summaryrefslogtreecommitdiffstats
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.c135
1 files changed, 107 insertions, 28 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5b027c69cbc5..95738aa0d8a6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -85,6 +85,8 @@
#include <crypto/hash.h>
#include <linux/scatterlist.h>
+#include <trace/events/tcp.h>
+
#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -480,7 +482,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
TCP_TIMEOUT_INIT;
icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
- skb = tcp_write_queue_head(sk);
+ skb = tcp_rtx_queue_head(sk);
BUG_ON(!skb);
tcp_mstamp_refresh(tp);
@@ -701,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
* routing might fail in this case. No choice here, if we choose to force
* input interface, we will misroute in case of asymmetric route.
*/
- if (sk)
+ if (sk) {
arg.bound_dev_if = sk->sk_bound_dev_if;
+ trace_tcp_send_reset(sk, skb);
+ }
BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -844,7 +848,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
@@ -1587,6 +1591,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_filter);
+static void tcp_v4_restore_cb(struct sk_buff *skb)
+{
+ memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4,
+ sizeof(struct inet_skb_parm));
+}
+
+static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
+ const struct tcphdr *th)
+{
+ /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+ * barrier() makes sure compiler wont play fool^Waliasing games.
+ */
+ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+ sizeof(struct inet_skb_parm));
+ barrier();
+
+ TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+ TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+ skb->len - th->doff * 4);
+ TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+ TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+ TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+ TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
+ TCP_SKB_CB(skb)->sacked = 0;
+ TCP_SKB_CB(skb)->has_rxtstamp =
+ skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+}
+
/*
* From tcp_input.c
*/
@@ -1627,24 +1659,6 @@ int tcp_v4_rcv(struct sk_buff *skb)
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
- /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
- * barrier() makes sure compiler wont play fool^Waliasing games.
- */
- memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
- sizeof(struct inet_skb_parm));
- barrier();
-
- TCP_SKB_CB(skb)->seq = ntohl(th->seq);
- TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
- skb->len - th->doff * 4);
- TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
- TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
- TCP_SKB_CB(skb)->tcp_tw_isn = 0;
- TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
- TCP_SKB_CB(skb)->sacked = 0;
- TCP_SKB_CB(skb)->has_rxtstamp =
- skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
-
lookup:
sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
th->dest, sdif, &refcounted);
@@ -1675,14 +1689,19 @@ process:
sock_hold(sk);
refcounted = true;
nsk = NULL;
- if (!tcp_filter(sk, skb))
+ if (!tcp_filter(sk, skb)) {
+ th = (const struct tcphdr *)skb->data;
+ iph = ip_hdr(skb);
+ tcp_v4_fill_cb(skb, iph, th);
nsk = tcp_check_req(sk, skb, req, false);
+ }
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
+ tcp_v4_restore_cb(skb);
} else if (tcp_child_process(sk, nsk, skb)) {
tcp_v4_send_reset(nsk, skb);
goto discard_and_relse;
@@ -1708,6 +1727,7 @@ process:
goto discard_and_relse;
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
+ tcp_v4_fill_cb(skb, iph, th);
skb->dev = NULL;
@@ -1738,6 +1758,8 @@ no_tcp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
+ tcp_v4_fill_cb(skb, iph, th);
+
if (tcp_checksum_complete(skb)) {
csum_error:
__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
@@ -1764,6 +1786,8 @@ do_time_wait:
goto discard_it;
}
+ tcp_v4_fill_cb(skb, iph, th);
+
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
@@ -1780,11 +1804,13 @@ do_time_wait:
if (sk2) {
inet_twsk_deschedule_put(inet_twsk(sk));
sk = sk2;
+ tcp_v4_restore_cb(skb);
refcounted = false;
goto process;
}
- /* Fall through to ACK */
}
+ /* to ACK */
+ /* fall through */
case TCP_TW_ACK:
tcp_v4_timewait_ack(sk, skb);
break;
@@ -1864,6 +1890,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ trace_tcp_destroy_sock(sk);
+
tcp_clear_xmit_timers(sk);
tcp_cleanup_congestion_control(sk);
@@ -1883,7 +1911,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
/* Clean up the MD5 key list, if any */
if (tp->md5sig_info) {
tcp_clear_md5_list(sk);
- kfree_rcu(tp->md5sig_info, rcu);
+ kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu);
tp->md5sig_info = NULL;
}
#endif
@@ -1896,6 +1924,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
/* If socket is aborted during connect operation */
tcp_free_fastopen_req(tp);
+ tcp_fastopen_destroy_cipher(sk);
tcp_saved_syn_free(tp);
sk_sockets_allocated_dec(sk);
@@ -2252,7 +2281,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
timer_expires = jiffies;
}
- state = sk_state_load(sk);
+ state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
rx_queue = sk->sk_ack_backlog;
else
@@ -2329,7 +2358,6 @@ out:
}
static const struct file_operations tcp_afinfo_seq_fops = {
- .owner = THIS_MODULE,
.open = tcp_seq_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -2401,8 +2429,8 @@ struct proto tcp_prot = {
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.sysctl_mem = sysctl_tcp_mem,
- .sysctl_wmem = sysctl_tcp_wmem,
- .sysctl_rmem = sysctl_tcp_rmem,
+ .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
+ .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
@@ -2422,6 +2450,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
{
int cpu;
+ module_put(net->ipv4.tcp_congestion_control->owner);
+
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
free_percpu(net->ipv4.tcp_sk);
@@ -2476,6 +2506,50 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_sack = 1;
net->ipv4.sysctl_tcp_window_scaling = 1;
net->ipv4.sysctl_tcp_timestamps = 1;
+ net->ipv4.sysctl_tcp_early_retrans = 3;
+ net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION;
+ net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */
+ net->ipv4.sysctl_tcp_retrans_collapse = 1;
+ net->ipv4.sysctl_tcp_max_reordering = 300;
+ net->ipv4.sysctl_tcp_dsack = 1;
+ net->ipv4.sysctl_tcp_app_win = 31;
+ net->ipv4.sysctl_tcp_adv_win_scale = 1;
+ net->ipv4.sysctl_tcp_frto = 2;
+ net->ipv4.sysctl_tcp_moderate_rcvbuf = 1;
+ /* This limits the percentage of the congestion window which we
+ * will allow a single TSO frame to consume. Building TSO frames
+ * which are too large can cause TCP streams to be bursty.
+ */
+ net->ipv4.sysctl_tcp_tso_win_divisor = 3;
+ /* Default TSQ limit of four TSO segments */
+ net->ipv4.sysctl_tcp_limit_output_bytes = 262144;
+ /* rfc5961 challenge ack rate limiting */
+ net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
+ net->ipv4.sysctl_tcp_min_tso_segs = 2;
+ net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
+ net->ipv4.sysctl_tcp_autocorking = 1;
+ net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
+ net->ipv4.sysctl_tcp_pacing_ss_ratio = 200;
+ net->ipv4.sysctl_tcp_pacing_ca_ratio = 120;
+ if (net != &init_net) {
+ memcpy(net->ipv4.sysctl_tcp_rmem,
+ init_net.ipv4.sysctl_tcp_rmem,
+ sizeof(init_net.ipv4.sysctl_tcp_rmem));
+ memcpy(net->ipv4.sysctl_tcp_wmem,
+ init_net.ipv4.sysctl_tcp_wmem,
+ sizeof(init_net.ipv4.sysctl_tcp_wmem));
+ }
+ net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
+ spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
+ net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+ atomic_set(&net->ipv4.tfo_active_disable_times, 0);
+
+ /* Reno is always built in */
+ if (!net_eq(net, &init_net) &&
+ try_module_get(init_net.ipv4.tcp_congestion_control->owner))
+ net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control;
+ else
+ net->ipv4.tcp_congestion_control = &tcp_reno;
return 0;
fail:
@@ -2486,7 +2560,12 @@ fail:
static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
+ struct net *net;
+
inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
+ list_for_each_entry(net, net_exit_list, exit_list)
+ tcp_fastopen_ctx_destroy(net);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-07-18 00:14:21 +0200