int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_frto __read_mostly;
+int sysctl_tcp_frto __read_mostly = 2;
int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_nometrics_save __read_mostly;
#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
+#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
+#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained DSACK info */
+#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE)
#define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED)
-
-#define IsReno(tp) ((tp)->rx_opt.sack_ok == 0)
-#define IsFack(tp) ((tp)->rx_opt.sack_ok & 2)
-#define IsDSack(tp) ((tp)->rx_opt.sack_ok & 4)
+#define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
#define IsSackFrto() (sysctl_tcp_frto == 0x2)
#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
+#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))
/* Adapt the MSS value used to make delayed ack decision to the
* real world.
*
* "len" is invariant segment length, including TCP header.
*/
- len += skb->data - skb->h.raw;
+ len += skb->data - skb_transport_header(skb);
if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
/* If PSH is not set, packet should be
* full sized, provided peer TCP is not badly broken.
* to handle super-low mtu links fairly.
*/
(len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
- !(tcp_flag_word(skb->h.th)&TCP_REMNANT))) {
+ !(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) {
/* Subtract also invariant (if peer is RFC compliant),
* tcp header plus fixed timestamp option length.
* Resulting "len" is MSS free of SACK jitter.
return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong;
}
+static inline void TCP_ECN_queue_cwr(struct tcp_sock *tp)
+{
+ if (tp->ecn_flags&TCP_ECN_OK)
+ tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
+}
+
+static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, struct sk_buff *skb)
+{
+ if (tcp_hdr(skb)->cwr)
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp)
+{
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
+{
+ if (tp->ecn_flags&TCP_ECN_OK) {
+ if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags))
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ /* Funny extension: if ECT is not set on a segment,
+ * it is surely retransmit. It is not in ECN RFC,
+ * but Linux follows this rule. */
+ else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags)))
+ tcp_enter_quickack_mode((struct sock *)tp);
+ }
+}
+
+static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, struct tcphdr *th)
+{
+ if ((tp->ecn_flags&TCP_ECN_OK) && (!th->ece || th->cwr))
+ tp->ecn_flags &= ~TCP_ECN_OK;
+}
+
+static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, struct tcphdr *th)
+{
+ if ((tp->ecn_flags&TCP_ECN_OK) && (!th->ece || !th->cwr))
+ tp->ecn_flags &= ~TCP_ECN_OK;
+}
+
+static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th)
+{
+ if (th->ece && !th->syn && (tp->ecn_flags&TCP_ECN_OK))
+ return 1;
+ return 0;
+}
+
/* Buffer size and advertised window tuning.
*
* 1. Tuning sk->sk_sndbuf, when connection enters established state.
*/
/* Slow part of check#2. */
-static int __tcp_grow_window(const struct sock *sk, struct tcp_sock *tp,
- const struct sk_buff *skb)
+static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(skb->truesize)/2;
int window = tcp_win_from_space(sysctl_tcp_rmem[2])/2;
return 0;
}
-static void tcp_grow_window(struct sock *sk, struct tcp_sock *tp,
+static void tcp_grow_window(struct sock *sk,
struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
if (tcp_win_from_space(skb->truesize) <= skb->len)
incr = 2*tp->advmss;
else
- incr = __tcp_grow_window(sk, tp, skb);
+ incr = __tcp_grow_window(sk, skb);
if (incr) {
tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp);
}
/* 5. Recalculate window clamp after socket hit its memory bounds. */
-static void tcp_clamp_window(struct sock *sk, struct tcp_sock *tp)
+static void tcp_clamp_window(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_ack.quick = 0;
* each ACK we send, he increments snd_cwnd and transmits more of his
* queue. -DaveM
*/
-static void tcp_event_data_recv(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
u32 now;
TCP_ECN_check_ce(tp, skb);
if (skb->len >= 128)
- tcp_grow_window(sk, tp, skb);
+ tcp_grow_window(sk, skb);
+}
+
+static u32 tcp_rto_min(struct sock *sk)
+{
+ struct dst_entry *dst = __sk_dst_get(sk);
+ u32 rto_min = TCP_RTO_MIN;
+
+ if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
+ rto_min = dst->metrics[RTAX_RTO_MIN-1];
+ return rto_min;
}
/* Called to compute a smoothed rtt estimate. The data fed to this
if (tp->mdev_max < tp->rttvar)
tp->rttvar -= (tp->rttvar-tp->mdev_max)>>2;
tp->rtt_seq = tp->snd_nxt;
- tp->mdev_max = TCP_RTO_MIN;
+ tp->mdev_max = tcp_rto_min(sk);
}
} else {
/* no previous measure. */
tp->srtt = m<<3; /* take the measured time to be rtt */
tp->mdev = m<<1; /* make sure rto = 3*rtt */
- tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN);
+ tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
tp->rtt_seq = tp->snd_nxt;
}
}
}
}
-/* Numbers are taken from RFC2414. */
+/* Numbers are taken from RFC3390.
