Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma into master

Pull rdma fixes from Jason Gunthorpe:
 "One merge window regression, some corruption bugs in HNS and a few
  more syzkaller fixes:

   - Two long standing syzkaller races

   - Fix incorrect HW configuration in HNS

   - Restore accidentally dropped locking in IB CM

   - Fix ODP prefetch bug added in the big rework several versions ago"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/mlx5: Prevent prefetch from racing with implicit destruction
  RDMA/cm: Protect access to remote_sidr_table
  RDMA/core: Fix race in rdma_alloc_commit_uobject()
  RDMA/hns: Fix wrong PBL offset when VA is not aligned to PAGE_SIZE
  RDMA/hns: Fix wrong assignment of lp_pktn_ini in QPC
  RDMA/mlx5: Use xa_lock_irq when access to SRQ table

1 files changed, 19 insertions, 3 deletions

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 7d2ec9ee5097..1ab676b66894 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -601,6 +601,23 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 	 */
 	synchronize_srcu(&dev->odp_srcu);
 
+	/*
+	 * All work on the prefetch list must be completed, xa_erase() prevented
+	 * new work from being created.
+	 */
+	wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work));
+
+	/*
+	 * At this point it is forbidden for any other thread to enter
+	 * pagefault_mr() on this imr. It is already forbidden to call
+	 * pagefault_mr() on an implicit child. Due to this additions to
+	 * implicit_children are prevented.
+	 */
+
+	/*
+	 * Block destroy_unused_implicit_child_mr() from incrementing
+	 * num_deferred_work.
+	 */
 	xa_lock(&imr->implicit_children);
 	xa_for_each (&imr->implicit_children, idx, mtt) {
 		__xa_erase(&imr->implicit_children, idx);
@@ -609,9 +626,8 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 	xa_unlock(&imr->implicit_children);
 
 	/*
-	 * num_deferred_work can only be incremented inside the odp_srcu, or
-	 * under xa_lock while the child is in the xarray. Thus at this point
-	 * it is only decreasing, and all work holding it is now on the wq.
+	 * Wait for any concurrent destroy_unused_implicit_child_mr() to
+	 * complete.
 	 */
 	wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work));