Patch "NFSv4: Fix a state manager thread deadlock regression" has been added to the 5.10-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    NFSv4: Fix a state manager thread deadlock regression

to the 5.10-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     nfsv4-fix-a-state-manager-thread-deadlock-regression.patch
and it can be found in the queue-5.10 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 2dd17c2cafc3f03f89013275267c0da0f798795a
Author: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Date:   Sun Sep 24 13:14:15 2023 -0400

    NFSv4: Fix a state manager thread deadlock regression
    
    [ Upstream commit 956fd46f97d238032cb5fa4771cdaccc6e760f9a ]
    
    Commit 4dc73c679114 reintroduces the deadlock that was fixed by commit
    aeabb3c96186 ("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: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled")
    Cc: stable@xxxxxxxxxxxxxxx
    Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
    Signed-off-by: Anna Schumaker <Anna.Schumaker@xxxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c34df51a8f2b7..1c2ed14bccef2 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10408,7 +10408,9 @@ 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 = {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3fcef19e91984..10946b24c66f9 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1212,13 +1212,23 @@ 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);
 
@@ -1235,8 +1245,9 @@ 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);
 	}
@@ -2717,22 +2728,25 @@ 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);