#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
+#include <net/dst.h>
#include <net/tcp.h>
#include <net/inet_common.h>
#include <linux/ipsec.h>
#define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED)
#define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
-#define IsSackFrto() (sysctl_tcp_frto == 0x2)
-
#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))
u32 rto_min = TCP_RTO_MIN;
if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
- rto_min = dst->metrics[RTAX_RTO_MIN - 1];
+ rto_min = dst_metric(dst, RTAX_RTO_MIN);
return rto_min;
}
dst->metrics[RTAX_RTTVAR - 1] = m;
else
dst->metrics[RTAX_RTTVAR-1] -=
- (dst->metrics[RTAX_RTTVAR-1] - m)>>2;
+ (dst_metric(dst, RTAX_RTTVAR) - m)>>2;
}
if (tp->snd_ssthresh >= 0xFFFF) {
dst->metrics[RTAX_SSTHRESH-1] =
max(tp->snd_cwnd >> 1, tp->snd_ssthresh);
if (!dst_metric_locked(dst, RTAX_CWND))
- dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_cwnd) >> 1;
+ dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_cwnd) >> 1;
} else {
/* Else slow start did not finish, cwnd is non-sense,
ssthresh may be also invalid.
*/
if (!dst_metric_locked(dst, RTAX_CWND))
- dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_ssthresh) >> 1;
- if (dst->metrics[RTAX_SSTHRESH-1] &&
+ dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_ssthresh) >> 1;
+ if (dst_metric(dst, RTAX_SSTHRESH) &&
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
- tp->snd_ssthresh > dst->metrics[RTAX_SSTHRESH-1])
+ tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh;
}
if (!dst_metric_locked(dst, RTAX_REORDERING)) {
- if (dst->metrics[RTAX_REORDERING-1] < tp->reordering &&
+ if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
tp->reordering != sysctl_tcp_reordering)
dst->metrics[RTAX_REORDERING-1] = tp->reordering;
}
struct tcp_sack_block_wire *sp, int num_sacks,
u32 prior_snd_una)
{
- u32 start_seq_0 = ntohl(get_unaligned(&sp[0].start_seq));
- u32 end_seq_0 = ntohl(get_unaligned(&sp[0].end_seq));
+ u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq);
+ u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq);
int dup_sack = 0;
if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
tcp_dsack_seen(tp);
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
} else if (num_sacks > 1) {
- u32 end_seq_1 = ntohl(get_unaligned(&sp[1].end_seq));
- u32 start_seq_1 = ntohl(get_unaligned(&sp[1].start_seq));
+ u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq);
+ u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq);
if (!after(end_seq_0, end_seq_1) &&
!before(start_seq_0, start_seq_1)) {
for (i = 0; i < num_sacks; i++) {
int dup_sack = !i && found_dup_sack;
- sp[used_sacks].start_seq = ntohl(get_unaligned(&sp_wire[i].start_seq));
- sp[used_sacks].end_seq = ntohl(get_unaligned(&sp_wire[i].end_seq));
+ sp[used_sacks].start_seq = get_unaligned_be32(&sp_wire[i].start_seq);
+ sp[used_sacks].end_seq = get_unaligned_be32(&sp_wire[i].end_seq);
if (!tcp_is_sackblock_valid(tp, dup_sack,
sp[used_sacks].start_seq,
tp->sacked_out = 0;
}
+static int tcp_is_sackfrto(const struct tcp_sock *tp)
+{
+ return (sysctl_tcp_frto == 0x2) && !tcp_is_reno(tp);
+}
+
/* F-RTO can only be used if TCP has never retransmitted anything other than
* head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
*/
if (icsk->icsk_mtup.probe_size)
return 0;
- if (IsSackFrto())
+ if (tcp_is_sackfrto(tp))
return 1;
/* Avoid expensive walking of rexmit queue if possible */
/* Earlier loss recovery underway (see RFC4138; Appendix B).
* The last condition is necessary at least in tp->frto_counter case.
*/
- if (IsSackFrto() && (tp->frto_counter ||
+ if (tcp_is_sackfrto(tp) && (tp->frto_counter ||
((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
after(tp->high_seq, tp->snd_una)) {
tp->frto_highmark = tp->high_seq;
{
return !tp->retrans_stamp ||
(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
- (__s32)(tp->rx_opt.rcv_tsecr - tp->retrans_stamp) < 0);
+ before(tp->rx_opt.rcv_tsecr, tp->retrans_stamp));
}
/* Undo procedures. */
struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
- printk(KERN_DEBUG "Undo %s %u.%u.%u.%u/%u c%u l%u ss%u/%u p%u\n",
- msg,
- NIPQUAD(inet->daddr), ntohs(inet->dport),
- tp->snd_cwnd, tcp_left_out(tp),
- tp->snd_ssthresh, tp->prior_ssthresh,
- tp->packets_out);
+ if (sk->sk_family == AF_INET) {
+ printk(KERN_DEBUG "Undo %s " NIPQUAD_FMT "/%u c%u l%u ss%u/%u p%u\n",
+ msg,
+ NIPQUAD(inet->daddr), ntohs(inet->dport),
+ tp->snd_cwnd, tcp_left_out(tp),
+ tp->snd_ssthresh, tp->prior_ssthresh,
+ tp->packets_out);
+ }
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ else if (sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ printk(KERN_DEBUG "Undo %s " NIP6_FMT "/%u c%u l%u ss%u/%u p%u\n",
+ msg,
+ NIP6(np->daddr), ntohs(inet->dport),
+ tp->snd_cwnd, tcp_left_out(tp),
+ tp->snd_ssthresh, tp->prior_ssthresh,
+ tp->packets_out);
+ }
+#endif
}
#else
#define DBGUNDO(x...) do { } while (0)
tcp_verify_left_out(tp);
- if (tp->retrans_out == 0)
+ if (!tp->frto_counter && tp->retrans_out == 0)
tp->retrans_stamp = 0;
if (flag & FLAG_ECE)
return 1;
}
- if (!IsSackFrto() || tcp_is_reno(tp)) {
+ if (!tcp_is_sackfrto(tp)) {
/* RFC4138 shortcoming in step 2; should also have case c):
* ACK isn't duplicate nor advances window, e.g., opposite dir
* data, winupdate
switch (opcode) {
case TCPOPT_MSS:
if (opsize == TCPOLEN_MSS && th->syn && !estab) {
- u16 in_mss = ntohs(get_unaligned((__be16 *)ptr));
+ u16 in_mss = get_unaligned_be16(ptr);
if (in_mss) {
if (opt_rx->user_mss &&
opt_rx->user_mss < in_mss)
((estab && opt_rx->tstamp_ok) ||
(!estab && sysctl_tcp_timestamps))) {
opt_rx->saw_tstamp = 1;
- opt_rx->rcv_tsval = ntohl(get_unaligned((__be32 *)ptr));
- opt_rx->rcv_tsecr = ntohl(get_unaligned((__be32 *)(ptr+4)));
+ opt_rx->rcv_tsval = get_unaligned_be32(ptr);
+ opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
}
break;
case TCPOPT_SACK_PERM:
* cases we should never reach this piece of code.
*/
printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
- __FUNCTION__, sk->sk_state);
+ __func__, sk->sk_state);
break;
}
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (seq == TCP_SKB_CB(skb1)->end_seq) {
- __skb_append(skb1, skb, &tp->out_of_order_queue);
+ __skb_queue_after(&tp->out_of_order_queue, skb1, skb);
if (!tp->rx_opt.num_sacks ||
tp->selective_acks[0].end_seq != seq)
}
}
+static int tcp_defer_accept_check(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->defer_tcp_accept.request) {
+ int queued_data = tp->rcv_nxt - tp->copied_seq;
+ int hasfin = !skb_queue_empty(&sk->sk_receive_queue) ?
+ tcp_hdr((struct sk_buff *)
+ sk->sk_receive_queue.prev)->fin : 0;
+
+ if (queued_data && hasfin)
+ queued_data--;
+
+ if (queued_data &&
+ tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) {
+ if (sock_flag(sk, SOCK_KEEPOPEN)) {
+ inet_csk_reset_keepalive_timer(sk,
+ keepalive_time_when(tp));
+ } else {
+ inet_csk_delete_keepalive_timer(sk);
+ }
+
+ inet_csk_reqsk_queue_add(
+ tp->defer_tcp_accept.listen_sk,
+ tp->defer_tcp_accept.request,
+ sk);
+
+ tp->defer_tcp_accept.listen_sk->sk_data_ready(
+ tp->defer_tcp_accept.listen_sk, 0);
+
+ sock_put(tp->defer_tcp_accept.listen_sk);
+ sock_put(sk);
+ tp->defer_tcp_accept.listen_sk = NULL;
+ tp->defer_tcp_accept.request = NULL;
+ } else if (hasfin ||
+ tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) {
+ tcp_reset(sk);
+ return -1;
+ }
+ }
+ return 0;
+}
+
static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
{
struct tcp_sock *tp = tcp_sk(sk);
tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
+
+ tcp_defer_accept_check(sk);
return 0;
csum_error:
EXPORT_SYMBOL(sysctl_tcp_ecn);
EXPORT_SYMBOL(sysctl_tcp_reordering);
+EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
EXPORT_SYMBOL(tcp_parse_options);
EXPORT_SYMBOL(tcp_rcv_established);
EXPORT_SYMBOL(tcp_rcv_state_process);
projects / linux-2.6-omap-h63xx.git / blobdiff