summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c60
1 files changed, 31 insertions, 29 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b710958393e6..fd17f25ff288 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -93,7 +93,9 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);
-static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
+ .bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
static u32 tcp_v4_init_seq(const struct sk_buff *skb)
{
@@ -114,6 +116,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
const struct inet_timewait_sock *tw = inet_twsk(sktw);
const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
struct tcp_sock *tp = tcp_sk(sk);
+ int ts_recent_stamp;
if (reuse == 2) {
/* Still does not detect *everything* that goes through
@@ -152,10 +155,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
If TW bucket has been already destroyed we fall back to VJ's scheme
and use initial timestamp retrieved from peer table.
*/
- if (tcptw->tw_ts_recent_stamp &&
+ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
+ if (ts_recent_stamp &&
(!twp || (reuse && time_after32(ktime_get_seconds(),
- tcptw->tw_ts_recent_stamp)))) {
- /* inet_twsk_hashdance() sets sk_refcnt after putting twsk
+ ts_recent_stamp)))) {
+ /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk
* and releasing the bucket lock.
*/
if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt)))
@@ -178,8 +182,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
if (!seq)
seq = 1;
WRITE_ONCE(tp->write_seq, seq);
- tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
- tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ tp->rx_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent);
+ tp->rx_opt.ts_recent_stamp = ts_recent_stamp;
}
return 1;
@@ -611,15 +615,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th);
- if (!sock_owned_by_user(sk)) {
- WRITE_ONCE(sk->sk_err, err);
-
- sk_error_report(sk);
-
- tcp_done(sk);
- } else {
+ if (!sock_owned_by_user(sk))
+ tcp_done_with_error(sk, err);
+ else
WRITE_ONCE(sk->sk_err_soft, err);
- }
goto out;
}
@@ -885,7 +884,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
arg.tos = ip_hdr(skb)->tos;
arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ctl_sk = this_cpu_read(ipv4_tcp_sk);
+ local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+ ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
+
sock_net_set(ctl_sk, net);
if (sk) {
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
@@ -910,6 +911,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
+ local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
local_bh_enable();
#ifdef CONFIG_TCP_MD5SIG
@@ -1005,7 +1007,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
arg.tos = tos;
arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ctl_sk = this_cpu_read(ipv4_tcp_sk);
+ local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+ ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
sock_net_set(ctl_sk, net);
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
@@ -1020,6 +1023,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
+ local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
local_bh_enable();
}
@@ -1057,19 +1061,17 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
#else
if (0) {
#endif
-#ifdef CONFIG_TCP_MD5SIG
- } else if (static_branch_unlikely(&tcp_md5_needed.key)) {
+ } else if (static_branch_tcp_md5()) {
key.md5_key = tcp_twsk_md5_key(tcptw);
if (key.md5_key)
key.type = TCP_KEY_MD5;
-#endif
}
tcp_v4_send_ack(sk, skb,
tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_tw_tsval(tcptw),
- tcptw->tw_ts_recent,
+ READ_ONCE(tcptw->tw_ts_recent),
tw->tw_bound_dev_if, &key,
tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
tw->tw_tos,
@@ -1131,8 +1133,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
#else
if (0) {
#endif
-#ifdef CONFIG_TCP_MD5SIG
- } else if (static_branch_unlikely(&tcp_md5_needed.key)) {
+ } else if (static_branch_tcp_md5()) {
const union tcp_md5_addr *addr;
int l3index;
@@ -1141,7 +1142,6 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
if (key.md5_key)
key.type = TCP_KEY_MD5;
-#endif
}
tcp_v4_send_ack(sk, skb, seq,
@@ -1939,7 +1939,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
reset:
tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason));
discard:
- kfree_skb_reason(skb, reason);
+ sk_skb_reason_drop(sk, skb, reason);
/* Be careful here. If this function gets more complicated and
* gcc suffers from register pressure on the x86, sk (in %ebx)
* might be destroyed here. This current version compiles correctly,
@@ -2049,8 +2049,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
((TCP_SKB_CB(tail)->tcp_flags ^
TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
- !mptcp_skb_can_collapse(tail, skb) ||
- skb_cmp_decrypted(tail, skb) ||
+ !tcp_skb_can_collapse_rx(tail, skb) ||
thtail->doff != th->doff ||
memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
goto no_coalesce;
@@ -2176,8 +2175,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
int dif = inet_iif(skb);
const struct iphdr *iph;
const struct tcphdr *th;
+ struct sock *sk = NULL;
bool refcounted;
- struct sock *sk;
int ret;
u32 isn;
@@ -2376,7 +2375,7 @@ bad_packet:
discard_it:
SKB_DR_OR(drop_reason, NOT_SPECIFIED);
/* Discard frame. */
- kfree_skb_reason(skb, drop_reason);
+ sk_skb_reason_drop(sk, skb, drop_reason);
return 0;
discard_and_relse:
@@ -3506,6 +3505,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_shrink_window = 0;
net->ipv4.sysctl_tcp_pingpong_thresh = 1;
+ net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN);
return 0;
}
@@ -3620,7 +3620,9 @@ void __init tcp_v4_init(void)
*/
inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
- per_cpu(ipv4_tcp_sk, cpu) = sk;
+ sk->sk_clockid = CLOCK_MONOTONIC;
+
+ per_cpu(ipv4_tcp_sk.sock, cpu) = sk;
}
if (register_pernet_subsys(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-11-21 13:03:41 +0000