aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_minisocks.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_minisocks.c')
-rw-r--r--net/ipv4/tcp_minisocks.c112
1 files changed, 54 insertions, 58 deletions
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b83a49cc381..e68e0d4af6c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -93,13 +93,12 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
const struct tcphdr *th)
{
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
bool paws_reject = false;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
@@ -294,13 +293,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
- struct inet6_timewait_sock *tw6;
- tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
- tw6 = inet6_twsk((struct sock *)tw);
- tw6->tw_v6_daddr = np->daddr;
- tw6->tw_v6_rcv_saddr = np->rcv_saddr;
+ tw->tw_v6_daddr = sk->sk_v6_daddr;
+ tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_tclass = np->tclass;
+ tw->tw_flowlabel = np->flow_label >> 12;
tw->tw_ipv6only = np->ipv6only;
}
#endif
@@ -318,7 +315,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
key = tp->af_specific->md5_lookup(sk, sk);
if (key != NULL) {
tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
- if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL)
+ if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
BUG();
}
} while (0);
@@ -359,14 +356,43 @@ void tcp_twsk_destructor(struct sock *sk)
#ifdef CONFIG_TCP_MD5SIG
struct tcp_timewait_sock *twsk = tcp_twsk(sk);
- if (twsk->tw_md5_key) {
- tcp_free_md5sig_pool();
+ if (twsk->tw_md5_key)
kfree_rcu(twsk->tw_md5_key, rcu);
- }
#endif
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
+void tcp_openreq_init_rwin(struct request_sock *req,
+ struct sock *sk, struct dst_entry *dst)
+{
+ struct inet_request_sock *ireq = inet_rsk(req);
+ struct tcp_sock *tp = tcp_sk(sk);
+ __u8 rcv_wscale;
+ int mss = dst_metric_advmss(dst);
+
+ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
+ mss = tp->rx_opt.user_mss;
+
+ /* Set this up on the first call only */
+ req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+ req->window_clamp = tcp_full_space(sk);
+
+ /* tcp_full_space because it is guaranteed to be the first packet */
+ tcp_select_initial_window(tcp_full_space(sk),
+ mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+ &req->rcv_wnd,
+ &req->window_clamp,
+ ireq->wscale_ok,
+ &rcv_wscale,
+ dst_metric(dst, RTAX_INITRWND));
+ ireq->rcv_wscale = rcv_wscale;
+}
+EXPORT_SYMBOL(tcp_openreq_init_rwin);
+
static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
struct request_sock *req)
{
@@ -388,32 +414,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
struct tcp_sock *newtp = tcp_sk(newsk);
- struct tcp_sock *oldtp = tcp_sk(sk);
- struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
-
- /* TCP Cookie Transactions require space for the cookie pair,
- * as it differs for each connection. There is no need to
- * copy any s_data_payload stored at the original socket.
- * Failure will prevent resuming the connection.
- *
- * Presumed copied, in order of appearance:
- * cookie_in_always, cookie_out_never
- */
- if (oldcvp != NULL) {
- struct tcp_cookie_values *newcvp =
- kzalloc(sizeof(*newtp->cookie_values),
- GFP_ATOMIC);
-
- if (newcvp != NULL) {
- kref_init(&newcvp->kref);
- newcvp->cookie_desired =
- oldcvp->cookie_desired;
- newtp->cookie_values = newcvp;
- } else {
- /* Not Yet Implemented */
- newtp->cookie_values = NULL;
- }
- }
/* Now setup tcp_sock */
newtp->pred_flags = 0;
@@ -422,16 +422,15 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una =
- newtp->snd_nxt = newtp->snd_up =
- treq->snt_isn + 1 + tcp_s_data_size(oldtp);
+ newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
INIT_LIST_HEAD(&newtp->tsq_node);
tcp_init_wl(newtp, treq->rcv_isn);
- newtp->srtt = 0;
- newtp->mdev = TCP_TIMEOUT_INIT;
+ newtp->srtt_us = 0;
+ newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
newtp->packets_out = 0;
@@ -440,6 +439,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->fackets_out = 0;
newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tcp_enable_early_retrans(newtp);
+ newtp->tlp_high_seq = 0;
+ newtp->lsndtime = treq->snt_synack;
+ 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
@@ -449,18 +451,14 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->snd_cwnd = TCP_INIT_CWND;
newtp->snd_cwnd_cnt = 0;
- newtp->frto_counter = 0;
- newtp->frto_highmark = 0;
-
if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
!try_module_get(newicsk->icsk_ca_ops->owner))
newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
- skb_queue_head_init(&newtp->out_of_order_queue);
- newtp->write_seq = newtp->pushed_seq =
- treq->snt_isn + 1 + tcp_s_data_size(oldtp);
+ __skb_queue_head_init(&newtp->out_of_order_queue);
+ newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
newtp->rx_opt.saw_tstamp = 0;
@@ -537,7 +535,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
bool fastopen)
{
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct sock *child;
const struct tcphdr *th = tcp_hdr(skb);
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
@@ -547,7 +544,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
@@ -583,8 +580,13 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
*
* Note that even if there is new data in the SYN packet
* they will be thrown away too.
+ *
+ * Reset timer after retransmitting SYNACK, similar to
+ * the idea of fast retransmit in recovery.
*/
- inet_rtx_syn_ack(sk, req);
+ if (!inet_rtx_syn_ack(sk, req))
+ req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout,
+ TCP_RTO_MAX) + jiffies;
return NULL;
}
@@ -647,7 +649,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
*/
if ((flg & TCP_FLAG_ACK) && !fastopen &&
(TCP_SKB_CB(skb)->ack_seq !=
- tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk))))
+ tcp_rsk(req)->snt_isn + 1))
return sk;
/* Also, it would be not so bad idea to check rcv_tsecr, which
@@ -695,12 +697,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!(flg & TCP_FLAG_ACK))
return NULL;
- /* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */
- if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr)
- tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr;
- else if (req->num_retrans) /* don't take RTT sample if retrans && ~TS */
- tcp_rsk(req)->snt_synack = 0;
-
/* For Fast Open no more processing is needed (sk is the
* child socket).
*/
@@ -780,7 +776,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
skb->len);
/* Wakeup parent, send SIGIO */
if (state == TCP_SYN_RECV && child->sk_state != state)
- parent->sk_data_ready(parent, 0);
+ parent->sk_data_ready(parent);
} else {
/* Alas, it is possible again, because we do lookup
* in main socket hash table and lock on listening
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 02:26:30 +0000