#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
+#include <linux/kernel.h>
#include <net/dst.h>
#include <net/tcp.h>
#include <net/inet_common.h>
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_ecn __read_mostly = 2;
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 2;
* "len" is invariant segment length, including TCP header.
*/
len += skb->data - skb_transport_header(skb);
- if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
+ if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) ||
/* If PSH is not set, packet should be
* full sized, provided peer TCP is not badly broken.
* This observation (if it is correct 8)) allows
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 = min(hint, TCP_MSS_DEFAULT);
hint = max(hint, TCP_MIN_MSS);
inet_csk(sk)->icsk_ack.rcv_mss = hint;
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_metric_rtt(dst, RTAX_RTO_MIN);
- return rto_min;
-}
-
/* Called to compute a smoothed rtt estimate. The data fed to this
* routine either comes from timestamps, or from segments that were
* known _not_ to have been retransmitted [see Karn/Partridge
* is invisible. Actually, Linux-2.4 also generates erratic
* ACKs in some circumstances.
*/
- inet_csk(sk)->icsk_rto = (tp->srtt >> 3) + tp->rttvar;
+ inet_csk(sk)->icsk_rto = __tcp_set_rto(tp);
/* 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 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 sock *sk)
-{
- if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
- inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
+ /* NOTE: clamping at TCP_RTO_MIN is not required, current algo
+ * guarantees that rto is higher.
+ */
+ tcp_bound_rto(sk);
}
/* Save metrics learned by this TCP session.
set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
}
- if (tp->snd_ssthresh >= 0xFFFF) {
+ if (tcp_in_initial_slowstart(tp)) {
/* Slow start still did not finish. */
if (dst_metric(dst, RTAX_SSTHRESH) &&
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
}
tcp_set_rto(sk);
- tcp_bound_rto(sk);
if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
goto reset;
+
+cwnd:
tp->snd_cwnd = tcp_init_cwnd(tp, dst);
tp->snd_cwnd_stamp = tcp_time_stamp;
return;
tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
}
+ goto cwnd;
}
static void tcp_update_reordering(struct sock *sk, const int metric,
}
}
+/* This must be called before lost_out is incremented */
+static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
+{
+ if ((tp->retransmit_skb_hint == NULL) ||
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+ tp->retransmit_skb_hint = skb;
+
+ if (!tp->lost_out ||
+ after(TCP_SKB_CB(skb)->end_seq, tp->retransmit_high))
+ tp->retransmit_high = TCP_SKB_CB(skb)->end_seq;
+}
+
+static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
+{
+ if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
+ tcp_verify_retransmit_hint(tp, skb);
+
+ tp->lost_out += tcp_skb_pcount(skb);
+ TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ }
+}
+
+static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp,
+ struct sk_buff *skb)
+{
+ tcp_verify_retransmit_hint(tp, skb);
+
+ 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;
+ }
+}
+
/* This procedure tags the retransmission queue when SACKs arrive.
*
* We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS))
continue;
- if (after(received_upto, ack_seq) &&
- (tcp_is_fack(tp) ||
- !before(received_upto,
- ack_seq + tp->reordering * tp->mss_cache))) {
+ /* TODO: We would like to get rid of tcp_is_fack(tp) only
+ * constraint here (see above) but figuring out that at
+ * least tp->reordering SACK blocks reside between ack_seq
+ * and received_upto is not easy task to do cheaply with
+ * the available datastructures.
+ *
+ * Whether FACK should check here for tp->reordering segs
+ * in-between one could argue for either way (it would be
+ * rather simple to implement as we could count fack_count
+ * during the walk and do tp->fackets_out - fack_count).
+ */
+ if (after(received_upto, ack_seq)) {
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;
- }
+ tcp_skb_mark_lost_uncond_verify(tp, skb);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
} else {
if (before(ack_seq, new_low_seq))
return dup_sack;
}
+struct tcp_sacktag_state {
+ int reord;
+ int fack_count;
+ int flag;
+};
+
/* Check if skb is fully within the SACK block. In presence of GSO skbs,
* the incoming SACK may not exactly match but we can find smaller MSS
* aligned portion of it that matches. Therefore we might need to fragment
* which may fail and creates some hassle (caller must handle error case
* returns).
+ *
+ * FIXME: this could be merged to shift decision code
*/
static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
u32 start_seq, u32 end_seq)
{
int in_sack, err;
unsigned int pkt_len;
+ unsigned int mss;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
!before(end_seq, TCP_SKB_CB(skb)->end_seq);
if (tcp_skb_pcount(skb) > 1 && !in_sack &&
after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
-
+ mss = tcp_skb_mss(skb);
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);
- if (!in_sack)
+ if (!in_sack) {
pkt_len = start_seq - TCP_SKB_CB(skb)->seq;
- else
+ if (pkt_len < mss)
+ pkt_len = mss;
+ } else {
pkt_len = end_seq - TCP_SKB_CB(skb)->seq;
- err = tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size);
+ if (pkt_len < mss)
+ return -EINVAL;
+ }
+
+ /* Round if necessary so that SACKs cover only full MSSes
+ * and/or the remaining small portion (if present)
+ */
+ if (pkt_len > mss) {
+ unsigned int new_len = (pkt_len / mss) * mss;
+ if (!in_sack && new_len < pkt_len) {
+ new_len += mss;
+ if (new_len > skb->len)
+ return 0;
+ }
+ pkt_len = new_len;
+ }
+ err = tcp_fragment(sk, skb, pkt_len, mss);
if (err < 0)
return err;
}
return in_sack;
}
-static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
- int *reord, int dup_sack, int fack_count)
+static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
+ struct tcp_sacktag_state *state,
+ int dup_sack, int pcount)
{
struct tcp_sock *tp = tcp_sk(sk);
u8 sacked = TCP_SKB_CB(skb)->sacked;
- int flag = 0;
+ int fack_count = state->fack_count;
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
- *reord = min(fack_count, *reord);
+ state->reord = min(fack_count, state->reord);
}
/* Nothing to do; acked frame is about to be dropped (was ACKed). */
if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- return flag;
+ return sacked;
if (!(sacked & TCPCB_SACKED_ACKED)) {
if (sacked & TCPCB_SACKED_RETRANS) {
* that retransmission is still in flight.
