net/mlx5: Make mlx5_cmd_exec_cb() a safe API

APIs that have deferred callbacks should have some kind of cleanup
function that callers can use to fence the callbacks. Otherwise things
like module unloading can lead to dangling function pointers, or worse.

The IB MR code is the only place that calls this function and had a
really poor attempt at creating this fence. Provide a good version in
the core code as future patches will add more places that need this
fence.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>

2 files changed, 9 insertions, 32 deletions

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index efe383c0ac86..eedba0d2ec4b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -587,6 +587,7 @@ struct mlx5_ib_mr {
 	struct mlx5_ib_mr      *parent;
 	atomic_t		num_leaf_free;
 	wait_queue_head_t       q_leaf_free;
+	struct mlx5_async_work  cb_work;
 };
 
 struct mlx5_ib_mw {
@@ -944,6 +945,7 @@ struct mlx5_ib_dev {
 	struct mlx5_memic	memic;
 	u16			devx_whitelist_uid;
 	struct mlx5_srq_table   srq_table;
+	struct mlx5_async_ctx   async_ctx;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index fd6ea1f75085..bf2b6ea23851 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -123,9 +123,10 @@ static void update_odp_mr(struct mlx5_ib_mr *mr)
 }
 #endif
 
-static void reg_mr_callback(int status, void *context)
+static void reg_mr_callback(int status, struct mlx5_async_work *context)
 {
-	struct mlx5_ib_mr *mr = context;
+	struct mlx5_ib_mr *mr =
+		container_of(context, struct mlx5_ib_mr, cb_work);
 	struct mlx5_ib_dev *dev = mr->dev;
 	struct mlx5_mr_cache *cache = &dev->cache;
 	int c = order2idx(dev, mr->order);
@@ -216,9 +217,9 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 		ent->pending++;
 		spin_unlock_irq(&ent->lock);
 		err = mlx5_core_create_mkey_cb(dev->mdev, &mr->mmkey,
-					       in, inlen,
+					       &dev->async_ctx, in, inlen,
 					       mr->out, sizeof(mr->out),
-					       reg_mr_callback, mr);
+					       reg_mr_callback, &mr->cb_work);
 		if (err) {
 			spin_lock_irq(&ent->lock);
 			ent->pending--;
@@ -679,6 +680,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		return -ENOMEM;
 	}
 
+	mlx5_cmd_init_async_ctx(dev->mdev, &dev->async_ctx);
 	timer_setup(&dev->delay_timer, delay_time_func, 0);
 	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
 		ent = &cache->ent[i];
@@ -725,33 +727,6 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 	return 0;
 }
 
-static void wait_for_async_commands(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_mr_cache *cache = &dev->cache;
-	struct mlx5_cache_ent *ent;
-	int total = 0;
-	int i;
-	int j;
-
-	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
-		ent = &cache->ent[i];
-		for (j = 0 ; j < 1000; j++) {
-			if (!ent->pending)
-				break;
-			msleep(50);
-		}
-	}
-	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
-		ent = &cache->ent[i];
-		total += ent->pending;
-	}
-
-	if (total)
-		mlx5_ib_warn(dev, "aborted while there are %d pending mr requests\n", total);
-	else
-		mlx5_ib_warn(dev, "done with all pending requests\n");
-}
-
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 {
 	int i;
@@ -763,12 +738,12 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 	flush_workqueue(dev->cache.wq);
 
 	mlx5_mr_cache_debugfs_cleanup(dev);
+	mlx5_cmd_cleanup_async_ctx(&dev->async_ctx);
 
 	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++)
 		clean_keys(dev, i);
 
 	destroy_workqueue(dev->cache.wq);
-	wait_for_async_commands(dev);
 	del_timer_sync(&dev->delay_timer);
 
 	return 0;