Merge branch 'mlx4-better-big-tcp-support'

Eric Dumazet says:

====================
mlx4: better BIG-TCP support

mlx4 uses a bounce buffer in TX whenever the tx descriptors
wrap around the right edge of the ring.

Size of this bounce buffer was hard coded and can be
increased if/when needed.
====================

Link: https://lore.kernel.org/r/20221207141237.2575012-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 23 insertions, 13 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 43a4102e9c09..c5758637b7be 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -65,7 +65,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->sp_stride = stride;
-	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
+	ring->full_size = ring->size - HEADROOM - MLX4_MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kvmalloc_node(tmp, GFP_KERNEL, node);
@@ -77,9 +77,11 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	en_dbg(DRV, priv, "Allocated tx_info ring at addr:%p size:%d\n",
 		 ring->tx_info, tmp);
 
-	ring->bounce_buf = kmalloc_node(MAX_DESC_SIZE, GFP_KERNEL, node);
+	ring->bounce_buf = kmalloc_node(MLX4_TX_BOUNCE_BUFFER_SIZE,
+					GFP_KERNEL, node);
 	if (!ring->bounce_buf) {
-		ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
+		ring->bounce_buf = kmalloc(MLX4_TX_BOUNCE_BUFFER_SIZE,
+					   GFP_KERNEL);
 		if (!ring->bounce_buf) {
 			err = -ENOMEM;
 			goto err_info;
@@ -909,11 +911,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Align descriptor to TXBB size */
 	desc_size = ALIGN(real_size, TXBB_SIZE);
 	nr_txbb = desc_size >> LOG_TXBB_SIZE;
-	if (unlikely(nr_txbb > MAX_DESC_TXBBS)) {
-		if (netif_msg_tx_err(priv))
-			en_warn(priv, "Oversized header or SG list\n");
-		goto tx_drop_count;
-	}
 
 	bf_ok = ring->bf_enabled;
 	if (skb_vlan_tag_present(skb)) {
@@ -941,6 +938,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (likely(index + nr_txbb <= ring->size))
 		tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
 	else {
+		if (unlikely(nr_txbb > MLX4_MAX_DESC_TXBBS)) {
+			if (netif_msg_tx_err(priv))
+				en_warn(priv, "Oversized header or SG list\n");
+			goto tx_drop_count;
+		}
 		tx_desc = (struct mlx4_en_tx_desc *) ring->bounce_buf;
 		bounce = true;
 		bf_ok = false;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index e132ff4c82f2..3d4226ddba5e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -89,9 +89,19 @@
 #define MLX4_EN_FILTER_HASH_SHIFT 4
 #define MLX4_EN_FILTER_EXPIRY_QUOTA 60
 
-/* Typical TSO descriptor with 16 gather entries is 352 bytes... */
-#define MAX_DESC_SIZE		512
-#define MAX_DESC_TXBBS		(MAX_DESC_SIZE / TXBB_SIZE)
+#define CTRL_SIZE	sizeof(struct mlx4_wqe_ctrl_seg)
+#define DS_SIZE		sizeof(struct mlx4_wqe_data_seg)
+
+/* Maximal size of the bounce buffer:
+ * 256 bytes for LSO headers.
+ * CTRL_SIZE for control desc.
+ * DS_SIZE if skb->head contains some payload.
+ * MAX_SKB_FRAGS frags.
+ */
+#define MLX4_TX_BOUNCE_BUFFER_SIZE \
+	ALIGN(256 + CTRL_SIZE + DS_SIZE + MAX_SKB_FRAGS * DS_SIZE, TXBB_SIZE)
+
+#define MLX4_MAX_DESC_TXBBS	   (MLX4_TX_BOUNCE_BUFFER_SIZE / TXBB_SIZE)
 
 /*
  * OS related constants and tunables
@@ -217,9 +227,7 @@ struct mlx4_en_tx_info {
 
 
 #define MLX4_EN_BIT_DESC_OWN	0x80000000
-#define CTRL_SIZE	sizeof(struct mlx4_wqe_ctrl_seg)
 #define MLX4_EN_MEMTYPE_PAD	0x100
-#define DS_SIZE		sizeof(struct mlx4_wqe_data_seg)
 
 
 struct mlx4_en_tx_desc {