Merge branch 'mlx5-updates'

Saeed Mahameed says:

====================
Mellanox 100G mlx5 updates 2016-11-29

The following series from Tariq and Roi, provides some critical fixes
and updates for the mlx5e driver.

From Tariq:
 - Fix driver coherent memory huge allocation issues by fragmenting
   completion queues, in a way that is transparent to the netdev driver by
   providing a new buffer type "mlx5_frag_buf" with the same access API.
 - Create UMR MKey per RQ to have better scalability.

From Roi:
 - Some fixes for the encap-decap support and tc flower added lately to the
   mlx5e driver.

v1->v2:
 - Fix start index in error flow of mlx5_frag_buf_alloc_node, pointed out by Eric.

This series was generated against commit:
31ac1c19455f ("geneve: fix ip_hdr_len reserved for geneve6 tunnel.")
====================

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

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

@@ -106,6 +106,63 @@ void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf)
 }
 EXPORT_SYMBOL_GPL(mlx5_buf_free);
 
+int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
+			     struct mlx5_frag_buf *buf, int node)
+{
+	int i;
+
+	buf->size = size;
+	buf->npages = 1 << get_order(size);
+	buf->page_shift = PAGE_SHIFT;
+	buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
+			     GFP_KERNEL);
+	if (!buf->frags)
+		goto err_out;
+
+	for (i = 0; i < buf->npages; i++) {
+		struct mlx5_buf_list *frag = &buf->frags[i];
+		int frag_sz = min_t(int, size, PAGE_SIZE);
+
+		frag->buf = mlx5_dma_zalloc_coherent_node(dev, frag_sz,
+							  &frag->map, node);
+		if (!frag->buf)
+			goto err_free_buf;
+		if (frag->map & ((1 << buf->page_shift) - 1)) {
+			dma_free_coherent(&dev->pdev->dev, frag_sz,
+					  buf->frags[i].buf, buf->frags[i].map);
+			mlx5_core_warn(dev, "unexpected map alignment: 0x%p, page_shift=%d\n",
+				       (void *)frag->map, buf->page_shift);
+			goto err_free_buf;
+		}
+		size -= frag_sz;
+	}
+
+	return 0;
+
+err_free_buf:
+	while (i--)
+		dma_free_coherent(&dev->pdev->dev, PAGE_SIZE, buf->frags[i].buf,
+				  buf->frags[i].map);
+	kfree(buf->frags);
+err_out:
+	return -ENOMEM;
+}
+
+void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
+{
+	int size = buf->size;
+	int i;
+
+	for (i = 0; i < buf->npages; i++) {
+		int frag_sz = min_t(int, size, PAGE_SIZE);
+
+		dma_free_coherent(&dev->pdev->dev, frag_sz, buf->frags[i].buf,
+				  buf->frags[i].map);
+		size -= frag_sz;
+	}
+	kfree(buf->frags);
+}
+
 static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 						 int node)
 {
@@ -230,3 +287,12 @@ void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas)
 	}
 }
 EXPORT_SYMBOL_GPL(mlx5_fill_page_array);
+
+void mlx5_fill_page_frag_array(struct mlx5_frag_buf *buf, __be64 *pas)
+{
+	int i;
+
+	for (i = 0; i < buf->npages; i++)
+		pas[i] = cpu_to_be64(buf->frags[i].map);
+}
+EXPORT_SYMBOL_GPL(mlx5_fill_page_frag_array);

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

@@ -77,9 +77,9 @@
 						 MLX5_MPWRQ_WQE_PAGE_ORDER)
 
 #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
-#define MLX5E_REQUIRED_MTTS(rqs, wqes)\
-	(rqs * wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
-#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX)
+#define MLX5E_REQUIRED_MTTS(wqes)		\
+	(wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
 
 #define MLX5_UMR_ALIGN				(2048)
 #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(128)
@@ -286,7 +286,7 @@ struct mlx5e_cq {
 	u16                        decmprs_wqe_counter;
 
