[PATCH 7.2.y 1/6] NFSD: Prevent client use-after-free during delegation revoke

[Sasha Levin <sashal@kernel.org>]

From: Chuck Lever <cel@kernel.org>

[ Upstream commit 4683ca76b3b7e5808338491c6eb3c20e6b4894d5 ]

A delegation stateid holds only a bare pointer to its owning
nfs4_client and does not keep it alive.  The client survives its
stateids only because __destroy_client() drains cl_delegations and
cl_revoked before free_client() runs.

nfs4_laundromat() breaks that invariant: it unhashes an
expired delegation from cl_delegations, drops deleg_lock, then
revoke_delegation() relinks it onto cl_revoked under cl_lock.  In that
window the delegation is on neither list, so client_has_state() can
report no remaining state.

Every teardown path first requires cl_rpc_users to be zero, but
the laundromat holds no such reference.  A client whose recalled
delegation has just timed out can therefore reach free_client()
while revoke_delegation() is still about to dereference cl_lock,
a use-after-free.

Pin the client with cl_rpc_users across the revoke so teardown blocks
until it completes, then reap the delegation from cl_revoked.  A client
already expiring reaps its own, so skip it and leave the delegation on
del_recall_lru.

Fixes: 3bd64a5ba171 ("nfsd4: implement SEQ4_STATUS_RECALLABLE_STATE_REVOKED")
Cc: stable@vger.kernel.org
Reviewed-by: NeilBrown <neil@brown.name>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260709-cel-v4-2-1d519d9be0cb@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
Stable-dep-of: 2330b788d732 ("NFSD: Prevent client use-after-free during close_lru reaping")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfsd/netns.h     |  6 ++++--
 fs/nfsd/nfs4state.c | 23 +++++++++++++++++++++++
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 27da1a3edacbf..21ed2f1ec48d4 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -101,7 +101,8 @@ struct nfsd_net {
 	struct list_head client_lru;
 	struct list_head close_lru;
 
-	/* protects del_recall_lru and delegation hash/unhash */
+	/* protects del_recall_lru and delegation hash/unhash;
+	 * nests outside client_lock */
 	spinlock_t deleg_lock ____cacheline_aligned;
 	struct list_head del_recall_lru;
 
@@ -110,7 +111,8 @@ struct nfsd_net {
 
 	struct delayed_work laundromat_work;
 
-	/* client_lock protects the client lru list and session hash table */
+	/* client_lock protects the client lru list and session hash
+	 * table; nests inside deleg_lock */
 	spinlock_t client_lock;
 
 	/* protects blocked_locks_lru */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a42f34842d776..e1a8d300636b9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7062,6 +7062,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		.new_timeo = nn->nfsd4_lease
 	};
 	struct nfs4_cpntf_state *cps;
+	struct nfs4_client *clp;
 	copy_stateid_t *cps_t;
 	int i;
 
@@ -7090,6 +7091,18 @@ nfs4_laundromat(struct nfsd_net *nn)
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		if (!state_expired(&lt, dp->dl_time))
 			break;
+		clp = dp->dl_stid.sc_client;
+		spin_lock(&nn->client_lock);
+		if (is_client_expired(clp)) {
+			spin_unlock(&nn->client_lock);
+			continue;
+		}
+		/*
+		 * Pin without reviving: get_client_locked() would
+		 * flip a courtesy client back to NFSD4_ACTIVE.
+		 */
+		atomic_inc(&clp->cl_rpc_users);
+		spin_unlock(&nn->client_lock);
 		refcount_inc(&dp->dl_stid.sc_count);
 		unhash_delegation_locked(dp, SC_STATUS_REVOKED);
 		list_add(&dp->dl_recall_lru, &reaplist);
@@ -7098,8 +7111,18 @@ nfs4_laundromat(struct nfsd_net *nn)
 	while (!list_empty(&reaplist)) {
 		dp = list_first_entry(&reaplist, struct nfs4_delegation,
 					dl_recall_lru);
+		clp = dp->dl_stid.sc_client;
 		list_del_init(&dp->dl_recall_lru);
 		revoke_delegation(dp);
+		/*
+		 * Unpin without renewing: put_client_renew() would
+		 * renew the reaped client's lease.
+		 */
+		if (atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) {
+			if (is_client_expired(clp))
+				wake_up_all(&expiry_wq);
+			spin_unlock(&nn->client_lock);
+		}
 	}
 
 	spin_lock(&nn->client_lock);
-- 
2.53.0