diff mbox series

[rdma-next,1/7] RDMA/mlx5: Fix MR cache initialization error flow

Message ID c41d525fb3c72e28dd38511bf3aaccb5d584063e.1741875692.git.leon@kernel.org (mailing list archive)
State New
Headers show
Series Batch of mlx5_ib fixes | expand

Commit Message

Leon Romanovsky March 13, 2025, 2:29 p.m. UTC 
From: Michael Guralnik <michaelgur@nvidia.com>

Destroy all previously created cache entries and work queue when rolling
back the MR cache initialization upon an error.

Fixes: 73d09b2fe833 ("RDMA/mlx5: Introduce mlx5r_cache_rb_key")
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mr.c | 33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)
diff mbox series

Patch

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index bb02b6adbf2c..1ffa4b3d0f76 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -919,6 +919,25 @@  mlx5r_cache_create_ent_locked(struct mlx5_ib_dev *dev,
 	return ERR_PTR(ret);
 }
 
+static void mlx5r_destroy_cache_entries(struct mlx5_ib_dev *dev)
+{
+	struct rb_root *root = &dev->cache.rb_root;
+	struct mlx5_cache_ent *ent;
+	struct rb_node *node;
+
+	mutex_lock(&dev->cache.rb_lock);
+	node = rb_first(root);
+	while (node) {
+		ent = rb_entry(node, struct mlx5_cache_ent, node);
+		node = rb_next(node);
+		clean_keys(dev, ent);
+		rb_erase(&ent->node, root);
+		mlx5r_mkeys_uninit(ent);
+		kfree(ent);
+	}
+	mutex_unlock(&dev->cache.rb_lock);
+}
+
 int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_mkey_cache *cache = &dev->cache;
@@ -970,6 +989,8 @@  int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 err:
 	mutex_unlock(&cache->rb_lock);
 	mlx5_mkey_cache_debugfs_cleanup(dev);
+	mlx5r_destroy_cache_entries(dev);
+	destroy_workqueue(cache->wq);
 	mlx5_ib_warn(dev, "failed to create mkey cache entry\n");
 	return ret;
 }
@@ -1003,17 +1024,7 @@  void mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_cmd_cleanup_async_ctx(&dev->async_ctx);
 
 	/* At this point all entries are disabled and have no concurrent work. */
-	mutex_lock(&dev->cache.rb_lock);
-	node = rb_first(root);
-	while (node) {
-		ent = rb_entry(node, struct mlx5_cache_ent, node);
-		node = rb_next(node);
-		clean_keys(dev, ent);
-		rb_erase(&ent->node, root);
-		mlx5r_mkeys_uninit(ent);
-		kfree(ent);
-	}
-	mutex_unlock(&dev->cache.rb_lock);
+	mlx5r_destroy_cache_entries(dev);
 
 	destroy_workqueue(dev->cache.wq);
 	del_timer_sync(&dev->delay_timer);