[PATCH net-next 2/3] net/mlx5: allocate doorbells from dma pools

[Tariq Toukan <tariqt@nvidia.com>]

From: Nimrod Oren <noren@nvidia.com>

Allocate doorbells from dma pools instead of the pgdir allocator.
Doorbell records remain cache-line sized coherent DMA allocations, but
their sub-allocation is now handled by the common mlx5 DMA pool
infrastructure.

This also makes doorbell allocation honor the requested NUMA node when
reusing existing backing pages. The old pgdir allocator used the
requested node only when allocating a new pgdir page; later
allocations scanned one global pgdir list and could take any pgdir with
a free entry, even if that page had been allocated for a different
NUMA node. Selecting the per-node DMA pool before sub-allocation keeps
reused doorbell records on pages allocated for the requested node.

Signed-off-by: Nimrod Oren <noren@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/alloc.c   | 111 +++---------------
 .../net/ethernet/mellanox/mlx5/core/main.c    |   4 -
 include/linux/mlx5/driver.h                   |   5 +-
 3 files changed, 18 insertions(+), 102 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 3c9938068c56..3975c726d35c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -48,13 +48,6 @@
 #define MLX5_FRAG_BUF_POOLS_NUM \
 	(PAGE_SHIFT - MLX5_FRAG_BUF_POOL_MIN_BLOCK_SHIFT + 1)
 
-struct mlx5_db_pgdir {
-	struct list_head	list;
-	unsigned long	       *bitmap;
-	__be32		       *db_page;
-	dma_addr_t		db_dma;
-};
-
 struct mlx5_dma_pool {
 	/* Protects page_list and per-page allocation bitmaps. */
 	struct mutex lock;
@@ -481,106 +474,36 @@ int mlx5_db_pools_init(struct mlx5_core_dev *dev)
 	return 0;
 }
 
-static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
-						 int node)
-{
-	u32 db_per_page = PAGE_SIZE / cache_line_size();
-	struct mlx5_db_pgdir *pgdir;
-
-	pgdir = kzalloc_node(sizeof(*pgdir), GFP_KERNEL, node);
-	if (!pgdir)
-		return NULL;
-
-	pgdir->bitmap = bitmap_zalloc_node(db_per_page, GFP_KERNEL, node);
-	if (!pgdir->bitmap) {
-		kfree(pgdir);
-		return NULL;
-	}
-
-	bitmap_fill(pgdir->bitmap, db_per_page);
-
-	pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE,
-						       &pgdir->db_dma, node);
-	if (!pgdir->db_page) {
-		bitmap_free(pgdir->bitmap);
-		kfree(pgdir);
-		return NULL;
-	}
-
-	return pgdir;
-}
-
-static int mlx5_alloc_db_from_pgdir(struct mlx5_db_pgdir *pgdir,
-				    struct mlx5_db *db)
+int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node)
 {
-	u32 db_per_page = PAGE_SIZE / cache_line_size();
+	struct mlx5_dma_pool_page *page;
+	struct mlx5_dma_pool *pool;
+	unsigned long idx;
 	int offset;
-	int i;
-
-	i = find_first_bit(pgdir->bitmap, db_per_page);
-	if (i >= db_per_page)
-		return -ENOMEM;
 
-	__clear_bit(i, pgdir->bitmap);
+	node = node == NUMA_NO_NODE ? numa_mem_id() : node;
 
-	db->u.pgdir = pgdir;
-	db->index   = i;
-	offset = db->index * cache_line_size();
-	db->db      = pgdir->db_page + offset / sizeof(*pgdir->db_page);
-	db->dma     = pgdir->db_dma  + offset;
+	pool = dev->priv.db_node_pools[node];
+	page = mlx5_dma_pool_alloc(pool, &idx);
+	if (!page)
+		return -ENOMEM;
 
-	db->db[0] = 0;
-	db->db[1] = 0;
+	offset = idx << pool->block_shift;
+	db->u.pool_page = page;
+	db->index = idx;
+	db->db = (__be32 *)((u8 *)page->buf + offset);
+	db->dma = page->dma + offset;
 
 	return 0;
 }
-
-int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node)
-{
-	struct mlx5_db_pgdir *pgdir;
-	int ret = 0;
-
-	mutex_lock(&dev->priv.pgdir_mutex);
-
-	list_for_each_entry(pgdir, &dev->priv.pgdir_list, list)
-		if (!mlx5_alloc_db_from_pgdir(pgdir, db))
-			goto out;
-
-	pgdir = mlx5_alloc_db_pgdir(dev, node);
-	if (!pgdir) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	list_add(&pgdir->list, &dev->priv.pgdir_list);
-
-	/* This should never fail -- we just allocated an empty page: */
-	WARN_ON(mlx5_alloc_db_from_pgdir(pgdir, db));
-
-out:
-	mutex_unlock(&dev->priv.pgdir_mutex);
-
-	return ret;
-}
 EXPORT_SYMBOL_GPL(mlx5_db_alloc_node);
 
 void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 {
-	u32 db_per_page = PAGE_SIZE / cache_line_size();
-
-	mutex_lock(&dev->priv.pgdir_mutex);
-
-	__set_bit(db->index, db->u.pgdir->bitmap);
-
-	if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) {
-		dma_free_coherent(mlx5_core_dma_dev(dev), PAGE_SIZE,
-				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
-		list_del(&db->u.pgdir->list);
-		bitmap_free(db->u.pgdir->bitmap);
-		kfree(db->u.pgdir);
-	}
+	struct mlx5_dma_pool_page *page = db->u.pool_page;
+	struct mlx5_dma_pool *pool = page->pool;
 
-	mutex_unlock(&dev->priv.pgdir_mutex);
+	mlx5_dma_pool_free(pool, page, db->index);
 }
 EXPORT_SYMBOL_GPL(mlx5_db_free);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index b3cb090b5677..5f28d906c35b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1819,8 +1819,6 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	INIT_LIST_HEAD(&priv->bfregs.wc_head.list);
 
 	mutex_init(&priv->alloc_mutex);
-	mutex_init(&priv->pgdir_mutex);
-	INIT_LIST_HEAD(&priv->pgdir_list);
 
 	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
 	priv->dbg.dbg_root = debugfs_create_dir(dev_name(dev->device),
@@ -1900,7 +1898,6 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	mlx5_frag_buf_pools_cleanup(dev);
 err_frag_buf_pools_init:
 	debugfs_remove(dev->priv.dbg.dbg_root);
-	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
@@ -1926,7 +1923,6 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mlx5_db_pools_cleanup(dev);
 	mlx5_frag_buf_pools_cleanup(dev);
 	debugfs_remove_recursive(dev->priv.dbg.dbg_root);
-	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4246d6d904ba..2c56bb1d676d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -599,9 +599,6 @@ struct mlx5_priv {
 	struct mutex            alloc_mutex;
 	int                     numa_node;
 
-	struct mutex            pgdir_mutex;
-	struct list_head        pgdir_list;
-
 	struct mlx5_frag_buf_node_pools **frag_buf_node_pools;
 	struct mlx5_dma_pool **db_node_pools;
 	/* end: alloc stuff */
@@ -808,7 +805,7 @@ struct mlx5_core_dev {
 struct mlx5_db {
 	__be32			*db;
 	union {
-		struct mlx5_db_pgdir		*pgdir;
+		struct mlx5_dma_pool_page	*pool_page;
 		struct mlx5_ib_user_db_page	*user_page;
 	}			u;
 	dma_addr_t		dma;
-- 
2.44.0