From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/net/ipv4/tcp_minisocks.c | 106 +++++++++++++++++++++++++---------------------------
1 files changed, 51 insertions(+), 55 deletions(-)
diff --git a/kernel/net/ipv4/tcp_minisocks.c b/kernel/net/ipv4/tcp_minisocks.c
index a20b393..01e2762 100644
--- a/kernel/net/ipv4/tcp_minisocks.c
+++ b/kernel/net/ipv4/tcp_minisocks.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
@@ -179,7 +180,7 @@
* Oh well... nobody has a sufficient solution to this
* protocol bug yet.
*/
- if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) {
+ if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) {
kill:
inet_twsk_deschedule_put(tw);
return TCP_TW_SUCCESS;
@@ -265,6 +266,7 @@
tw->tw_transparent = inet->transparent;
tw->tw_mark = sk->sk_mark;
+ tw->tw_priority = sk->sk_priority;
tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale;
tcptw->tw_rcv_nxt = tp->rcv_nxt;
tcptw->tw_snd_nxt = tp->snd_nxt;
@@ -273,7 +275,7 @@
tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
tcptw->tw_ts_offset = tp->tsoffset;
tcptw->tw_last_oow_ack_time = 0;
-
+ tcptw->tw_tx_delay = tp->tcp_tx_delay;
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -282,6 +284,7 @@
tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_tclass = np->tclass;
tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
+ tw->tw_txhash = sk->sk_txhash;
tw->tw_ipv6only = sk->sk_ipv6only;
}
#endif
@@ -294,12 +297,15 @@
* so the timewait ack generating code has the key.
*/
do {
- struct tcp_md5sig_key *key;
tcptw->tw_md5_key = NULL;
- key = tp->af_specific->md5_lookup(sk, sk);
- if (key) {
- tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
- BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
+ if (static_branch_unlikely(&tcp_md5_needed)) {
+ struct tcp_md5sig_key *key;
+
+ key = tp->af_specific->md5_lookup(sk, sk);
+ if (key) {
+ tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
+ BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
+ }
}
} while (0);
#endif
@@ -338,10 +344,12 @@
void tcp_twsk_destructor(struct sock *sk)
{
#ifdef CONFIG_TCP_MD5SIG
- struct tcp_timewait_sock *twsk = tcp_twsk(sk);
+ if (static_branch_unlikely(&tcp_md5_needed)) {
+ struct tcp_timewait_sock *twsk = tcp_twsk(sk);
- if (twsk->tw_md5_key)
- kfree_rcu(twsk->tw_md5_key, rcu);
+ if (twsk->tw_md5_key)
+ kfree_rcu(twsk->tw_md5_key, rcu);
+ }
#endif
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
@@ -406,7 +414,7 @@
rcu_read_lock();
ca = tcp_ca_find_key(ca_key);
- if (likely(ca && try_module_get(ca->owner))) {
+ if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
icsk->icsk_ca_ops = ca;
ca_got_dst = true;
@@ -417,7 +425,7 @@
/* If no valid choice made yet, assign current system default ca. */
if (!ca_got_dst &&
(!icsk->icsk_ca_setsockopt ||
- !try_module_get(icsk->icsk_ca_ops->owner)))
+ !bpf_try_module_get(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner)))
tcp_assign_congestion_control(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
@@ -474,50 +482,25 @@
WRITE_ONCE(newtp->rcv_nxt, seq);
newtp->segs_in = 1;
- newtp->snd_sml = newtp->snd_una =
- newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
+ seq = treq->snt_isn + 1;
+ newtp->snd_sml = newtp->snd_una = seq;
+ WRITE_ONCE(newtp->snd_nxt, seq);
+ newtp->snd_up = seq;
INIT_LIST_HEAD(&newtp->tsq_node);
INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
tcp_init_wl(newtp, treq->rcv_isn);
- newtp->srtt_us = 0;
- newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U);
- newicsk->icsk_rto = TCP_TIMEOUT_INIT;
newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
- newtp->packets_out = 0;
- newtp->retrans_out = 0;
- newtp->sacked_out = 0;
- newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
- newtp->tlp_high_seq = 0;
newtp->lsndtime = tcp_jiffies32;
newsk->sk_txhash = treq->txhash;
- newtp->last_oow_ack_time = 0;
newtp->total_retrans = req->num_retrans;
-
- /* So many TCP implementations out there (incorrectly) count the
- * initial SYN frame in their delayed-ACK and congestion control
- * algorithms that we must have the following bandaid to talk
- * efficiently to them. -DaveM
- */
- newtp->snd_cwnd = TCP_INIT_CWND;
- newtp->snd_cwnd_cnt = 0;
-
- /* There's a bubble in the pipe until at least the first ACK. */
- newtp->app_limited = ~0U;
tcp_init_xmit_timers(newsk);
WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
-
- newtp->rx_opt.saw_tstamp = 0;
-
- newtp->rx_opt.dsack = 0;
- newtp->rx_opt.num_sacks = 0;
-
- newtp->urg_data = 0;
if (sock_flag(newsk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(newsk,
@@ -540,17 +523,22 @@
newtp->max_window = newtp->snd_wnd;
if (newtp->rx_opt.tstamp_ok) {
- newtp->rx_opt.ts_recent = req->ts_recent;
+ newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent);
newtp->rx_opt.ts_recent_stamp = ktime_get_seconds();
newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
} else {
newtp->rx_opt.ts_recent_stamp = 0;
newtp->tcp_header_len = sizeof(struct tcphdr);
}
+ if (req->num_timeout) {
+ newtp->undo_marker = treq->snt_isn;
+ newtp->retrans_stamp = div_u64(treq->snt_synack,
+ USEC_PER_SEC / TCP_TS_HZ);
+ }
newtp->tsoffset = treq->ts_off;
#ifdef CONFIG_TCP_MD5SIG
newtp->md5sig_info = NULL; /*XXX*/
- if (newtp->af_specific->md5_lookup(sk, newsk))
+ if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req)))
newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
@@ -558,14 +546,9 @@
newtp->rx_opt.mss_clamp = req->mss;
tcp_ecn_openreq_child(newtp, req);
newtp->fastopen_req = NULL;
- newtp->fastopen_rsk = NULL;
- newtp->syn_data_acked = 0;
- newtp->rack.mstamp = 0;
- newtp->rack.advanced = 0;
- newtp->rack.reo_wnd_steps = 1;
- newtp->rack.last_delivered = 0;
- newtp->rack.reo_wnd_persist = 0;
- newtp->rack.dsack_seen = 0;
+ RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
+
+ tcp_bpf_clone(sk, newsk);
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
@@ -582,6 +565,9 @@
* validation and inside tcp_v4_reqsk_send_ack(). Can we do better?
*
* We don't need to initialize tmp_opt.sack_ok as we don't use the results
+ *
+ * Note: If @fastopen is true, this can be called from process context.
+ * Otherwise, this is from BH context.
*/
struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
@@ -600,7 +586,7 @@
tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
- tmp_opt.ts_recent = req->ts_recent;
+ tmp_opt.ts_recent = READ_ONCE(req->ts_recent);
if (tmp_opt.rcv_tsecr)
tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off;
/* We do not store true stamp, but it is not required,
@@ -734,14 +720,17 @@
&tcp_rsk(req)->last_oow_ack_time))
req->rsk_ops->send_ack(sk, skb, req);
if (paws_reject)
- __NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
return NULL;
}
/* In sequence, PAWS is OK. */
+ /* TODO: We probably should defer ts_recent change once
+ * we take ownership of @req.
+ */
if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
- req->ts_recent = tmp_opt.rcv_tsval;
+ WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
/* Truncate SYN, it is out of window starting
@@ -753,7 +742,7 @@
* "fourth, check the SYN bit"
*/
if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) {
- __TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
goto embryonic_reset;
}
@@ -790,6 +779,12 @@
req, &own_req);
if (!child)
goto listen_overflow;
+
+ if (own_req && rsk_drop_req(req)) {
+ reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ return child;
+ }
sock_rps_save_rxhash(child, skb);
tcp_synack_rtt_meas(child, req);
@@ -839,6 +834,7 @@
int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb)
+ __releases(&((child)->sk_lock.slock))
{
int ret = 0;
int state = child->sk_state;
--
Gitblit v1.6.2