Merge tag 'mlx5-updates-2018-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2018-03-30

This series contains updates to mlx5 core and mlx5e netdev drivers.
The main highlight of this series is the RX optimizations for striding RQ path,
introduced by Tariq.

First Four patches are trivial misc cleanups.
 - Spelling mistake fix
 - Dead code removal
 - Warning messages

RX optimizations for striding RQ:

1) RX refactoring, cleanups and micro optimizations
   - MTU calculation simplifications, obsoletes some WQEs-to-packets translation
     functions and helps delete ~60 LOC.
   - Do not busy-wait a pending UMR completion.
   - post the new values of UMR WQE inline, instead of using a data pointer.
   - use pre-initialized structures to save calculations in datapath.

2) Use linear SKB in Striding RQ "build_skb", (Using linear SKB has many advantages):
    - Saves a memcpy of the headers.
    - No page-boundary checks in datapath.
    - No filler CQEs.
    - Significantly smaller CQ.
    - SKB data continuously resides in linear part, and not split to
      small amount (linear part) and large amount (fragment).
      This saves datapath cycles in driver and improves utilization
      of SKB fragments in GRO.
    - The fragments of a resulting GRO SKB follow the IP forwarding
      assumption of equal-size fragments.

    implementation details:
    HW writes the packets to the beginning of a stride,
    i.e. does not keep headroom. To overcome this we make sure we can
    extend backwards and use the last bytes of stride i-1.
    Extra care is needed for stride 0 as it has no preceding stride.
    We make sure headroom bytes are available by shifting the buffer
    pointer passed to HW by headroom bytes.

    This configuration now becomes default, whenever capable.
    Of course, this implies turning LRO off.

    Performance testing:
    ConnectX-5, single core, single RX ring, default MTU.

    UDP packet rate, early drop in TC layer:

    --------------------------------------------
    | pkt size | before    | after     | ratio |
    --------------------------------------------
    | 1500byte | 4.65 Mpps | 5.96 Mpps | 1.28x |
    |  500byte | 5.23 Mpps | 5.97 Mpps | 1.14x |
    |   64byte | 5.94 Mpps | 5.96 Mpps | 1.00x |
    --------------------------------------------

    TCP streams: ~20% gain

3) Support XDP over Striding RQ:
    Now that linear SKB is supported over Striding RQ,
    we can support XDP by setting stride size to PAGE_SIZE
    and headroom to XDP_PACKET_HEADROOM.

    Striding RQ is capable of a higher packet-rate than
    conventional RQ.

    Performance testing:
    ConnectX-5, 24 rings, default MTU.
    CQE compression ON (to reduce completions BW in PCI).

    XDP_DROP packet rate:
    --------------------------------------------------
    | pkt size | XDP rate   | 100GbE linerate | pct% |
    --------------------------------------------------
    |   64byte | 126.2 Mpps |      148.0 Mpps |  85% |
    |  128byte |  80.0 Mpps |       84.8 Mpps |  94% |
    |  256byte |  42.7 Mpps |       42.7 Mpps | 100% |
    |  512byte |  23.4 Mpps |       23.4 Mpps | 100% |
    --------------------------------------------------

4) Remove mlx5 page_ref bulking in Striding RQ and use page_ref_inc only when needed.
   Without this bulking, we have:
    - no atomic ops on WQE allocation or free
    - one atomic op per SKB
    - In the default MTU configuration (1500, stride size is 2K),
      the non-bulking method execute 2 atomic ops as before
    - For larger MTUs with stride size of 4K, non-bulking method
      executes only a single op.
    - For XDP (stride size of 4K, no SKBs), non-bulking have no atomic ops per packet at all.

    Performance testing:
    ConnectX-5, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz.

    Single core packet rate (64 bytes).

    Early drop in TC: no degradation.

    XDP_DROP:
    before: 14,270,188 pps
    after:  20,503,603 pps, 43% improvement.
====================

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

9 files changed, 402 insertions, 443 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 353ac6daa3dc..30cad07be2b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -57,24 +57,12 @@
 
 #define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
 
-#define MLX5E_HW2SW_MTU(priv, hwmtu) ((hwmtu) - ((priv)->hard_mtu))
-#define MLX5E_SW2HW_MTU(priv, swmtu) ((swmtu) + ((priv)->hard_mtu))
+#define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
+#define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
 
 #define MLX5E_MAX_DSCP          64
 #define MLX5E_MAX_NUM_TC	8
 
-#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x6
-#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE                0xa
-#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE                0xd
-
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x1
-#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE                0xa
-#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE                0xd
-
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
-#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW            0x3
-#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW            0x6
-
 #define MLX5_RX_HEADROOM NET_SKB_PAD
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -95,11 +83,29 @@
 #define MLX5_MPWRQ_PAGES_PER_WQE		BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
 
 #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
-#define MLX5E_REQUIRED_MTTS(wqes)		\
-	(wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
-#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
+#define MLX5E_REQUIRED_WQE_MTTS		(ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_LOG_ALIGNED_MPWQE_PPW	(ilog2(MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_REQUIRED_MTTS(wqes)	(wqes * MLX5E_REQUIRED_WQE_MTTS)
+#define MLX5E_MAX_RQ_NUM_MTTS	\
+	((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
+#define MLX5E_ORDER2_MAX_PACKET_MTU (order_base_2(10 * 1024))
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW	\
+		(ilog2(MLX5E_MAX_RQ_NUM_MTTS / MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW \
+	(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW + \
+	 (MLX5_MPWRQ_LOG_WQE_SZ - MLX5E_ORDER2_MAX_PACKET_MTU))
+
+#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x6
+#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE                0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE                0xd
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x1
+#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE                0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE min_t(u8, 0xd,	\
+					       MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW)
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
 
-#define MLX5_UMR_ALIGN				(2048)
 #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
@@ -124,8 +130,13 @@
 #define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
-#define MLX5E_ICOSQ_MAX_WQEBBS \
-	(DIV_ROUND_UP(sizeof(struct mlx5e_umr_wqe), MLX5_SEND_WQE_BB))
+#define MLX5E_UMR_WQE_INLINE_SZ \
+	(sizeof(struct mlx5e_umr_wqe) + \
+	 ALIGN(MLX5_MPWRQ_PAGES_PER_WQE * sizeof(struct mlx5_mtt), \
+	       MLX5_UMR_MTT_ALIGNMENT))
+#define MLX5E_UMR_WQEBBS \
+	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
+#define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
 
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 #define MLX5E_XDP_TX_DS_COUNT \
@@ -155,26 +166,6 @@ static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
 	}
 }
 
-static inline int mlx5_min_log_rq_size(int wq_type)
-{
-	switch (wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
-	default:
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
-	}
-}
-
-static inline int mlx5_max_log_rq_size(int wq_type)
-{
-	switch (wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW;
-	default:
-		return MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
-	}
-}
-
 static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
@@ -197,7 +188,7 @@ struct mlx5e_umr_wqe {
 	struct mlx5_wqe_ctrl_seg       ctrl;
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
-	struct mlx5_wqe_data_seg       data;
+	struct mlx5_mtt                inline_mtts[0];
 };
 
 extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
@@ -233,7 +224,7 @@ enum mlx5e_priv_flag {
 struct mlx5e_params {
 	u8  log_sq_size;
 	u8  rq_wq_type;
-	u8  log_rq_size;
+	u8  log_rq_mtu_frames;
 	u16 num_channels;
 	u8  num_tc;
 	bool rx_cqe_compress_def;
@@ -251,6 +242,8 @@ struct mlx5e_params {
 	u32 lro_timeout;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
+	unsigned int sw_mtu;
+	int hard_mtu;
 };
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -433,7 +426,6 @@ struct mlx5e_icosq {
 	void __iomem              *uar_map;
 	u32                        sqn;
 	u16                        edge;
-	__be32                     mkey_be;
 	unsigned long              state;
 
 	/* control path */
@@ -458,16 +450,13 @@ struct mlx5e_wqe_frag_info {
 };
 
 struct mlx5e_umr_dma_info {
-	__be64                *mtt;
-	dma_addr_t             mtt_addr;
 	struct mlx5e_dma_info  dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
-	struct mlx5e_umr_wqe   wqe;
 };
 
 struct mlx5e_mpw_info {
 	struct mlx5e_umr_dma_info umr;
 	u16 consumed_strides;
-	u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
+	DECLARE_BITMAP(xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
 };
 
 /* a single cache unit is capable to serve one napi call (for non-striding rq)
@@ -484,9 +473,16 @@ struct mlx5e_page_cache {
 
 struct mlx5e_rq;
 typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
+typedef struct sk_buff *
+(*mlx5e_fp_skb_from_cqe_mpwrq)(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+			       u16 cqe_bcnt, u32 head_offset, u32 page_idx);
 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),
+};
+
 struct mlx5e_rq {
 	/* data path */
 	struct mlx5_wq_ll      wq;
@@ -497,12 +493,12 @@ struct mlx5e_rq {
 			u32 frag_sz;	/* max possible skb frag_sz */
 			union {
 				bool page_reuse;
-				bool xdp_xmit;
 			};
 		} wqe;
 		struct {
+			struct mlx5e_umr_wqe   umr_wqe;
 			struct mlx5e_mpw_info *info;
-			void                  *mtt_no_align;
+			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
 			u16                    num_strides;
 			u8                     log_stride_sz;
 			bool                   umr_in_progress;
@@ -534,7 +530,9 @@ struct mlx5e_rq {
 
 	/* XDP */
 	struct bpf_prog       *xdp_prog;
+	unsigned int           hw_mtu;
 	struct mlx5e_xdpsq     xdpsq;
+	DECLARE_BITMAP(flags, 8);
 
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
@@ -767,7 +765,6 @@ struct mlx5e_priv {
 	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
-	int                        hard_mtu;
 
 	struct mlx5e_flow_steering fs;
 	struct mlx5e_vxlan_db      vxlan;
@@ -846,11 +843,12 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
-
-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);
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				   u16 cqe_bcnt, u32 head_offset, u32 page_idx);
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
@@ -981,11 +979,6 @@ static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
 	mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc);
 }
 
-static inline u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix)
-{
-	return wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8);
-}
-
 extern const struct ethtool_ops mlx5e_ethtool_ops;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
@@ -1111,7 +1104,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
-			    u16 max_channels);
+			    u16 max_channels, u16 mtu);
 u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 #endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c57c929d7973..a87d46bc2299 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -220,60 +220,12 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 	mlx5e_ethtool_get_ethtool_stats(priv, stats, data);
 }
 
-static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
-				    int num_wqe)
-{
-	int packets_per_wqe;
-	int stride_size;
-	int num_strides;
-	int wqe_size;
-
-	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		return num_wqe;
-
-	stride_size = 1 << mlx5e_mpwqe_get_log_stride_size(priv->mdev, &priv->channels.params);
-	num_strides = 1 << mlx5e_mpwqe_get_log_num_strides(priv->mdev, &priv->channels.params);
-	wqe_size = stride_size * num_strides;
-
-	packets_per_wqe = wqe_size /
-			  ALIGN(ETH_DATA_LEN, stride_size);
-	return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1));
-}
-
-static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
-				    int num_packets)
-{
-	int packets_per_wqe;
-	int stride_size;
-	int num_strides;
-	int wqe_size;
-	int num_wqes;
-
-	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		return num_packets;
-
-	stride_size = 1 << mlx5e_mpwqe_get_log_stride_size(priv->mdev, &priv->channels.params);
-	num_strides = 1 << mlx5e_mpwqe_get_log_num_strides(priv->mdev, &priv->channels.params);
-	wqe_size = stride_size * num_strides;
-
-	num_packets = (1 << order_base_2(num_packets));
-
-	packets_per_wqe = wqe_size /
-			  ALIGN(ETH_DATA_LEN, stride_size);
-	num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe);
-	return 1 << (order_base_2(num_wqes));
-}
-
 void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 				 struct ethtool_ringparam *param)
 {
-	int rq_wq_type = priv->channels.params.rq_wq_type;
-
-	param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-							 1 << mlx5_max_log_rq_size(rq_wq_type));
+	param->rx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
 	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
-	param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-						     1 << priv->channels.params.log_rq_size);
+	param->rx_pending     = 1 << priv->channels.params.log_rq_mtu_frames;
 	param->tx_pending     = 1 << priv->channels.params.log_sq_size;
 }
 
@@ -288,13 +240,9 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 				struct ethtool_ringparam *param)
 {
-	int rq_wq_type = priv->channels.params.rq_wq_type;
 	struct mlx5e_channels new_channels = {};
-	u32 rx_pending_wqes;
-	u32 min_rq_size;
 	u8 log_rq_size;
 	u8 log_sq_size;
-	u32 num_mtts;
 	int err = 0;
 
 	if (param->rx_jumbo_pending) {
@@ -308,23 +256,10 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 		return -EINVAL;
 	}
 
-	min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-					       1 << mlx5_min_log_rq_size(rq_wq_type));
-	rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type,
-						   param->rx_pending);
-
-	if (param->rx_pending < min_rq_size) {
+	if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) {
 		netdev_info(priv->netdev, "%s: rx_pending (%d) < min (%d)\n",
 			    __func__, param->rx_pending,
-			    min_rq_size);
-		return -EINVAL;
-	}
-
-	num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
-	if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
-	    !MLX5E_VALID_NUM_MTTS(num_mtts)) {
-		netdev_info(priv->netdev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
-			    __func__, param->rx_pending);
+			    1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE);
 		return -EINVAL;
 	}
 
@@ -335,17 +270,17 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 		return -EINVAL;
 	}
 
-	log_rq_size = order_base_2(rx_pending_wqes);
+	log_rq_size = order_base_2(param->rx_pending);
 	log_sq_size = order_base_2(param->tx_pending);
 
-	if (log_rq_size == priv->channels.params.log_rq_size &&
+	if (log_rq_size == priv->channels.params.log_rq_mtu_frames &&
 	    log_sq_size == priv->channels.params.log_sq_size)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
 	new_channels.params = priv->channels.params;
-	new_channels.params.log_rq_size = log_rq_size;
+	new_channels.params.log_rq_mtu_frames = log_rq_size;
 	new_channels.params.log_sq_size = log_sq_size;
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1b48dec67abf..0339609cfa56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -73,26 +73,89 @@ struct mlx5e_channel_param {
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
-	return MLX5_CAP_GEN(mdev, striding_rq) &&
+	bool striding_rq_umr = MLX5_CAP_GEN(mdev, striding_rq) &&
 		MLX5_CAP_GEN(mdev, umr_ptr_rlky) &&
 		MLX5_CAP_ETH(mdev, reg_umr_sq);
+	u16 max_wqe_sz_cap = MLX5_CAP_GEN(mdev, max_wqe_sz_sq);
+	bool inline_umr = MLX5E_UMR_WQE_INLINE_SZ <= max_wqe_sz_cap;
+
+	if (!striding_rq_umr)
+		return false;
+	if (!inline_umr) {
+		mlx5_core_warn(mdev, "Cannot support Striding RQ: UMR WQE size (%d) exceeds maximum supported (%d).\n",
+			       (int)MLX5E_UMR_WQE_INLINE_SZ, max_wqe_sz_cap);
+		return false;
+	}
+	return true;
+}
+
+static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
+{
+	if (!params->xdp_prog) {
+		u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+		u16 rq_headroom = MLX5_RX_HEADROOM + NET_IP_ALIGN;
+
+		return MLX5_SKB_FRAG_SZ(rq_headroom + hw_mtu);
+	}
+
+	return PAGE_SIZE;
 }
 
-u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params)
+static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
 {
+	u32 linear_frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params);
+
+	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
+}
+
+static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
+					 struct mlx5e_params *params)
+{
+	u32 frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params);
+	s8 signed_log_num_strides_param;
+	u8 log_num_strides;
+
+	if (params->lro_en || frag_sz > PAGE_SIZE)
+		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_mpwqe_get_linear_frag_sz(params));
+
 	return MLX5E_MPWQE_STRIDE_SZ(mdev,
 		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
-u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params)
+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 mlx5e_params *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;
@@ -102,6 +165,9 @@ static u16 mlx5e_get_rq_headroom(struct mlx5e_params *params)
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST)
 		return linear_rq_headroom;
 
+	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+		return linear_rq_headroom;
+
 	return 0;
 }
 
@@ -109,25 +175,23 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params)
 {
 	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+	params->log_rq_mtu_frames = is_kdump_kernel() ?
+		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
+		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		params->log_rq_size = is_kdump_kernel() ?
-			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
-			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		params->log_rq_size = is_kdump_kernel() ?
-			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
-			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
-
 		/* Extra room needed for build_skb */
-		params->lro_wqe_sz -= mlx5e_get_rq_headroom(params) +
+		params->lro_wqe_sz -= mlx5e_get_rq_headroom(mdev, params) +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	}
 
 	mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
 		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
-		       BIT(params->log_rq_size),
+		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
+		       BIT(mlx5e_mpwqe_get_log_rq_size(params)) :
+		       BIT(params->log_rq_mtu_frames),
 		       BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
 		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
@@ -136,7 +200,8 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params)
 {
 	return mlx5e_check_fragmented_striding_rq_cap(mdev) &&
-		!params->xdp_prog && !MLX5_IPSEC_DEV(mdev);
+		!MLX5_IPSEC_DEV(mdev) &&
+		!(params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params));
 }
 
 void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
@@ -239,107 +304,38 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
 }
 
-static inline int mlx5e_get_wqe_mtt_sz(void)
-{
-	/* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes.
-	 * To avoid copying garbage after the mtt array, we allocate
-	 * a little more.
-	 */
-	return ALIGN(MLX5_MPWRQ_PAGES_PER_WQE * sizeof(__be64),
-		     MLX5_UMR_MTT_ALIGNMENT);
-}
-
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 				       struct mlx5e_icosq *sq,
-				       struct mlx5e_umr_wqe *wqe,
-				       u16 ix)
+				       struct mlx5e_umr_wqe *wqe)
 {
 	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->ctrl;
 	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
-	struct mlx5_wqe_data_seg      *dseg = &wqe->data;
-	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-	u8 ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
-	u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix);
+	u8 ds_cnt = DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_DS);
 
 	cseg->qpn_ds    = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
 				      ds_cnt);
 	cseg->fm_ce_se  = MLX5_WQE_CTRL_CQ_UPDATE;
 	cseg->imm       = rq->mkey_be;
 
-	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN;
+	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
 	ucseg->xlt_octowords =
 		cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
-	ucseg->bsf_octowords =
-		cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset));
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
-
-	dseg->lkey = sq->mkey_be;
-	dseg->addr = cpu_to_be64(wi->umr.mtt_addr);
 }
 
 static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 				     struct mlx5e_channel *c)
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
-	int mtt_sz = mlx5e_get_wqe_mtt_sz();
-	int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
-	int i;
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
 				      GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
-		goto err_out;
-
-	/* We allocate more than mtt_sz as we will align the pointer */
-	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
-					cpu_to_node(c->cpu));
-	if (unlikely(!rq->mpwqe.mtt_no_align))
-		goto err_free_wqe_info;
-
-	for (i = 0; i < wq_sz; i++) {
-		struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
-
-		wi->umr.mtt = PTR_ALIGN(rq->mpwqe.mtt_no_align + i * mtt_alloc,
-					MLX5_UMR_ALIGN);
-		wi->umr.mtt_addr = dma_map_single(c->pdev, wi->umr.mtt, mtt_sz,
-						  PCI_DMA_TODEVICE);
-		if (unlikely(dma_mapping_error(c->pdev, wi->umr.mtt_addr)))
-			goto err_unmap_mtts;
+		return -ENOMEM;
 
-		mlx5e_build_umr_wqe(rq, &c->icosq, &wi->umr.wqe, i);
-	}
+	mlx5e_build_umr_wqe(rq, &c->icosq, &rq->mpwqe.umr_wqe);
 
 	return 0;
-
-err_unmap_mtts:
-	while (--i >= 0) {
-		struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
-
-		dma_unmap_single(c->pdev, wi->umr.mtt_addr, mtt_sz,
-				 PCI_DMA_TODEVICE);
-	}
-	kfree(rq->mpwqe.mtt_no_align);
-err_free_wqe_info:
-	kfree(rq->mpwqe.info);
-
-err_out:
-	return -ENOMEM;
-}
-
-static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
-{
-	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
-	int mtt_sz = mlx5e_get_wqe_mtt_sz();
-	int i;
-
-	for (i = 0; i < wq_sz; i++) {
-		struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
-
-		dma_unmap_single(rq->pdev, wi->umr.mtt_addr, mtt_sz,
-				 PCI_DMA_TODEVICE);
-	}
-	kfree(rq->mpwqe.mtt_no_align);
-	kfree(rq->mpwqe.info);
 }
 
 static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
@@ -351,9 +347,6 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	u32 *in;
 	int err;
 
-	if (!MLX5E_VALID_NUM_MTTS(npages))
-		return -EINVAL;
-
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -386,6 +379,11 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
 }
 
+static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
+{
+	return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
+}
+
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_rq_param *rqp,
@@ -419,6 +417,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
+	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
 	if (IS_ERR(rq->xdp_prog)) {
@@ -432,11 +431,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		goto err_rq_wq_destroy;
 
 	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-	rq->buff.headroom = mlx5e_get_rq_headroom(params);
+	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-
 		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
@@ -454,6 +452,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_rq_wq_destroy;
 		}
 
+		rq->mpwqe.skb_from_cqe_mpwrq =
+			mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ?
+			mlx5e_skb_from_cqe_mpwrq_linear :
+			mlx5e_skb_from_cqe_mpwrq_nonlinear;
 		rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params);
 		rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params));
 
@@ -494,7 +496,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		byte_count = params->lro_en  ?
 				params->lro_wqe_sz :
-				MLX5E_SW2HW_MTU(c->priv, c->netdev->mtu);
+				MLX5E_SW2HW_MTU(params, params->sw_mtu);
 #ifdef CONFIG_MLX5_EN_IPSEC
 		if (MLX5_IPSEC_DEV(mdev))
 			byte_count += MLX5E_METADATA_ETHER_LEN;
@@ -514,9 +516,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
 
 		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-			u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, i) << PAGE_SHIFT;
+			u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
 
-			wqe->data.addr = cpu_to_be64(dma_offset);
+			wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom);
 		}
 
 		wqe->data.byte_count = cpu_to_be32(byte_count);
@@ -562,7 +564,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		mlx5e_rq_free_mpwqe_info(rq);
+		kfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
@@ -901,7 +903,6 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
 
-	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
@@ -1867,18 +1868,21 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		MLX5_SET(wq, wq, log_wqe_num_of_strides,
-			 mlx5e_mpwqe_get_log_num_strides(mdev, params) - 9);
+			 mlx5e_mpwqe_get_log_num_strides(mdev, params) -
+			 MLX5_MPWQE_LOG_NUM_STRIDES_BASE);
 		MLX5_SET(wq, wq, log_wqe_stride_size,
-			 mlx5e_mpwqe_get_log_stride_size(mdev, params) - 6);
+			 mlx5e_mpwqe_get_log_stride_size(mdev, params) -
+			 MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
 		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+		MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
 	}
 
 	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
-	MLX5_SET(wq, wq, log_wq_sz,        params->log_rq_size);
 	MLX5_SET(wq, wq, pd,               mdev->mlx5e_res.pdn);
 	MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
@@ -1938,16 +1942,17 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 				    struct mlx5e_params *params,
 				    struct mlx5e_cq_param *param)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		log_cq_size = params->log_rq_size +
-			mlx5e_mpwqe_get_log_num_strides(priv->mdev, params);
+		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
+			mlx5e_mpwqe_get_log_num_strides(mdev, params);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		log_cq_size = params->log_rq_size;
+		log_cq_size = params->log_rq_mtu_frames;
 	}
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
@@ -2498,10 +2503,10 @@ static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
 	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
 }
 
-static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
+static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
+			 struct mlx5e_params *params, u16 mtu)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 hw_mtu = MLX5E_SW2HW_MTU(priv, mtu);
+	u16 hw_mtu = MLX5E_SW2HW_MTU(params, mtu);
 	int err;
 
 	err = mlx5_set_port_mtu(mdev, hw_mtu, 1);
@@ -2513,9 +2518,9 @@ static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
 	return 0;
 }
 
-static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
+static void mlx5e_query_mtu(struct mlx5_core_dev *mdev,
+			    struct mlx5e_params *params, u16 *mtu)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 hw_mtu = 0;
 	int err;
 
@@ -2523,25 +2528,27 @@ static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
 	if (err || !hw_mtu) /* fallback to port oper mtu */
 		mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1);
 
-	*mtu = MLX5E_HW2SW_MTU(priv, hw_mtu);
+	*mtu = MLX5E_HW2SW_MTU(params, hw_mtu);
 }
 
 static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 {
+	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 mtu;
 	int err;
 
-	err = mlx5e_set_mtu(priv, netdev->mtu);
+	err = mlx5e_set_mtu(mdev, params, params->sw_mtu);
 	if (err)
 		return err;
 
-	mlx5e_query_mtu(priv, &mtu);
-	if (mtu != netdev->mtu)
+	mlx5e_query_mtu(mdev, params, &mtu);
+	if (mtu != params->sw_mtu)
 		netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n",
-			    __func__, mtu, netdev->mtu);
+			    __func__, mtu, params->sw_mtu);
 
-	netdev->mtu = mtu;
+	params->sw_mtu = mtu;
 	return 0;
 }
 
@@ -3222,20 +3229,28 @@ typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable);
 static int set_feature_lro(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channels new_channels = {};
+	struct mlx5e_params *old_params;
 	int err = 0;
 	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	reset = (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST);
-	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
+	old_params = &priv->channels.params;
+	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	new_channels.params = priv->channels.params;
+	new_channels.params = *old_params;
 	new_channels.params.lro_en = enable;
 
+	if (old_params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) ==
+		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params))
+			reset = false;
+	}
+
 	if (!reset) {
-		priv->channels.params = new_channels.params;
+		*old_params = new_channels.params;
 		err = mlx5e_modify_tirs_lro(priv);
 		goto out;
 	}
@@ -3411,34 +3426,40 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
-	int curr_mtu;
+	struct mlx5e_params *params;
 	int err = 0;
 	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	reset = !priv->channels.params.lro_en &&
-		(priv->channels.params.rq_wq_type !=
-		 MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+	params = &priv->channels.params;
 
+	reset = !params->lro_en;
 	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	curr_mtu    = netdev->mtu;
-	netdev->mtu = new_mtu;
+	new_channels.params = *params;
+	new_channels.params.sw_mtu = new_mtu;
+
+	if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
+		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
+
+		reset = reset && (ppw_old != ppw_new);
+	}
 
 	if (!reset) {
+		params->sw_mtu = new_mtu;
 		mlx5e_set_dev_port_mtu(priv);
+		netdev->mtu = params->sw_mtu;
 		goto out;
 	}
 
-	new_channels.params = priv->channels.params;
 	err = mlx5e_open_channels(priv, &new_channels);
-	if (err) {
-		netdev->mtu = curr_mtu;
+	if (err)
 		goto out;
-	}
 
 	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
+	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
 	mutex_unlock(&priv->state_lock);
@@ -3728,21 +3749,11 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
 					struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int irqn_not_used, eqn;
-	struct mlx5_eq *eq;
+	struct mlx5_eq *eq = sq->cq.mcq.eq;
 	u32 eqe_count;
 
-	if (mlx5_vector2eqn(mdev, sq->cq.mcq.vector, &eqn, &irqn_not_used))
-		return false;
-
-	eq = mlx5_eqn2eq(mdev, eqn);
-	if (IS_ERR(eq))
-		return false;
-
 	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eqn, eq->cons_index, eq->irqn);
+		   eq->eqn, eq->cons_index, eq->irqn);
 
 	eqe_count = mlx5_eq_poll_irq_disabled(eq);
 	if (!eqe_count)
@@ -4121,10 +4132,12 @@ static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeo
 
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
-			    u16 max_channels)
+			    u16 max_channels, u16 mtu)
 {
 	u8 cq_period_mode = 0;
 
+	params->sw_mtu = mtu;
+	params->hard_mtu = MLX5E_ETH_HARD_MTU;
 	params->num_channels = max_channels;
 	params->num_tc       = 1;
 
@@ -4152,7 +4165,8 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 
 	/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		params->lro_en = !slow_pci_heuristic(mdev);
+		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+			params->lro_en = !slow_pci_heuristic(mdev);
 	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
@@ -4185,9 +4199,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	priv->profile     = profile;
 	priv->ppriv       = ppriv;
 	priv->msglevel    = MLX5E_MSG_LEVEL;
-	priv->hard_mtu = MLX5E_ETH_HARD_MTU;
 
-	mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+	mlx5e_build_nic_params(mdev, &priv->channels.params,
+			       profile->max_nch(mdev), netdev->mtu);
 
 	mutex_init(&priv->state_lock);
 
@@ -4464,7 +4478,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	/* MTU range: 68 - hw-specific max */
 	netdev->min_mtu = ETH_MIN_MTU;
 	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(priv, max_mtu);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 	mlx5e_set_dev_port_mtu(priv);
 
 	mlx5_lag_add(mdev, netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index dd32f3e390ff..8e70fa9ef39a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -877,9 +877,10 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
+	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
 	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
-	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	params->log_rq_mtu_frames = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
@@ -926,8 +927,6 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
 
 	priv->channels.params.num_channels = profile->max_nch(mdev);
 
-	priv->hard_mtu = MLX5E_ETH_HARD_MTU;
-
 	mlx5e_build_rep_params(mdev, &priv->channels.params);
 	mlx5e_build_rep_netdev(netdev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 781b8f21d6d1..176645762e49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -296,37 +296,28 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 		mlx5e_free_rx_wqe(rq, wi);
 }
 
-static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
-{
-	return rq->mpwqe.num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
-}
-
 static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
 					    struct sk_buff *skb,
-					    struct mlx5e_mpw_info *wi,
-					    u32 page_idx, u32 frag_offset,
-					    u32 len)
+					    struct mlx5e_dma_info *di,
+					    u32 frag_offset, u32 len)
 {
 	unsigned int truesize = ALIGN(len, BIT(rq->mpwqe.log_stride_sz));
 
 	dma_sync_single_for_cpu(rq->pdev,
-				wi->umr.dma_info[page_idx].addr + frag_offset,
+				di->addr + frag_offset,
 				len, DMA_FROM_DEVICE);
-	wi->skbs_frags[page_idx]++;
+	page_ref_inc(di->page);
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-			wi->umr.dma_info[page_idx].page, frag_offset,
-			len, truesize);
+			di->page, frag_offset, len, truesize);
 }
 
 static inline void
 mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 			    struct sk_buff *skb,
-			    struct mlx5e_mpw_info *wi,
-			    u32 page_idx, u32 offset,
-			    u32 headlen)
+			    struct mlx5e_dma_info *dma_info,
+			    u32 offset, u32 headlen)
 {
 	u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset);
-	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[page_idx];
 	unsigned int len;
 
 	 /* Aligning len to sizeof(long) optimizes memcpy performance */
@@ -347,14 +338,49 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 	}
 }
 
-static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
+void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
+{
+	const bool no_xdp_xmit =
+		bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
+	struct mlx5e_dma_info *dma_info = wi->umr.dma_info;
+	int i;
+
+	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
+		if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
+			mlx5e_page_release(rq, &dma_info[i], true);
+}
+
+static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
+
+	rq->mpwqe.umr_in_progress = false;
+
+	mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
+
+	/* ensure wqes are visible to device before updating doorbell record */
+	dma_wmb();
+
+	mlx5_wq_ll_update_db_record(wq);
+}
+
+static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
+{
+	return sq->pc >> MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+}
+
+static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
+	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
 	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_umr_wqe *wqe;
-	u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
+	struct mlx5e_umr_wqe *umr_wqe;
+	u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
+	int err;
 	u16 pi;
+	int i;
 
 	/* fill sq edge with nops to avoid wqe wrap around */
 	while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
@@ -362,90 +388,44 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
 
-	wqe = mlx5_wq_cyc_get_wqe(wq, pi);
-	memcpy(wqe, &wi->umr.wqe, sizeof(*wqe));
-	wqe->ctrl.opmod_idx_opcode =
-		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
-			    MLX5_OPCODE_UMR);
-
-	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
-	sq->pc += num_wqebbs;
-	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
-}
-
-static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
-				    u16 ix)
-{
-	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-	int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
-	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
-	int err;
-	int i;
+	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+	if (unlikely(mlx5e_icosq_wrap_cnt(sq) < 2))
+		memcpy(umr_wqe, &rq->mpwqe.umr_wqe,
+		       offsetof(struct mlx5e_umr_wqe, inline_mtts));
 
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
 		err = mlx5e_page_alloc_mapped(rq, dma_info);
 		if (unlikely(err))
 			goto err_unmap;
-		wi->umr.mtt[i] = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
-		page_ref_add(dma_info->page, pg_strides);
+		umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
 	}
 
-	memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE);
+	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);
+	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
+
+	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
+	sq->pc += MLX5E_UMR_WQEBBS;
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+
 	return 0;
 
 err_unmap:
 	while (--i >= 0) {
 		dma_info--;
-		page_ref_sub(dma_info->page, pg_strides);
 		mlx5e_page_release(rq, dma_info, true);
 	}
+	rq->stats.buff_alloc_err++;
 
 	return err;
 }
 
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
-{
-	int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
-	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
-	int i;
-
-	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
-		page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
-		mlx5e_page_release(rq, dma_info, true);
-	}
-}
-
-static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
-{
-	struct mlx5_wq_ll *wq = &rq->wq;
-	struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
-
-	rq->mpwqe.umr_in_progress = false;
-
-	mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
-
-	/* ensure wqes are visible to device before updating doorbell record */
-	dma_wmb();
-
-	mlx5_wq_ll_update_db_record(wq);
-}
-
-static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
-{
-	int err;
-
-	err = mlx5e_alloc_rx_umr_mpwqe(rq, ix);
-	if (unlikely(err)) {
-		rq->stats.buff_alloc_err++;
-		return err;
-	}
-	rq->mpwqe.umr_in_progress = true;
-	mlx5e_post_umr_wqe(rq, ix);
-	return 0;
-}
-
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
@@ -544,7 +524,7 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 	if (!rq->mpwqe.umr_in_progress)
 		mlx5e_alloc_rx_mpwqe(rq, wq->head);
 
-	return true;
+	return false;
 }
 
 static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
@@ -766,8 +746,7 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
 
 	prefetchw(wqe);
 
-	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE ||
-		     MLX5E_SW2HW_MTU(rq->channel->priv, rq->netdev->mtu) < dma_len)) {
+	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
 		rq->stats.xdp_drop++;
 		return false;
 	}
@@ -806,7 +785,7 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
 	/* move page to reference to sq responsibility,
 	 * and mark so it's not put back in page-cache.
 	 */
-	rq->wqe.xdp_xmit = true;
+	__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
 	sq->db.di[pi] = *di;
 	sq->pc++;
 
@@ -855,6 +834,24 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
 }
 
 static inline
+struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
+				       u32 frag_size, u16 headroom,
+				       u32 cqe_bcnt)
+{
+	struct sk_buff *skb = build_skb(va, frag_size);
+
+	if (unlikely(!skb)) {
+		rq->stats.buff_alloc_err++;
+		return NULL;
+	}
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, cqe_bcnt);
+
+	return skb;
+}
+
+static inline
 struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
@@ -885,18 +882,13 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	if (consumed)
 		return NULL; /* page/packet was consumed by XDP */
 
-	skb = build_skb(va, frag_size);
-	if (unlikely(!skb)) {
-		rq->stats.buff_alloc_err++;
+	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
+	if (unlikely(!skb))
 		return NULL;
-	}
 
 	/* queue up for recycling/reuse */
 	page_ref_inc(di->page);
 
-	skb_reserve(skb, rx_headroom);
-	skb_put(skb, cqe_bcnt);
-
 	return skb;
 }
 
@@ -918,9 +910,8 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
-		if (rq->wqe.xdp_xmit) {
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			wi->di.page = NULL;
-			rq->wqe.xdp_xmit = false;
 			/* do not return page to cache, it will be returned on XDP_TX completion */
 			goto wq_ll_pop;
 		}
@@ -960,9 +951,8 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (!skb) {
-		if (rq->wqe.xdp_xmit) {
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			wi->di.page = NULL;
-			rq->wqe.xdp_xmit = false;
 			/* do not return page to cache, it will be returned on XDP_TX completion */
 			goto wq_ll_pop;
 		}
@@ -985,23 +975,28 @@ wq_ll_pop:
 }
 #endif
 
-static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
-					   struct mlx5_cqe64 *cqe,
-					   struct mlx5e_mpw_info *wi,
-					   u32 cqe_bcnt,
-					   struct sk_buff *skb)
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				   u16 cqe_bcnt, u32 head_offset, u32 page_idx)
 {
-	u16 stride_ix      = mpwrq_get_cqe_stride_index(cqe);
-	u32 wqe_offset     = stride_ix << rq->mpwqe.log_stride_sz;
-	u32 head_offset    = wqe_offset & (PAGE_SIZE - 1);
-	u32 page_idx       = wqe_offset >> PAGE_SHIFT;
-	u32 head_page_idx  = page_idx;
 	u16 headlen = min_t(u16, MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, cqe_bcnt);
+	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
 	u32 frag_offset    = head_offset + headlen;
-	u16 byte_cnt       = cqe_bcnt - headlen;
+	u32 byte_cnt       = cqe_bcnt - headlen;
+	struct mlx5e_dma_info *head_di = di;
+	struct sk_buff *skb;
+
+	skb = napi_alloc_skb(rq->cq.napi,
+			     ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, sizeof(long)));
+	if (unlikely(!skb)) {
+		rq->stats.buff_alloc_err++;
+		return NULL;
+	}
+
+	prefetchw(skb->data);
 
 	if (unlikely(frag_offset >= PAGE_SIZE)) {
-		page_idx++;
+		di++;
 		frag_offset -= PAGE_SIZE;
 	}
 
@@ -1009,18 +1004,59 @@ static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
 		u32 pg_consumed_bytes =
 			min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
 
-		mlx5e_add_skb_frag_mpwqe(rq, skb, wi, page_idx, frag_offset,
+		mlx5e_add_skb_frag_mpwqe(rq, skb, di, frag_offset,
 					 pg_consumed_bytes);
 		byte_cnt -= pg_consumed_bytes;
 		frag_offset = 0;
-		page_idx++;
+		di++;
 	}
 	/* copy header */
-	mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, wi, head_page_idx,
+	mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, head_di,
 				    head_offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
+
+	return skb;
+}
+
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				u16 cqe_bcnt, u32 head_offset, u32 page_idx)
+{
+	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
+	u16 rx_headroom = rq->buff.headroom;
+	u32 cqe_bcnt32 = cqe_bcnt;
+	struct sk_buff *skb;
+	void *va, *data;
+	u32 frag_size;
+	bool consumed;
+
+	va             = page_address(di->page) + head_offset;
+	data           = va + rx_headroom;
+	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
+
+	dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset,
+				      frag_size, DMA_FROM_DEVICE);
+	prefetch(data);
+
+	rcu_read_lock();
+	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32);
+	rcu_read_unlock();
+	if (consumed) {
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
+			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
+		return NULL; /* page/packet was consumed by XDP */
+	}
+
+	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* queue up for recycling/reuse */
+	page_ref_inc(di->page);
+
+	return skb;
 }
 