*/
if (sacked & TCPCB_LOST) {
- 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;
+ sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
+ tp->lost_out -= pcount;
+ tp->retrans_out -= pcount;
}
} else {
if (!(sacked & TCPCB_RETRANS)) {
*/
if (before(TCP_SKB_CB(skb)->seq,
tcp_highest_sack_seq(tp)))
- *reord = min(fack_count, *reord);
+ state->reord = min(fack_count,
+ state->reord);
/* SACK enhanced F-RTO (RFC4138; Appendix B) */
if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark))
- flag |= FLAG_ONLY_ORIG_SACKED;
+ state->flag |= FLAG_ONLY_ORIG_SACKED;
}
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;
+ sacked &= ~TCPCB_LOST;
+ tp->lost_out -= pcount;
}
}
- TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
- flag |= FLAG_DATA_SACKED;
- tp->sacked_out += tcp_skb_pcount(skb);
+ sacked |= TCPCB_SACKED_ACKED;
+ state->flag |= FLAG_DATA_SACKED;
+ tp->sacked_out += pcount;
- fack_count += tcp_skb_pcount(skb);
+ fack_count += pcount;
/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
before(TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(tp->lost_skb_hint)->seq))
- tp->lost_cnt_hint += tcp_skb_pcount(skb);
+ tp->lost_cnt_hint += pcount;
if (fack_count > tp->fackets_out)
tp->fackets_out = fack_count;
-
- if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
- tcp_advance_highest_sack(sk, skb);
}
/* D-SACK. We can detect redundant retransmission in S|R and plain R
* frames and clear it. undo_retrans is decreased above, L|R frames
* are accounted above as well.
*/
- if (dup_sack && (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;
+ if (dup_sack && (sacked & TCPCB_SACKED_RETRANS)) {
+ sacked &= ~TCPCB_SACKED_RETRANS;
+ tp->retrans_out -= pcount;
}
- return flag;
+ return sacked;
+}
+
+static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
+ struct tcp_sacktag_state *state,
+ unsigned int pcount, int shifted, int mss,
+ int dup_sack)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
+
+ BUG_ON(!pcount);
+
+ /* Tweak before seqno plays */
+ if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint &&
+ !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq))
+ tp->lost_cnt_hint += pcount;
+
+ TCP_SKB_CB(prev)->end_seq += shifted;
+ TCP_SKB_CB(skb)->seq += shifted;
+
+ skb_shinfo(prev)->gso_segs += pcount;
+ BUG_ON(skb_shinfo(skb)->gso_segs < pcount);
+ skb_shinfo(skb)->gso_segs -= pcount;
+
+ /* When we're adding to gso_segs == 1, gso_size will be zero,
+ * in theory this shouldn't be necessary but as long as DSACK
+ * code can come after this skb later on it's better to keep
+ * setting gso_size to something.
+ */
+ if (!skb_shinfo(prev)->gso_size) {
+ skb_shinfo(prev)->gso_size = mss;
+ skb_shinfo(prev)->gso_type = sk->sk_gso_type;
+ }
+
+ /* CHECKME: To clear or not to clear? Mimics normal skb currently */
+ if (skb_shinfo(skb)->gso_segs <= 1) {
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
+ }
+
+ /* We discard results */
+ tcp_sacktag_one(skb, sk, state, dup_sack, pcount);
+
+ /* Difference in this won't matter, both ACKed by the same cumul. ACK */
+ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
+
+ if (skb->len > 0) {
+ BUG_ON(!tcp_skb_pcount(skb));
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTED);
+ return 0;
+ }
+
+ /* Whole SKB was eaten :-) */
+
+ if (skb == tp->retransmit_skb_hint)
+ tp->retransmit_skb_hint = prev;
+ if (skb == tp->scoreboard_skb_hint)
+ tp->scoreboard_skb_hint = prev;
+ if (skb == tp->lost_skb_hint) {
+ tp->lost_skb_hint = prev;
+ tp->lost_cnt_hint -= tcp_skb_pcount(prev);
+ }
+
+ TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags;
+ if (skb == tcp_highest_sack(sk))
+ tcp_advance_highest_sack(sk, skb);
+
+ tcp_unlink_write_queue(skb, sk);
+ sk_wmem_free_skb(sk, skb);
+
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKMERGED);
+
+ return 1;
+}
+
+/* I wish gso_size would have a bit more sane initialization than
+ * something-or-zero which complicates things
+ */
+static int tcp_skb_seglen(struct sk_buff *skb)
+{
+ return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb);
+}
+
+/* Shifting pages past head area doesn't work */
+static int skb_can_shift(struct sk_buff *skb)
+{
+ return !skb_headlen(skb) && skb_is_nonlinear(skb);
+}
+
+/* Try collapsing SACK blocks spanning across multiple skbs to a single
+ * skb.
+ */
+static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
+ struct tcp_sacktag_state *state,
+ u32 start_seq, u32 end_seq,
+ int dup_sack)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *prev;
+ int mss;
+ int pcount = 0;
+ int len;
+ int in_sack;
+
+ if (!sk_can_gso(sk))
+ goto fallback;
+
+ /* Normally R but no L won't result in plain S */
+ if (!dup_sack &&
+ (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS)
+ goto fallback;
+ if (!skb_can_shift(skb))
+ goto fallback;
+ /* This frame is about to be dropped (was ACKed). */
+ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
+ goto fallback;
+
+ /* Can only happen with delayed DSACK + discard craziness */
+ if (unlikely(skb == tcp_write_queue_head(sk)))
+ goto fallback;
+ prev = tcp_write_queue_prev(sk, skb);
+
+ if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
+ goto fallback;
+
+ in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
+ !before(end_seq, TCP_SKB_CB(skb)->end_seq);
+
+ if (in_sack) {
+ len = skb->len;
+ pcount = tcp_skb_pcount(skb);
+ mss = tcp_skb_seglen(skb);
+
+ /* TODO: Fix DSACKs to not fragment already SACKed and we can
+ * drop this restriction as unnecessary
+ */
+ if (mss != tcp_skb_seglen(prev))
+ goto fallback;
+ } else {
+ if (!after(TCP_SKB_CB(skb)->end_seq, start_seq))
+ goto noop;
+ /* CHECKME: This is non-MSS split case only?, this will
+ * cause skipped skbs due to advancing loop btw, original
+ * has that feature too
+ */
+ if (tcp_skb_pcount(skb) <= 1)
+ goto noop;
+
+ in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);
+ if (!in_sack) {
+ /* TODO: head merge to next could be attempted here
+ * if (!after(TCP_SKB_CB(skb)->end_seq, end_seq)),
+ * though it might not be worth of the additional hassle
+ *
+ * ...we can probably just fallback to what was done
+ * previously. We could try merging non-SACKed ones
+ * as well but it probably isn't going to buy off
+ * because later SACKs might again split them, and
+ * it would make skb timestamp tracking considerably
+ * harder problem.
+ */
+ goto fallback;
+ }
+
+ len = end_seq - TCP_SKB_CB(skb)->seq;
+ BUG_ON(len < 0);
+ BUG_ON(len > skb->len);
+
+ /* MSS boundaries should be honoured or else pcount will
+ * severely break even though it makes things bit trickier.
+ * Optimize common case to avoid most of the divides
+ */
+ mss = tcp_skb_mss(skb);
+
+ /* TODO: Fix DSACKs to not fragment already SACKed and we can
+ * drop this restriction as unnecessary
+ */
+ if (mss != tcp_skb_seglen(prev))
+ goto fallback;
+
+ if (len == mss) {
+ pcount = 1;
+ } else if (len < mss) {
+ goto noop;
+ } else {
+ pcount = len / mss;
+ len = pcount * mss;
+ }
+ }
+
+ if (!skb_shift(prev, skb, len))
+ goto fallback;
+ if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
+ goto out;
+
+ /* Hole filled allows collapsing with the next as well, this is very
+ * useful when hole on every nth skb pattern happens
+ */
+ if (prev == tcp_write_queue_tail(sk))
+ goto out;
+ skb = tcp_write_queue_next(sk, prev);
+
+ if (!skb_can_shift(skb) ||
+ (skb == tcp_send_head(sk)) ||
+ ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) ||
+ (mss != tcp_skb_seglen(skb)))
+ goto out;
+
+ len = skb->len;
+ if (skb_shift(prev, skb, len)) {
+ pcount += tcp_skb_pcount(skb);
+ tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
+ }
+
+out:
+ state->fack_count += pcount;
+ return prev;
+
+noop:
+ return skb;
+
+fallback:
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK);
+ return NULL;
}
static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
struct tcp_sack_block *next_dup,
+ struct tcp_sacktag_state *state,
u32 start_seq, u32 end_seq,
- int dup_sack_in, int *fack_count,
- int *reord, int *flag)
+ int dup_sack_in)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *tmp;
+
tcp_for_write_queue_from(skb, sk) {
int in_sack = 0;
int dup_sack = dup_sack_in;
dup_sack = 1;
}
- if (in_sack <= 0)
- in_sack = tcp_match_skb_to_sack(sk, skb, start_seq,
- end_seq);
+ /* skb reference here is a bit tricky to get right, since
+ * shifting can eat and free both this skb and the next,
+ * so not even _safe variant of the loop is enough.
+ */
+ if (in_sack <= 0) {
+ tmp = tcp_shift_skb_data(sk, skb, state,
+ start_seq, end_seq, dup_sack);
+ if (tmp != NULL) {
+ if (tmp != skb) {
+ skb = tmp;
+ continue;
+ }
+
+ in_sack = 0;
+ } else {
+ in_sack = tcp_match_skb_to_sack(sk, skb,
+ start_seq,
+ end_seq);
+ }
+ }
+
if (unlikely(in_sack < 0))
break;
- if (in_sack)
- *flag |= tcp_sacktag_one(skb, sk, reord, dup_sack,
- *fack_count);
+ if (in_sack) {
+ TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk,
+ state,
+ dup_sack,
+ tcp_skb_pcount(skb));
- *fack_count += tcp_skb_pcount(skb);
+ if (!before(TCP_SKB_CB(skb)->seq,
+ tcp_highest_sack_seq(tp)))
+ tcp_advance_highest_sack(sk, skb);
+ }
+
+ state->fack_count += tcp_skb_pcount(skb);
}
return skb;
}
* a normal way
*/
static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
- u32 skip_to_seq, int *fack_count)
+ struct tcp_sacktag_state *state,
+ u32 skip_to_seq)
{
tcp_for_write_queue_from(skb, sk) {
if (skb == tcp_send_head(sk))
break;
- if (!before(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
+ if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
break;
- *fack_count += tcp_skb_pcount(skb);
+ state->fack_count += tcp_skb_pcount(skb);
}
return skb;
}
static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
struct sock *sk,
struct tcp_sack_block *next_dup,
- u32 skip_to_seq,
- int *fack_count, int *reord,
- int *flag)
+ struct tcp_sacktag_state *state,
+ u32 skip_to_seq)
{
if (next_dup == NULL)
return skb;
if (before(next_dup->start_seq, skip_to_seq)) {
- skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count);
- skb = tcp_sacktag_walk(skb, sk, NULL,
- next_dup->start_seq, next_dup->end_seq,
- 1, fack_count, reord, flag);
+ skb = tcp_sacktag_skip(skb, sk, state, next_dup->start_seq);
+ skb = tcp_sacktag_walk(skb, sk, NULL, state,
+ next_dup->start_seq, next_dup->end_seq,
+ 1);
}
return skb;
struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2);
struct tcp_sack_block sp[TCP_NUM_SACKS];
struct tcp_sack_block *cache;
+ struct tcp_sacktag_state state;
struct sk_buff *skb;
int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3);
int used_sacks;
- int reord = tp->packets_out;
- int flag = 0;
int found_dup_sack = 0;
- int fack_count;
int i, j;
int first_sack_index;
+ state.flag = 0;
+ state.reord = tp->packets_out;
+
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
tp->fackets_out = 0;
found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
num_sacks, prior_snd_una);
if (found_dup_sack)
- flag |= FLAG_DSACKING_ACK;
+ state.flag |= FLAG_DSACKING_ACK;
/* Eliminate too old ACKs, but take into
* account more or less fresh ones, they can
for (i = used_sacks - 1; i > 0; i--) {
for (j = 0; j < i; j++) {
if (after(sp[j].start_seq, sp[j + 1].start_seq)) {
- struct tcp_sack_block tmp;
-
- tmp = sp[j];
- sp[j] = sp[j + 1];
- sp[j + 1] = tmp;
+ swap(sp[j], sp[j + 1]);
/* Track where the first SACK block goes to */
if (j == first_sack_index)
}
skb = tcp_write_queue_head(sk);
- fack_count = 0;
+ state.fack_count = 0;
i = 0;
if (!tp->sacked_out) {
/* Event "B" in the comment above. */
if (after(end_seq, tp->high_seq))
- flag |= FLAG_DATA_LOST;
+ state.flag |= FLAG_DATA_LOST;
/* Skip too early cached blocks */
while (tcp_sack_cache_ok(tp, cache) &&
/* Head todo? */
if (before(start_seq, cache->start_seq)) {
- skb = tcp_sacktag_skip(skb, sk, start_seq,
- &fack_count);
+ skb = tcp_sacktag_skip(skb, sk, &state,
+ start_seq);
skb = tcp_sacktag_walk(skb, sk, next_dup,
+ &state,
start_seq,
cache->start_seq,
- dup_sack, &fack_count,
- &reord, &flag);
+ dup_sack);
}
/* Rest of the block already fully processed? */
goto advance_sp;
skb = tcp_maybe_skipping_dsack(skb, sk, next_dup,
- cache->end_seq,
- &fack_count, &reord,
- &flag);
+ &state,
+ cache->end_seq);
/* ...tail remains todo... */
if (tcp_highest_sack_seq(tp) == cache->end_seq) {
skb = tcp_highest_sack(sk);
if (skb == NULL)
break;
- fack_count = tp->fackets_out;
+ state.fack_count = tp->fackets_out;
cache++;
goto walk;
}
- skb = tcp_sacktag_skip(skb, sk, cache->end_seq,
- &fack_count);
+ skb = tcp_sacktag_skip(skb, sk, &state, cache->end_seq);
/* Check overlap against next cached too (past this one already) */
cache++;
continue;
skb = tcp_highest_sack(sk);
if (skb == NULL)
break;
- fack_count = tp->fackets_out;
+ state.fack_count = tp->fackets_out;
}
- skb = tcp_sacktag_skip(skb, sk, start_seq, &fack_count);
+ skb = tcp_sacktag_skip(skb, sk, &state, start_seq);
walk:
- skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, end_seq,
- dup_sack, &fack_count, &reord, &flag);
+ skb = tcp_sacktag_walk(skb, sk, next_dup, &state,
+ start_seq, end_seq, dup_sack);
advance_sp:
/* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct
* due to in-order walk
*/
if (after(end_seq, tp->frto_highmark))
- flag &= ~FLAG_ONLY_ORIG_SACKED;
+ state.flag &= ~FLAG_ONLY_ORIG_SACKED;
i++;
}
tcp_verify_left_out(tp);
- if ((reord < tp->fackets_out) &&
+ if ((state.reord < tp->fackets_out) &&
((icsk->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker) &&
(!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
- tcp_update_reordering(sk, tp->fackets_out - reord, 0);
+ tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);
out:
WARN_ON((int)tp->retrans_out < 0);
WARN_ON((int)tcp_packets_in_flight(tp) < 0);
#endif
- return flag;
+ return state.flag;
}
/* Limits sacked_out so that sum with lost_out isn't ever larger than
* packets_out. Returns zero if sacked_out adjustement wasn't necessary.
*/
-int tcp_limit_reno_sacked(struct tcp_sock *tp)
+static int tcp_limit_reno_sacked(struct tcp_sock *tp)
{
u32 holes;
return 0;
skb = tcp_write_queue_head(sk);
+ if (tcp_skb_is_last(sk, skb))
+ return 1;
skb = tcp_write_queue_next(sk, skb); /* Skips head */
tcp_for_write_queue_from(skb, sk) {
if (skb == tcp_send_head(sk))
if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
+ tp->retransmit_high = TCP_SKB_CB(skb)->end_seq;
}
}
tcp_verify_left_out(tp);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
- tcp_clear_retrans_hints_partial(tp);
+ tcp_clear_all_retrans_hints(tp);
}
static void tcp_clear_retrans_partial(struct tcp_sock *tp)
/* 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 {
tp->sacked_out = 0;
tp->fackets_out = 0;
- tcp_clear_all_retrans_hints(tp);
}
+ tcp_clear_all_retrans_hints(tp);
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
+ tp->retransmit_high = TCP_SKB_CB(skb)->end_seq;
}
}
tcp_verify_left_out(tp);
* they differ. Since neither occurs due to loss, TCP should really
* ignore them.
*/
-static inline int tcp_dupack_heurestics(struct tcp_sock *tp)
+static inline int tcp_dupack_heuristics(struct tcp_sock *tp)
{
return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
}
return 1;
/* Not-A-Trick#2 : Classic rule... */
- if (tcp_dupack_heurestics(tp) > tp->reordering)
+ if (tcp_dupack_heuristics(tp) > tp->reordering)
return 1;
/* Trick#3 : when we use RFC2988 timer restart, fast
return 0;
}
-/* 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?
+/* New heuristics: it is possible only after we switched to restart timer
+ * each time when something is ACKed. Hence, we can detect timed out packets
+ * during fast retransmit without falling to slow start.
+ *
+ * Usefulness of this as is very questionable, since we should know which of
+ * the segments is the next to timeout which is relatively expensive to find
+ * in general case unless we add some data structure just for that. The
+ * current approach certainly won't find the right one too often and when it
+ * finally does find _something_ it usually marks large part of the window
+ * right away (because a retransmission with a larger timestamp blocks the
+ * loop from advancing). -ij
*/
-static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_timeout_skbs(struct sock *sk)
{
- 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;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+
+ if (!tcp_is_fack(tp) || !tcp_head_timedout(sk))
+ return;
+
+ skb = tp->scoreboard_skb_hint;
+ if (tp->scoreboard_skb_hint == NULL)
+ skb = 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;
+
+ tcp_skb_mark_lost(tp, skb);
+ }
+
+ tp->scoreboard_skb_hint = skb;
+
+ tcp_verify_left_out(tp);
}
/* Mark head of queue up as lost. With RFC3517 SACK, the packets is
cnt = packets;
}
- if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_SACKED_ACKED|TCPCB_LOST))) {
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- tcp_verify_retransmit_hint(tp, skb);
- }
+ tcp_skb_mark_lost(tp, skb);
}
tcp_verify_left_out(tp);
}
tcp_mark_head_lost(sk, sacked_upto);
}
- /* New heuristics: it is possible only after we switched
- * to restart timer each time when something is ACKed.
- * Hence, we can detect timed out packets during fast
- * retransmit without falling to slow start.
- */
- if (tcp_is_fack(tp) && tcp_head_timedout(sk)) {
- struct sk_buff *skb;
-
- 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_SACKED_ACKED|TCPCB_LOST))) {
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- tcp_verify_retransmit_hint(tp, skb);
- }
- }
-
- tp->scoreboard_skb_hint = skb;
-
- tcp_verify_left_out(tp);
- }
+ tcp_timeout_skbs(sk);
}
/* CWND moderation, preventing bursts due to too big ACKs
struct inet_sock *inet = inet_sk(sk);
if (sk->sk_family == AF_INET) {
- printk(KERN_DEBUG "Undo %s " NIPQUAD_FMT "/%u c%u l%u ss%u/%u p%u\n",
+ printk(KERN_DEBUG "Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n",
msg,
- NIPQUAD(inet->daddr), ntohs(inet->dport),
+ &inet->daddr, ntohs(inet->dport),
tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
else if (sk->sk_family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
- printk(KERN_DEBUG "Undo %s " NIP6_FMT "/%u c%u l%u ss%u/%u p%u\n",
+ printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
msg,
- NIP6(np->daddr), ntohs(inet->dport),
+ &np->daddr, ntohs(inet->dport),
tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
}
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)
}
}
+/* We can clear retrans_stamp when there are no retransmissions in the
+ * window. It would seem that it is trivially available for us in
+ * tp->retrans_out, however, that kind of assumptions doesn't consider
+ * what will happen if errors occur when sending retransmission for the
+ * second time. ...It could the that such segment has only
+ * TCPCB_EVER_RETRANS set at the present time. It seems that checking
+ * the head skb is enough except for some reneging corner cases that
+ * are not worth the effort.
+ *
+ * Main reason for all this complexity is the fact that connection dying
+ * time now depends on the validity of the retrans_stamp, in particular,
+ * that successive retransmissions of a segment must not advance
+ * retrans_stamp under any conditions.
+ */
+static int tcp_any_retrans_done(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+
+ if (tp->retrans_out)
+ return 1;
+
+ skb = tcp_write_queue_head(sk);
+ if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
+ return 1;
+
+ return 0;
+}
+
/* Undo during fast recovery after partial ACK. */
static int tcp_try_undo_partial(struct sock *sk, int acked)
/* Plain luck! Hole if filled with delayed
* packet, rather than with a retransmit.
*/
- if (tp->retrans_out == 0)
+ if (!tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
struct tcp_sock *tp = tcp_sk(sk);
int state = TCP_CA_Open;
- if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
+ if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker)
state = TCP_CA_Disorder;
if (inet_csk(sk)->icsk_ca_state != state) {
tcp_verify_left_out(tp);
- if (!tp->frto_counter && tp->retrans_out == 0)
+ if (!tp->frto_counter && !tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
if (flag & FLAG_ECE)
icsk->icsk_mtup.probe_size = 0;
}
-static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
+static void tcp_mtup_probe_success(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
+/* Do a simple retransmit without using the backoff mechanisms in
+ * tcp_timer. This is used for path mtu discovery.
+ * The socket is already locked here.
+ */
+void tcp_simple_retransmit(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+ unsigned int mss = tcp_current_mss(sk);
+ u32 prior_lost = tp->lost_out;
+
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ if (tcp_skb_seglen(skb) > mss &&
+ !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
+ 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_skb_mark_lost_uncond_verify(tp, skb);
+ }
+ }
+
+ tcp_clear_retrans_hints_partial(tp);
+
+ if (prior_lost == tp->lost_out)
+ return;
+
+ if (tcp_is_reno(tp))
+ tcp_limit_reno_sacked(tp);
+
+ tcp_verify_left_out(tp);
+
+ /* Don't muck with the congestion window here.
+ * Reason is that we do not increase amount of _data_
+ * in network, but units changed and effective
+ * cwnd/ssthresh really reduced now.
+ */
+ if (icsk->icsk_ca_state != TCP_CA_Loss) {
+ tp->high_seq = tp->snd_nxt;
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
+ tp->prior_ssthresh = 0;
+ tp->undo_marker = 0;
+ tcp_set_ca_state(sk, TCP_CA_Loss);
+ }
+ tcp_xmit_retransmit_queue(sk);
+}
+
/* 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(sk);
}
+static void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt)
+{
+ tcp_rtt_estimator(sk, seq_rtt);
+ tcp_set_rto(sk);
+ inet_csk(sk)->icsk_backoff = 0;
+}
+
/* Read draft-ietf-tcplw-high-performance before mucking
* with this code. (Supersedes RFC1323)
*/
* in window is lost... Voila. --ANK (010210)
*/
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);
+
+ tcp_valid_rtt_meas(sk, tcp_time_stamp - tp->rx_opt.rcv_tsecr);
}
static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag)
if (flag & FLAG_RETRANS_DATA_ACKED)
return;
- tcp_rtt_estimator(sk, seq_rtt);
- tcp_set_rto(sk);
- inet_csk(sk)->icsk_backoff = 0;
- tcp_bound_rto(sk);
+ tcp_valid_rtt_meas(sk, seq_rtt);
}
static inline void tcp_ack_update_rtt(struct sock *sk, const int flag,
* 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, int prior_fackets)
+static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
+ u32 prior_snd_una)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
int flag = 0;
u32 pkts_acked = 0;
u32 reord = tp->packets_out;
+ u32 prior_sacked = tp->sacked_out;
s32 seq_rtt = -1;
s32 ca_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 acked_pcount;
u8 sacked = scb->sacked;
break;
fully_acked = 0;
- end_seq = tp->snd_una;
} else {
acked_pcount = 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);
}
if (sacked & TCPCB_RETRANS) {
if (sacked & TCPCB_LOST)
tp->lost_out -= acked_pcount;
- if (unlikely(tp->urg_mode && !before(end_seq, tp->snd_up)))
- tp->urg_mode = 0;
-
tp->packets_out -= acked_pcount;
pkts_acked += acked_pcount;
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
- tcp_clear_all_retrans_hints(tp);
+ tp->scoreboard_skb_hint = NULL;
+ if (skb == tp->retransmit_skb_hint)
+ tp->retransmit_skb_hint = NULL;
+ if (skb == tp->lost_skb_hint)
+ tp->lost_skb_hint = NULL;
}
+ if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
+ tp->snd_up = tp->snd_una;
+
if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
flag |= FLAG_SACK_RENEGING;
const struct tcp_congestion_ops *ca_ops
= inet_csk(sk)->icsk_ca_ops;
+ if (unlikely(icsk->icsk_mtup.probe_size &&
+ !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
+ tcp_mtup_probe_success(sk);
+ }
+
tcp_ack_update_rtt(sk, flag, seq_rtt);
tcp_rearm_rto(sk);
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
} else {
+ int delta;
+
/* Non-retransmitted hole got filled? That's reordering */
if (reord < prior_fackets)
tcp_update_reordering(sk, tp->fackets_out - reord, 0);
+
+ delta = tcp_is_fack(tp) ? pkts_acked :
+ prior_sacked - tp->sacked_out;
+ tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
}
tp->fackets_out -= min(pkts_acked, tp->fackets_out);
if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
flag |= FLAG_WIN_UPDATE;
- tcp_update_wl(tp, ack, ack_seq);
+ tcp_update_wl(tp, ack_seq);
if (tp->snd_wnd != nwin) {
tp->snd_wnd = nwin;
int prior_packets;
int frto_cwnd = 0;
- /* If the ack is newer than sent or older than previous acks
+ /* If the ack is older than previous acks
* then we can probably ignore it.
*/
- if (after(ack, tp->snd_nxt))
- goto uninteresting_ack;
-
if (before(ack, prior_snd_una))
goto old_ack;
+ /* If the ack includes data we haven't sent yet, discard
+ * this segment (RFC793 Section 3.9).
+ */
+ if (after(ack, tp->snd_nxt))
+ goto invalid_ack;
+
if (after(ack, prior_snd_una))
flag |= FLAG_SND_UNA_ADVANCED;
* No more checks are required.
* Note, we use the fact that SND.UNA>=SND.WL2.
*/
- tcp_update_wl(tp, ack, ack_seq);
+ tcp_update_wl(tp, ack_seq);
tp->snd_una = ack;
flag |= FLAG_WIN_UPDATE;
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- flag |= tcp_clean_rtx_queue(sk, prior_fackets);
+ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
if (tp->frto_counter)
frto_cwnd = tcp_process_frto(sk, flag);
tcp_ack_probe(sk);
return 1;
+invalid_ack:
+ SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
+ return -1;
+
old_ack:
if (TCP_SKB_CB(skb)->sacked) {
tcp_sacktag_write_queue(sk, skb, prior_snd_una);
tcp_try_keep_open(sk);
}
-uninteresting_ack:
- SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
+ SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
return 0;
}
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- int estab)
+ u8 **hvpp, int estab)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
*/
break;
#endif
- }
+ case TCPOPT_COOKIE:
+ /* This option is variable length.
+ */
+ switch (opsize) {
+ case TCPOLEN_COOKIE_BASE:
+ /* not yet implemented */
+ break;
+ case TCPOLEN_COOKIE_PAIR:
+ /* not yet implemented */
+ break;
+ case TCPOLEN_COOKIE_MIN+0:
+ case TCPOLEN_COOKIE_MIN+2:
+ case TCPOLEN_COOKIE_MIN+4:
+ case TCPOLEN_COOKIE_MIN+6:
+ case TCPOLEN_COOKIE_MAX:
+ /* 16-bit multiple */
+ opt_rx->cookie_plus = opsize;
+ *hvpp = ptr;
+ default:
+ /* ignore option */
+ break;
+ };
+ break;
+ };
ptr += opsize-2;
length -= opsize;
}
}
+static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
+{
+ __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;
+ tp->rx_opt.rcv_tsval = ntohl(*ptr);
+ ++ptr;
+ tp->rx_opt.rcv_tsecr = ntohl(*ptr);
+ return 1;
+ }
+ return 0;
+}
+
/* Fast parse options. This hopes to only see timestamps.
* If it is wrong it falls back on tcp_parse_options().
*/
static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
- struct tcp_sock *tp)
+ struct tcp_sock *tp, u8 **hvpp)
{
- if (th->doff == sizeof(struct tcphdr) >> 2) {
+ /* In the spirit of fast parsing, compare doff directly to constant
+ * values. Because equality is used, short doff can be ignored here.
+ */
+ if (th->doff == (sizeof(*th) / 4)) {
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)) {
- __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;
- tp->rx_opt.rcv_tsval = ntohl(*ptr);
- ++ptr;
- tp->rx_opt.rcv_tsecr = ntohl(*ptr);
+ th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
+ if (tcp_parse_aligned_timestamp(tp, th))
return 1;
- }
}
- tcp_parse_options(skb, &tp->rx_opt, 1);
+ tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
return 1;
}
* Not only, also it occurs for expired timestamps.
*/
- if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
- get_seconds() >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
+ if (tcp_paws_check(&tp->rx_opt, 0))
tcp_store_ts_recent(tp);
}
}
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 &&
- get_seconds() < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
- !tcp_disordered_ack(sk, skb));
+
+ return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) &&
+ !tcp_disordered_ack(sk, skb);
}
/* Check segment sequence number for validity.
tp->rx_opt.dsack = 1;
tp->duplicate_sack[0].start_seq = seq;
tp->duplicate_sack[0].end_seq = end_seq;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks + 1;
}
}
* Decrease num_sacks.
*/
tp->rx_opt.num_sacks--;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks +
- tp->rx_opt.dsack;
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)
-{
- __u32 tmp;
-
- tmp = sack1->start_seq;
- sack1->start_seq = sack2->start_seq;
- sack2->start_seq = tmp;
-
- tmp = sack1->end_seq;
- sack1->end_seq = sack2->end_seq;
- sack2->end_seq = tmp;
-}
-
static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_sack_extend(sp, seq, end_seq)) {
/* Rotate this_sack to the first one. */
for (; this_sack > 0; this_sack--, sp--)
- tcp_sack_swap(sp, sp - 1);
+ swap(*sp, *(sp - 1));
if (cur_sacks > 1)
tcp_sack_maybe_coalesce(tp);
return;
sp->start_seq = seq;
sp->end_seq = end_seq;
tp->rx_opt.num_sacks++;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
}
/* RCV.NXT advances, some SACKs should be eaten. */
/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
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;
}
this_sack++;
sp++;
}
- if (num_sacks != tp->rx_opt.num_sacks) {
- tp->rx_opt.num_sacks = num_sacks;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks +
- tp->rx_opt.dsack;
- }
+ tp->rx_opt.num_sacks = num_sacks;
}
/* This one checks to see if we can put data from the
TCP_ECN_accept_cwr(tp, skb);
- if (tp->rx_opt.dsack) {
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks;
- }
+ tp->rx_opt.dsack = 0;
/* Queue data for delivery to the user.
* Packets in sequence go to the receive queue.
/* Initial out of order segment, build 1 SACK. */
if (tcp_is_sack(tp)) {
tp->rx_opt.num_sacks = 1;
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks = 1;
tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq;
tp->selective_acks[0].end_seq =
TCP_SKB_CB(skb)->end_seq;
}
__skb_queue_head(&tp->out_of_order_queue, skb);
} else {
- struct sk_buff *skb1 = tp->out_of_order_queue.prev;
+ struct sk_buff *skb1 = skb_peek_tail(&tp->out_of_order_queue);
u32 seq = TCP_SKB_CB(skb)->seq;
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
}
/* Find place to insert this segment. */
- do {
+ while (1) {
if (!after(TCP_SKB_CB(skb1)->seq, seq))
break;
- } while ((skb1 = skb1->prev) !=
- (struct sk_buff *)&tp->out_of_order_queue);
+ if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) {
+ skb1 = NULL;
+ break;
+ }
+ skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1);
+ }
/* Do skb overlap to previous one? */
- if (skb1 != (struct sk_buff *)&tp->out_of_order_queue &&
- before(seq, TCP_SKB_CB(skb1)->end_seq)) {
+ if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) {
if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
/* All the bits are present. Drop. */
__kfree_skb(skb);
tcp_dsack_set(sk, seq,
TCP_SKB_CB(skb1)->end_seq);
} else {
- skb1 = skb1->prev;
+ if (skb_queue_is_first(&tp->out_of_order_queue,
+ skb1))
+ skb1 = NULL;
+ else
+ skb1 = skb_queue_prev(
+ &tp->out_of_order_queue,
+ skb1);
}
}
- __skb_insert(skb, skb1, skb1->next, &tp->out_of_order_queue);
+ if (!skb1)
+ __skb_queue_head(&tp->out_of_order_queue, skb);
+ else
+ __skb_queue_after(&tp->out_of_order_queue, skb1, skb);
/* And clean segments covered by new one as whole. */
- while ((skb1 = skb->next) !=
- (struct sk_buff *)&tp->out_of_order_queue &&
- after(end_seq, TCP_SKB_CB(skb1)->seq)) {
+ while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) {
+ skb1 = skb_queue_next(&tp->out_of_order_queue, skb);
+
+ if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
+ break;
if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
end_seq);
static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
struct sk_buff_head *list)
{
- struct sk_buff *next = skb->next;
+ struct sk_buff *next = NULL;
+
+ if (!skb_queue_is_last(list, skb))
+ next = skb_queue_next(list, skb);
__skb_unlink(skb, list);
__kfree_skb(skb);
/* Collapse contiguous sequence of skbs head..tail with
* sequence numbers start..end.
+ *
+ * If tail is NULL, this means until the end of the list.
+ *
* Segments with FIN/SYN are not collapsed (only because this
* simplifies code)
*/
struct sk_buff *head, struct sk_buff *tail,
u32 start, u32 end)
{
- struct sk_buff *skb;
+ struct sk_buff *skb, *n;
+ bool end_of_skbs;
/* First, check that queue is collapsible and find
* the point where collapsing can be useful. */
- for (skb = head; skb != tail;) {
+ skb = head;
+restart:
+ end_of_skbs = true;
+ skb_queue_walk_from_safe(list, skb, n) {
+ if (skb == tail)
+ break;
/* No new bits? It is possible on ofo queue. */
if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
skb = tcp_collapse_one(sk, skb, list);
- continue;
+ if (!skb)
+ break;
+ goto restart;
}
/* The first skb to collapse is:
*/
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 &&
- TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb->next)->seq)))
+ before(TCP_SKB_CB(skb)->seq, start))) {
+ end_of_skbs = false;
break;
+ }
+
+ if (!skb_queue_is_last(list, skb)) {
+ struct sk_buff *next = skb_queue_next(list, skb);
+ if (next != tail &&
+ TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) {
+ end_of_skbs = false;
+ break;
+ }
+ }
/* Decided to skip this, advance start seq. */
start = TCP_SKB_CB(skb)->end_seq;
- skb = skb->next;
}
- if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
+ if (end_of_skbs || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
return;
while (before(start, end)) {
memcpy(nskb->head, skb->head, header);
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, list);
+ __skb_queue_before(list, skb, nskb);
skb_set_owner_r(nskb, sk);
/* Copy data, releasing collapsed skbs. */
}
if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
skb = tcp_collapse_one(sk, skb, list);
- if (skb == tail ||
+ if (!skb ||
+ skb == tail ||
tcp_hdr(skb)->syn ||
tcp_hdr(skb)->fin)
return;
head = skb;
for (;;) {
- skb = skb->next;
+ struct sk_buff *next = NULL;
+
+ if (!skb_queue_is_last(&tp->out_of_order_queue, skb))
+ next = skb_queue_next(&tp->out_of_order_queue, skb);
+ skb = next;
/* Segment is terminated when we see gap or when
* we are at the end of all the queue. */
- if (skb == (struct sk_buff *)&tp->out_of_order_queue ||
+ if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
tcp_collapse(sk, &tp->out_of_order_queue,
head, skb, start, end);
head = skb;
- if (skb == (struct sk_buff *)&tp->out_of_order_queue)
+ if (!skb)
break;
/* Start new segment */
start = TCP_SKB_CB(skb)->seq;
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tcp_collapse_ofo_queue(sk);
- 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);
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ tcp_collapse(sk, &sk->sk_receive_queue,
+ skb_peek(&sk->sk_receive_queue),
+ NULL,
+ tp->copied_seq, tp->rcv_nxt);
sk_mem_reclaim(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
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,
+ MAX_TCP_HEADER + 16 + sizeof(struct sk_buff);
+ int demanded = max_t(unsigned int, tp->snd_cwnd,
tp->reordering + 1);
sndmem *= 2 * demanded;
if (sndmem > sk->sk_sndbuf)
struct tcp_sock *tp = tcp_sk(sk);
/* More than one full frame received... */
- if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_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) ||
+ __tcp_select_window(sk) >= tp->rcv_wnd) ||
/* We ACK each frame or... */
tcp_in_quickack_mode(sk) ||
/* We have out of order data. */
return 0;
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = get_softnet_dma();
+ tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, int syn_inerr)
{
+ u8 *hash_location;
struct tcp_sock *tp = tcp_sk(sk);
/* RFC1323: H1. Apply PAWS check first. */
- if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
+ if (tcp_fast_parse_options(skb, th, tp, &hash_location) &&
+ tp->rx_opt.saw_tstamp &&
tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
*/
if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
- TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
+ TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
+ !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
int tcp_header_len = tp->tcp_header_len;
/* Timestamp header prediction: tcp_header_len
/* Check timestamp */
if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
- __be32 *ptr = (__be32 *)(th + 1);
-
/* No? Slow path! */
- if (*ptr != htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
- | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP))
+ if (!tcp_parse_aligned_timestamp(tp, th))
goto slow_path;
- tp->rx_opt.saw_tstamp = 1;
- ++ptr;
- tp->rx_opt.rcv_tsval = ntohl(*ptr);
- ++ptr;
- tp->rx_opt.rcv_tsecr = ntohl(*ptr);
-
/* If PAWS failed, check it more carefully in slow path */
if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0)
goto slow_path;
goto no_ack;
}
- __tcp_ack_snd_check(sk, 0);
+ if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
+ __tcp_ack_snd_check(sk, 0);
no_ack:
#ifdef CONFIG_NET_DMA
if (copied_early)
return -res;
step5:
- if (th->ack)
- tcp_ack(sk, skb, FLAG_SLOWPATH);
+ if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
+ goto discard;
tcp_rcv_rtt_measure_ts(sk, skb);
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
{
- struct tcp_sock *tp = tcp_sk(sk);
+ u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_cookie_values *cvp = tp->cookie_values;
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, 0);
+ tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
if (th->ack) {
/* rfc793:
* never scaled.
*/
tp->snd_wnd = ntohs(th->window);
- tcp_init_wl(tp, TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(skb)->seq);
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
if (!tp->rx_opt.wscale_ok) {
tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0;
* Change state from SYN-SENT only after copied_seq
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
+
+ if (cvp != NULL &&
+ cvp->cookie_pair_size > 0 &&
+ tp->rx_opt.cookie_plus > 0) {
+ int cookie_size = tp->rx_opt.cookie_plus
+ - TCPOLEN_COOKIE_BASE;
+ int cookie_pair_size = cookie_size
+ + cvp->cookie_desired;
+
+ /* A cookie extension option was sent and returned.
+ * Note that each incoming SYNACK replaces the
+ * Responder cookie. The initial exchange is most
+ * fragile, as protection against spoofing relies
+ * entirely upon the sequence and timestamp (above).
+ * This replacement strategy allows the correct pair to
+ * pass through, while any others will be filtered via
+ * Responder verification later.
+ */
+ if (sizeof(cvp->cookie_pair) >= cookie_pair_size) {
+ memcpy(&cvp->cookie_pair[cvp->cookie_desired],
+ hash_location, cookie_size);
+ cvp->cookie_pair_size = cookie_pair_size;
+ }
+ }
+
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
/* PAWS check. */
if (tp->rx_opt.ts_recent_stamp && tp->rx_opt.saw_tstamp &&
- tcp_paws_check(&tp->rx_opt, 0))
+ tcp_paws_reject(&tp->rx_opt, 0))
goto discard_and_undo;
if (th->syn) {
/* step 5: check the ACK field */
if (th->ack) {
- int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH);
+ int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;
switch (sk->sk_state) {
case TCP_SYN_RECV:
tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
tp->snd_wnd = ntohs(th->window) <<
tp->rx_opt.snd_wscale;
- tcp_init_wl(tp, TCP_SKB_CB(skb)->ack_seq,
- TCP_SKB_CB(skb)->seq);
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
/* tcp_ack considers this ACK as duplicate
* and does not calculate rtt.