FAILED: patch "[PATCH] NFSv4: Fix a state manager thread deadlock regression" failed to apply to 5.10-stable tree

FAILED: patch "[PATCH] NFSv4: Fix a state manager thread deadlock regression" failed to apply to 5.10-stable tree

[gregkh]

The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 956fd46f97d238032cb5fa4771cdaccc6e760f9a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2023100429-stonework-conceal-099d@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 956fd46f97d238032cb5fa4771cdaccc6e760f9a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sun, 24 Sep 2023 13:14:15 -0400
Subject: [PATCH] NFSv4: Fix a state manager thread deadlock regression

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@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3508d8238826..7016eaadf555 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10622,7 +10622,9 @@ 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 0bc160fbabec..9a5d911a7edc 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1209,16 +1209,26 @@ 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;
 
-	if (clp->cl_rpcclient->cl_shutdown)
+	if (clnt->cl_shutdown)
 		return;
 
 	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);
 	}
@@ -2748,22 +2759,25 @@ 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);