IB: Improve uverbs_cleanup_ucontext algorithm

Improve uverbs_cleanup_ucontext algorithm to work properly when the
topology graph of the objects cannot be determined at compile time.  This
is the case with objects created via the devx interface in mlx5.

Typically uverbs objects must be created in a strict topologically sorted
order, so that LIFO ordering will generally cause them to be freed
properly. There are only a few cases (eg memory windows) where objects can
point to things out of the strict LIFO order.

Instead of using an explicit ordering scheme where the HW destroy is not
allowed to fail, go over the list multiple times and allow the destroy
function to fail. If progress halts then a final, desperate, cleanup is
done before leaking the memory. This indicates a driver bug.

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

1 files changed, 8 insertions, 3 deletions

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 5fc14fde274c..5d0fd36b009d 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -116,6 +116,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	ucontext->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
 	rcu_read_unlock();
 	ucontext->closing = 0;
+	ucontext->cleanup_retryable = false;
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	ucontext->umem_tree = RB_ROOT_CACHED;
@@ -611,12 +612,13 @@ ssize_t ib_uverbs_close_xrcd(struct ib_uverbs_file *file,
 	return ret ?: in_len;
 }
 
-int ib_uverbs_dealloc_xrcd(struct ib_uverbs_device *dev,
+int ib_uverbs_dealloc_xrcd(struct ib_uobject *uobject,
 			   struct ib_xrcd *xrcd,
 			   enum rdma_remove_reason why)
 {
 	struct inode *inode;
 	int ret;
+	struct ib_uverbs_device *dev = uobject->context->ufile->device;
 
 	inode = xrcd->inode;
 	if (inode && !atomic_dec_and_test(&xrcd->usecnt))
@@ -624,9 +626,12 @@ int ib_uverbs_dealloc_xrcd(struct ib_uverbs_device *dev,
 
 	ret = ib_dealloc_xrcd(xrcd);
 
-	if (why == RDMA_REMOVE_DESTROY && ret)
+	if (ib_is_destroy_retryable(ret, why, uobject)) {
 		atomic_inc(&xrcd->usecnt);
-	else if (inode)
+		return ret;
+	}
+
+	if (inode)
 		xrcd_table_delete(dev, inode);
 
 	return ret;