 	/* control */
-	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5_frag_wq_ctrl   wq_ctrl;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_rq;
@@ -347,7 +347,6 @@ struct mlx5e_rq {
 		struct {
 			struct mlx5e_mpw_info *info;
 			void                  *mtt_no_align;
-			u32                    mtt_offset;
 		} mpwqe;
 	};
 	struct {
@@ -382,6 +381,7 @@ struct mlx5e_rq {
 	u32                    rqn;
 	struct mlx5e_channel  *channel;
 	struct mlx5e_priv     *priv;
+	struct mlx5_core_mkey  umr_mkey;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_umr_dma_info {
@@ -689,7 +689,6 @@ struct mlx5e_priv {
 
 	unsigned long              state;
 	struct mutex               state_lock; /* Protects Interface state */
-	struct mlx5_core_mkey      umr_mkey;
 	struct mlx5e_rq            drop_rq;
 
 	struct mlx5e_channel     **channel;
@@ -838,8 +837,7 @@ static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
 
 static inline u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix)
 {
-	return rq->mpwqe.mtt_offset +
-		wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8);
+	return wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8);
 }
 
 static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)

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

@@ -499,8 +499,7 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels,
-				       rx_pending_wqes);
+	num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
 	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
 	    !MLX5E_VALID_NUM_MTTS(num_mtts)) {
 		netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
@@ -565,7 +564,6 @@ static int mlx5e_set_channels(struct net_device *dev,
 	unsigned int count = ch->combined_count;
 	bool arfs_enabled;
 	bool was_opened;
-	u32 num_mtts;
 	int err = 0;
 
 	if (!count) {
@@ -584,14 +582,6 @@ static int mlx5e_set_channels(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	num_mtts = MLX5E_REQUIRED_MTTS(count, BIT(priv->params.log_rq_size));
-	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
-	    !MLX5E_VALID_NUM_MTTS(num_mtts)) {
-		netdev_info(dev, "%s: rx count (%d) request can't be satisfied, try to reduce.\n",
-			    __func__, count);
-		return -EINVAL;
-	}
-
 	if (priv->params.num_channels == count)
 		return 0;
 

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

@@ -471,6 +471,52 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
 	kfree(rq->mpwqe.info);
 }
 
+static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
+				 u64 npages, u8 page_shift,
+				 struct mlx5_core_mkey *umr_mkey)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+	void *mkc;
+	u32 *in;
+	int err;
+
+	if (!MLX5E_VALID_NUM_MTTS(npages))
+		return -EINVAL;
+
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+
+	MLX5_SET(mkc, mkc, free, 1);
+	MLX5_SET(mkc, mkc, umr_en, 1);
+	MLX5_SET(mkc, mkc, lw, 1);
+	MLX5_SET(mkc, mkc, lr, 1);
+	MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT);
+
+	MLX5_SET(mkc, mkc, qpn, 0xffffff);
+	MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn);
+	MLX5_SET64(mkc, mkc, len, npages << page_shift);
+	MLX5_SET(mkc, mkc, translations_octword_size,
+		 MLX5_MTT_OCTW(npages));
+	MLX5_SET(mkc, mkc, log_page_size, page_shift);
+
+	err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
+
+	kvfree(in);
+	return err;
+}
+
+static int mlx5e_create_rq_umr_mkey(struct mlx5e_rq *rq)
+{
+	struct mlx5e_priv *priv = rq->priv;
+	u64 num_mtts = MLX5E_REQUIRED_MTTS(BIT(priv->params.log_rq_size));
+
+	return mlx5e_create_umr_mkey(priv, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+}
+
 static int mlx5e_create_rq(struct mlx5e_channel *c,
 			   struct mlx5e_rq_param *param,
 			   struct mlx5e_rq *rq)
@@ -527,18 +573,20 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
-		rq->mpwqe.mtt_offset = c->ix *
-			MLX5E_REQUIRED_MTTS(1, BIT(priv->params.log_rq_size));
-
 		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
 		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
 
 		rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
 		byte_count = rq->buff.wqe_sz;
-		rq->mkey_be = cpu_to_be32(c->priv->umr_mkey.key);
-		err = mlx5e_rq_alloc_mpwqe_info(rq, c);
+
+		err = mlx5e_create_rq_umr_mkey(rq);
 		if (err)
 			goto err_rq_wq_destroy;
+		rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
+
+		err = mlx5e_rq_alloc_mpwqe_info(rq, c);
+		if (err)
+			goto err_destroy_umr_mkey;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		rq->dma_info = kzalloc_node(wq_sz * sizeof(*rq->dma_info),
@@ -589,6 +637,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 
 	return 0;
 
+err_destroy_umr_mkey:
+	mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+
 err_rq_wq_destroy:
 	if (rq->xdp_prog)
 		bpf_prog_put(rq->xdp_prog);
@@ -607,6 +658,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		mlx5e_rq_free_mpwqe_info(rq);
+		mlx5_core_destroy_mkey(rq->priv->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		kfree(rq->dma_info);
@@ -1201,7 +1253,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 
 static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
 {
-	mlx5_wq_destroy(&cq->wq_ctrl);
+	mlx5_cqwq_destroy(&cq->wq_ctrl);
 }
 
 static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
@@ -1218,7 +1270,7 @@ static int mlx5e_enable_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.buf.npages;
+		sizeof(u64) * cq->wq_ctrl.frag_buf.npages;
 	in = mlx5_vzalloc(inlen);
 	if (!in)
 		return -ENOMEM;
@@ -1227,15 +1279,15 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 
 	memcpy(cqc, param->cqc, sizeof(param->cqc));
 
-	mlx5_fill_page_array(&cq->wq_ctrl.buf,
-			     (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
+	mlx5_fill_page_frag_array(&cq->wq_ctrl.frag_buf,
+				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
 	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
 
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mcq->uar->index);
-	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
+	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.frag_buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
 
@@ -3625,43 +3677,6 @@ static void mlx5e_destroy_q_counter(struct mlx5e_priv *priv)
 	mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
 }
 
-static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u64 npages = MLX5E_REQUIRED_MTTS(priv->profile->max_nch(mdev),
-					 BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW));
-	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
-	void *mkc;
-	u32 *in;
-	int err;
-
-	in = mlx5_vzalloc(inlen);
-	if (!in)
-		return -ENOMEM;
-
-	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
-
-	npages = min_t(u32, ALIGN(U16_MAX, 4) * 2, npages);
-
-	MLX5_SET(mkc, mkc, free, 1);
-	MLX5_SET(mkc, mkc, umr_en, 1);
-	MLX5_SET(mkc, mkc, lw, 1);
-	MLX5_SET(mkc, mkc, lr, 1);
-	MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT);
-
-	MLX5_SET(mkc, mkc, qpn, 0xffffff);
-	MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn);
-	MLX5_SET64(mkc, mkc, len, npages << PAGE_SHIFT);
-	MLX5_SET(mkc, mkc, translations_octword_size,
-		 MLX5_MTT_OCTW(npages));
-	MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
-
-	err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen);
-
-	kvfree(in);
-	return err;
-}
-
 static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 			   struct net_device *netdev,
 			   const struct mlx5e_profile *profile,
@@ -3868,15 +3883,9 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	profile = priv->profile;
 	clear_bit(MLX5E_STATE_DESTROYING, &priv->state);
 
-	err = mlx5e_create_umr_mkey(priv);
-	if (err) {
-		mlx5_core_err(mdev, "create umr mkey failed, %d\n", err);
-		goto out;
-	}
-
 	err = profile->init_tx(priv);
 	if (err)
-		goto err_destroy_umr_mkey;
+		goto out;
 
 	err = mlx5e_open_drop_rq(priv);
 	if (err) {
@@ -3916,9 +3925,6 @@ err_close_drop_rq:
 err_cleanup_tx:
 	profile->cleanup_tx(priv);
 
-err_destroy_umr_mkey:
-	mlx5_core_destroy_mkey(mdev, &priv->umr_mkey);
-
 out:
 	return err;
 }
@@ -3967,7 +3973,6 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	profile->cleanup_rx(priv);
 	mlx5e_close_drop_rq(priv);
 	profile->cleanup_tx(priv);
-	mlx5_core_destroy_mkey(priv->mdev, &priv->umr_mkey);
 	cancel_delayed_work_sync(&priv->update_stats_work);
 }
 

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

@@ -142,19 +142,39 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
 }
 
+static void mlx5e_detach_encap(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow) {
+	struct list_head *next = flow->encap.next;
+
+	list_del(&flow->encap);
+	if (list_empty(next)) {
+		struct mlx5_encap_entry *e;
+
+		e = list_entry(next, struct mlx5_encap_entry, flows);
+		if (e->n) {
+			mlx5_encap_dealloc(priv->mdev, e->encap_id);
+			neigh_release(e->n);
+		}
+		hlist_del_rcu(&e->encap_hlist);
+		kfree(e);
+	}
+}
+
 static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
-			      struct mlx5_flow_handle *rule,
-			      struct mlx5_esw_flow_attr *attr)
+			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_fc *counter = NULL;
 
-	counter = mlx5_flow_rule_counter(rule);
+	counter = mlx5_flow_rule_counter(flow->rule);
 
-	if (esw && esw->mode == SRIOV_OFFLOADS)
-		mlx5_eswitch_del_vlan_action(esw, attr);
+	mlx5_del_flow_rules(flow->rule);
 
-	mlx5_del_flow_rules(rule);
+	if (esw && esw->mode == SRIOV_OFFLOADS) {
+		mlx5_eswitch_del_vlan_action(esw, flow->attr);
+		if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+			mlx5e_detach_encap(priv, flow);
+	}
 
 	mlx5_fc_destroy(priv->mdev, counter);
 
@@ -915,25 +935,17 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	u32 flow_tag, action;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_flow_spec *spec;
-	struct mlx5_flow_handle *old = NULL;
-	struct mlx5_esw_flow_attr *old_attr = NULL;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 
 	if (esw && esw->mode == SRIOV_OFFLOADS)
 		fdb_flow = true;
 
-	flow = rhashtable_lookup_fast(&tc->ht, &f->cookie,
-				      tc->ht_params);
-	if (flow) {
-		old = flow->rule;
-		old_attr = flow->attr;
-	} else {
-		if (fdb_flow)
-			flow = kzalloc(sizeof(*flow) + sizeof(struct mlx5_esw_flow_attr),
-				       GFP_KERNEL);
-		else
-			flow = kzalloc(sizeof(*flow), GFP_KERNEL);
-	}
+	if (fdb_flow)
+		flow = kzalloc(sizeof(*flow) +
+			       sizeof(struct mlx5_esw_flow_attr),
+			       GFP_KERNEL);
+	else
+		flow = kzalloc(sizeof(*flow), GFP_KERNEL);
 
 	spec = mlx5_vzalloc(sizeof(*spec));
 	if (!spec || !flow) {
@@ -970,40 +982,18 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	if (err)
 		goto err_del_rule;
 
-	if (old)
-		mlx5e_tc_del_flow(priv, old, old_attr);
-
 	goto out;
 
 err_del_rule:
 	mlx5_del_flow_rules(flow->rule);
 
 err_free:
-	if (!old)
-		kfree(flow);
+	kfree(flow);
 out:
 	kvfree(spec);
 	return err;
 }
 
-static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow) {
-	struct list_head *next = flow->encap.next;
-
-	list_del(&flow->encap);
-	if (list_empty(next)) {
-		struct mlx5_encap_entry *e;
-
-		e = list_entry(next, struct mlx5_encap_entry, flows);
-		if (e->n) {
-			mlx5_encap_dealloc(priv->mdev, e->encap_id);
-			neigh_release(e->n);
-		}
-		hlist_del_rcu(&e->encap_hlist);
-		kfree(e);
-	}
-}
-
 int mlx5e_delete_flower(struct mlx5e_priv *priv,
 			struct tc_cls_flower_offload *f)
 {
@@ -1017,10 +1007,8 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
 
 	rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params);
 
-	mlx5e_tc_del_flow(priv, flow->rule, flow->attr);
+	mlx5e_tc_del_flow(priv, flow);
 
-	if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
-		mlx5e_detach_encap(priv, flow);
 
 	kfree(flow);
 
@@ -1077,7 +1065,7 @@ static void _mlx5e_tc_del_flow(void *ptr, void *arg)
 	struct mlx5e_tc_flow *flow = ptr;
 	struct mlx5e_priv *priv = arg;
 
-	mlx5e_tc_del_flow(priv, flow->rule, flow->attr);
+	mlx5e_tc_del_flow(priv, flow);
 	kfree(flow);
 }
 

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

@@ -101,13 +101,15 @@ err_db_free:
 
 int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
-		     struct mlx5_wq_ctrl *wq_ctrl)
+		     struct mlx5_frag_wq_ctrl *wq_ctrl)
 {
 	int err;
 
-	wq->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz);
-	wq->log_sz = MLX5_GET(cqc, cqc, log_cq_size);
-	wq->sz_m1 = (1 << wq->log_sz) - 1;
+	wq->log_stride	= 6 + MLX5_GET(cqc, cqc, cqe_sz);
+	wq->log_sz	= MLX5_GET(cqc, cqc, log_cq_size);
+	wq->sz_m1	= (1 << wq->log_sz) - 1;
+	wq->log_frag_strides = PAGE_SHIFT - wq->log_stride;
+	wq->frag_sz_m1	= (1 << wq->log_frag_strides) - 1;
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -115,14 +117,16 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		return err;
 	}
 
-	err = mlx5_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq),
-				  &wq_ctrl->buf, param->buf_numa_node);
+	err = mlx5_frag_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq),
+				       &wq_ctrl->frag_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.direct.buf;
+	wq->frag_buf = wq_ctrl->frag_buf;
 	wq->db  = wq_ctrl->db.db;
 
 	wq_ctrl->mdev = mdev;
@@ -184,3 +188,9 @@ void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)
 	mlx5_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

@@ -47,6 +47,12 @@ 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;
 	__be32			*db;
@@ -55,12 +61,14 @@ struct mlx5_wq_cyc {
 };
 
 struct mlx5_cqwq {
-	void			*buf;
+	struct mlx5_frag_buf	frag_buf;
 	__be32			*db;
 	u32			sz_m1;
+	u32			frag_sz_m1;
 	u32			cc; /* consumer counter */
 	u8			log_sz;
 	u8			log_stride;
+	u8			log_frag_strides;
 };
 
 struct mlx5_wq_ll {
@@ -81,7 +89,7 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
 
 int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
-		     struct mlx5_wq_ctrl *wq_ctrl);
+		     struct mlx5_frag_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,
@@ -90,6 +98,7 @@ 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)
 {
@@ -116,7 +125,10 @@ static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq)
 
 static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
 {
-	return wq->buf + (ix << wq->log_stride);
+	unsigned int frag = (ix >> wq->log_frag_strides);
+
+	return wq->frag_buf.frags[frag].buf +
+		((wq->frag_sz_m1 & ix) << wq->log_stride);
 }
 
 static inline u32 mlx5_cqwq_get_wrap_cnt(struct mlx5_cqwq *wq)

include/linux/mlx5/driver.h

@@ -318,6 +318,13 @@ struct mlx5_buf {
 	u8			page_shift;
 };
 
+struct mlx5_frag_buf {
+	struct mlx5_buf_list	*frags;
+	int			npages;
+	int			size;
+	u8			page_shift;
+};
+
 struct mlx5_eq_tasklet {
 	struct list_head list;
 	struct list_head process_list;
@@ -822,6 +829,9 @@ int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
 void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf);
+int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
+			     struct mlx5_frag_buf *buf, int node);
+void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
 struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev,
 						      gfp_t flags, int npages);
 void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev,
@@ -866,6 +876,7 @@ void mlx5_unregister_debugfs(void);
 int mlx5_eq_init(struct mlx5_core_dev *dev);
 void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
 void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas);
+void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
 void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn);
 void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING