NFSv4.1 fix infinite loop on I/O.

trondmy · amschuma-ntap · commit 994b15b983a7 · 2018-09-14T16:24:11.000-04:00
The previous fix broke recovery of delegated stateids because it assumes that if we did not mark the delegation as suspect, then the delegation has effectively been revoked, and so it removes that delegation irrespectively of whether or not it is valid and still in use. While this is "mostly harmless" for ordinary I/O, we've seen pNFS fail with LAYOUTGET spinning in an infinite loop while complaining that we're using an invalid stateid (in this case the all-zero stateid). What we rather want to do here is ensure that the delegation is always correctly marked as needing testing when that is the case. So we want to close the loophole offered by nfs4_schedule_stateid_recovery(), which marks the state as needing to be reclaimed, but not the delegation that may be backing it. Fixes: 0e3d3e5 ("NFSv4.1 fix infinite loop on IO BAD_STATEID error") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: stable@vger.kernel.org # v4.11+ Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
@@ -2676,14 +2676,18 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state)
 	}
 
 	nfs4_stateid_copy(&stateid, &delegation->stateid);
-	if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) ||
-		!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
-			&delegation->flags)) {
+	if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
 		rcu_read_unlock();
 		nfs_finish_clear_delegation_stateid(state, &stateid);
 		return;
 	}
 
+	if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
+				&delegation->flags)) {
+		rcu_read_unlock();
+		return;
+	}
+
 	cred = get_rpccred(delegation->cred);
 	rcu_read_unlock();
 	status = nfs41_test_and_free_expired_stateid(server, &stateid, cred);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
@@ -1390,6 +1390,8 @@ int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_
 
 	if (!nfs4_state_mark_reclaim_nograce(clp, state))
 		return -EBADF;
+	nfs_inode_find_delegation_state_and_recover(state->inode,
+			&state->stateid);
 	dprintk("%s: scheduling stateid recovery for server %s\n", __func__,
 			clp->cl_hostname);
 	nfs4_schedule_state_manager(clp);
