*/
#include <linux/mm.h>
+#include <linux/slab.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;
+EXPORT_SYMBOL(sysctl_tcp_reordering);
+int sysctl_tcp_ecn __read_mostly = 2;
+EXPORT_SYMBOL(sysctl_tcp_ecn);
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 2;
+EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_nometrics_save __read_mostly;
+int sysctl_tcp_thin_dupack __read_mostly;
+
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_abc __read_mostly;
* "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
icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
}
-void tcp_enter_quickack_mode(struct sock *sk)
+static void tcp_enter_quickack_mode(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_incr_quickack(sk);
tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}
-static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
+static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
{
- if (tp->ecn_flags & TCP_ECN_OK) {
- if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags))
- tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ if (!(tp->ecn_flags & TCP_ECN_OK))
+ return;
+
+ switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
+ case INET_ECN_NOT_ECT:
/* 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)))
+ * and we already seen ECT on a previous segment,
+ * it is probably a retransmit.
+ */
+ if (tp->ecn_flags & TCP_ECN_SEEN)
tcp_enter_quickack_mode((struct sock *)tp);
+ break;
+ case INET_ECN_CE:
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ /* fallinto */
+ default:
+ tp->ecn_flags |= TCP_ECN_SEEN;
}
}
int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 +
sizeof(struct sk_buff);
- if (sk->sk_sndbuf < 3 * sndmem)
- sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]);
+ if (sk->sk_sndbuf < 3 * sndmem) {
+ sk->sk_sndbuf = 3 * sndmem;
+ if (sk->sk_sndbuf > sysctl_tcp_wmem[2])
+ sk->sk_sndbuf = sysctl_tcp_wmem[2];
+ }
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
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]) {
+ atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
sysctl_tcp_rmem[2]);
}
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;
}
+EXPORT_SYMBOL(tcp_initialize_rcv_mss);
/* Receiver "autotuning" code.
*
* The algorithm for RTT estimation w/o timestamps is based on
* Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL.
- * <http://www.lanl.gov/radiant/website/pubs/drs/lacsi2001.ps>
+ * <http://public.lanl.gov/radiant/pubs.html#DRS>
*
* More detail on this code can be found at
- * <http://www.psc.edu/~jheffner/senior_thesis.ps>,
+ * <http://staff.psc.edu/jheffner/>,
* though this reference is out of date. A new paper
* is pending.
*/
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.
* Reset our results.
*/
if (!(dst_metric_locked(dst, RTAX_RTT)))
- dst->metrics[RTAX_RTT - 1] = 0;
+ dst_metric_set(dst, RTAX_RTT, 0);
return;
}
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->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
- dst->metrics[RTAX_SSTHRESH-1] = tp->snd_cwnd >> 1;
+ dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1);
if (!dst_metric_locked(dst, RTAX_CWND) &&
tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
- dst->metrics[RTAX_CWND - 1] = tp->snd_cwnd;
+ dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd);
} else if (tp->snd_cwnd > tp->snd_ssthresh &&
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] =
- max(tp->snd_cwnd >> 1, tp->snd_ssthresh);
+ dst_metric_set(dst, RTAX_SSTHRESH,
+ max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
if (!dst_metric_locked(dst, RTAX_CWND))
- dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_cwnd) >> 1;
+ dst_metric_set(dst, RTAX_CWND,
+ (dst_metric(dst, RTAX_CWND) +
+ tp->snd_cwnd) >> 1);
} else {
/* Else slow start did not finish, cwnd is non-sense,
ssthresh may be also invalid.
*/
if (!dst_metric_locked(dst, RTAX_CWND))
- dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_ssthresh) >> 1;
+ dst_metric_set(dst, RTAX_CWND,
+ (dst_metric(dst, RTAX_CWND) +
+ tp->snd_ssthresh) >> 1);
if (dst_metric(dst, RTAX_SSTHRESH) &&
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
- dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh;
+ dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh);
}
if (!dst_metric_locked(dst, RTAX_REORDERING)) {
if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
tp->reordering != sysctl_tcp_reordering)
- dst->metrics[RTAX_REORDERING-1] = tp->reordering;
+ dst_metric_set(dst, RTAX_REORDERING, tp->reordering);
}
}
}
-/* 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 > 1460)
- cwnd = 2;
- else
- cwnd = (tp->mss_cache > 1095) ? 3 : 4;
- }
+ if (!cwnd)
+ cwnd = TCP_INIT_CWND;
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
tp->snd_ssthresh = tp->snd_cwnd_clamp;
+ } else {
+ /* ssthresh may have been reduced unnecessarily during.
+ * 3WHS. Restore it back to its initial default.
+ */
+ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
}
if (dst_metric(dst, RTAX_REORDERING) &&
tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
tp->reordering = dst_metric(dst, RTAX_REORDERING);
}
- if (dst_metric(dst, RTAX_RTT) == 0)
- goto reset;
-
- if (!tp->srtt && dst_metric_rtt(dst, RTAX_RTT) < (TCP_TIMEOUT_INIT << 3))
+ if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0)
goto reset;
/* Initial rtt is determined from SYN,SYN-ACK.
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;
- tp->snd_cwnd = tcp_init_cwnd(tp, dst);
- tp->snd_cwnd_stamp = tcp_time_stamp;
- return;
-
reset:
- /* Play conservative. If timestamps are not
- * supported, TCP will fail to recalculate correct
- * rtt, if initial rto is too small. FORGET ALL AND RESET!
- */
- if (!tp->rx_opt.saw_tstamp && tp->srtt) {
- tp->srtt = 0;
- tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
- inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
+ if (tp->srtt == 0) {
+ /* RFC2988bis: We've failed to get a valid RTT sample from
+ * 3WHS. This is most likely due to retransmission,
+ * including spurious one. Reset the RTO back to 3secs
+ * from the more aggressive 1sec to avoid more spurious
+ * retransmission.
+ */
+ tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
+ inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
}
+ /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
+ * retransmitted. In light of RFC2988bis' more aggressive 1sec
+ * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
+ * retransmission has occurred.
+ */
+ if (tp->total_retrans > 1)
+ tp->snd_cwnd = 1;
+ else
+ tp->snd_cwnd = tcp_init_cwnd(tp, dst);
+ tp->snd_cwnd_stamp = tcp_time_stamp;
}
static void tcp_update_reordering(struct sock *sk, const int metric,
return 0;
/* ...Then it's D-SACK, and must reside below snd_una completely */
- if (!after(end_seq, tp->snd_una))
+ if (after(end_seq, tp->snd_una))
return 0;
if (!before(start_seq, tp->undo_marker))
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);
}
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack &&
+ if (dup_sack && tp->undo_marker && tp->undo_retrans &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
tp->undo_retrans--;
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
- if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
+ if (tp->undo_marker && tp->undo_retrans &&
+ after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
state->reord = min(fack_count, state->reord);
return sacked;
}
-static int tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
- struct sk_buff *skb,
+static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
struct tcp_sacktag_state *state,
- unsigned int pcount, int shifted, int mss)
+ 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))
+ if (skb == tp->lost_skb_hint)
tp->lost_cnt_hint += pcount;
TCP_SKB_CB(prev)->end_seq += shifted;
}
/* We discard results */
- tcp_sacktag_one(skb, sk, state, 0, pcount);
+ 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);
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
}
- TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags;
+ TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
if (!skb_shift(prev, skb, len))
goto fallback;
- if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, 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
len = skb->len;
if (skb_shift(prev, skb, len)) {
pcount += tcp_skb_pcount(skb);
- tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb), len,
- mss);
+ tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
}
out:
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)
* 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;
}
static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb)
{
- return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
+ return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto;
}
static inline int tcp_head_timedout(struct sock *sk)
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 1;
}
+ /* If a thin stream is detected, retransmit after first
+ * received dupack. Employ only if SACK is supported in order
+ * to avoid possible corner-case series of spurious retransmissions
+ * Use only if there are no unsent data.
+ */
+ if ((tp->thin_dupack || sysctl_tcp_thin_dupack) &&
+ tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 &&
+ tcp_is_sack(tp) && !tcp_send_head(sk))
+ return 1;
+
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"
*/
-static void tcp_mark_head_lost(struct sock *sk, int packets)
+static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
if (tp->lost_skb_hint) {
skb = tp->lost_skb_hint;
cnt = tp->lost_cnt_hint;
+ /* Head already handled? */
+ if (mark_head && skb != tcp_write_queue_head(sk))
+ return;
} else {
skb = tcp_write_queue_head(sk);
cnt = 0;
cnt += tcp_skb_pcount(skb);
if (cnt > packets) {
- if (tcp_is_sack(tp) || (oldcnt >= packets))
+ if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+ (oldcnt >= packets))
break;
mss = skb_shinfo(skb)->gso_size;
}
tcp_skb_mark_lost(tp, skb);
+
+ if (mark_head)
+ break;
}
tcp_verify_left_out(tp);
}
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_is_reno(tp)) {
- tcp_mark_head_lost(sk, 1);
+ tcp_mark_head_lost(sk, 1, 1);
} else if (tcp_is_fack(tp)) {
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, lost);
+ tcp_mark_head_lost(sk, lost, 0);
} else {
int sacked_upto = tp->sacked_out - tp->reordering;
- if (sacked_upto < fast_rexmit)
- sacked_upto = fast_rexmit;
- tcp_mark_head_lost(sk, sacked_upto);
+ if (sacked_upto >= 0)
+ tcp_mark_head_lost(sk, sacked_upto, 0);
+ else if (fast_rexmit)
+ tcp_mark_head_lost(sk, 1, 1);
}
- /* 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
if (sk->sk_family == AF_INET) {
printk(KERN_DEBUG "Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n",
msg,
- &inet->daddr, ntohs(inet->dport),
+ &inet->inet_daddr, ntohs(inet->inet_dport),
tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
struct ipv6_pinfo *np = inet6_sk(sk);
printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
msg,
- &np->daddr, ntohs(inet->dport),
+ &np->daddr, ntohs(inet->inet_dport),
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 sock *sk, const int undo)
+static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
{
struct tcp_sock *tp = tcp_sk(sk);
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);
- if (undo && tp->prior_ssthresh > tp->snd_ssthresh) {
+ if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) {
tp->snd_ssthresh = tp->prior_ssthresh;
TCP_ECN_withdraw_cwr(tp);
}
} else {
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
- tcp_moderate_cwnd(tp);
tp->snd_cwnd_stamp = tcp_time_stamp;
}
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
if (tp->undo_marker && !tp->undo_retrans) {
DBGUNDO(sk, "D-SACK");
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
tp->undo_marker = 0;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
}
}
+/* 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);
DBGUNDO(sk, "Hoe");
- tcp_undo_cwr(sk, 0);
+ tcp_undo_cwr(sk, false);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
/* So... Do not make Hoe's retransmit yet.
DBGUNDO(sk, "partial loss");
tp->lost_out = 0;
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
inet_csk(sk)->icsk_retransmits = 0;
tp->undo_marker = 0;
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;
+
+ /* Do not moderate cwnd if it's already undone in cwr or recovery. */
+ if (tp->undo_marker) {
+ if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR)
+ tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
+ else /* PRR */
+ tp->snd_cwnd = tp->snd_ssthresh;
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ }
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
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);
icsk->icsk_mtup.probe_size;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
- tp->rcv_ssthresh = tcp_current_ssthresh(sk);
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size;
icsk->icsk_mtup.probe_size = 0;
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) {
}
tcp_xmit_retransmit_queue(sk);
}
+EXPORT_SYMBOL(tcp_simple_retransmit);
+
+/* This function implements the PRR algorithm, specifcally the PRR-SSRB
+ * (proportional rate reduction with slow start reduction bound) as described in
+ * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt.
+ * It computes the number of packets to send (sndcnt) based on packets newly
+ * delivered:
+ * 1) If the packets in flight is larger than ssthresh, PRR spreads the
+ * cwnd reductions across a full RTT.
+ * 2) If packets in flight is lower than ssthresh (such as due to excess
+ * losses and/or application stalls), do not perform any further cwnd
+ * reductions, but instead slow start up to ssthresh.
+ */
+static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked,
+ int fast_rexmit, int flag)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int sndcnt = 0;
+ int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);
+
+ if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) {
+ u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
+ tp->prior_cwnd - 1;
+ sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
+ } else {
+ sndcnt = min_t(int, delta,
+ max_t(int, tp->prr_delivered - tp->prr_out,
+ newly_acked_sacked) + 1);
+ }
+
+ sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0));
+ tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt;
+}
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
-static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag)
+static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
+ int newly_acked_sacked, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
before(tp->snd_una, tp->high_seq) &&
icsk->icsk_ca_state != TCP_CA_Open &&
tp->fackets_out > tp->reordering) {
- tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering);
+ tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering, 0);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSS);
}
tp->bytes_acked = 0;
tp->snd_cwnd_cnt = 0;
+ tp->prior_cwnd = tp->snd_cwnd;
+ tp->prr_delivered = 0;
+ tp->prr_out = 0;
tcp_set_ca_state(sk, TCP_CA_Recovery);
fast_rexmit = 1;
}
if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk)))
tcp_update_scoreboard(sk, fast_rexmit);
- tcp_cwnd_down(sk, flag);
+ tp->prr_delivered += newly_acked_sacked;
+ tcp_update_cwnd_in_recovery(sk, newly_acked_sacked, fast_rexmit, flag);
tcp_xmit_retransmit_queue(sk);
}
+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;
+}
+EXPORT_SYMBOL(tcp_valid_rtt_meas);
+
/* 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) {
* connection startup slow start one packet too
* quickly. This is severely frowned upon behavior.