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -1028,7 +1064,11 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	u16 cstrides       = mpwrq_get_cqe_consumed_strides(cqe);
 	u16 wqe_id         = be16_to_cpu(cqe->wqe_id);
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[wqe_id];
-	struct mlx5e_rx_wqe  *wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id);
+	u16 stride_ix      = mpwrq_get_cqe_stride_index(cqe);
+	u32 wqe_offset     = stride_ix << rq->mpwqe.log_stride_sz;
+	u32 head_offset    = wqe_offset & (PAGE_SIZE - 1);
+	u32 page_idx       = wqe_offset >> PAGE_SHIFT;
+	struct mlx5e_rx_wqe *wqe;
 	struct sk_buff *skb;
 	u16 cqe_bcnt;
 
@@ -1044,18 +1084,13 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto mpwrq_cqe_out;
 	}
 
-	skb = napi_alloc_skb(rq->cq.napi,
-			     ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD,
-				   sizeof(long)));
-	if (unlikely(!skb)) {
-		rq->stats.buff_alloc_err++;
-		goto mpwrq_cqe_out;
-	}
-
-	prefetchw(skb->data);
 	cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
 
-	mlx5e_mpwqe_fill_rx_skb(rq, cqe, wi, cqe_bcnt, skb);
+	skb = rq->mpwqe.skb_from_cqe_mpwrq(rq, wi, cqe_bcnt, head_offset,
+					   page_idx);
+	if (!skb)
+		goto mpwrq_cqe_out;
+
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
@@ -1063,6 +1098,7 @@ mpwrq_cqe_out:
 	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
 		return;
 
+	wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id);
 	mlx5e_free_rx_mpwqe(rq, wi);
 	mlx5_wq_ll_pop(&rq->wq, cqe->wqe_id, &wqe->next.next_wqe_index);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index d7bb10ab2173..70066975f1b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -245,7 +245,7 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev)
 
 	force_state = MLX5_GET(teardown_hca_out, out, force_state);
 	if (force_state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) {
-		mlx5_core_err(dev, "teardown with force mode failed\n");
+		mlx5_core_warn(dev, "teardown with force mode failed, doing normal teardown\n");
 		return -EIO;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index a35608faf8d2..af3bb2f7a504 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -61,11 +61,12 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 	mlx5e_init_rq_type_params(mdev, params);
 
 	/* RQ size in ipoib by default is 512 */
-	params->log_rq_size = is_kdump_kernel() ?
+	params->log_rq_mtu_frames = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE;
 
 	params->lro_en = false;
+	params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
 }
 
 /* Called directly after IPoIB netdevice was created to initialize SW structs */
@@ -81,10 +82,10 @@ void mlx5i_init(struct mlx5_core_dev *mdev,
 	priv->netdev      = netdev;
 	priv->profile     = profile;
 	priv->ppriv       = ppriv;
-	priv->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
 	mutex_init(&priv->state_lock);
 
-	mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+	mlx5e_build_nic_params(mdev, &priv->channels.params,
+			       profile->max_nch(mdev), netdev->mtu);
 	mlx5i_build_nic_params(mdev, &priv->channels.params);
 
 	mlx5e_timestamp_init(priv);
@@ -368,25 +369,27 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
 	struct mlx5e_channels new_channels = {};
-	int curr_mtu;
+	struct mlx5e_params *params;
 	int err = 0;
 
 	mutex_lock(&priv->state_lock);
 
-	curr_mtu    = netdev->mtu;
-	netdev->mtu = new_mtu;
+	params = &priv->channels.params;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		params->sw_mtu = new_mtu;
+		netdev->mtu = params->sw_mtu;
 		goto out;
+	}
 
-	new_channels.params = priv->channels.params;
+	new_channels.params = *params;
+	new_channels.params.sw_mtu = new_mtu;
 	err = mlx5e_open_channels(priv, &new_channels);
-	if (err) {
-		netdev->mtu = curr_mtu;
+	if (err)
 		goto out;
-	}
 
 	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
 	mutex_unlock(&priv->state_lock);
@@ -540,7 +543,7 @@ static int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
 
 	err = mlx5_core_detach_mcg(mdev, gid, ipriv->qp.qpn);
 	if (err)
-		mlx5_core_dbg(mdev, "failed dettaching QPN 0x%x, MGID %pI6\n",
+		mlx5_core_dbg(mdev, "failed detaching QPN 0x%x, MGID %pI6\n",
 			      ipriv->qp.qpn, gid->raw);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index b69e9d847a6b..54a188f41f90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -290,7 +290,7 @@ static void mlx5i_pkey_init(struct mlx5_core_dev *mdev,
 	netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops;
 
 	/* Use dummy rqs */
-	priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	priv->channels.params.log_rq_mtu_frames = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 }
 
 /* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index c64957b5ef47..dae1c5c5d27c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -354,27 +354,6 @@ int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 xsrqn)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-int mlx5_core_query_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u32 *out)
-{
-	u32 in[MLX5_ST_SZ_DW(query_xrc_srq_in)] = {0};
-	void *srqc;
-	void *xrc_srqc;
-	int err;
-
-	MLX5_SET(query_xrc_srq_in, in, opcode,   MLX5_CMD_OP_QUERY_XRC_SRQ);
-	MLX5_SET(query_xrc_srq_in, in, xrc_srqn, xsrqn);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out,
-			    MLX5_ST_SZ_BYTES(query_xrc_srq_out));
-	if (!err) {
-		xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, out,
-					xrc_srq_context_entry);
-		srqc = MLX5_ADDR_OF(query_srq_out, out, srq_context_entry);
-		memcpy(srqc, xrc_srqc, MLX5_ST_SZ_BYTES(srqc));
-	}
-
-	return err;
-}
-
 int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u16 lwm)
 {
 	u32 in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};