NFSv4: Fix a state manager thread deadlock regression

[ Upstream commit 956fd46 ]

Commit 4dc73c6 reintroduces the deadlock that was fixed by commit
aeabb3c ("NFSv4: Fix a NFSv4 state manager deadlock") because it
prevents the setup of new threads to handle reboot recovery, while the
older recovery thread is stuck returning delegations.

Fixes: 4dc73c6 ("NFSv4: keep state manager thread active if swap is enabled")
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

fs/nfs/nfs4proc.c

@@ -10629,7 +10629,9 @@ static void nfs4_disable_swap(struct inode *inode)
 	 */
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 
-	nfs4_schedule_state_manager(clp);
+	set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
+	clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+	wake_up_var(&clp->cl_state);
 }
 
 static const struct inode_operations nfs4_dir_inode_operations = {

fs/nfs/nfs4state.c

@@ -1209,13 +1209,23 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 {
 	struct task_struct *task;
 	char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
+	struct rpc_clnt *clnt = clp->cl_rpcclient;
+	bool swapon = false;
 
 	set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
-	if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) {
-		wake_up_var(&clp->cl_state);
-		return;
+
+	if (atomic_read(&clnt->cl_swapper)) {
+		swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE,
+					   &clp->cl_state);
+		if (!swapon) {
+			wake_up_var(&clp->cl_state);
+			return;
+		}
 	}
-	set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
+
+	if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
+		return;
+
 	__module_get(THIS_MODULE);
 	refcount_inc(&clp->cl_count);
 
@@ -1232,8 +1242,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 			__func__, PTR_ERR(task));
 		if (!nfs_client_init_is_complete(clp))
 			nfs_mark_client_ready(clp, PTR_ERR(task));
+		if (swapon)
+			clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
 		nfs4_clear_state_manager_bit(clp);
-		clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
 		nfs_put_client(clp);
 		module_put(THIS_MODULE);
 	}
@@ -2737,22 +2748,25 @@ static int nfs4_run_state_manager(void *ptr)
 
 	allow_signal(SIGKILL);
 again:
-	set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
 	nfs4_state_manager(clp);
-	if (atomic_read(&cl->cl_swapper)) {
+
+	if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) &&
+	    !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) {
 		wait_var_event_interruptible(&clp->cl_state,
 					     test_bit(NFS4CLNT_RUN_MANAGER,
 						      &clp->cl_state));
-		if (atomic_read(&cl->cl_swapper) &&
-		    test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state))
+		if (!atomic_read(&cl->cl_swapper))
+			clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+		if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
+		    !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state))
 			goto again;
 		/* Either no longer a swapper, or were signalled */
+		clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
 	}
-	clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
 
 	if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
 	    test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) &&
-	    !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state))
+	    !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state))
 		goto again;
 
 	nfs_put_client(clp);