*/
- if (!(scb->flags & TCPCB_FLAG_SYN)) {
+ if (!(scb->tcp_flags & TCPHDR_SYN)) {
flag |= FLAG_DATA_ACKED;
} else {
flag |= FLAG_SYN_ACKED;
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);
net_invalid_timestamp()))
rtt_us = ktime_us_delta(ktime_get_real(),
last_ackt);
- else if (ca_seq_rtt > 0)
+ else if (ca_seq_rtt >= 0)
rtt_us = jiffies_to_usecs(ca_seq_rtt);
}
static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag)
{
- return (!(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
- inet_csk(sk)->icsk_ca_state != TCP_CA_Open);
+ return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
+ inet_csk(sk)->icsk_ca_state != TCP_CA_Open;
}
static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag)
const u32 ack, const u32 ack_seq,
const u32 nwin)
{
- return (after(ack, tp->snd_una) ||
+ return after(ack, tp->snd_una) ||
after(ack_seq, tp->snd_wl1) ||
- (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd));
+ (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
}
/* Update our send window.
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;
if (flag & FLAG_ECE)
tcp_ratehalving_spur_to_response(sk);
else
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
}
/* F-RTO spurious RTO detection algorithm (RFC4138)
u32 prior_in_flight;
u32 prior_fackets;
int prior_packets;
+ int prior_sacked = tp->sacked_out;
+ int newly_acked_sacked = 0;
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;
/* See if we can take anything off of the retransmit queue. */
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
+ newly_acked_sacked = (prior_packets - prior_sacked) -
+ (tp->packets_out - tp->sacked_out);
+
if (tp->frto_counter)
frto_cwnd = tcp_process_frto(sk, flag);
/* Guarantee sacktag reordering detection against wrap-arounds */
tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
tcp_fastretrans_alert(sk, prior_packets - tp->packets_out,
- flag);
+ newly_acked_sacked, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
tcp_cong_avoid(sk, ack, prior_in_flight);
}
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
- dst_confirm(sk->sk_dst_cache);
+ dst_confirm(__sk_dst_get(sk));
return 1;
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;
+ break;
+ default:
+ /* ignore option */
+ break;
+ }
+ break;
}
ptr += opsize-2;
}
}
}
+EXPORT_SYMBOL(tcp_parse_options);
static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
{
* 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)) {
+ 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;
}
if (opsize < 2 || opsize > length)
return NULL;
if (opcode == TCPOPT_MD5SIG)
- return ptr;
+ return opsize == TCPOLEN_MD5SIG ? ptr : NULL;
}
ptr += opsize - 2;
length -= opsize;
}
return NULL;
}
+EXPORT_SYMBOL(tcp_parse_md5sig_option);
#endif
static inline void tcp_store_ts_recent(struct tcp_sock *tp)
* 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.
default:
sk->sk_err = ECONNRESET;
}
+ /* This barrier is coupled with smp_rmb() in tcp_poll() */
+ smp_wmb();
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_error_report(sk);
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
}
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
- SOCK_DEBUG(sk, "ofo packet was already received \n");
+ SOCK_DEBUG(sk, "ofo packet was already received\n");
__skb_unlink(skb, &tp->out_of_order_queue);
__kfree_skb(skb);
continue;
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
goto drop;
+ skb_dst_drop(skb);
__skb_pull(skb, th->doff * 4);
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.
if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) {
tp->ucopy.len -= chunk;
tp->copied_seq += chunk;
- eaten = (chunk == skb->len && !th->fin);
+ eaten = (chunk == skb->len);
tcp_rcv_space_adjust(sk);
}
local_bh_disable();
/* 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_queue_after(&tp->out_of_order_queue, skb1, skb);
+ 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)) {
}
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)
return 0;
/* If we are under soft global TCP memory pressure, do not expand. */
- if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+ if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
return 0;
/* If we filled the congestion window, do not expand. */
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
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);
__kfree_skb(skb);
return 0;
}
+EXPORT_SYMBOL(tcp_rcv_established);
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_ack considers this ACK as duplicate
- * and does not calculate rtt.
- * Fix it at least with timestamps.
- */
- if (tp->rx_opt.saw_tstamp &&
- tp->rx_opt.rcv_tsecr && !tp->srtt)
- tcp_ack_saw_tstamp(sk, 0);
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
if (tp->snd_una == tp->write_seq) {
tcp_set_state(sk, TCP_FIN_WAIT2);
sk->sk_shutdown |= SEND_SHUTDOWN;
- dst_confirm(sk->sk_dst_cache);
+ dst_confirm(__sk_dst_get(sk));
if (!sock_flag(sk, SOCK_DEAD))
/* Wake up lingering close() */
}
return 0;
}
-
-EXPORT_SYMBOL(sysctl_tcp_ecn);
-EXPORT_SYMBOL(sysctl_tcp_reordering);
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-EXPORT_SYMBOL(tcp_parse_options);
-#ifdef CONFIG_TCP_MD5SIG
-EXPORT_SYMBOL(tcp_parse_md5sig_option);
-#endif
-EXPORT_SYMBOL(tcp_rcv_established);
EXPORT_SYMBOL(tcp_rcv_state_process);
-EXPORT_SYMBOL(tcp_initialize_rcv_mss);
Code Review / linux-3.10.git / blobdiff