Merge v6.8-rc1 into drm-misc-fixes

Let's kickstart the 6.8 fix cycle.

Signed-off-by: Maxime Ripard <mripard@kernel.org>

5 files changed, 27 insertions, 19 deletions

diff --git a/drivers/gpu/drm/ttm/tests/ttm_device_test.c b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
index b1b423b68cdf..19eaff22e6ae 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_device_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
@@ -175,7 +175,7 @@ static void ttm_device_init_pools(struct kunit *test)
 
 	if (params->pools_init_expected) {
 		for (int i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
-			for (int j = 0; j <= MAX_ORDER; ++j) {
+			for (int j = 0; j < NR_PAGE_ORDERS; ++j) {
 				pt = pool->caching[i].orders[j];
 				KUNIT_EXPECT_PTR_EQ(test, pt.pool, pool);
 				KUNIT_EXPECT_EQ(test, pt.caching, i);
diff --git a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
index 2d9cae8cd984..cceaa18d4e46 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
@@ -109,7 +109,7 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	},
 	{
 		.description = "Above the allocation limit",
-		.order = MAX_ORDER + 1,
+		.order = MAX_PAGE_ORDER + 1,
 	},
 	{
 		.description = "One page, with coherent DMA mappings enabled",
@@ -118,7 +118,7 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	},
 	{
 		.description = "Above the allocation limit, with coherent DMA mappings enabled",
-		.order = MAX_ORDER + 1,
+		.order = MAX_PAGE_ORDER + 1,
 		.use_dma_alloc = true,
 	},
 };
@@ -165,7 +165,7 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 	fst_page = tt->pages[0];
 	last_page = tt->pages[tt->num_pages - 1];
 
-	if (params->order <= MAX_ORDER) {
+	if (params->order <= MAX_PAGE_ORDER) {
 		if (params->use_dma_alloc) {
 			KUNIT_ASSERT_NOT_NULL(test, (void *)fst_page->private);
 			KUNIT_ASSERT_NOT_NULL(test, (void *)last_page->private);
@@ -182,7 +182,7 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 			 * order 0 blocks
 			 */
 			KUNIT_ASSERT_EQ(test, fst_page->private,
-					min_t(unsigned int, MAX_ORDER,
+					min_t(unsigned int, MAX_PAGE_ORDER,
 					      params->order));
 			KUNIT_ASSERT_EQ(test, last_page->private, 0);
 		}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index e58b7e249816..edf10618fe2b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -370,7 +370,13 @@ static void ttm_bo_release(struct kref *kref)
 			spin_unlock(&bo->bdev->lru_lock);
 
 			INIT_WORK(&bo->delayed_delete, ttm_bo_delayed_delete);
-			queue_work(bdev->wq, &bo->delayed_delete);
+
+			/* Schedule the worker on the closest NUMA node. This
+			 * improves performance since system memory might be
+			 * cleared on free and that is best done on a CPU core
+			 * close to it.
+			 */
+			queue_work_node(bdev->pool.nid, bdev->wq, &bo->delayed_delete);
 			return;
 		}
 
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index c9fa8561f71f..e787c155a569 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -210,7 +210,8 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 	if (ret)
 		return ret;
 
-	bdev->wq = alloc_workqueue("ttm", WQ_MEM_RECLAIM | WQ_HIGHPRI, 16);
+	bdev->wq = alloc_workqueue("ttm",
+				   WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 16);
 	if (!bdev->wq) {
 		ttm_global_release();
 		return -ENOMEM;
@@ -219,7 +220,8 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 	bdev->funcs = funcs;
 
 	ttm_sys_man_init(bdev);
-	ttm_pool_init(&bdev->pool, dev, NUMA_NO_NODE, use_dma_alloc, use_dma32);
+
+	ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index fe610a3cace0..b62f420a9f96 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -65,11 +65,11 @@ module_param(page_pool_size, ulong, 0644);
 
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[MAX_ORDER + 1];
-static struct ttm_pool_type global_uncached[MAX_ORDER + 1];
+static struct ttm_pool_type global_write_combined[NR_PAGE_ORDERS];
+static struct ttm_pool_type global_uncached[NR_PAGE_ORDERS];
 
-static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1];
-static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
+static struct ttm_pool_type global_dma32_write_combined[NR_PAGE_ORDERS];
+static struct ttm_pool_type global_dma32_uncached[NR_PAGE_ORDERS];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
@@ -447,7 +447,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages));
+	for (order = min_t(unsigned int, MAX_PAGE_ORDER, __fls(num_pages));
 	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		struct ttm_pool_type *pt;
@@ -568,7 +568,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc || nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j <= MAX_ORDER; ++j)
+			for (j = 0; j < NR_PAGE_ORDERS; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -601,7 +601,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j <= MAX_ORDER; ++j)
+			for (j = 0; j < NR_PAGE_ORDERS; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -656,7 +656,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i <= MAX_ORDER; ++i)
+	for (i = 0; i < NR_PAGE_ORDERS; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -667,7 +667,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i <= MAX_ORDER; ++i)
+	for (i = 0; i < NR_PAGE_ORDERS; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -776,7 +776,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i <= MAX_ORDER; ++i) {
+	for (i = 0; i < NR_PAGE_ORDERS; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -816,7 +816,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i <= MAX_ORDER; ++i) {
+	for (i = 0; i < NR_PAGE_ORDERS; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);