Merge branch 'mlx4-next'

Amir Vadai says:

====================
net/mlx4_en: Optimizations to TX flow

This patchset contains optimizations to TX flow in mlx4_en driver. It also introduce
setting/getting tx copybreak, to enable controlling inline threshold dynamically.

TX flow optimizations was authored and posted to the mailing list by Eric
Dumazet [1] as a single patch. I splitted this patch to smaller patches,
Reviewed it and tested.
Changed from original patch:
- s/iowrite32be/iowrite32/, since ring->doorbell_qpn is stored as be32

The tx copybreak patch was also suggested by Eric Dumazet, and was edited and
reviewed by me. User space patch will be sent after kernel code is ready.

I am sending this patchset now since the merge window is near and don't want to
miss it.

More work need to do:
- Disable BF when xmit_more is in use
- Make TSO use xmit_more too. Maybe by splitting small TSO packets in the
  driver itself, to avoid extra cpu/memory costs of GSO before the driver
- Fix mlx4_en_xmit buggy handling of queue full in the middle of a burst
  partially posted to send queue using xmit_more

Eric, I edited the patches to have you as the Author and the first
signed-off-by. I hope it is ok with you (I wasn't sure if it is ok to sign by
you), anyway all the credit to those changes should go to you.

Patchset was tested and applied over commit 1e203c1 "(net: sched:
suspicious RCU usage in qdisc_watchdog")

[1] - https://patchwork.ozlabs.org/patch/394256/
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 49 insertions, 41 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 84c9d5dbfa4..8fef65840b3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -216,13 +216,16 @@ enum cq_type {
 
 struct mlx4_en_tx_info {
 	struct sk_buff *skb;
-	u32 nr_txbb;
-	u32 nr_bytes;
-	u8 linear;
-	u8 data_offset;
-	u8 inl;
-	u8 ts_requested;
-};
+	dma_addr_t	map0_dma;
+	u32		map0_byte_count;
+	u32		nr_txbb;
+	u32		nr_bytes;
+	u8		linear;
+	u8		data_offset;
+	u8		inl;
+	u8		ts_requested;
+	u8		nr_maps;
+} ____cacheline_aligned_in_smp;
 
 
 #define MLX4_EN_BIT_DESC_OWN	0x80000000
@@ -253,41 +256,46 @@ struct mlx4_en_rx_alloc {
 };
 
 struct mlx4_en_tx_ring {
+	/* cache line used and dirtied in tx completion
+	 * (mlx4_en_free_tx_buf())
+	 */
+	u32			last_nr_txbb;
+	u32			cons;
+	unsigned long		wake_queue;
+
+	/* cache line used and dirtied in mlx4_en_xmit() */
+	u32			prod ____cacheline_aligned_in_smp;
+	unsigned long		bytes;
+	unsigned long		packets;
+	unsigned long		tx_csum;
+	unsigned long		tso_packets;
+	unsigned long		xmit_more;
+	struct mlx4_bf		bf;
+	unsigned long		queue_stopped;
+
+	/* Following part should be mostly read */
+	cpumask_t		affinity_mask;
+	struct mlx4_qp		qp;
 	struct mlx4_hwq_resources wqres;
-	u32 size ; /* number of TXBBs */
-	u32 size_mask;
-	u16 stride;
-	u16 cqn;	/* index of port CQ associated with this ring */
-	u32 prod;
-	u32 cons;
-	u32 buf_size;
-	u32 doorbell_qpn;
-	void *buf;
-	u16 poll_cnt;
-	struct mlx4_en_tx_info *tx_info;
-	u8 *bounce_buf;
-	u8 queue_index;
-	cpumask_t affinity_mask;
-	u32 last_nr_txbb;
-	struct mlx4_qp qp;
-	struct mlx4_qp_context context;
-	int qpn;
-	enum mlx4_qp_state qp_state;
-	struct mlx4_srq dummy;
-	unsigned long bytes;
-	unsigned long packets;
-	unsigned long tx_csum;
-	unsigned long queue_stopped;
-	unsigned long wake_queue;
-	unsigned long tso_packets;
-	unsigned long xmit_more;
-	struct mlx4_bf bf;
-	bool bf_enabled;
-	bool bf_alloced;
-	struct netdev_queue *tx_queue;
-	int hwtstamp_tx_type;
-	int inline_thold;
-};
+	u32			size; /* number of TXBBs */
+	u32			size_mask;
+	u16			stride;
+	u16			cqn;	/* index of port CQ associated with this ring */
+	u32			buf_size;
+	__be32			doorbell_qpn;
+	__be32			mr_key;
+	void			*buf;
+	struct mlx4_en_tx_info	*tx_info;
+	u8			*bounce_buf;
+	struct mlx4_qp_context	context;
+	int			qpn;
+	enum mlx4_qp_state	qp_state;
+	u8			queue_index;
+	bool			bf_enabled;
+	bool			bf_alloced;
+	struct netdev_queue	*tx_queue;
+	int			hwtstamp_tx_type;
+} ____cacheline_aligned_in_smp;
 
 struct mlx4_en_rx_desc {
 	/* actual number of entries depends on rx ring stride */