net: Remove acked SYN flag from packet in the transmit queue correctly

[ Upstream commit f99cd56230f56c8b6b33713c5be4da5d6766be1f ]

syzkaller report:

 kernel BUG at net/core/skbuff.c:3452!
 invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI
 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.7.0-rc4-00009-gbee0e7762ad2-dirty #135
 RIP: 0010:skb_copy_and_csum_bits (net/core/skbuff.c:3452)
 Call Trace:
 icmp_glue_bits (net/ipv4/icmp.c:357)
 __ip_append_data.isra.0 (net/ipv4/ip_output.c:1165)
 ip_append_data (net/ipv4/ip_output.c:1362 net/ipv4/ip_output.c:1341)
 icmp_push_reply (net/ipv4/icmp.c:370)
 __icmp_send (./include/net/route.h:252 net/ipv4/icmp.c:772)
 ip_fragment.constprop.0 (./include/linux/skbuff.h:1234 net/ipv4/ip_output.c:592 net/ipv4/ip_output.c:577)
 __ip_finish_output (net/ipv4/ip_output.c:311 net/ipv4/ip_output.c:295)
 ip_output (net/ipv4/ip_output.c:427)
 __ip_queue_xmit (net/ipv4/ip_output.c:535)
 __tcp_transmit_skb (net/ipv4/tcp_output.c:1462)
 __tcp_retransmit_skb (net/ipv4/tcp_output.c:3387)
 tcp_retransmit_skb (net/ipv4/tcp_output.c:3404)
 tcp_retransmit_timer (net/ipv4/tcp_timer.c:604)
 tcp_write_timer (./include/linux/spinlock.h:391 net/ipv4/tcp_timer.c:716)

The panic issue was trigered by tcp simultaneous initiation.
The initiation process is as follows:

      TCP A                                            TCP B

  1.  CLOSED                                           CLOSED

  2.  SYN-SENT     --> <SEQ=100><CTL=SYN>              ...

  3.  SYN-RECEIVED <-- <SEQ=300><CTL=SYN>              <-- SYN-SENT

  4.               ... <SEQ=100><CTL=SYN>              --> SYN-RECEIVED

  5.  SYN-RECEIVED --> <SEQ=100><ACK=301><CTL=SYN,ACK> ...

  // TCP B: not send challenge ack for ack limit or packet loss
  // TCP A: close
	tcp_close
	   tcp_send_fin
              if (!tskb && tcp_under_memory_pressure(sk))
                  tskb = skb_rb_last(&sk->tcp_rtx_queue); //pick SYN_ACK packet
           TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;  // set FIN flag

  6.  FIN_WAIT_1  --> <SEQ=100><ACK=301><END_SEQ=102><CTL=SYN,FIN,ACK> ...

  // TCP B: send challenge ack to SYN_FIN_ACK

  7.               ... <SEQ=301><ACK=101><CTL=ACK>   <-- SYN-RECEIVED //challenge ack

  // TCP A:  <SND.UNA=101>

  8.  FIN_WAIT_1 --> <SEQ=101><ACK=301><END_SEQ=102><CTL=SYN,FIN,ACK> ... // retransmit panic

	__tcp_retransmit_skb  //skb->len=0
	    tcp_trim_head
		len = tp->snd_una - TCP_SKB_CB(skb)->seq // len=101-100
		    __pskb_trim_head
			skb->data_len -= len // skb->len=-1, wrap around
	    ... ...
	    ip_fragment
		icmp_glue_bits //BUG_ON

If we use tcp_trim_head() to remove acked SYN from packet that contains data
or other flags, skb->len will be incorrectly decremented. We can remove SYN
flag that has been acked from rtx_queue earlier than tcp_trim_head(), which
can fix the problem mentioned above.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Co-developed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Dong Chenchen <dongchenchen2@huawei.com>
Link: https://lore.kernel.org/r/20231210020200.1539875-1-dongchenchen2@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 6 insertions, 0 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 67636017f275..2a07a167124c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2883,7 +2883,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (skb_still_in_host_queue(sk, skb))
 		return -EBUSY;
 
+start:
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+		if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+			TCP_SKB_CB(skb)->seq++;
+			goto start;
+		}
 		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;