mlx5e-updates-2018-06-01

1) From Tariq, Two patches to Fix IPoIB issues introduced in
    "net/mlx5e: TX, Use actual WQE size for SQ edge fill"
 
 2) From Eran, Additional improvements to mlx5e statistics reporting
 
 3) From Maor, Increase aRFS flow tables size
 
 4) From Adi, Support MTU change for ethernet representors
 
 5) From Ilan and Adi, Handle QP error events in FPGA
 
 6) From Tariq, last 10 patches mainly deals with RX buffer scheme improvements for legacy RQ
    to use only order-0 pages and fragmented SKBs for large MTUs.
 
 -  Tariq starts with some refactoring and removing HW LRO support from traditional
    (legacy) RQ, since it complicates the buffer scheme and removing it makes it smoother
    to move to cyclic descriptor buffer for traditional RQ.
 
 - Use cyclic WQ in legacy RQ, which has many benefits and paves the way for fragmented SKBs
   for large MTUs.
 
 - Enhance legacy Receive Queue memory scheme, such that only order-0 pages are used.
   Whenever possible, prefer using a linear SKB, and build it wrapping the WQE buffer.
   Otherwise (for example, jumbo frames on x86), use non-linear SKB, with as many frags
   as needed. In this case, multiple WQE scatter entries are used, up to a maximum of 4
   frags and 10KB of MTU.
 
 - TX statistics access improvements.
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJbEdtNAAoJEEg/ir3gV/o+UgkH/RaMnaRB8sscXJHRHDS+PWIe
 d+nkvHCX/b8yOABzReoWfTzFjwqZR4JQ4otxFVJY357Jm3Dcobg+OwncS96LNShy
 a1U6O6GLtBJ+Z2NjHepdsSLWp4260+6AGwhkZ7lM71v+nkC4kGIR4ByBafh83RUq
 ezEF3oxqp9YSjGj1JPIGJlUEfUbc4+3uYNLMuH8hx3hZf96gGrDW+jRgSGGKOMJT
 MM6CPCsTZ3jqR/kSFiPoRsCywN/Q9vfZRgfKNuGaymqoSW8PiQdthwAtnA0OS3RG
 nyuuAPvAPDde48ZT/GSZiLEWvrR5NRPy7/kLEUaQzjqoftdrbmDNTeo+0zPqoaY=
 =ipPp
 -----END PGP SIGNATURE-----

Merge tag 'mlx5e-updates-2018-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5e-updates-2018-06-01

1) From Tariq, Two patches to Fix IPoIB issues introduced in
   "net/mlx5e: TX, Use actual WQE size for SQ edge fill"

2) From Eran, Additional improvements to mlx5e statistics reporting

3) From Maor, Increase aRFS flow tables size

4) From Adi, Support MTU change for ethernet representors

5) From Ilan and Adi, Handle QP error events in FPGA

6) From Tariq, last 10 patches mainly deals with RX buffer scheme improvements for legacy RQ
   to use only order-0 pages and fragmented SKBs for large MTUs.

-  Tariq starts with some refactoring and removing HW LRO support from traditional
   (legacy) RQ, since it complicates the buffer scheme and removing it makes it smoother
   to move to cyclic descriptor buffer for traditional RQ.

- Use cyclic WQ in legacy RQ, which has many benefits and paves the way for fragmented SKBs
  for large MTUs.

- Enhance legacy Receive Queue memory scheme, such that only order-0 pages are used.
  Whenever possible, prefer using a linear SKB, and build it wrapping the WQE buffer.
  Otherwise (for example, jumbo frames on x86), use non-linear SKB, with as many frags
  as needed. In this case, multiple WQE scatter entries are used, up to a maximum of 4
  frags and 10KB of MTU.

- TX statistics access improvements.
====================

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

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

@@ -101,18 +101,22 @@ struct page_pool;
 	(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW + \
 	 (MLX5_MPWRQ_LOG_WQE_SZ - MLX5E_ORDER2_MAX_PACKET_MTU))
 
+#define MLX5E_MIN_SKB_FRAG_SZ		(MLX5_SKB_FRAG_SZ(MLX5_RX_HEADROOM))
+#define MLX5E_LOG_MAX_RX_WQE_BULK	\
+	(ilog2(PAGE_SIZE / roundup_pow_of_two(MLX5E_MIN_SKB_FRAG_SZ)))
+
 #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_MINIMUM_LOG_RQ_SIZE (1 + MLX5E_LOG_MAX_RX_WQE_BULK)
 #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_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
+#define MLX5E_RX_MAX_HEAD (256)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
@@ -186,9 +190,13 @@ struct mlx5e_tx_wqe {
 	struct mlx5_wqe_data_seg data[0];
 };
 
-struct mlx5e_rx_wqe {
+struct mlx5e_rx_wqe_ll {
 	struct mlx5_wqe_srq_next_seg  next;
-	struct mlx5_wqe_data_seg      data;
+	struct mlx5_wqe_data_seg      data[0];
+};
+
+struct mlx5e_rx_wqe_cyc {
+	struct mlx5_wqe_data_seg      data[0];
 };
 
 struct mlx5e_umr_wqe {
@@ -458,8 +466,9 @@ struct mlx5e_dma_info {
 };
 
 struct mlx5e_wqe_frag_info {
-	struct mlx5e_dma_info di;
+	struct mlx5e_dma_info *di;
 	u32 offset;
+	bool last_in_page;
 };
 
 struct mlx5e_umr_dma_info {
@@ -472,6 +481,8 @@ struct mlx5e_mpw_info {
 	DECLARE_BITMAP(xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
 };
 
+#define MLX5E_MAX_RX_FRAGS 4
+
 /* a single cache unit is capable to serve one napi call (for non-striding rq)
  * or a MPWQE (for striding rq).
  */
@@ -489,6 +500,9 @@ 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 struct sk_buff *
+(*mlx5e_fp_skb_from_cqe)(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+			 struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
 typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
 typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
 
@@ -496,19 +510,30 @@ enum mlx5e_rq_flag {
 	MLX5E_RQ_FLAG_XDP_XMIT = BIT(0),
 };
 
+struct mlx5e_rq_frag_info {
+	int frag_size;
+	int frag_stride;
+};
+
+struct mlx5e_rq_frags_info {
+	struct mlx5e_rq_frag_info arr[MLX5E_MAX_RX_FRAGS];
+	u8 num_frags;
+	u8 log_num_frags;
+	u8 wqe_bulk;
+};
+
 struct mlx5e_rq {
 	/* data path */
-	struct mlx5_wq_ll      wq;
-
 	union {
 		struct {
-			struct mlx5e_wqe_frag_info *frag_info;
+			struct mlx5_wq_cyc          wq;
-			u32 frag_sz;	/* max possible skb frag_sz */
+			struct mlx5e_wqe_frag_info *frags;
-			union {
+			struct mlx5e_dma_info      *di;
-				bool page_reuse;
+			struct mlx5e_rq_frags_info  info;
-			};
+			mlx5e_fp_skb_from_cqe       skb_from_cqe;
 		} wqe;
 		struct {
+			struct mlx5_wq_ll      wq;
 			struct mlx5e_umr_wqe   umr_wqe;
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
@@ -519,7 +544,6 @@ struct mlx5e_rq {
 	};
 	struct {
 		u16            headroom;
-		u8             page_order;
 		u8             map_dir;   /* dma map direction */
 	} buff;
 
@@ -777,8 +801,6 @@ struct mlx5e_priv {
 	struct mutex               state_lock; /* Protects Interface state */
 	struct mlx5e_rq            drop_rq;
 
-	rwlock_t                   stats_lock; /* Protects channels SW stats updates */
-	bool                       channels_active;
 	struct mlx5e_channels      channels;
 	u32                        tisn[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rqt           indir_rqt;
@@ -877,6 +899,12 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 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);
+struct sk_buff *
+mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+			  struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
+struct sk_buff *
+mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
@@ -1104,6 +1132,10 @@ void mlx5e_update_stats_work(struct work_struct *work);
 
 int mlx5e_bits_invert(unsigned long a, int size);
 
+typedef int (*change_hw_mtu_cb)(struct mlx5e_priv *priv);
+int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
+		     change_hw_mtu_cb set_mtu_cb);
+
 /* ethtool helpers */
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo);

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

@@ -213,7 +213,7 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 }
 
 #define MLX5E_ARFS_NUM_GROUPS	2
-#define MLX5E_ARFS_GROUP1_SIZE	BIT(12)
+#define MLX5E_ARFS_GROUP1_SIZE	(BIT(16) - 1)
 #define MLX5E_ARFS_GROUP2_SIZE	BIT(0)
 #define MLX5E_ARFS_TABLE_SIZE	(MLX5E_ARFS_GROUP1_SIZE +\
 				 MLX5E_ARFS_GROUP2_SIZE)

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

@@ -1515,6 +1515,9 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 			return -EOPNOTSUPP;
 		if (!mlx5e_striding_rq_possible(mdev, &priv->channels.params))
 			return -EINVAL;
+	} else if (priv->channels.params.lro_en) {
+		netdev_warn(netdev, "Can't set legacy RQ with LRO, disable LRO first\n");
+		return -EINVAL;
 	}
 
 	new_channels.params = priv->channels.params;
@@ -1589,6 +1592,10 @@ static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags)
 
 out:
 	mutex_unlock(&priv->state_lock);
+
+	/* Need to fix some features.. */
+	netdev_update_features(netdev);
+
 	return err;
 }
 

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

@@ -51,6 +51,7 @@
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param	wq;
+	struct mlx5e_rq_frags_info frags_info;
 };
 
 struct mlx5e_sq_param {
@@ -93,7 +94,7 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 	return true;
 }
 
-static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
+static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
 {
 	if (!params->xdp_prog) {
 		u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
@@ -107,19 +108,27 @@ static u32 mlx5e_mpwqe_get_linear_frag_sz(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);
+	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;
+}
+
 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);
+	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
 	s8 signed_log_num_strides_param;
 	u8 log_num_strides;
 
-	if (params->lro_en || frag_sz > PAGE_SIZE)
+	if (!mlx5e_rx_is_linear_skb(mdev, params))
 		return false;
 
 	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
@@ -145,7 +154,7 @@ 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 order_base_2(mlx5e_rx_get_linear_frag_sz(params));
 
 	return MLX5E_MPWQE_STRIDE_SZ(mdev,
 		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
@@ -163,16 +172,15 @@ static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 {
 	u16 linear_rq_headroom = params->xdp_prog ?
 		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	bool is_linear_skb;
 
 	linear_rq_headroom += NET_IP_ALIGN;
 
-	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST)
+	is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
-		return linear_rq_headroom;
+		mlx5e_rx_is_linear_skb(mdev, params) :
+		mlx5e_rx_mpwqe_is_linear_skb(mdev, params);
 
-	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+	return is_linear_skb ? linear_rq_headroom : 0;
-		return linear_rq_headroom;
-
-	return 0;
 }
 
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
@@ -182,14 +190,6 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 	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:
-		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		/* Extra room needed for build_skb */
-		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,
@@ -213,7 +213,7 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 	params->rq_wq_type = mlx5e_striding_rq_possible(mdev, params) &&
 		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ) ?
 		MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
-		MLX5_WQ_TYPE_LINKED_LIST;
+		MLX5_WQ_TYPE_CYCLIC;
 }
 
 static void mlx5e_update_carrier(struct mlx5e_priv *priv)
@@ -327,10 +327,30 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
+static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
+{
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
+	default:
+		return mlx5_wq_cyc_get_size(&rq->wqe.wq);
+	}
+}
+
+static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
+{
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return rq->mpwqe.wq.cur_sz;
+	default:
+		return rq->wqe.wq.cur_sz;
+	}
+}
+
 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 wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
 				      GFP_KERNEL, cpu_to_node(c->cpu));
@@ -378,7 +398,7 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 
 static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq)
 {
-	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->wq));
+	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq));
 
 	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
 }
@@ -388,6 +408,61 @@ 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 void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
+{
+	struct mlx5e_wqe_frag_info next_frag, *prev;
+	int i;
+
+	next_frag.di = &rq->wqe.di[0];
+	next_frag.offset = 0;
+	prev = NULL;
+
+	for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) {
+		struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+		struct mlx5e_wqe_frag_info *frag =
+			&rq->wqe.frags[i << rq->wqe.info.log_num_frags];
+		int f;
+
+		for (f = 0; f < rq->wqe.info.num_frags; f++, frag++) {
+			if (next_frag.offset + frag_info[f].frag_stride > PAGE_SIZE) {
+				next_frag.di++;
+				next_frag.offset = 0;
+				if (prev)
+					prev->last_in_page = true;
+			}
+			*frag = next_frag;
+
+			/* prepare next */
+			next_frag.offset += frag_info[f].frag_stride;
+			prev = frag;
+		}
+	}
+
+	if (prev)
+		prev->last_in_page = true;
+}
+
+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;
+
+	rq->wqe.di = kvzalloc_node(len * sizeof(*rq->wqe.di),
+				   GFP_KERNEL, cpu_to_node(cpu));
+	if (!rq->wqe.di)
+		return -ENOMEM;
+
+	mlx5e_init_frags_partition(rq);
+
+	return 0;
+}
+
+static void mlx5e_free_di_list(struct mlx5e_rq *rq)
+{
+	kvfree(rq->wqe.di);
+}
+
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_rq_param *rqp,
@@ -397,23 +472,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->mdev;
 	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
-	u32 byte_count, pool_size;
+	u32 pool_size;
-	int npages;
 	int wq_sz;
 	int err;
 	int i;
 
 	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
 
-	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
-				&rq->wq_ctrl);
-	if (err)
-		return err;
-
-	rq->wq.db = &rq->wq.db[MLX5_RCV_DBR];
-
-	wq_sz = mlx5_wq_ll_get_size(&rq->wq);
-
 	rq->wq_type = params->rq_wq_type;
 	rq->pdev    = c->pdev;
 	rq->netdev  = c->netdev;
@@ -442,8 +507,17 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
+					&rq->wq_ctrl);
+		if (err)
+			return err;
+
+		rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR];
+
+		wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
 		pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params);
+
 		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
@@ -468,8 +542,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		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));
 
-		byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
-
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_wq_destroy;
@@ -477,16 +549,29 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		err = mlx5e_rq_alloc_mpwqe_info(rq, c);
 		if (err)
-			goto err_destroy_umr_mkey;
+			goto err_free;
 		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
+	default: /* MLX5_WQ_TYPE_CYCLIC */
-		rq->wqe.frag_info =
+		err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq,
-			kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
+					 &rq->wq_ctrl);
-				     GFP_KERNEL, cpu_to_node(c->cpu));
+		if (err)
-		if (!rq->wqe.frag_info) {
+			return err;
-			err = -ENOMEM;
+
-			goto err_rq_wq_destroy;
+		rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR];
-		}
+
+		wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq);
+
+		rq->wqe.info = rqp->frags_info;
+		rq->wqe.frags =
+			kvzalloc_node((wq_sz << rq->wqe.info.log_num_frags) *
+				      sizeof(*rq->wqe.frags),
+				      GFP_KERNEL, cpu_to_node(c->cpu));
+		if (!rq->wqe.frags)
+			goto err_free;
+
+		err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu);
+		if (err)
+			goto err_free;
 		rq->post_wqes = mlx5e_post_rx_wqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
@@ -497,32 +582,19 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 #endif
 			rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe;
 		if (!rq->handle_rx_cqe) {
-			kfree(rq->wqe.frag_info);
 			err = -EINVAL;
 			netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err);
-			goto err_rq_wq_destroy;
+			goto err_free;
 		}
 
-		byte_count = params->lro_en  ?
+		rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(mdev, params) ?
-				params->lro_wqe_sz :
+			mlx5e_skb_from_cqe_linear :
-				MLX5E_SW2HW_MTU(params, params->sw_mtu);
+			mlx5e_skb_from_cqe_nonlinear;
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if (MLX5_IPSEC_DEV(mdev))
-			byte_count += MLX5E_METADATA_ETHER_LEN;
-#endif
-		rq->wqe.page_reuse = !params->xdp_prog && !params->lro_en;
-
-		/* calc the required page order */
-		rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->buff.headroom + byte_count);
-		npages = DIV_ROUND_UP(rq->wqe.frag_sz, PAGE_SIZE);
-		rq->buff.page_order = order_base_2(npages);
-
-		byte_count |= MLX5_HW_START_PADDING;
 		rq->mkey_be = c->mkey_be;
 	}
 
 	/* Create a page_pool and register it with rxq */
-	pp_params.order     = rq->buff.page_order;
+	pp_params.order     = 0;
 	pp_params.flags     = 0; /* No-internal DMA mapping in page_pool */
 	pp_params.pool_size = pool_size;
 	pp_params.nid       = cpu_to_node(c->cpu);
@@ -536,28 +608,45 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	 */
 	rq->page_pool = page_pool_create(&pp_params);
 	if (IS_ERR(rq->page_pool)) {
-		if (rq->wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-			kfree(rq->wqe.frag_info);
 		err = PTR_ERR(rq->page_pool);
 		rq->page_pool = NULL;
-		goto err_rq_wq_destroy;
+		goto err_free;
 	}
 	err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 					 MEM_TYPE_PAGE_POOL, rq->page_pool);
 	if (err)
-		goto err_rq_wq_destroy;
+		goto err_free;
 
 	for (i = 0; i < wq_sz; i++) {
-		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
-
 		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+			struct mlx5e_rx_wqe_ll *wqe =
+				mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i);
+			u32 byte_count =
+				rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
 			u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
 
-			wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom);
+			wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom);
-		}
+			wqe->data[0].byte_count = cpu_to_be32(byte_count);
+			wqe->data[0].lkey = rq->mkey_be;
+		} else {
+			struct mlx5e_rx_wqe_cyc *wqe =
+				mlx5_wq_cyc_get_wqe(&rq->wqe.wq, i);
+			int f;
 
-		wqe->data.byte_count = cpu_to_be32(byte_count);
+			for (f = 0; f < rq->wqe.info.num_frags; f++) {
-		wqe->data.lkey = rq->mkey_be;
+				u32 frag_size = rq->wqe.info.arr[f].frag_size |
+					MLX5_HW_START_PADDING;
+
+				wqe->data[f].byte_count = cpu_to_be32(frag_size);
+				wqe->data[f].lkey = rq->mkey_be;
+			}
+			/* check if num_frags is not a pow of two */
+			if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) {
+				wqe->data[f].byte_count = 0;
+				wqe->data[f].lkey = cpu_to_be32(MLX5_INVALID_LKEY);
+				wqe->data[f].addr = 0;
+			}
+		}
 	}
 
 	INIT_WORK(&rq->dim.work, mlx5e_rx_dim_work);
@@ -576,8 +665,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	return 0;
 
-err_destroy_umr_mkey:
+err_free:
-	mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		kfree(rq->mpwqe.info);
+		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+		break;
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		kvfree(rq->wqe.frags);
+		mlx5e_free_di_list(rq);
+	}
 
 err_rq_wq_destroy:
 	if (rq->xdp_prog)
@@ -606,8 +703,9 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 		kfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
+	default: /* MLX5_WQ_TYPE_CYCLIC */
-		kfree(rq->wqe.frag_info);
+		kvfree(rq->wqe.frags);
+		mlx5e_free_di_list(rq);
 	}
 
 	for (i = rq->page_cache.head; i != rq->page_cache.tail;
@@ -754,52 +852,53 @@ static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time);
 	struct mlx5e_channel *c = rq->channel;
 
-	struct mlx5_wq_ll *wq = &rq->wq;
+	u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5e_rqwq_get_size(rq));
-	u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
 
 	do {
-		if (wq->cur_sz >= min_wqes)
+		if (mlx5e_rqwq_get_cur_sz(rq) >= min_wqes)
 			return 0;
 
 		msleep(20);
 	} while (time_before(jiffies, exp_time));
 
 	netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
-		    c->ix, rq->rqn, wq->cur_sz, min_wqes);
+		    c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes);
 
 	return -ETIMEDOUT;
 }
 
 static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
-	struct mlx5_wq_ll *wq = &rq->wq;
-	struct mlx5e_rx_wqe *wqe;
 	__be16 wqe_ix_be;
 	u16 wqe_ix;
 
-	/* UMR WQE (if in progress) is always at wq->head */
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
-	    rq->mpwqe.umr_in_progress)
-		mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
 
-	while (!mlx5_wq_ll_is_empty(wq)) {
+		/* UMR WQE (if in progress) is always at wq->head */
-		wqe_ix_be = *wq->tail_next;
+		if (rq->mpwqe.umr_in_progress)
-		wqe_ix    = be16_to_cpu(wqe_ix_be);
+			mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
-		wqe       = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
-		rq->dealloc_wqe(rq, wqe_ix);
-		mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
-			       &wqe->next.next_wqe_index);
-	}
 
-	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST && rq->wqe.page_reuse) {
+		while (!mlx5_wq_ll_is_empty(wq)) {
-		/* Clean outstanding pages on handled WQEs that decided to do page-reuse,
+			struct mlx5e_rx_wqe_ll *wqe;
-		 * but yet to be re-posted.
-		 */
-		int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 
-		for (wqe_ix = 0; wqe_ix < wq_sz; wqe_ix++)
+			wqe_ix_be = *wq->tail_next;
+			wqe_ix    = be16_to_cpu(wqe_ix_be);
+			wqe       = mlx5_wq_ll_get_wqe(wq, wqe_ix);
 			rq->dealloc_wqe(rq, wqe_ix);
+			mlx5_wq_ll_pop(wq, wqe_ix_be,
+				       &wqe->next.next_wqe_index);
+		}
+	} else {
+		struct mlx5_wq_cyc *wq = &rq->wqe.wq;
+
+		while (!mlx5_wq_cyc_is_empty(wq)) {
+			wqe_ix = mlx5_wq_cyc_get_tail(wq);
+			rq->dealloc_wqe(rq, wqe_ix);
+			mlx5_wq_cyc_pop(wq);
+		}
 	}
+
 }
 
 static int mlx5e_open_rq(struct mlx5e_channel *c,
@@ -1920,6 +2019,76 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	kfree(c);
 }
 
+#define DEFAULT_FRAG_SIZE (2048)
+
+static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
+				      struct mlx5e_params *params,
+				      struct mlx5e_rq_frags_info *info)
+{
+	u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	int frag_size_max = DEFAULT_FRAG_SIZE;
+	u32 buf_size = 0;
+	int i;
+
+#ifdef CONFIG_MLX5_EN_IPSEC
+	if (MLX5_IPSEC_DEV(mdev))
+		byte_count += MLX5E_METADATA_ETHER_LEN;
+#endif
+
+	if (mlx5e_rx_is_linear_skb(mdev, params)) {
+		int frag_stride;
+
+		frag_stride = mlx5e_rx_get_linear_frag_sz(params);
+		frag_stride = roundup_pow_of_two(frag_stride);
+
+		info->arr[0].frag_size = byte_count;
+		info->arr[0].frag_stride = frag_stride;
+		info->num_frags = 1;
+		info->wqe_bulk = PAGE_SIZE / frag_stride;
+		goto out;
+	}
+
+	if (byte_count > PAGE_SIZE +
+	    (MLX5E_MAX_RX_FRAGS - 1) * frag_size_max)
+		frag_size_max = PAGE_SIZE;
+
+	i = 0;
+	while (buf_size < byte_count) {
+		int frag_size = byte_count - buf_size;
+
+		if (i < MLX5E_MAX_RX_FRAGS - 1)
+			frag_size = min(frag_size, frag_size_max);
+
+		info->arr[i].frag_size = frag_size;
+		info->arr[i].frag_stride = roundup_pow_of_two(frag_size);
+
+		buf_size += frag_size;
+		i++;
+	}
+	info->num_frags = i;
+	/* number of different wqes sharing a page */
+	info->wqe_bulk = 1 + (info->num_frags % 2);
+
+out:
+	info->wqe_bulk = max_t(u8, info->wqe_bulk, 8);
+	info->log_num_frags = order_base_2(info->num_frags);
+}
+
+static inline u8 mlx5e_get_rqwq_log_stride(u8 wq_type, int ndsegs)
+{
+	int sz = sizeof(struct mlx5_wqe_data_seg) * ndsegs;
+
+	switch (wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		sz += sizeof(struct mlx5e_rx_wqe_ll);
+		break;
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		sz += sizeof(struct mlx5e_rx_wqe_cyc);
+	}
+
+	return order_base_2(sz);
+}
+
 static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 				 struct mlx5e_params *params,
 				 struct mlx5e_rq_param *param)
@@ -1927,6 +2096,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	int ndsegs = 1;
 
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
@@ -1936,16 +2106,18 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 		MLX5_SET(wq, wq, log_wqe_stride_size,
 			 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 */
+	default: /* MLX5_WQ_TYPE_CYCLIC */
-		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
 		MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
+		mlx5e_build_rq_frags_info(mdev, params, &param->frags_info);
+		ndsegs = param->frags_info.num_frags;
 	}
 
+	MLX5_SET(wq, wq, wq_type,          params->rq_wq_type);
 	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_stride,
+		 mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
 	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);
@@ -1961,8 +2133,9 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
 
-	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
+	MLX5_SET(wq, wq, log_wq_stride,
+		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
 	MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter);
 
 	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
@@ -2013,7 +2186,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 		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 */
+	default: /* MLX5_WQ_TYPE_CYCLIC */
 		log_cq_size = params->log_rq_mtu_frames;
 	}
 
@@ -2633,16 +2806,22 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
-static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv)
+static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv)
+{
+	int max_nch = priv->profile->max_nch(priv->mdev);
+	int i, tc;
+
+	for (i = 0; i < max_nch; i++)
+		for (tc = 0; tc < priv->profile->max_tc; tc++)
+			priv->channel_tc2txq[i][tc] = i + tc * max_nch;
+}
+
+static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
 {
 	struct mlx5e_channel *c;
 	struct mlx5e_txqsq *sq;
 	int i, tc;
 
-	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++)
-		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			priv->channel_tc2txq[i][tc] = i + tc * priv->channels.num;
-
 	for (i = 0; i < priv->channels.num; i++) {
 		c = priv->channels.c[i];
 		for (tc = 0; tc < c->num_tc; tc++) {
@@ -2661,11 +2840,8 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	netif_set_real_num_tx_queues(netdev, num_txqs);
 	netif_set_real_num_rx_queues(netdev, priv->channels.num);
 
-	mlx5e_build_channels_tx_maps(priv);
+	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
-	write_lock(&priv->stats_lock);
-	priv->channels_active = true;
-	write_unlock(&priv->stats_lock);
 	netif_tx_start_all_queues(priv->netdev);
 
 	if (MLX5_VPORT_MANAGER(priv->mdev))
@@ -2687,9 +2863,6 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
-	write_lock(&priv->stats_lock);
-	priv->channels_active = false;
-	write_unlock(&priv->stats_lock);
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
@@ -2819,8 +2992,8 @@ static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev,
 
 	param->wq.db_numa_node = param->wq.buf_numa_node;
 
-	err = mlx5_wq_ll_create(mdev, &param->wq, rqc_wq, &rq->wq,
+	err = mlx5_wq_cyc_create(mdev, &param->wq, rqc_wq, &rq->wqe.wq,
-				&rq->wq_ctrl);
+				 &rq->wq_ctrl);
 	if (err)
 		return err;
 
@@ -3311,12 +3484,18 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 	mutex_lock(&priv->state_lock);
 
 	old_params = &priv->channels.params;
+	if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
+		netdev_warn(netdev, "can't set LRO with legacy RQ\n");
+		err = -EINVAL;
+		goto out;
+	}
+
 	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
 
 	new_channels.params = *old_params;
 	new_channels.params.lro_en = enable;
 
-	if (old_params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+	if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) {
 		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) ==
 		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params))
 			reset = false;
@@ -3480,22 +3659,31 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_params *params;
 
 	mutex_lock(&priv->state_lock);
+	params = &priv->channels.params;
 	if (!bitmap_empty(priv->fs.vlan.active_svlans, VLAN_N_VID)) {
 		/* HW strips the outer C-tag header, this is a problem
 		 * for S-tag traffic.
 		 */
 		features &= ~NETIF_F_HW_VLAN_CTAG_RX;
-		if (!priv->channels.params.vlan_strip_disable)
+		if (!params->vlan_strip_disable)
 			netdev_warn(netdev, "Dropping C-tag vlan stripping offload due to S-tag vlan\n");
 	}
+	if (!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
+		features &= ~NETIF_F_LRO;
+		if (params->lro_en)
+			netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n");
+	}
+
 	mutex_unlock(&priv->state_lock);
 
 	return features;
 }
 
-static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
+int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
+		     change_hw_mtu_cb set_mtu_cb)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
@@ -3513,7 +3701,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
 
-	if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
 
@@ -3522,7 +3710,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 
 	if (!reset) {
 		params->sw_mtu = new_mtu;
-		mlx5e_set_dev_port_mtu(priv);
+		set_mtu_cb(priv);
 		netdev->mtu = params->sw_mtu;
 		goto out;
 	}
@@ -3531,7 +3719,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
+	mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
@@ -3539,6 +3727,11 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	return err;
 }
 
+static int mlx5e_change_nic_mtu(struct net_device *netdev, int new_mtu)
+{
+	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
+}
+
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 {
 	struct hwtstamp_config config;
@@ -4033,7 +4226,7 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_vlan_rx_kill_vid    = mlx5e_vlan_rx_kill_vid,
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_fix_features        = mlx5e_fix_features,
-	.ndo_change_mtu          = mlx5e_change_mtu,
+	.ndo_change_mtu          = mlx5e_change_nic_mtu,
 	.ndo_do_ioctl            = mlx5e_ioctl,
 	.ndo_set_tx_maxrate      = mlx5e_set_tx_maxrate,
 	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
@@ -4212,9 +4405,16 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
 
 	/* RQ */
-	if (mlx5e_striding_rq_possible(mdev, params))
+	/* Prefer Striding RQ, unless any of the following holds:
-		MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ,
+	 * - Striding RQ configuration is not possible/supported.
-				!slow_pci_heuristic(mdev));
+	 * - Slow PCI heuristic.
+	 * - Legacy RQ would use linear SKB while Striding RQ would use non-linear.
+	 */
+	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_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true);
 	mlx5e_set_rq_type(mdev, params);
 	mlx5e_init_rq_type_params(mdev, params);
 
@@ -4263,7 +4463,6 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 			       profile->max_nch(mdev), netdev->mtu);
 
 	mutex_init(&priv->state_lock);
-	rwlock_init(&priv->stats_lock);
 
 	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
 	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
@@ -4323,7 +4522,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_RX;
 
-	if (!!MLX5_CAP_ETH(mdev, lro_cap))
+	if (!!MLX5_CAP_ETH(mdev, lro_cap) &&
+	    mlx5e_check_fragmented_striding_rq_cap(mdev))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
 	netdev->hw_features       = netdev->vlan_features;
@@ -4446,6 +4646,7 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
+	mlx5e_build_tc2txq_maps(priv);
 	mlx5e_vxlan_init(priv);
 }
 

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

@@ -130,10 +130,6 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 	struct mlx5e_sq_stats *sq_stats;
 	int i, j;
 
-	read_lock(&priv->stats_lock);
-	if (!priv->channels_active)
-	        goto out;
-
 	memset(s, 0, sizeof(*s));
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
@@ -150,8 +146,6 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 			s->tx_bytes		+= sq_stats->bytes;
 		}
 	}
-out:
-	read_unlock(&priv->stats_lock);
 }
 
 static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
@@ -906,6 +900,11 @@ static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
 	.switchdev_port_attr_get	= mlx5e_attr_get,
 };
 
+int mlx5e_change_rep_mtu(struct net_device *netdev, int new_mtu)
+{
+	return mlx5e_change_mtu(netdev, new_mtu, NULL);
+}
+
 static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_open                = mlx5e_rep_open,
 	.ndo_stop                = mlx5e_rep_close,
@@ -915,6 +914,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_get_stats64         = mlx5e_rep_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
+	.ndo_change_mtu          = mlx5e_change_rep_mtu,
 };
 
 static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
@@ -927,7 +927,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
 	params->sw_mtu      = mtu;
 	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
-	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
+	params->rq_wq_type  = MLX5_WQ_TYPE_CYCLIC;
 	params->log_rq_mtu_frames = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
 
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
@@ -941,6 +941,10 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
 {
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u16 max_mtu;
+
 	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
 
 	netdev->watchdog_timeo    = 15 * HZ;
@@ -953,6 +957,10 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_TC;
 
 	eth_hw_addr_random(netdev);
+
+	netdev->min_mtu = ETH_MIN_MTU;
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 }
 
 static void mlx5e_init_rep(struct mlx5_core_dev *mdev,

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

@@ -113,7 +113,7 @@ static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
 			mpwrq_get_cqe_consumed_strides(&cq->title);
 	else
 		cq->decmprs_wqe_counter =
-			mlx5_wq_ll_ctr2ix(&rq->wq, cq->decmprs_wqe_counter + 1);
+			mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, cq->decmprs_wqe_counter + 1);
 }
 
 static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
@@ -164,8 +164,6 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 	return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
 }
 
-#define RQ_PAGE_SIZE(rq) ((1 << rq->buff.page_order) << PAGE_SHIFT)
-
 static inline bool mlx5e_page_is_reserved(struct page *page)
 {
 	return page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id();
@@ -214,7 +212,7 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq,
 	stats->cache_reuse++;
 
 	dma_sync_single_for_device(rq->pdev, dma_info->addr,
-				   RQ_PAGE_SIZE(rq),
+				   PAGE_SIZE,
 				   DMA_FROM_DEVICE);
 	return true;
 }
@@ -230,7 +228,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 		return -ENOMEM;
 
 	dma_info->addr = dma_map_page(rq->pdev, dma_info->page, 0,
-				      RQ_PAGE_SIZE(rq), rq->buff.map_dir);
+				      PAGE_SIZE, rq->buff.map_dir);
 	if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) {
 		put_page(dma_info->page);
 		dma_info->page = NULL;
@@ -243,8 +241,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq,
 					struct mlx5e_dma_info *dma_info)
 {
-	dma_unmap_page(rq->pdev, dma_info->addr, RQ_PAGE_SIZE(rq),
+	dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
-		       rq->buff.map_dir);
 }
 
 void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
@@ -262,62 +259,103 @@ void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 	}
 }
 
-static inline bool mlx5e_page_reuse(struct mlx5e_rq *rq,
+static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
-				    struct mlx5e_wqe_frag_info *wi)
+				    struct mlx5e_wqe_frag_info *frag)
 {
-	return rq->wqe.page_reuse && wi->di.page &&
+	int err = 0;
-		(wi->offset + rq->wqe.frag_sz <= RQ_PAGE_SIZE(rq)) &&
+
-		!mlx5e_page_is_reserved(wi->di.page);
+	if (!frag->offset)
+		/* On first frag (offset == 0), replenish page (dma_info actually).
+		 * Other frags that point to the same dma_info (with a different
+		 * offset) should just use the new one without replenishing again
+		 * by themselves.
+		 */
+		err = mlx5e_page_alloc_mapped(rq, frag->di);
+
+	return err;
 }
 
-static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
+static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
+				     struct mlx5e_wqe_frag_info *frag)
 {
-	struct mlx5e_wqe_frag_info *wi = &rq->wqe.frag_info[ix];
+	if (frag->last_in_page)
+		mlx5e_page_release(rq, frag->di, true);
+}
 
-	/* check if page exists, hence can be reused */
+static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
-	if (!wi->di.page) {
+{
-		if (unlikely(mlx5e_page_alloc_mapped(rq, &wi->di)))
+	return &rq->wqe.frags[ix << rq->wqe.info.log_num_frags];
-			return -ENOMEM;
+}
-		wi->offset = 0;
+
+static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
+			      u16 ix)
+{
+	struct mlx5e_wqe_frag_info *frag = get_frag(rq, ix);
+	int err;
+	int i;
+
+	for (i = 0; i < rq->wqe.info.num_frags; i++, frag++) {
+		err = mlx5e_get_rx_frag(rq, frag);
+		if (unlikely(err))
+			goto free_frags;
+
+		wqe->data[i].addr = cpu_to_be64(frag->di->addr +
+						frag->offset + rq->buff.headroom);
 	}
 
-	wqe->data.addr = cpu_to_be64(wi->di.addr + wi->offset + rq->buff.headroom);
 	return 0;
+
+free_frags:
+	while (--i >= 0)
+		mlx5e_put_rx_frag(rq, --frag);
+
+	return err;
 }
 
 static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq,
 				     struct mlx5e_wqe_frag_info *wi)
 {
-	mlx5e_page_release(rq, &wi->di, true);
+	int i;
-	wi->di.page = NULL;
-}
 
-static inline void mlx5e_free_rx_wqe_reuse(struct mlx5e_rq *rq,
+	for (i = 0; i < rq->wqe.info.num_frags; i++, wi++)
-					   struct mlx5e_wqe_frag_info *wi)
+		mlx5e_put_rx_frag(rq, wi);
-{
-	if (mlx5e_page_reuse(rq, wi)) {
-		rq->stats->page_reuse++;
-		return;
-	}
-
-	mlx5e_free_rx_wqe(rq, wi);
 }
 
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
-	struct mlx5e_wqe_frag_info *wi = &rq->wqe.frag_info[ix];
+	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
-	if (wi->di.page)
+	mlx5e_free_rx_wqe(rq, wi);
-		mlx5e_free_rx_wqe(rq, wi);
 }
 
-static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
+static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
-					    struct sk_buff *skb,
-					    struct mlx5e_dma_info *di,
-					    u32 frag_offset, u32 len)
 {
-	unsigned int truesize = ALIGN(len, BIT(rq->mpwqe.log_stride_sz));
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
+	int err;
+	int i;
 
+	for (i = 0; i < wqe_bulk; i++) {
+		struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i);
+
+		err = mlx5e_alloc_rx_wqe(rq, wqe, ix + i);
+		if (unlikely(err))
+			goto free_wqes;
+	}
+
+	return 0;
+
+free_wqes:
+	while (--i >= 0)
+		mlx5e_dealloc_rx_wqe(rq, ix + i);
+
+	return err;
+}
+
+static inline void
+mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
+		   struct mlx5e_dma_info *di, u32 frag_offset, u32 len,
+		   unsigned int truesize)
+{
 	dma_sync_single_for_cpu(rq->pdev,
 				di->addr + frag_offset,
 				len, DMA_FROM_DEVICE);
@@ -326,6 +364,20 @@ static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
 			di->page, frag_offset, len, truesize);
 }
 
+static inline void
+mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
+		      struct mlx5e_dma_info *dma_info,
+		      int offset_from, int offset_to, u32 headlen)
+{
+	const void *from = page_address(dma_info->page) + offset_from;
+	/* Aligning len to sizeof(long) optimizes memcpy performance */
+	unsigned int len = ALIGN(headlen, sizeof(long));
+
+	dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len,
+				DMA_FROM_DEVICE);
+	skb_copy_to_linear_data_offset(skb, offset_to, from, len);
+}
+
 static inline void
 mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 			    struct sk_buff *skb,
@@ -333,23 +385,13 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 			    u32 offset, u32 headlen)
 {
 	u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset);
-	unsigned int len;
 
-	 /* Aligning len to sizeof(long) optimizes memcpy performance */
+	mlx5e_copy_skb_header(pdev, skb, dma_info, offset, 0, headlen_pg);
-	len = ALIGN(headlen_pg, sizeof(long));
-	dma_sync_single_for_cpu(pdev, dma_info->addr + offset, len,
-				DMA_FROM_DEVICE);
-	skb_copy_to_linear_data(skb, page_address(dma_info->page) + offset, len);
 
 	if (unlikely(offset + headlen > PAGE_SIZE)) {
 		dma_info++;
-		headlen_pg = len;
+		mlx5e_copy_skb_header(pdev, skb, dma_info, 0, headlen_pg,
-		len = ALIGN(headlen - headlen_pg, sizeof(long));
+				      headlen - headlen_pg);
-		dma_sync_single_for_cpu(pdev, dma_info->addr, len,
-					DMA_FROM_DEVICE);
-		skb_copy_to_linear_data_offset(skb, headlen_pg,
-					       page_address(dma_info->page),
-					       len);
 	}
 }
 
@@ -367,8 +409,8 @@ void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 
 static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
 {
-	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
-	struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
+	struct mlx5e_rx_wqe_ll *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
 
 	rq->mpwqe.umr_in_progress = false;
 
@@ -468,31 +510,34 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 {
-	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
+	u8 wqe_bulk;
 	int err;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return false;
 
-	if (mlx5_wq_ll_is_full(wq))
+	wqe_bulk = rq->wqe.info.wqe_bulk;
+
+	if (mlx5_wq_cyc_missing(wq) < wqe_bulk)
 		return false;
 
 	do {
-		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
+		u16 head = mlx5_wq_cyc_get_head(wq);
 
-		err = mlx5e_alloc_rx_wqe(rq, wqe, wq->head);
+		err = mlx5e_alloc_rx_wqes(rq, head, wqe_bulk);
 		if (unlikely(err)) {
 			rq->stats->buff_alloc_err++;
 			break;
 		}
 
-		mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
+		mlx5_wq_cyc_push_n(wq, wqe_bulk);
-	} while (!mlx5_wq_ll_is_full(wq));
+	} while (mlx5_wq_cyc_missing(wq) >= wqe_bulk);
 
 	/* ensure wqes are visible to device before updating doorbell record */
 	dma_wmb();
 
-	mlx5_wq_ll_update_db_record(wq);
+	mlx5_wq_cyc_update_db_record(wq);
 
 	return !!err;
 }
@@ -544,7 +589,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 {
-	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return false;
@@ -941,11 +986,11 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 	return skb;
 }
 
-static inline
+struct sk_buff *
-struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
-			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
+			  struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
-	struct mlx5e_dma_info *di = &wi->di;
+	struct mlx5e_dma_info *di = wi->di;
 	u16 rx_headroom = rq->buff.headroom;
 	struct sk_buff *skb;
 	void *va, *data;
@@ -960,7 +1005,6 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 				      frag_size, DMA_FROM_DEVICE);
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
-	wi->offset += frag_size;
 
 	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
@@ -983,41 +1027,87 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	return skb;
 }
 
+struct sk_buff *
+mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
+{
+	struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+	struct mlx5e_wqe_frag_info *head_wi = wi;
+	u16 headlen      = min_t(u32, MLX5E_RX_MAX_HEAD, cqe_bcnt);
+	u16 frag_headlen = headlen;
+	u16 byte_cnt     = cqe_bcnt - headlen;
+	struct sk_buff *skb;
+
+	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+		rq->stats->wqe_err++;
+		return NULL;
+	}
+
+	/* XDP is not supported in this configuration, as incoming packets
+	 * might spread among multiple pages.
+	 */
+	skb = napi_alloc_skb(rq->cq.napi,
+			     ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long)));
+	if (unlikely(!skb)) {
+		rq->stats->buff_alloc_err++;
+		return NULL;
+	}
+
+	prefetchw(skb->data);
+
+	while (byte_cnt) {
+		u16 frag_consumed_bytes =
+			min_t(u16, frag_info->frag_size - frag_headlen, byte_cnt);
+
+		mlx5e_add_skb_frag(rq, skb, wi->di, wi->offset + frag_headlen,
+				   frag_consumed_bytes, frag_info->frag_stride);
+		byte_cnt -= frag_consumed_bytes;
+		frag_headlen = 0;
+		frag_info++;
+		wi++;
+	}
+
+	/* copy header */
+	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset,
+			      0, headlen);
+	/* skb linear part was allocated with headlen and aligned to long */
+	skb->tail += headlen;
+	skb->len  += headlen;
+
+	return skb;
+}
+
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
-	struct mlx5e_rx_wqe *wqe;
-	__be16 wqe_counter_be;
 	struct sk_buff *skb;
-	u16 wqe_counter;
 	u32 cqe_bcnt;
+	u16 ci;
 
-	wqe_counter_be = cqe->wqe_counter;
+	ci       = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wi       = get_frag(rq, ci);
-	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
-	wi             = &rq->wqe.frag_info[wqe_counter];
-	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
 
-	skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			wi->di.page = NULL;
+			/* do not return page to cache,
-			/* do not return page to cache, it will be returned on XDP_TX completion */
+			 * it will be returned on XDP_TX completion.
-			goto wq_ll_pop;
+			 */
+			goto wq_cyc_pop;
 		}
-		/* probably an XDP_DROP, save the page-reuse checks */
+		goto free_wqe;
-		mlx5e_free_rx_wqe(rq, wi);
-		goto wq_ll_pop;
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5e_free_rx_wqe_reuse(rq, wi);
+free_wqe:
-wq_ll_pop:
+	mlx5e_free_rx_wqe(rq, wi);
-	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+wq_cyc_pop:
-		       &wqe->next.next_wqe_index);
+	mlx5_wq_cyc_pop(wq);
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -1027,29 +1117,26 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_rep_priv *rpriv  = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
-	struct mlx5e_rx_wqe *wqe;
 	struct sk_buff *skb;
-	__be16 wqe_counter_be;
-	u16 wqe_counter;
 	u32 cqe_bcnt;
+	u16 ci;
 
-	wqe_counter_be = cqe->wqe_counter;
+	ci       = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wi       = get_frag(rq, ci);
-	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
-	wi             = &rq->wqe.frag_info[wqe_counter];
-	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
 
-	skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (!skb) {
+		/* probably for XDP */
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			wi->di.page = NULL;
+			/* do not return page to cache,
-			/* do not return page to cache, it will be returned on XDP_TX completion */
+			 * it will be returned on XDP_TX completion.
-			goto wq_ll_pop;
+			 */
+			goto wq_cyc_pop;
 		}
-		/* probably an XDP_DROP, save the page-reuse checks */
+		goto free_wqe;
-		mlx5e_free_rx_wqe(rq, wi);
-		goto wq_ll_pop;
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
@@ -1059,10 +1146,10 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5e_free_rx_wqe_reuse(rq, wi);
+free_wqe:
-wq_ll_pop:
+	mlx5e_free_rx_wqe(rq, wi);
-	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+wq_cyc_pop:
-		       &wqe->next.next_wqe_index);
+	mlx5_wq_cyc_pop(wq);
 }
 #endif
 
@@ -1070,7 +1157,7 @@ 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 headlen = min_t(u16, MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, cqe_bcnt);
+	u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
 	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
 	u32 frag_offset    = head_offset + headlen;
 	u32 byte_cnt       = cqe_bcnt - headlen;
@@ -1078,7 +1165,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	struct sk_buff *skb;
 
 	skb = napi_alloc_skb(rq->cq.napi,
-			     ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, sizeof(long)));
+			     ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long)));
 	if (unlikely(!skb)) {
 		rq->stats->buff_alloc_err++;
 		return NULL;
@@ -1094,9 +1181,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	while (byte_cnt) {
 		u32 pg_consumed_bytes =
 			min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
+		unsigned int truesize =
+			ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
 
-		mlx5e_add_skb_frag_mpwqe(rq, skb, di, frag_offset,
+		mlx5e_add_skb_frag(rq, skb, di, frag_offset,
-					 pg_consumed_bytes);
+				   pg_consumed_bytes, truesize);
 		byte_cnt -= pg_consumed_bytes;
 		frag_offset = 0;
 		di++;
@@ -1159,7 +1248,8 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *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 mlx5e_rx_wqe_ll *wqe;
+	struct mlx5_wq_ll *wq;
 	struct sk_buff *skb;
 	u16 cqe_bcnt;
 
@@ -1189,9 +1279,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
 		return;
 
-	wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id);
+	wq  = &rq->mpwqe.wq;
+	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
 	mlx5e_free_rx_mpwqe(rq, wi);
-	mlx5_wq_ll_pop(&rq->wq, cqe->wqe_id, &wqe->next.next_wqe_index);
+	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
 }
 
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
@@ -1395,20 +1486,17 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 
 void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
-	struct mlx5e_rx_wqe *wqe;
-	__be16 wqe_counter_be;
 	struct sk_buff *skb;
-	u16 wqe_counter;
 	u32 cqe_bcnt;
+	u16 ci;
 
-	wqe_counter_be = cqe->wqe_counter;
+	ci       = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wi       = get_frag(rq, ci);
-	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
-	wi             = &rq->wqe.frag_info[wqe_counter];
-	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
 
-	skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (!skb)
 		goto wq_free_wqe;
 
@@ -1420,9 +1508,8 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 wq_free_wqe:
-	mlx5e_free_rx_wqe_reuse(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi);
-	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+	mlx5_wq_cyc_pop(wq);
-		       &wqe->next.next_wqe_index);
 }
 
 #endif /* CONFIG_MLX5_CORE_IPOIB */
@@ -1431,38 +1518,34 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
-	struct mlx5e_rx_wqe *wqe;
-	__be16 wqe_counter_be;
 	struct sk_buff *skb;
-	u16 wqe_counter;
 	u32 cqe_bcnt;
+	u16 ci;
 
-	wqe_counter_be = cqe->wqe_counter;
+	ci       = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wi       = get_frag(rq, ci);
-	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
-	wi             = &rq->wqe.frag_info[wqe_counter];
-	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
 
-	skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (unlikely(!skb)) {
 		/* a DROP, save the page-reuse checks */
 		mlx5e_free_rx_wqe(rq, wi);
-		goto wq_ll_pop;
+		goto wq_cyc_pop;
 	}
 	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb);
 	if (unlikely(!skb)) {
 		mlx5e_free_rx_wqe(rq, wi);
-		goto wq_ll_pop;
+		goto wq_cyc_pop;
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5e_free_rx_wqe_reuse(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi);
-wq_ll_pop:
+wq_cyc_pop:
-	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+	mlx5_wq_cyc_pop(wq);
-		       &wqe->next.next_wqe_index);
 }
 
 #endif /* CONFIG_MLX5_EN_IPSEC */

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

@@ -100,7 +100,7 @@ static int mlx5e_test_link_speed(struct mlx5e_priv *priv)
 
 #ifdef CONFIG_INET
 /* loopback test */
-#define MLX5E_TEST_PKT_SIZE (MLX5_MPWRQ_SMALL_PACKET_THRESHOLD - NET_IP_ALIGN)
+#define MLX5E_TEST_PKT_SIZE (MLX5E_RX_MAX_HEAD - NET_IP_ALIGN)
 static const char mlx5e_test_text[ETH_GSTRING_LEN] = "MLX5E SELF TEST";
 #define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
 

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

@@ -64,11 +64,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+	{ 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, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
@@ -114,9 +114,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 	int i;
 
 	memset(s, 0, sizeof(*s));
-	read_lock(&priv->stats_lock);
-	if (!priv->channels_active)
-		goto out;
 
 	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) {
 		struct mlx5e_channel_stats *channel_stats =
@@ -177,8 +174,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 	}
 
 	memcpy(&priv->stats.sw, s, sizeof(*s));
-out:
-	read_unlock(&priv->stats_lock);
 }
 
 static const struct counter_desc q_stats_desc[] = {
@@ -1142,11 +1137,11 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
 
 static const struct counter_desc ch_stats_desc[] = {
@@ -1161,9 +1156,6 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
 {
 	int max_nch = priv->profile->max_nch(priv->mdev);
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return 0;
-
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
 	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc);
@@ -1175,9 +1167,6 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 	int max_nch = priv->profile->max_nch(priv->mdev);
 	int i, j, tc;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return idx;
-
 	for (i = 0; i < max_nch; i++)
 		for (j = 0; j < NUM_CH_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
@@ -1187,7 +1176,6 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i);
 
-	/* priv->channel_tc2txq[i][tc] is valid only when device is open */
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
@@ -1204,9 +1192,6 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	int max_nch = priv->profile->max_nch(priv->mdev);
 	int i, j, tc;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return idx;
-
 	for (i = 0; i < max_nch; i++)
 		for (j = 0; j < NUM_CH_STATS; j++)
 			data[idx++] =

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

@@ -75,11 +75,11 @@ struct mlx5e_sw_stats {
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
-	u64 tx_queue_wake;
 	u64 tx_queue_dropped;
 	u64 tx_xmit_more;
-	u64 tx_cqe_err;
 	u64 tx_recover;
+	u64 tx_queue_wake;
+	u64 tx_cqe_err;
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler;
 	u64 rx_buff_alloc_err;
@@ -203,10 +203,11 @@ struct mlx5e_sq_stats {
 	/* less likely accessed in data path */
 	u64 csum_none;
 	u64 stopped;
-	u64 wake;
 	u64 dropped;
-	u64 cqe_err;
 	u64 recover;
+	/* dirtied @completion */
+	u64 wake ____cacheline_aligned_in_smp;
+	u64 cqe_err;
 };
 
 struct mlx5e_ch_stats {

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

@@ -188,28 +188,16 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	return min_t(u16, hlen, skb_headlen(skb));
 }
 
-static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
+static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
-					    unsigned int *skb_len,
-					    unsigned int len)
-{
-	*skb_len -= len;
-	*skb_data += len;
-}
-
-static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs,
-				     unsigned char **skb_data,
-				     unsigned int *skb_len)
 {
 	struct vlan_ethhdr *vhdr = (struct vlan_ethhdr *)start;
 	int cpy1_sz = 2 * ETH_ALEN;
 	int cpy2_sz = ihs - cpy1_sz;
 
-	memcpy(vhdr, *skb_data, cpy1_sz);
+	memcpy(vhdr, skb->data, cpy1_sz);
-	mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy1_sz);
 	vhdr->h_vlan_proto = skb->vlan_proto;
 	vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb));
-	memcpy(&vhdr->h_vlan_encapsulated_proto, *skb_data, cpy2_sz);
+	memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
-	mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz);
 }
 
 static inline void
@@ -357,8 +345,6 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
-	unsigned char *skb_data = skb->data;
-	unsigned int skb_len = skb->len;
 	u16 ds_cnt, ds_cnt_inl = 0;
 	u16 headlen, ihs, frag_pi;
 	u8 num_wqebbs, opcode;
@@ -385,7 +371,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	stats->bytes     += num_bytes;
 	stats->xmit_more += skb->xmit_more;
 
-	headlen = skb_len - ihs - skb->data_len;
+	headlen = skb->len - ihs - skb->data_len;
 	ds_cnt += !!headlen;
 	ds_cnt += skb_shinfo(skb)->nr_frags;
 
@@ -414,15 +400,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	eseg->mss = mss;
 
 	if (ihs) {
+		eseg->inline_hdr.sz = cpu_to_be16(ihs);
 		if (skb_vlan_tag_present(skb)) {
-			mlx5e_insert_vlan(eseg->inline_hdr.start, skb,
+			ihs -= VLAN_HLEN;
-					  ihs - VLAN_HLEN, &skb_data, &skb_len);
+			mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs);
 			stats->added_vlan_packets++;
 		} else {
-			memcpy(eseg->inline_hdr.start, skb_data, ihs);
+			memcpy(eseg->inline_hdr.start, skb->data, ihs);
-			mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs);
 		}
-		eseg->inline_hdr.sz = cpu_to_be16(ihs);
 		dseg += ds_cnt_inl;
 	} else if (skb_vlan_tag_present(skb)) {
 		eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
@@ -432,7 +417,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		stats->added_vlan_packets++;
 	}
 
-	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, dseg);
+	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + ihs, headlen, dseg);
 	if (unlikely(num_dma < 0))
 		goto err_drop;
 
@@ -644,8 +629,6 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
-	unsigned char *skb_data = skb->data;
-	unsigned int skb_len = skb->len;
 	u16 headlen, ihs, pi, frag_pi;
 	u16 ds_cnt, ds_cnt_inl = 0;
 	u8 num_wqebbs, opcode;
@@ -653,8 +636,6 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	int num_dma;
 	__be16 mss;
 
-	mlx5i_sq_fetch_wqe(sq, &wqe, &pi);
-
 	/* Calc ihs and ds cnt, no writes to wqe yet */
 	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
 	if (skb_is_gso(skb)) {
@@ -674,7 +655,7 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	stats->bytes     += num_bytes;
 	stats->xmit_more += skb->xmit_more;
 
-	headlen = skb_len - ihs - skb->data_len;
+	headlen = skb->len - ihs - skb->data_len;
 	ds_cnt += !!headlen;
 	ds_cnt += skb_shinfo(skb)->nr_frags;
 
@@ -686,10 +667,12 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
 	if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) {
+		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi);
-		mlx5i_sq_fetch_wqe(sq, &wqe, &pi);
 	}
 
+	mlx5i_sq_fetch_wqe(sq, &wqe, &pi);
+
 	/* fill wqe */
 	wi       = &sq->db.wqe_info[pi];
 	cseg     = &wqe->ctrl;
@@ -704,12 +687,12 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	eseg->mss = mss;
 
 	if (ihs) {
-		memcpy(eseg->inline_hdr.start, skb_data, ihs);
+		memcpy(eseg->inline_hdr.start, skb->data, ihs);
 		eseg->inline_hdr.sz = cpu_to_be16(ihs);
 		dseg += ds_cnt_inl;
 	}
 
-	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, dseg);
+	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + ihs, headlen, dseg);
 	if (unlikely(num_dma < 0))
 		goto err_drop;
 

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

@@ -50,6 +50,11 @@ static const char *const mlx5_fpga_error_strings[] = {
 	"Temperature Critical",
 };
 
+static const char * const mlx5_fpga_qp_error_strings[] = {
+	"Null Syndrome",
+	"Retry Counter Expired",
+	"RNR Expired",
+};
 static struct mlx5_fpga_device *mlx5_fpga_device_alloc(void)
 {
 	struct mlx5_fpga_device *fdev = NULL;
@@ -271,23 +276,38 @@ static const char *mlx5_fpga_syndrome_to_string(u8 syndrome)
 	return "Unknown";
 }
 
+static const char *mlx5_fpga_qp_syndrome_to_string(u8 syndrome)
+{
+	if (syndrome < ARRAY_SIZE(mlx5_fpga_qp_error_strings))
+		return mlx5_fpga_qp_error_strings[syndrome];
+	return "Unknown";
+}
+
 void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
 {
 	struct mlx5_fpga_device *fdev = mdev->fpga;
 	const char *event_name;
 	bool teardown = false;
 	unsigned long flags;
+	u32 fpga_qpn;
 	u8 syndrome;
 
-	if (event != MLX5_EVENT_TYPE_FPGA_ERROR) {
+	switch (event) {
+	case MLX5_EVENT_TYPE_FPGA_ERROR:
+		syndrome = MLX5_GET(fpga_error_event, data, syndrome);
+		event_name = mlx5_fpga_syndrome_to_string(syndrome);
+		break;
+	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
+		syndrome = MLX5_GET(fpga_qp_error_event, data, syndrome);
+		event_name = mlx5_fpga_qp_syndrome_to_string(syndrome);
+		fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn);
+		break;
+	default:
 		mlx5_fpga_warn_ratelimited(fdev, "Unexpected event %u\n",
 					   event);
 		return;
 	}
 
-	syndrome = MLX5_GET(fpga_error_event, data, syndrome);
-	event_name = mlx5_fpga_syndrome_to_string(syndrome);
-
 	spin_lock_irqsave(&fdev->state_lock, flags);
 	switch (fdev->state) {
 	case MLX5_FPGA_STATUS_SUCCESS:

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

@@ -85,6 +85,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 	mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride),
 		      MLX5_GET(wq, wqc, log_wq_sz),
 		      fbc);
+	wq->sz    = wq->fbc.sz_m1 + 1;
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {

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

@@ -51,6 +51,9 @@ struct mlx5_wq_ctrl {
 struct mlx5_wq_cyc {
 	struct mlx5_frag_buf_ctrl fbc;
 	__be32			*db;
+	u16			sz;
+	u16			wqe_ctr;
+	u16			cur_sz;
 };
 
 struct mlx5_wq_qp {
@@ -95,6 +98,43 @@ u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
 
+static inline int mlx5_wq_cyc_is_full(struct mlx5_wq_cyc *wq)
+{
+	return wq->cur_sz == wq->sz;
+}
+
+static inline int mlx5_wq_cyc_missing(struct mlx5_wq_cyc *wq)
+{
+	return wq->sz - wq->cur_sz;
+}
+
+static inline int mlx5_wq_cyc_is_empty(struct mlx5_wq_cyc *wq)
+{
+	return !wq->cur_sz;
+}
+
+static inline void mlx5_wq_cyc_push(struct mlx5_wq_cyc *wq)
+{
+	wq->wqe_ctr++;
+	wq->cur_sz++;
+}
+
+static inline void mlx5_wq_cyc_push_n(struct mlx5_wq_cyc *wq, u8 n)
+{
+	wq->wqe_ctr += n;
+	wq->cur_sz += n;
+}
+
+static inline void mlx5_wq_cyc_pop(struct mlx5_wq_cyc *wq)
+{
+	wq->cur_sz--;
+}
+
+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_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr)
 {
 	return ctr & wq->fbc.sz_m1;
@@ -105,6 +145,16 @@ static inline u16 mlx5_wq_cyc_ctr2fragix(struct mlx5_wq_cyc *wq, u16 ctr)
 	return ctr & wq->fbc.frag_sz_m1;
 }
 
+static inline u16 mlx5_wq_cyc_get_head(struct mlx5_wq_cyc *wq)
+{
+	return mlx5_wq_cyc_ctr2ix(wq, wq->wqe_ctr);
+}
+
+static inline u16 mlx5_wq_cyc_get_tail(struct mlx5_wq_cyc *wq)
+{
+	return mlx5_wq_cyc_ctr2ix(wq, wq->wqe_ctr - wq->cur_sz);
+}
+
 static inline void *mlx5_wq_cyc_get_wqe(struct mlx5_wq_cyc *wq, u16 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
@@ -179,11 +229,6 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
 	return !wq->cur_sz;
 }
 
-static inline u16 mlx5_wq_ll_ctr2ix(struct mlx5_wq_ll *wq, u16 ctr)
-{
-	return ctr & wq->fbc.sz_m1;
-}
-
 static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);