net/mlx5: EQ, Different EQ types

In mlx5 we have three types of usages for EQs,
1. Asynchronous EQs, used internally by mlx5 core for
 a. FW command completions
 b. FW page requests
 c. one EQ for all other Asynchronous events

2. Completion EQs, used for CQ completion (we create one per core)

3. *Special type of EQ (page fault) used for RDMA on demand paging
(ODP).

*The 3rd type shouldn't be special at least in mlx5 core, it is yet
another async events EQ with specific use case, it will be removed in
the next two patches, and will completely move its logic to mlx5_ib,
as it is rdma specific.

In this patch we remove use case (eq type) specific fields from
struct mlx5_eq into a new eq type specific structures.

struct mlx5_eq_async;
truct mlx5_eq_comp;
struct mlx5_eq_pagefault;

Separate between their type specific flows.

In the future we will allow users to create there own generic EQs.
for now we will allow only one for ODP in next patches.

We will introduce event listeners registration API for those who
want to receive mlx5 async events.
After that mlx5 eq handling will be clean from feature/user specific
handling.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>

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

@@ -93,10 +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);
 
@@ -120,7 +120,7 @@ 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;
 
@@ -140,7 +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));
@@ -162,7 +162,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *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/en_main.c

@@ -320,7 +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,
@@ -4117,17 +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;
 }

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

@@ -1568,7 +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

@@ -85,7 +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

@@ -8,11 +8,8 @@
 #define MLX5_MAX_IRQ_NAME       (32)
 
 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,
+	MLX5_EQ_MAX_ASYNC_EQS = 4, /* mlx5_core needs at least 3 */
+	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
 };
 
 struct mlx5_eq_tasklet {
@@ -22,13 +19,6 @@ struct mlx5_eq_tasklet {
 	spinlock_t            lock; /* lock completion tasklet list */
 };
 
-struct mlx5_eq_pagefault {
-	struct work_struct       work;
-	spinlock_t               lock; /* Pagefaults spinlock */
-	struct workqueue_struct  *wq;
-	mempool_t                *pool;
-};
-
 struct mlx5_cq_table {
 	spinlock_t              lock;	/* protect radix tree */
 	struct radix_tree_root  tree;
@@ -44,29 +34,48 @@ struct mlx5_eq {
 	unsigned int            irqn;
 	u8                      eqn;
 	int                     nent;
-	struct list_head        list;
 	struct mlx5_rsc_debug   *dbg;
-	enum mlx5_eq_type       type;
-	union {
+};
+
+struct mlx5_eq_comp {
+	struct mlx5_eq          core; /* Must be first */
 	struct mlx5_eq_tasklet  tasklet_ctx;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		struct mlx5_eq_pagefault pf_ctx;
-#endif
-	};
+	struct list_head        list;
+};
+
+struct mlx5_eq_pagefault {
+	struct mlx5_eq           core; /* Must be first */
+	struct work_struct       work;
+	spinlock_t               lock; /* Pagefaults spinlock */
+	struct workqueue_struct  *wq;
+	mempool_t                *pool;
 };
 
 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_create_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+			 int nent, u64 mask, const char *name,
+			 irq_handler_t handler);
+int mlx5_destroy_async_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);
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
+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);
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
 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);
 

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

@@ -53,8 +53,8 @@
 #endif
 #include <net/devlink.h>
 #include "mlx5_core.h"
-#include "fs_core.h"
 #include "lib/eq.h"
+#include "fs_core.h"
 #include "lib/mpfs.h"
 #include "eswitch.h"
 #include "lib/mlx5.h"

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

@@ -125,10 +125,6 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 
 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);
 

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/driver.h

@@ -210,14 +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;
@@ -692,7 +684,7 @@ struct mlx5_pagefault {
 		} rdma;
 	};
 
-	struct mlx5_eq	       *eq;
+	struct mlx5_eq_pagefault *eq;
 	struct work_struct	work;
 };