net/mlx5_core: Use tasklet for user-space CQ completion events

Previously, we've fired all our completion callbacks straight from
our ISR.

Some of those callbacks were lightweight (for example, mlx5 Ethernet
napi callbacks), but some of them did more work (for example,
the user-space RDMA stack uverbs' completion handler). Besides that,
doing more than the minimal work in ISR is generally considered wrong,
it could even lead to a hard lockup of the system. Since when a lot
of completion events are generated by the hardware, the loop over
those events could be so long, that we'll get into a hard lockup by
the system watchdog.

In order to avoid that, add a new way of invoking completion events
callbacks. In the interrupt itself, we add the CQs which receive
completion event to a per-EQ list and schedule a tasklet. In the
tasklet context we loop over all the CQs in the list and invoke the
user callback.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 11 insertions, 1 deletions

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;