#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 __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;
-EXPORT_SYMBOL(sysctl_tcp_mtu_probing);
-EXPORT_SYMBOL(sysctl_tcp_base_mss);
+/* By default, RFC2861 behavior. */
+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)
struct inet_connection_sock *icsk = inet_csk(sk);
const u32 now = tcp_time_stamp;
- if (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)
+ if (sysctl_tcp_slow_start_after_idle &&
+ (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
tcp_cwnd_restart(sk, __sk_dst_get(sk));
tp->lsndtime = now;
space = (space / mss) * mss;
/* NOTE: offering an initial window larger than 32767
- * will break some buggy TCP stacks. We try to be nice.
- * If we are not window scaling, then this truncates
- * our initial window offering to 32k. There should also
- * be a sysctl option to stop being nice.
+ * will break some buggy TCP stacks. If the admin tells us
+ * it is likely we could be speaking with such a buggy stack
+ * we will truncate our initial window offering to 32K-1
+ * unless the remote has sent us a window scaling option,
+ * which we interpret as a sign the remote TCP is not
+ * misinterpreting the window field as a signed quantity.
*/
- (*rcv_wnd) = min(space, MAX_TCP_WINDOW);
+ if (sysctl_tcp_workaround_signed_windows)
+ (*rcv_wnd) = min(space, MAX_TCP_WINDOW);
+ else
+ (*rcv_wnd) = space;
+
(*rcv_wscale) = 0;
if (wscale_ok) {
/* Set window scaling on max possible window
* 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)++;
/* Make sure we do not exceed the maximum possible
* scaled window.
*/
- if (!tp->rx_opt.rcv_wscale)
+ if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows)
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
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 (unlikely(err <= 0))
+ if (likely(err <= 0))
return err;
tcp_enter_cwr(sk);
static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
{
- if (skb->len <= mss_now ||
- !(sk->sk_route_caps & NETIF_F_TSO)) {
+ if (skb->len <= mss_now || !sk_can_gso(sk)) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
} else {
unsigned int factor;
factor = skb->len + (mss_now - 1);
factor /= mss_now;
- skb_shinfo(skb)->tso_segs = factor;
- skb_shinfo(skb)->tso_size = mss_now;
+ skb_shinfo(skb)->gso_segs = factor;
+ skb_shinfo(skb)->gso_size = mss_now;
+ skb_shinfo(skb)->gso_type = sk->sk_gso_type;
}
}
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
int nsize, old_factor;
+ int nlen;
u16 flags;
BUG_ON(len > skb->len);
buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC);
if (buff == NULL)
return -ENOMEM; /* We'll just try again later. */
+
sk_charge_skb(sk, buff);
+ nlen = skb->len - len - nsize;
+ buff->truesize += nlen;
+ skb->truesize -= nlen;
/* Correct the sequence numbers. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
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);
}
* eventually). The difference is that pulled data not copied, but
* immediately discarded.
*/
-static unsigned char *__pskb_trim_head(struct sk_buff *skb, int len)
+static void __pskb_trim_head(struct sk_buff *skb, int len)
{
int i, k, eat;
skb->tail = skb->data;
skb->data_len -= len;
skb->len = skb->data_len;
- return skb->tail;
}
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
return -ENOMEM;
- if (len <= skb_headlen(skb)) {
+ /* If len == headlen, we avoid __skb_pull to preserve alignment. */
+ if (unlikely(len < skb_headlen(skb)))
__skb_pull(skb, len);
- } else {
- if (__pskb_trim_head(skb, len-skb_headlen(skb)) == NULL)
- return -ENOMEM;
- }
+ else
+ __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;
mss_now = tp->mss_cache;
- if (large_allowed &&
- (sk->sk_route_caps & NETIF_F_TSO) &&
- !tp->urg_mode)
+ if (large_allowed && sk_can_gso(sk) && !tp->urg_mode)
doing_tso = 1;
if (dst) {
if (!tso_segs ||
(tso_segs > 1 &&
- skb_shinfo(skb)->tso_size != mss_now)) {
+ tcp_skb_mss(skb) != mss_now)) {
tcp_set_skb_tso_segs(sk, skb, mss_now);
tso_segs = tcp_skb_pcount(skb);
}
if (unlikely(buff == NULL))
return -ENOMEM;
- buff->truesize = nlen;
+ sk_charge_skb(sk, buff);
+ buff->truesize += nlen;
skb->truesize -= nlen;
/* Correct the sequence numbers. */
/* 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. */
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. */
tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
if (!pskb_trim(skb, 0)) {
TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
skb->ip_summed = CHECKSUM_NONE;
skb->csum = 0;
}
skb->csum = 0;
TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
TCP_SKB_CB(skb)->sacked = 0;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
TCP_SKB_CB(skb)->seq = tp->write_seq;
skb->csum = 0;
TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
TCP_SKB_CB(skb)->sacked = 0;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
/* Send it off. */
TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
memset(th, 0, sizeof(struct tcphdr));
th->syn = 1;
th->ack = 1;
- if (dst->dev->features&NETIF_F_TSO)
- ireq->ecn_ok = 0;
TCP_ECN_make_synack(req, th);
th->source = inet_sk(sk)->sport;
th->dest = ireq->rmt_port;
TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
TCP_SKB_CB(skb)->sacked = 0;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
th->seq = htonl(TCP_SKB_CB(skb)->seq);
th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN;
TCP_ECN_send_syn(sk, tp, buff);
TCP_SKB_CB(buff)->sacked = 0;
- skb_shinfo(buff)->tso_segs = 1;
- skb_shinfo(buff)->tso_size = 0;
+ skb_shinfo(buff)->gso_segs = 1;
+ 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. */
buff->csum = 0;
TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
TCP_SKB_CB(buff)->sacked = 0;
- skb_shinfo(buff)->tso_segs = 1;
- skb_shinfo(buff)->tso_size = 0;
+ skb_shinfo(buff)->gso_segs = 1;
+ skb_shinfo(buff)->gso_size = 0;
+ skb_shinfo(buff)->gso_type = 0;
/* Send it off, this clears delayed acks for us. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk, tp);
skb->csum = 0;
TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
TCP_SKB_CB(skb)->sacked = urgent;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
/* Use a previous sequence. This should cause the other
* end to send an ack. Don't queue or clone SKB, just
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff