[net,v3] kcm: close race conditions on sk_receive_queue

Commit Message

Cong Wang Nov. 14, 2022, 12:51 a.m. UTC

From: Cong Wang <[e-mail]>

sk->sk_receive_queue is protected by skb queue lock, but for KCM
sockets its RX path takes mux->rx_lock to protect more than just
skb queue. However, kcm_recvmsg() still only grabs the skb queue
lock, so race conditions still exist.

We can teach kcm_recvmsg() to grab mux->rx_lock too but this would
introduce a potential performance regression as struct kcm_mux can
be shared by multiple KCM sockets.

So we have to enforce skb queue lock in requeue_rx_msgs() and handle
skb peek case carefully in kcm_wait_data(). Fortunately,
skb_recv_datagram() already handles it nicely and is widely used by
other sockets, we can just switch to skb_recv_datagram() after
getting rid of the unnecessary sock lock in kcm_recvmsg() and
kcm_splice_read(). Side note: SOCK_DONE is not used by KCM sockets,
so it is safe to get rid of this check too.

I ran the original syzbot reproducer for 30 min without seeing any
issue.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reported-by: [e-mail]
Reported-by: shaozhengchao <[e-mail]>
Cc: Paolo Abeni <[e-mail]>
Cc: Tom Herbert <[e-mail]>
Signed-off-by: Cong Wang <[e-mail]>
---
 net/kcm/kcmsock.c | 58 +++++------------------------------------------
 1 file changed, 6 insertions(+), 52 deletions(-)

Comments

[e-mail] Nov. 15, 2022, noon UTC | #1

Hello:

This patch was applied to netdev/net.git (master)
by Paolo Abeni <[e-mail]>:

On Sun, 13 Nov 2022 16:51:19 -0800 you wrote:
> From: Cong Wang <[e-mail]>
> 
> sk->sk_receive_queue is protected by skb queue lock, but for KCM
> sockets its RX path takes mux->rx_lock to protect more than just
> skb queue. However, kcm_recvmsg() still only grabs the skb queue
> lock, so race conditions still exist.
> 
> [...]

Here is the summary with links:
  - [net,v3] kcm: close race conditions on sk_receive_queue
    https://git.kernel.org/netdev/net/c/5121197ecc5d

You are awesome, thank you!

Patch

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a5004228111d..890a2423f559 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -222,7 +222,7 @@  static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head)
 	struct sk_buff *skb;
 	struct kcm_sock *kcm;
 
-	while ((skb = __skb_dequeue(head))) {
+	while ((skb = skb_dequeue(head))) {
 		/* Reset destructor to avoid calling kcm_rcv_ready */
 		skb->destructor = sock_rfree;
 		skb_orphan(skb);
@@ -1085,53 +1085,17 @@  static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	return err;
 }
 
-static struct sk_buff *kcm_wait_data(struct sock *sk, int flags,
-				     long timeo, int *err)
-{
-	struct sk_buff *skb;
-
-	while (!(skb = skb_peek(&sk->sk_receive_queue))) {
-		if (sk->sk_err) {
-			*err = sock_error(sk);
-			return NULL;
-		}
-
-		if (sock_flag(sk, SOCK_DONE))
-			return NULL;
-
-		if ((flags & MSG_DONTWAIT) || !timeo) {
-			*err = -EAGAIN;
-			return NULL;
-		}
-
-		sk_wait_data(sk, &timeo, NULL);
-
-		/* Handle signals */
-		if (signal_pending(current)) {
-			*err = sock_intr_errno(timeo);
-			return NULL;
-		}
-	}
-
-	return skb;
-}
-
 static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
 		       size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
 	int err = 0;
-	long timeo;
 	struct strp_msg *stm;
 	int copied = 0;
 	struct sk_buff *skb;
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	lock_sock(sk);
-
-	skb = kcm_wait_data(sk, flags, timeo, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
@@ -1162,14 +1126,11 @@  static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
 			/* Finished with message */
 			msg->msg_flags |= MSG_EOR;
 			KCM_STATS_INCR(kcm->stats.rx_msgs);
-			skb_unlink(skb, &sk->sk_receive_queue);
-			kfree_skb(skb);
 		}
 	}
 
 out:
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return copied ? : err;
 }
 
@@ -1179,7 +1140,6 @@  static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
-	long timeo;
 	struct strp_msg *stm;
 	int err = 0;
 	ssize_t copied;
@@ -1187,11 +1147,7 @@  static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 
 	/* Only support splice for SOCKSEQPACKET */
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	lock_sock(sk);
-
-	skb = kcm_wait_data(sk, flags, timeo, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto err_out;
 
@@ -1219,13 +1175,11 @@  static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 	 * finish reading the message.
 	 */
 
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return copied;
 
 err_out:
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return err;
 }