Merge tag 'mlx5-updates-2019-04-22' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-04-22

This series includes updates to mlx5e driver RX data path and some
significant XDP RX/TX improvements to overcome/mitigate HW and PCIE
bottlenecks.

From Tariq:
1) Some Enhancements in rq->flags
2) Stabilize RX packet rate (on Striding RQ) with
multiple outstanding UMR posts
In this patch, we add support for multiple outstanding UMR posts,
 to allow faster gap closure between consuming MPWQEs and reposting
them back into the WQ.

Performance test:
As expected, huge improvement in large-scale (48 cores).

xdp_redirect_map, 64B UDP multi-stream.
Redirect from ConnectX-5 100Gbps to ConnectX-6 100Gbps.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz.

Before: Unstable, 7 to 30 Mpps
After:  Stable,   at 70.5 Mpps

From Shay:
3) XDP, Inline small packets into the TX MPWQE in XDP xmit flow

Upon high packet rate with multiple CPUs TX workloads, much of the HCA's
resources are spent on prefetching TX descriptors, thus affecting
transmission rates.
This patch comes to mitigate this problem by moving some workload to the
CPU and reducing the HW data prefetch overhead for small packets (<= 256B).

When forwarding packets with XDP, a packet that is smaller
than a certain size (set to ~256 bytes) would be sent inline within
its WQE TX descrptor (mem-copied), when the hardware tx queue is congested
beyond a pre-defined water-mark.

Performance:
    Tested packet rate for UDP 64Byte multi-stream
    over two dual port ConnectX-5 100Gbps NICs.
    CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

    * Tested with hyper-threading disabled

    XDP_TX:

    |          | before | after   |       |
    | 24 rings | 51Mpps | 116Mpps | +126% |
    | 1 ring   | 12Mpps | 12Mpps  | same  |

    XDP_REDIRECT:

    ** Below is the transmit rate, not the redirection rate
    which might be larger, and is not affected by this patch.

    |          | before  | after   |      |
    | 32 rings | 64Mpps  | 92Mpps  | +43% |
    | 1 ring   | 6.4Mpps | 6.4Mpps | same |

As we can see, feature significantly improves scaling, without
hurting single ring performance.

From Maxim:
4) Some trivial refactoring and code improvements prior to a larger series
to support AF_XDP.
====================
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -22,7 +22,8 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 #
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o
+		en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \
+		en/params.o
 
 #
 # Netdev extra

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

@@ -409,14 +409,17 @@ struct mlx5e_xdp_info_fifo {
 
 struct mlx5e_xdp_wqe_info {
 	u8 num_wqebbs;
-	u8 num_ds;
+	u8 num_pkts;
 };
 
 struct mlx5e_xdp_mpwqe {
 	/* Current MPWQE session */
 	struct mlx5e_tx_wqe *wqe;
 	u8                   ds_count;
+	u8                   pkt_count;
 	u8                   max_ds_count;
+	u8                   complete;
+	u8                   inline_on;
 };
 
 struct mlx5e_xdpsq;
@@ -428,7 +431,6 @@ struct mlx5e_xdpsq {
 	/* dirtied @completion */
 	u32                        xdpi_fifo_cc;
 	u16                        cc;
-	bool                       redirect_flush;
 
 	/* dirtied @xmit */
 	u32                        xdpi_fifo_pc ____cacheline_aligned_in_smp;
@@ -461,10 +463,10 @@ struct mlx5e_xdpsq {
 
 struct mlx5e_icosq {
 	/* data path */
+	u16                        cc;
+	u16                        pc;
 
-	/* dirtied @xmit */
-	u16                        pc ____cacheline_aligned_in_smp;
-
+	struct mlx5_wqe_ctrl_seg  *doorbell_cseg;
 	struct mlx5e_cq            cq;
 
 	/* write@xmit, read@completion */
@@ -531,7 +533,8 @@ typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
 typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
 
 enum mlx5e_rq_flag {
-	MLX5E_RQ_FLAG_XDP_XMIT = BIT(0),
+	MLX5E_RQ_FLAG_XDP_XMIT,
+	MLX5E_RQ_FLAG_XDP_REDIRECT,
 };
 
 struct mlx5e_rq_frag_info {
@@ -562,8 +565,10 @@ struct mlx5e_rq {
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
 			u16                    num_strides;
+			u16                    actual_wq_head;
 			u8                     log_stride_sz;
-			bool                   umr_in_progress;
+			u8                     umr_in_progress;
+			u8                     umr_last_bulk;
 		} mpwqe;
 	};
 	struct {
@@ -773,6 +778,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
 
+void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
 void mlx5e_completion_event(struct mlx5_core_cq *mcq);
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);

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

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "en/params.h"
+
+u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
+{
+	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	u16 linear_rq_headroom = params->xdp_prog ?
+		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	u32 frag_sz;
+
+	linear_rq_headroom += NET_IP_ALIGN;
+
+	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
+
+	if (params->xdp_prog && frag_sz < PAGE_SIZE)
+		frag_sz = PAGE_SIZE;
+
+	return frag_sz;
+}
+
+u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
+{
+	u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params);
+
+	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
+}
+
+bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params)
+{
+	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
+
+	return !params->lro_en && frag_sz <= PAGE_SIZE;
+}
+
+#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
+					  MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
+bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
+				  struct mlx5e_params *params)
+{
+	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
+	s8 signed_log_num_strides_param;
+	u8 log_num_strides;
+
+	if (!mlx5e_rx_is_linear_skb(params))
+		return false;
+
+	if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
+		return false;
+
+	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
+		return true;
+
+	log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz);
+	signed_log_num_strides_param =
+		(s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
+
+	return signed_log_num_strides_param >= 0;
+}
+
+u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
+{
+	u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params);
+
+	/* Numbers are unsigned, don't subtract to avoid underflow. */
+	if (params->log_rq_mtu_frames <
+	    log_pkts_per_wqe + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
+		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
+
+	return params->log_rq_mtu_frames - log_pkts_per_wqe;
+}
+
+u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params)
+{
+	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+		return order_base_2(mlx5e_rx_get_linear_frag_sz(params));
+
+	return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
+}
+
+u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params)
+{
+	return MLX5_MPWRQ_LOG_WQE_SZ -
+		mlx5e_mpwqe_get_log_stride_size(mdev, params);
+}
+
+u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
+			  struct mlx5e_params *params)
+{
+	u16 linear_rq_headroom = params->xdp_prog ?
+		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	bool is_linear_skb;
+
+	linear_rq_headroom += NET_IP_ALIGN;
+
+	is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
+		mlx5e_rx_is_linear_skb(params) :
+		mlx5e_rx_mpwqe_is_linear_skb(mdev, params);
+
+	return is_linear_skb ? linear_rq_headroom : 0;
+}

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

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_PARAMS_H__
+#define __MLX5_EN_PARAMS_H__
+
+#include "en.h"
+
+u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params);
+u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params);
+bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params);
+bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
+				  struct mlx5e_params *params);
+u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params);
+u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params);
+u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params);
+u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
+			  struct mlx5e_params *params);
+
+#endif /* __MLX5_EN_PARAMS_H__ */

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

@@ -85,7 +85,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		if (unlikely(err))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-		rq->xdpsq.redirect_flush = true;
+		__set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
 		mlx5e_page_dma_unmap(rq, di);
 		rq->stats->xdp_redirect++;
 		return true;
@@ -105,6 +105,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	u8  wqebbs;
 	u16 pi;
@@ -112,7 +113,9 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
 
 	prefetchw(session->wqe->data);
-	session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->pkt_count = 0;
+	session->complete  = 0;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
@@ -131,6 +134,10 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 		       MLX5E_XDP_MPW_MAX_WQEBBS);
 
 	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+
+	mlx5e_xdp_update_inline_state(sq);
+
+	stats->mpwqe++;
 }
 
 static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
@@ -147,7 +154,7 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
 	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count);
 
 	wi->num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS);
-	wi->num_ds     = ds_count - MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	wi->num_pkts   = session->pkt_count;
 
 	sq->pc += wi->num_wqebbs;
 
@@ -162,11 +169,9 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
-	dma_addr_t dma_addr    = xdpi->dma_addr;
 	struct xdp_frame *xdpf = xdpi->xdpf;
-	unsigned int dma_len   = xdpf->len;
 
-	if (unlikely(sq->hw_mtu < dma_len)) {
+	if (unlikely(sq->hw_mtu < xdpf->len)) {
 		stats->err++;
 		return false;
 	}
@@ -183,9 +188,10 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 		mlx5e_xdp_mpwqe_session_start(sq);
 	}
 
-	mlx5e_xdp_mpwqe_add_dseg(sq, dma_addr, dma_len);
+	mlx5e_xdp_mpwqe_add_dseg(sq, xdpi, stats);
 
-	if (unlikely(session->ds_count == session->max_ds_count))
+	if (unlikely(session->complete ||
+		     session->ds_count == session->max_ds_count))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
@@ -299,7 +305,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 			sqcc += wi->num_wqebbs;
 
-			for (j = 0; j < wi->num_ds; j++) {
+			for (j = 0; j < wi->num_pkts; j++) {
 				struct mlx5e_xdp_info xdpi =
 					mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
@@ -340,7 +346,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 
 		sq->cc += wi->num_wqebbs;
 
-		for (i = 0; i < wi->num_ds; i++) {
+		for (i = 0; i < wi->num_pkts; i++) {
 			struct mlx5e_xdp_info xdpi =
 				mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
@@ -419,9 +425,9 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
 
 	mlx5e_xmit_xdp_doorbell(xdpsq);
 
-	if (xdpsq->redirect_flush) {
+	if (test_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags)) {
 		xdp_do_flush_map();
-		xdpsq->redirect_flush = false;
+		__clear_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
 	}
 }
 

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

@@ -75,16 +75,68 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 	}
 }
 
+/* Enable inline WQEs to shift some load from a congested HCA (HW) to
+ * a less congested cpu (SW).
+ */
+static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
+{
+	u16 outstanding = sq->xdpi_fifo_pc - sq->xdpi_fifo_cc;
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+
+#define MLX5E_XDP_INLINE_WATERMARK_LOW	10
+#define MLX5E_XDP_INLINE_WATERMARK_HIGH 128
+
+	if (session->inline_on) {
+		if (outstanding <= MLX5E_XDP_INLINE_WATERMARK_LOW)
+			session->inline_on = 0;
+		return;
+	}
+
+	/* inline is false */
+	if (outstanding >= MLX5E_XDP_INLINE_WATERMARK_HIGH)
+		session->inline_on = 1;
+}
+
 static inline void
-mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, dma_addr_t dma_addr, u16 dma_len)
+mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi,
+			 struct mlx5e_xdpsq_stats *stats)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	dma_addr_t dma_addr    = xdpi->dma_addr;
+	struct xdp_frame *xdpf = xdpi->xdpf;
 	struct mlx5_wqe_data_seg *dseg =
-		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count++;
+		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count;
+	u16 dma_len = xdpf->len;
 
+	session->pkt_count++;
+
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
+
+	if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
+		struct mlx5_wqe_inline_seg *inline_dseg =
+			(struct mlx5_wqe_inline_seg *)dseg;
+		u16 ds_len = sizeof(*inline_dseg) + dma_len;
+		u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS);
+
+		if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) {
+			/* Not enough space for inline wqe, send with memory pointer */
+			session->complete = true;
+			goto no_inline;
+		}
+
+		inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
+		memcpy(inline_dseg->data, xdpf->data, dma_len);
+
+		session->ds_count += ds_cnt;
+		stats->inlnw++;
+		return;
+	}
+
+no_inline:
 	dseg->addr       = cpu_to_be64(dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
 	dseg->lkey       = sq->mkey_be;
+	session->ds_count++;
 }
 
 static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
@@ -111,5 +163,4 @@ mlx5e_xdpi_fifo_pop(struct mlx5e_xdp_info_fifo *fifo)
 {
 	return fifo->xi[(*fifo->cc)++ & fifo->mask];
 }
-
 #endif

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -55,6 +55,7 @@
 #include "lib/eq.h"
 #include "en/monitor_stats.h"
 #include "en/reporter.h"
+#include "en/params.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -103,104 +104,6 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 	return true;
 }
 
-static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
-{
-	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	u16 linear_rq_headroom = params->xdp_prog ?
-		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
-	u32 frag_sz;
-
-	linear_rq_headroom += NET_IP_ALIGN;
-
-	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
-
-	if (params->xdp_prog && frag_sz < PAGE_SIZE)
-		frag_sz = PAGE_SIZE;
-
-	return frag_sz;
-}
-
-static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
-{
-	u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-
-	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
-}
-
-static bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params)
-{
-	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-
-	return !params->lro_en && frag_sz <= PAGE_SIZE;
-}
-
-#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
-					  MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
-static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
-					 struct mlx5e_params *params)
-{
-	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-	s8 signed_log_num_strides_param;
-	u8 log_num_strides;
-
-	if (!mlx5e_rx_is_linear_skb(mdev, params))
-		return false;
-
-	if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
-		return false;
-
-	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
-		return true;
-
-	log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz);
-	signed_log_num_strides_param =
-		(s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
-
-	return signed_log_num_strides_param >= 0;
-}
-
-static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
-{
-	if (params->log_rq_mtu_frames <
-	    mlx5e_mpwqe_log_pkts_per_wqe(params) + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
-
-	return params->log_rq_mtu_frames - mlx5e_mpwqe_log_pkts_per_wqe(params);
-}
-
-static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
-					  struct mlx5e_params *params)
-{
-	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
-		return order_base_2(mlx5e_rx_get_linear_frag_sz(params));
-
-	return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
-}
-
-static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
-					  struct mlx5e_params *params)
-{
-	return MLX5_MPWRQ_LOG_WQE_SZ -
-		mlx5e_mpwqe_get_log_stride_size(mdev, params);
-}
-
-static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
-				 struct mlx5e_params *params)
-{
-	u16 linear_rq_headroom = params->xdp_prog ?
-		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
-	bool is_linear_skb;
-
-	linear_rq_headroom += NET_IP_ALIGN;
-
-	is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
-		mlx5e_rx_is_linear_skb(mdev, params) :
-		mlx5e_rx_mpwqe_is_linear_skb(mdev, params);
-
-	return is_linear_skb ? linear_rq_headroom : 0;
-}
-
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params)
 {
@@ -470,7 +373,6 @@ static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
 }
 
 static int mlx5e_init_di_list(struct mlx5e_rq *rq,
-			      struct mlx5e_params *params,
 			      int wq_sz, int cpu)
 {
 	int len = wq_sz << rq->wqe.info.log_num_frags;
@@ -598,7 +500,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_free;
 		}
 
-		err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu);
+		err = mlx5e_init_di_list(rq, wq_sz, c->cpu);
 		if (err)
 			goto err_free;
 		rq->post_wqes = mlx5e_post_rx_wqes;
@@ -616,7 +518,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_free;
 		}
 
-		rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(mdev, params) ?
+		rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(params) ?
 			mlx5e_skb_from_cqe_linear :
 			mlx5e_skb_from_cqe_nonlinear;
 		rq->mkey_be = c->mkey_be;
@@ -903,10 +805,14 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
+		u16 head = wq->head;
+		int i;
 
-		/* UMR WQE (if in progress) is always at wq->head */
-		if (rq->mpwqe.umr_in_progress)
-			rq->dealloc_wqe(rq, wq->head);
+		/* Outstanding UMR WQEs (in progress) start at wq->head */
+		for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
+			rq->dealloc_wqe(rq, head);
+			head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+		}
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
@@ -971,16 +877,8 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 
 static void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
-	struct mlx5e_icosq *sq = &rq->channel->icosq;
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *nopwqe;
-
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
-	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+	mlx5e_trigger_irq(&rq->channel->icosq);
 }
 
 static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
@@ -1092,7 +990,7 @@ static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
-	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
 	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
 						  sizeof(*sq->db.ico_wqe)),
@@ -1528,7 +1426,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			dseg->lkey = sq->mkey_be;
 
 			wi->num_wqebbs = 1;
-			wi->num_ds     = 1;
+			wi->num_pkts   = 1;
 		}
 	}
 
@@ -2054,7 +1952,7 @@ static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 		byte_count += MLX5E_METADATA_ETHER_LEN;
 #endif
 
-	if (mlx5e_rx_is_linear_skb(mdev, params)) {
+	if (mlx5e_rx_is_linear_skb(params)) {
 		int frag_stride;
 
 		frag_stride = mlx5e_rx_get_linear_frag_sz(params);
@@ -2108,6 +2006,13 @@ static inline u8 mlx5e_get_rqwq_log_stride(u8 wq_type, int ndsegs)
 	return order_base_2(sz);
 }
 
+static u8 mlx5e_get_rq_log_wq_sz(void *rqc)
+{
+	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+
+	return MLX5_GET(wq, wq, log_wq_sz);
+}
+
 static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 				 struct mlx5e_params *params,
 				 struct mlx5e_rq_param *param)
@@ -2274,13 +2179,28 @@ static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
 	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
 }
 
+static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params,
+				      struct mlx5e_rq_param *rqp)
+{
+	switch (params->rq_wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return order_base_2(MLX5E_UMR_WQEBBS) +
+			mlx5e_get_rq_log_wq_sz(rqp->rqc);
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	}
+}
+
 static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
 				      struct mlx5e_params *params,
 				      struct mlx5e_channel_param *cparam)
 {
-	u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	u8 icosq_log_wq_sz;
 
 	mlx5e_build_rq_param(priv, params, &cparam->rq);
+
+	icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(params, &cparam->rq);
+
 	mlx5e_build_sq_param(priv, params, &cparam->sq);
 	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
 	mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
@@ -2336,14 +2256,18 @@ static void mlx5e_activate_channels(struct mlx5e_channels *chs)
 		mlx5e_activate_channel(chs->c[i]);
 }
 
+#define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */
+
 static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
 {
 	int err = 0;
 	int i;
 
-	for (i = 0; i < chs->num; i++)
-		err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq,
-						  err ? 0 : 20000);
+	for (i = 0; i < chs->num; i++) {
+		int timeout = err ? 0 : MLX5E_RQ_WQES_TIMEOUT;
+
+		err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq, timeout);
+	}
 
 	return err ? -ETIMEDOUT : 0;
 }
@@ -3794,7 +3718,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	new_channels.params.sw_mtu = new_mtu;
 
 	if (params->xdp_prog &&
-	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+	    !mlx5e_rx_is_linear_skb(&new_channels.params)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
 			   new_mtu, MLX5E_XDP_MAX_MTU);
 		err = -EINVAL;
@@ -4235,7 +4159,7 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	new_channels.params = priv->channels.params;
 	new_channels.params.xdp_prog = prog;
 
-	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+	if (!mlx5e_rx_is_linear_skb(&new_channels.params)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
 			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
 		return -EINVAL;
@@ -4288,7 +4212,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		mlx5e_set_rq_type(priv->mdev, &priv->channels.params);
 
 	if (was_opened && reset)
-		mlx5e_open_locked(netdev);
+		err = mlx5e_open_locked(netdev);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
 		goto unlock;
@@ -4578,7 +4502,7 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 	if (!slow_pci_heuristic(mdev) &&
 	    mlx5e_striding_rq_possible(mdev, params) &&
 	    (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ||
-	     !mlx5e_rx_is_linear_skb(mdev, params)))
+	     !mlx5e_rx_is_linear_skb(params)))
 		MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true);
 	mlx5e_set_rq_type(mdev, params);
 	mlx5e_init_rq_type_params(mdev, params);

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -409,14 +409,15 @@ mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle
 			mlx5e_page_release(rq, &dma_info[i], recycle);
 }
 
-static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
+static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n)
 {
 	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
-	struct mlx5e_rx_wqe_ll *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
 
-	rq->mpwqe.umr_in_progress = false;
+	do {
+		u16 next_wqe_index = mlx5_wq_ll_get_wqe_next_ix(wq, wq->head);
 
-	mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
+		mlx5_wq_ll_push(wq, next_wqe_index);
+	} while (--n);
 
 	/* ensure wqes are visible to device before updating doorbell record */
 	dma_wmb();
@@ -426,7 +427,7 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
 
 static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
 {
-	return sq->pc >> MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	return mlx5_wq_cyc_get_ctr_wrap_cnt(&sq->wq, sq->pc);
 }
 
 static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
@@ -478,8 +479,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
 	wi->consumed_strides = 0;
 
-	rq->mpwqe.umr_in_progress = true;
-
 	umr_wqe->ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
@@ -487,7 +486,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->pc += MLX5E_UMR_WQEBBS;
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+
+	sq->doorbell_cseg = &umr_wqe->ctrl;
 
 	return 0;
 
@@ -542,37 +542,13 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 	return !!err;
 }
 
-static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
-					     struct mlx5e_icosq *sq,
-					     struct mlx5e_rq *rq,
-					     struct mlx5_cqe64 *cqe)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	u16 ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci];
-
-	mlx5_cqwq_pop(&cq->wq);
-
-	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
-		netdev_WARN_ONCE(cq->channel->netdev,
-				 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
-		return;
-	}
-
-	if (likely(icowi->opcode == MLX5_OPCODE_UMR)) {
-		mlx5e_post_rx_mpwqe(rq);
-		return;
-	}
-
-	if (unlikely(icowi->opcode != MLX5_OPCODE_NOP))
-		netdev_WARN_ONCE(cq->channel->netdev,
-				 "Bad OPCODE in ICOSQ WQE info: 0x%x\n", icowi->opcode);
-}
-
 static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 {
 	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
 	struct mlx5_cqe64 *cqe;
+	u8  completed_umr = 0;
+	u16 sqcc;
+	int i;
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
 		return;
@@ -581,28 +557,96 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 	if (likely(!cqe))
 		return;
 
-	/* by design, there's only a single cqe */
-	mlx5e_poll_ico_single_cqe(cq, sq, rq, cqe);
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	i = 0;
+	do {
+		u16 wqe_counter;
+		bool last_wqe;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
+			netdev_WARN_ONCE(cq->channel->netdev,
+					 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
+			break;
+		}
+		do {
+			struct mlx5e_sq_wqe_info *wi;
+			u16 ci;
+
+			last_wqe = (sqcc == wqe_counter);
+
+			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			wi = &sq->db.ico_wqe[ci];
+
+			if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
+				sqcc += MLX5E_UMR_WQEBBS;
+				completed_umr++;
+			} else if (likely(wi->opcode == MLX5_OPCODE_NOP)) {
+				sqcc++;
+			} else {
+				netdev_WARN_ONCE(cq->channel->netdev,
+						 "Bad OPCODE in ICOSQ WQE info: 0x%x\n",
+						 wi->opcode);
+			}
+
+		} while (!last_wqe);
+
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+
+	sq->cc = sqcc;
 
 	mlx5_cqwq_update_db_record(&cq->wq);
+
+	if (likely(completed_umr)) {
+		mlx5e_post_rx_mpwqe(rq, completed_umr);
+		rq->mpwqe.umr_in_progress -= completed_umr;
+	}
 }
 
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 {
+	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
+	u8  missing, i;
+	u16 head;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return false;
 
-	mlx5e_poll_ico_cq(&rq->channel->icosq.cq, rq);
+	mlx5e_poll_ico_cq(&sq->cq, rq);
+
+	missing = mlx5_wq_ll_missing(wq) - rq->mpwqe.umr_in_progress;
 
-	if (mlx5_wq_ll_is_full(wq))
+	if (unlikely(rq->mpwqe.umr_in_progress > rq->mpwqe.umr_last_bulk))
+		rq->stats->congst_umr++;
+
+#define UMR_WQE_BULK (2)
+	if (likely(missing < UMR_WQE_BULK))
 		return false;
 
-	if (!rq->mpwqe.umr_in_progress)
-		mlx5e_alloc_rx_mpwqe(rq, wq->head);
-	else
-		rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
+	head = rq->mpwqe.actual_wq_head;
+	i = missing;
+	do {
+		if (unlikely(mlx5e_alloc_rx_mpwqe(rq, head)))
+			break;
+		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+	} while (--i);
+
+	rq->mpwqe.umr_last_bulk    = missing - i;
+	if (sq->doorbell_cseg) {
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, sq->doorbell_cseg);
+		sq->doorbell_cseg = NULL;
+	}
+
+	rq->mpwqe.umr_in_progress += rq->mpwqe.umr_last_bulk;
+	rq->mpwqe.actual_wq_head   = head;
 
 	return false;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

@@ -65,6 +65,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
@@ -79,6 +81,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
@@ -89,7 +93,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_page_reuse) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_reuse) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
@@ -160,6 +163,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_xdp_drop     += rq_stats->xdp_drop;
 		s->rx_xdp_redirect += rq_stats->xdp_redirect;
 		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
+		s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe;
+		s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw;
 		s->rx_xdp_tx_full  += xdpsq_stats->full;
 		s->rx_xdp_tx_err   += xdpsq_stats->err;
 		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
@@ -170,7 +175,6 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
-		s->rx_page_reuse  += rq_stats->page_reuse;
 		s->rx_cache_reuse += rq_stats->cache_reuse;
 		s->rx_cache_full  += rq_stats->cache_full;
 		s->rx_cache_empty += rq_stats->cache_empty;
@@ -185,6 +189,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->ch_eq_rearm    += ch_stats->eq_rearm;
 		/* xdp redirect */
 		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
+		s->tx_xdp_mpwqe   += xdpsq_red_stats->mpwqe;
+		s->tx_xdp_inlnw   += xdpsq_red_stats->inlnw;
 		s->tx_xdp_full    += xdpsq_red_stats->full;
 		s->tx_xdp_err     += xdpsq_red_stats->err;
 		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
@@ -1212,7 +1218,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, page_reuse) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_reuse) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
@@ -1245,6 +1250,8 @@ static const struct counter_desc sq_stats_desc[] = {
 
 static const struct counter_desc rq_xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
@@ -1252,6 +1259,8 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = {
 
 static const struct counter_desc xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },

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

@@ -77,6 +77,8 @@ struct mlx5e_sw_stats {
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
 	u64 rx_xdp_tx_xmit;
+	u64 rx_xdp_tx_mpwqe;
+	u64 rx_xdp_tx_inlnw;
 	u64 rx_xdp_tx_full;
 	u64 rx_xdp_tx_err;
 	u64 rx_xdp_tx_cqe;
@@ -91,6 +93,8 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_wake;
 	u64 tx_cqe_err;
 	u64 tx_xdp_xmit;
+	u64 tx_xdp_mpwqe;
+	u64 tx_xdp_inlnw;
 	u64 tx_xdp_full;
 	u64 tx_xdp_err;
 	u64 tx_xdp_cqes;
@@ -101,7 +105,6 @@ struct mlx5e_sw_stats {
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
-	u64 rx_page_reuse;
 	u64 rx_cache_reuse;
 	u64 rx_cache_full;
 	u64 rx_cache_empty;
@@ -201,7 +204,6 @@ struct mlx5e_rq_stats {
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
-	u64 page_reuse;
 	u64 cache_reuse;
 	u64 cache_full;
 	u64 cache_empty;
@@ -241,6 +243,8 @@ struct mlx5e_sq_stats {
 
 struct mlx5e_xdpsq_stats {
 	u64 xmit;
+	u64 mpwqe;
+	u64 inlnw;
 	u64 full;
 	u64 err;
 	/* dirtied @completion */

drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c

@@ -71,6 +71,17 @@ static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
 	net_dim(&rq->dim, dim_sample);
 }
 
+void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct mlx5e_tx_wqe *nopwqe;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+
+	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+}
+
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -43,11 +43,6 @@
 #include "ecpf.h"
 #include "lib/eq.h"
 
-enum {
-	FDB_FAST_PATH = 0,
-	FDB_SLOW_PATH
-};
-
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
  */

drivers/net/ethernet/mellanox/mlx5/core/fs_core.c

@@ -2516,8 +2516,16 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (!steering->fdb_sub_ns)
 		return -ENOMEM;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH,
+				  1);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1);
-	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, 0,
+	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns,
+					  FDB_FAST_PATH,
 					  levels);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
@@ -2542,7 +2550,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		steering->fdb_sub_ns[chain] = ns;
 	}
 
-	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, 1, 1);
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
 		goto out_err;

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

@@ -134,6 +134,11 @@ static inline void mlx5_wq_cyc_update_db_record(struct mlx5_wq_cyc *wq)
 	*wq->db = cpu_to_be32(wq->wqe_ctr);
 }
 
+static inline u16 mlx5_wq_cyc_get_ctr_wrap_cnt(struct mlx5_wq_cyc *wq, u16 ctr)
+{
+	return ctr >> wq->fbc.log_sz;
+}
+
 static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr)
 {
 	return ctr & wq->fbc.sz_m1;
@@ -243,6 +248,13 @@ static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
 }
 
+static inline u16 mlx5_wq_ll_get_wqe_next_ix(struct mlx5_wq_ll *wq, u16 ix)
+{
+	struct mlx5_wqe_srq_next_seg *wqe = mlx5_wq_ll_get_wqe(wq, ix);
+
+	return be16_to_cpu(wqe->next_wqe_index);
+}
+
 static inline void mlx5_wq_ll_push(struct mlx5_wq_ll *wq, u16 head_next)
 {
 	wq->head = head_next;

include/linux/mlx5/fs.h

@@ -75,6 +75,12 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_EGRESS,
 };
 
+enum {
+	FDB_BYPASS_PATH,
+	FDB_FAST_PATH,
+	FDB_SLOW_PATH,
+};
+
 struct mlx5_flow_table;
 struct mlx5_flow_group;
 struct mlx5_flow_namespace;

include/linux/mlx5/qp.h

@@ -395,6 +395,7 @@ struct mlx5_wqe_signature_seg {
 
 struct mlx5_wqe_inline_seg {
 	__be32	byte_count;
+	__be32	data[0];
 };
 
 enum mlx5_sig_type {