+++ /dev/null
-From 8b5d51432765dd4d2c08a92607727eab3832ae24 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Mon, 7 Jul 2025 11:03:59 -0300
-Subject: sched: Do not call __put_task_struct() on rt if pi_blocked_on is set
-
-From: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
-
-[ Upstream commit 8671bad873ebeb082afcf7b4501395c374da6023 ]
-
-With PREEMPT_RT enabled, some of the calls to put_task_struct() coming
-from rt_mutex_adjust_prio_chain() could happen in preemptible context and
-with a mutex enqueued. That could lead to this sequence:
-
- rt_mutex_adjust_prio_chain()
- put_task_struct()
- __put_task_struct()
- sched_ext_free()
- spin_lock_irqsave()
- rtlock_lock() ---> TRIGGERS
- lockdep_assert(!current->pi_blocked_on);
-
-This is not a SCHED_EXT bug. The first cleanup function called by
-__put_task_struct() is sched_ext_free() and it happens to take a
-(RT) spin_lock, which in the scenario described above, would trigger
-the lockdep assertion of "!current->pi_blocked_on".
-
-Crystal Wood was able to identify the problem as __put_task_struct()
-being called during rt_mutex_adjust_prio_chain(), in the context of
-a process with a mutex enqueued.
-
-Instead of adding more complex conditions to decide when to directly
-call __put_task_struct() and when to defer the call, unconditionally
-resort to the deferred call on PREEMPT_RT to simplify the code.
-
-Fixes: 893cdaaa3977 ("sched: avoid false lockdep splat in put_task_struct()")
-Suggested-by: Crystal Wood <crwood@redhat.com>
-Signed-off-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Reviewed-by: Wander Lairson Costa <wander@redhat.com>
-Reviewed-by: Valentin Schneider <vschneid@redhat.com>
-Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
-Link: https://lore.kernel.org/r/aGvTz5VaPFyj0pBV@uudg.org
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/sched/task.h | 27 ++++++++++-----------------
- 1 file changed, 10 insertions(+), 17 deletions(-)
-
-diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
-index 8dbecab4c400..d440ee805900 100644
---- a/include/linux/sched/task.h
-+++ b/include/linux/sched/task.h
-@@ -127,24 +127,17 @@ static inline void put_task_struct(struct task_struct *t)
- return;
-
- /*
-- * In !RT, it is always safe to call __put_task_struct().
-- * Under RT, we can only call it in preemptible context.
-- */
-- if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
-- static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);
--
-- lock_map_acquire_try(&put_task_map);
-- __put_task_struct(t);
-- lock_map_release(&put_task_map);
-- return;
-- }
--
-- /*
-- * under PREEMPT_RT, we can't call put_task_struct
-+ * Under PREEMPT_RT, we can't call __put_task_struct
- * in atomic context because it will indirectly
-- * acquire sleeping locks.
-+ * acquire sleeping locks. The same is true if the
-+ * current process has a mutex enqueued (blocked on
-+ * a PI chain).
-+ *
-+ * In !RT, it is always safe to call __put_task_struct().
-+ * Though, in order to simplify the code, resort to the
-+ * deferred call too.
- *
-- * call_rcu() will schedule delayed_put_task_struct_rcu()
-+ * call_rcu() will schedule __put_task_struct_rcu_cb()
- * to be called in process context.
- *
- * __put_task_struct() is called when
-@@ -157,7 +150,7 @@ static inline void put_task_struct(struct task_struct *t)
- *
- * delayed_free_task() also uses ->rcu, but it is only called
- * when it fails to fork a process. Therefore, there is no
-- * way it can conflict with put_task_struct().
-+ * way it can conflict with __put_task_struct().
- */
- call_rcu(&t->rcu, __put_task_struct_rcu_cb);
- }
---
-2.39.5
-
--- /dev/null
+From bee47cb026e762841f3faece47b51f985e215edb Mon Sep 17 00:00:00 2001
+From: Olga Kornievskaia <okorniev@redhat.com>
+Date: Tue, 29 Jul 2025 12:40:20 -0400
+Subject: sunrpc: fix handling of server side tls alerts
+
+From: Olga Kornievskaia <okorniev@redhat.com>
+
+commit bee47cb026e762841f3faece47b51f985e215edb upstream.
+
+Scott Mayhew discovered a security exploit in NFS over TLS in
+tls_alert_recv() due to its assumption it can read data from
+the msg iterator's kvec..
+
+kTLS implementation splits TLS non-data record payload between
+the control message buffer (which includes the type such as TLS
+aler or TLS cipher change) and the rest of the payload (say TLS
+alert's level/description) which goes into the msg payload buffer.
+
+This patch proposes to rework how control messages are setup and
+used by sock_recvmsg().
+
+If no control message structure is setup, kTLS layer will read and
+process TLS data record types. As soon as it encounters a TLS control
+message, it would return an error. At that point, NFS can setup a
+kvec backed msg buffer and read in the control message such as a
+TLS alert. Msg iterator can advance the kvec pointer as a part of
+the copy process thus we need to revert the iterator before calling
+into the tls_alert_recv.
+
+Reported-by: Scott Mayhew <smayhew@redhat.com>
+Fixes: 5e052dda121e ("SUNRPC: Recognize control messages in server-side TCP socket code")
+Suggested-by: Trond Myklebust <trondmy@hammerspace.com>
+Cc: stable@vger.kernel.org
+Signed-off-by: Olga Kornievskaia <okorniev@redhat.com>
+Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/sunrpc/svcsock.c | 43 +++++++++++++++++++++++++++++++++++--------
+ 1 file changed, 35 insertions(+), 8 deletions(-)
+
+--- a/net/sunrpc/svcsock.c
++++ b/net/sunrpc/svcsock.c
+@@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket
+ }
+
+ static int
+-svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg)
++svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags)
+ {
+ union {
+ struct cmsghdr cmsg;
+ u8 buf[CMSG_SPACE(sizeof(u8))];
+ } u;
+- struct socket *sock = svsk->sk_sock;
++ u8 alert[2];
++ struct kvec alert_kvec = {
++ .iov_base = alert,
++ .iov_len = sizeof(alert),
++ };
++ struct msghdr msg = {
++ .msg_flags = *msg_flags,
++ .msg_control = &u,
++ .msg_controllen = sizeof(u),
++ };
++ int ret;
++
++ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
++ alert_kvec.iov_len);
++ ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
++ if (ret > 0 &&
++ tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
++ iov_iter_revert(&msg.msg_iter, ret);
++ ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN);
++ }
++ return ret;
++}
++
++static int
++svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg)
++{
+ int ret;
++ struct socket *sock = svsk->sk_sock;
+
+- msg->msg_control = &u;
+- msg->msg_controllen = sizeof(u);
+ ret = sock_recvmsg(sock, msg, MSG_DONTWAIT);
+- if (unlikely(msg->msg_controllen != sizeof(u)))
+- ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret);
++ if (msg->msg_flags & MSG_CTRUNC) {
++ msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
++ if (ret == 0 || ret == -EIO)
++ ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags);
++ }
+ return ret;
+ }
+
+@@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct s
+ iov_iter_advance(&msg.msg_iter, seek);
+ buflen -= seek;
+ }
+- len = svc_tcp_sock_recv_cmsg(svsk, &msg);
++ len = svc_tcp_sock_recvmsg(svsk, &msg);
+ if (len > 0)
+ svc_flush_bvec(bvec, len, seek);
+
+@@ -1019,7 +1046,7 @@ static ssize_t svc_tcp_read_marker(struc
+ iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen;
+ iov.iov_len = want;
+ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want);
+- len = svc_tcp_sock_recv_cmsg(svsk, &msg);
++ len = svc_tcp_sock_recvmsg(svsk, &msg);
+ if (len < 0)
+ return len;
+ svsk->sk_tcplen += len;
projects / thirdparty / kernel / stable-queue.git / commitdiff
