Commit 5b7ed089 authored by Yuchung Cheng's avatar Yuchung Cheng Committed by David S. Miller

tcp: move fastopen functions to tcp_fastopen.c

Move common TFO functions that will be used by both v4 and v6
to tcp_fastopen.c. Create a helper tcp_fastopen_queue_check().
Signed-off-by: default avatarYuchung Cheng <ycheng@google.com>
Signed-off-by: default avatarDaniel Lee <longinus00@gmail.com>
Signed-off-by: default avatarJerry Chu <hkchu@google.com>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 4b9734e5
...@@ -1329,8 +1329,14 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); ...@@ -1329,8 +1329,14 @@ void tcp_free_fastopen_req(struct tcp_sock *tp);
extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
int tcp_fastopen_reset_cipher(void *key, unsigned int len); int tcp_fastopen_reset_cipher(void *key, unsigned int len);
void tcp_fastopen_cookie_gen(__be32 src, __be32 dst, int tcp_fastopen_create_child(struct sock *sk,
struct tcp_fastopen_cookie *foc); struct sk_buff *skb,
struct sk_buff *skb_synack,
struct request_sock *req);
bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
struct tcp_fastopen_cookie *valid_foc);
void tcp_fastopen_init_key_once(bool publish); void tcp_fastopen_init_key_once(bool publish);
#define TCP_FASTOPEN_KEY_LENGTH 16 #define TCP_FASTOPEN_KEY_LENGTH 16
......
...@@ -94,3 +94,193 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst, ...@@ -94,3 +94,193 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
} }
rcu_read_unlock(); rcu_read_unlock();
} }
int tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct sk_buff *skb_synack,
struct request_sock *req)
{
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
const struct inet_request_sock *ireq = inet_rsk(req);
struct sock *child;
int err;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (child == NULL) {
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
kfree_skb(skb_synack);
return -1;
}
err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr, ireq->opt);
err = net_xmit_eval(err);
if (!err)
tcp_rsk(req)->snt_synack = tcp_time_stamp;
/* XXX (TFO) - is it ok to ignore error and continue? */
spin_lock(&queue->fastopenq->lock);
queue->fastopenq->qlen++;
spin_unlock(&queue->fastopenq->lock);
/* Initialize the child socket. Have to fix some values to take
* into account the child is a Fast Open socket and is created
* only out of the bits carried in the SYN packet.
*/
tp = tcp_sk(child);
tp->fastopen_rsk = req;
/* Do a hold on the listner sk so that if the listener is being
* closed, the child that has been accepted can live on and still
* access listen_lock.
*/
sock_hold(sk);
tcp_rsk(req)->listener = sk;
/* RFC1323: The window in SYN & SYN/ACK segments is never
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the SYN table of the parent
* because it's been added to the accept queue directly.
*/
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
/* Add the child socket directly into the accept queue */
inet_csk_reqsk_queue_add(sk, req, child);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
tcp_init_metrics(child);
tcp_init_buffer_space(child);
/* Queue the data carried in the SYN packet. We need to first
* bump skb's refcnt because the caller will attempt to free it.
*
* XXX (TFO) - we honor a zero-payload TFO request for now.
* (Any reason not to?)
*/
if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) {
/* Don't queue the skb if there is no payload in SYN.
* XXX (TFO) - How about SYN+FIN?
*/
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
} else {
skb = skb_get(skb);
skb_dst_drop(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
skb_set_owner_r(skb, child);
__skb_queue_tail(&child->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
tp->syn_data_acked = 1;
}
sk->sk_data_ready(sk);
bh_unlock_sock(child);
sock_put(child);
WARN_ON(req->sk == NULL);
return 0;
}
EXPORT_SYMBOL(tcp_fastopen_create_child);
static bool tcp_fastopen_queue_check(struct sock *sk)
{
struct fastopen_queue *fastopenq;
/* Make sure the listener has enabled fastopen, and we don't
* exceed the max # of pending TFO requests allowed before trying
* to validating the cookie in order to avoid burning CPU cycles
* unnecessarily.
*
* XXX (TFO) - The implication of checking the max_qlen before
* processing a cookie request is that clients can't differentiate
* between qlen overflow causing Fast Open to be disabled
* temporarily vs a server not supporting Fast Open at all.
*/
fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
if (fastopenq == NULL || fastopenq->max_qlen == 0)
return false;
if (fastopenq->qlen >= fastopenq->max_qlen) {
struct request_sock *req1;
spin_lock(&fastopenq->lock);
req1 = fastopenq->rskq_rst_head;
if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
spin_unlock(&fastopenq->lock);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
return false;
}
fastopenq->rskq_rst_head = req1->dl_next;
fastopenq->qlen--;
spin_unlock(&fastopenq->lock);
reqsk_free(req1);
}
return true;
}
bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
struct tcp_fastopen_cookie *valid_foc)
{
bool skip_cookie = false;
if (likely(!fastopen_cookie_present(foc))) {
/* See include/net/tcp.h for the meaning of these knobs */
if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) ||
((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) &&
(TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1)))
skip_cookie = true; /* no cookie to validate */
else
return false;
}
/* A FO option is present; bump the counter. */
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE);
if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 ||
!tcp_fastopen_queue_check(sk))
return false;
if (skip_cookie) {
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
return true;
}
if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, valid_foc);
if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
memcmp(&foc->val[0], &valid_foc->val[0],
TCP_FASTOPEN_COOKIE_SIZE) != 0)
return false;
valid_foc->len = -1;
}
/* Acknowledge the data received from the peer. */
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
return true;
} else if (foc->len == 0) { /* Client requesting a cookie */
tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, valid_foc);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENCOOKIEREQD);
} else {
/* Client sent a cookie with wrong size. Treat it
* the same as invalid and return a valid one.
