* 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 = 8;
+int sysctl_tcp_tso_win_divisor = 3;
static inline void update_send_head(struct sock *sk, struct tcp_sock *tp,
struct sk_buff *skb)
/* RFC2861. Reset CWND after idle period longer RTO to "restart window".
* This is the first part of cwnd validation mechanism. */
-static void tcp_cwnd_restart(struct tcp_sock *tp, struct dst_entry *dst)
+static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst)
{
+ struct tcp_sock *tp = tcp_sk(sk);
s32 delta = tcp_time_stamp - tp->lsndtime;
u32 restart_cwnd = tcp_init_cwnd(tp, dst);
u32 cwnd = tp->snd_cwnd;
- tcp_ca_event(tp, CA_EVENT_CWND_RESTART);
+ tcp_ca_event(sk, CA_EVENT_CWND_RESTART);
- tp->snd_ssthresh = tcp_current_ssthresh(tp);
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
restart_cwnd = min(restart_cwnd, cwnd);
- while ((delta -= tp->rto) > 0 && cwnd > restart_cwnd)
+ while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
cwnd >>= 1;
tp->snd_cwnd = max(cwnd, restart_cwnd);
tp->snd_cwnd_stamp = tcp_time_stamp;
static inline void tcp_event_data_sent(struct tcp_sock *tp,
struct sk_buff *skb, struct sock *sk)
{
- u32 now = tcp_time_stamp;
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ const u32 now = tcp_time_stamp;
- if (!tp->packets_out && (s32)(now - tp->lsndtime) > tp->rto)
- tcp_cwnd_restart(tp, __sk_dst_get(sk));
+ if (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)
+ tcp_cwnd_restart(sk, __sk_dst_get(sk));
tp->lsndtime = now;
/* If it is a reply for ato after last received
* packet, enter pingpong mode.
*/
- if ((u32)(now - tp->ack.lrcvtime) < tp->ack.ato)
- tp->ack.pingpong = 1;
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+ icsk->icsk_ack.pingpong = 1;
}
static __inline__ void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
{
- struct tcp_sock *tp = tcp_sk(sk);
-
- tcp_dec_quickack_mode(tp, pkts);
- tcp_clear_xmit_timer(sk, TCP_TIME_DACK);
+ tcp_dec_quickack_mode(sk, pkts);
+ inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
/* Determine a window scaling and initial window to offer.
static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (skb != NULL) {
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
#define SYSCTL_FLAG_SACK 0x4
/* If congestion control is doing timestamping */
- if (tp->ca_ops->rtt_sample)
- do_gettimeofday(&skb->stamp);
+ if (icsk->icsk_ca_ops->rtt_sample)
+ __net_timestamp(skb);
sysctl_flags = 0;
if (tcb->flags & TCPCB_FLAG_SYN) {
}
if (tcp_packets_in_flight(tp) == 0)
- tcp_ca_event(tp, CA_EVENT_TX_START);
+ tcp_ca_event(sk, CA_EVENT_TX_START);
th = (struct tcphdr *) skb_push(skb, tcp_header_size);
skb->h.th = th;
if (err <= 0)
return err;
- tcp_enter_cwr(tp);
+ tcp_enter_cwr(sk);
/* NET_XMIT_CN is special. It does not guarantee,
* that this packet is lost. It tells that device
sk->sk_send_head = skb;
}
-static inline void tcp_tso_set_push(struct sk_buff *skb)
+static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
{
- /* Force push to be on for any TSO frames to workaround
- * problems with busted implementations like Mac OS-X that
- * hold off socket receive wakeups until push is seen.
- */
- if (tcp_skb_pcount(skb) > 1)
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
-}
-
-static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb)
-{
- struct tcp_sock *tp = tcp_sk(sk);
-
- if (skb->len <= tp->mss_cache_std ||
+ if (skb->len <= mss_now ||
!(sk->sk_route_caps & NETIF_F_TSO)) {
/* Avoid the costly divide in the normal
* non-TSO case.
} else {
unsigned int factor;
- factor = skb->len + (tp->mss_cache_std - 1);
- factor /= tp->mss_cache_std;
+ factor = skb->len + (mss_now - 1);
+ factor /= mss_now;
skb_shinfo(skb)->tso_segs = factor;
- skb_shinfo(skb)->tso_size = tp->mss_cache_std;
- }
-}
-
-/* Does SKB fit into the send window? */
-static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, unsigned int cur_mss)
-{
- u32 end_seq = TCP_SKB_CB(skb)->end_seq;
-
- return !after(end_seq, tp->snd_una + tp->snd_wnd);
-}
-
-/* Can at least one segment of SKB be sent right now, according to the
- * congestion window rules? If so, return how many segments are allowed.
- */
-static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *skb)
-{
- u32 in_flight, cwnd;
-
- /* Don't be strict about the congestion window for the final FIN. */
- if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
- return 1;
-
- in_flight = tcp_packets_in_flight(tp);
- cwnd = tp->snd_cwnd;
- if (in_flight < cwnd)
- return (cwnd - in_flight);
-
- return 0;
-}
-
-static inline int tcp_minshall_check(const struct tcp_sock *tp)
-{
- return after(tp->snd_sml,tp->snd_una) &&
- !after(tp->snd_sml, tp->snd_nxt);
-}
-
-/* Return 0, if packet can be sent now without violation Nagle's rules:
- * 1. It is full sized.
- * 2. Or it contains FIN. (already checked by caller)
- * 3. Or TCP_NODELAY was set.
- * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
- * With Minshall's modification: all sent small packets are ACKed.
- */
-
-static inline int tcp_nagle_check(const struct tcp_sock *tp,
- const struct sk_buff *skb,
- unsigned mss_now, int nonagle)
-{
- return (skb->len < mss_now &&
- ((nonagle&TCP_NAGLE_CORK) ||
- (!nonagle &&
- tp->packets_out &&
- tcp_minshall_check(tp))));
-}
-
-/* Return non-zero if the Nagle test allows this packet to be
- * sent now.
- */
-static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
- unsigned int cur_mss, int nonagle)
-{
- /* Nagle rule does not apply to frames, which sit in the middle of the
- * write_queue (they have no chances to get new data).
- *
- * This is implemented in the callers, where they modify the 'nonagle'
- * argument based upon the location of SKB in the send queue.
- */
- if (nonagle & TCP_NAGLE_PUSH)
- return 1;
-
- /* Don't use the nagle rule for urgent data (or for the final FIN). */
- if (tp->urg_mode ||
- (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
- return 1;
-
- if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
- return 1;
-
- return 0;
-}
-
-/* This must be invoked the first time we consider transmitting
- * SKB onto the wire.
- */
-static inline int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb)
-{
- int tso_segs = tcp_skb_pcount(skb);
-
- if (!tso_segs) {
- tcp_set_skb_tso_segs(sk, skb);
- tso_segs = tcp_skb_pcount(skb);
- }
- return tso_segs;
-}
-
-/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
- * should be put on the wire right now. If so, it returns the number of
- * packets allowed by the congestion window.
- */
-static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
- unsigned int cur_mss, int nonagle)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- unsigned int cwnd_quota;
-
- tcp_init_tso_segs(sk, skb);
-
- if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
- return 0;
-
- cwnd_quota = tcp_cwnd_test(tp, skb);
- if (cwnd_quota &&
- !tcp_snd_wnd_test(tp, skb, cur_mss))
- cwnd_quota = 0;
-
- return cwnd_quota;
-}
-
-static inline int tcp_skb_is_last(const struct sock *sk,
- const struct sk_buff *skb)
-{
- return skb->next == (struct sk_buff *)&sk->sk_write_queue;
-}
-
-int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
-{
- struct sk_buff *skb = sk->sk_send_head;
-
- return (skb &&
- tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
- (tcp_skb_is_last(sk, skb) ?
- TCP_NAGLE_PUSH :
- tp->nonagle)));
-}
-
-
-/* Send _single_ skb sitting at the send head. This function requires
- * true push pending frames to setup probe timer etc.
- */
-void tcp_push_one(struct sock *sk, unsigned cur_mss)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = sk->sk_send_head;
-
- if (tcp_snd_test(sk, skb, cur_mss, TCP_NAGLE_PUSH)) {
- /* Send it out now. */
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_tso_set_push(skb);
- if (!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation))) {
- sk->sk_send_head = NULL;
- tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
- tcp_packets_out_inc(sk, tp, skb);
- return;
- }
+ skb_shinfo(skb)->tso_size = mss_now;
}
}
* packet to the list. This won't be called frequently, I hope.
* Remember, these are still headerless SKBs at this point.
*/
-static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len)
+int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
- int nsize;
+ int nsize, old_factor;
u16 flags;
nsize = skb_headlen(skb) - len;
* skbs, which it never sent before. --ANK
*/
TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
- buff->stamp = skb->stamp;
+ buff->tstamp = skb->tstamp;
if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
tp->lost_out -= tcp_skb_pcount(skb);
tp->left_out -= tcp_skb_pcount(skb);
}
- /* Fix up tso_factor for both original and new SKB. */
- tcp_set_skb_tso_segs(sk, skb);
- tcp_set_skb_tso_segs(sk, buff);
+ old_factor = tcp_skb_pcount(skb);
- if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
- tp->lost_out += tcp_skb_pcount(skb);
- tp->left_out += tcp_skb_pcount(skb);
- }
+ /* Fix up tso_factor for both original and new SKB. */
+ tcp_set_skb_tso_segs(sk, skb, mss_now);
+ tcp_set_skb_tso_segs(sk, buff, mss_now);
- if (TCP_SKB_CB(buff)->sacked&TCPCB_LOST) {
- tp->lost_out += tcp_skb_pcount(buff);
- tp->left_out += tcp_skb_pcount(buff);
+ /* If this packet has been sent out already, we must
+ * adjust the various packet counters.
+ */
+ if (after(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) {
+ int diff = old_factor - tcp_skb_pcount(skb) -
+ tcp_skb_pcount(buff);
+
+ tp->packets_out -= diff;
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
+ tp->lost_out -= diff;
+ tp->left_out -= diff;
+ }
+ if (diff > 0) {
+ tp->fackets_out -= diff;
+ if ((int)tp->fackets_out < 0)
+ tp->fackets_out = 0;
+ }
}
/* Link BUFF into the send queue. */
skb_header_release(buff);
- __skb_append(skb, buff);
+ __skb_append(skb, buff, &sk->sk_write_queue);
return 0;
}
* factor and mss.
*/
if (tcp_skb_pcount(skb) > 1)
- tcp_set_skb_tso_segs(sk, skb);
+ tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1));
return 0;
}
/* And store cached results */
tp->pmtu_cookie = pmtu;
- tp->mss_cache = tp->mss_cache_std = mss_now;
+ tp->mss_cache = mss_now;
return mss_now;
}
* cannot be large. However, taking into account rare use of URG, this
* is not a big flaw.
*/
-
-unsigned int tcp_current_mss(struct sock *sk, int large)
+unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
{
struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
- unsigned int do_large, mss_now;
+ u32 mss_now;
+ u16 xmit_size_goal;
+ int doing_tso = 0;
+
+ mss_now = tp->mss_cache;
+
+ if (large_allowed &&
+ (sk->sk_route_caps & NETIF_F_TSO) &&
+ !tp->urg_mode)
+ doing_tso = 1;
- mss_now = tp->mss_cache_std;
if (dst) {
u32 mtu = dst_mtu(dst);
if (mtu != tp->pmtu_cookie)
mss_now = tcp_sync_mss(sk, mtu);
}
- do_large = (large &&
- (sk->sk_route_caps & NETIF_F_TSO) &&
- !tp->urg_mode);
+ if (tp->rx_opt.eff_sacks)
+ mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
+ (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
- if (do_large) {
- unsigned int large_mss, factor, limit;
+ xmit_size_goal = mss_now;
- large_mss = 65535 - tp->af_specific->net_header_len -
+ if (doing_tso) {
+ xmit_size_goal = 65535 -
+ tp->af_specific->net_header_len -
tp->ext_header_len - tp->tcp_header_len;
- if (tp->max_window && large_mss > (tp->max_window>>1))
- large_mss = max((tp->max_window>>1),
- 68U - tp->tcp_header_len);
-
- factor = large_mss / mss_now;
-
- /* Always keep large mss multiple of real mss, but
- * do not exceed 1/tso_win_divisor of the congestion window
- * so we can keep the ACK clock ticking and minimize
- * bursting.
- */
- limit = tp->snd_cwnd;
- if (sysctl_tcp_tso_win_divisor)
- limit /= sysctl_tcp_tso_win_divisor;
- limit = max(1U, limit);
- if (factor > limit)
- factor = limit;
-
- tp->mss_cache = mss_now * factor;
+ if (tp->max_window &&
+ (xmit_size_goal > (tp->max_window >> 1)))
+ xmit_size_goal = max((tp->max_window >> 1),
+ 68U - tp->tcp_header_len);
- mss_now = tp->mss_cache;
+ xmit_size_goal -= (xmit_size_goal % mss_now);
}
+ tp->xmit_size_goal = xmit_size_goal;
- if (tp->rx_opt.eff_sacks)
- mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
- (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
return mss_now;
}
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
- if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= tp->rto)
+ if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
tcp_cwnd_application_limited(sk);
}
}
+static unsigned int tcp_window_allows(struct tcp_sock *tp, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd)
+{
+ u32 window, cwnd_len;
+
+ window = (tp->snd_una + tp->snd_wnd - TCP_SKB_CB(skb)->seq);
+ cwnd_len = mss_now * cwnd;
+ return min(window, cwnd_len);
+}
+
+/* Can at least one segment of SKB be sent right now, according to the
+ * congestion window rules? If so, return how many segments are allowed.
+ */
+static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *skb)
+{
+ u32 in_flight, cwnd;
+
+ /* Don't be strict about the congestion window for the final FIN. */
+ if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
+ return 1;
+
+ in_flight = tcp_packets_in_flight(tp);
+ cwnd = tp->snd_cwnd;
+ if (in_flight < cwnd)
+ return (cwnd - in_flight);
+
+ return 0;
+}
+
+/* This must be invoked the first time we consider transmitting
+ * SKB onto the wire.
+ */
+static inline int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
+{
+ int tso_segs = tcp_skb_pcount(skb);
+
+ if (!tso_segs ||
+ (tso_segs > 1 &&
+ skb_shinfo(skb)->tso_size != mss_now)) {
+ tcp_set_skb_tso_segs(sk, skb, mss_now);
+ tso_segs = tcp_skb_pcount(skb);
+ }
+ return tso_segs;
+}
+
+static inline int tcp_minshall_check(const struct tcp_sock *tp)
+{
+ return after(tp->snd_sml,tp->snd_una) &&
+ !after(tp->snd_sml, tp->snd_nxt);
+}
+
+/* Return 0, if packet can be sent now without violation Nagle's rules:
+ * 1. It is full sized.
+ * 2. Or it contains FIN. (already checked by caller)
+ * 3. Or TCP_NODELAY was set.
+ * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
+ * With Minshall's modification: all sent small packets are ACKed.
+ */
+
+static inline int tcp_nagle_check(const struct tcp_sock *tp,
+ const struct sk_buff *skb,
+ unsigned mss_now, int nonagle)
+{
+ return (skb->len < mss_now &&
+ ((nonagle&TCP_NAGLE_CORK) ||
+ (!nonagle &&
+ tp->packets_out &&
+ tcp_minshall_check(tp))));
+}
+
+/* Return non-zero if the Nagle test allows this packet to be
+ * sent now.
+ */
+static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
+ unsigned int cur_mss, int nonagle)
+{
+ /* Nagle rule does not apply to frames, which sit in the middle of the
+ * write_queue (they have no chances to get new data).
+ *
+ * This is implemented in the callers, where they modify the 'nonagle'
+ * argument based upon the location of SKB in the send queue.
+ */
+ if (nonagle & TCP_NAGLE_PUSH)
+ return 1;
+
+ /* Don't use the nagle rule for urgent data (or for the final FIN). */
+ if (tp->urg_mode ||
+ (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
+ return 1;
+
+ if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
+ return 1;
+
+ return 0;
+}
+
+/* Does at least the first segment of SKB fit into the send window? */
+static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, unsigned int cur_mss)
+{
+ u32 end_seq = TCP_SKB_CB(skb)->end_seq;
+
+ if (skb->len > cur_mss)
+ end_seq = TCP_SKB_CB(skb)->seq + cur_mss;
+
+ return !after(end_seq, tp->snd_una + tp->snd_wnd);
+}
+
+/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
+ * should be put on the wire right now. If so, it returns the number of
+ * packets allowed by the congestion window.
+ */
+static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
+ unsigned int cur_mss, int nonagle)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ unsigned int cwnd_quota;
+
+ tcp_init_tso_segs(sk, skb, cur_mss);
+
+ if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
+ return 0;
+
+ cwnd_quota = tcp_cwnd_test(tp, skb);
+ if (cwnd_quota &&
+ !tcp_snd_wnd_test(tp, skb, cur_mss))
+ cwnd_quota = 0;
+
+ return cwnd_quota;
+}
+
+static inline int tcp_skb_is_last(const struct sock *sk,
+ const struct sk_buff *skb)
+{
+ return skb->next == (struct sk_buff *)&sk->sk_write_queue;
+}
+
+int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
+{
+ struct sk_buff *skb = sk->sk_send_head;
+
+ return (skb &&
+ tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
+ (tcp_skb_is_last(sk, skb) ?
+ TCP_NAGLE_PUSH :
+ tp->nonagle)));
+}
+
+/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
+ * which is put after SKB on the list. It is very much like
+ * tcp_fragment() except that it may make several kinds of assumptions
+ * in order to speed up the splitting operation. In particular, we
+ * know that all the data is in scatter-gather pages, and that the
+ * packet has never been sent out before (and thus is not cloned).
+ */
+static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now)
+{
+ struct sk_buff *buff;
+ int nlen = skb->len - len;
+ u16 flags;
+
+ /* All of a TSO frame must be composed of paged data. */
+ if (skb->len != skb->data_len)
+ return tcp_fragment(sk, skb, len, mss_now);
+
+ buff = sk_stream_alloc_pskb(sk, 0, 0, GFP_ATOMIC);
+ if (unlikely(buff == NULL))
+ return -ENOMEM;
+
+ 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)->end_seq = TCP_SKB_CB(skb)->end_seq;
+ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
+
+ /* PSH and FIN should only be set in the second packet. */
+ flags = TCP_SKB_CB(skb)->flags;
+ TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
+ TCP_SKB_CB(buff)->flags = flags;
+
+ /* 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;
+ skb_split(skb, buff, len);
+
+ /* Fix up tso_factor for both original and new SKB. */
+ tcp_set_skb_tso_segs(sk, skb, mss_now);
+ tcp_set_skb_tso_segs(sk, buff, mss_now);
+
+ /* Link BUFF into the send queue. */
+ skb_header_release(buff);
+ __skb_append(skb, buff, &sk->sk_write_queue);
+
+ return 0;
+}
+
+/* Try to defer sending, if possible, in order to minimize the amount
+ * of TSO splitting we do. View it as a kind of TSO Nagle test.
+ *
+ * This algorithm is from John Heffner.
+ */
+static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ u32 send_win, cong_win, limit, in_flight;
+
+ if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
+ return 0;
+
+ if (icsk->icsk_ca_state != TCP_CA_Open)
+ return 0;
+
+ in_flight = tcp_packets_in_flight(tp);
+
+ BUG_ON(tcp_skb_pcount(skb) <= 1 ||
+ (tp->snd_cwnd <= in_flight));
+
+ send_win = (tp->snd_una + tp->snd_wnd) - TCP_SKB_CB(skb)->seq;
+
+ /* From in_flight test above, we know that cwnd > in_flight. */
+ cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;
+
+ limit = min(send_win, cong_win);
+
+ if (sysctl_tcp_tso_win_divisor) {
+ u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
+
+ /* If at least some fraction of a window is available,
+ * just use it.
+ */
+ chunk /= sysctl_tcp_tso_win_divisor;
+ if (limit >= chunk)
+ return 0;
+ } else {
+ /* Different approach, try not to defer past a single
+ * ACK. Receiver should ACK every other full sized
+ * frame, so if we have space for more than 3 frames
+ * then send now.
+ */
+ if (limit > tcp_max_burst(tp) * tp->mss_cache)
+ return 0;
+ }
+
+ /* Ok, it looks like it is advisable to defer. */
+ return 1;
+}
+
/* This routine writes packets to the network. It advances the
* send_head. This happens as incoming acks open up the remote
* window for us.
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int sent_pkts;
+ unsigned int tso_segs, sent_pkts;
+ int cwnd_quota;
/* If we are closed, the bytes will have to remain here.
* In time closedown will finish, we empty the write queue and all
return 0;
sent_pkts = 0;
- while ((skb = sk->sk_send_head) &&
- tcp_snd_test(sk, skb, mss_now,
- tcp_skb_is_last(sk, skb) ? nonagle :
- TCP_NAGLE_PUSH)) {
- if (skb->len > mss_now) {
- if (tcp_fragment(sk, skb, mss_now))
+ while ((skb = sk->sk_send_head)) {
+ unsigned int limit;
+
+ tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
+ BUG_ON(!tso_segs);
+
+ cwnd_quota = tcp_cwnd_test(tp, skb);
+ if (!cwnd_quota)
+ break;
+
+ if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
+ break;
+
+ if (tso_segs == 1) {
+ if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
+ (tcp_skb_is_last(sk, skb) ?
+ nonagle : TCP_NAGLE_PUSH))))
break;
+ } else {
+ if (tcp_tso_should_defer(sk, tp, skb))
+ break;
+ }
+
+ limit = mss_now;
+ if (tso_segs > 1) {
+ limit = tcp_window_allows(tp, skb,
+ mss_now, cwnd_quota);
+
+ if (skb->len < limit) {
+ unsigned int trim = skb->len % mss_now;
+
+ if (trim)
+ limit = skb->len - trim;
+ }
}
+ if (skb->len > limit &&
+ unlikely(tso_fragment(sk, skb, limit, mss_now)))
+ break;
+
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_tso_set_push(skb);
- if (tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC)))
+
+ if (unlikely(tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC))))
break;
/* Advance the send_head. This one is sent out.
update_send_head(sk, tp, skb);
tcp_minshall_update(tp, mss_now, skb);
- sent_pkts = 1;
+ sent_pkts++;
}
- if (sent_pkts) {
+ if (likely(sent_pkts)) {
tcp_cwnd_validate(sk, tp);
return 0;
}
-
return !tp->packets_out && sk->sk_send_head;
}
}
}
+/* Send _single_ skb sitting at the send head. This function requires
+ * true push pending frames to setup probe timer etc.
+ */
+void tcp_push_one(struct sock *sk, unsigned int mss_now)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb = sk->sk_send_head;
+ unsigned int tso_segs, cwnd_quota;
+
+ BUG_ON(!skb || skb->len < mss_now);
+
+ tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
+ cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);
+
+ if (likely(cwnd_quota)) {
+ unsigned int limit;
+
+ BUG_ON(!tso_segs);
+
+ limit = mss_now;
+ if (tso_segs > 1) {
+ limit = tcp_window_allows(tp, skb,
+ mss_now, cwnd_quota);
+
+ if (skb->len < limit) {
+ unsigned int trim = skb->len % mss_now;
+
+ if (trim)
+ limit = skb->len - trim;
+ }
+ }
+
+ if (skb->len > limit &&
+ unlikely(tso_fragment(sk, skb, limit, mss_now)))
+ return;
+
+ /* Send it out now. */
+ TCP_SKB_CB(skb)->when = tcp_time_stamp;
+
+ if (likely(!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation)))) {
+ update_send_head(sk, tp, skb);
+ tcp_cwnd_validate(sk, tp);
+ return;
+ }
+ }
+}
+
/* This function returns the amount that we can raise the
* usable window based on the following constraints
*
*/
u32 __tcp_select_window(struct sock *sk)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* MSS for the peer's data. Previous verions used mss_clamp
* here. I don't know if the value based on our guesses
* but may be worse for the performance because of rcv_mss
* fluctuations. --SAW 1998/11/1
*/
- int mss = tp->ack.rcv_mss;
+ int mss = icsk->icsk_ack.rcv_mss;
int free_space = tcp_space(sk);
int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk));
int window;
mss = full_space;
if (free_space < full_space/2) {
- tp->ack.quick = 0;
+ icsk->icsk_ack.quick = 0;
if (tcp_memory_pressure)
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U*tp->advmss);
tcp_skb_pcount(next_skb) != 1);
/* Ok. We will be able to collapse the packet. */
- __skb_unlink(next_skb, next_skb->list);
+ __skb_unlink(next_skb, &sk->sk_write_queue);
memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size);
*/
void tcp_simple_retransmit(struct sock *sk)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
unsigned int mss = tcp_current_mss(sk, 0);
* in network, but units changed and effective
* cwnd/ssthresh really reduced now.
*/
- if (tp->ca_state != TCP_CA_Loss) {
+ if (icsk->icsk_ca_state != TCP_CA_Loss) {
tp->high_seq = tp->snd_nxt;
- tp->snd_ssthresh = tcp_current_ssthresh(tp);
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
tp->prior_ssthresh = 0;
tp->undo_marker = 0;
- tcp_set_ca_state(tp, TCP_CA_Loss);
+ tcp_set_ca_state(sk, TCP_CA_Loss);
}
tcp_xmit_retransmit_queue(sk);
}
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
BUG();
-
- if (sk->sk_route_caps & NETIF_F_TSO) {
- sk->sk_route_caps &= ~NETIF_F_TSO;
- sock_set_flag(sk, SOCK_NO_LARGESEND);
- tp->mss_cache = tp->mss_cache_std;
- }
-
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
return -EAGAIN;
if (skb->len > cur_mss) {
- int old_factor = tcp_skb_pcount(skb);
- int new_factor;
-
- if (tcp_fragment(sk, skb, cur_mss))
+ if (tcp_fragment(sk, skb, cur_mss, cur_mss))
return -ENOMEM; /* We'll try again later. */
-
- /* New SKB created, account for it. */
- new_factor = tcp_skb_pcount(skb);
- tp->packets_out -= old_factor - new_factor;
- tp->packets_out += tcp_skb_pcount(skb->next);
}
/* Collapse two adjacent packets if worthwhile and we can. */
* is still in somebody's hands, else make a clone.
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_tso_set_push(skb);
err = tcp_transmit_skb(sk, (skb_cloned(skb) ?
pskb_copy(skb, GFP_ATOMIC):
*/
void tcp_xmit_retransmit_queue(struct sock *sk)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int packet_cnt = tp->lost_out;
if (!(sacked&(TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) {
if (tcp_retransmit_skb(sk, skb))
return;
- if (tp->ca_state != TCP_CA_Loss)
+ if (icsk->icsk_ca_state != TCP_CA_Loss)
NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS);
if (skb ==
skb_peek(&sk->sk_write_queue))
- tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto,
+ TCP_RTO_MAX);
}
packet_cnt -= tcp_skb_pcount(skb);
/* OK, demanded retransmission is finished. */
/* Forward retransmissions are possible only during Recovery. */
- if (tp->ca_state != TCP_CA_Recovery)
+ if (icsk->icsk_ca_state != TCP_CA_Recovery)
return;
/* No forward retransmissions in Reno are possible. */
break;
if (skb == skb_peek(&sk->sk_write_queue))
- tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto,
+ TCP_RTO_MAX);
NET_INC_STATS_BH(LINUX_MIB_TCPFORWARDRETRANS);
}
} else {
/* Socket is locked, keep trying until memory is available. */
for (;;) {
- skb = alloc_skb(MAX_TCP_HEADER, GFP_KERNEL);
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL);
if (skb)
break;
yield();
* was unread data in the receive queue. This behavior is recommended
* by draft-ietf-tcpimpl-prob-03.txt section 3.10. -DaveM
*/
-void tcp_send_active_reset(struct sock *sk, int priority)
+void tcp_send_active_reset(struct sock *sk, unsigned int __nocast priority)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
tp->rcv_wup = 0;
tp->copied_seq = 0;
- tp->rto = TCP_TIMEOUT_INIT;
- tp->retransmits = 0;
+ inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
+ inet_csk(sk)->icsk_retransmits = 0;
tcp_clear_retrans(tp);
}
tcp_connect_init(sk);
- buff = alloc_skb(MAX_TCP_HEADER + 15, sk->sk_allocation);
+ buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
if (unlikely(buff == NULL))
return -ENOBUFS;
TCP_INC_STATS(TCP_MIB_ACTIVEOPENS);
/* Timer for repeating the SYN until an answer. */
- tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
return 0;
}
*/
void tcp_send_delayed_ack(struct sock *sk)
{
- struct tcp_sock *tp = tcp_sk(sk);
- int ato = tp->ack.ato;
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ int ato = icsk->icsk_ack.ato;
unsigned long timeout;
if (ato > TCP_DELACK_MIN) {
+ const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ/2;
- if (tp->ack.pingpong || (tp->ack.pending&TCP_ACK_PUSHED))
+ if (icsk->icsk_ack.pingpong || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED))
max_ato = TCP_DELACK_MAX;
/* Slow path, intersegment interval is "high". */
/* If some rtt estimate is known, use it to bound delayed ack.
- * Do not use tp->rto here, use results of rtt measurements
+ * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements
* directly.
*/
if (tp->srtt) {
timeout = jiffies + ato;
/* Use new timeout only if there wasn't a older one earlier. */
- if (tp->ack.pending&TCP_ACK_TIMER) {
+ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
/* If delack timer was blocked or is about to expire,
* send ACK now.
*/
- if (tp->ack.blocked || time_before_eq(tp->ack.timeout, jiffies+(ato>>2))) {
+ if (icsk->icsk_ack.blocked ||
+ time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
tcp_send_ack(sk);
return;
}
- if (!time_before(timeout, tp->ack.timeout))
- timeout = tp->ack.timeout;
+ if (!time_before(timeout, icsk->icsk_ack.timeout))
+ timeout = icsk->icsk_ack.timeout;
}
- tp->ack.pending |= TCP_ACK_SCHED|TCP_ACK_TIMER;
- tp->ack.timeout = timeout;
- sk_reset_timer(sk, &tp->delack_timer, timeout);
+ icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
+ icsk->icsk_ack.timeout = timeout;
+ sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
}
/* This routine sends an ack and also updates the window. */
*/
buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
if (buff == NULL) {
- tcp_schedule_ack(tp);
- tp->ack.ato = TCP_ATO_MIN;
- tcp_reset_xmit_timer(sk, TCP_TIME_DACK, TCP_DELACK_MAX);
+ inet_csk_schedule_ack(sk);
+ inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+ TCP_DELACK_MAX, TCP_RTO_MAX);
return;
}
skb->len > mss) {
seg_size = min(seg_size, mss);
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
- if (tcp_fragment(sk, skb, seg_size))
+ if (tcp_fragment(sk, skb, seg_size, mss))
return -1;
- /* SWS override triggered forced fragmentation.
- * Disable TSO, the connection is too sick. */
- if (sk->sk_route_caps & NETIF_F_TSO) {
- sock_set_flag(sk, SOCK_NO_LARGESEND);
- sk->sk_route_caps &= ~NETIF_F_TSO;
- tp->mss_cache = tp->mss_cache_std;
- }
} else if (!tcp_skb_pcount(skb))
- tcp_set_skb_tso_segs(sk, skb);
+ tcp_set_skb_tso_segs(sk, skb, mss);
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_tso_set_push(skb);
err = tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC));
if (!err) {
update_send_head(sk, tp, skb);
*/
void tcp_send_probe0(struct sock *sk)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int err;
if (tp->packets_out || !sk->sk_send_head) {
/* Cancel probe timer, if it is not required. */
- tp->probes_out = 0;
- tp->backoff = 0;
+ icsk->icsk_probes_out = 0;
+ icsk->icsk_backoff = 0;
return;
}
if (err <= 0) {
- if (tp->backoff < sysctl_tcp_retries2)
- tp->backoff++;
- tp->probes_out++;
- tcp_reset_xmit_timer (sk, TCP_TIME_PROBE0,
- min(tp->rto << tp->backoff, TCP_RTO_MAX));
+ if (icsk->icsk_backoff < sysctl_tcp_retries2)
+ icsk->icsk_backoff++;
+ icsk->icsk_probes_out++;
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+ min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
+ TCP_RTO_MAX);
} else {
/* If packet was not sent due to local congestion,
- * do not backoff and do not remember probes_out.
+ * do not backoff and do not remember icsk_probes_out.
* Let local senders to fight for local resources.
*
* Use accumulated backoff yet.
*/
- if (!tp->probes_out)
- tp->probes_out=1;
- tcp_reset_xmit_timer (sk, TCP_TIME_PROBE0,
- min(tp->rto << tp->backoff, TCP_RESOURCE_PROBE_INTERVAL));
+ if (!icsk->icsk_probes_out)
+ icsk->icsk_probes_out = 1;
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+ min(icsk->icsk_rto << icsk->icsk_backoff,
+ TCP_RESOURCE_PROBE_INTERVAL),
+ TCP_RTO_MAX);
}
}