** + * ttm_resource_cursor_init() - Initialize a struct ttm_resource_cursor + * @cursor: The cursor to initialize. + * @man: The resource manager. + * + * Initialize the cursor before using it for iteration. + */ +void ttm_resource_cursor_init(struct ttm_resource_cursor *cursor, + struct ttm_resource_manager *man) +{ + cursor->priority = 0; + cursor->man = man; + ttm_lru_item_init(&cursor->hitch, TTM_LRU_HITCH); + INIT_LIST_HEAD(&cursor->bulk_link); + INIT_LIST_HEAD(&cursor->hitch.link); +} + +/** + * ttm_resource_cursor_fini() - Finalize the LRU list cursor usage + * @cursor: The struct ttm_resource_cursor to finalize. + * + * The function pulls the LRU list cursor off any lists it was previusly + * attached to. Needs to be called with the LRU lock held. The function + * can be called multiple times after eachother. + */ +void ttm_resource_cursor_fini(struct ttm_resource_cursor *cursor) +{ + lockdep_assert_held(&cursor->man->bdev->lru_lock); + list_del_init(&cursor->hitch.link); + ttm_resource_cursor_clear_bulk(cursor); +} + /** * ttm_lru_bulk_move_init - initialize a bulk move structure * @bulk: the structure to init @@ -41,10 +123,28 @@ void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk) { memset(bulk, 0, sizeof(*bulk)); + INIT_LIST_HEAD(&bulk->cursor_list); } EXPORT_SYMBOL(ttm_lru_bulk_move_init); /** + * ttm_lru_bulk_move_fini - finalize a bulk move structure + * @bdev: The struct ttm_device + * @bulk: the structure to finalize + * + * Sanity checks that bulk moves don't have any + * resources left and hence no cursors attached. + */ +void ttm_lru_bulk_move_fini(struct ttm_device *bdev, + struct ttm_lru_bulk_move *bulk) +{ + spin_lock(&bdev->lru_lock); + ttm_bulk_move_drop_cursors(bulk); + spin_unlock(&bdev->lru_lock); +} +EXPORT_SYMBOL(ttm_lru_bulk_move_fini); + +/** * ttm_lru_bulk_move_tail - bulk move range of resources to the LRU tail. * * @bulk: bulk move structure @@ -56,6 +156,7 @@ void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk) { unsigned i, j; + ttm_bulk_move_adjust_cursors(bulk); for (i = 0; i < TTM_NUM_MEM_TYPES; ++i) { for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) { struct ttm_lru_bulk_move_pos *pos = &bulk->pos[i][j]; @@ -69,8 +170,8 @@ void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk) dma_resv_assert_held(pos->last->bo->base.resv); man = ttm_manager_type(pos->first->bo->bdev, i); - list_bulk_move_tail(&man->lru[j], &pos->first->lru, - &pos->last->lru); + list_bulk_move_tail(&man->lru[j], &pos->first->lru.link, + &pos->last->lru.link); } } } @@ -83,14 +184,38 @@ ttm_lru_bulk_move_pos(struct ttm_lru_bulk_move *bulk, struct ttm_resource *res) return &bulk->pos[res->mem_type][res->bo->priority]; } +/* Return the previous resource on the list (skip over non-resource list items) */ +static struct ttm_resource *ttm_lru_prev_res(struct ttm_resource *cur) +{ + struct ttm_lru_item *lru = &cur->lru; + + do { + lru = list_prev_entry(lru, link); + } while (!ttm_lru_item_is_res(lru)); + + return ttm_lru_item_to_res(lru); +} + +/* Return the next resource on the list (skip over non-resource list items) */ +static struct ttm_resource *ttm_lru_next_res(struct ttm_resource *cur) +{ + struct ttm_lru_item *lru = &cur->lru; + + do { + lru = list_next_entry(lru, link); + } while (!ttm_lru_item_is_res(lru)); + + return ttm_lru_item_to_res(lru); +} + /* Move the resource to the tail of the bulk move range */ static void ttm_lru_bulk_move_pos_tail(struct ttm_lru_bulk_move_pos *pos, struct ttm_resource *res) { if (pos->last != res) { if (pos->first == res) - pos->first = list_next_entry(res, lru); - list_move(&res->lru, &pos->last->lru); + pos->first = ttm_lru_next_res(res); + list_move(&res->lru.link, &pos->last->lru.link); pos->last = res; } } @@ -105,6 +230,7 @@ static void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk, pos->first = res; pos->last = res; } else { + WARN_ON(pos->first->bo->base.resv != res->bo->base.resv); ttm_lru_bulk_move_pos_tail(pos, res); } } @@ -120,19 +246,39 @@ static void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk, pos->first = NULL; pos->last = NULL; } else if (pos->first == res) { - pos->first = list_next_entry(res, lru); + pos->first = ttm_lru_next_res(res); } else if (pos->last == res) { - pos->last = list_prev_entry(res, lru); + pos->last = ttm_lru_prev_res(res); } else { - list_move(&res->lru, &pos->last->lru); + list_move(&res->lru.link, &pos->last->lru.link); } } +static bool ttm_resource_is_swapped(struct ttm_resource *res, struct ttm_buffer_object *bo) +{ + /* + * Take care when creating a new resource for a bo, that it is not considered + * swapped if it's not the current resource for the bo and is thus logically + * associated with the ttm_tt. Think a VRAM resource created to move a + * swapped-out bo to VRAM. + */ + if (bo->resource != res || !bo->ttm) + return false; + + dma_resv_assert_held(bo->base.resv); + return ttm_tt_is_swapped(bo->ttm); +} + +static bool ttm_resource_unevictable(struct ttm_resource *res, struct ttm_buffer_object *bo) +{ + return bo->pin_count || ttm_resource_is_swapped(res, bo); +} + /* Add the resource to a bulk move if the BO is configured for it */ void ttm_resource_add_bulk_move(struct ttm_resource *res, struct ttm_buffer_object *bo) { - if (bo->bulk_move && !bo->pin_count) + if (bo->bulk_move && !ttm_resource_unevictable(res, bo)) ttm_lru_bulk_move_add(bo->bulk_move, res); } @@ -140,7 +286,7 @@ void ttm_resource_add_bulk_move(struct ttm_resource *res, void ttm_resource_del_bulk_move(struct ttm_resource *res, struct ttm_buffer_object *bo) { - if (bo->bulk_move && !bo->pin_count) + if (bo->bulk_move && !ttm_resource_unevictable(res, bo)) ttm_lru_bulk_move_del(bo->bulk_move, res); } @@ -152,10 +298,10 @@ void ttm_resource_move_to_lru_tail(struct ttm_resource *res) lockdep_assert_held(&bo->bdev->lru_lock); - if (bo->pin_count) { - list_move_tail(&res->lru, &bdev->pinned); + if (ttm_resource_unevictable(res, bo)) { + list_move_tail(&res->lru.link, &bdev->unevictable); - } else if (bo->bulk_move) { + } else if (bo->bulk_move) { struct ttm_lru_bulk_move_pos *pos = ttm_lru_bulk_move_pos(bo->bulk_move, res); @@ -164,7 +310,7 @@ void ttm_resource_move_to_lru_tail(struct ttm_resource *res) struct ttm_resource_manager *man; man = ttm_manager_type(bdev, res->mem_type); - list_move_tail(&res->lru, &man->lru[bo->priority]); + list_move_tail(&res->lru.link, &man->lru[bo->priority]); } } @@ -194,10 +340,10 @@ void ttm_resource_init(struct ttm_buffer_object *bo, man = ttm_manager_type(bo->bdev, place->mem_type); spin_lock(&bo->bdev->lru_lock); - if (bo->pin_count) - list_add_tail(&res->lru, &bo->bdev->pinned); + if (ttm_resource_unevictable(res, bo)) + list_add_tail(&res->lru.link, &bo->bdev->unevictable); else - list_add_tail(&res->lru, &man->lru[bo->priority]); + list_add_tail(&res->lru.link, &man->lru[bo->priority]); man->usage += res->size; spin_unlock(&bo->bdev->lru_lock); } @@ -219,7 +365,7 @@ void ttm_resource_fini(struct ttm_resource_manager *man, struct ttm_device *bdev = man->bdev; spin_lock(&bdev->lru_lock); - list_del_init(&res->lru); + list_del_init(&res->lru.link); man->usage -= res->size; spin_unlock(&bdev->lru_lock); } @@ -227,15 +373,28 @@ EXPORT_SYMBOL(ttm_resource_fini); int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource **res_ptr) + struct ttm_resource **res_ptr, + struct dmem_cgroup_pool_state **ret_limit_pool) { struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, place->mem_type); + struct dmem_cgroup_pool_state *pool = NULL; int ret; + if (man->cg) { + ret = dmem_cgroup_try_charge(man->cg, bo->base.size, &pool, ret_limit_pool); + if (ret) + return ret; + } + ret = man->func->alloc(man, bo, place, res_ptr); - if (ret) + if (ret) { + if (pool) + dmem_cgroup_uncharge(pool, bo->base.size); return ret; + } + + (*res_ptr)->css = pool; spin_lock(&bo->bdev->lru_lock); ttm_resource_add_bulk_move(*res_ptr, bo); @@ -247,6 +406,7 @@ EXPORT_SYMBOL_FOR_TESTS_ONLY(ttm_resource_alloc); void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) { struct ttm_resource_manager *man; + struct dmem_cgroup_pool_state *pool; if (!*res) return; @@ -254,9 +414,13 @@ void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) spin_lock(&bo->bdev->lru_lock); ttm_resource_del_bulk_move(*res, bo); spin_unlock(&bo->bdev->lru_lock); + + pool = (*res)->css; man = ttm_manager_type(bo->bdev, (*res)->mem_type); man->func->free(man, *res); *res = NULL; + if (man->cg) + dmem_cgroup_uncharge(pool, bo->base.size); } EXPORT_SYMBOL(ttm_resource_free); @@ -295,11 +459,13 @@ bool ttm_resource_intersects(struct ttm_device *bdev, * * @res: the resource to check * @placement: the placement to check against + * @evicting: true if the caller is doing evictions * * Returns true if the placement is compatible. */ bool ttm_resource_compatible(struct ttm_resource *res, - struct ttm_placement *placement) + struct ttm_placement *placement, + bool evicting) { struct ttm_buffer_object *bo = res->bo; struct ttm_device *bdev = bo->bdev; @@ -315,14 +481,20 @@ bool ttm_resource_compatible(struct ttm_resource *res, if (res->mem_type != place->mem_type) continue; + if (place->flags & (evicting ? TTM_PL_FLAG_DESIRED : + TTM_PL_FLAG_FALLBACK)) + continue; + + if (place->flags & TTM_PL_FLAG_CONTIGUOUS && + !(res->placement & TTM_PL_FLAG_CONTIGUOUS)) + continue; + man = ttm_manager_type(bdev, res->mem_type); if (man->func->compatible && !man->func->compatible(man, res, place, bo->base.size)) continue; - if ((!(place->flags & TTM_PL_FLAG_CONTIGUOUS) || - (res->placement & TTM_PL_FLAG_CONTIGUOUS))) - return true; + return true; } return false; } @@ -376,28 +548,14 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev, struct ttm_operation_ctx ctx = { .interruptible = false, .no_wait_gpu = false, - .force_alloc = true }; struct dma_fence *fence; int ret; - unsigned i; - - /* - * Can't use standard list traversal since we're unlocking. - */ - spin_lock(&bdev->lru_lock); - for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) { - while (!list_empty(&man->lru[i])) { - spin_unlock(&bdev->lru_lock); - ret = ttm_mem_evict_first(bdev, man, NULL, &ctx, - NULL); - if (ret) - return ret; - spin_lock(&bdev->lru_lock); - } - } - spin_unlock(&bdev->lru_lock); + do { + ret = ttm_bo_evict_first(bdev, man, &ctx); + cond_resched(); + } while (!ret); spin_lock(&man->move_lock); fence = dma_fence_get(man->move); @@ -450,53 +608,102 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man, } EXPORT_SYMBOL(ttm_resource_manager_debug); +static void +ttm_resource_cursor_check_bulk(struct ttm_resource_cursor *cursor, + struct ttm_lru_item *next_lru) +{ + struct ttm_resource *next = ttm_lru_item_to_res(next_lru); + struct ttm_lru_bulk_move *bulk = NULL; + struct ttm_buffer_object *bo = next->bo; + + lockdep_assert_held(&cursor->man->bdev->lru_lock); + bulk = bo->bulk_move; + + if (cursor->bulk != bulk) { + if (bulk) { + list_move_tail(&cursor->bulk_link, &bulk->cursor_list); + cursor->mem_type = next->mem_type; + } else { + list_del_init(&cursor->bulk_link); + } + cursor->bulk = bulk; + } +} + /** - * ttm_resource_manager_first - * - * @man: resource manager to iterate over + * ttm_resource_manager_first() - Start iterating over the resources + * of a resource manager * @cursor: cursor to record the position * - * Returns the first resource from the resource manager. + * Initializes the cursor and starts iterating. When done iterating, + * the caller must explicitly call ttm_resource_cursor_fini(). + * + * Return: The first resource from the resource manager. */ struct ttm_resource * -ttm_resource_manager_first(struct ttm_resource_manager *man, - struct ttm_resource_cursor *cursor) +ttm_resource_manager_first(struct ttm_resource_cursor *cursor) { - struct ttm_resource *res; + struct ttm_resource_manager *man = cursor->man; - lockdep_assert_held(&man->bdev->lru_lock); + if (WARN_ON_ONCE(!man)) + return NULL; - for (cursor->priority = 0; cursor->priority < TTM_MAX_BO_PRIORITY; - ++cursor->priority) - list_for_each_entry(res, &man->lru[cursor->priority], lru) - return res; + lockdep_assert_held(&man->bdev->lru_lock); - return NULL; + list_move(&cursor->hitch.link, &man->lru[cursor->priority]); + return ttm_resource_manager_next(cursor); } /** - * ttm_resource_manager_next - * - * @man: resource manager to iterate over + * ttm_resource_manager_next() - Continue iterating over the resource manager + * resources * @cursor: cursor to record the position - * @res: the current resource pointer * - * Returns the next resource from the resource manager. + * Return: the next resource from the resource manager. */ struct ttm_resource * -ttm_resource_manager_next(struct ttm_resource_manager *man, - struct ttm_resource_cursor *cursor, - struct ttm_resource *res) +ttm_resource_manager_next(struct ttm_resource_cursor *cursor) { + struct ttm_resource_manager *man = cursor->man; + struct ttm_lru_item *lru; + lockdep_assert_held(&man->bdev->lru_lock); - list_for_each_entry_continue(res, &man->lru[cursor->priority], lru) - return res; + for (;;) { + lru = &cursor->hitch; + list_for_each_entry_continue(lru, &man->lru[cursor->priority], link) { + if (ttm_lru_item_is_res(lru)) { + ttm_resource_cursor_check_bulk(cursor, lru); + list_move(&cursor->hitch.link, &lru->link); + return ttm_lru_item_to_res(lru); + } + } + + if (++cursor->priority >= TTM_MAX_BO_PRIORITY) + break; + + list_move(&cursor->hitch.link, &man->lru[cursor->priority]); + ttm_resource_cursor_clear_bulk(cursor); + } + + return NULL; +} - for (++cursor->priority; cursor->priority < TTM_MAX_BO_PRIORITY; - ++cursor->priority) - list_for_each_entry(res, &man->lru[cursor->priority], lru) - return res; +/** + * ttm_lru_first_res_or_null() - Return the first resource on an lru list + * @head: The list head of the lru list. + * + * Return: Pointer to the first resource on the lru list or NULL if + * there is none. + */ +struct ttm_resource *ttm_lru_first_res_or_null(struct list_head *head) +{ + struct ttm_lru_item *lru; + + list_for_each_entry(lru, head, link) { + if (ttm_lru_item_is_res(lru)) + return ttm_lru_item_to_res(lru); + } return NULL; } diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 578a7c37f00b..698cd4bf5e46 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -32,13 +32,15 @@ #define pr_fmt(fmt) "[TTM] " fmt #include <linux/cc_platform.h> -#include <linux/sched.h> -#include <linux/shmem_fs.h> +#include <linux/debugfs.h> #include <linux/file.h> #include <linux/module.h> +#include <linux/sched.h> +#include <linux/shmem_fs.h> #include <drm/drm_cache.h> #include <drm/drm_device.h> #include <drm/drm_util.h> +#include <drm/ttm/ttm_backup.h> #include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_tt.h> @@ -92,7 +94,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) */ if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { page_flags |= TTM_TT_FLAG_DECRYPTED; - drm_info(ddev, "TT memory decryption enabled."); + drm_info_once(ddev, "TT memory decryption enabled."); } bo->ttm = bdev->funcs->ttm_tt_create(bo, page_flags); @@ -157,6 +159,8 @@ static void ttm_tt_init_fields(struct ttm_tt *ttm, ttm->swap_storage = NULL; ttm->sg = bo->sg; ttm->caching = caching; + ttm->restore = NULL; + ttm->backup = NULL; } int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, @@ -181,6 +185,13 @@ void ttm_tt_fini(struct ttm_tt *ttm) fput(ttm->swap_storage); ttm->swap_storage = NULL; + if (ttm_tt_is_backed_up(ttm)) + ttm_pool_drop_backed_up(ttm); + if (ttm->backup) { + ttm_backup_fini(ttm->backup); + ttm->backup = NULL; + } + if (ttm->pages) kvfree(ttm->pages); else @@ -250,6 +261,50 @@ int ttm_tt_swapin(struct ttm_tt *ttm) out_err: return ret; } +EXPORT_SYMBOL_FOR_TESTS_ONLY(ttm_tt_swapin); + +/** + * ttm_tt_backup() - Helper to back up a struct ttm_tt. + * @bdev: The TTM device. + * @tt: The struct ttm_tt. + * @flags: Flags that govern the backup behaviour. + * + * Update the page accounting and call ttm_pool_shrink_tt to free pages + * or back them up. + * + * Return: Number of pages freed or swapped out, or negative error code on + * error. + */ +long ttm_tt_backup(struct ttm_device *bdev, struct ttm_tt *tt, + const struct ttm_backup_flags flags) +{ + long ret; + + if (WARN_ON(IS_ERR_OR_NULL(tt->backup))) + return 0; + + ret = ttm_pool_backup(&bdev->pool, tt, &flags); + if (ret > 0) { + tt->page_flags &= ~TTM_TT_FLAG_PRIV_POPULATED; + tt->page_flags |= TTM_TT_FLAG_BACKED_UP; + } + + return ret; +} + +int ttm_tt_restore(struct ttm_device *bdev, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx) +{ + int ret = ttm_pool_restore_and_alloc(&bdev->pool, tt, ctx); + + if (ret) + return ret; + + tt->page_flags &= ~TTM_TT_FLAG_BACKED_UP; + + return 0; +} +EXPORT_SYMBOL(ttm_tt_restore); /** * ttm_tt_swapout - swap out tt object @@ -307,6 +362,7 @@ out_err: return ret; } +EXPORT_SYMBOL_FOR_TESTS_ONLY(ttm_tt_swapout); int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) @@ -345,6 +401,7 @@ int ttm_tt_populate(struct ttm_device *bdev, goto error; ttm->page_flags |= TTM_TT_FLAG_PRIV_POPULATED; + ttm->page_flags &= ~TTM_TT_FLAG_BACKED_UP; if (unlikely(ttm->page_flags & TTM_TT_FLAG_SWAPPED)) { ret = ttm_tt_swapin(ttm); if (unlikely(ret != 0)) { @@ -364,7 +421,10 @@ error: } return ret; } + +#if IS_ENABLED(CONFIG_DRM_TTM_KUNIT_TEST) EXPORT_SYMBOL(ttm_tt_populate); +#endif void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) { @@ -385,6 +445,7 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) ttm->page_flags &= ~TTM_TT_FLAG_PRIV_POPULATED; } +EXPORT_SYMBOL_FOR_TESTS_ONLY(ttm_tt_unpopulate); #ifdef CONFIG_DEBUG_FS @@ -470,3 +531,32 @@ unsigned long ttm_tt_pages_limit(void) return ttm_pages_limit; } EXPORT_SYMBOL(ttm_tt_pages_limit); + +/** + * ttm_tt_setup_backup() - Allocate and assign a backup structure for a ttm_tt + * @tt: The ttm_tt for wich to allocate and assign a backup structure. + * + * Assign a backup structure to be used for tt backup. This should + * typically be done at bo creation, to avoid allocations at shrinking + * time. + * + * Return: 0 on success, negative error code on failure. + */ +int ttm_tt_setup_backup(struct ttm_tt *tt) +{ + struct file *backup = + ttm_backup_shmem_create(((loff_t)tt->num_pages) << PAGE_SHIFT); + + if (WARN_ON_ONCE(!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE))) + return -EINVAL; + + if (IS_ERR(backup)) + return PTR_ERR(backup); + + if (tt->backup) + ttm_backup_fini(tt->backup); + + tt->backup = backup; + return 0; +} +EXPORT_SYMBOL(ttm_tt_setup_backup); |