aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_input.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-06-27 10:05:35 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-06-27 10:05:35 -0700
commitfd19d4a492af77b1e8fb0439781a3048d1d1f554 (patch)
treec293c1a1218fe87c4b6712938352dbc349d0b68e /net/ipv4/tcp_input.c
parent3c1d29e53d34537063e60f5eafe0482780a1735a (diff)
parentb62cb6a7e83622783100182d9b70e9c70393cfbe (diff)
downloadlinux-fd19d4a492af77b1e8fb0439781a3048d1d1f554.tar.gz
linux-fd19d4a492af77b1e8fb0439781a3048d1d1f554.tar.bz2
linux-fd19d4a492af77b1e8fb0439781a3048d1d1f554.zip
Merge tag 'net-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni: "Including fixes from can, bpf and netfilter. There are a bunch of regressions addressed here, but hopefully nothing spectacular. We are still waiting the driver fix from Intel, mentioned by Jakub in the previous networking pull. Current release - regressions: - core: add softirq safety to netdev_rename_lock - tcp: fix tcp_rcv_fastopen_synack() to enter TCP_CA_Loss for failed TFO - batman-adv: fix RCU race at module unload time Previous releases - regressions: - openvswitch: get related ct labels from its master if it is not confirmed - eth: bonding: fix incorrect software timestamping report - eth: mlxsw: fix memory corruptions on spectrum-4 systems - eth: ionic: use dev_consume_skb_any outside of napi Previous releases - always broken: - netfilter: fully validate NFT_DATA_VALUE on store to data registers - unix: several fixes for OoB data - tcp: fix race for duplicate reqsk on identical SYN - bpf: - fix may_goto with negative offset - fix the corner case with may_goto and jump to the 1st insn - fix overrunning reservations in ringbuf - can: - j1939: recover socket queue on CAN bus error during BAM transmission - mcp251xfd: fix infinite loop when xmit fails - dsa: microchip: monitor potential faults in half-duplex mode - eth: vxlan: pull inner IP header in vxlan_xmit_one() - eth: ionic: fix kernel panic due to multi-buffer handling Misc: - selftest: unix tests refactor and a lot of new cases added" * tag 'net-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (61 commits) net: mana: Fix possible double free in error handling path selftest: af_unix: Check SIOCATMARK after every send()/recv() in msg_oob.c. af_unix: Fix wrong ioctl(SIOCATMARK) when consumed OOB skb is at the head. selftest: af_unix: Check EPOLLPRI after every send()/recv() in msg_oob.c selftest: af_unix: Check SIGURG after every send() in msg_oob.c selftest: af_unix: Add SO_OOBINLINE test cases in msg_oob.c af_unix: Don't stop recv() at consumed ex-OOB skb. selftest: af_unix: Add non-TCP-compliant test cases in msg_oob.c. af_unix: Don't stop recv(MSG_DONTWAIT) if consumed OOB skb is at the head. af_unix: Stop recv(MSG_PEEK) at consumed OOB skb. selftest: af_unix: Add msg_oob.c. selftest: af_unix: Remove test_unix_oob.c. tracing/net_sched: NULL pointer dereference in perf_trace_qdisc_reset() netfilter: nf_tables: fully validate NFT_DATA_VALUE on store to data registers net: usb: qmi_wwan: add Telit FN912 compositions tcp: fix tcp_rcv_fastopen_synack() to enter TCP_CA_Loss for failed TFO ionic: use dev_consume_skb_any outside of napi net: dsa: microchip: fix wrong register write when masking interrupt Fix race for duplicate reqsk on identical SYN ibmvnic: Add tx check to prevent skb leak ...
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r--net/ipv4/tcp_input.c45
1 files changed, 33 insertions, 12 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 01d208e0eef3..2e39cb881e20 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2782,13 +2782,37 @@ static void tcp_mtup_probe_success(struct sock *sk)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS);
}
+/* Sometimes we deduce that packets have been dropped due to reasons other than
+ * congestion, like path MTU reductions or failed client TFO attempts. In these
+ * cases we call this function to retransmit as many packets as cwnd allows,
+ * without reducing cwnd. Given that retransmits will set retrans_stamp to a
+ * non-zero value (and may do so in a later calling context due to TSQ), we
+ * also enter CA_Loss so that we track when all retransmitted packets are ACKed
+ * and clear retrans_stamp when that happens (to ensure later recurring RTOs
+ * are using the correct retrans_stamp and don't declare ETIMEDOUT
+ * prematurely).
+ */
+static void tcp_non_congestion_loss_retransmit(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (icsk->icsk_ca_state != TCP_CA_Loss) {
+ tp->high_seq = tp->snd_nxt;
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
+ tp->prior_ssthresh = 0;
+ tp->undo_marker = 0;
+ tcp_set_ca_state(sk, TCP_CA_Loss);
+ }
+ tcp_xmit_retransmit_queue(sk);
+}
+
/* Do a simple retransmit without using the backoff mechanisms in
* tcp_timer. This is used for path mtu discovery.
* The socket is already locked here.
*/
void tcp_simple_retransmit(struct sock *sk)
{
- const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int mss;
@@ -2828,14 +2852,7 @@ void tcp_simple_retransmit(struct sock *sk)
* in network, but units changed and effective
* cwnd/ssthresh really reduced now.
*/
- if (icsk->icsk_ca_state != TCP_CA_Loss) {
- tp->high_seq = tp->snd_nxt;
- tp->snd_ssthresh = tcp_current_ssthresh(sk);
- tp->prior_ssthresh = 0;
- tp->undo_marker = 0;
- tcp_set_ca_state(sk, TCP_CA_Loss);
- }
- tcp_xmit_retransmit_queue(sk);
+ tcp_non_congestion_loss_retransmit(sk);
}
EXPORT_SYMBOL(tcp_simple_retransmit);
@@ -6295,8 +6312,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
skb_rbtree_walk_from(data)
tcp_mark_skb_lost(sk, data);
- tcp_xmit_retransmit_queue(sk);
- tp->retrans_stamp = 0;
+ tcp_non_congestion_loss_retransmit(sk);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
return true;
@@ -7257,7 +7273,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->tfo_listener = false;
if (!want_cookie) {
req->timeout = tcp_timeout_init((struct sock *)req);
- inet_csk_reqsk_queue_hash_add(sk, req, req->timeout);
+ if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
+ req->timeout))) {
+ reqsk_free(req);
+ return 0;
+ }
+
}
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :