RDMA/umem: Handle a half-complete start/end sequence

mmu_notifier_unregister() can race between a invalidate_start/end and
cause the invalidate_end to be skipped. This causes an imbalance in the
locking, which lockdep complains about.

This is not actually a bug, as we immediately kfree the memory holding the
lock, but it simple enough to fix.

Mark when the notifier is being destroyed and abort the start callback.
This can be done under the lock we already obtained, and can re-purpose
the invalidate_range test we already have.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

include/rdma/ib_umem_odp.h

@@ -89,6 +89,7 @@ struct ib_ucontext_per_mm {
 	struct ib_ucontext *context;
 	struct mm_struct *mm;
 	struct pid *tgid;
+	bool active;
 
 	struct rb_root_cached umem_tree;
 	/* Protects umem_tree */