Merge branch 'mlx5-odp'

Saeed Mahameed says:

====================
Mellanox mlx5 core and ODP updates 2017-01-01

The following eleven patches mainly come from Artemy Kovalyov
who expanded mlx5 on-demand-paging (ODP) support. In addition
there are three cleanup patches which don't change any functionality,
but are needed to align codebase prior accepting other patches.

Memory region (MR) in IB can be huge and ODP (on-demand paging)
technique allows to use unpinned memory, which can be consumed and
released on demand. This allows to applications do not pin down
the underlying physical pages of the address space, and save from them
need to track the validity of the mappings.

Rather, the HCA requests the latest translations from the OS when pages
are not present, and the OS invalidates translations which are no longer
valid due to either non-present pages or mapping changes.

In existing ODP implementation applications is needed to register
memory buffers for communication, though registered memory regions
need not have valid mappings at registration time.

This patch set performs the following steps to expand
current ODP implementation:

1. It refactors UMR to support large regions, by introducing generic
   function to perform HCA translation table modifications. This
   function supports both atomic and process contexts and is not limited
   by number of modified entries.

   This function allows to enable reallocated memory regions of
   arbitrary size, so adding MR cache buckets to support up to 16GB MRs.

2. It changes page fault event format and refactor page faults logic
   together with addition of atomic support.

3. It prepares mlx5 core code to support implicit registration with
   simplified and relaxed semantics.

   Implicit ODP semantics allows to applications provide special memory
   key that represents their complete address space. Thus all IO accesses
   referencing to this key (with proper access rights associated with the key)
   wouldn't need not register any virtual address range.

Thanks,
        Artemy, Ilya and Leon

v1->v2:
  - Don't use 'inline' in .c files
====================

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

6 files changed, 332 insertions, 150 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index a9dbc28f6b97..a62f4b6a21a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -71,6 +71,16 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	if (dev_ctx->context) {
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+		if (dev_ctx->intf->pfault) {
+			if (priv->pfault) {
+				mlx5_core_err(dev, "multiple page fault handlers not supported");
+			} else {
+				priv->pfault_ctx = dev_ctx->context;
+				priv->pfault = dev_ctx->intf->pfault;
+			}
+		}
+#endif
 		spin_unlock_irq(&priv->ctx_lock);
 	} else {
 		kfree(dev_ctx);
@@ -97,6 +107,15 @@ void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	if (!dev_ctx)
 		return;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	spin_lock_irq(&priv->ctx_lock);
+	if (priv->pfault == dev_ctx->intf->pfault)
+		priv->pfault = NULL;
+	spin_unlock_irq(&priv->ctx_lock);
+
+	synchronize_srcu(&priv->pfault_srcu);
+#endif
+
 	spin_lock_irq(&priv->ctx_lock);
 	list_del(&dev_ctx->list);
 	spin_unlock_irq(&priv->ctx_lock);
@@ -329,6 +348,20 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 	spin_unlock_irqrestore(&priv->ctx_lock, flags);
 }
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+void mlx5_core_page_fault(struct mlx5_core_dev *dev,
+			  struct mlx5_pagefault *pfault)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	int srcu_idx;
+
+	srcu_idx = srcu_read_lock(&priv->pfault_srcu);
+	if (priv->pfault)
+		priv->pfault(dev, priv->pfault_ctx, pfault);
+	srcu_read_unlock(&priv->pfault_srcu, srcu_idx);
+}
+#endif
+
 void mlx5_dev_list_lock(void)
 {
 	mutex_lock(&mlx5_intf_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cbfa38fc72c0..5ff86f0ecb7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -396,7 +396,7 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5e_sq *sq,
 	cseg->imm       = rq->mkey_be;
 
 	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN;
-	ucseg->klm_octowords =
+	ucseg->xlt_octowords =
 		cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
 	ucseg->bsf_octowords =
 		cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 8ffcc8808e50..4aff8ac68e14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -54,6 +54,7 @@ enum {
 	MLX5_NUM_SPARE_EQE	= 0x80,
 	MLX5_NUM_ASYNC_EQE	= 0x100,
 	MLX5_NUM_CMD_EQE	= 32,
+	MLX5_NUM_PF_DRAIN	= 64,
 };
 
 enum {
@@ -188,10 +189,193 @@ static void eq_update_ci(struct mlx5_eq *eq, int arm)
 	mb();
 }
 
-static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+static void eqe_pf_action(struct work_struct *work)
+{
+	struct mlx5_pagefault *pfault = container_of(work,
+						     struct mlx5_pagefault,
+						     work);
+	struct mlx5_eq *eq = pfault->eq;
+
+	mlx5_core_page_fault(eq->dev, pfault);
+	mempool_free(pfault, eq->pf_ctx.pool);
+}
+
+static void eq_pf_process(struct mlx5_eq *eq)
+{
+	struct mlx5_core_dev *dev = eq->dev;
+	struct mlx5_eqe_page_fault *pf_eqe;
+	struct mlx5_pagefault *pfault;
+	struct mlx5_eqe *eqe;
+	int set_ci = 0;
+
+	while ((eqe = next_eqe_sw(eq))) {
+		pfault = mempool_alloc(eq->pf_ctx.pool, GFP_ATOMIC);
+		if (!pfault) {
+			schedule_work(&eq->pf_ctx.work);
+			break;
+		}
+
+		dma_rmb();
+		pf_eqe = &eqe->data.page_fault;
+		pfault->event_subtype = eqe->sub_type;
+		pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed);
+
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n",
+			      eqe->sub_type, pfault->bytes_committed);
+
+		switch (eqe->sub_type) {
+		case MLX5_PFAULT_SUBTYPE_RDMA:
+			/* RDMA based event */
+			pfault->type =
+				be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24;
+			pfault->token =
+				be32_to_cpu(pf_eqe->rdma.pftype_token) &
+				MLX5_24BIT_MASK;
+			pfault->rdma.r_key =
+				be32_to_cpu(pf_eqe->rdma.r_key);
+			pfault->rdma.packet_size =
+				be16_to_cpu(pf_eqe->rdma.packet_length);
+			pfault->rdma.rdma_op_len =
+				be32_to_cpu(pf_eqe->rdma.rdma_op_len);
+			pfault->rdma.rdma_va =
+				be64_to_cpu(pf_eqe->rdma.rdma_va);
+			mlx5_core_dbg(dev,
+				      "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n",
+				      pfault->type, pfault->token,
+				      pfault->rdma.r_key);
+			mlx5_core_dbg(dev,
+				      "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n",
+				      pfault->rdma.rdma_op_len,
+				      pfault->rdma.rdma_va);
+			break;
+
+		case MLX5_PFAULT_SUBTYPE_WQE:
+			/* WQE based event */
+			pfault->type =
+				be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24;
+			pfault->token =
+				be32_to_cpu(pf_eqe->wqe.token);
+			pfault->wqe.wq_num =
+				be32_to_cpu(pf_eqe->wqe.pftype_wq) &
+				MLX5_24BIT_MASK;
+			pfault->wqe.wqe_index =
+				be16_to_cpu(pf_eqe->wqe.wqe_index);
+			pfault->wqe.packet_size =
+				be16_to_cpu(pf_eqe->wqe.packet_length);
+			mlx5_core_dbg(dev,
+				      "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n",
+				      pfault->type, pfault->token,
+				      pfault->wqe.wq_num,
+				      pfault->wqe.wqe_index);
+			break;
+
+		default:
+			mlx5_core_warn(dev,
+				       "Unsupported page fault event sub-type: 0x%02hhx\n",
+				       eqe->sub_type);
+			/* Unsupported page faults should still be
+			 * resolved by the page fault handler
+			 */
+		}
+
+		pfault->eq = eq;
+		INIT_WORK(&pfault->work, eqe_pf_action);
