From 7ba5e7bd64a5715f624d39815f567842178afb72 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 9 Oct 2017 16:59:50 +0300 Subject: net/mlx4_en: Use __force to fix a sparse warning in TX datapath In TX data-path, we intentionally do not byte-swap, as documented in code and in the cited commit log. This fixes sparse warning: en_tx.c:720:23: warning: incorrect type in argument 1 (different base types) en_tx.c:720:23: expected unsigned int [unsigned] [usertype] en_tx.c:720:23: got restricted __be32 [usertype] doorbell_qpn Fixes: 492f5add4be8 ("net/mlx4_en: Doorbell is byteswapped in Little Endian archs") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox/mlx4/en_tx.c') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8a32a8f7f9c0..2cc82dc07397 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -718,7 +718,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring) #else iowrite32be( #endif - ring->doorbell_qpn, + (__force u32)ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL); } -- cgit v1.2.3 From 5dad61b83840d7eceaba5bf316419be11bbb993a Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 11 Oct 2017 13:17:25 +0300 Subject: net/mlx4_en: Replace netdev parameter with priv in XDP xmit function The struct net_device parameter was passed only to extract struct mlx4_en_priv out of it. Here we pass the priv parameter directly. Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 3 +-- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx4/en_tx.c') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index a7866954d106..92aec17f4b4d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -778,7 +778,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_PASS: break; case XDP_TX: - if (likely(!mlx4_en_xmit_frame(ring, frags, dev, + if (likely(!mlx4_en_xmit_frame(ring, frags, priv, length, cq_ring, &doorbell_pending))) { frags[0].page = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 2cc82dc07397..f16774c9c347 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1087,10 +1087,9 @@ tx_drop: 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, + struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - struct mlx4_en_priv *priv = netdev_priv(dev); union mlx4_wqe_qpn_vlan qpn_vlan = {}; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 245e9ea09ab2..8cad9b4f1936 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -693,7 +693,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, 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, + struct mlx4_en_priv *priv, unsigned int length, 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, -- cgit v1.2.3 From f6f0aa97413a420606aabe8142f8a5c0f15b9246 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 11 Oct 2017 13:17:26 +0300 Subject: net/mlx4_en: Obsolete call to generic write_desc in XDP xmit flow Function mlx4_en_tx_write_desc() is not optimized to use of XDP xmit. Use the relevant parts inline instead. Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx4/en_tx.c') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index f16774c9c347..ac7254e3f909 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1090,7 +1090,9 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - union mlx4_wqe_qpn_vlan qpn_vlan = {}; + union mlx4_wqe_qpn_vlan qpn_vlan = { + .fence_size = MLX4_EN_XDP_TX_REAL_SZ, + }; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; struct mlx4_wqe_data_seg *data; @@ -1140,7 +1142,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, data->byte_count = cpu_to_be32(length); /* tx completion can avoid cache line miss for common cases */ - tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; op_own = cpu_to_be32(MLX4_OPCODE_SEND) | ((ring->prod & ring->size) ? @@ -1151,10 +1152,16 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, ring->prod += MLX4_EN_XDP_TX_NRTXBB; - qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ; + tx_desc->ctrl.qpn_vlan = qpn_vlan; + tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; + + /* Ensure new descriptor hits memory + * before setting ownership of this descriptor to HW + */ + dma_wmb(); + tx_desc->ctrl.owner_opcode = op_own; + ring->xmit_more++; - mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, 0, - op_own, false, false); *doorbell_pending = true; return NETDEV_TX_OK; -- cgit v1.2.3 From f025fd6061e120713d6c11c92983804c6805d6cb Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 11 Oct 2017 13:17:27 +0300 Subject: net/mlx4_en: XDP_TX, assign constant values of TX descs on ring creaion In XDP_TX, some fields in tx_info and tx_desc are constants across all entries of the different XDP_TX rings. Assign values to these fields on ring creation time, rather than in data-path. Patchset performance tests: Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz Single queue no-RSS optimization ON. XDP_TX packet rate: ------------------------------ Before | After | Gain | 13.7 Mpps | 14.0 Mpps | %2.2 | ------------------------------ Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_tx.c | 38 ++++++++++++++++---------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 ++ 3 files changed, 27 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx4/en_tx.c') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index e4c7a80ef5a8..d611df2f274d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1752,6 +1752,7 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_arm_cq(priv, cq); } else { + mlx4_en_init_tx_xdp_ring_descs(priv, tx_ring); mlx4_en_init_recycle_ring(priv, i); /* XDP TX CQ should never be armed */ } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index ac7254e3f909..596445a4a241 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1085,14 +1085,35 @@ tx_drop: #define MLX4_EN_XDP_TX_REAL_SZ (((CTRL_SIZE + MLX4_EN_XDP_TX_NRTXBB * DS_SIZE) \ / 16) & 0x3f) +void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring) +{ + int i; + + for (i = 0; i < ring->size; i++) { + struct mlx4_en_tx_info *tx_info = &ring->tx_info[i]; + struct mlx4_en_tx_desc *tx_desc = ring->buf + + (i << LOG_TXBB_SIZE); + + tx_info->map0_byte_count = PAGE_SIZE; + tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB; + tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data); + tx_info->ts_requested = 0; + tx_info->nr_maps = 1; + tx_info->linear = 1; + tx_info->inl = 0; + + tx_desc->data.lkey = ring->mr_key; + tx_desc->ctrl.qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ; + tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; + } +} + netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - union mlx4_wqe_qpn_vlan qpn_vlan = { - .fence_size = MLX4_EN_XDP_TX_REAL_SZ, - }; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; struct mlx4_wqe_data_seg *data; @@ -1124,20 +1145,12 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, tx_info->page = frame->page; frame->page = NULL; tx_info->map0_dma = dma; - tx_info->map0_byte_count = PAGE_SIZE; - tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB; tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN); - tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data); - tx_info->ts_requested = 0; - tx_info->nr_maps = 1; - tx_info->linear = 1; - tx_info->inl = 0; dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset, length, PCI_DMA_TODEVICE); data->addr = cpu_to_be64(dma + frame->page_offset); - data->lkey = ring->mr_key; dma_wmb(); data->byte_count = cpu_to_be32(length); @@ -1152,9 +1165,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, ring->prod += MLX4_EN_XDP_TX_NRTXBB; - tx_desc->ctrl.qpn_vlan = qpn_vlan; - tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; - /* Ensure new descriptor hits memory * before setting ownership of this descriptor to HW */ diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 8cad9b4f1936..1856e279a7e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -705,6 +705,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, int node, int queue_index); void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring **pring); +void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring); int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, int cq, int user_prio); -- cgit v1.2.3