[PATCH 11/11] eth: mlx4: use dma_alloc_coherent_node()

[Jakub Kicinski <kuba@kernel.org>]

mlx4_en temporarily changes the node of the device around
mlx4_alloc_hwq_res() to place the queue buffers on the queue's node.
This is racy against other users of the device's node, e.g. mlx4_ib
allocating its own buffers at the same time.

Add a node argument to mlx4_alloc_hwq_res() and use
dma_alloc_coherent_node() for the queue buffer. mlx4_buf_alloc()
and the en_netdev page keep using the device's node.

The comment about the MTT allocation was stale, the MTT ICM is not
coherent and uses mlx4_dev->numa_node, which set_dev_node() did not
affect.

The doorbell record pages, which mlx4_db_alloc() allocates on demand
and shares between all queues, now always come from the device's node.
So far they ended up on the node of whichever queue happened to need
a new page.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
v1: no change
rfc: https://lore.kernel.org/20261027022528.633359-12-kuba@kernel.org
---
 include/linux/mlx4/device.h                    |  2 +-
 drivers/net/ethernet/mellanox/mlx4/alloc.c     | 12 ++++++------
 drivers/net/ethernet/mellanox/mlx4/en_cq.c     |  9 ++-------
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     |  5 ++---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c     |  5 ++---
 6 files changed, 14 insertions(+), 21 deletions(-)

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f016263e1fcf..0d34e0e18580 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1139,7 +1139,7 @@ int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order);
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
-		       int size);
+		       int size, int node);
 void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres,
 		       int size);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index 7ed4452e20a9..0621347112df 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -553,7 +553,7 @@ u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u3
 }
 
 static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size,
-				 struct mlx4_buf *buf)
+				 struct mlx4_buf *buf, int node)
 {
 	dma_addr_t t;
 
@@ -561,8 +561,8 @@ static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size,
 	buf->npages       = 1;
 	buf->page_shift   = get_order(size) + PAGE_SHIFT;
 	buf->direct.buf   =
-		dma_alloc_coherent(&dev->persist->pdev->dev, size, &t,
-				   GFP_KERNEL);
+		dma_alloc_coherent_node(&dev->persist->pdev->dev, size, &t,
+					GFP_KERNEL, node);
 	if (!buf->direct.buf)
 		return -ENOMEM;
 
@@ -585,7 +585,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		   struct mlx4_buf *buf)
 {
 	if (size <= max_direct) {
-		return mlx4_buf_direct_alloc(dev, size, buf);
+		return mlx4_buf_direct_alloc(dev, size, buf, dev->numa_node);
 	} else {
 		dma_addr_t t;
 		int i;
@@ -749,7 +749,7 @@ void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db)
 EXPORT_SYMBOL_GPL(mlx4_db_free);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
-		       int size)
+		       int size, int node)
 {
 	int err;
 
@@ -759,7 +759,7 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
 
 	*wqres->db.db = 0;
 
-	err = mlx4_buf_direct_alloc(dev, size, &wqres->buf);
+	err = mlx4_buf_direct_alloc(dev, size, &wqres->buf, node);
 	if (err)
 		goto err_db;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 0e92956e84cf..6c47509422f6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -65,13 +65,8 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	cq->type = mode;
 	cq->vector = mdev->dev->caps.num_comp_vectors;
 
-	/* Allocate HW buffers on provided NUMA node.
-	 * dev->numa_node is used in mtt range allocation flow.
-	 */
-	set_dev_node(&mdev->dev->persist->pdev->dev, node);
-	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
-				cq->buf_size);
-	set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
+	/* Allocate HW buffers on provided NUMA node */
+	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres, cq->buf_size, node);
 	if (err)
 		goto err_cq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 071564c54522..68f1eb57c32a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3299,7 +3299,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 
 	/* Allocate page for receive rings */
 	err = mlx4_alloc_hwq_res(mdev->dev, &priv->res,
-				MLX4_EN_PAGE_SIZE);
+				 MLX4_EN_PAGE_SIZE, mdev->dev->numa_node);
 	if (err) {
 		en_err(priv, "Failed to allocate page for rx qps\n");
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index fe18606c2ab5..e2d97ecbafd2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -292,9 +292,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 		 ring->rx_info, tmp);
 
 	/* Allocate HW buffers on provided NUMA node */
-	set_dev_node(&mdev->dev->persist->pdev->dev, node);
-	err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
-	set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
+	err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres, ring->buf_size,
+				 node);
 	if (err)
 		goto err_info;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c5d564e5a581..9865ccd8d6e9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -91,9 +91,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->buf_size = ALIGN(size * ring->sp_stride, MLX4_EN_PAGE_SIZE);
 
 	/* Allocate HW buffers on provided NUMA node */
-	set_dev_node(&mdev->dev->persist->pdev->dev, node);
-	err = mlx4_alloc_hwq_res(mdev->dev, &ring->sp_wqres, ring->buf_size);
-	set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
+	err = mlx4_alloc_hwq_res(mdev->dev, &ring->sp_wqres, ring->buf_size,
+				 node);
 	if (err) {
 		en_err(priv, "Failed allocating hwq resources\n");
 		goto err_bounce;
-- 
2.56.0