Merge branch 'mlx5-next' into rdma.git

From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

mlx5 updates taken for dependencies on later ODP patches.

Conflict resolved by deleting mlx5_ib_get_vector_affinity()

* branch 'mlx5-next': (21 commits)
  net/mlx5: EQ, Make EQE access methods inline
  {net,IB}/mlx5: Move Page fault EQ and ODP logic to RDMA
  net/mlx5: EQ, Generic EQ
  net/mlx5: EQ, Different EQ types
  net/mlx5: EQ, Privatize eq_table and friends
  net/mlx5: EQ, irq_info and rmap belong to eq_table
  net/mlx5: EQ, Create all EQs in one place
  net/mlx5: EQ, Move all EQ logic to eq.c
  net/mlx5: EQ, Remove redundant completion EQ list lock
  net/mlx5: EQ, No need to store eq index as a field
  net/mlx5: EQ, Remove unused fields and structures
  net/mlx5: EQ, Use the right place to store/read IRQ affinity hint
  IB/mlx5: Improve ODP debugging messages
  net/mlx5: Use multi threaded workqueue for page fault handling
  net/mlx5: Return success for PAGE_FAULT_RESUME in internal error state
  IB/mlx5: Lock QP during page fault handling
  net/mlx5: Enumerate page fault types
  net/mlx5: Add interface to hold and release core resources
  net/mlx5: Release resource on error flow
  net/mlx5: Fix offsets of ifc reserved fields
  ...
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/core/umem_odp.c

@@ -655,8 +655,13 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 				flags, local_page_list, NULL, NULL);
 		up_read(&owning_mm->mmap_sem);
 
-		if (npages < 0)
+		if (npages < 0) {
+			if (npages != -EAGAIN)
+				pr_warn("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
+			else
+				pr_debug("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
 			break;
+		}
 
 		bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
 		mutex_lock(&umem_odp->umem_mutex);
@@ -674,8 +679,13 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 			ret = ib_umem_odp_map_dma_single_page(
 					umem_odp, k, local_page_list[j],
 					access_mask, current_seq);
-			if (ret < 0)
+			if (ret < 0) {
+				if (ret != -EAGAIN)
+					pr_warn("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
+				else
+					pr_debug("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
 				break;
+			}
 
 			p = page_to_phys(local_page_list[j]);
 			k++;

drivers/infiniband/hw/mlx5/main.c

@@ -5693,8 +5693,7 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
 	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->ib_dev.phys_port_cnt	= dev->num_ports;
-	dev->ib_dev.num_comp_vectors    =
-		dev->mdev->priv.eq_table.num_comp_vectors;
+	dev->ib_dev.num_comp_vectors    = mlx5_comp_vectors_count(mdev);
 	dev->ib_dev.dev.parent		= &mdev->pdev->dev;
 
 	mutex_init(&dev->cap_mask_mutex);
@@ -6032,6 +6031,11 @@ static int mlx5_ib_stage_odp_init(struct mlx5_ib_dev *dev)
 	return mlx5_ib_odp_init_one(dev);
 }
 
+void mlx5_ib_stage_odp_cleanup(struct mlx5_ib_dev *dev)
+{
+	mlx5_ib_odp_cleanup_one(dev);
+}
+
 int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
@@ -6217,7 +6221,7 @@ static const struct mlx5_ib_profile pf_profile = {
 		     mlx5_ib_stage_dev_res_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_ODP,
 		     mlx5_ib_stage_odp_init,
-		     NULL),
+		     mlx5_ib_stage_odp_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_COUNTERS,
 		     mlx5_ib_stage_counters_init,
 		     mlx5_ib_stage_counters_cleanup),
@@ -6387,9 +6391,6 @@ static struct mlx5_interface mlx5_ib_interface = {
 	.add            = mlx5_ib_add,
 	.remove         = mlx5_ib_remove,
 	.event          = mlx5_ib_event,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	.pfault		= mlx5_ib_pfault,
-#endif
 	.protocol	= MLX5_INTERFACE_PROTOCOL_IB,
 };
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -880,6 +880,15 @@ struct mlx5_ib_lb_state {
 	bool			enabled;
 };
 
+struct mlx5_ib_pf_eq {
+	struct mlx5_ib_dev *dev;
+	struct mlx5_eq *core;
+	struct work_struct work;
+	spinlock_t lock; /* Pagefaults spinlock */
+	struct workqueue_struct *wq;
+	mempool_t *pool;
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	const struct uverbs_object_tree_def *driver_trees[7];
@@ -902,6 +911,8 @@ struct mlx5_ib_dev {
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	struct ib_odp_caps	odp_caps;
 	u64			odp_max_size;
+	struct mlx5_ib_pf_eq	odp_pf_eq;
+
 	/*
 	 * Sleepable RCU that prevents destruction of MRs while they are still
 	 * being used by a page fault handler.
@@ -1158,9 +1169,8 @@ struct ib_mr *mlx5_ib_reg_dm_mr(struct ib_pd *pd, struct ib_dm *dm,
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev);
-void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
-		    struct mlx5_pagefault *pfault);
 int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
+void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
 void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
@@ -1175,6 +1185,7 @@ static inline void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 }
 
 static inline int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev) { return 0; }
+static inline void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev) {}
 static inline int mlx5_ib_odp_init(void) { return 0; }
 static inline void mlx5_ib_odp_cleanup(void)				    {}
 static inline void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent) {}

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

@@ -313,6 +313,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_FPGA_DESTROY_QP:
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
+	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -326,7 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_MKEY:
 	case MLX5_CMD_OP_QUERY_MKEY:
 	case MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS:
-	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 	case MLX5_CMD_OP_CREATE_EQ:
 	case MLX5_CMD_OP_QUERY_EQ:
 	case MLX5_CMD_OP_GEN_EQE:

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

@@ -38,6 +38,7 @@
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/cq.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 #define TASKLET_MAX_TIME 2
 #define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
@@ -92,10 +93,10 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
 	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
-	struct mlx5_eq *eq;
+	struct mlx5_eq_comp *eq;
 	int err;
 
-	eq = mlx5_eqn2eq(dev, eqn);
+	eq = mlx5_eqn2comp_eq(dev, eqn);
 	if (IS_ERR(eq))
 		return PTR_ERR(eq);
 
@@ -119,12 +120,12 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
 
 	/* Add to comp EQ CQ tree to recv comp events */
-	err = mlx5_eq_add_cq(eq, cq);
+	err = mlx5_eq_add_cq(&eq->core, cq);
 	if (err)
 		goto err_cmd;
 
 	/* Add to async EQ CQ tree to recv async events */
-	err = mlx5_eq_add_cq(&dev->priv.eq_table.async_eq, cq);
+	err = mlx5_eq_add_cq(mlx5_get_async_eq(dev), cq);
 	if (err)
 		goto err_cq_add;
 
@@ -139,7 +140,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	return 0;
 
 err_cq_add:
-	mlx5_eq_del_cq(eq, cq);
+	mlx5_eq_del_cq(&eq->core, cq);
 err_cmd:
 	memset(din, 0, sizeof(din));
 	memset(dout, 0, sizeof(dout));
@@ -157,11 +158,11 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
 	int err;
 
-	err = mlx5_eq_del_cq(&dev->priv.eq_table.async_eq, cq);
+	err = mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
 	if (err)
 		return err;
 
-	err = mlx5_eq_del_cq(cq->eq, cq);
+	err = mlx5_eq_del_cq(&cq->eq->core, cq);
 	if (err)
 		return err;
 

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

@@ -36,6 +36,7 @@
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	QP_PID,
@@ -349,6 +350,16 @@ static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 	return param;
 }
 
+static int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+			      u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {};
+
+	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
+	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
 static u64 eq_read_field(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 			 int index)
 {

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

@@ -139,17 +139,6 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 
 		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);
 	}
 
@@ -179,15 +168,6 @@ 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);
@@ -447,20 +427,6 @@ 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);

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

@@ -178,8 +178,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
 		MLX5E_MIN_NUM_CHANNELS :
-		min_t(int, mdev->priv.eq_table.num_comp_vectors,
-		      MLX5E_MAX_NUM_CHANNELS);
+		min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS);
 }
 
 /* Use this function to get max num channels after netdev was created */

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

@@ -49,6 +49,7 @@
 #include "lib/clock.h"
 #include "en/port.h"
 #include "en/xdp.h"
+#include "lib/eq.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -319,7 +320,7 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
 	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
+	mlx5_eq_synchronize_async_irq(priv->mdev);
 }
 
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
@@ -1758,11 +1759,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
-}
-
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1913,9 +1909,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_channel_param *cparam,
 			      struct mlx5e_channel **cp)
 {
+	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
 	struct net_dim_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	unsigned int irq;
 	int err;
@@ -4121,17 +4117,17 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
 					struct mlx5e_txqsq *sq)
 {
-	struct mlx5_eq *eq = sq->cq.mcq.eq;
+	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
 	u32 eqe_count;
 
 	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->eqn, eq->cons_index, eq->irqn);
+		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
 
 	eqe_count = mlx5_eq_poll_irq_disabled(eq);
 	if (!eqe_count)
 		return false;
 
-	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
+	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn);
 	sq->channel->stats->eq_rearm++;
 	return true;
 }
@@ -4960,7 +4956,7 @@ int mlx5e_netdev_init(struct net_device *netdev,
 	netif_carrier_off(netdev);
 
 #ifdef CONFIG_MLX5_EN_ARFS
-	netdev->rx_cpu_rmap = mdev->rmap;
+	netdev->rx_cpu_rmap =  mlx5_eq_table_get_rmap(mdev);
 #endif
 
 	return 0;

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

@@ -38,6 +38,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "fs_core.h"
+#include "lib/eq.h"
 
 #define UPLINK_VPORT 0xFFFF
 
@@ -1567,7 +1568,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
+	mlx5_eq_synchronize_async_irq(esw->dev);
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */

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

@@ -38,6 +38,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	MLX5_HEALTH_POLL_INTERVAL	= 2 * HZ,
@@ -84,7 +85,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	u64 vector;
 
 	/* wait for pending handlers to complete */
-	synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
+	mlx5_eq_synchronize_cmd_irq(dev);
 	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
 	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
 	if (!vector)

drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#ifndef __LIB_MLX5_EQ_H__
+#define __LIB_MLX5_EQ_H__
+#include <linux/mlx5/driver.h>
+
+#define MLX5_MAX_IRQ_NAME   (32)
+#define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
+
+struct mlx5_eq_tasklet {
+	struct list_head      list;
+	struct list_head      process_list;
+	struct tasklet_struct task;
+	spinlock_t            lock; /* lock completion tasklet list */
+};
+
+struct mlx5_cq_table {
+	spinlock_t              lock;	/* protect radix tree */
+	struct radix_tree_root  tree;
+};
+
+struct mlx5_eq {
+	struct mlx5_core_dev    *dev;
+	struct mlx5_cq_table    cq_table;
+	__be32 __iomem	        *doorbell;
+	u32                     cons_index;
+	struct mlx5_frag_buf    buf;
+	int                     size;
+	unsigned int            vecidx;
+	unsigned int            irqn;
+	u8                      eqn;
+	int                     nent;
+	struct mlx5_rsc_debug   *dbg;
+};
+
+struct mlx5_eq_comp {
+	struct mlx5_eq          core; /* Must be first */
+	struct mlx5_eq_tasklet  tasklet_ctx;
+	struct list_head        list;
+};
+
+static inline struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
+{
+	return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
+}
+
+static inline struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
+{
+	struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
+
+	return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
+}
+
+static inline void eq_update_ci(struct mlx5_eq *eq, int arm)
+{
+	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+	u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+	__raw_writel((__force u32)cpu_to_be32(val), addr);
+	/* We still want ordering, just not swabbing, so add a barrier */
+	mb();
+}
+
+int mlx5_eq_table_init(struct mlx5_core_dev *dev);
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_eq_table_create(struct mlx5_core_dev *dev);
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
+
+int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn);
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
+void mlx5_cq_tasklet_cb(unsigned long data);
+struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);
+
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq);
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev);
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev);
+
+int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
+void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
+#endif
+
+#endif

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -100,8 +100,6 @@ int mlx5_cmd_fast_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, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
@@ -124,28 +122,7 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 
-int mlx5_eq_init(struct mlx5_core_dev *dev);
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name,
-		       enum mlx5_eq_type type);
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-		       u32 *out, int outlen);
-int mlx5_start_eqs(struct mlx5_core_dev *dev);
-void mlx5_stop_eqs(struct mlx5_core_dev *dev);
-/* This function should only be called after mlx5_cmd_force_teardown_hca */
-void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
-void mlx5_cq_tasklet_cb(unsigned long data);
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
-int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
-void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
 

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

@@ -132,7 +132,7 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type)) {
 		mlx5_core_warn(dev, "event 0x%.2x is not allowed on resource 0x%.8x\n",
 			       event_type, rsn);
-		return;
+		goto out;
 	}
 
 	switch (common->res) {
@@ -150,7 +150,7 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	default:
 		mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
 	}
-
+out:
 	mlx5_core_put_rsc(common);
 }
 
@@ -670,3 +670,19 @@ int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_q_counter);
+
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type)
+{
+	u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
+
+	return mlx5_get_rsc(dev, rsn);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_hold);
+
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res)
+{
+	mlx5_core_put_rsc(res);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_put);

include/linux/mlx5/cq.h

@@ -60,7 +60,7 @@ struct mlx5_core_cq {
 	} tasklet_ctx;
 	int			reset_notify_added;
 	struct list_head	reset_notify;
-	struct mlx5_eq		*eq;
+	struct mlx5_eq_comp	*eq;
 	u16 uid;
 };
 

include/linux/mlx5/device.h

@@ -212,6 +212,13 @@ enum {
 	MLX5_PFAULT_SUBTYPE_RDMA = 1,
 };
 
+enum wqe_page_fault_type {
+	MLX5_WQE_PF_TYPE_RMP = 0,
+	MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE = 1,
+	MLX5_WQE_PF_TYPE_RESP = 2,
+	MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC = 3,
+};
+
 enum {
 	MLX5_PERM_LOCAL_READ	= 1 << 2,
 	MLX5_PERM_LOCAL_WRITE	= 1 << 3,

include/linux/mlx5/driver.h

@@ -84,18 +84,6 @@ enum {
 	MLX5_MAX_PORTS	= 2,
 };
 
-enum {
-	MLX5_EQ_VEC_PAGES	 = 0,
-	MLX5_EQ_VEC_CMD		 = 1,
-	MLX5_EQ_VEC_ASYNC	 = 2,
-	MLX5_EQ_VEC_PFAULT	 = 3,
-	MLX5_EQ_VEC_COMP_BASE,
-};
-
-enum {
-	MLX5_MAX_IRQ_NAME	= 32
-};
-
 enum {
 	MLX5_ATOMIC_MODE_OFFSET = 16,
 	MLX5_ATOMIC_MODE_IB_COMP = 1,
@@ -222,14 +210,6 @@ enum mlx5_port_status {
 	MLX5_PORT_DOWN      = 2,
 };
 
-enum mlx5_eq_type {
-	MLX5_EQ_TYPE_COMP,
-	MLX5_EQ_TYPE_ASYNC,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	MLX5_EQ_TYPE_PF,
-#endif
-};
-
 struct mlx5_bfreg_info {
 	u32		       *sys_pages;
 	int			num_low_latency_bfregs;
@@ -366,51 +346,6 @@ struct mlx5_frag_buf_ctrl {
 	u8			log_frag_strides;
 };
 
-struct mlx5_eq_tasklet {
-	struct list_head list;
-	struct list_head process_list;
-	struct tasklet_struct task;
-	/* lock on completion tasklet list */
-	spinlock_t lock;
-};
-
-struct mlx5_eq_pagefault {
-	struct work_struct       work;
-	/* Pagefaults lock */
-	spinlock_t		 lock;
-	struct workqueue_struct *wq;
-	mempool_t		*pool;
-};
-
-struct mlx5_cq_table {
-	/* protect radix tree */
-	spinlock_t		lock;
-	struct radix_tree_root	tree;
-};
-
-struct mlx5_eq {
-	struct mlx5_core_dev   *dev;
-	struct mlx5_cq_table	cq_table;
-	__be32 __iomem	       *doorbell;
-	u32			cons_index;
-	struct mlx5_frag_buf	buf;
-	int			size;
-	unsigned int		irqn;
-	u8			eqn;
-	int			nent;
-	u64			mask;
-	struct list_head	list;
-	int			index;
-	struct mlx5_rsc_debug	*dbg;
-	enum mlx5_eq_type	type;
-	union {
-		struct mlx5_eq_tasklet   tasklet_ctx;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		struct mlx5_eq_pagefault pf_ctx;
-#endif
-	};
-};
-
 struct mlx5_core_psv {
 	u32	psv_idx;
 	struct psv_layout {
@@ -477,22 +412,6 @@ struct mlx5_core_srq {
 	u16		uid;
 };
 
-struct mlx5_eq_table {
-	void __iomem	       *update_ci;
-	void __iomem	       *update_arm_ci;
-	struct list_head	comp_eqs_list;
-	struct mlx5_eq		pages_eq;
-	struct mlx5_eq		async_eq;
-	struct mlx5_eq		cmd_eq;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	struct mlx5_eq		pfault_eq;
-#endif
-	int			num_comp_vectors;
-	/* protect EQs list
-	 */
-	spinlock_t		lock;
-};
-
 struct mlx5_uars_page {
 	void __iomem	       *map;
 	bool			wc;
@@ -575,11 +494,6 @@ struct mlx5_core_sriov {
 	int			enabled_vfs;
 };
 
-struct mlx5_irq_info {
-	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
-};
-
 struct mlx5_fc_stats {
 	spinlock_t counters_idr_lock; /* protects counters_idr */
 	struct idr counters_idr;
@@ -596,7 +510,7 @@ struct mlx5_fc_stats {
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
-struct mlx5_pagefault;
+struct mlx5_eq_table;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -646,8 +560,7 @@ struct mlx5_port_module_event_stats {
 
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
-	struct mlx5_eq_table	eq_table;
-	struct mlx5_irq_info	*irq_info;
+	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
 	struct workqueue_struct *pg_wq;
@@ -705,13 +618,6 @@ struct mlx5_priv {
 
 	struct mlx5_port_module_event_stats  pme_stats;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	void		      (*pfault)(struct mlx5_core_dev *dev,
-					void *context,
-					struct mlx5_pagefault *pfault);
-	void		       *pfault_ctx;
-	struct srcu_struct      pfault_srcu;
-#endif
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_uars_page	       *uar;
 };
@@ -736,44 +642,6 @@ enum mlx5_pagefault_type_flags {
 	MLX5_PFAULT_RDMA      = 1 << 2,
 };
 
-/* Contains the details of a pagefault. */
-struct mlx5_pagefault {
-	u32			bytes_committed;
-	u32			token;
-	u8			event_subtype;
-	u8			type;
-	union {
-		/* Initiator or send message responder pagefault details. */
-		struct {
-			/* Received packet size, only valid for responders. */
-			u32	packet_size;
-			/*
-			 * Number of resource holding WQE, depends on type.
-			 */
-			u32	wq_num;
-			/*
-			 * WQE index. Refers to either the send queue or
-			 * receive queue, according to event_subtype.
-			 */
-			u16	wqe_index;
-		} wqe;
-		/* RDMA responder pagefault details */
-		struct {
-			u32	r_key;
-			/*
-			 * Received packet size, minimal size page fault
-			 * resolution required for forward progress.
-			 */
-			u32	packet_size;
-			u32	rdma_op_len;
-			u64	rdma_va;
-		} rdma;
-	};
-
-	struct mlx5_eq	       *eq;
-	struct work_struct	work;
-};
-
 struct mlx5_td {
 	struct list_head tirs_list;
 	u32              tdn;
@@ -858,9 +726,6 @@ struct mlx5_core_dev {
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
-#endif
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap         *rmap;
 #endif
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
@@ -1155,6 +1020,9 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
 		     bool map_wc, bool fast_path);
 void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector);
 unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
 int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   u8 roce_version, u8 roce_l3_type, const u8 *gid,
@@ -1204,9 +1072,6 @@ struct mlx5_interface {
 	void			(*detach)(struct mlx5_core_dev *dev, void *context);
 	void			(*event)(struct mlx5_core_dev *dev, void *context,
 					 enum mlx5_dev_event event, unsigned long param);
-	void			(*pfault)(struct mlx5_core_dev *dev,
-					  void *context,
-					  struct mlx5_pagefault *pfault);
 	void *                  (*get_dev)(void *context);
 	int			protocol;
 	struct list_head	list;

include/linux/mlx5/eq.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef MLX5_CORE_EQ_H
+#define MLX5_CORE_EQ_H
+
+#include <linux/mlx5/driver.h>
+
+enum {
+	MLX5_EQ_PAGEREQ_IDX        = 0,
+	MLX5_EQ_CMD_IDX            = 1,
+	MLX5_EQ_ASYNC_IDX          = 2,
+	/* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */
+	MLX5_EQ_PFAULT_IDX         = 3,
+	MLX5_EQ_MAX_ASYNC_EQS,
+	/* completion eqs vector indices start here */
+	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
+};
+
+#define MLX5_NUM_CMD_EQE   (32)
+#define MLX5_NUM_ASYNC_EQE (0x1000)
+#define MLX5_NUM_SPARE_EQE (0x80)
+
+struct mlx5_eq;
+
+struct mlx5_eq_param {
+	u8             index;
+	int            nent;
+	u64            mask;
+	void          *context;
+	irq_handler_t  handler;
+};
+
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+		       struct mlx5_eq_param *param);
+int
+mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc);
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm);
+
+/* The HCA will think the queue has overflowed if we
+ * don't tell it we've been processing events.  We
+ * create EQs with MLX5_NUM_SPARE_EQE extra entries,
+ * so we must update our consumer index at
+ * least that often.
+ *
+ * mlx5_eq_update_cc must be called on every EQE @EQ irq handler
+ */
+static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc)
+{
+	if (unlikely(cc >= MLX5_NUM_SPARE_EQE)) {
+		mlx5_eq_update_ci(eq, cc, 0);
+		cc = 0;
+	}
+	return cc;
+}
+
+#endif /* MLX5_CORE_EQ_H */

include/linux/mlx5/mlx5_ifc.h

@@ -349,7 +349,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8	   reformat_l3_tunnel_to_l2[0x1];
 	u8	   reformat_l2_to_l3_tunnel[0x1];
 	u8	   reformat_and_modify_action[0x1];
-	u8         reserved_at_14[0xb];
+	u8         reserved_at_15[0xb];
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
 	u8         log_max_modify_header_context[0x8];
@@ -586,7 +586,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      fdb_multi_path_to_table[0x1];
 	u8      reserved_at_1d[0x1];
 	u8      multi_fdb_encap[0x1];
-	u8      reserved_at_1e[0x1e1];
+	u8      reserved_at_1f[0x1e1];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
 
@@ -829,7 +829,7 @@ struct mlx5_ifc_vector_calc_cap_bits {
 	struct mlx5_ifc_calc_op calc2;
 	struct mlx5_ifc_calc_op calc3;
 
-	u8         reserved_at_e0[0x720];
+	u8         reserved_at_c0[0x720];
 };
 
 enum {
@@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits {
 
 	u8         wq_signature[0x1];
 	u8         cont_srq[0x1];
-	u8         dbr_umem_valid[0x1];
+	u8         reserved_at_22[0x1];
 	u8         rlky[0x1];
 	u8         basic_cyclic_rcv_wqe[0x1];
 	u8         log_rq_stride[0x3];
 	u8         xrcd[0x18];
 
 	u8         page_offset[0x6];
-	u8         reserved_at_46[0x2];
+	u8         reserved_at_46[0x1];
+	u8         dbr_umem_valid[0x1];
 	u8         cqn[0x18];
 
 	u8         reserved_at_60[0x20];
@@ -5566,7 +5567,7 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
 	u8         reserved_at_0[0x12];
 	u8	   affiliation[0x1];
-	u8	   reserved_at_e[0x1];
+	u8	   reserved_at_13[0x1];
 	u8         disable_uc_local_lb[0x1];
 	u8         disable_mc_local_lb[0x1];
 	u8         node_guid[0x1];
@@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits {
 
 	struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry;
 
-	u8         reserved_at_280[0x40];
+	u8         reserved_at_280[0x60];
+
 	u8         xrc_srq_umem_valid[0x1];
-	u8         reserved_at_2c1[0x5bf];
+	u8         reserved_at_2e1[0x1f];
+
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
@@ -9024,7 +9028,7 @@ struct mlx5_ifc_dcbx_param_bits {
 	u8         dcbx_cee_cap[0x1];
 	u8         dcbx_ieee_cap[0x1];
 	u8         dcbx_standby_cap[0x1];
-	u8         reserved_at_0[0x5];
+	u8         reserved_at_3[0x5];
 	u8         port_number[0x8];
 	u8         reserved_at_10[0xa];
 	u8         max_application_table_size[6];

include/linux/mlx5/qp.h

@@ -596,6 +596,11 @@ int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id);
 int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
 			      int reset, void *out, int out_size);
 
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type);
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
+
 static inline const char *mlx5_qp_type_str(int type)
 {
 	switch (type) {