+		queue_work(eq->pf_ctx.wq, &pfault->work);
+
+		++eq->cons_index;
+		++set_ci;
+
+		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
+			eq_update_ci(eq, 0);
+			set_ci = 0;
+		}
+	}
+
+	eq_update_ci(eq, 1);
+}
+
+static irqreturn_t mlx5_eq_pf_int(int irq, void *eq_ptr)
+{
+	struct mlx5_eq *eq = eq_ptr;
+	unsigned long flags;
+
+	if (spin_trylock_irqsave(&eq->pf_ctx.lock, flags)) {
+		eq_pf_process(eq);
+		spin_unlock_irqrestore(&eq->pf_ctx.lock, flags);
+	} else {
+		schedule_work(&eq->pf_ctx.work);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* mempool_refill() was proposed but unfortunately wasn't accepted
+ * http://lkml.iu.edu/hypermail/linux/kernel/1512.1/05073.html
+ * Chip workaround.
+ */
+static void mempool_refill(mempool_t *pool)
+{
+	while (pool->curr_nr < pool->min_nr)
+		mempool_free(mempool_alloc(pool, GFP_KERNEL), pool);
+}
+
+static void eq_pf_action(struct work_struct *work)
+{
+	struct mlx5_eq *eq = container_of(work, struct mlx5_eq, pf_ctx.work);
+
+	mempool_refill(eq->pf_ctx.pool);
+
+	spin_lock_irq(&eq->pf_ctx.lock);
+	eq_pf_process(eq);
+	spin_unlock_irq(&eq->pf_ctx.lock);
+}
+
+static int init_pf_ctx(struct mlx5_eq_pagefault *pf_ctx, const char *name)
 {
+	spin_lock_init(&pf_ctx->lock);
+	INIT_WORK(&pf_ctx->work, eq_pf_action);
+
+	pf_ctx->wq = alloc_ordered_workqueue(name,
+					     WQ_MEM_RECLAIM);
+	if (!pf_ctx->wq)
+		return -ENOMEM;
+
+	pf_ctx->pool = mempool_create_kmalloc_pool
+		(MLX5_NUM_PF_DRAIN, sizeof(struct mlx5_pagefault));
+	if (!pf_ctx->pool)
+		goto err_wq;
+
+	return 0;
+err_wq:
+	destroy_workqueue(pf_ctx->wq);
+	return -ENOMEM;
+}
+
+int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
+				u32 wq_num, u8 type, int error)
+{
+	u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)]   = {0};
+
+	MLX5_SET(page_fault_resume_in, in, opcode,
+		 MLX5_CMD_OP_PAGE_FAULT_RESUME);
+	MLX5_SET(page_fault_resume_in, in, error, !!error);
+	MLX5_SET(page_fault_resume_in, in, page_fault_type, type);
+	MLX5_SET(page_fault_resume_in, in, wq_number, wq_num);
+	MLX5_SET(page_fault_resume_in, in, token, token);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
+#endif
+
+static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
+{
+	struct mlx5_eq *eq = eq_ptr;
+	struct mlx5_core_dev *dev = eq->dev;
 	struct mlx5_eqe *eqe;
-	int eqes_found = 0;
 	int set_ci = 0;
 	u32 cqn = -1;
 	u32 rsn;
@@ -276,12 +460,6 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			}
 			break;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		case MLX5_EVENT_TYPE_PAGE_FAULT:
-			mlx5_eq_pagefault(dev, eqe);
-			break;
-#endif
-
 #ifdef CONFIG_MLX5_CORE_EN
 		case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
 			mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
@@ -299,7 +477,6 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 		}
 
