#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>
* 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)
-{
+ /* NOTE: clamping at TCP_RTO_MIN is not required, current algo
+ * guarantees that rto is higher.
+ */
if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
}
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,
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);
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
return in_sack;
}
-static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
- int *reord, int dup_sack, int fack_count,
- u8 *sackedto, int pcount)
+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) {
- *sackedto &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
+ sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
tp->lost_out -= pcount;
tp->retrans_out -= pcount;
}
*/
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) {
- *sackedto &= ~TCPCB_LOST;
+ sacked &= ~TCPCB_LOST;
tp->lost_out -= pcount;
}
}
- *sackedto |= TCPCB_SACKED_ACKED;
- flag |= FLAG_DATA_SACKED;
+ sacked |= TCPCB_SACKED_ACKED;
+ state->flag |= FLAG_DATA_SACKED;
tp->sacked_out += pcount;
fack_count += pcount;
* frames and clear it. undo_retrans is decreased above, L|R frames
* are accounted above as well.
*/
- if (dup_sack && (*sackedto & TCPCB_SACKED_RETRANS)) {
- *sackedto &= ~TCPCB_SACKED_RETRANS;
+ 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 *prev,
- struct sk_buff *skb, unsigned int pcount,
- int shifted, int fack_count, int *reord,
- int *flag, int mss)
+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);
- u8 dummy_sacked = TCP_SKB_CB(skb)->sacked; /* We discard results */
+ struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
BUG_ON(!pcount);
skb_shinfo(skb)->gso_type = 0;
}
- *flag |= tcp_sacktag_one(skb, sk, reord, 0, fack_count, &dummy_sacked,
- pcount);
+ /* 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);
/* I wish gso_size would have a bit more sane initialization than
* something-or-zero which complicates things
*/
-static int tcp_shift_mss(struct sk_buff *skb)
+static int tcp_skb_seglen(struct sk_buff *skb)
{
- int mss = tcp_skb_mss(skb);
-
- if (!mss)
- mss = skb->len;
-
- return mss;
+ return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb);
}
/* Shifting pages past head area doesn't work */
* 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, int *fack_count,
- int *reord, int *flag)
+ int dup_sack)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *prev;
/* Normally R but no L won't result in plain S */
if (!dup_sack &&
- (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) == TCPCB_SACKED_RETRANS)
+ (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS)
goto fallback;
if (!skb_can_shift(skb))
goto fallback;
if (in_sack) {
len = skb->len;
pcount = tcp_skb_pcount(skb);
- mss = tcp_shift_mss(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_shift_mss(prev))
+ if (mss != tcp_skb_seglen(prev))
goto fallback;
} else {
if (!after(TCP_SKB_CB(skb)->end_seq, start_seq))
/* TODO: Fix DSACKs to not fragment already SACKed and we can
* drop this restriction as unnecessary
*/
- if (mss != tcp_shift_mss(prev))
+ if (mss != tcp_skb_seglen(prev))
goto fallback;
if (len == mss) {
if (!skb_shift(prev, skb, len))
goto fallback;
- if (!tcp_shifted_skb(sk, prev, skb, pcount, len, *fack_count, reord,
- flag, mss))
+ 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
goto out;
skb = tcp_write_queue_next(sk, prev);
- if (!skb_can_shift(skb))
- goto out;
- if (skb == tcp_send_head(sk))
- goto out;
- if ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
+ 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, prev, skb, tcp_skb_pcount(skb), len,
- *fack_count, reord, flag, mss);
+ tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
}
out:
- *fack_count += pcount;
+ state->fack_count += pcount;
return prev;
noop:
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;
* so not even _safe variant of the loop is enough.
*/
if (in_sack <= 0) {
- tmp = tcp_shift_skb_data(sk, skb, start_seq,
- end_seq, dup_sack,
- fack_count, reord, flag);
+ tmp = tcp_shift_skb_data(sk, skb, state,
+ start_seq, end_seq, dup_sack);
if (tmp != NULL) {
if (tmp != skb) {
skb = tmp;
break;
if (in_sack) {
- *flag |= tcp_sacktag_one(skb, sk, reord, dup_sack,
- *fack_count,
- &(TCP_SKB_CB(skb)->sacked),
- tcp_skb_pcount(skb));
+ TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk,
+ state,
+ dup_sack,
+ tcp_skb_pcount(skb));
if (!before(TCP_SKB_CB(skb)->seq,
tcp_highest_sack_seq(tp)))
tcp_advance_highest_sack(sk, skb);
}
- *fack_count += tcp_skb_pcount(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))
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
return 0;
}
+/* 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_timeout_skbs(struct sock *sk)
+{
+ 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
* is against sacked "cnt", otherwise it's against facked "cnt"
*/
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;
-
- tcp_skb_mark_lost(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
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);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- unsigned int mss = tcp_current_mss(sk, 0);
+ 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 (skb->len > mss &&
+ 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;
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,
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) {
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);
- /* No need to care for underflows here because
- * the lost_skb_hint gets NULLed if we're past it
- * (or something non-trivial happened)
- */
- if (tcp_is_fack(tp))
- tp->lost_cnt_hint -= pkts_acked;
- else
- tp->lost_cnt_hint -= prior_sacked - tp->sacked_out;
+ 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;
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;
}
* 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;
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)) {
*/
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
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);
* 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;
/* 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.
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff