Merge branch 'mlx4-XDP-performance-improvements'

Tariq Toukan says:

====================
mlx4 XDP performance improvements

This patchset contains data-path improvements, mainly for XDP_DROP
and XDP_TX cases.

Main patches:
* Patch 2 by Saeed allows enabling optimized A0 RX steering (in HW) when
  setting a single RX ring.
  With this configuration, HW packet-rate dramatically improves,
  reaching 28.1 Mpps in XDP_DROP case for both IPv4 (37% gain)
  and IPv6 (53% gain).
* Patch 6 enhances the XDP xmit function. Among other changes, now we
  ring one doorbell per NAPI. Patch gives 17% gain in XDP_TX case.
* Patch 7 obsoletes the NAPI of XDP_TX completion queue and integrates its
  poll into the respective RX NAPI. Patch gives 15% gain in XDP_TX case.

Series generated against net-next commit:
f7aec129 rxrpc: Cache the congestion window setting
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_cq.c

@@ -146,16 +146,25 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	if (err)
 		goto free_eq;
 
-	cq->mcq.comp  = cq->type != RX ? mlx4_en_tx_irq : mlx4_en_rx_irq;
 	cq->mcq.event = mlx4_en_cq_event;
 
-	if (cq->type != RX)
+	switch (cq->type) {
+	case TX:
+		cq->mcq.comp = mlx4_en_tx_irq;
 		netif_tx_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
 				  NAPI_POLL_WEIGHT);
-	else
+		napi_enable(&cq->napi);
+		break;
+	case RX:
+		cq->mcq.comp = mlx4_en_rx_irq;
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64);
-
-	napi_enable(&cq->napi);
+		napi_enable(&cq->napi);
+		break;
+	case TX_XDP:
+		/* nothing regarding napi, it's shared with rx ring */
+		cq->xdp_busy = false;
+		break;
+	}
 
 	return 0;
 
@@ -184,8 +193,10 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 
 void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 {
-	napi_disable(&cq->napi);
-	netif_napi_del(&cq->napi);
+	if (cq->type != TX_XDP) {
+		napi_disable(&cq->napi);
+		netif_napi_del(&cq->napi);
+	}
 
 	mlx4_cq_free(priv->mdev->dev, &cq->mcq);
 }

drivers/net/ethernet/mellanox/mlx4/en_main.c

@@ -125,9 +125,9 @@ void mlx4_en_update_loopback_state(struct net_device *dev,
 		priv->flags |= MLX4_EN_FLAG_ENABLE_HW_LOOPBACK;
 
 	mutex_lock(&priv->mdev->state_lock);
-	if (priv->mdev->dev->caps.flags2 &
-	    MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB &&
-	    priv->rss_map.indir_qp.qpn) {
+	if ((priv->mdev->dev->caps.flags2 &
+	     MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB) &&
+	    priv->rss_map.indir_qp && priv->rss_map.indir_qp->qpn) {
 		int i;
 		int err = 0;
 		int loopback = !!(features & NETIF_F_LOOPBACK);

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -596,6 +596,8 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 		return err;
 	}
 
+	en_info(priv, "Steering Mode %d\n", dev->caps.steering_mode);
+
 	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
 		int base_qpn = mlx4_get_base_qpn(dev, priv->port);
 		*qpn = base_qpn + index;
@@ -1010,7 +1012,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
 				memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
 				mc_list[5] = priv->port;
 				err = mlx4_multicast_detach(mdev->dev,
-							    &priv->rss_map.indir_qp,
+							    priv->rss_map.indir_qp,
 							    mc_list,
 							    MLX4_PROT_ETH,
 							    mclist->reg_id);
@@ -1032,7 +1034,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
 				/* needed for B0 steering support */
 				mc_list[5] = priv->port;
 				err = mlx4_multicast_attach(mdev->dev,
-							    &priv->rss_map.indir_qp,
+							    priv->rss_map.indir_qp,
 							    mc_list,
 							    priv->port, 0,
 							    MLX4_PROT_ETH,
@@ -1677,13 +1679,15 @@ int mlx4_en_start_port(struct net_device *dev)
 			if (t != TX_XDP) {
 				tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
 				tx_ring->recycle_ring = NULL;
+
+				/* Arm CQ for TX completions */
+				mlx4_en_arm_cq(priv, cq);
+
 			} else {
 				mlx4_en_init_recycle_ring(priv, i);
+				/* XDP TX CQ should never be armed */
 			}
 
-			/* Arm CQ for TX completions */
-			mlx4_en_arm_cq(priv, cq);
-
 			/* Set initial ownership of all Tx TXBBs to SW (1) */
 			for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE)
 				*((u32 *)(tx_ring->buf + j)) = 0xffffffff;
@@ -1742,7 +1746,7 @@ int mlx4_en_start_port(struct net_device *dev)
 	/* Attach rx QP to bradcast address */
 	eth_broadcast_addr(&mc_list[10]);
 	mc_list[5] = priv->port; /* needed for B0 steering support */
-	if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
+	if (mlx4_multicast_attach(mdev->dev, priv->rss_map.indir_qp, mc_list,
 				  priv->port, 0, MLX4_PROT_ETH,
 				  &priv->broadcast_id))
 		mlx4_warn(mdev, "Failed Attaching Broadcast\n");
@@ -1866,12 +1870,12 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 	/* Detach All multicasts */
 	eth_broadcast_addr(&mc_list[10]);
 	mc_list[5] = priv->port; /* needed for B0 steering support */
-	mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
+	mlx4_multicast_detach(mdev->dev, priv->rss_map.indir_qp, mc_list,
 			      MLX4_PROT_ETH, priv->broadcast_id);
 	list_for_each_entry(mclist, &priv->curr_list, list) {
 		memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
 		mc_list[5] = priv->port;
-		mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
+		mlx4_multicast_detach(mdev->dev, priv->rss_map.indir_qp,
 				      mc_list, MLX4_PROT_ETH, mclist->reg_id);
 		if (mclist->tunnel_reg_id)
 			mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id);

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -2356,8 +2356,8 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 					MLX4_A0_STEERING_TABLE_SIZE;
 			}
 
-			mlx4_dbg(dev, "DMFS high rate steer mode is: %s\n",
-				 dmfs_high_rate_steering_mode_str(
+			mlx4_info(dev, "DMFS high rate steer mode is: %s\n",
+				  dmfs_high_rate_steering_mode_str(
 					dev->caps.dmfs_high_steer_mode));
 		}
 	} else {

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -72,7 +72,8 @@
 #define DEF_RX_RINGS		16
 #define MAX_RX_RINGS		128
 #define MIN_RX_RINGS		4
-#define TXBB_SIZE		64
+#define LOG_TXBB_SIZE		6
+#define TXBB_SIZE		BIT(LOG_TXBB_SIZE)
 #define HEADROOM		(2048 / TXBB_SIZE + 1)
 #define STAMP_STRIDE		64
 #define STAMP_DWORDS		(STAMP_STRIDE / 4)
@@ -115,13 +116,12 @@
 #define MLX4_EN_MIN_TX_RING_P_UP	1
 #define MLX4_EN_MAX_TX_RING_P_UP	32
 #define MLX4_EN_NUM_UP			8
-#define MLX4_EN_DEF_TX_RING_SIZE	512
 #define MLX4_EN_DEF_RX_RING_SIZE  	1024
+#define MLX4_EN_DEF_TX_RING_SIZE	MLX4_EN_DEF_RX_RING_SIZE
 #define MAX_TX_RINGS			(MLX4_EN_MAX_TX_RING_P_UP * \
 					 MLX4_EN_NUM_UP)
 
 #define MLX4_EN_DEFAULT_TX_WORK		256
-#define MLX4_EN_DOORBELL_BUDGET		8
 
 /* Target number of packets to coalesce with interrupt moderation */
 #define MLX4_EN_RX_COAL_TARGET	44
@@ -276,7 +276,7 @@ struct mlx4_en_tx_ring {
 	struct netdev_queue	*tx_queue;
 	u32			(*free_tx_desc)(struct mlx4_en_priv *priv,
 						struct mlx4_en_tx_ring *ring,
-						int index, u8 owner,
+						int index,
 						u64 timestamp, int napi_mode);
 	struct mlx4_en_rx_ring	*recycle_ring;
 
@@ -359,7 +359,10 @@ struct mlx4_en_cq {
 	struct mlx4_hwq_resources wqres;
 	int                     ring;
 	struct net_device      *dev;
-	struct napi_struct	napi;
+	union {
+		struct napi_struct napi;
+		bool               xdp_busy;
+	};
 	int size;
 	int buf_size;
 	int vector;
@@ -431,7 +434,7 @@ struct mlx4_en_rss_map {
 	int base_qpn;
 	struct mlx4_qp qps[MAX_RX_RINGS];
 	enum mlx4_qp_state state[MAX_RX_RINGS];
-	struct mlx4_qp indir_qp;
+	struct mlx4_qp *indir_qp;
 	enum mlx4_qp_state indir_state;
 };
 
@@ -689,7 +692,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
 			       struct net_device *dev, unsigned int length,
-			       int tx_ind, int *doorbell_pending);
+			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
 bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
 			struct mlx4_en_rx_alloc *frame);
@@ -721,13 +724,15 @@ int mlx4_en_process_rx_cq(struct net_device *dev,
 			  int budget);
 int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget);
 int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget);
+bool mlx4_en_process_tx_cq(struct net_device *dev,
+			   struct mlx4_en_cq *cq, int napi_budget);
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
-			 int index, u8 owner, u64 timestamp,
+			 int index, u64 timestamp,
 			 int napi_mode);
 u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    struct mlx4_en_tx_ring *ring,
-			    int index, u8 owner, u64 timestamp,
+			    int index, u64 timestamp,
 			    int napi_mode);
 void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 		int is_tx, int rss, int qpn, int cqn, int user_prio,