*/
tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, valid_foc);
}
return false;
}
EXPORT_SYMBOL(tcp_fastopen_check);
...@@ -1260,187 +1260,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { ...@@ -1260,187 +1260,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
}; };
#endif #endif
static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
struct tcp_fastopen_cookie *valid_foc)
{
bool skip_cookie = false;
struct fastopen_queue *fastopenq;
if (likely(!fastopen_cookie_present(foc))) {
/* See include/net/tcp.h for the meaning of these knobs */
if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) ||
((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) &&
(TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1)))
skip_cookie = true; /* no cookie to validate */
else
return false;
}
fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
/* A FO option is present; bump the counter. */
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE);
/* Make sure the listener has enabled fastopen, and we don't
* exceed the max # of pending TFO requests allowed before trying
* to validating the cookie in order to avoid burning CPU cycles
* unnecessarily.
*
* XXX (TFO) - The implication of checking the max_qlen before
* processing a cookie request is that clients can't differentiate
* between qlen overflow causing Fast Open to be disabled
* temporarily vs a server not supporting Fast Open at all.
*/
if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 ||
fastopenq == NULL || fastopenq->max_qlen == 0)
return false;
if (fastopenq->qlen >= fastopenq->max_qlen) {
struct request_sock *req1;
spin_lock(&fastopenq->lock);
req1 = fastopenq->rskq_rst_head;
if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
spin_unlock(&fastopenq->lock);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
/* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/
foc->len = -1;
return false;
}
fastopenq->rskq_rst_head = req1->dl_next;
fastopenq->qlen--;
spin_unlock(&fastopenq->lock);
reqsk_free(req1);
}
if (skip_cookie) {
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
return true;
}
if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, valid_foc);
if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
memcmp(&foc->val[0], &valid_foc->val[0],
TCP_FASTOPEN_COOKIE_SIZE) != 0)
return false;
valid_foc->len = -1;
}
/* Acknowledge the data received from the peer. */
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
return true;
} else if (foc->len == 0) { /* Client requesting a cookie */
tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, valid_foc);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENCOOKIEREQD);
} else {
/* Client sent a cookie with wrong size. Treat it
* the same as invalid and return a valid one.
*/
tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, valid_foc);
}
return false;
}
static int tcp_v4_conn_req_fastopen(struct sock *sk,
struct sk_buff *skb,
struct sk_buff *skb_synack,
struct request_sock *req)
{
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
const struct inet_request_sock *ireq = inet_rsk(req);
struct sock *child;
int err;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (child == NULL) {
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
kfree_skb(skb_synack);
return -1;
}
err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr, ireq->opt);
err = net_xmit_eval(err);
if (!err)
tcp_rsk(req)->snt_synack = tcp_time_stamp;
/* XXX (TFO) - is it ok to ignore error and continue? */
spin_lock(&queue->fastopenq->lock);
queue->fastopenq->qlen++;
spin_unlock(&queue->fastopenq->lock);
/* Initialize the child socket. Have to fix some values to take
* into account the child is a Fast Open socket and is created
* only out of the bits carried in the SYN packet.
*/
tp = tcp_sk(child);
tp->fastopen_rsk = req;
/* Do a hold on the listner sk so that if the listener is being
* closed, the child that has been accepted can live on and still
* access listen_lock.
*/
sock_hold(sk);
tcp_rsk(req)->listener = sk;
/* RFC1323: The window in SYN & SYN/ACK segments is never
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the SYN table of the parent
* because it's been added to the accept queue directly.
*/
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
/* Add the child socket directly into the accept queue */
inet_csk_reqsk_queue_add(sk, req, child);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
tcp_init_metrics(child);
tcp_init_buffer_space(child);
/* Queue the data carried in the SYN packet. We need to first
* bump skb's refcnt because the caller will attempt to free it.
*
* XXX (TFO) - we honor a zero-payload TFO request for now.
* (Any reason not to?)
*/
if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) {
/* Don't queue the skb if there is no payload in SYN.
* XXX (TFO) - How about SYN+FIN?
*/
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
} else {
skb = skb_get(skb);
skb_dst_drop(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
skb_set_owner_r(skb, child);
__skb_queue_tail(&child->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
tp->syn_data_acked = 1;
}
sk->sk_data_ready(sk);
bh_unlock_sock(child);
sock_put(child);
WARN_ON(req->sk == NULL);
return 0;
}
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{ {
struct tcp_options_received tmp_opt; struct tcp_options_received tmp_opt;
...@@ -1599,8 +1418,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ...@@ -1599,8 +1418,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (fastopen_cookie_present(&foc) && foc.len != 0) if (fastopen_cookie_present(&foc) && foc.len != 0)
NET_INC_STATS_BH(sock_net(sk), NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENPASSIVEFAIL); LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
} else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req)) } else if (tcp_fastopen_create_child(sk, skb, skb_synack, req))
goto drop_and_free; goto drop_and_release;
return 0; return 0;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment