* Andi Kleen : Moved open_request checking here
* and process RSTs for open_requests.
* Andi Kleen : Better prune_queue, and other fixes.
- * Andrey Savochkin: Fix RTT measurements in the presnce of
+ * Andrey Savochkin: Fix RTT measurements in the presence of
* timestamps.
* Andrey Savochkin: Check sequence numbers correctly when
* removing SACKs due to in sequence incoming
* Andi Kleen: Make sure we never ack data there is not
* enough room for. Also make this condition
* a fatal error if it might still happen.
- * Andi Kleen: Add tcp_measure_rcv_mss to make
+ * Andi Kleen: Add tcp_measure_rcv_mss to make
* connections with MSS<min(MTU,ann. MSS)
- * work without delayed acks.
+ * work without delayed acks.
* Andi Kleen: Process packets with PSH set in the
* fast path.
* J Hadi Salim: ECN support
* Pasi Sarolahti: F-RTO for dealing with spurious RTOs
*/
-#include <linux/config.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <net/inet_common.h>
#include <linux/ipsec.h>
#include <asm/unaligned.h>
-
-int sysctl_tcp_timestamps = 1;
-int sysctl_tcp_window_scaling = 1;
-int sysctl_tcp_sack = 1;
-int sysctl_tcp_fack = 1;
-int sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH;
-int sysctl_tcp_ecn;
-int sysctl_tcp_dsack = 1;
-int sysctl_tcp_app_win = 31;
-int sysctl_tcp_adv_win_scale = 2;
-
-int sysctl_tcp_stdurg;
-int sysctl_tcp_rfc1337;
-int sysctl_tcp_max_orphans = NR_FILE;
-int sysctl_tcp_frto;
-int sysctl_tcp_nometrics_save;
-
-int sysctl_tcp_moderate_rcvbuf = 1;
+#include <net/netdma.h>
+
+int sysctl_tcp_timestamps __read_mostly = 1;
+int sysctl_tcp_window_scaling __read_mostly = 1;
+int sysctl_tcp_sack __read_mostly = 1;
+int sysctl_tcp_fack __read_mostly = 1;
+int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
+int sysctl_tcp_ecn __read_mostly;
+int sysctl_tcp_dsack __read_mostly = 1;
+int sysctl_tcp_app_win __read_mostly = 31;
+int sysctl_tcp_adv_win_scale __read_mostly = 2;
+
+int sysctl_tcp_stdurg __read_mostly;
+int sysctl_tcp_rfc1337 __read_mostly;
+int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
+int sysctl_tcp_frto __read_mostly = 2;
+int sysctl_tcp_frto_response __read_mostly;
+int sysctl_tcp_nometrics_save __read_mostly;
+
+int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
+int sysctl_tcp_abc __read_mostly;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
#define FLAG_ECE 0x40 /* ECE in this ACK */
#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
+#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
+#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
+#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained DSACK info */
+#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE)
#define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED)
+#define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
-#define IsReno(tp) ((tp)->rx_opt.sack_ok == 0)
-#define IsFack(tp) ((tp)->rx_opt.sack_ok & 2)
-#define IsDSack(tp) ((tp)->rx_opt.sack_ok & 4)
+#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))
-/* Adapt the MSS value used to make delayed ack decision to the
+/* Adapt the MSS value used to make delayed ack decision to the
* real world.
- */
-static inline void tcp_measure_rcv_mss(struct tcp_sock *tp,
- struct sk_buff *skb)
+ */
+static void tcp_measure_rcv_mss(struct sock *sk,
+ const struct sk_buff *skb)
{
- unsigned int len, lss;
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ const unsigned int lss = icsk->icsk_ack.last_seg_size;
+ unsigned int len;
- lss = tp->ack.last_seg_size;
- tp->ack.last_seg_size = 0;
+ icsk->icsk_ack.last_seg_size = 0;
/* skb->len may jitter because of SACKs, even if peer
* sends good full-sized frames.
*/
- len = skb->len;
- if (len >= tp->ack.rcv_mss) {
- tp->ack.rcv_mss = len;
+ len = skb_shinfo(skb)->gso_size ?: skb->len;
+ if (len >= icsk->icsk_ack.rcv_mss) {
+ icsk->icsk_ack.rcv_mss = len;
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
*
* "len" is invariant segment length, including TCP header.
*/
- len += skb->data - skb->h.raw;
+ len += skb->data - skb_transport_header(skb);
if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
/* If PSH is not set, packet should be
* full sized, provided peer TCP is not badly broken.
* to handle super-low mtu links fairly.
*/
(len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
- !(tcp_flag_word(skb->h.th)&TCP_REMNANT))) {
+ !(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) {
/* Subtract also invariant (if peer is RFC compliant),
* tcp header plus fixed timestamp option length.
* Resulting "len" is MSS free of SACK jitter.
*/
- len -= tp->tcp_header_len;
- tp->ack.last_seg_size = len;
+ len -= tcp_sk(sk)->tcp_header_len;
+ icsk->icsk_ack.last_seg_size = len;
if (len == lss) {
- tp->ack.rcv_mss = len;
+ icsk->icsk_ack.rcv_mss = len;
return;
}
}
- tp->ack.pending |= TCP_ACK_PUSHED;
+ if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)
+ icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2;
+ icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
}
}
-static void tcp_incr_quickack(struct tcp_sock *tp)
+static void tcp_incr_quickack(struct sock *sk)
{
- unsigned quickacks = tp->rcv_wnd/(2*tp->ack.rcv_mss);
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ unsigned quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);
if (quickacks==0)
quickacks=2;
- if (quickacks > tp->ack.quick)
- tp->ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
+ if (quickacks > icsk->icsk_ack.quick)
+ icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
}
-void tcp_enter_quickack_mode(struct tcp_sock *tp)
+void tcp_enter_quickack_mode(struct sock *sk)
{
- tcp_incr_quickack(tp);
- tp->ack.pingpong = 0;
- tp->ack.ato = TCP_ATO_MIN;
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ tcp_incr_quickack(sk);
+ icsk->icsk_ack.pingpong = 0;
+ icsk->icsk_ack.ato = TCP_ATO_MIN;
}
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
*/
-static __inline__ int tcp_in_quickack_mode(struct tcp_sock *tp)
+static inline int tcp_in_quickack_mode(const struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong;
+}
+
+static inline void TCP_ECN_queue_cwr(struct tcp_sock *tp)
+{
+ if (tp->ecn_flags&TCP_ECN_OK)
+ tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
+}
+
+static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, struct sk_buff *skb)
+{
+ if (tcp_hdr(skb)->cwr)
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp)
+{
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
{
- return (tp->ack.quick && !tp->ack.pingpong);
+ if (tp->ecn_flags&TCP_ECN_OK) {
+ if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags))
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ /* Funny extension: if ECT is not set on a segment,
+ * it is surely retransmit. It is not in ECN RFC,
+ * but Linux follows this rule. */
+ else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags)))
+ tcp_enter_quickack_mode((struct sock *)tp);
+ }
+}
+
+static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, struct tcphdr *th)
+{
+ if ((tp->ecn_flags&TCP_ECN_OK) && (!th->ece || th->cwr))
+ tp->ecn_flags &= ~TCP_ECN_OK;
+}
+
+static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, struct tcphdr *th)
+{
+ if ((tp->ecn_flags&TCP_ECN_OK) && (!th->ece || !th->cwr))
+ tp->ecn_flags &= ~TCP_ECN_OK;
+}
+
+static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th)
+{
+ if (th->ece && !th->syn && (tp->ecn_flags&TCP_ECN_OK))
+ return 1;
+ return 0;
}
/* Buffer size and advertised window tuning.
* of receiver window. Check #2.
*
* The scheme does not work when sender sends good segments opening
- * window and then starts to feed us spagetti. But it should work
+ * window and then starts to feed us spaghetti. But it should work
* in common situations. Otherwise, we have to rely on queue collapsing.
*/
/* Slow part of check#2. */
-static int __tcp_grow_window(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb)
+static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(skb->truesize)/2;
- int window = tcp_full_space(sk)/2;
+ int window = tcp_win_from_space(sysctl_tcp_rmem[2])/2;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
- return 2*tp->ack.rcv_mss;
+ return 2 * inet_csk(sk)->icsk_ack.rcv_mss;
truesize >>= 1;
window >>= 1;
return 0;
}
-static inline void tcp_grow_window(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb)
+static void tcp_grow_window(struct sock *sk,
+ struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
if (tcp_win_from_space(skb->truesize) <= skb->len)
incr = 2*tp->advmss;
else
- incr = __tcp_grow_window(sk, tp, skb);
+ incr = __tcp_grow_window(sk, skb);
if (incr) {
tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp);
- tp->ack.quick |= 1;
+ inet_csk(sk)->icsk_ack.quick |= 1;
}
}
}
int rcvmem = tp->advmss + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff);
/* Try to select rcvbuf so that 4 mss-sized segments
- * will fit to window and correspoding skbs will fit to our rcvbuf.
+ * will fit to window and corresponding skbs will fit to our rcvbuf.
* (was 3; 4 is minimum to allow fast retransmit to work.)
*/
while (tcp_win_from_space(rcvmem) < tp->advmss)
sk->sk_rcvbuf = min(4 * rcvmem, sysctl_tcp_rmem[2]);
}
-/* 4. Try to fixup all. It is made iimediately after connection enters
+/* 4. Try to fixup all. It is made immediately after connection enters
* established state.
*/
static void tcp_init_buffer_space(struct sock *sk)
}
/* 5. Recalculate window clamp after socket hit its memory bounds. */
-static void tcp_clamp_window(struct sock *sk, struct tcp_sock *tp)
+static void tcp_clamp_window(struct sock *sk)
{
- struct sk_buff *skb;
- unsigned int app_win = tp->rcv_nxt - tp->copied_seq;
- int ofo_win = 0;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
- tp->ack.quick = 0;
+ icsk->icsk_ack.quick = 0;
- skb_queue_walk(&tp->out_of_order_queue, skb) {
- ofo_win += skb->len;
- }
-
- /* If overcommit is due to out of order segments,
- * do not clamp window. Try to expand rcvbuf instead.
- */
- if (ofo_win) {
- if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
- !tcp_memory_pressure &&
- atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0])
- sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
- sysctl_tcp_rmem[2]);
+ if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
+ !tcp_memory_pressure &&
+ atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+ sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
+ sysctl_tcp_rmem[2]);
}
- if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
- app_win += ofo_win;
- if (atomic_read(&sk->sk_rmem_alloc) >= 2 * sk->sk_rcvbuf)
- app_win >>= 1;
- if (app_win > tp->ack.rcv_mss)
- app_win -= tp->ack.rcv_mss;
- app_win = max(app_win, 2U*tp->advmss);
-
- if (!ofo_win)
- tp->window_clamp = min(tp->window_clamp, app_win);
+ if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U*tp->advmss);
- }
+}
+
+
+/* Initialize RCV_MSS value.
+ * RCV_MSS is an our guess about MSS used by the peer.
+ * We haven't any direct information about the MSS.
+ * It's better to underestimate the RCV_MSS rather than overestimate.
+ * Overestimations make us ACKing less frequently than needed.
+ * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
+ */
+void tcp_initialize_rcv_mss(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
+
+ hint = min(hint, tp->rcv_wnd/2);
+ hint = min(hint, TCP_MIN_RCVMSS);
+ hint = max(hint, TCP_MIN_MSS);
+
+ inet_csk(sk)->icsk_ack.rcv_mss = hint;
}
/* Receiver "autotuning" code.
* are stalled on filesystem I/O.
*
* Also, since we are only going for a minimum in the
- * non-timestamp case, we do not smoothe things out
- * else with timestamps disabled convergance takes too
+ * non-timestamp case, we do not smooth things out
+ * else with timestamps disabled convergence takes too
* long.
*/
if (!win_dep) {
} else if (m < new_sample)
new_sample = m << 3;
} else {
- /* No previous mesaure. */
+ /* No previous measure. */
new_sample = m << 3;
}
tp->rcv_rtt_est.time = tcp_time_stamp;
}
-static inline void tcp_rcv_rtt_measure_ts(struct tcp_sock *tp, struct sk_buff *skb)
+static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
if (tp->rx_opt.rcv_tsecr &&
(TCP_SKB_CB(skb)->end_seq -
- TCP_SKB_CB(skb)->seq >= tp->ack.rcv_mss))
+ TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss))
tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0);
}
struct tcp_sock *tp = tcp_sk(sk);
int time;
int space;
-
+
if (tp->rcvq_space.time == 0)
goto new_measure;
-
+
time = tcp_time_stamp - tp->rcvq_space.time;
if (time < (tp->rcv_rtt_est.rtt >> 3) ||
tp->rcv_rtt_est.rtt == 0)
return;
-
+
space = 2 * (tp->copied_seq - tp->rcvq_space.seq);
space = max(tp->rcvq_space.space, space);
tp->rcvq_space.space = space;
- if (sysctl_tcp_moderate_rcvbuf) {
+ if (sysctl_tcp_moderate_rcvbuf &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int new_clamp = space;
/* Receive space grows, normalize in order to
}
}
}
-
+
new_measure:
tp->rcvq_space.seq = tp->copied_seq;
tp->rcvq_space.time = tcp_time_stamp;
* each ACK we send, he increments snd_cwnd and transmits more of his
* queue. -DaveM
*/
-static void tcp_event_data_recv(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
u32 now;
- tcp_schedule_ack(tp);
+ inet_csk_schedule_ack(sk);
- tcp_measure_rcv_mss(tp, skb);
+ tcp_measure_rcv_mss(sk, skb);
tcp_rcv_rtt_measure(tp);
-
+
now = tcp_time_stamp;
- if (!tp->ack.ato) {
+ if (!icsk->icsk_ack.ato) {
/* The _first_ data packet received, initialize
* delayed ACK engine.
*/
- tcp_incr_quickack(tp);
- tp->ack.ato = TCP_ATO_MIN;
+ tcp_incr_quickack(sk);
+ icsk->icsk_ack.ato = TCP_ATO_MIN;
} else {
- int m = now - tp->ack.lrcvtime;
+ int m = now - icsk->icsk_ack.lrcvtime;
if (m <= TCP_ATO_MIN/2) {
/* The fastest case is the first. */
- tp->ack.ato = (tp->ack.ato>>1) + TCP_ATO_MIN/2;
- } else if (m < tp->ack.ato) {
- tp->ack.ato = (tp->ack.ato>>1) + m;
- if (tp->ack.ato > tp->rto)
- tp->ack.ato = tp->rto;
- } else if (m > tp->rto) {
- /* Too long gap. Apparently sender falled to
+ icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2;
+ } else if (m < icsk->icsk_ack.ato) {
+ icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m;
+ if (icsk->icsk_ack.ato > icsk->icsk_rto)
+ icsk->icsk_ack.ato = icsk->icsk_rto;
+ } else if (m > icsk->icsk_rto) {
+ /* Too long gap. Apparently sender failed to
* restart window, so that we send ACKs quickly.
*/
- tcp_incr_quickack(tp);
+ tcp_incr_quickack(sk);
sk_stream_mem_reclaim(sk);
}
}
- tp->ack.lrcvtime = now;
+ icsk->icsk_ack.lrcvtime = now;
TCP_ECN_check_ce(tp, skb);
if (skb->len >= 128)
- tcp_grow_window(sk, tp, skb);
+ tcp_grow_window(sk, skb);
+}
+
+static u32 tcp_rto_min(struct sock *sk)
+{
+ struct dst_entry *dst = __sk_dst_get(sk);
+ u32 rto_min = TCP_RTO_MIN;
+
+ if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
+ rto_min = dst->metrics[RTAX_RTO_MIN-1];
+ return rto_min;
}
/* Called to compute a smoothed rtt estimate. The data fed to this
* To save cycles in the RFC 1323 implementation it was better to break
* it up into three procedures. -- erics
*/
-static void tcp_rtt_estimator(struct tcp_sock *tp, __u32 mrtt, u32 *usrtt)
+static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
{
+ struct tcp_sock *tp = tcp_sk(sk);
long m = mrtt; /* RTT */
/* The following amusing code comes from Jacobson's
* article in SIGCOMM '88. Note that rtt and mdev
* are scaled versions of rtt and mean deviation.
- * This is designed to be as fast as possible
+ * This is designed to be as fast as possible
* m stands for "measurement".
*
* On a 1990 paper the rto value is changed to:
*
* Funny. This algorithm seems to be very broken.
* These formulae increase RTO, when it should be decreased, increase
- * too slowly, when it should be incresed fastly, decrease too fastly
+ * too slowly, when it should be increased quickly, decrease too quickly
* etc. I guess in BSD RTO takes ONE value, so that it is absolutely
* does not matter how to _calculate_ it. Seems, it was trap
* that VJ failed to avoid. 8)
*/
- if(m == 0)
+ if (m == 0)
m = 1;
if (tp->srtt != 0) {
m -= (tp->srtt >> 3); /* m is now error in rtt est */
if (tp->mdev_max < tp->rttvar)
tp->rttvar -= (tp->rttvar-tp->mdev_max)>>2;
tp->rtt_seq = tp->snd_nxt;
- tp->mdev_max = TCP_RTO_MIN;
+ tp->mdev_max = tcp_rto_min(sk);
}
} else {
/* no previous measure. */
tp->srtt = m<<3; /* take the measured time to be rtt */
tp->mdev = m<<1; /* make sure rto = 3*rtt */
- tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN);
+ tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
tp->rtt_seq = tp->snd_nxt;
}
-
- if (tp->ca_ops->rtt_sample)
- tp->ca_ops->rtt_sample(tp, *usrtt);
}
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
-static inline void tcp_set_rto(struct tcp_sock *tp)
+static inline void tcp_set_rto(struct sock *sk)
{
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Old crap is replaced with new one. 8)
*
* More seriously:
* at least by solaris and freebsd. "Erratic ACKs" has _nothing_
* to do with delayed acks, because at cwnd>2 true delack timeout
* is invisible. Actually, Linux-2.4 also generates erratic
- * ACKs in some curcumstances.
+ * ACKs in some circumstances.
*/
- tp->rto = (tp->srtt >> 3) + tp->rttvar;
+ inet_csk(sk)->icsk_rto = (tp->srtt >> 3) + tp->rttvar;
/* 2. Fixups made earlier cannot be right.
* If we do not estimate RTO correctly without them,
* all the algo is pure shit and should be replaced
- * with correct one. It is exaclty, which we pretend to do.
+ * with correct one. It is exactly, which we pretend to do.
*/
}
/* NOTE: clamping at TCP_RTO_MIN is not required, current algo
* guarantees that rto is higher.
*/
-static inline void tcp_bound_rto(struct tcp_sock *tp)
+static inline void tcp_bound_rto(struct sock *sk)
{
- if (tp->rto > TCP_RTO_MAX)
- tp->rto = TCP_RTO_MAX;
+ if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
+ inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
}
/* Save metrics learned by this TCP session.
dst_confirm(dst);
if (dst && (dst->flags&DST_HOST)) {
+ const struct inet_connection_sock *icsk = inet_csk(sk);
int m;
- if (tp->backoff || !tp->srtt) {
+ if (icsk->icsk_backoff || !tp->srtt) {
/* This session failed to estimate rtt. Why?
* Probably, no packets returned in time.
* Reset our results.
tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
dst->metrics[RTAX_CWND-1] = tp->snd_cwnd;
} else if (tp->snd_cwnd > tp->snd_ssthresh &&
- tp->ca_state == TCP_CA_Open) {
+ icsk->icsk_ca_state == TCP_CA_Open) {
/* Cong. avoidance phase, cwnd is reliable. */
if (!dst_metric_locked(dst, RTAX_SSTHRESH))
dst->metrics[RTAX_SSTHRESH-1] =
}
}
-/* Numbers are taken from RFC2414. */
+/* Numbers are taken from RFC3390.
+ *
+ * John Heffner states:
+ *
+ * The RFC specifies a window of no more than 4380 bytes
+ * unless 2*MSS > 4380. Reading the pseudocode in the RFC
+ * is a bit misleading because they use a clamp at 4380 bytes
+ * rather than use a multiplier in the relevant range.
+ */
__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)
{
__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
if (!cwnd) {
- if (tp->mss_cache_std > 1460)
+ if (tp->mss_cache > 1460)
cwnd = 2;
else
- cwnd = (tp->mss_cache_std > 1095) ? 3 : 4;
+ cwnd = (tp->mss_cache > 1095) ? 3 : 4;
}
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
+/* Set slow start threshold and cwnd not falling to slow start */
+void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ tp->prior_ssthresh = 0;
+ tp->bytes_acked = 0;
+ if (icsk->icsk_ca_state < TCP_CA_CWR) {
+ tp->undo_marker = 0;
+ if (set_ssthresh)
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ tp->snd_cwnd = min(tp->snd_cwnd,
+ tcp_packets_in_flight(tp) + 1U);
+ tp->snd_cwnd_cnt = 0;
+ tp->high_seq = tp->snd_nxt;
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ TCP_ECN_queue_cwr(tp);
+
+ tcp_set_ca_state(sk, TCP_CA_CWR);
+ }
+}
+
+/*
+ * Packet counting of FACK is based on in-order assumptions, therefore TCP
+ * disables it when reordering is detected
+ */
+static void tcp_disable_fack(struct tcp_sock *tp)
+{
+ tp->rx_opt.sack_ok &= ~2;
+}
+
+/* Take a notice that peer is sending DSACKs */
+static void tcp_dsack_seen(struct tcp_sock *tp)
+{
+ tp->rx_opt.sack_ok |= 4;
+}
+
/* Initialize metrics on socket. */
static void tcp_init_metrics(struct sock *sk)
}
if (dst_metric(dst, RTAX_REORDERING) &&
tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
- tp->rx_opt.sack_ok &= ~2;
+ tcp_disable_fack(tp);
tp->reordering = dst_metric(dst, RTAX_REORDERING);
}
* to make it more realistic.
*
* A bit of theory. RTT is time passed after "normal" sized packet
- * is sent until it is ACKed. In normal curcumstances sending small
+ * is sent until it is ACKed. In normal circumstances sending small
* packets force peer to delay ACKs and calculation is correct too.
* The algorithm is adaptive and, provided we follow specs, it
* NEVER underestimate RTT. BUT! If peer tries to make some clever
tp->mdev = dst_metric(dst, RTAX_RTTVAR);
tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN);
}
- tcp_set_rto(tp);
- tcp_bound_rto(tp);
- if (tp->rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
+ tcp_set_rto(sk);
+ tcp_bound_rto(sk);
+ if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
goto reset;
tp->snd_cwnd = tcp_init_cwnd(tp, dst);
tp->snd_cwnd_stamp = tcp_time_stamp;
if (!tp->rx_opt.saw_tstamp && tp->srtt) {
tp->srtt = 0;
tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
- tp->rto = TCP_TIMEOUT_INIT;
+ inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
}
}
-static void tcp_update_reordering(struct tcp_sock *tp, int metric, int ts)
+static void tcp_update_reordering(struct sock *sk, const int metric,
+ const int ts)
{
+ struct tcp_sock *tp = tcp_sk(sk);
if (metric > tp->reordering) {
tp->reordering = min(TCP_MAX_REORDERING, metric);
/* This exciting event is worth to be remembered. 8) */
if (ts)
NET_INC_STATS_BH(LINUX_MIB_TCPTSREORDER);
- else if (IsReno(tp))
+ else if (tcp_is_reno(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPRENOREORDER);
- else if (IsFack(tp))
+ else if (tcp_is_fack(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPFACKREORDER);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSACKREORDER);
#if FASTRETRANS_DEBUG > 1
printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n",
- tp->rx_opt.sack_ok, tp->ca_state,
+ tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
tp->reordering,
tp->fackets_out,
tp->sacked_out,
tp->undo_marker ? tp->undo_retrans : 0);
#endif
- /* Disable FACK yet. */
- tp->rx_opt.sack_ok &= ~2;
+ tcp_disable_fack(tp);
}
}
* for retransmitted and already SACKed segment -> reordering..
* Both of these heuristics are not used in Loss state, when we cannot
* account for retransmits accurately.
+ *
+ * SACK block validation.
+ * ----------------------
+ *
+ * SACK block range validation checks that the received SACK block fits to
+ * the expected sequence limits, i.e., it is between SND.UNA and SND.NXT.
+ * Note that SND.UNA is not included to the range though being valid because
+ * it means that the receiver is rather inconsistent with itself (reports
+ * SACK reneging when it should advance SND.UNA).
+ *
+ * Implements also blockage to start_seq wrap-around. Problem lies in the
+ * fact that though start_seq (s) is before end_seq (i.e., not reversed),
+ * there's no guarantee that it will be before snd_nxt (n). The problem
+ * happens when start_seq resides between end_seq wrap (e_w) and snd_nxt
+ * wrap (s_w):
+ *
+ * <- outs wnd -> <- wrapzone ->
+ * u e n u_w e_w s n_w
+ * | | | | | | |
+ * |<------------+------+----- TCP seqno space --------------+---------->|
+ * ...-- <2^31 ->| |<--------...
+ * ...---- >2^31 ------>| |<--------...
+ *
+ * Current code wouldn't be vulnerable but it's better still to discard such
+ * crazy SACK blocks. Doing this check for start_seq alone closes somewhat
+ * similar case (end_seq after snd_nxt wrap) as earlier reversed check in
+ * snd_nxt wrap -> snd_una region will then become "well defined", i.e.,
+ * equal to the ideal case (infinite seqno space without wrap caused issues).
+ *
+ * With D-SACK the lower bound is extended to cover sequence space below
+ * SND.UNA down to undo_marker, which is the last point of interest. Yet
+ * again, DSACK block must not to go across snd_una (for the same reason as
+ * for the normal SACK blocks, explained above). But there all simplicity
+ * ends, TCP might receive valid D-SACKs below that. As long as they reside
+ * fully below undo_marker they do not affect behavior in anyway and can
+ * therefore be safely ignored. In rare cases (which are more or less
+ * theoretical ones), the D-SACK will nicely cross that boundary due to skb
+ * fragmentation and packet reordering past skb's retransmission. To consider
+ * them correctly, the acceptable range must be extended even more though
+ * the exact amount is rather hard to quantify. However, tp->max_window can
+ * be used as an exaggerated estimate.
*/
+static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack,
+ u32 start_seq, u32 end_seq)
+{
+ /* Too far in future, or reversed (interpretation is ambiguous) */
+ if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq))
+ return 0;
+
+ /* Nasty start_seq wrap-around check (see comments above) */
+ if (!before(start_seq, tp->snd_nxt))
+ return 0;
+
+ /* In outstanding window? ...This is valid exit for DSACKs too.
+ * start_seq == snd_una is non-sensical (see comments above)
+ */
+ if (after(start_seq, tp->snd_una))
+ return 1;
+
+ if (!is_dsack || !tp->undo_marker)
+ return 0;
+
+ /* ...Then it's D-SACK, and must reside below snd_una completely */
+ if (!after(end_seq, tp->snd_una))
+ return 0;
+
+ if (!before(start_seq, tp->undo_marker))
+ return 1;
+
+ /* Too old */
+ if (!after(end_seq, tp->undo_marker))
+ return 0;
+
+ /* Undo_marker boundary crossing (overestimates a lot). Known already:
+ * start_seq < undo_marker and end_seq >= undo_marker.
+ */
+ return !before(start_seq, end_seq - tp->max_window);
+}
+
+
+static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
+ 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));
+ int dup_sack = 0;
+
+ if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
+ dup_sack = 1;
+ 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));
+
+ if (!after(end_seq_0, end_seq_1) &&
+ !before(start_seq_0, start_seq_1)) {
+ dup_sack = 1;
+ tcp_dsack_seen(tp);
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
+ }
+ }
+
+ /* D-SACK for already forgotten data... Do dumb counting. */
+ if (dup_sack &&
+ !after(end_seq_0, prior_snd_una) &&
+ after(end_seq_0, tp->undo_marker))
+ tp->undo_retrans--;
+
+ return dup_sack;
+}
+
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- unsigned char *ptr = ack_skb->h.raw + TCP_SKB_CB(ack_skb)->sacked;
- struct tcp_sack_block *sp = (struct tcp_sack_block *)(ptr+2);
+ unsigned char *ptr = (skb_transport_header(ack_skb) +
+ TCP_SKB_CB(ack_skb)->sacked);
+ struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
+ struct sk_buff *cached_skb;
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int reord = tp->packets_out;
int prior_fackets;
u32 lost_retrans = 0;
int flag = 0;
+ int found_dup_sack = 0;
+ int cached_fack_count;
int i;
+ int first_sack_index;
- /* So, SACKs for already sent large segments will be lost.
- * Not good, but alternative is to resegment the queue. */
- 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 (!tp->sacked_out)
+ if (!tp->sacked_out) {
tp->fackets_out = 0;
+ tp->highest_sack = tp->snd_una;
+ }
prior_fackets = tp->fackets_out;
- for (i=0; i<num_sacks; i++, sp++) {
- struct sk_buff *skb;
- __u32 start_seq = ntohl(sp->start_seq);
- __u32 end_seq = ntohl(sp->end_seq);
- int fack_count = 0;
- int dup_sack = 0;
+ found_dup_sack = tcp_check_dsack(tp, ack_skb, sp,
+ num_sacks, prior_snd_una);
+ if (found_dup_sack)
+ flag |= FLAG_DSACKING_ACK;
+
+ /* Eliminate too old ACKs, but take into
+ * account more or less fresh ones, they can
+ * contain valid SACK info.
+ */
+ if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
+ return 0;
+
+ /* SACK fastpath:
+ * if the only SACK change is the increase of the end_seq of
+ * the first block then only apply that SACK block
+ * and use retrans queue hinting otherwise slowpath */
+ flag = 1;
+ for (i = 0; i < num_sacks; i++) {
+ __be32 start_seq = sp[i].start_seq;
+ __be32 end_seq = sp[i].end_seq;
- /* Check for D-SACK. */
if (i == 0) {
- u32 ack = TCP_SKB_CB(ack_skb)->ack_seq;
-
- if (before(start_seq, ack)) {
- dup_sack = 1;
- tp->rx_opt.sack_ok |= 4;
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
- } else if (num_sacks > 1 &&
- !after(end_seq, ntohl(sp[1].end_seq)) &&
- !before(start_seq, ntohl(sp[1].start_seq))) {
- dup_sack = 1;
- tp->rx_opt.sack_ok |= 4;
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
+ if (tp->recv_sack_cache[i].start_seq != start_seq)
+ flag = 0;
+ } else {
+ if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
+ (tp->recv_sack_cache[i].end_seq != end_seq))
+ flag = 0;
+ }
+ tp->recv_sack_cache[i].start_seq = start_seq;
+ tp->recv_sack_cache[i].end_seq = end_seq;
+ }
+ /* Clear the rest of the cache sack blocks so they won't match mistakenly. */
+ for (; i < ARRAY_SIZE(tp->recv_sack_cache); i++) {
+ tp->recv_sack_cache[i].start_seq = 0;
+ tp->recv_sack_cache[i].end_seq = 0;
+ }
+
+ first_sack_index = 0;
+ if (flag)
+ num_sacks = 1;
+ else {
+ int j;
+ tp->fastpath_skb_hint = NULL;
+
+ /* order SACK blocks to allow in order walk of the retrans queue */
+ for (i = num_sacks-1; i > 0; i--) {
+ for (j = 0; j < i; j++){
+ if (after(ntohl(sp[j].start_seq),
+ ntohl(sp[j+1].start_seq))){
+ struct tcp_sack_block_wire tmp;
+
+ tmp = sp[j];
+ sp[j] = sp[j+1];
+ sp[j+1] = tmp;
+
+ /* Track where the first SACK block goes to */
+ if (j == first_sack_index)
+ first_sack_index = j+1;
+ }
+
}
+ }
+ }
- /* D-SACK for already forgotten data...
- * Do dumb counting. */
- if (dup_sack &&
- !after(end_seq, prior_snd_una) &&
- after(end_seq, tp->undo_marker))
- tp->undo_retrans--;
+ /* clear flag as used for different purpose in following code */
+ flag = 0;
- /* Eliminate too old ACKs, but take into
- * account more or less fresh ones, they can
- * contain valid SACK info.
- */
- if (before(ack, prior_snd_una - tp->max_window))
- return 0;
+ /* Use SACK fastpath hint if valid */
+ cached_skb = tp->fastpath_skb_hint;
+ cached_fack_count = tp->fastpath_cnt_hint;
+ if (!cached_skb) {
+ cached_skb = tcp_write_queue_head(sk);
+ cached_fack_count = 0;
+ }
+
+ for (i=0; i<num_sacks; i++, sp++) {
+ struct sk_buff *skb;
+ __u32 start_seq = ntohl(sp->start_seq);
+ __u32 end_seq = ntohl(sp->end_seq);
+ int fack_count;
+ int dup_sack = (found_dup_sack && (i == first_sack_index));
+
+ if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) {
+ if (dup_sack) {
+ if (!tp->undo_marker)
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDNOUNDO);
+ else
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDOLD);
+ } else
+ NET_INC_STATS_BH(LINUX_MIB_TCPSACKDISCARD);
+ continue;
}
+ skb = cached_skb;
+ fack_count = cached_fack_count;
+
/* Event "B" in the comment above. */
if (after(end_seq, tp->high_seq))
flag |= FLAG_DATA_LOST;
- sk_stream_for_retrans_queue(skb, sk) {
- u8 sacked = TCP_SKB_CB(skb)->sacked;
- int in_sack;
+ tcp_for_write_queue_from(skb, sk) {
+ int in_sack, pcount;
+ u8 sacked;
+
+ if (skb == tcp_send_head(sk))
+ break;
+
+ cached_skb = skb;
+ cached_fack_count = fack_count;
+ if (i == first_sack_index) {
+ tp->fastpath_skb_hint = skb;
+ tp->fastpath_cnt_hint = fack_count;
+ }
/* The retransmission queue is always in order, so
* we can short-circuit the walk early.
*/
- if(!before(TCP_SKB_CB(skb)->seq, end_seq))
+ if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
- fack_count += tcp_skb_pcount(skb);
-
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
!before(end_seq, TCP_SKB_CB(skb)->end_seq);
+ pcount = tcp_skb_pcount(skb);
+
+ if (pcount > 1 && !in_sack &&
+ after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
+ unsigned int pkt_len;
+
+ in_sack = !after(start_seq,
+ TCP_SKB_CB(skb)->seq);
+
+ if (!in_sack)
+ pkt_len = (start_seq -
+ TCP_SKB_CB(skb)->seq);
+ else
+ pkt_len = (end_seq -
+ TCP_SKB_CB(skb)->seq);
+ if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
+ break;
+ pcount = tcp_skb_pcount(skb);
+ }
+
+ fack_count += pcount;
+
+ sacked = TCP_SKB_CB(skb)->sacked;
+
/* Account D-SACK for retransmitted packet. */
if ((dup_sack && in_sack) &&
(sacked & TCPCB_RETRANS) &&
TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
tp->lost_out -= tcp_skb_pcount(skb);
tp->retrans_out -= tcp_skb_pcount(skb);
+
+ /* clear lost hint */
+ tp->retransmit_skb_hint = NULL;
}
} else {
/* New sack for not retransmitted frame,
if (sacked & TCPCB_LOST) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
tp->lost_out -= tcp_skb_pcount(skb);
+
+ /* clear lost hint */
+ tp->retransmit_skb_hint = NULL;
+ }
+ /* SACK enhanced F-RTO detection.
+ * Set flag if and only if non-rexmitted
+ * segments below frto_highmark are
+ * SACKed (RFC4138; Appendix B).
+ * Clearing correct due to in-order walk
+ */
+ if (after(end_seq, tp->frto_highmark)) {
+ flag &= ~FLAG_ONLY_ORIG_SACKED;
+ } else {
+ if (!(sacked & TCPCB_RETRANS))
+ flag |= FLAG_ONLY_ORIG_SACKED;
}
}
if (fack_count > tp->fackets_out)
tp->fackets_out = fack_count;
+
+ if (after(TCP_SKB_CB(skb)->seq,
+ tp->highest_sack))
+ tp->highest_sack = TCP_SKB_CB(skb)->seq;
} else {
if (dup_sack && (sacked&TCPCB_RETRANS))
reord = min(fack_count, reord);
(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS)) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
+ tp->retransmit_skb_hint = NULL;
}
}
}
* we have to account for reordering! Ugly,
* but should help.
*/
- if (lost_retrans && tp->ca_state == TCP_CA_Recovery) {
+ if (lost_retrans && icsk->icsk_ca_state == TCP_CA_Recovery) {
struct sk_buff *skb;
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
if (after(TCP_SKB_CB(skb)->seq, lost_retrans))
break;
if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
continue;
if ((TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) &&
after(lost_retrans, TCP_SKB_CB(skb)->ack_seq) &&
- (IsFack(tp) ||
+ (tcp_is_fack(tp) ||
!before(lost_retrans,
TCP_SKB_CB(skb)->ack_seq + tp->reordering *
- tp->mss_cache_std))) {
+ tp->mss_cache))) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
+ /* clear lost hint */
+ tp->retransmit_skb_hint = NULL;
+
if (!(TCP_SKB_CB(skb)->sacked&(TCPCB_LOST|TCPCB_SACKED_ACKED))) {
tp->lost_out += tcp_skb_pcount(skb);
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
}
}
- tp->left_out = tp->sacked_out + tp->lost_out;
+ tcp_verify_left_out(tp);
- if ((reord < tp->fackets_out) && tp->ca_state != TCP_CA_Loss)
- tcp_update_reordering(tp, ((tp->fackets_out + 1) - reord), 0);
+ if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss &&
+ (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
+ tcp_update_reordering(sk, ((tp->fackets_out + 1) - reord), 0);
#if FASTRETRANS_DEBUG > 0
BUG_TRAP((int)tp->sacked_out >= 0);
return flag;
}
-/* RTO occurred, but do not yet enter loss state. Instead, transmit two new
- * segments to see from the next ACKs whether any data was really missing.
- * If the RTO was spurious, new ACKs should arrive.
+/* 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)
*/
-void tcp_enter_frto(struct sock *sk)
+static void tcp_check_reno_reordering(struct sock *sk, const int addend)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 holes;
+
+ holes = max(tp->lost_out, 1U);
+ holes = min(holes, tp->packets_out);
+
+ if ((tp->sacked_out + holes) > tp->packets_out) {
+ tp->sacked_out = tp->packets_out - holes;
+ tcp_update_reordering(sk, tp->packets_out + addend, 0);
+ }
+}
+
+/* Emulate SACKs for SACKless connection: account for a new dupack. */
+
+static void tcp_add_reno_sack(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ tp->sacked_out++;
+ tcp_check_reno_reordering(sk, 0);
+ tcp_verify_left_out(tp);
+}
+
+/* Account for ACK, ACKing some data in Reno Recovery phase. */
+
+static void tcp_remove_reno_sacks(struct sock *sk, int acked)
{
struct tcp_sock *tp = tcp_sk(sk);
+
+ if (acked > 0) {
+ /* One ACK acked hole. The rest eat duplicate ACKs. */
+ if (acked-1 >= tp->sacked_out)
+ tp->sacked_out = 0;
+ else
+ tp->sacked_out -= acked-1;
+ }
+ tcp_check_reno_reordering(sk, acked);
+ tcp_verify_left_out(tp);
+}
+
+static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
+{
+ tp->sacked_out = 0;
+}
+
+int tcp_use_frto(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- tp->frto_counter = 1;
+ if (!sysctl_tcp_frto)
+ return 0;
+
+ if (IsSackFrto())
+ return 1;
- if (tp->ca_state <= TCP_CA_Disorder ||
- tp->snd_una == tp->high_seq ||
- (tp->ca_state == TCP_CA_Loss && !tp->retransmits)) {
- tp->prior_ssthresh = tcp_current_ssthresh(tp);
- tp->snd_ssthresh = tp->ca_ops->ssthresh(tp);
- tcp_ca_event(tp, CA_EVENT_FRTO);
+ /* Avoid expensive walking of rexmit queue if possible */
+ if (tp->retrans_out > 1)
+ return 0;
+
+ skb = tcp_write_queue_head(sk);
+ skb = tcp_write_queue_next(sk, skb); /* Skips head */
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
+ return 0;
+ /* Short-circuit when first non-SACKed skb has been checked */
+ if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED))
+ break;
+ }
+ return 1;
+}
+
+/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO
+ * recovery a bit and use heuristics in tcp_process_frto() to detect if
+ * the RTO was spurious. Only clear SACKED_RETRANS of the head here to
+ * keep retrans_out counting accurate (with SACK F-RTO, other than head
+ * may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS
+ * bits are handled if the Loss state is really to be entered (in
+ * tcp_enter_frto_loss).
+ *
+ * Do like tcp_enter_loss() would; when RTO expires the second time it
+ * does:
+ * "Reduce ssthresh if it has not yet been made inside this window."
+ */
+void tcp_enter_frto(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+
+ if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) ||
+ tp->snd_una == tp->high_seq ||
+ ((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) &&
+ !icsk->icsk_retransmits)) {
+ tp->prior_ssthresh = tcp_current_ssthresh(sk);
+ /* Our state is too optimistic in ssthresh() call because cwnd
+ * is not reduced until tcp_enter_frto_loss() when previous FRTO
+ * recovery has not yet completed. Pattern would be this: RTO,
+ * Cumulative ACK, RTO (2xRTO for the same segment does not end
+ * up here twice).
+ * RFC4138 should be more specific on what to do, even though
+ * RTO is quite unlikely to occur after the first Cumulative ACK
+ * due to back-off and complexity of triggering events ...
+ */
+ if (tp->frto_counter) {
+ u32 stored_cwnd;
+ stored_cwnd = tp->snd_cwnd;
+ tp->snd_cwnd = 2;
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ tp->snd_cwnd = stored_cwnd;
+ } else {
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ }
+ /* ... in theory, cong.control module could do "any tricks" in
+ * ssthresh(), which means that ca_state, lost bits and lost_out
+ * counter would have to be faked before the call occurs. We
+ * consider that too expensive, unlikely and hacky, so modules
+ * using these in ssthresh() must deal these incompatibility
+ * issues if they receives CA_EVENT_FRTO and frto_counter != 0
+ */
+ tcp_ca_event(sk, CA_EVENT_FRTO);
}
- /* Have to clear retransmission markers here to keep the bookkeeping
- * in shape, even though we are not yet in Loss state.
- * If something was really lost, it is eventually caught up
- * in tcp_enter_frto_loss.
- */
- tp->retrans_out = 0;
tp->undo_marker = tp->snd_una;
tp->undo_retrans = 0;
- sk_stream_for_retrans_queue(skb, sk) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_RETRANS;
+ skb = tcp_write_queue_head(sk);
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ tp->undo_marker = 0;
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+ tp->retrans_out -= tcp_skb_pcount(skb);
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
- tcp_set_ca_state(tp, TCP_CA_Open);
- tp->frto_highmark = tp->snd_nxt;
+ /* 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 ||
+ ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
+ after(tp->high_seq, tp->snd_una)) {
+ tp->frto_highmark = tp->high_seq;
+ } else {
+ tp->frto_highmark = tp->snd_nxt;
+ }
+ tcp_set_ca_state(sk, TCP_CA_Disorder);
+ tp->high_seq = tp->snd_nxt;
+ tp->frto_counter = 1;
}
/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO,
* which indicates that we should follow the traditional RTO recovery,
* i.e. mark everything lost and do go-back-N retransmission.
*/
-static void tcp_enter_frto_loss(struct sock *sk)
+static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt = 0;
- tp->sacked_out = 0;
tp->lost_out = 0;
- tp->fackets_out = 0;
-
- sk_stream_for_retrans_queue(skb, sk) {
- cnt += tcp_skb_pcount(skb);
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
+ tp->retrans_out = 0;
+ if (tcp_is_reno(tp))
+ tcp_reset_reno_sack(tp);
- /* Do not mark those segments lost that were
- * forward transmitted after RTO
- */
- if (!after(TCP_SKB_CB(skb)->end_seq,
- tp->frto_highmark)) {
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- }
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ /*
+ * Count the retransmission made on RTO correctly (only when
+ * waiting for the first ACK and did not get it)...
+ */
+ if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) {
+ /* For some reason this R-bit might get cleared? */
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
+ tp->retrans_out += tcp_skb_pcount(skb);
+ /* ...enter this if branch just for the first segment */
+ flag |= FLAG_DATA_ACKED;
} else {
- tp->sacked_out += tcp_skb_pcount(skb);
- tp->fackets_out = cnt;
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ tp->undo_marker = 0;
+ TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
+ }
+
+ /* Don't lost mark skbs that were fwd transmitted after RTO */
+ if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) &&
+ !after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) {
+ TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ tp->lost_out += tcp_skb_pcount(skb);
}
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
- tp->snd_cwnd = tp->frto_counter + tcp_packets_in_flight(tp)+1;
+ tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
- tp->undo_marker = 0;
tp->frto_counter = 0;
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
- tcp_set_ca_state(tp, TCP_CA_Loss);
+ tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->frto_highmark;
TCP_ECN_queue_cwr(tp);
+
+ tcp_clear_retrans_hints_partial(tp);
}
void tcp_clear_retrans(struct tcp_sock *tp)
{
- tp->left_out = 0;
tp->retrans_out = 0;
tp->fackets_out = 0;
*/
void tcp_enter_loss(struct sock *sk, int how)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cnt = 0;
/* Reduce ssthresh if it has not yet been made inside this window. */
- if (tp->ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
- (tp->ca_state == TCP_CA_Loss && !tp->retransmits)) {
- tp->prior_ssthresh = tcp_current_ssthresh(tp);
- tp->snd_ssthresh = tp->ca_ops->ssthresh(tp);
- tcp_ca_event(tp, CA_EVENT_LOSS);
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
+ (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
+ tp->prior_ssthresh = tcp_current_ssthresh(sk);
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ tcp_ca_event(sk, CA_EVENT_LOSS);
}
tp->snd_cwnd = 1;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->bytes_acked = 0;
tcp_clear_retrans(tp);
- /* Push undo marker, if it was plain RTO and nothing
- * was retransmitted. */
- if (!how)
+ if (!how) {
+ /* Push undo marker, if it was plain RTO and nothing
+ * was retransmitted. */
tp->undo_marker = tp->snd_una;
+ tcp_clear_retrans_hints_partial(tp);
+ } else {
+ tcp_clear_all_retrans_hints(tp);
+ }
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
cnt += tcp_skb_pcount(skb);
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
tp->undo_marker = 0;
tp->fackets_out = cnt;
}
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
- tcp_set_ca_state(tp, TCP_CA_Loss);
+ tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
+ /* Abort FRTO algorithm if one is in progress */
+ tp->frto_counter = 0;
}
-static int tcp_check_sack_reneging(struct sock *sk, struct tcp_sock *tp)
+static int tcp_check_sack_reneging(struct sock *sk)
{
struct sk_buff *skb;
* receiver _host_ is heavily congested (or buggy).
* Do processing similar to RTO timeout.
*/
- if ((skb = skb_peek(&sk->sk_write_queue)) != NULL &&
+ if ((skb = tcp_write_queue_head(sk)) != NULL &&
(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
+ struct inet_connection_sock *icsk = inet_csk(sk);
NET_INC_STATS_BH(LINUX_MIB_TCPSACKRENEGING);
tcp_enter_loss(sk, 1);
- tp->retransmits++;
- tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue));
- tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
+ icsk->icsk_retransmits++;
+ tcp_retransmit_skb(sk, tcp_write_queue_head(sk));
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ icsk->icsk_rto, TCP_RTO_MAX);
return 1;
}
return 0;
static inline int tcp_fackets_out(struct tcp_sock *tp)
{
- return IsReno(tp) ? tp->sacked_out+1 : tp->fackets_out;
+ return tcp_is_reno(tp) ? tp->sacked_out+1 : tp->fackets_out;
}
-static inline int tcp_skb_timedout(struct tcp_sock *tp, struct sk_buff *skb)
+static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb)
{
- return (tcp_time_stamp - TCP_SKB_CB(skb)->when > tp->rto);
+ return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
}
-static inline int tcp_head_timedout(struct sock *sk, struct tcp_sock *tp)
+static inline int tcp_head_timedout(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
return tp->packets_out &&
- tcp_skb_timedout(tp, skb_peek(&sk->sk_write_queue));
+ tcp_skb_timedout(sk, tcp_write_queue_head(sk));
}
/* Linux NewReno/SACK/FACK/ECN state machine.
* Main question: may we further continue forward transmission
* with the same cwnd?
*/
-static int tcp_time_to_recover(struct sock *sk, struct tcp_sock *tp)
+static int tcp_time_to_recover(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
+ /* Do not perform any recovery during FRTO algorithm */
+ if (tp->frto_counter)
+ return 0;
+
/* Trick#1: The loss is proven. */
if (tp->lost_out)
return 1;
/* Trick#3 : when we use RFC2988 timer restart, fast
* retransmit can be triggered by timeout of queue head.
*/
- if (tcp_head_timedout(sk, tp))
+ if (tcp_head_timedout(sk))
return 1;
/* Trick#4: It is still not OK... But will it be useful to delay
packets_out = tp->packets_out;
if (packets_out <= tp->reordering &&
tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
- !tcp_may_send_now(sk, tp)) {
+ !tcp_may_send_now(sk)) {
/* We have nothing to send. This connection is limited
* either by receiver window or by application.
*/
return 0;
}
-/* If we receive more dupacks than we expected counting segments
- * in assumption of absent reordering, interpret this as reordering.
- * The only another reason could be bug in receiver TCP.
+/* RFC: This is from the original, I doubt that this is necessary at all:
+ * clear xmit_retrans hint if seq of this skb is beyond hint. How could we
+ * retransmitted past LOST markings in the first place? I'm not fully sure
+ * about undo and end of connection cases, which can cause R without L?
*/
-static void tcp_check_reno_reordering(struct tcp_sock *tp, int addend)
-{
- u32 holes;
-
- holes = max(tp->lost_out, 1U);
- holes = min(holes, tp->packets_out);
-
- if ((tp->sacked_out + holes) > tp->packets_out) {
- tp->sacked_out = tp->packets_out - holes;
- tcp_update_reordering(tp, tp->packets_out+addend, 0);
- }
-}
-
-/* Emulate SACKs for SACKless connection: account for a new dupack. */
-
-static void tcp_add_reno_sack(struct tcp_sock *tp)
-{
- tp->sacked_out++;
- tcp_check_reno_reordering(tp, 0);
- tcp_sync_left_out(tp);
-}
-
-/* Account for ACK, ACKing some data in Reno Recovery phase. */
-
-static void tcp_remove_reno_sacks(struct sock *sk, struct tcp_sock *tp, int acked)
-{
- if (acked > 0) {
- /* One ACK acked hole. The rest eat duplicate ACKs. */
- if (acked-1 >= tp->sacked_out)
- tp->sacked_out = 0;
- else
- tp->sacked_out -= acked-1;
- }
- tcp_check_reno_reordering(tp, acked);
- tcp_sync_left_out(tp);
-}
-
-static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
+static void tcp_verify_retransmit_hint(struct tcp_sock *tp,
+ struct sk_buff *skb)
{
- tp->sacked_out = 0;
- tp->left_out = tp->lost_out;
+ if ((tp->retransmit_skb_hint != NULL) &&
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+ tp->retransmit_skb_hint = NULL;
}
/* Mark head of queue up as lost. */
-static void tcp_mark_head_lost(struct sock *sk, struct tcp_sock *tp,
+static void tcp_mark_head_lost(struct sock *sk,
int packets, u32 high_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt = packets;
+ int cnt;
- BUG_TRAP(cnt <= tp->packets_out);
+ BUG_TRAP(packets <= tp->packets_out);
+ if (tp->lost_skb_hint) {
+ skb = tp->lost_skb_hint;
+ cnt = tp->lost_cnt_hint;
+ } else {
+ skb = tcp_write_queue_head(sk);
+ cnt = 0;
+ }
- sk_stream_for_retrans_queue(skb, sk) {
- cnt -= tcp_skb_pcount(skb);
- if (cnt < 0 || after(TCP_SKB_CB(skb)->end_seq, high_seq))
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ /* TODO: do this better */
+ /* this is not the most efficient way to do this... */
+ tp->lost_skb_hint = skb;
+ tp->lost_cnt_hint = cnt;
+ cnt += tcp_skb_pcount(skb);
+ if (cnt > packets || after(TCP_SKB_CB(skb)->end_seq, high_seq))
break;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
+ tcp_verify_retransmit_hint(tp, skb);
}
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
}
/* Account newly detected lost packet(s) */
-static void tcp_update_scoreboard(struct sock *sk, struct tcp_sock *tp)
+static void tcp_update_scoreboard(struct sock *sk)
{
- if (IsFack(tp)) {
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tcp_is_fack(tp)) {
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, tp, lost, tp->high_seq);
+ tcp_mark_head_lost(sk, lost, tp->high_seq);
} else {
- tcp_mark_head_lost(sk, tp, 1, tp->high_seq);
+ tcp_mark_head_lost(sk, 1, tp->high_seq);
}
/* New heuristics: it is possible only after we switched
* Hence, we can detect timed out packets during fast
* retransmit without falling to slow start.
*/
- if (tcp_head_timedout(sk, tp)) {
+ if (!tcp_is_reno(tp) && tcp_head_timedout(sk)) {
struct sk_buff *skb;
- sk_stream_for_retrans_queue(skb, sk) {
- if (tcp_skb_timedout(tp, skb) &&
- !(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
+ skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
+ : tcp_write_queue_head(sk);
+
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ if (!tcp_skb_timedout(sk, skb))
+ break;
+
+ if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
+ tcp_verify_retransmit_hint(tp, skb);
}
}
- tcp_sync_left_out(tp);
+
+ tp->scoreboard_skb_hint = skb;
+
+ tcp_verify_left_out(tp);
}
}
tp->snd_cwnd_stamp = tcp_time_stamp;
}
+/* Lower bound on congestion window is slow start threshold
+ * unless congestion avoidance choice decides to overide it.
+ */
+static inline u32 tcp_cwnd_min(const struct sock *sk)
+{
+ const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
+
+ return ca_ops->min_cwnd ? ca_ops->min_cwnd(sk) : tcp_sk(sk)->snd_ssthresh;
+}
+
/* Decrease cwnd each second ack. */
-static void tcp_cwnd_down(struct tcp_sock *tp)
+static void tcp_cwnd_down(struct sock *sk, int flag)
{
+ struct tcp_sock *tp = tcp_sk(sk);
int decr = tp->snd_cwnd_cnt + 1;
- tp->snd_cwnd_cnt = decr&1;
- decr >>= 1;
+ if ((flag&(FLAG_ANY_PROGRESS|FLAG_DSACKING_ACK)) ||
+ (tcp_is_reno(tp) && !(flag&FLAG_NOT_DUP))) {
+ tp->snd_cwnd_cnt = decr&1;
+ decr >>= 1;
- if (decr && tp->snd_cwnd > tp->ca_ops->min_cwnd(tp))
- tp->snd_cwnd -= decr;
+ if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
+ tp->snd_cwnd -= decr;
- tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
- tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ }
}
/* Nothing was retransmitted or returned timestamp is less
/* Undo procedures. */
#if FASTRETRANS_DEBUG > 1
-static void DBGUNDO(struct sock *sk, struct tcp_sock *tp, const char *msg)
+static void DBGUNDO(struct sock *sk, const char *msg)
{
+ 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, tp->left_out,
+ tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
}
#define DBGUNDO(x...) do { } while (0)
#endif
-static void tcp_undo_cwr(struct tcp_sock *tp, int undo)
+static void tcp_undo_cwr(struct sock *sk, const int undo)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tp->prior_ssthresh) {
- if (tp->ca_ops->undo_cwnd)
- tp->snd_cwnd = tp->ca_ops->undo_cwnd(tp);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ca_ops->undo_cwnd)
+ tp->snd_cwnd = icsk->icsk_ca_ops->undo_cwnd(sk);
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh<<1);
}
tcp_moderate_cwnd(tp);
tp->snd_cwnd_stamp = tcp_time_stamp;
+
+ /* There is something screwy going on with the retrans hints after
+ an undo */
+ tcp_clear_all_retrans_hints(tp);
}
static inline int tcp_may_undo(struct tcp_sock *tp)
}
/* People celebrate: "We love our President!" */
-static int tcp_try_undo_recovery(struct sock *sk, struct tcp_sock *tp)
+static int tcp_try_undo_recovery(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tcp_may_undo(tp)) {
/* Happy end! We did not retransmit anything
* or our original transmission succeeded.
*/
- DBGUNDO(sk, tp, tp->ca_state == TCP_CA_Loss ? "loss" : "retrans");
- tcp_undo_cwr(tp, 1);
- if (tp->ca_state == TCP_CA_Loss)
+ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
+ tcp_undo_cwr(sk, 1);
+ if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
else
NET_INC_STATS_BH(LINUX_MIB_TCPFULLUNDO);
tp->undo_marker = 0;
}
- if (tp->snd_una == tp->high_seq && IsReno(tp)) {
+ if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
* is ACKed. For Reno it is MUST to prevent false
* fast retransmits (RFC2582). SACK TCP is safe. */
tcp_moderate_cwnd(tp);
return 1;
}
- tcp_set_ca_state(tp, TCP_CA_Open);
+ tcp_set_ca_state(sk, TCP_CA_Open);
return 0;
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
-static void tcp_try_undo_dsack(struct sock *sk, struct tcp_sock *tp)
+static void tcp_try_undo_dsack(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tp->undo_marker && !tp->undo_retrans) {
- DBGUNDO(sk, tp, "D-SACK");
- tcp_undo_cwr(tp, 1);
+ DBGUNDO(sk, "D-SACK");
+ tcp_undo_cwr(sk, 1);
tp->undo_marker = 0;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKUNDO);
}
/* Undo during fast recovery after partial ACK. */
-static int tcp_try_undo_partial(struct sock *sk, struct tcp_sock *tp,
- int acked)
+static int tcp_try_undo_partial(struct sock *sk, int acked)
{
+ struct tcp_sock *tp = tcp_sk(sk);
/* Partial ACK arrived. Force Hoe's retransmit. */
- int failed = IsReno(tp) || tp->fackets_out>tp->reordering;
+ int failed = tcp_is_reno(tp) || tp->fackets_out>tp->reordering;
if (tcp_may_undo(tp)) {
/* Plain luck! Hole if filled with delayed
if (tp->retrans_out == 0)
tp->retrans_stamp = 0;
- tcp_update_reordering(tp, tcp_fackets_out(tp)+acked, 1);
+ tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
- DBGUNDO(sk, tp, "Hoe");
- tcp_undo_cwr(tp, 0);
+ DBGUNDO(sk, "Hoe");
+ tcp_undo_cwr(sk, 0);
NET_INC_STATS_BH(LINUX_MIB_TCPPARTIALUNDO);
/* So... Do not make Hoe's retransmit yet.
}
/* Undo during loss recovery after partial ACK. */
-static int tcp_try_undo_loss(struct sock *sk, struct tcp_sock *tp)
+static int tcp_try_undo_loss(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tcp_may_undo(tp)) {
struct sk_buff *skb;
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
}
- DBGUNDO(sk, tp, "partial loss");
+
+ tcp_clear_all_retrans_hints(tp);
+
+ DBGUNDO(sk, "partial loss");
tp->lost_out = 0;
- tp->left_out = tp->sacked_out;
- tcp_undo_cwr(tp, 1);
+ tcp_undo_cwr(sk, 1);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
- tp->retransmits = 0;
+ inet_csk(sk)->icsk_retransmits = 0;
tp->undo_marker = 0;
- if (!IsReno(tp))
- tcp_set_ca_state(tp, TCP_CA_Open);
+ if (tcp_is_sack(tp))
+ tcp_set_ca_state(sk, TCP_CA_Open);
return 1;
}
return 0;
}
-static inline void tcp_complete_cwr(struct tcp_sock *tp)
+static inline void tcp_complete_cwr(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_stamp = tcp_time_stamp;
- tcp_ca_event(tp, CA_EVENT_COMPLETE_CWR);
+ tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
-static void tcp_try_to_open(struct sock *sk, struct tcp_sock *tp, int flag)
+static void tcp_try_to_open(struct sock *sk, int flag)
{
- tp->left_out = tp->sacked_out;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ tcp_verify_left_out(tp);
if (tp->retrans_out == 0)
tp->retrans_stamp = 0;
if (flag&FLAG_ECE)
- tcp_enter_cwr(tp);
+ tcp_enter_cwr(sk, 1);
- if (tp->ca_state != TCP_CA_CWR) {
+ if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
int state = TCP_CA_Open;
- if (tp->left_out || tp->retrans_out || tp->undo_marker)
+ if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
state = TCP_CA_Disorder;
- if (tp->ca_state != state) {
- tcp_set_ca_state(tp, state);
+ if (inet_csk(sk)->icsk_ca_state != state) {
+ tcp_set_ca_state(sk, state);
tp->high_seq = tp->snd_nxt;
}
tcp_moderate_cwnd(tp);
} else {
- tcp_cwnd_down(tp);
+ tcp_cwnd_down(sk, flag);
}
}
+static void tcp_mtup_probe_failed(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1;
+ icsk->icsk_mtup.probe_size = 0;
+}
+
+static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ /* FIXME: breaks with very large cwnd */
+ tp->prior_ssthresh = tcp_current_ssthresh(sk);
+ tp->snd_cwnd = tp->snd_cwnd *
+ tcp_mss_to_mtu(sk, tp->mss_cache) /
+ icsk->icsk_mtup.probe_size;
+ tp->snd_cwnd_cnt = 0;
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->rcv_ssthresh = tcp_current_ssthresh(sk);
+
+ icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size;
+ icsk->icsk_mtup.probe_size = 0;
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+}
+
+
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
* tcp_xmit_retransmit_queue().
*/
static void
-tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
- int prior_packets, int flag)
+tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int is_dupack = (tp->snd_una == prior_snd_una && !(flag&FLAG_NOT_DUP));
+ int is_dupack = !(flag&(FLAG_SND_UNA_ADVANCED|FLAG_NOT_DUP));
+ int do_lost = is_dupack || ((flag&FLAG_DATA_SACKED) &&
+ (tp->fackets_out > tp->reordering));
/* Some technical things:
* 1. Reno does not count dupacks (sacked_out) automatically. */
if (!tp->packets_out)
tp->sacked_out = 0;
- /* 2. SACK counts snd_fack in packets inaccurately. */
- if (tp->sacked_out == 0)
+
+ if (WARN_ON(!tp->sacked_out && tp->fackets_out))
tp->fackets_out = 0;
- /* Now state machine starts.
+ /* Now state machine starts.
* A. ECE, hence prohibit cwnd undoing, the reduction is required. */
if (flag&FLAG_ECE)
tp->prior_ssthresh = 0;
/* B. In all the states check for reneging SACKs. */
- if (tp->sacked_out && tcp_check_sack_reneging(sk, tp))
+ if (tp->sacked_out && tcp_check_sack_reneging(sk))
return;
/* C. Process data loss notification, provided it is valid. */
if ((flag&FLAG_DATA_LOST) &&
before(tp->snd_una, tp->high_seq) &&
- tp->ca_state != TCP_CA_Open &&
+ icsk->icsk_ca_state != TCP_CA_Open &&
tp->fackets_out > tp->reordering) {
- tcp_mark_head_lost(sk, tp, tp->fackets_out-tp->reordering, tp->high_seq);
+ tcp_mark_head_lost(sk, tp->fackets_out-tp->reordering, tp->high_seq);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}
- /* D. Synchronize left_out to current state. */
- tcp_sync_left_out(tp);
+ /* D. Check consistency of the current state. */
+ tcp_verify_left_out(tp);
/* E. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
- if (tp->ca_state == TCP_CA_Open) {
- if (!sysctl_tcp_frto)
- BUG_TRAP(tp->retrans_out == 0);
+ if (icsk->icsk_ca_state == TCP_CA_Open) {
+ BUG_TRAP(tp->retrans_out == 0);
tp->retrans_stamp = 0;
} else if (!before(tp->snd_una, tp->high_seq)) {
- switch (tp->ca_state) {
+ switch (icsk->icsk_ca_state) {
case TCP_CA_Loss:
- tp->retransmits = 0;
- if (tcp_try_undo_recovery(sk, tp))
+ icsk->icsk_retransmits = 0;
+ if (tcp_try_undo_recovery(sk))
return;
break;
/* CWR is to be held something *above* high_seq
* is ACKed for CWR bit to reach receiver. */
if (tp->snd_una != tp->high_seq) {
- tcp_complete_cwr(tp);
- tcp_set_ca_state(tp, TCP_CA_Open);
+ tcp_complete_cwr(sk);
+ tcp_set_ca_state(sk, TCP_CA_Open);
}
break;
case TCP_CA_Disorder:
- tcp_try_undo_dsack(sk, tp);
+ tcp_try_undo_dsack(sk);
if (!tp->undo_marker ||
/* For SACK case do not Open to allow to undo
* catching for all duplicate ACKs. */
- IsReno(tp) || tp->snd_una != tp->high_seq) {
+ tcp_is_reno(tp) || tp->snd_una != tp->high_seq) {
tp->undo_marker = 0;
- tcp_set_ca_state(tp, TCP_CA_Open);
+ tcp_set_ca_state(sk, TCP_CA_Open);
}
break;
case TCP_CA_Recovery:
- if (IsReno(tp))
+ if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
- if (tcp_try_undo_recovery(sk, tp))
+ if (tcp_try_undo_recovery(sk))
return;
- tcp_complete_cwr(tp);
+ tcp_complete_cwr(sk);
break;
}
}
/* F. Process state. */
- switch (tp->ca_state) {
+ switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
- if (prior_snd_una == tp->snd_una) {
- if (IsReno(tp) && is_dupack)
- tcp_add_reno_sack(tp);
- } else {
- int acked = prior_packets - tp->packets_out;
- if (IsReno(tp))
- tcp_remove_reno_sacks(sk, tp, acked);
- is_dupack = tcp_try_undo_partial(sk, tp, acked);
- }
+ if (!(flag & FLAG_SND_UNA_ADVANCED)) {
+ if (tcp_is_reno(tp) && is_dupack)
+ tcp_add_reno_sack(sk);
+ } else
+ do_lost = tcp_try_undo_partial(sk, pkts_acked);
break;
case TCP_CA_Loss:
if (flag&FLAG_DATA_ACKED)
- tp->retransmits = 0;
- if (!tcp_try_undo_loss(sk, tp)) {
+ icsk->icsk_retransmits = 0;
+ if (!tcp_try_undo_loss(sk)) {
tcp_moderate_cwnd(tp);
tcp_xmit_retransmit_queue(sk);
return;
}
- if (tp->ca_state != TCP_CA_Open)
+ if (icsk->icsk_ca_state != TCP_CA_Open)
return;
/* Loss is undone; fall through to processing in Open state. */
default:
- if (IsReno(tp)) {
- if (tp->snd_una != prior_snd_una)
+ if (tcp_is_reno(tp)) {
+ if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
if (is_dupack)
- tcp_add_reno_sack(tp);
+ tcp_add_reno_sack(sk);
}
- if (tp->ca_state == TCP_CA_Disorder)
- tcp_try_undo_dsack(sk, tp);
+ if (icsk->icsk_ca_state == TCP_CA_Disorder)
+ tcp_try_undo_dsack(sk);
+
+ if (!tcp_time_to_recover(sk)) {
+ tcp_try_to_open(sk, flag);
+ return;
+ }
- if (!tcp_time_to_recover(sk, tp)) {
- tcp_try_to_open(sk, tp, flag);
+ /* MTU probe failure: don't reduce cwnd */
+ if (icsk->icsk_ca_state < TCP_CA_CWR &&
+ icsk->icsk_mtup.probe_size &&
+ tp->snd_una == tp->mtu_probe.probe_seq_start) {
+ tcp_mtup_probe_failed(sk);
+ /* Restores the reduction we did in tcp_mtup_probe() */
+ tp->snd_cwnd++;
+ tcp_simple_retransmit(sk);
return;
}
/* Otherwise enter Recovery state */
- if (IsReno(tp))
+ if (tcp_is_reno(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERY);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERY);
tp->undo_marker = tp->snd_una;
tp->undo_retrans = tp->retrans_out;
- if (tp->ca_state < TCP_CA_CWR) {
+ if (icsk->icsk_ca_state < TCP_CA_CWR) {
if (!(flag&FLAG_ECE))
- tp->prior_ssthresh = tcp_current_ssthresh(tp);
- tp->snd_ssthresh = tp->ca_ops->ssthresh(tp);
+ tp->prior_ssthresh = tcp_current_ssthresh(sk);
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
TCP_ECN_queue_cwr(tp);
}
+ tp->bytes_acked = 0;
tp->snd_cwnd_cnt = 0;
- tcp_set_ca_state(tp, TCP_CA_Recovery);
+ tcp_set_ca_state(sk, TCP_CA_Recovery);
}
- if (is_dupack || tcp_head_timedout(sk, tp))
- tcp_update_scoreboard(sk, tp);
- tcp_cwnd_down(tp);
+ if (do_lost || tcp_head_timedout(sk))
+ tcp_update_scoreboard(sk);
+ tcp_cwnd_down(sk, flag);
tcp_xmit_retransmit_queue(sk);
}
/* Read draft-ietf-tcplw-high-performance before mucking
- * with this code. (Superceeds RFC1323)
+ * with this code. (Supersedes RFC1323)
*/
-static void tcp_ack_saw_tstamp(struct tcp_sock *tp, u32 *usrtt, int flag)
+static void tcp_ack_saw_tstamp(struct sock *sk, int flag)
{
- __u32 seq_rtt;
-
/* RTTM Rule: A TSecr value received in a segment is used to
* update the averaged RTT measurement only if the segment
* acknowledges some new data, i.e., only if it advances the
* 1998/04/10 Andrey V. Savochkin <saw@msu.ru>
*
* Changed: reset backoff as soon as we see the first valid sample.
- * If we do not, we get strongly overstimated rto. With timestamps
+ * If we do not, we get strongly overestimated rto. With timestamps
* samples are accepted even from very old segments: f.e., when rtt=1
* increases to 8, we retransmit 5 times and after 8 seconds delayed
* answer arrives rto becomes 120 seconds! If at least one of segments
* in window is lost... Voila. --ANK (010210)
*/
- seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
- tcp_rtt_estimator(tp, seq_rtt, usrtt);
- tcp_set_rto(tp);
- tp->backoff = 0;
- tcp_bound_rto(tp);
+ struct tcp_sock *tp = tcp_sk(sk);
+ const __u32 seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+ tcp_rtt_estimator(sk, seq_rtt);
+ tcp_set_rto(sk);
+ inet_csk(sk)->icsk_backoff = 0;
+ tcp_bound_rto(sk);
}
-static void tcp_ack_no_tstamp(struct tcp_sock *tp, u32 seq_rtt, u32 *usrtt, int flag)
+static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag)
{
/* We don't have a timestamp. Can only use
* packets that are not retransmitted to determine
if (flag & FLAG_RETRANS_DATA_ACKED)
return;
- tcp_rtt_estimator(tp, seq_rtt, usrtt);
- tcp_set_rto(tp);
- tp->backoff = 0;
- tcp_bound_rto(tp);
+ tcp_rtt_estimator(sk, seq_rtt);
+ tcp_set_rto(sk);
+ inet_csk(sk)->icsk_backoff = 0;
+ tcp_bound_rto(sk);
}
-static inline void tcp_ack_update_rtt(struct tcp_sock *tp,
- int flag, s32 seq_rtt, u32 *usrtt)
+static inline void tcp_ack_update_rtt(struct sock *sk, const int flag,
+ const s32 seq_rtt)
{
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Note that peer MAY send zero echo. In this case it is ignored. (rfc1323) */
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
- tcp_ack_saw_tstamp(tp, usrtt, flag);
+ tcp_ack_saw_tstamp(sk, flag);
else if (seq_rtt >= 0)
- tcp_ack_no_tstamp(tp, seq_rtt, usrtt, flag);
+ tcp_ack_no_tstamp(sk, seq_rtt, flag);
}
-static inline void tcp_cong_avoid(struct tcp_sock *tp, u32 ack, u32 rtt,
- u32 in_flight, int good)
+static void tcp_cong_avoid(struct sock *sk, u32 ack,
+ u32 in_flight, int good)
{
- tp->ca_ops->cong_avoid(tp, ack, rtt, in_flight, good);
- tp->snd_cwnd_stamp = tcp_time_stamp;
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ icsk->icsk_ca_ops->cong_avoid(sk, ack, in_flight, good);
+ tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
}
/* Restart timer after forward progress on connection.
* RFC2988 recommends to restart timer to now+rto.
*/
-
-static inline void tcp_ack_packets_out(struct sock *sk, struct tcp_sock *tp)
+static void tcp_rearm_rto(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (!tp->packets_out) {
- tcp_clear_xmit_timer(sk, TCP_TIME_RETRANS);
+ inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
} else {
- 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);
}
}
-static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb,
- __u32 now, __s32 *seq_rtt)
+/* If we get here, the whole TSO packet has not been acked. */
+static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- __u32 seq = tp->snd_una;
- __u32 packets_acked;
- int acked = 0;
+ u32 packets_acked;
- /* If we get here, the whole TSO packet has not been
- * acked.
- */
- BUG_ON(!after(scb->end_seq, seq));
+ BUG_ON(!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una));
packets_acked = tcp_skb_pcount(skb);
- if (tcp_trim_head(sk, skb, seq - scb->seq))
+ if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return 0;
packets_acked -= tcp_skb_pcount(skb);
if (packets_acked) {
- __u8 sacked = scb->sacked;
+ BUG_ON(tcp_skb_pcount(skb) == 0);
+ BUG_ON(!before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq));
+ }
+
+ return packets_acked;
+}
+
+/* Remove acknowledged frames from the retransmission queue. If our packet
+ * is before the ack sequence we can discard it as it's confirmed to have
+ * arrived at the other end.
+ */
+static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct sk_buff *skb;
+ u32 now = tcp_time_stamp;
+ int fully_acked = 1;
+ int flag = 0;
+ int prior_packets = tp->packets_out;
+ s32 seq_rtt = -1;
+ ktime_t last_ackt = net_invalid_timestamp();
+
+ while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+ struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+ u32 end_seq;
+ u32 packets_acked;
+ u8 sacked = scb->sacked;
+
+ if (after(scb->end_seq, tp->snd_una)) {
+ if (tcp_skb_pcount(skb) == 1 ||
+ !after(tp->snd_una, scb->seq))
+ break;
+
+ packets_acked = tcp_tso_acked(sk, skb);
+ if (!packets_acked)
+ break;
+
+ fully_acked = 0;
+ end_seq = tp->snd_una;
+ } else {
+ packets_acked = tcp_skb_pcount(skb);
+ end_seq = scb->end_seq;
+ }
+
+ /* MTU probing checks */
+ if (fully_acked && icsk->icsk_mtup.probe_size &&
+ !after(tp->mtu_probe.probe_seq_end, scb->end_seq)) {
+ tcp_mtup_probe_success(sk, skb);
+ }
- acked |= FLAG_DATA_ACKED;
if (sacked) {
if (sacked & TCPCB_RETRANS) {
if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= packets_acked;
- acked |= FLAG_RETRANS_DATA_ACKED;
- *seq_rtt = -1;
- } else if (*seq_rtt < 0)
- *seq_rtt = now - scb->when;
+ flag |= FLAG_RETRANS_DATA_ACKED;
+ seq_rtt = -1;
+ if ((flag & FLAG_DATA_ACKED) ||
+ (packets_acked > 1))
+ flag |= FLAG_NONHEAD_RETRANS_ACKED;
+ } else if (seq_rtt < 0) {
+ seq_rtt = now - scb->when;
+ if (fully_acked)
+ last_ackt = skb->tstamp;
+ }
+
if (sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= packets_acked;
if (sacked & TCPCB_LOST)
tp->lost_out -= packets_acked;
- if (sacked & TCPCB_URG) {
- if (tp->urg_mode &&
- !before(seq, tp->snd_up))
- tp->urg_mode = 0;
- }
- } else if (*seq_rtt < 0)
- *seq_rtt = now - scb->when;
- if (tp->fackets_out) {
- __u32 dval = min(tp->fackets_out, packets_acked);
- tp->fackets_out -= dval;
+ if ((sacked & TCPCB_URG) && tp->urg_mode &&
+ !before(end_seq, tp->snd_up))
+ tp->urg_mode = 0;
+ } else if (seq_rtt < 0) {
+ seq_rtt = now - scb->when;
+ if (fully_acked)
+ last_ackt = skb->tstamp;
}
tp->packets_out -= packets_acked;
- BUG_ON(tcp_skb_pcount(skb) == 0);
- BUG_ON(!before(scb->seq, scb->end_seq));
- }
-
- return acked;
-}
-
-
-/* Remove acknowledged frames from the retransmission queue. */
-static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p, s32 *seq_usrtt)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
- __u32 now = tcp_time_stamp;
- int acked = 0;
- __s32 seq_rtt = -1;
- struct timeval usnow;
- u32 pkts_acked = 0;
-
- if (seq_usrtt)
- do_gettimeofday(&usnow);
-
- while ((skb = skb_peek(&sk->sk_write_queue)) &&
- skb != sk->sk_send_head) {
- struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- __u8 sacked = scb->sacked;
-
- /* If our packet is before the ack sequence we can
- * discard it as it's confirmed to have arrived at
- * the other end.
- */
- if (after(scb->end_seq, tp->snd_una)) {
- if (tcp_skb_pcount(skb) > 1)
- acked |= tcp_tso_acked(sk, skb,
- now, &seq_rtt);
- break;
- }
-
/* Initial outgoing SYN's get put onto the write_queue
* just like anything else we transmit. It is not
* true data, and if we misinform our callers that
* quickly. This is severely frowned upon behavior.
*/
if (!(scb->flags & TCPCB_FLAG_SYN)) {
- acked |= FLAG_DATA_ACKED;
- ++pkts_acked;
+ flag |= FLAG_DATA_ACKED;
} else {
- acked |= FLAG_SYN_ACKED;
+ flag |= FLAG_SYN_ACKED;
tp->retrans_stamp = 0;
}
- if (sacked) {
- if (sacked & TCPCB_RETRANS) {
- if(sacked & TCPCB_SACKED_RETRANS)
- tp->retrans_out -= tcp_skb_pcount(skb);
- acked |= FLAG_RETRANS_DATA_ACKED;
- seq_rtt = -1;
- } else if (seq_rtt < 0)
- seq_rtt = now - scb->when;
- if (seq_usrtt)
- *seq_usrtt = (usnow.tv_sec - skb->stamp.tv_sec) * 1000000
- + (usnow.tv_usec - skb->stamp.tv_usec);
+ if (!fully_acked)
+ break;
- if (sacked & TCPCB_SACKED_ACKED)
- tp->sacked_out -= tcp_skb_pcount(skb);
- if (sacked & TCPCB_LOST)
- tp->lost_out -= tcp_skb_pcount(skb);
- if (sacked & TCPCB_URG) {
- if (tp->urg_mode &&
- !before(scb->end_seq, tp->snd_up))
- tp->urg_mode = 0;
- }
- } else if (seq_rtt < 0)
- seq_rtt = now - scb->when;
- tcp_dec_pcount_approx(&tp->fackets_out, skb);
- tcp_packets_out_dec(tp, skb);
- __skb_unlink(skb, skb->list);
+ tcp_unlink_write_queue(skb, sk);
sk_stream_free_skb(sk, skb);
+ tcp_clear_all_retrans_hints(tp);
}
- if (acked&FLAG_ACKED) {
- tcp_ack_update_rtt(tp, acked, seq_rtt, seq_usrtt);
- tcp_ack_packets_out(sk, tp);
+ if (flag & FLAG_ACKED) {
+ u32 pkts_acked = prior_packets - tp->packets_out;
+ const struct tcp_congestion_ops *ca_ops
+ = inet_csk(sk)->icsk_ca_ops;
+
+ tcp_ack_update_rtt(sk, flag, seq_rtt);
+ tcp_rearm_rto(sk);
+
+ tp->fackets_out -= min(pkts_acked, tp->fackets_out);
+ /* hint's skb might be NULL but we don't need to care */
+ tp->fastpath_cnt_hint -= min_t(u32, pkts_acked,
+ tp->fastpath_cnt_hint);
+ if (tcp_is_reno(tp))
+ tcp_remove_reno_sacks(sk, pkts_acked);
+
+ if (ca_ops->pkts_acked) {
+ s32 rtt_us = -1;
+
+ /* Is the ACK triggering packet unambiguous? */
+ if (!(flag & FLAG_RETRANS_DATA_ACKED)) {
+ /* High resolution needed and available? */
+ if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
+ !ktime_equal(last_ackt,
+ net_invalid_timestamp()))
+ rtt_us = ktime_us_delta(ktime_get_real(),
+ last_ackt);
+ else if (seq_rtt > 0)
+ rtt_us = jiffies_to_usecs(seq_rtt);
+ }
- if (tp->ca_ops->pkts_acked)
- tp->ca_ops->pkts_acked(tp, pkts_acked);
+ ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
+ }
}
#if FASTRETRANS_DEBUG > 0
BUG_TRAP((int)tp->sacked_out >= 0);
BUG_TRAP((int)tp->lost_out >= 0);
BUG_TRAP((int)tp->retrans_out >= 0);
- if (!tp->packets_out && tp->rx_opt.sack_ok) {
+ if (!tp->packets_out && tcp_is_sack(tp)) {
+ const struct inet_connection_sock *icsk = inet_csk(sk);
if (tp->lost_out) {
printk(KERN_DEBUG "Leak l=%u %d\n",
- tp->lost_out, tp->ca_state);
+ tp->lost_out, icsk->icsk_ca_state);
tp->lost_out = 0;
}
if (tp->sacked_out) {
printk(KERN_DEBUG "Leak s=%u %d\n",
- tp->sacked_out, tp->ca_state);
+ tp->sacked_out, icsk->icsk_ca_state);
tp->sacked_out = 0;
}
if (tp->retrans_out) {
printk(KERN_DEBUG "Leak r=%u %d\n",
- tp->retrans_out, tp->ca_state);
+ tp->retrans_out, icsk->icsk_ca_state);
tp->retrans_out = 0;
}
}
#endif
*seq_rtt_p = seq_rtt;
- return acked;
+ return flag;
}
static void tcp_ack_probe(struct sock *sk)
{
- struct tcp_sock *tp = tcp_sk(sk);
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
/* Was it a usable window open? */
- if (!after(TCP_SKB_CB(sk->sk_send_head)->end_seq,
+ if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
- tp->backoff = 0;
- tcp_clear_xmit_timer(sk, TCP_TIME_PROBE0);
+ icsk->icsk_backoff = 0;
+ inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
/* Socket must be waked up by subsequent tcp_data_snd_check().
* This function is not for random using!
*/
} else {
- tcp_reset_xmit_timer(sk, TCP_TIME_PROBE0,
- min(tp->rto << tp->backoff, TCP_RTO_MAX));
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+ min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
+ TCP_RTO_MAX);
}
}
-static inline int tcp_ack_is_dubious(struct tcp_sock *tp, int flag)
+static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag)
{
return (!(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
- tp->ca_state != TCP_CA_Open);
+ inet_csk(sk)->icsk_ca_state != TCP_CA_Open);
}
-static inline int tcp_may_raise_cwnd(struct tcp_sock *tp, int flag)
+static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
+ const struct tcp_sock *tp = tcp_sk(sk);
return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) &&
- !((1<<tp->ca_state)&(TCPF_CA_Recovery|TCPF_CA_CWR));
+ !((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_Recovery | TCPF_CA_CWR));
}
/* Check that window update is acceptable.
* The function assumes that snd_una<=ack<=snd_next.
*/
-static inline int tcp_may_update_window(struct tcp_sock *tp, u32 ack,
- u32 ack_seq, u32 nwin)
+static inline int tcp_may_update_window(const struct tcp_sock *tp, const u32 ack,
+ const u32 ack_seq, const u32 nwin)
{
return (after(ack, tp->snd_una) ||
after(ack_seq, tp->snd_wl1) ||
* Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
* and in FreeBSD. NetBSD's one is even worse.) is wrong.
*/
-static int tcp_ack_update_window(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb, u32 ack, u32 ack_seq)
+static int tcp_ack_update_window(struct sock *sk, struct sk_buff *skb, u32 ack,
+ u32 ack_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
int flag = 0;
- u32 nwin = ntohs(skb->h.th->window);
+ u32 nwin = ntohs(tcp_hdr(skb)->window);
- if (likely(!skb->h.th->syn))
+ if (likely(!tcp_hdr(skb)->syn))
nwin <<= tp->rx_opt.snd_wscale;
if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
/* Note, it is the only place, where
* fast path is recovered for sending TCP.
*/
- tcp_fast_path_check(sk, tp);
+ tp->pred_flags = 0;
+ tcp_fast_path_check(sk);
if (nwin > tp->max_window) {
tp->max_window = nwin;
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie);
}
}
}
return flag;
}
-static void tcp_process_frto(struct sock *sk, u32 prior_snd_una)
+/* A very conservative spurious RTO response algorithm: reduce cwnd and
+ * continue in congestion avoidance.
+ */
+static void tcp_conservative_spur_to_response(struct tcp_sock *tp)
+{
+ tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
+ tp->snd_cwnd_cnt = 0;
+ TCP_ECN_queue_cwr(tp);
+ tcp_moderate_cwnd(tp);
+}
+
+/* A conservative spurious RTO response algorithm: reduce cwnd using
+ * rate halving and continue in congestion avoidance.
+ */
+static void tcp_ratehalving_spur_to_response(struct sock *sk)
+{
+ tcp_enter_cwr(sk, 0);
+}
+
+static void tcp_undo_spur_to_response(struct sock *sk, int flag)
+{
+ if (flag&FLAG_ECE)
+ tcp_ratehalving_spur_to_response(sk);
+ else
+ tcp_undo_cwr(sk, 1);
+}
+
+/* F-RTO spurious RTO detection algorithm (RFC4138)
+ *
+ * F-RTO affects during two new ACKs following RTO (well, almost, see inline
+ * comments). State (ACK number) is kept in frto_counter. When ACK advances
+ * window (but not to or beyond highest sequence sent before RTO):
+ * On First ACK, send two new segments out.
+ * On Second ACK, RTO was likely spurious. Do spurious response (response
+ * algorithm is not part of the F-RTO detection algorithm
+ * given in RFC4138 but can be selected separately).
+ * Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
+ * and TCP falls back to conventional RTO recovery. F-RTO allows overriding
+ * of Nagle, this is done using frto_counter states 2 and 3, when a new data
+ * segment of any size sent during F-RTO, state 2 is upgraded to 3.
+ *
+ * Rationale: if the RTO was spurious, new ACKs should arrive from the
+ * original window even after we transmit two new data segments.
+ *
+ * SACK version:
+ * on first step, wait until first cumulative ACK arrives, then move to
+ * the second step. In second step, the next ACK decides.
+ *
+ * F-RTO is implemented (mainly) in four functions:
+ * - tcp_use_frto() is used to determine if TCP is can use F-RTO
+ * - tcp_enter_frto() prepares TCP state on RTO if F-RTO is used, it is
+ * called when tcp_use_frto() showed green light
+ * - tcp_process_frto() handles incoming ACKs during F-RTO algorithm
+ * - tcp_enter_frto_loss() is called if there is not enough evidence
+ * to prove that the RTO is indeed spurious. It transfers the control
+ * from F-RTO to the conventional RTO recovery
+ */
+static int tcp_process_frto(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
-
- tcp_sync_left_out(tp);
-
- if (tp->snd_una == prior_snd_una ||
- !before(tp->snd_una, tp->frto_highmark)) {
- /* RTO was caused by loss, start retransmitting in
- * go-back-N slow start
+
+ tcp_verify_left_out(tp);
+
+ /* Duplicate the behavior from Loss state (fastretrans_alert) */
+ if (flag&FLAG_DATA_ACKED)
+ inet_csk(sk)->icsk_retransmits = 0;
+
+ if ((flag & FLAG_NONHEAD_RETRANS_ACKED) ||
+ ((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED)))
+ tp->undo_marker = 0;
+
+ if (!before(tp->snd_una, tp->frto_highmark)) {
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
+ return 1;
+ }
+
+ if (!IsSackFrto() || tcp_is_reno(tp)) {
+ /* RFC4138 shortcoming in step 2; should also have case c):
+ * ACK isn't duplicate nor advances window, e.g., opposite dir
+ * data, winupdate
*/
- tcp_enter_frto_loss(sk);
- return;
+ if (!(flag&FLAG_ANY_PROGRESS) && (flag&FLAG_NOT_DUP))
+ return 1;
+
+ if (!(flag&FLAG_DATA_ACKED)) {
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3),
+ flag);
+ return 1;
+ }
+ } else {
+ if (!(flag&FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
+ /* Prevent sending of new data. */
+ tp->snd_cwnd = min(tp->snd_cwnd,
+ tcp_packets_in_flight(tp));
+ return 1;
+ }
+
+ if ((tp->frto_counter >= 2) &&
+ (!(flag&FLAG_FORWARD_PROGRESS) ||
+ ((flag&FLAG_DATA_SACKED) && !(flag&FLAG_ONLY_ORIG_SACKED)))) {
+ /* RFC4138 shortcoming (see comment above) */
+ if (!(flag&FLAG_FORWARD_PROGRESS) && (flag&FLAG_NOT_DUP))
+ return 1;
+
+ tcp_enter_frto_loss(sk, 3, flag);
+ return 1;
+ }
}
if (tp->frto_counter == 1) {
- /* First ACK after RTO advances the window: allow two new
- * segments out.
- */
+ /* Sending of the next skb must be allowed or no FRTO */
+ if (!tcp_send_head(sk) ||
+ after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
+ tp->snd_una + tp->snd_wnd)) {
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3),
+ flag);
+ return 1;
+ }
+
tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
+ tp->frto_counter = 2;
+ return 1;
} else {
- /* Also the second ACK after RTO advances the window.
- * The RTO was likely spurious. Reduce cwnd and continue
- * in congestion avoidance
- */
- tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
- tcp_moderate_cwnd(tp);
+ switch (sysctl_tcp_frto_response) {
+ case 2:
+ tcp_undo_spur_to_response(sk, flag);
+ break;
+ case 1:
+ tcp_conservative_spur_to_response(tp);
+ break;
+ default:
+ tcp_ratehalving_spur_to_response(sk);
+ break;
+ }
+ tp->frto_counter = 0;
+ tp->undo_marker = 0;
}
-
- /* F-RTO affects on two new ACKs following RTO.
- * At latest on third ACK the TCP behavor is back to normal.
- */
- tp->frto_counter = (tp->frto_counter + 1) % 3;
+ return 0;
}
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 prior_snd_una = tp->snd_una;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
u32 prior_in_flight;
s32 seq_rtt;
- s32 seq_usrtt = 0;
int prior_packets;
+ int frto_cwnd = 0;
/* If the ack is newer than sent or older than previous acks
* then we can probably ignore it.
if (before(ack, prior_snd_una))
goto old_ack;
+ if (after(ack, prior_snd_una))
+ flag |= FLAG_SND_UNA_ADVANCED;
+
+ if (sysctl_tcp_abc) {
+ if (icsk->icsk_ca_state < TCP_CA_CWR)
+ tp->bytes_acked += ack - prior_snd_una;
+ else if (icsk->icsk_ca_state == TCP_CA_Loss)
+ /* we assume just one segment left network */
+ tp->bytes_acked += min(ack - prior_snd_una, tp->mss_cache);
+ }
+
if (!(flag&FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
/* Window is constant, pure forward advance.
* No more checks are required.
tp->snd_una = ack;
flag |= FLAG_WIN_UPDATE;
- tcp_ca_event(tp, CA_EVENT_FAST_ACK);
+ tcp_ca_event(sk, CA_EVENT_FAST_ACK);
NET_INC_STATS_BH(LINUX_MIB_TCPHPACKS);
} else {
else
NET_INC_STATS_BH(LINUX_MIB_TCPPUREACKS);
- flag |= tcp_ack_update_window(sk, tp, skb, ack, ack_seq);
+ flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);
if (TCP_SKB_CB(skb)->sacked)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- if (TCP_ECN_rcv_ecn_echo(tp, skb->h.th))
+ if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
- tcp_ca_event(tp, CA_EVENT_SLOW_ACK);
+ tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
}
/* We passed data and got it acked, remove any soft error
prior_in_flight = tcp_packets_in_flight(tp);
/* See if we can take anything off of the retransmit queue. */
- flag |= tcp_clean_rtx_queue(sk, &seq_rtt,
- tp->ca_ops->rtt_sample ? &seq_usrtt : NULL);
+ flag |= tcp_clean_rtx_queue(sk, &seq_rtt);
if (tp->frto_counter)
- tcp_process_frto(sk, prior_snd_una);
-
- if (tcp_ack_is_dubious(tp, flag)) {
- /* Advanve CWND, if state allows this. */
- if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(tp, flag))
- tcp_cong_avoid(tp, ack, seq_rtt, prior_in_flight, 0);
- tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag);
+ frto_cwnd = tcp_process_frto(sk, flag);
+
+ if (tcp_ack_is_dubious(sk, flag)) {
+ /* Advance CWND, if state allows this. */
+ if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
+ tcp_may_raise_cwnd(sk, flag))
+ tcp_cong_avoid(sk, ack, prior_in_flight, 0);
+ tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, flag);
} else {
- if ((flag & FLAG_DATA_ACKED))
- tcp_cong_avoid(tp, ack, seq_rtt, prior_in_flight, 1);
+ if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
+ tcp_cong_avoid(sk, ack, prior_in_flight, 1);
}
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag&FLAG_NOT_DUP))
return 1;
no_queue:
- tp->probes_out = 0;
+ icsk->icsk_probes_out = 0;
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
*/
- if (sk->sk_send_head)
+ if (tcp_send_head(sk))
tcp_ack_probe(sk);
return 1;
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab)
{
unsigned char *ptr;
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
int length=(th->doff*4)-sizeof(struct tcphdr);
ptr = (unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
- while(length>0) {
- int opcode=*ptr++;
+ while (length > 0) {
+ int opcode=*ptr++;
int opsize;
switch (opcode) {
return;
if (opsize > length)
return; /* don't parse partial options */
- switch(opcode) {
+ switch (opcode) {
case TCPOPT_MSS:
- if(opsize==TCPOLEN_MSS && th->syn && !estab) {
- u16 in_mss = ntohs(get_unaligned((__u16 *)ptr));
+ if (opsize==TCPOLEN_MSS && th->syn && !estab) {
+ u16 in_mss = ntohs(get_unaligned((__be16 *)ptr));
if (in_mss) {
if (opt_rx->user_mss && opt_rx->user_mss < in_mss)
in_mss = opt_rx->user_mss;
}
break;
case TCPOPT_WINDOW:
- if(opsize==TCPOLEN_WINDOW && th->syn && !estab)
+ if (opsize==TCPOLEN_WINDOW && th->syn && !estab)
if (sysctl_tcp_window_scaling) {
__u8 snd_wscale = *(__u8 *) ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > 14) {
- if(net_ratelimit())
+ if (net_ratelimit())
printk(KERN_INFO "tcp_parse_options: Illegal window "
"scaling value %d >14 received.\n",
snd_wscale);
}
break;
case TCPOPT_TIMESTAMP:
- if(opsize==TCPOLEN_TIMESTAMP) {
+ if (opsize==TCPOLEN_TIMESTAMP) {
if ((estab && opt_rx->tstamp_ok) ||
(!estab && sysctl_tcp_timestamps)) {
opt_rx->saw_tstamp = 1;
- opt_rx->rcv_tsval = ntohl(get_unaligned((__u32 *)ptr));
- opt_rx->rcv_tsecr = ntohl(get_unaligned((__u32 *)(ptr+4)));
+ opt_rx->rcv_tsval = ntohl(get_unaligned((__be32 *)ptr));
+ opt_rx->rcv_tsecr = ntohl(get_unaligned((__be32 *)(ptr+4)));
}
}
break;
case TCPOPT_SACK_PERM:
- if(opsize==TCPOLEN_SACK_PERM && th->syn && !estab) {
+ if (opsize==TCPOLEN_SACK_PERM && th->syn && !estab) {
if (sysctl_tcp_sack) {
opt_rx->sack_ok = 1;
tcp_sack_reset(opt_rx);
break;
case TCPOPT_SACK:
- if((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
+ if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
!((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) &&
opt_rx->sack_ok) {
TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
}
- };
- ptr+=opsize-2;
- length-=opsize;
- };
+ break;
+#ifdef CONFIG_TCP_MD5SIG
+ case TCPOPT_MD5SIG:
+ /*
+ * The MD5 Hash has already been
+ * checked (see tcp_v{4,6}_do_rcv()).
+ */
+ break;
+#endif
+ }
+
+ ptr+=opsize-2;
+ length-=opsize;
+ }
}
}
/* Fast parse options. This hopes to only see timestamps.
* If it is wrong it falls back on tcp_parse_options().
*/
-static inline int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
- struct tcp_sock *tp)
+static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
+ struct tcp_sock *tp)
{
if (th->doff == sizeof(struct tcphdr)>>2) {
tp->rx_opt.saw_tstamp = 0;
return 0;
} else if (tp->rx_opt.tstamp_ok &&
th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) {
- __u32 *ptr = (__u32 *)(th + 1);
- if (*ptr == ntohl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
+ __be32 *ptr = (__be32 *)(th + 1);
+ if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
| (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) {
tp->rx_opt.saw_tstamp = 1;
++ptr;
static inline void tcp_store_ts_recent(struct tcp_sock *tp)
{
tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
- tp->rx_opt.ts_recent_stamp = xtime.tv_sec;
+ tp->rx_opt.ts_recent_stamp = get_seconds();
}
static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
* Not only, also it occurs for expired timestamps.
*/
- if((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
- xtime.tv_sec >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
+ if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
+ get_seconds() >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
tcp_store_ts_recent(tp);
}
}
* up to bandwidth of 18Gigabit/sec. 8) ]
*/
-static int tcp_disordered_ack(struct tcp_sock *tp, struct sk_buff *skb)
+static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcphdr *th = tcp_hdr(skb);
u32 seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
/* 4. ... and sits in replay window. */
- (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (tp->rto*1024)/HZ);
+ (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
}
-static inline int tcp_paws_discard(struct tcp_sock *tp, struct sk_buff *skb)
+static inline int tcp_paws_discard(const struct sock *sk, const struct sk_buff *skb)
{
+ const struct tcp_sock *tp = tcp_sk(sk);
return ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > TCP_PAWS_WINDOW &&
- xtime.tv_sec < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
- !tcp_disordered_ack(tp, skb));
+ get_seconds() < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
+ !tcp_disordered_ack(sk, skb));
}
/* Check segment sequence number for validity.
{
struct tcp_sock *tp = tcp_sk(sk);
- tcp_schedule_ack(tp);
+ inet_csk_schedule_ack(sk);
sk->sk_shutdown |= RCV_SHUTDOWN;
sock_set_flag(sk, SOCK_DONE);
case TCP_ESTABLISHED:
/* Move to CLOSE_WAIT */
tcp_set_state(sk, TCP_CLOSE_WAIT);
- tp->ack.pingpong = 1;
+ inet_csk(sk)->icsk_ack.pingpong = 1;
break;
case TCP_CLOSE_WAIT:
printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
__FUNCTION__, sk->sk_state);
break;
- };
+ }
/* It _is_ possible, that we have something out-of-order _after_ FIN.
* Probably, we should reset in this case. For now drop them.
*/
__skb_queue_purge(&tp->out_of_order_queue);
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
sk_stream_mem_reclaim(sk);
}
}
-static __inline__ int
-tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, u32 end_seq)
+static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, u32 end_seq)
{
if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) {
if (before(seq, sp->start_seq))
return 0;
}
-static inline void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq)
+static void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
- if (tp->rx_opt.sack_ok && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
if (before(seq, tp->rcv_nxt))
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOLDSENT);
else
}
}
-static inline void tcp_dsack_extend(struct tcp_sock *tp, u32 seq, u32 end_seq)
+static void tcp_dsack_extend(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
if (!tp->rx_opt.dsack)
tcp_dsack_set(tp, seq, end_seq);
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOST);
- tcp_enter_quickack_mode(tp);
+ tcp_enter_quickack_mode(sk);
- if (tp->rx_opt.sack_ok && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
*/
tp->rx_opt.num_sacks--;
tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
- for(i=this_sack; i < tp->rx_opt.num_sacks; i++)
+ for (i=this_sack; i < tp->rx_opt.num_sacks; i++)
sp[i] = sp[i+1];
continue;
}
}
}
-static __inline__ void tcp_sack_swap(struct tcp_sack_block *sack1, struct tcp_sack_block *sack2)
+static inline void tcp_sack_swap(struct tcp_sack_block *sack1, struct tcp_sack_block *sack2)
{
__u32 tmp;
tp->rx_opt.num_sacks--;
sp--;
}
- for(; this_sack > 0; this_sack--, sp--)
+ for (; this_sack > 0; this_sack--, sp--)
*sp = *(sp-1);
new_sack:
int this_sack;
/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
- if (skb_queue_len(&tp->out_of_order_queue) == 0) {
+ if (skb_queue_empty(&tp->out_of_order_queue)) {
tp->rx_opt.num_sacks = 0;
tp->rx_opt.eff_sacks = tp->rx_opt.dsack;
return;
}
- for(this_sack = 0; this_sack < num_sacks; ) {
+ for (this_sack = 0; this_sack < num_sacks; ) {
/* Check if the start of the sack is covered by RCV.NXT. */
if (!before(tp->rcv_nxt, sp->start_seq)) {
int i;
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
SOCK_DEBUG(sk, "ofo packet was already received \n");
- __skb_unlink(skb, skb->list);
+ __skb_unlink(skb, &tp->out_of_order_queue);
__kfree_skb(skb);
continue;
}
tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq);
- __skb_unlink(skb, skb->list);
+ __skb_unlink(skb, &tp->out_of_order_queue);
__skb_queue_tail(&sk->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
- if(skb->h.th->fin)
- tcp_fin(skb, sk, skb->h.th);
+ if (tcp_hdr(skb)->fin)
+ tcp_fin(skb, sk, tcp_hdr(skb));
}
}
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
struct tcp_sock *tp = tcp_sk(sk);
int eaten = -1;
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
- if(skb->len)
- tcp_event_data_recv(sk, tp, skb);
- if(th->fin)
+ if (skb->len)
+ tcp_event_data_recv(sk, skb);
+ if (th->fin)
tcp_fin(skb, sk, th);
- if (skb_queue_len(&tp->out_of_order_queue)) {
+ if (!skb_queue_empty(&tp->out_of_order_queue)) {
tcp_ofo_queue(sk);
/* RFC2581. 4.2. SHOULD send immediate ACK, when
* gap in queue is filled.
*/
- if (!skb_queue_len(&tp->out_of_order_queue))
- tp->ack.pingpong = 0;
+ if (skb_queue_empty(&tp->out_of_order_queue))
+ inet_csk(sk)->icsk_ack.pingpong = 0;
}
if (tp->rx_opt.num_sacks)
tcp_sack_remove(tp);
- tcp_fast_path_check(sk, tp);
+ tcp_fast_path_check(sk);
if (eaten > 0)
__kfree_skb(skb);
tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
out_of_window:
- tcp_enter_quickack_mode(tp);
- tcp_schedule_ack(tp);
+ tcp_enter_quickack_mode(sk);
+ inet_csk_schedule_ack(sk);
drop:
__kfree_skb(skb);
return;
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
goto out_of_window;
- tcp_enter_quickack_mode(tp);
+ tcp_enter_quickack_mode(sk);
if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
/* Partial packet, seq < rcv_next < end_seq */
TCP_SKB_CB(skb)->end_seq);
tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, tp->rcv_nxt);
-
+
/* If window is closed, drop tail of packet. But after
* remembering D-SACK for its head made in previous line.
*/
/* Disable header prediction. */
tp->pred_flags = 0;
- tcp_schedule_ack(tp);
+ inet_csk_schedule_ack(sk);
SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
if (!skb_peek(&tp->out_of_order_queue)) {
/* Initial out of order segment, build 1 SACK. */
- if (tp->rx_opt.sack_ok) {
+ if (tcp_is_sack(tp)) {
tp->rx_opt.num_sacks = 1;
tp->rx_opt.dsack = 0;
tp->rx_opt.eff_sacks = 1;
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (seq == TCP_SKB_CB(skb1)->end_seq) {
- __skb_append(skb1, skb);
+ __skb_append(skb1, skb, &tp->out_of_order_queue);
if (!tp->rx_opt.num_sacks ||
tp->selective_acks[0].end_seq != seq)
}
}
__skb_insert(skb, skb1, skb1->next, &tp->out_of_order_queue);
-
+
/* And clean segments covered by new one as whole. */
while ((skb1 = skb->next) !=
(struct sk_buff*)&tp->out_of_order_queue &&
tcp_dsack_extend(tp, TCP_SKB_CB(skb1)->seq, end_seq);
break;
}
- __skb_unlink(skb1, skb1->list);
+ __skb_unlink(skb1, &tp->out_of_order_queue);
tcp_dsack_extend(tp, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq);
__kfree_skb(skb1);
}
add_sack:
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
tcp_sack_new_ofo_skb(sk, seq, end_seq);
}
}
* simplifies code)
*/
static void
-tcp_collapse(struct sock *sk, struct sk_buff *head,
- struct sk_buff *tail, u32 start, u32 end)
+tcp_collapse(struct sock *sk, struct sk_buff_head *list,
+ struct sk_buff *head, struct sk_buff *tail,
+ u32 start, u32 end)
{
struct sk_buff *skb;
- /* First, check that queue is collapsable and find
+ /* First, check that queue is collapsible and find
* the point where collapsing can be useful. */
for (skb = head; skb != tail; ) {
/* No new bits? It is possible on ofo queue. */
if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
struct sk_buff *next = skb->next;
- __skb_unlink(skb, skb->list);
+ __skb_unlink(skb, list);
__kfree_skb(skb);
NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
skb = next;
* - bloated or contains data before "start" or
* overlaps to the next one.
*/
- if (!skb->h.th->syn && !skb->h.th->fin &&
+ if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
(tcp_win_from_space(skb->truesize) > skb->len ||
before(TCP_SKB_CB(skb)->seq, start) ||
(skb->next != tail &&
start = TCP_SKB_CB(skb)->end_seq;
skb = skb->next;
}
- if (skb == tail || skb->h.th->syn || skb->h.th->fin)
+ if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
return;
while (before(start, end)) {
nskb = alloc_skb(copy+header, GFP_ATOMIC);
if (!nskb)
return;
+
+ skb_set_mac_header(nskb, skb_mac_header(skb) - skb->head);
+ skb_set_network_header(nskb, (skb_network_header(skb) -
+ skb->head));
+ skb_set_transport_header(nskb, (skb_transport_header(skb) -
+ skb->head));
skb_reserve(nskb, header);
memcpy(nskb->head, skb->head, header);
- nskb->nh.raw = nskb->head + (skb->nh.raw-skb->head);
- nskb->h.raw = nskb->head + (skb->h.raw-skb->head);
- nskb->mac.raw = nskb->head + (skb->mac.raw-skb->head);
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
- __skb_insert(nskb, skb->prev, skb, skb->list);
+ __skb_insert(nskb, skb->prev, skb, list);
sk_stream_set_owner_r(nskb, sk);
/* Copy data, releasing collapsed skbs. */
int offset = start - TCP_SKB_CB(skb)->seq;
int size = TCP_SKB_CB(skb)->end_seq - start;
- if (offset < 0) BUG();
+ BUG_ON(offset < 0);
if (size > 0) {
size = min(copy, size);
if (skb_copy_bits(skb, offset, skb_put(nskb, size), size))
}
if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
struct sk_buff *next = skb->next;
- __skb_unlink(skb, skb->list);
+ __skb_unlink(skb, list);
__kfree_skb(skb);
NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
skb = next;
- if (skb == tail || skb->h.th->syn || skb->h.th->fin)
+ if (skb == tail ||
+ tcp_hdr(skb)->syn ||
+ tcp_hdr(skb)->fin)
return;
}
}
if (skb == (struct sk_buff *)&tp->out_of_order_queue ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
- tcp_collapse(sk, head, skb, start, end);
+ tcp_collapse(sk, &tp->out_of_order_queue,
+ head, skb, start, end);
head = skb;
if (skb == (struct sk_buff *)&tp->out_of_order_queue)
break;
*/
static int tcp_prune_queue(struct sock *sk)
{
- struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq);
NET_INC_STATS_BH(LINUX_MIB_PRUNECALLED);
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
- tcp_clamp_window(sk, tp);
+ tcp_clamp_window(sk);
else if (tcp_memory_pressure)
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tcp_collapse_ofo_queue(sk);
- tcp_collapse(sk, sk->sk_receive_queue.next,
+ tcp_collapse(sk, &sk->sk_receive_queue,
+ sk->sk_receive_queue.next,
(struct sk_buff*)&sk->sk_receive_queue,
tp->copied_seq, tp->rcv_nxt);
sk_stream_mem_reclaim(sk);
* This must not ever occur. */
/* First, purge the out_of_order queue. */
- if (skb_queue_len(&tp->out_of_order_queue)) {
- NET_ADD_STATS_BH(LINUX_MIB_OFOPRUNED,
- skb_queue_len(&tp->out_of_order_queue));
+ if (!skb_queue_empty(&tp->out_of_order_queue)) {
+ NET_INC_STATS_BH(LINUX_MIB_OFOPRUNED);
__skb_queue_purge(&tp->out_of_order_queue);
/* Reset SACK state. A conforming SACK implementation will
* is in a sad state like this, we care only about integrity
* of the connection not performance.
*/
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
sk_stream_mem_reclaim(sk);
}
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tp->ca_state == TCP_CA_Open &&
+ if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
/* Limited by application or receiver window. */
- u32 win_used = max(tp->snd_cwnd_used, 2U);
+ u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
+ u32 win_used = max(tp->snd_cwnd_used, init_win);
if (win_used < tp->snd_cwnd) {
- tp->snd_ssthresh = tcp_current_ssthresh(tp);
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
}
tp->snd_cwnd_used = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
}
+static int tcp_should_expand_sndbuf(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ /* If the user specified a specific send buffer setting, do
+ * not modify it.
+ */
+ if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
+ return 0;
+
+ /* If we are under global TCP memory pressure, do not expand. */
+ if (tcp_memory_pressure)
+ return 0;
+
+ /* If we are under soft global TCP memory pressure, do not expand. */
+ if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+ return 0;
+
+ /* If we filled the congestion window, do not expand. */
+ if (tp->packets_out >= tp->snd_cwnd)
+ return 0;
+
+ return 1;
+}
/* When incoming ACK allowed to free some skb from write_queue,
* we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tp->packets_out < tp->snd_cwnd &&
- !(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
- !tcp_memory_pressure &&
- atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
- int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache_std) +
+ if (tcp_should_expand_sndbuf(sk)) {
+ int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
MAX_TCP_HEADER + 16 + sizeof(struct sk_buff),
demanded = max_t(unsigned int, tp->snd_cwnd,
tp->reordering + 1);
sk->sk_write_space(sk);
}
-static inline void tcp_check_space(struct sock *sk)
+static void tcp_check_space(struct sock *sk)
{
if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
}
}
-static __inline__ void tcp_data_snd_check(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_data_snd_check(struct sock *sk)
{
- tcp_push_pending_frames(sk, tp);
+ tcp_push_pending_frames(sk);
tcp_check_space(sk);
}
struct tcp_sock *tp = tcp_sk(sk);
/* More than one full frame received... */
- if (((tp->rcv_nxt - tp->rcv_wup) > tp->ack.rcv_mss
+ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss
/* ... and right edge of window advances far enough.
* (tcp_recvmsg() will send ACK otherwise). Or...
*/
&& __tcp_select_window(sk) >= tp->rcv_wnd) ||
/* We ACK each frame or... */
- tcp_in_quickack_mode(tp) ||
+ tcp_in_quickack_mode(sk) ||
/* We have out of order data. */
(ofo_possible &&
skb_peek(&tp->out_of_order_queue))) {
}
}
-static __inline__ void tcp_ack_snd_check(struct sock *sk)
+static inline void tcp_ack_snd_check(struct sock *sk)
{
- struct tcp_sock *tp = tcp_sk(sk);
- if (!tcp_ack_scheduled(tp)) {
+ if (!inet_csk_ack_scheduled(sk)) {
/* We sent a data segment already. */
return;
}
/*
* This routine is only called when we have urgent data
- * signalled. Its the 'slow' part of tcp_urg. It could be
+ * signaled. Its the 'slow' part of tcp_urg. It could be
* moved inline now as tcp_urg is only called from one
* place. We handle URGent data wrong. We have to - as
* BSD still doesn't use the correction from RFC961.
* For 1003.1g we should support a new option TCP_STDURG to permit
* either form (or just set the sysctl tcp_stdurg).
*/
-
+
static void tcp_check_urg(struct sock * sk, struct tcphdr * th)
{
struct tcp_sock *tp = tcp_sk(sk);
* urgent. To do this requires some care. We cannot just ignore
* tp->copied_seq since we would read the last urgent byte again
* as data, nor can we alter copied_seq until this data arrives
- * or we break the sematics of SIOCATMARK (and thus sockatmark())
+ * or we break the semantics of SIOCATMARK (and thus sockatmark())
*
* NOTE. Double Dutch. Rendering to plain English: author of comment
* above did something sort of send("A", MSG_OOB); send("B", MSG_OOB);
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
tp->copied_seq++;
if (skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)) {
- __skb_unlink(skb, skb->list);
+ __skb_unlink(skb, &sk->sk_receive_queue);
__kfree_skb(skb);
}
}
u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) -
th->syn;
- /* Is the urgent pointer pointing into this packet? */
+ /* Is the urgent pointer pointing into this packet? */
if (ptr < skb->len) {
u8 tmp;
if (skb_copy_bits(skb, ptr, &tmp, 1))
int err;
local_bh_enable();
- if (skb->ip_summed==CHECKSUM_UNNECESSARY)
+ if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk);
else
err = skb_copy_and_csum_datagram_iovec(skb, hlen,
return err;
}
-static int __tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
+static __sum16 __tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
{
- int result;
+ __sum16 result;
if (sock_owned_by_user(sk)) {
local_bh_enable();
return result;
}
-static __inline__ int
-tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
+static inline int tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
{
- return skb->ip_summed != CHECKSUM_UNNECESSARY &&
+ return !skb_csum_unnecessary(skb) &&
__tcp_checksum_complete_user(sk, skb);
}
+#ifdef CONFIG_NET_DMA
+static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, int hlen)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int chunk = skb->len - hlen;
+ int dma_cookie;
+ int copied_early = 0;
+
+ if (tp->ucopy.wakeup)
+ return 0;
+
+ if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
+ tp->ucopy.dma_chan = get_softnet_dma();
+
+ if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
+
+ dma_cookie = dma_skb_copy_datagram_iovec(tp->ucopy.dma_chan,
+ skb, hlen, tp->ucopy.iov, chunk, tp->ucopy.pinned_list);
+
+ if (dma_cookie < 0)
+ goto out;
+
+ tp->ucopy.dma_cookie = dma_cookie;
+ copied_early = 1;
+
+ tp->ucopy.len -= chunk;
+ tp->copied_seq += chunk;
+ tcp_rcv_space_adjust(sk);
+
+ if ((tp->ucopy.len == 0) ||
+ (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
+ (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
+ tp->ucopy.wakeup = 1;
+ sk->sk_data_ready(sk, 0);
+ }
+ } else if (chunk > 0) {
+ tp->ucopy.wakeup = 1;
+ sk->sk_data_ready(sk, 0);
+ }
+out:
+ return copied_early;
+}
+#endif /* CONFIG_NET_DMA */
+
/*
- * TCP receive function for the ESTABLISHED state.
+ * TCP receive function for the ESTABLISHED state.
*
- * It is split into a fast path and a slow path. The fast path is
+ * It is split into a fast path and a slow path. The fast path is
* disabled when:
* - A zero window was announced from us - zero window probing
- * is only handled properly in the slow path.
+ * is only handled properly in the slow path.
* - Out of order segments arrived.
* - Urgent data is expected.
* - There is no buffer space left
* - Unexpected TCP flags/window values/header lengths are received
- * (detected by checking the TCP header against pred_flags)
+ * (detected by checking the TCP header against pred_flags)
* - Data is sent in both directions. Fast path only supports pure senders
* or pure receivers (this means either the sequence number or the ack
* value must stay constant)
* - Unexpected TCP option.
*
- * When these conditions are not satisfied it drops into a standard
+ * When these conditions are not satisfied it drops into a standard
* receive procedure patterned after RFC793 to handle all cases.
* The first three cases are guaranteed by proper pred_flags setting,
- * the rest is checked inline. Fast processing is turned on in
+ * the rest is checked inline. Fast processing is turned on in
* tcp_data_queue when everything is OK.
*/
int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
/*
* Header prediction.
- * The code loosely follows the one in the famous
+ * The code loosely follows the one in the famous
* "30 instruction TCP receive" Van Jacobson mail.
- *
- * Van's trick is to deposit buffers into socket queue
+ *
+ * Van's trick is to deposit buffers into socket queue
* on a device interrupt, to call tcp_recv function
* on the receive process context and checksum and copy
* the buffer to user space. smart...
*
- * Our current scheme is not silly either but we take the
+ * Our current scheme is not silly either but we take the
* extra cost of the net_bh soft interrupt processing...
* We do checksum and copy also but from device to kernel.
*/
tp->rx_opt.saw_tstamp = 0;
/* pred_flags is 0xS?10 << 16 + snd_wnd
- * if header_predition is to be made
+ * if header_prediction is to be made
* 'S' will always be tp->tcp_header_len >> 2
* '?' will be 0 for the fast path, otherwise pred_flags is 0 to
- * turn it off (when there are holes in the receive
+ * turn it off (when there are holes in the receive
* space for instance)
* PSH flag is ignored.
*/
/* Check timestamp */
if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
- __u32 *ptr = (__u32 *)(th + 1);
+ __be32 *ptr = (__be32 *)(th + 1);
/* No? Slow path! */
- if (*ptr != ntohl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
+ if (*ptr != htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
| (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP))
goto slow_path;
tp->rx_opt.saw_tstamp = 1;
- ++ptr;
+ ++ptr;
tp->rx_opt.rcv_tsval = ntohl(*ptr);
++ptr;
tp->rx_opt.rcv_tsecr = ntohl(*ptr);
tp->rcv_nxt == tp->rcv_wup)
tcp_store_ts_recent(tp);
- tcp_rcv_rtt_measure_ts(tp, skb);
-
/* We know that such packets are checksummed
* on entry.
*/
tcp_ack(sk, skb, 0);
- __kfree_skb(skb);
- tcp_data_snd_check(sk, tp);
+ __kfree_skb(skb);
+ tcp_data_snd_check(sk);
return 0;
} else { /* Header too small */
TCP_INC_STATS_BH(TCP_MIB_INERRS);
}
} else {
int eaten = 0;
+ int copied_early = 0;
- if (tp->ucopy.task == current &&
- tp->copied_seq == tp->rcv_nxt &&
- len - tcp_header_len <= tp->ucopy.len &&
- sock_owned_by_user(sk)) {
- __set_current_state(TASK_RUNNING);
+ if (tp->copied_seq == tp->rcv_nxt &&
+ len - tcp_header_len <= tp->ucopy.len) {
+#ifdef CONFIG_NET_DMA
+ if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
+ copied_early = 1;
+ eaten = 1;
+ }
+#endif
+ if (tp->ucopy.task == current && sock_owned_by_user(sk) && !copied_early) {
+ __set_current_state(TASK_RUNNING);
- if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) {
+ if (!tcp_copy_to_iovec(sk, skb, tcp_header_len))
+ eaten = 1;
+ }
+ if (eaten) {
/* Predicted packet is in window by definition.
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
tp->rcv_nxt == tp->rcv_wup)
tcp_store_ts_recent(tp);
- tcp_rcv_rtt_measure_ts(tp, skb);
+ tcp_rcv_rtt_measure_ts(sk, skb);
__skb_pull(skb, tcp_header_len);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
NET_INC_STATS_BH(LINUX_MIB_TCPHPHITSTOUSER);
- eaten = 1;
}
+ if (copied_early)
+ tcp_cleanup_rbuf(sk, skb->len);
}
if (!eaten) {
if (tcp_checksum_complete_user(sk, skb))
tp->rcv_nxt == tp->rcv_wup)
tcp_store_ts_recent(tp);
- tcp_rcv_rtt_measure_ts(tp, skb);
+ tcp_rcv_rtt_measure_ts(sk, skb);
if ((int)skb->truesize > sk->sk_forward_alloc)
goto step5;
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
}
- tcp_event_data_recv(sk, tp, skb);
+ tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
/* Well, only one small jumplet in fast path... */
tcp_ack(sk, skb, FLAG_DATA);
- tcp_data_snd_check(sk, tp);
- if (!tcp_ack_scheduled(tp))
+ tcp_data_snd_check(sk);
+ if (!inet_csk_ack_scheduled(sk))
goto no_ack;
}
__tcp_ack_snd_check(sk, 0);
no_ack:
+#ifdef CONFIG_NET_DMA
+ if (copied_early)
+ __skb_queue_tail(&sk->sk_async_wait_queue, skb);
+ else
+#endif
if (eaten)
__kfree_skb(skb);
else
* RFC1323: H1. Apply PAWS check first.
*/
if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
- tcp_paws_discard(tp, skb)) {
+ tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
tcp_send_dupack(sk, skb);
goto discard;
}
- if(th->rst) {
+ if (th->rst) {
tcp_reset(sk);
goto discard;
}
}
step5:
- if(th->ack)
+ if (th->ack)
tcp_ack(sk, skb, FLAG_SLOWPATH);
- tcp_rcv_rtt_measure_ts(tp, skb);
+ tcp_rcv_rtt_measure_ts(sk, skb);
/* Process urgent data. */
tcp_urg(sk, skb, th);
/* step 7: process the segment text */
tcp_data_queue(sk, skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
return 0;
struct tcphdr *th, unsigned len)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
int saved_clamp = tp->rx_opt.mss_clamp;
tcp_parse_options(skb, &tp->rx_opt, 0);
*/
TCP_ECN_rcv_synack(tp, th);
- if (tp->ecn_flags&TCP_ECN_OK)
- sock_set_flag(sk, SOCK_NO_LARGESEND);
tp->snd_wl1 = TCP_SKB_CB(skb)->seq;
tcp_ack(sk, skb, FLAG_SLOWPATH);
tp->tcp_header_len = sizeof(struct tcphdr);
}
- if (tp->rx_opt.sack_ok && sysctl_tcp_fack)
- tp->rx_opt.sack_ok |= 2;
+ if (tcp_is_sack(tp) && sysctl_tcp_fack)
+ tcp_enable_fack(tp);
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ tcp_mtup_init(sk);
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
/* Remember, tcp_poll() does not lock socket!
* Change state from SYN-SENT only after copied_seq
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
- mb();
+ smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
+ security_inet_conn_established(sk, skb);
+
/* Make sure socket is routed, for correct metrics. */
- tp->af_specific->rebuild_header(sk);
+ icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_metrics(sk);
- tcp_init_congestion_control(tp);
+ tcp_init_congestion_control(sk);
/* Prevent spurious tcp_cwnd_restart() on first data
* packet.
tcp_init_buffer_space(sk);
if (sock_flag(sk, SOCK_KEEPOPEN))
- tcp_reset_keepalive_timer(sk, keepalive_time_when(tp));
+ inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
if (!tp->rx_opt.snd_wscale)
__tcp_fast_path_on(tp, tp->snd_wnd);
sk_wake_async(sk, 0, POLL_OUT);
}
- if (sk->sk_write_pending || tp->defer_accept || tp->ack.pingpong) {
+ if (sk->sk_write_pending ||
+ icsk->icsk_accept_queue.rskq_defer_accept ||
+ icsk->icsk_ack.pingpong) {
/* Save one ACK. Data will be ready after
* several ticks, if write_pending is set.
*
* look so _wonderfully_ clever, that I was not able
* to stand against the temptation 8) --ANK
*/
- tcp_schedule_ack(tp);
- tp->ack.lrcvtime = tcp_time_stamp;
- tp->ack.ato = TCP_ATO_MIN;
- tcp_incr_quickack(tp);
- tcp_enter_quickack_mode(tp);
- tcp_reset_xmit_timer(sk, TCP_TIME_DACK, TCP_DELACK_MAX);
+ inet_csk_schedule_ack(sk);
+ icsk->icsk_ack.lrcvtime = tcp_time_stamp;
+ icsk->icsk_ack.ato = TCP_ATO_MIN;
+ tcp_incr_quickack(sk);
+ tcp_enter_quickack_mode(sk);
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+ TCP_DELACK_MAX, TCP_RTO_MAX);
discard:
__kfree_skb(skb);
tp->max_window = tp->snd_wnd;
TCP_ECN_rcv_syn(tp, th);
- if (tp->ecn_flags&TCP_ECN_OK)
- sock_set_flag(sk, SOCK_NO_LARGESEND);
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ tcp_mtup_init(sk);
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
/*
* This function implements the receiving procedure of RFC 793 for
- * all states except ESTABLISHED and TIME_WAIT.
+ * all states except ESTABLISHED and TIME_WAIT.
* It's called from both tcp_v4_rcv and tcp_v6_rcv and should be
* address independent.
*/
-
+
int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
int queued = 0;
tp->rx_opt.saw_tstamp = 0;
goto discard;
case TCP_LISTEN:
- if(th->ack)
+ if (th->ack)
return 1;
- if(th->rst)
+ if (th->rst)
goto discard;
- if(th->syn) {
- if(tp->af_specific->conn_request(sk, skb) < 0)
+ if (th->syn) {
+ if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
return 1;
- /* Now we have several options: In theory there is
- * nothing else in the frame. KA9Q has an option to
+ /* Now we have several options: In theory there is
+ * nothing else in the frame. KA9Q has an option to
* send data with the syn, BSD accepts data with the
- * syn up to the [to be] advertised window and
- * Solaris 2.1 gives you a protocol error. For now
- * we just ignore it, that fits the spec precisely
+ * syn up to the [to be] advertised window and
+ * Solaris 2.1 gives you a protocol error. For now
+ * we just ignore it, that fits the spec precisely
* and avoids incompatibilities. It would be nice in
* future to drop through and process the data.
*
- * Now that TTCP is starting to be used we ought to
+ * Now that TTCP is starting to be used we ought to
* queue this data.
* But, this leaves one open to an easy denial of
- * service attack, and SYN cookies can't defend
+ * service attack, and SYN cookies can't defend
* against this problem. So, we drop the data
- * in the interest of security over speed.
+ * in the interest of security over speed unless
+ * it's still in use.
*/
- goto discard;
+ kfree_skb(skb);
+ return 0;
}
goto discard;
/* Do step6 onward by hand. */
tcp_urg(sk, skb, th);
__kfree_skb(skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
return 0;
}
if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
- tcp_paws_discard(tp, skb)) {
+ tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
tcp_send_dupack(sk, skb);
}
/* step 2: check RST bit */
- if(th->rst) {
+ if (th->rst) {
tcp_reset(sk);
goto discard;
}
if (th->ack) {
int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH);
- switch(sk->sk_state) {
+ switch (sk->sk_state) {
case TCP_SYN_RECV:
if (acceptable) {
tp->copied_seq = tp->rcv_nxt;
- mb();
+ smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
sk->sk_state_change(sk);
*/
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
!tp->srtt)
- tcp_ack_saw_tstamp(tp, 0, 0);
+ tcp_ack_saw_tstamp(sk, 0);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
/* Make sure socket is routed, for
* correct metrics.
*/
- tp->af_specific->rebuild_header(sk);
+ icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_metrics(sk);
- tcp_init_congestion_control(tp);
+ tcp_init_congestion_control(sk);
/* Prevent spurious tcp_cwnd_restart() on
* first data packet.
*/
tp->lsndtime = tcp_time_stamp;
+ tcp_mtup_init(sk);
tcp_initialize_rcv_mss(sk);
tcp_init_buffer_space(sk);
tcp_fast_path_on(tp);
return 1;
}
- tmo = tcp_fin_time(tp);
+ tmo = tcp_fin_time(sk);
if (tmo > TCP_TIMEWAIT_LEN) {
- tcp_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
+ inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
} else if (th->fin || sock_owned_by_user(sk)) {
/* Bad case. We could lose such FIN otherwise.
* It is not a big problem, but it looks confusing
* if it spins in bh_lock_sock(), but it is really
* marginal case.
*/
- tcp_reset_keepalive_timer(sk, tmo);
+ inet_csk_reset_keepalive_timer(sk, tmo);
} else {
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
goto discard;
case TCP_FIN_WAIT1:
case TCP_FIN_WAIT2:
/* RFC 793 says to queue data in these states,
- * RFC 1122 says we MUST send a reset.
+ * RFC 1122 says we MUST send a reset.
* BSD 4.4 also does reset.
*/
if (sk->sk_shutdown & RCV_SHUTDOWN) {
}
}
/* Fall through */
- case TCP_ESTABLISHED:
+ case TCP_ESTABLISHED:
tcp_data_queue(sk, skb);
queued = 1;
break;
/* tcp_data could move socket to TIME-WAIT */
if (sk->sk_state != TCP_CLOSE) {
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
}
- if (!queued) {
+ if (!queued) {
discard:
__kfree_skb(skb);
}
EXPORT_SYMBOL(tcp_parse_options);
EXPORT_SYMBOL(tcp_rcv_established);
EXPORT_SYMBOL(tcp_rcv_state_process);
+EXPORT_SYMBOL(tcp_initialize_rcv_mss);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff