net/mlx4_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, mlx4_en's and
IPoIB 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: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index f48e7c3eecf8..b67ef488c30c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -43,6 +43,8 @@
 #include <linux/timer.h>
 #include <linux/semaphore.h>
 #include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -373,6 +375,14 @@ struct mlx4_srq_context {
 	__be64			db_rec_addr;
 };
 
+struct mlx4_eq_tasklet {
+	struct list_head list;
+	struct list_head process_list;
+	struct tasklet_struct task;
+	/* lock on completion tasklet list */
+	spinlock_t lock;
+};
+
 struct mlx4_eq {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *doorbell;
@@ -383,6 +393,7 @@ struct mlx4_eq {
 	int			nent;
 	struct mlx4_buf_list   *page_list;
 	struct mlx4_mtt		mtt;
+	struct mlx4_eq_tasklet	tasklet_ctx;
 };
 
 struct mlx4_slave_eqe {
@@ -1146,6 +1157,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev);
 int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
 		  unsigned long timeout);
 
+void mlx4_cq_tasklet_cb(unsigned long data);
 void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
 void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);