#include <linux/smp_lock.h>
/* People can turn this off for buggy TCP's found in printers etc. */
-int sysctl_tcp_retrans_collapse = 1;
+int sysctl_tcp_retrans_collapse __read_mostly = 1;
/* People can turn this on to work with those rare, broken TCPs that
* interpret the window field as a signed quantity.
*/
-int sysctl_tcp_workaround_signed_windows = 0;
+int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
/* 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.
*/
-int sysctl_tcp_tso_win_divisor = 3;
+int sysctl_tcp_tso_win_divisor __read_mostly = 3;
-int sysctl_tcp_mtu_probing = 0;
-int sysctl_tcp_base_mss = 512;
+int sysctl_tcp_mtu_probing __read_mostly = 0;
+int sysctl_tcp_base_mss __read_mostly = 512;
/* By default, RFC2861 behavior. */
-int sysctl_tcp_slow_start_after_idle = 1;
+int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
static void update_send_head(struct sock *sk, struct tcp_sock *tp,
struct sk_buff *skb)
* See RFC1323 for an explanation of the limit to 14
*/
space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+ space = min_t(u32, space, *window_clamp);
while (space > 65535 && (*rcv_wscale) < 14) {
space >>= 1;
(*rcv_wscale)++;
return new_win;
}
-static void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp,
+static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp,
__u32 tstamp)
{
if (tp->rx_opt.tstamp_ok) {
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) |
- TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp);
*ptr++ = htonl(tp->rx_opt.ts_recent);
}
* MAX_SYN_SIZE to match the new maximum number of options that you
* can generate.
*/
-static void tcp_syn_build_options(__u32 *ptr, int mss, int ts, int sack,
+static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack,
int offer_wscale, int wscale, __u32 tstamp,
__u32 ts_recent)
{
*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
if (ts) {
if(sack)
- *ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
+ (TCPOLEN_SACK_PERM << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
else
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp); /* TSVAL */
*ptr++ = htonl(ts_recent); /* TSECR */
} else if(sack)
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_SACK_PERM << 8) |
+ TCPOLEN_SACK_PERM);
if (offer_wscale)
- *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale));
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_WINDOW << 16) |
+ (TCPOLEN_WINDOW << 8) |
+ (wscale));
}
/* This routine actually transmits TCP packets queued in by
th->dest = inet->dport;
th->seq = htonl(tcb->seq);
th->ack_seq = htonl(tp->rcv_nxt);
- *(((__u16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
+ *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->flags);
if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
}
if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
- tcp_syn_build_options((__u32 *)(th + 1),
+ tcp_syn_build_options((__be32 *)(th + 1),
tcp_advertise_mss(sk),
(sysctl_flags & SYSCTL_FLAG_TSTAMPS),
(sysctl_flags & SYSCTL_FLAG_SACK),
tcb->when,
tp->rx_opt.ts_recent);
} else {
- tcp_build_and_update_options((__u32 *)(th + 1),
+ tcp_build_and_update_options((__be32 *)(th + 1),
tp, tcb->when);
TCP_ECN_send(sk, tp, skb, tcp_header_size);
}
if (skb->len != tcp_header_size)
tcp_event_data_sent(tp, skb, sk);
- TCP_INC_STATS(TCP_MIB_OUTSEGS);
+ if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
+ TCP_INC_STATS(TCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
if (likely(err <= 0))
TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
TCP_SKB_CB(skb)->sacked &= ~TCPCB_AT_TAIL;
- if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_HW) {
+ if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) {
/* Copy and checksum data tail into the new buffer. */
buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize),
nsize, 0);
skb->csum = csum_block_sub(skb->csum, buff->csum, len);
} else {
- skb->ip_summed = CHECKSUM_HW;
+ skb->ip_summed = CHECKSUM_PARTIAL;
skb_split(skb, buff, len);
}
__pskb_trim_head(skb, len - skb_headlen(skb));
TCP_SKB_CB(skb)->seq += len;
- skb->ip_summed = CHECKSUM_HW;
+ skb->ip_summed = CHECKSUM_PARTIAL;
skb->truesize -= len;
sk->sk_wmem_queued -= len;
/* This packet was never sent out yet, so no SACK bits. */
TCP_SKB_CB(buff)->sacked = 0;
- buff->ip_summed = skb->ip_summed = CHECKSUM_HW;
+ buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL;
skb_split(skb, buff, len);
/* Fix up tso_factor for both original and new SKB. */
u32 send_win, cong_win, limit, in_flight;
if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
- return 0;
+ goto send_now;
if (icsk->icsk_ca_state != TCP_CA_Open)
- return 0;
+ goto send_now;
+
+ /* Defer for less than two clock ticks. */
+ if (!tp->tso_deferred && ((jiffies<<1)>>1) - (tp->tso_deferred>>1) > 1)
+ goto send_now;
in_flight = tcp_packets_in_flight(tp);
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= 65536)
- return 0;
+ goto send_now;
if (sysctl_tcp_tso_win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
*/
chunk /= sysctl_tcp_tso_win_divisor;
if (limit >= chunk)
- return 0;
+ goto send_now;
} else {
/* Different approach, try not to defer past a single
* ACK. Receiver should ACK every other full sized
* then send now.
*/
if (limit > tcp_max_burst(tp) * tp->mss_cache)
- return 0;
+ goto send_now;
}
/* Ok, it looks like it is advisable to defer. */
+ tp->tso_deferred = 1 | (jiffies<<1);
+
return 1;
+
+send_now:
+ tp->tso_deferred = 0;
+ return 0;
}
/* Create a new MTU probe if we are ready.
TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK;
TCP_SKB_CB(nskb)->sacked = 0;
nskb->csum = 0;
- if (skb->ip_summed == CHECKSUM_HW)
- nskb->ip_summed = CHECKSUM_HW;
+ nskb->ip_summed = skb->ip_summed;
len = 0;
while (len < probe_size) {
~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
if (!skb_shinfo(skb)->nr_frags) {
skb_pull(skb, copy);
- if (skb->ip_summed != CHECKSUM_HW)
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
skb->csum = csum_partial(skb->data, skb->len, 0);
} else {
__pskb_trim_head(skb, copy);
memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size);
- if (next_skb->ip_summed == CHECKSUM_HW)
- skb->ip_summed = CHECKSUM_HW;
+ skb->ip_summed = next_skb->ip_summed;
- if (skb->ip_summed != CHECKSUM_HW)
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size);
/* Update sequence range on original skb. */
th->window = htons(req->rcv_wnd);
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
+ tcp_syn_build_options((__be32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale,
TCP_SKB_CB(skb)->when,
req->ts_recent);
skb_shinfo(buff)->gso_size = 0;
skb_shinfo(buff)->gso_type = 0;
buff->csum = 0;
+ tp->snd_nxt = tp->write_seq;
TCP_SKB_CB(buff)->seq = tp->write_seq++;
TCP_SKB_CB(buff)->end_seq = tp->write_seq;
- tp->snd_nxt = tp->write_seq;
- tp->pushed_seq = tp->write_seq;
/* Send it off. */
TCP_SKB_CB(buff)->when = tcp_time_stamp;
sk_charge_skb(sk, buff);
tp->packets_out += tcp_skb_pcount(buff);
tcp_transmit_skb(sk, buff, 1, GFP_KERNEL);
+
+ /* We change tp->snd_nxt after the tcp_transmit_skb() call
+ * in order to make this packet get counted in tcpOutSegs.
+ */
+ tp->snd_nxt = tp->write_seq;
+ tp->pushed_seq = tp->write_seq;
TCP_INC_STATS(TCP_MIB_ACTIVEOPENS);
/* Timer for repeating the SYN until an answer. */
projects / powerpc.git / blobdiff