8 files changed, 107 insertions, 15 deletions

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 06b819db51b1..0ff8e60deccb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -23,7 +23,7 @@ static void nicvf_get_page(struct nicvf *nic)
 	if (!nic->rb_pageref || !nic->rb_page)
 		return;
 
-	atomic_add(nic->rb_pageref, &nic->rb_page->_count);
+	page_ref_add(nic->rb_page, nic->rb_pageref);
 	nic->rb_pageref = 0;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 80417fc564d4..4705e2dea423 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -1392,6 +1392,10 @@ struct ulp_mem_io {
 #define T5_ULP_MEMIO_ORDER_V(x) ((x) << T5_ULP_MEMIO_ORDER_S)
 #define T5_ULP_MEMIO_ORDER_F    T5_ULP_MEMIO_ORDER_V(1U)
 
+#define T5_ULP_MEMIO_FID_S	4
+#define T5_ULP_MEMIO_FID_M	0x7ff
+#define T5_ULP_MEMIO_FID_V(x)	((x) << T5_ULP_MEMIO_FID_S)
+
 /* ulp_mem_io.lock_addr fields */
 #define ULP_MEMIO_ADDR_S    0
 #define ULP_MEMIO_ADDR_V(x) ((x) << ULP_MEMIO_ADDR_S)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index b51e42d6fbec..873a631ad155 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -39,6 +39,53 @@
 #include <linux/mlx5/cq.h>
 #include "mlx5_core.h"
 
+#define TASKLET_MAX_TIME 2
+#define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
+
+void mlx5_cq_tasklet_cb(unsigned long data)
+{
+	unsigned long flags;
+	unsigned long end = jiffies + TASKLET_MAX_TIME_JIFFIES;
+	struct mlx5_eq_tasklet *ctx = (struct mlx5_eq_tasklet *)data;
+	struct mlx5_core_cq *mcq;
+	struct mlx5_core_cq *temp;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	list_splice_tail_init(&ctx->list, &ctx->process_list);
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	list_for_each_entry_safe(mcq, temp, &ctx->process_list,
+				 tasklet_ctx.list) {
+		list_del_init(&mcq->tasklet_ctx.list);
+		mcq->tasklet_ctx.comp(mcq);
+		if (atomic_dec_and_test(&mcq->refcount))
+			complete(&mcq->free);
+		if (time_after(jiffies, end))
+			break;
+	}
+
+	if (!list_empty(&ctx->process_list))
+		tasklet_schedule(&ctx->task);
+}
+
+static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq)
+{
+	unsigned long flags;
+	struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
+
+	spin_lock_irqsave(&tasklet_ctx->lock, flags);
+	/* When migrating CQs between EQs will be implemented, please note
+	 * that you need to sync this point. It is possible that
+	 * while migrating a CQ, completions on the old EQs could
+	 * still arrive.
+	 */
+	if (list_empty_careful(&cq->tasklet_ctx.list)) {
+		atomic_inc(&cq->refcount);
+		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
+	}
+	spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
+}
+
 void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn)
 {
 	struct mlx5_core_cq *cq;
@@ -96,6 +143,13 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	struct mlx5_create_cq_mbox_out out;
 	struct mlx5_destroy_cq_mbox_in din;
 	struct mlx5_destroy_cq_mbox_out dout;
+	int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context),
+			   c_eqn);
+	struct mlx5_eq *eq;
+
+	eq = mlx5_eqn2eq(dev, eqn);
+	if (IS_ERR(eq))
+		return PTR_ERR(eq);
 
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_CQ);
 	memset(&out, 0, sizeof(out));
@@ -111,6 +165,11 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	cq->arm_sn     = 0;
 	atomic_set(&cq->refcount, 1);
 	init_completion(&cq->free);
+	if (!cq->comp)
+		cq->comp = mlx5_add_cq_to_tasklet;
+	/* assuming CQ will be deleted before the EQ */
+	cq->tasklet_ctx.priv = &eq->tasklet_ctx;
+	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
 
 	spin_lock_irq(&table->lock);
 	err = radix_tree_insert(&table->tree, cq->cqn, cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f3456798c596..bd947704b59c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -433,8 +433,8 @@ static int mlx5e_alloc_rx_fragmented_mpwqe(struct mlx5e_rq *rq,
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
 		if (unlikely(mlx5e_alloc_and_map_page(rq, wi, i)))
 			goto err_unmap;
-		atomic_add(mlx5e_mpwqe_strides_per_page(rq),
-			   &wi->umr.dma_info[i].page->_count);
+		page_ref_add(wi->umr.dma_info[i].page,
+			     mlx5e_mpwqe_strides_per_page(rq));
 		wi->skbs_frags[i] = 0;
 	}
 
@@ -452,8 +452,8 @@ err_unmap:
 	while (--i >= 0) {
 		dma_unmap_page(rq->pdev, wi->umr.dma_info[i].addr, PAGE_SIZE,
 			       PCI_DMA_FROMDEVICE);
-		atomic_sub(mlx5e_mpwqe_strides_per_page(rq),
-			   &wi->umr.dma_info[i].page->_count);
+		page_ref_sub(wi->umr.dma_info[i].page,
+			     mlx5e_mpwqe_strides_per_page(rq));
 		put_page(wi->umr.dma_info[i].page);
 	}
 	dma_unmap_single(rq->pdev, wi->umr.mtt_addr, mtt_sz, PCI_DMA_TODEVICE);
@@ -477,8 +477,8 @@ void mlx5e_free_rx_fragmented_mpwqe(struct mlx5e_rq *rq,
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
 		dma_unmap_page(rq->pdev, wi->umr.dma_info[i].addr, PAGE_SIZE,
 			       PCI_DMA_FROMDEVICE);
-		atomic_sub(mlx5e_mpwqe_strides_per_page(rq) - wi->skbs_frags[i],
-			   &wi->umr.dma_info[i].page->_count);
+		page_ref_sub(wi->umr.dma_info[i].page,
+			mlx5e_mpwqe_strides_per_page(rq) - wi->skbs_frags[i]);
 		put_page(wi->umr.dma_info[i].page);
 	}
 	dma_unmap_single(rq->pdev, wi->umr.mtt_addr, mtt_sz, PCI_DMA_TODEVICE);
@@ -527,8 +527,8 @@ static int mlx5e_alloc_rx_linear_mpwqe(struct mlx5e_rq *rq,
 	 */
 	split_page(wi->dma_info.page, MLX5_MPWRQ_WQE_PAGE_ORDER);
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
-		atomic_add(mlx5e_mpwqe_strides_per_page(rq),
-			   &wi->dma_info.page[i]._count);
+		page_ref_add(&wi->dma_info.page[i],
+			     mlx5e_mpwqe_strides_per_page(rq));
 		wi->skbs_frags[i] = 0;
 	}
 
@@ -551,8 +551,8 @@ void mlx5e_free_rx_linear_mpwqe(struct mlx5e_rq *rq,
 	dma_unmap_page(rq->pdev, wi->dma_info.addr, rq->wqe_sz,
 		       PCI_DMA_FROMDEVICE);
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
-		atomic_sub(mlx5e_mpwqe_strides_per_page(rq) - wi->skbs_frags[i],
-			   &wi->dma_info.page[i]._count);
+		page_ref_sub(&wi->dma_info.page[i],
+			mlx5e_mpwqe_strides_per_page(rq) - wi->skbs_frags[i]);
 		put_page(&wi->dma_info.page[i]);
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 18fccec72c5d..0e30602ef76d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -202,7 +202,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 	struct mlx5_eqe *eqe;
 	int eqes_found = 0;
 	int set_ci = 0;
-	u32 cqn;
+	u32 cqn = -1;
 	u32 rsn;
 	u8 port;
 
@@ -320,6 +320,9 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 
 	eq_update_ci(eq, 1);
 
+	if (cqn != -1)
+		tasklet_schedule(&eq->tasklet_ctx.task);
+
 	return eqes_found;
 }
 
@@ -403,6 +406,12 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	if (err)
 		goto err_irq;
 
+	INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+	INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+	spin_lock_init(&eq->tasklet_ctx.lock);
+	tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
+		     (unsigned long)&eq->tasklet_ctx);
+
 	/* EQs are created in ARMED state
 	 */
 	eq_update_ci(eq, 1);
@@ -436,6 +445,7 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 		mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
 			       eq->eqn);
 	synchronize_irq(eq->irqn);
+	tasklet_disable(&eq->tasklet_ctx.task);
 	mlx5_buf_free(dev, &eq->buf);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6feef7fb9d6a..a19b59348dd6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -663,6 +663,23 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 }
 EXPORT_SYMBOL(mlx5_vector2eqn);
 
+struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
+{
+	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq *eq;
+
+	spin_lock(&table->lock);
+	list_for_each_entry(eq, &table->comp_eqs_list, list)
+		if (eq->eqn == eqn) {
+			spin_unlock(&table->lock);
+			return eq;
+		}
+
+	spin_unlock(&table->lock);
+
+	return ERR_PTR(-ENOENT);
+}
+
 static void free_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 482604bd051c..2f86ec6fcf25 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -102,6 +102,8 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id);
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
+struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
+void mlx5_cq_tasklet_cb(unsigned long data);
 
 void mlx5e_init(void);
 void mlx5e_cleanup(void);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 901a9acc2d2d..337e839ca586 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -920,7 +920,7 @@ static inline int qede_realloc_rx_buffer(struct qede_dev *edev,
 		 * network stack to take the ownership of the page
 		 * which can be recycled multiple times by the driver.
 		 */
-		atomic_inc(&curr_cons->data->_count);
+		page_ref_inc(curr_cons->data);
 		qede_reuse_page(edev, rxq, curr_cons);
 	}
 
@@ -1036,7 +1036,7 @@ static int qede_fill_frag_skb(struct qede_dev *edev,
 		/* Incr page ref count to reuse on allocation failure
 		 * so that it doesn't get freed while freeing SKB.
 		 */
-		atomic_inc(&current_bd->data->_count);
+		page_ref_inc(current_bd->data);
 		goto out;
 	}
 
@@ -1486,7 +1486,7 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
 				 * freeing SKB.
 				 */
 
-				atomic_inc(&sw_rx_data->data->_count);
+				page_ref_inc(sw_rx_data->data);
 				rxq->rx_alloc_errors++;
 				qede_recycle_rx_bd_ring(rxq, edev,
 							fp_cqe->bd_num);