[PATCH 3/3] nfsd: drop st_mutex_mutex before calling move_to_close_lru()

[NeilBrown <neilb@suse.de>]

move_to_close_lru() is currently called with ->st_mutex held.
This can lead to a deadlock as move_to_close_lru() waits for sc_count to
drop to 2, and some threads holding a reference might be waiting for the
mutex.  These references will never be dropped so sc_count will never
reach 2.

There can be no harm in dropping ->st_mutex before
move_to_close_lru() because the only place that takes the mutex is
nfsd4_lock_ol_stateid(), and it quickly aborts if sc_type is
NFS4_CLOSED_STID, which it will be before move_to_close_lru() is called.

See also
 https://lore.kernel.org/lkml/4dd1fe21e11344e5969bb112e954affb@jd.com/T/
where this problem was raised but not successfully resolved.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5dab316932d3..bb0f563cb2d2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7015,7 +7015,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	return status;
 }
 
-static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
+static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 {
 	struct nfs4_client *clp = s->st_stid.sc_client;
 	bool unhashed;
@@ -7032,11 +7032,11 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 		list_for_each_entry(stp, &reaplist, st_locks)
 			nfs4_free_cpntf_statelist(clp->net, &stp->st_stid);
 		free_ol_stateid_reaplist(&reaplist);
+		return false;
 	} else {
 		spin_unlock(&clp->cl_lock);
 		free_ol_stateid_reaplist(&reaplist);
-		if (unhashed)
-			move_to_close_lru(s, clp->net);
+		return unhashed;
 	}
 }
 
@@ -7052,6 +7052,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfs4_ol_stateid *stp;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	bool need_move_to_close_list;
 
 	dprintk("NFSD: nfsd4_close on file %pd\n", 
 			cstate->current_fh.fh_dentry);
@@ -7074,8 +7075,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 */
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
 
-	nfsd4_close_open_stateid(stp);
+	need_move_to_close_list = nfsd4_close_open_stateid(stp);
 	mutex_unlock(&stp->st_mutex);
+	if (need_move_to_close_list)
+		move_to_close_lru(stp, net);
 
 	/* v4.1+ suggests that we send a special stateid in here, since the
 	 * clients should just ignore this anyway. Since this is not useful
-- 
2.43.0