 		++eq->cons_index;
-		eqes_found = 1;
 		++set_ci;
 
 		/* The HCA will think the queue has overflowed if we
@@ -319,17 +496,6 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 	if (cqn != -1)
 		tasklet_schedule(&eq->tasklet_ctx.task);
 
-	return eqes_found;
-}
-
-static irqreturn_t mlx5_msix_handler(int irq, void *eq_ptr)
-{
-	struct mlx5_eq *eq = eq_ptr;
-	struct mlx5_core_dev *dev = eq->dev;
-
-	mlx5_eq_int(dev, eq);
-
-	/* MSI-X vectors always belong to us */
 	return IRQ_HANDLED;
 }
 
@@ -345,22 +511,32 @@ static void init_eq_buf(struct mlx5_eq *eq)
 }
 
 int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name, struct mlx5_uar *uar)
+		       int nent, u64 mask, const char *name,
+		       struct mlx5_uar *uar, enum mlx5_eq_type type)
 {
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
+	irq_handler_t handler;
 	__be64 *pas;
 	void *eqc;
 	int inlen;
 	u32 *in;
 	int err;
 
+	eq->type = type;
 	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
 	eq->cons_index = 0;
 	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf);
 	if (err)
 		return err;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (type == MLX5_EQ_TYPE_PF)
+		handler = mlx5_eq_pf_int;
+	else
+#endif
+		handler = mlx5_eq_int;
+
 	init_eq_buf(eq);
 
 	inlen = MLX5_ST_SZ_BYTES(create_eq_in) +
@@ -396,7 +572,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	eq->irqn = priv->msix_arr[vecidx].vector;
 	eq->dev = dev;
 	eq->doorbell = uar->map + MLX5_EQ_DOORBEL_OFFSET;
-	err = request_irq(eq->irqn, mlx5_msix_handler, 0,
+	err = request_irq(eq->irqn, handler, 0,
 			  priv->irq_info[vecidx].name, eq);
 	if (err)
 		goto err_eq;
@@ -405,11 +581,20 @@ 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);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (type == MLX5_EQ_TYPE_PF) {
+		err = init_pf_ctx(&eq->pf_ctx, name);
+		if (err)
+			goto err_irq;
+	} else
+#endif
+	{
+		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
 	 */
@@ -444,7 +629,16 @@ 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);
+
+	if (eq->type == MLX5_EQ_TYPE_COMP) {
+		tasklet_disable(&eq->tasklet_ctx.task);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	} else if (eq->type == MLX5_EQ_TYPE_PF) {
+		cancel_work_sync(&eq->pf_ctx.work);
+		destroy_workqueue(eq->pf_ctx.wq);
+		mempool_destroy(eq->pf_ctx.pool);
+#endif
+	}
 	mlx5_buf_free(dev, &eq->buf);
 
 	return err;
@@ -479,8 +673,6 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
 	int err;
 
-	if (MLX5_CAP_GEN(dev, pg))
-		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PAGE_FAULT);
 
 	if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH &&
 	    MLX5_CAP_GEN(dev, vport_group_manager) &&
@@ -494,7 +686,8 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
-				 "mlx5_cmd_eq", &dev->priv.uuari.uars[0]);
+				 "mlx5_cmd_eq", &dev->priv.uuari.uars[0],
+				 MLX5_EQ_TYPE_ASYNC);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
 		return err;
@@ -504,7 +697,8 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 
 	err = mlx5_create_map_eq(dev, &table->async_eq, MLX5_EQ_VEC_ASYNC,
 				 MLX5_NUM_ASYNC_EQE, async_event_mask,
-				 "mlx5_async_eq", &dev->priv.uuari.uars[0]);
+				 "mlx5_async_eq", &dev->priv.uuari.uars[0],
+				 MLX5_EQ_TYPE_ASYNC);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
 		goto err1;
@@ -514,13 +708,35 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 				 MLX5_EQ_VEC_PAGES,
 				 /* TODO: sriov max_vf + */ 1,
 				 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
-				 &dev->priv.uuari.uars[0]);
+				 &dev->priv.uuari.uars[0],
+				 MLX5_EQ_TYPE_ASYNC);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
 		goto err2;
 	}
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (MLX5_CAP_GEN(dev, pg)) {
+		err = mlx5_create_map_eq(dev, &table->pfault_eq,
+					 MLX5_EQ_VEC_PFAULT,
+					 MLX5_NUM_ASYNC_EQE,
+					 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
+					 "mlx5_page_fault_eq",
+					 &dev->priv.uuari.uars[0],
+					 MLX5_EQ_TYPE_PF);
+		if (err) {
+			mlx5_core_warn(dev, "failed to create page fault EQ %d\n",
+				       err);
+			goto err3;
+		}
+	}
+
 	return err;
+err3:
+	mlx5_destroy_unmap_eq(dev, &table->pages_eq);
+#else
+	return err;
+#endif
 
 err2:
 	mlx5_destroy_unmap_eq(dev, &table->async_eq);
@@ -536,6 +752,14 @@ int mlx5_stop_eqs(struct mlx5_core_dev *dev)
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	int err;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (MLX5_CAP_GEN(dev, pg)) {
+		err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
+		if (err)
+			return err;
+	}
+#endif
+
 	err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 54e5a786f191..f4115135e30b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -152,6 +152,26 @@ static struct mlx5_profile profile[] = {
 			.size	= 8,
 			.limit	= 4
 		},
+		.mr_cache[16]	= {
+			.size	= 8,
+			.limit	= 4
+		},
+		.mr_cache[17]	= {
+			.size	= 8,
+			.limit	= 4
+		},
+		.mr_cache[18]	= {
+			.size	= 8,
+			.limit	= 4
+		},
+		.mr_cache[19]	= {
+			.size	= 4,
+			.limit	= 2
+		},
+		.mr_cache[20]	= {
+			.size	= 4,
+			.limit	= 2
+		},
 	},
 };
 
@@ -733,7 +753,8 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
 		err = mlx5_create_map_eq(dev, eq,
 					 i + MLX5_EQ_VEC_COMP_BASE, nent, 0,
-					 name, &dev->priv.uuari.uars[0]);
+					 name, &dev->priv.uuari.uars[0],
+					 MLX5_EQ_TYPE_COMP);
 		if (err) {
 			kfree(eq);
 			goto clean;
@@ -1275,10 +1296,19 @@ static int init_one(struct pci_dev *pdev,
 	spin_lock_init(&priv->ctx_lock);
 	mutex_init(&dev->pci_status_mutex);
 	mutex_init(&dev->intf_state_mutex);
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	err = init_srcu_struct(&priv->pfault_srcu);
+	if (err) {
+		dev_err(&pdev->dev, "init_srcu_struct failed with error code %d\n",
+			err);
+		goto clean_dev;
+	}
+#endif
 	err = mlx5_pci_init(dev, priv);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
-		goto clean_dev;
+		goto clean_srcu;
 	}
 
 	err = mlx5_health_init(dev);
@@ -1312,7 +1342,11 @@ clean_health:
 	mlx5_health_cleanup(dev);
 close_pci:
 	mlx5_pci_close(dev, priv);
+clean_srcu:
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	cleanup_srcu_struct(&priv->pfault_srcu);
 clean_dev:
+#endif
 	pci_set_drvdata(pdev, NULL);
 	devlink_free(devlink);
 
@@ -1337,6 +1371,9 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	mlx5_pci_close(dev, priv);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	cleanup_srcu_struct(&priv->pfault_srcu);
+#endif
 	pci_set_drvdata(pdev, NULL);
 	devlink_free(devlink);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index d4a99c9757cb..74241e82de63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -86,6 +86,8 @@ int mlx5_cmd_init_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
+void mlx5_core_page_fault(struct mlx5_core_dev *dev,
+			  struct mlx5_pagefault *pfault);
 void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index d0a4005fe63a..cbbcef2884be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -143,95 +143,6 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	mlx5_core_put_rsc(common);
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
-{
-	struct mlx5_eqe_page_fault *pf_eqe = &eqe->data.page_fault;
-	int qpn = be32_to_cpu(pf_eqe->flags_qpn) & MLX5_QPN_MASK;
-	struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, qpn);
-	struct mlx5_core_qp *qp =
-		container_of(common, struct mlx5_core_qp, common);
-	struct mlx5_pagefault pfault;
-
-	if (!qp) {
-		mlx5_core_warn(dev, "ODP event for non-existent QP %06x\n",
-			       qpn);
-		return;
-	}
-
-	pfault.event_subtype = eqe->sub_type;
-	pfault.flags = (be32_to_cpu(pf_eqe->flags_qpn) >> MLX5_QPN_BITS) &
-		(MLX5_PFAULT_REQUESTOR | MLX5_PFAULT_WRITE | MLX5_PFAULT_RDMA);
-	pfault.bytes_committed = be32_to_cpu(
-		pf_eqe->bytes_committed);
-
-	mlx5_core_dbg(dev,
-		      "PAGE_FAULT: subtype: 0x%02x, flags: 0x%02x,\n",
-		      eqe->sub_type, pfault.flags);
-
-	switch (eqe->sub_type) {
-	case MLX5_PFAULT_SUBTYPE_RDMA:
-		/* RDMA based event */
-		pfault.rdma.r_key =
-			be32_to_cpu(pf_eqe->rdma.r_key);
-		pfault.rdma.packet_size =
-			be16_to_cpu(pf_eqe->rdma.packet_length);
-		pfault.rdma.rdma_op_len =
-			be32_to_cpu(pf_eqe->rdma.rdma_op_len);
-		pfault.rdma.rdma_va =
-			be64_to_cpu(pf_eqe->rdma.rdma_va);
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: qpn: 0x%06x, r_key: 0x%08x,\n",
-			      qpn, pfault.rdma.r_key);
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: rdma_op_len: 0x%08x,\n",
-			      pfault.rdma.rdma_op_len);
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: rdma_va: 0x%016llx,\n",
-			      pfault.rdma.rdma_va);
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: bytes_committed: 0x%06x\n",
-			      pfault.bytes_committed);
-		break;
-
-	case MLX5_PFAULT_SUBTYPE_WQE:
-		/* WQE based event */
-		pfault.wqe.wqe_index =
-			be16_to_cpu(pf_eqe->wqe.wqe_index);
-		pfault.wqe.packet_size =
-			be16_to_cpu(pf_eqe->wqe.packet_length);
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: qpn: 0x%06x, wqe_index: 0x%04x,\n",
-			      qpn, pfault.wqe.wqe_index);
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: bytes_committed: 0x%06x\n",
-			      pfault.bytes_committed);
-		break;
-
-	default:
-		mlx5_core_warn(dev,
-			       "Unsupported page fault event sub-type: 0x%02hhx, QP %06x\n",
-			       eqe->sub_type, qpn);
-		/* Unsupported page faults should still be resolved by the
-		 * page fault handler
-		 */
-	}
-
-	if (qp->pfault_handler) {
-		qp->pfault_handler(qp, &pfault);
-	} else {
-		mlx5_core_err(dev,
-			      "ODP event for QP %08x, without a fault handler in QP\n",
-			      qpn);
-		/* Page fault will remain unresolved. QP will hang until it is
-		 * destroyed
-		 */
-	}
-
-	mlx5_core_put_rsc(common);
-}
-#endif
-
 static int create_qprqsq_common(struct mlx5_core_dev *dev,
 				struct mlx5_core_qp *qp,
 				int rsc_type)
@@ -506,31 +417,6 @@ int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn)
 }
 EXPORT_SYMBOL_GPL(mlx5_core_xrcd_dealloc);
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
-				u8 flags, int error)
-{
-	u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)]   = {0};
-
-	MLX5_SET(page_fault_resume_in, in, opcode,
-		 MLX5_CMD_OP_PAGE_FAULT_RESUME);
-	MLX5_SET(page_fault_resume_in, in, qpn, qpn);
-
-	if (flags & MLX5_PAGE_FAULT_RESUME_REQUESTOR)
-		MLX5_SET(page_fault_resume_in, in, req_res, 1);
-	if (flags & MLX5_PAGE_FAULT_RESUME_WRITE)
-		MLX5_SET(page_fault_resume_in, in, read_write, 1);
-	if (flags & MLX5_PAGE_FAULT_RESUME_RDMA)
-		MLX5_SET(page_fault_resume_in, in, rdma, 1);
-	if (error)
-		MLX5_SET(page_fault_resume_in, in, error, 1);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
-#endif
-
 int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
 				struct mlx5_core_qp *rq)
 {