net/mlx5: Use order-0 allocations for all WQ types

Complete the transition of all WQ types to use fragmented
order-0 coherent memory instead of high-order allocations.

CQ-WQ already uses order-0.
Here we do the same for cyclic and linked-list WQs.

This allows the driver to load cleanly on systems with a highly
fragmented coherent memory.

Performance tests:
ConnectX-5 100Gbps, CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Packet rate of 64B packets, single transmit ring, size 8K.

No degradation is sensed.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

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

@@ -314,7 +314,7 @@ struct mlx5e_cq {
 
 	/* control */
 	struct mlx5_core_dev      *mdev;
-	struct mlx5_frag_wq_ctrl   wq_ctrl;
+	struct mlx5_wq_ctrl        wq_ctrl;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_tx_wqe_info {

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

@@ -646,7 +646,7 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq,
 						MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
 
-	mlx5_fill_page_array(&rq->wq_ctrl.buf,
+	mlx5_fill_page_frag_array(&rq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
 
 	err = mlx5_core_create_rq(mdev, in, inlen, &rq->rqn);
@@ -1096,7 +1096,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 					  MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq, dbr_addr,      csp->wq_ctrl->db.dma);
 
-	mlx5_fill_page_array(&csp->wq_ctrl->buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+	mlx5_fill_page_frag_array(&csp->wq_ctrl->buf,
+				  (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
 
 	err = mlx5_core_create_sq(mdev, in, inlen, sqn);
 
@@ -1538,7 +1539,7 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
 
 static void mlx5e_free_cq(struct mlx5e_cq *cq)
 {
-	mlx5_cqwq_destroy(&cq->wq_ctrl);
+	mlx5_wq_destroy(&cq->wq_ctrl);
 }
 
 static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
@@ -1554,7 +1555,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	int err;
 
 	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
-		sizeof(u64) * cq->wq_ctrl.frag_buf.npages;
+		sizeof(u64) * cq->wq_ctrl.buf.npages;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1563,7 +1564,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 
 	memcpy(cqc, param->cqc, sizeof(param->cqc));
 
-	mlx5_fill_page_frag_array(&cq->wq_ctrl.frag_buf,
+	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
 	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
@@ -1571,7 +1572,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
-	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.frag_buf.page_shift -
+	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
 

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

@@ -383,16 +383,16 @@ static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
 	return sq->pc >> MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 }
 
-static inline void mlx5e_fill_icosq_edge(struct mlx5e_icosq *sq,
+static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
 					      struct mlx5_wq_cyc *wq,
-					 u16 pi)
+					      u16 pi, u16 frag_pi)
 {
 	struct mlx5e_sq_wqe_info *edge_wi, *wi = &sq->db.ico_wqe[pi];
-	u8 nnops = mlx5_wq_cyc_get_size(wq) - pi;
+	u8 nnops = mlx5_wq_cyc_get_frag_size(wq) - frag_pi;
 
 	edge_wi = wi + nnops;
 
-	/* fill sq edge with nops to avoid wqe wrapping two pages */
+	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
 	for (; wi < edge_wi; wi++) {
 		wi->opcode = MLX5_OPCODE_NOP;
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
@@ -407,14 +407,15 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *umr_wqe;
 	u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
-	u16 pi;
+	u16 pi, frag_pi;
 	int err;
 	int i;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
 
-	if (unlikely(pi + MLX5E_UMR_WQEBBS > mlx5_wq_cyc_get_size(wq))) {
-		mlx5e_fill_icosq_edge(sq, wq, pi);
+	if (unlikely(frag_pi + MLX5E_UMR_WQEBBS > mlx5_wq_cyc_get_frag_size(wq))) {
+		mlx5e_fill_icosq_frag_edge(sq, wq, pi, frag_pi);
 		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	}
 

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

@@ -296,16 +296,16 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	return -ENOMEM;
 }
 
-static inline void mlx5e_fill_sq_edge(struct mlx5e_txqsq *sq,
+static inline void mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq,
 					   struct mlx5_wq_cyc *wq,
-				      u16 pi)
+					   u16 pi, u16 frag_pi)
 {
 	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-	u8 nnops = mlx5_wq_cyc_get_size(wq) - pi;
+	u8 nnops = mlx5_wq_cyc_get_frag_size(wq) - frag_pi;
 
 	edge_wi = wi + nnops;
 
-	/* fill sq edge with nops to avoid wqe wrap around */
+	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
 	for (; wi < edge_wi; wi++) {
 		wi->skb        = NULL;
 		wi->num_wqebbs = 1;
@@ -358,8 +358,8 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	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;
-	u16 headlen, ihs;
 	u32 num_bytes;
 	int num_dma;
 	__be16 mss;
@@ -395,8 +395,9 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	if (unlikely(pi + num_wqebbs > mlx5_wq_cyc_get_size(wq))) {
-		mlx5e_fill_sq_edge(sq, wq, pi);
+	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
+	if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) {
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi);
 		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
 	}
 
@@ -642,9 +643,9 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	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;
-	u16 headlen, ihs, pi;
 	u32 num_bytes;
 	int num_dma;
 	__be16 mss;
@@ -680,8 +681,9 @@ 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);
-	if (unlikely(pi + num_wqebbs > mlx5_wq_cyc_get_size(wq))) {
-		mlx5e_fill_sq_edge(sq, wq, pi);
+	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
+	if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) {
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi);
 		mlx5i_sq_fetch_wqe(sq, &wqe, &pi);
 	}
 

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

@@ -454,7 +454,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	}
 
 	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
-		sizeof(u64) * conn->cq.wq_ctrl.frag_buf.npages;
+		sizeof(u64) * conn->cq.wq_ctrl.buf.npages;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		err = -ENOMEM;
@@ -469,12 +469,12 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size));
 	MLX5_SET(cqc, cqc, c_eqn, eqn);
 	MLX5_SET(cqc, cqc, uar_page, fdev->conn_res.uar->index);
-	MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.frag_buf.page_shift -
+	MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.buf.page_shift -
 			   MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr, conn->cq.wq_ctrl.db.dma);
 
 	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
-	mlx5_fill_page_frag_array(&conn->cq.wq_ctrl.frag_buf, pas);
+	mlx5_fill_page_frag_array(&conn->cq.wq_ctrl.buf, pas);
 
 	err = mlx5_core_create_cq(mdev, &conn->cq.mcq, in, inlen);
 	kvfree(in);
@@ -500,7 +500,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	goto out;
 
 err_cqwq:
-	mlx5_cqwq_destroy(&conn->cq.wq_ctrl);
+	mlx5_wq_destroy(&conn->cq.wq_ctrl);
 out:
 	return err;
 }
@@ -510,7 +510,7 @@ static void mlx5_fpga_conn_destroy_cq(struct mlx5_fpga_conn *conn)
 	tasklet_disable(&conn->cq.tasklet);
 	tasklet_kill(&conn->cq.tasklet);
 	mlx5_core_destroy_cq(conn->fdev->mdev, &conn->cq.mcq);
-	mlx5_cqwq_destroy(&conn->cq.wq_ctrl);
+	mlx5_wq_destroy(&conn->cq.wq_ctrl);
 }
 
 static int mlx5_fpga_conn_create_wq(struct mlx5_fpga_conn *conn, void *qpc)
@@ -591,7 +591,7 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn,
 	if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
 		MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
 
-	mlx5_fill_page_array(&conn->qp.wq_ctrl.buf,
+	mlx5_fill_page_frag_array(&conn->qp.wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_qp_in, in, pas));
 
 	err = mlx5_core_create_qp(mdev, &conn->qp.mqp, in, inlen);

drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h

@@ -54,7 +54,7 @@ struct mlx5_fpga_conn {
 	/* CQ */
 	struct {
 		struct mlx5_cqwq wq;
-		struct mlx5_frag_wq_ctrl wq_ctrl;
+		struct mlx5_wq_ctrl wq_ctrl;
 		struct mlx5_core_cq mcq;
 		struct tasklet_struct tasklet;
 	} cq;

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

@@ -36,7 +36,12 @@
 
 u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
 {
-	return (u32)wq->sz_m1 + 1;
+	return (u32)wq->fbc.sz_m1 + 1;
+}
+
+u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq)
+{
+	return (u32)wq->fbc.frag_sz_m1 + 1;
 }
 
 u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
@@ -46,12 +51,12 @@ u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
 
 u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
 {
-	return (u32)wq->sz_m1 + 1;
+	return (u32)wq->fbc.sz_m1 + 1;
 }
 
 static u32 mlx5_wq_cyc_get_byte_size(struct mlx5_wq_cyc *wq)
 {
-	return mlx5_wq_cyc_get_size(wq) << wq->log_stride;
+	return mlx5_wq_cyc_get_size(wq) << wq->fbc.log_stride;
 }
 
 static u32 mlx5_wq_qp_get_byte_size(struct mlx5_wq_qp *wq)
@@ -67,17 +72,19 @@ static u32 mlx5_cqwq_get_byte_size(struct mlx5_cqwq *wq)
 
 static u32 mlx5_wq_ll_get_byte_size(struct mlx5_wq_ll *wq)
 {
-	return mlx5_wq_ll_get_size(wq) << wq->log_stride;
+	return mlx5_wq_ll_get_size(wq) << wq->fbc.log_stride;
 }
 
 int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl)
 {
+	struct mlx5_frag_buf_ctrl *fbc = &wq->fbc;
 	int err;
 
-	wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride);
-	wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1;
+	mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride),
+		      MLX5_GET(wq, wqc, log_wq_sz),
+		      fbc);
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -85,14 +92,14 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		return err;
 	}
 
-	err = mlx5_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq),
+	err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq),
 				       &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
-	wq->buf = wq_ctrl->buf.frags->buf;
+	fbc->frag_buf = wq_ctrl->buf;
 	wq->db  = wq_ctrl->db.db;
 
 	wq_ctrl->mdev = mdev;
@@ -105,17 +112,35 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 	return err;
 }
 
+static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf,
+				  struct mlx5_wq_qp *qp)
+{
+	struct mlx5_frag_buf *rqb, *sqb;
+
+	rqb = &qp->rq.fbc.frag_buf;
+	*rqb = *buf;
+	rqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
+	rqb->npages = 1 << get_order(rqb->size);
+
+	sqb = &qp->sq.fbc.frag_buf;
+	*sqb = *buf;
+	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
+	sqb->npages = 1 << get_order(sqb->size);
+	sqb->frags += rqb->npages; /* first part is for the rq */
+}
+
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
 	int err;
 
-	wq->rq.log_stride = MLX5_GET(qpc, qpc, log_rq_stride) + 4;
-	wq->rq.sz_m1 = (1 << MLX5_GET(qpc, qpc, log_rq_size)) - 1;
-
-	wq->sq.log_stride = ilog2(MLX5_SEND_WQE_BB);
-	wq->sq.sz_m1 = (1 << MLX5_GET(qpc, qpc, log_sq_size)) - 1;
+	mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4,
+		      MLX5_GET(qpc, qpc, log_rq_size),
+		      &wq->rq.fbc);
+	mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB),
+		      MLX5_GET(qpc, qpc, log_sq_size),
+		      &wq->sq.fbc);
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -123,15 +148,15 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		return err;
 	}
 
-	err = mlx5_buf_alloc_node(mdev, mlx5_wq_qp_get_byte_size(wq),
+	err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_qp_get_byte_size(wq),
 				       &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
-	wq->rq.buf = wq_ctrl->buf.frags->buf;
-	wq->sq.buf = wq->rq.buf + mlx5_wq_cyc_get_byte_size(&wq->rq);
+	mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq);
+
 	wq->rq.db  = &wq_ctrl->db.db[MLX5_RCV_DBR];
 	wq->sq.db  = &wq_ctrl->db.db[MLX5_SND_DBR];
 
@@ -147,7 +172,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
-		     struct mlx5_frag_wq_ctrl *wq_ctrl)
+		     struct mlx5_wq_ctrl *wq_ctrl)
 {
 	int err;
 
@@ -160,7 +185,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 	}
 
 	err = mlx5_frag_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq),
-				       &wq_ctrl->frag_buf,
+				       &wq_ctrl->buf,
 				       param->buf_numa_node);
 	if (err) {
 		mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n",
@@ -168,7 +193,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		goto err_db_free;
 	}
 
-	wq->fbc.frag_buf = wq_ctrl->frag_buf;
+	wq->fbc.frag_buf = wq_ctrl->buf;
 	wq->db  = wq_ctrl->db.db;
 
 	wq_ctrl->mdev = mdev;
@@ -185,12 +210,14 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
+	struct mlx5_frag_buf_ctrl *fbc = &wq->fbc;
 	struct mlx5_wqe_srq_next_seg *next_seg;
 	int err;
 	int i;
 
-	wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride);
-	wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1;
+	mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride),
+		      MLX5_GET(wq, wqc, log_wq_sz),
+		      fbc);
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -198,17 +225,17 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		return err;
 	}
 
-	err = mlx5_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq),
+	err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq),
 				       &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
-	wq->buf = wq_ctrl->buf.frags->buf;
+	wq->fbc.frag_buf = wq_ctrl->buf;
 	wq->db  = wq_ctrl->db.db;
 
-	for (i = 0; i < wq->sz_m1; i++) {
+	for (i = 0; i < fbc->sz_m1; i++) {
 		next_seg = mlx5_wq_ll_get_wqe(wq, i);
 		next_seg->next_wqe_index = cpu_to_be16(i + 1);
 	}
@@ -227,12 +254,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)
 {
-	mlx5_buf_free(wq_ctrl->mdev, &wq_ctrl->buf);
+	mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf);
 	mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db);
 }
 
-void mlx5_cqwq_destroy(struct mlx5_frag_wq_ctrl *wq_ctrl)
-{
-	mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->frag_buf);
-	mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db);
-}

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

@@ -48,17 +48,9 @@ struct mlx5_wq_ctrl {
 	struct mlx5_db		db;
 };
 
-struct mlx5_frag_wq_ctrl {
-	struct mlx5_core_dev	*mdev;
-	struct mlx5_frag_buf	frag_buf;
-	struct mlx5_db		db;
-};
-
 struct mlx5_wq_cyc {
-	void			*buf;
+	struct mlx5_frag_buf_ctrl fbc;
 	__be32			*db;
-	u16			sz_m1;
-	u8			log_stride;
 };
 
 struct mlx5_wq_qp {
@@ -73,20 +65,19 @@ struct mlx5_cqwq {
 };
 
 struct mlx5_wq_ll {
-	void			*buf;
+	struct mlx5_frag_buf_ctrl fbc;
 	__be32			*db;
 	__be16			*tail_next;
-	u16			sz_m1;
 	u16			head;
 	u16			wqe_ctr;
 	u16			cur_sz;
-	u8			log_stride;
 };
 
 int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
+u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
@@ -94,7 +85,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
-		     struct mlx5_frag_wq_ctrl *wq_ctrl);
+		     struct mlx5_wq_ctrl *wq_ctrl);
 u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq);
 
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
@@ -103,16 +94,20 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
-void mlx5_cqwq_destroy(struct mlx5_frag_wq_ctrl *wq_ctrl);
 
 static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr)
 {
-	return ctr & wq->sz_m1;
+	return ctr & wq->fbc.sz_m1;
+}
+
+static inline u16 mlx5_wq_cyc_ctr2fragix(struct mlx5_wq_cyc *wq, u16 ctr)
+{
+	return ctr & wq->fbc.frag_sz_m1;
 }
 
 static inline void *mlx5_wq_cyc_get_wqe(struct mlx5_wq_cyc *wq, u16 ix)
 {
-	return wq->buf + (ix << wq->log_stride);
+	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
 }
 
 static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2)
@@ -176,7 +171,7 @@ static inline struct mlx5_cqe64 *mlx5_cqwq_get_cqe(struct mlx5_cqwq *wq)
 
 static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq)
 {
-	return wq->cur_sz == wq->sz_m1;
+	return wq->cur_sz == wq->fbc.sz_m1;
 }
 
 static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
@@ -186,12 +181,12 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
 
 static inline u16 mlx5_wq_ll_ctr2ix(struct mlx5_wq_ll *wq, u16 ctr)
 {
-	return ctr & wq->sz_m1;
+	return ctr & wq->fbc.sz_m1;
 }
 
 static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 {
-	return wq->buf + (ix << wq->log_stride);
+	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
 }
 
 static inline void mlx5_wq_ll_push(struct mlx5_wq_ll *wq, u16 head_next)

include/linux/mlx5/driver.h

@@ -983,16 +983,24 @@ static inline u32 mlx5_base_mkey(const u32 key)
 	return key & 0xffffff00u;
 }
 
-static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
-					      void *cqc)
+static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
+				 struct mlx5_frag_buf_ctrl *fbc)
 {
-	fbc->log_stride	= 6 + MLX5_GET(cqc, cqc, cqe_sz);
-	fbc->log_sz	= MLX5_GET(cqc, cqc, log_cq_size);
+	fbc->log_stride = log_stride;
+	fbc->log_sz     = log_sz;
 	fbc->sz_m1	= (1 << fbc->log_sz) - 1;
 	fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
 	fbc->frag_sz_m1	= (1 << fbc->log_frag_strides) - 1;
 }
 
+static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
+					      void *cqc)
+{
+	mlx5_fill_fbc(6 + MLX5_GET(cqc, cqc, cqe_sz),
+		      MLX5_GET(cqc, cqc, log_cq_size),
+		      fbc);
+}
+
 static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
 					  u32 ix)
 {