RDMA/mlx5: Fix MR cache initialization error flow

JIRA: https://issues.redhat.com/browse/RHEL-72227
JIRA: https://issues.redhat.com/browse/RHEL-73520
Upstream-status: v6.15-rc1

commit a0130ef
Author: Michael Guralnik <michaelgur@nvidia.com>
Date:   Thu Mar 13 16:29:48 2025 +0200

    RDMA/mlx5: Fix MR cache initialization error flow

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

    Fixes: 73d09b2 ("RDMA/mlx5: Introduce mlx5r_cache_rb_key")
    Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
    Reviewed-by: Yishai Hadas <yishaih@nvidia.com>
    Link: https://patch.msgid.link/c41d525fb3c72e28dd38511bf3aaccb5d584063e.1741875692.git.leon@kernel.org
    Signed-off-by: Leon Romanovsky <leon@kernel.org>

Signed-off-by: Benjamin Poirier <bpoirier@redhat.com>

Author: Benjamin Poirier

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);