Merge branch 'mlx5e-xdp-extend'

Tariq Toukan says:

====================
net/mlx5e: Extend XDP multi-buffer capabilities

This series extends the XDP multi-buffer support in the mlx5e driver.

Patchset breakdown:
- Infrastructural changes and preparations.
- Add XDP multi-buffer support for XDP redirect-in.
- Use TX MPWQE (multi-packet WQE) HW feature for non-linear
  single-segmented XDP frames.
- Add XDP multi-buffer support for striding RQ.

In Striding RQ, we overcome the lack of headroom and tailroom between
the RQ strides by allocating a side page per packet and using it for the
xdp_buff descriptor. We structure the xdp_buff so that it contains
nothing in the linear part, and the whole packet resides in the
fragments.

Performance highlight:

Packet rate test, 64 bytes, 32 channels, MTU 9000 bytes.
CPU: Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz.
NIC: ConnectX-6 Dx, at 100 Gbps.

+----------+-------------+-------------+---------+
| Test     | Legacy RQ   | Striding RQ | Speedup |
+----------+-------------+-------------+---------+
| XDP_DROP | 101,615,544 | 117,191,020 | +15%    |
+----------+-------------+-------------+---------+
| XDP_TX   |  95,608,169 | 117,043,422 | +22%    |
+----------+-------------+-------------+---------+

Series generated against net commit:
e61caf0 Merge branch 'page_pool-allow-caching-from-safely-localized-napi'

I'm submitting this directly as Saeed is traveling.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -475,59 +475,18 @@ struct mlx5e_txqsq {
 	cqe_ts_to_ns               ptp_cyc2time;
 } ____cacheline_aligned_in_smp;
 
-/* XDP packets can be transmitted in different ways. On completion, we need to
- * distinguish between them to clean up things in a proper way.
- */
-enum mlx5e_xdp_xmit_mode {
-	/* An xdp_frame was transmitted due to either XDP_REDIRECT from another
-	 * device or XDP_TX from an XSK RQ. The frame has to be unmapped and
-	 * returned.
-	 */
-	MLX5E_XDP_XMIT_MODE_FRAME,
-
-	/* The xdp_frame was created in place as a result of XDP_TX from a
-	 * regular RQ. No DMA remapping happened, and the page belongs to us.
-	 */
-	MLX5E_XDP_XMIT_MODE_PAGE,
-
-	/* No xdp_frame was created at all, the transmit happened from a UMEM
-	 * page. The UMEM Completion Ring producer pointer has to be increased.
-	 */
-	MLX5E_XDP_XMIT_MODE_XSK,
-};
-
-struct mlx5e_xdp_info {
-	enum mlx5e_xdp_xmit_mode mode;
-	union {
-		struct {
-			struct xdp_frame *xdpf;
-			dma_addr_t dma_addr;
-		} frame;
-		struct {
-			struct mlx5e_rq *rq;
-			struct page *page;
-		} page;
-	};
-};
-
-struct mlx5e_xmit_data {
-	dma_addr_t  dma_addr;
-	void       *data;
-	u32         len;
-};
-
 struct mlx5e_xdp_info_fifo {
-	struct mlx5e_xdp_info *xi;
+	union mlx5e_xdp_info *xi;
 	u32 *cc;
 	u32 *pc;
 	u32 mask;
 };
 
 struct mlx5e_xdpsq;
+struct mlx5e_xmit_data;
 typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
 typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
 					struct mlx5e_xmit_data *,
-					struct skb_shared_info *,
 					int);
 
 struct mlx5e_xdpsq {
@@ -628,6 +587,7 @@ union mlx5e_alloc_units {
 struct mlx5e_mpw_info {
 	u16 consumed_strides;
 	DECLARE_BITMAP(skip_release_bitmap, MLX5_MPWRQ_MAX_PAGES_PER_WQE);
+	struct mlx5e_frag_page linear_page;
 	union mlx5e_alloc_units alloc_units;
 };
 

drivers/net/ethernet/mellanox/mlx5/core/en/params.c

@@ -253,17 +253,20 @@ static u32 mlx5e_rx_get_linear_stride_sz(struct mlx5_core_dev *mdev,
 					 struct mlx5e_xsk_param *xsk,
 					 bool mpwqe)
 {
+	u32 sz;
+
 	/* XSK frames are mapped as individual pages, because frames may come in
 	 * an arbitrary order from random locations in the UMEM.
 	 */
 	if (xsk)
 		return mpwqe ? 1 << mlx5e_mpwrq_page_shift(mdev, xsk) : PAGE_SIZE;
 
-	/* XDP in mlx5e doesn't support multiple packets per page. */
-	if (params->xdp_prog)
-		return PAGE_SIZE;
+	sz = roundup_pow_of_two(mlx5e_rx_get_linear_sz_skb(params, false));
 
-	return roundup_pow_of_two(mlx5e_rx_get_linear_sz_skb(params, false));
+	/* XDP in mlx5e doesn't support multiple packets per page.
+	 * Do not assume sz <= PAGE_SIZE if params->xdp_prog is set.
+	 */
+	return params->xdp_prog && sz < PAGE_SIZE ? PAGE_SIZE : sz;
 }
 
 static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5_core_dev *mdev,
@@ -320,6 +323,20 @@ static bool mlx5e_verify_rx_mpwqe_strides(struct mlx5_core_dev *mdev,
 	return log_num_strides >= MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
 }
 
+bool mlx5e_verify_params_rx_mpwqe_strides(struct mlx5_core_dev *mdev,
+					  struct mlx5e_params *params,
+					  struct mlx5e_xsk_param *xsk)
+{
+	u8 log_wqe_num_of_strides = mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
+	u8 log_wqe_stride_size = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+	enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk);
+	u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk);
+
+	return mlx5e_verify_rx_mpwqe_strides(mdev, log_wqe_stride_size,
+					     log_wqe_num_of_strides,
+					     page_shift, umr_mode);
+}
+
 bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
 				  struct mlx5e_params *params,
 				  struct mlx5e_xsk_param *xsk)
@@ -402,6 +419,10 @@ u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
 	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk))
 		return order_base_2(mlx5e_rx_get_linear_stride_sz(mdev, params, xsk, true));
 
+	/* XDP in mlx5e doesn't support multiple packets per page. */
+	if (params->xdp_prog)
+		return PAGE_SHIFT;
+
 	return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
 }
 
@@ -572,9 +593,6 @@ int mlx5e_mpwrq_validate_regular(struct mlx5_core_dev *mdev, struct mlx5e_params
 	if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode))
 		return -EOPNOTSUPP;
 
-	if (params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-		return -EINVAL;
-
 	return 0;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en/params.h

@@ -153,6 +153,9 @@ int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 
 u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 int mlx5e_validate_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
+bool mlx5e_verify_params_rx_mpwqe_strides(struct mlx5_core_dev *mdev,
+					  struct mlx5e_params *params,
+					  struct mlx5e_xsk_param *xsk);
 
 static inline void mlx5e_params_print_info(struct mlx5_core_dev *mdev,
 					   struct mlx5e_params *params)

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -77,6 +77,19 @@ static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 }
 
 /* TX */
+struct mlx5e_xmit_data {
+	dma_addr_t  dma_addr;
+	void       *data;
+	u32         len : 31;
+	u32         has_frags : 1;
+};
+
+struct mlx5e_xmit_data_frags {
+	struct mlx5e_xmit_data xd;
+	struct skb_shared_info *sinfo;
+	dma_addr_t *dma_arr;
+};
+
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);