+ *
+ * John Heffner states:
+ *
+ * The RFC specifies a window of no more than 4380 bytes
+ * unless 2*MSS > 4380. Reading the pseudocode in the RFC
+ * is a bit misleading because they use a clamp at 4380 bytes
+ * rather than use a multiplier in the relevant range.
+ */
__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)
{
__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
}
}
+/*
+ * Packet counting of FACK is based on in-order assumptions, therefore TCP
+ * disables it when reordering is detected
+ */
+static void tcp_disable_fack(struct tcp_sock *tp)
+{
+ tp->rx_opt.sack_ok &= ~2;
+}
+
+/* Take a notice that peer is sending DSACKs */
+static void tcp_dsack_seen(struct tcp_sock *tp)
+{
+ tp->rx_opt.sack_ok |= 4;
+}
+
/* Initialize metrics on socket. */
static void tcp_init_metrics(struct sock *sk)
}
if (dst_metric(dst, RTAX_REORDERING) &&
tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
- tp->rx_opt.sack_ok &= ~2;
+ tcp_disable_fack(tp);
tp->reordering = dst_metric(dst, RTAX_REORDERING);
}
/* This exciting event is worth to be remembered. 8) */
if (ts)
NET_INC_STATS_BH(LINUX_MIB_TCPTSREORDER);
- else if (IsReno(tp))
+ else if (tcp_is_reno(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPRENOREORDER);
- else if (IsFack(tp))
+ else if (tcp_is_fack(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPFACKREORDER);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSACKREORDER);
tp->sacked_out,
tp->undo_marker ? tp->undo_retrans : 0);
#endif
- /* Disable FACK yet. */
- tp->rx_opt.sack_ok &= ~2;
+ tcp_disable_fack(tp);
}
}
* for retransmitted and already SACKed segment -> reordering..
* Both of these heuristics are not used in Loss state, when we cannot
* account for retransmits accurately.
+ *
+ * SACK block validation.
+ * ----------------------
+ *
+ * SACK block range validation checks that the received SACK block fits to
+ * the expected sequence limits, i.e., it is between SND.UNA and SND.NXT.
+ * Note that SND.UNA is not included to the range though being valid because
+ * it means that the receiver is rather inconsistent with itself (reports
+ * SACK reneging when it should advance SND.UNA).
+ *
+ * Implements also blockage to start_seq wrap-around. Problem lies in the
+ * fact that though start_seq (s) is before end_seq (i.e., not reversed),
+ * there's no guarantee that it will be before snd_nxt (n). The problem
+ * happens when start_seq resides between end_seq wrap (e_w) and snd_nxt
+ * wrap (s_w):
+ *
+ * <- outs wnd -> <- wrapzone ->
+ * u e n u_w e_w s n_w
+ * | | | | | | |
+ * |<------------+------+----- TCP seqno space --------------+---------->|
+ * ...-- <2^31 ->| |<--------...
+ * ...---- >2^31 ------>| |<--------...
+ *
+ * Current code wouldn't be vulnerable but it's better still to discard such
+ * crazy SACK blocks. Doing this check for start_seq alone closes somewhat
+ * similar case (end_seq after snd_nxt wrap) as earlier reversed check in
+ * snd_nxt wrap -> snd_una region will then become "well defined", i.e.,
+ * equal to the ideal case (infinite seqno space without wrap caused issues).
+ *
+ * With D-SACK the lower bound is extended to cover sequence space below
+ * SND.UNA down to undo_marker, which is the last point of interest. Yet
+ * again, DSACK block must not to go across snd_una (for the same reason as
+ * for the normal SACK blocks, explained above). But there all simplicity
+ * ends, TCP might receive valid D-SACKs below that. As long as they reside
+ * fully below undo_marker they do not affect behavior in anyway and can
+ * therefore be safely ignored. In rare cases (which are more or less
+ * theoretical ones), the D-SACK will nicely cross that boundary due to skb
+ * fragmentation and packet reordering past skb's retransmission. To consider
+ * them correctly, the acceptable range must be extended even more though
+ * the exact amount is rather hard to quantify. However, tp->max_window can
+ * be used as an exaggerated estimate.
*/
+static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack,
+ u32 start_seq, u32 end_seq)
+{
+ /* Too far in future, or reversed (interpretation is ambiguous) */
+ if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq))
+ return 0;
+
+ /* Nasty start_seq wrap-around check (see comments above) */
+ if (!before(start_seq, tp->snd_nxt))
+ return 0;
+
+ /* In outstanding window? ...This is valid exit for DSACKs too.
+ * start_seq == snd_una is non-sensical (see comments above)
+ */
+ if (after(start_seq, tp->snd_una))
+ return 1;
+
+ if (!is_dsack || !tp->undo_marker)
+ return 0;
+
+ /* ...Then it's D-SACK, and must reside below snd_una completely */
+ if (!after(end_seq, tp->snd_una))
+ return 0;
+
+ if (!before(start_seq, tp->undo_marker))
+ return 1;
+
+ /* Too old */
+ if (!after(end_seq, tp->undo_marker))
+ return 0;
+
+ /* Undo_marker boundary crossing (overestimates a lot). Known already:
+ * start_seq < undo_marker and end_seq >= undo_marker.
+ */
+ return !before(start_seq, end_seq - tp->max_window);
+}
+
+
+static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
+ struct tcp_sack_block_wire *sp, int num_sacks,
+ u32 prior_snd_una)
+{
+ u32 start_seq_0 = ntohl(get_unaligned(&sp[0].start_seq));
+ u32 end_seq_0 = ntohl(get_unaligned(&sp[0].end_seq));
+ int dup_sack = 0;
+
+ if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
+ dup_sack = 1;
+ tcp_dsack_seen(tp);
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
+ } else if (num_sacks > 1) {
+ u32 end_seq_1 = ntohl(get_unaligned(&sp[1].end_seq));
+ u32 start_seq_1 = ntohl(get_unaligned(&sp[1].start_seq));
+
+ if (!after(end_seq_0, end_seq_1) &&
+ !before(start_seq_0, start_seq_1)) {
+ dup_sack = 1;
+ tcp_dsack_seen(tp);
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
+ }
+ }
+
+ /* D-SACK for already forgotten data... Do dumb counting. */
+ if (dup_sack &&
+ !after(end_seq_0, prior_snd_una) &&
+ after(end_seq_0, tp->undo_marker))
+ tp->undo_retrans--;
+
+ return dup_sack;
+}
+
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- unsigned char *ptr = ack_skb->h.raw + TCP_SKB_CB(ack_skb)->sacked;
+ unsigned char *ptr = (skb_transport_header(ack_skb) +
+ TCP_SKB_CB(ack_skb)->sacked);
struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
struct sk_buff *cached_skb;
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int prior_fackets;
u32 lost_retrans = 0;
int flag = 0;
- int dup_sack = 0;
+ int found_dup_sack = 0;
int cached_fack_count;
int i;
int first_sack_index;
- if (!tp->sacked_out)
+ if (!tp->sacked_out) {
tp->fackets_out = 0;
- prior_fackets = tp->fackets_out;
-
- /* Check for D-SACK. */
- if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) {
- dup_sack = 1;
- tp->rx_opt.sack_ok |= 4;
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
- } else if (num_sacks > 1 &&
- !after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) &&
- !before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) {
- dup_sack = 1;
- tp->rx_opt.sack_ok |= 4;
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
+ tp->highest_sack = tp->snd_una;
}
+ prior_fackets = tp->fackets_out;
- /* D-SACK for already forgotten data...
- * Do dumb counting. */
- if (dup_sack &&
- !after(ntohl(sp[0].end_seq), prior_snd_una) &&
- after(ntohl(sp[0].end_seq), tp->undo_marker))
- tp->undo_retrans--;
+ found_dup_sack = tcp_check_dsack(tp, ack_skb, sp,
+ num_sacks, prior_snd_una);
+ if (found_dup_sack)
+ flag |= FLAG_DSACKING_ACK;
/* Eliminate too old ACKs, but take into
* account more or less fresh ones, they can
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
+ int dup_sack = (found_dup_sack && (i == first_sack_index));
+
+ if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) {
+ if (dup_sack) {
+ if (!tp->undo_marker)
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDNOUNDO);
+ else
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDOLD);
+ } else
+ NET_INC_STATS_BH(LINUX_MIB_TCPSACKDISCARD);
+ continue;
+ }
skb = cached_skb;
fack_count = cached_fack_count;
if (fack_count > tp->fackets_out)
tp->fackets_out = fack_count;
+
+ if (after(TCP_SKB_CB(skb)->seq,
+ tp->highest_sack))
+ tp->highest_sack = TCP_SKB_CB(skb)->seq;
} else {
if (dup_sack && (sacked&TCPCB_RETRANS))
reord = min(fack_count, reord);
continue;
if ((TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) &&
after(lost_retrans, TCP_SKB_CB(skb)->ack_seq) &&
- (IsFack(tp) ||
+ (tcp_is_fack(tp) ||
!before(lost_retrans,
TCP_SKB_CB(skb)->ack_seq + tp->reordering *
tp->mss_cache))) {
}
}
- tp->left_out = tp->sacked_out + tp->lost_out;
+ tcp_verify_left_out(tp);
if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss &&
(!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
return flag;
}
-/* F-RTO can only be used if these conditions are satisfied:
- * - there must be some unsent new data
- * - the advertised window should allow sending it
- * - TCP has never retransmitted anything other than head (SACK enhanced
- * variant from Appendix B of RFC4138 is more robust here)
+/* F-RTO can only be used if TCP has never retransmitted anything other than
+ * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
*/
+static void tcp_check_reno_reordering(struct sock *sk, const int addend)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 holes;
+
+ holes = max(tp->lost_out, 1U);
+ holes = min(holes, tp->packets_out);
+
+ if ((tp->sacked_out + holes) > tp->packets_out) {
+ tp->sacked_out = tp->packets_out - holes;
+ tcp_update_reordering(sk, tp->packets_out + addend, 0);
+ }
+}
+
+/* Emulate SACKs for SACKless connection: account for a new dupack. */
+
+static void tcp_add_reno_sack(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ tp->sacked_out++;
+ tcp_check_reno_reordering(sk, 0);
+ tcp_verify_left_out(tp);
+}
+
+/* Account for ACK, ACKing some data in Reno Recovery phase. */
+
+static void tcp_remove_reno_sacks(struct sock *sk, int acked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (acked > 0) {
+ /* One ACK acked hole. The rest eat duplicate ACKs. */
+ if (acked-1 >= tp->sacked_out)
+ tp->sacked_out = 0;
+ else
+ tp->sacked_out -= acked-1;
+ }
+ tcp_check_reno_reordering(sk, acked);
+ tcp_verify_left_out(tp);
+}
+
+static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
+{
+ tp->sacked_out = 0;
+}
+
int tcp_use_frto(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- if (!sysctl_tcp_frto || !tcp_send_head(sk) ||
- after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
- tp->snd_una + tp->snd_wnd))
+ if (!sysctl_tcp_frto)
return 0;
if (IsSackFrto())
tp->undo_retrans = 0;
skb = tcp_write_queue_head(sk);
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ tp->undo_marker = 0;
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
/* Earlier loss recovery underway (see RFC4138; Appendix B).
* The last condition is necessary at least in tp->frto_counter case.
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt = 0;
- tp->sacked_out = 0;
tp->lost_out = 0;
- tp->fackets_out = 0;
tp->retrans_out = 0;
+ if (tcp_is_reno(tp))
+ tcp_reset_reno_sack(tp);
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
- cnt += tcp_skb_pcount(skb);
/*
* Count the retransmission made on RTO correctly (only when
* waiting for the first ACK and did not get it)...
*/
if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) {
- tp->retrans_out += tcp_skb_pcount(skb);
+ /* For some reason this R-bit might get cleared? */
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
+ tp->retrans_out += tcp_skb_pcount(skb);
/* ...enter this if branch just for the first segment */
flag |= FLAG_DATA_ACKED;
} else {
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ tp->undo_marker = 0;
TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
}
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
- /* Do not mark those segments lost that were
- * forward transmitted after RTO
- */
- if (!after(TCP_SKB_CB(skb)->end_seq,
- tp->frto_highmark)) {
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- }
- } else {
- tp->sacked_out += tcp_skb_pcount(skb);
- tp->fackets_out = cnt;
+ /* Don't lost mark skbs that were fwd transmitted after RTO */
+ if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) &&
+ !after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) {
+ TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ tp->lost_out += tcp_skb_pcount(skb);
}
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
- tp->undo_marker = 0;
tp->frto_counter = 0;
tp->reordering = min_t(unsigned int, tp->reordering,
tp->high_seq = tp->frto_highmark;
TCP_ECN_queue_cwr(tp);
- clear_all_retrans_hints(tp);
+ tcp_clear_retrans_hints_partial(tp);
}
void tcp_clear_retrans(struct tcp_sock *tp)
{
- tp->left_out = 0;
tp->retrans_out = 0;
tp->fackets_out = 0;
tp->bytes_acked = 0;
tcp_clear_retrans(tp);
- /* Push undo marker, if it was plain RTO and nothing
- * was retransmitted. */
- if (!how)
+ if (!how) {
+ /* Push undo marker, if it was plain RTO and nothing
+ * was retransmitted. */
tp->undo_marker = tp->snd_una;
+ tcp_clear_retrans_hints_partial(tp);
+ } else {
+ tcp_clear_all_retrans_hints(tp);
+ }
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
tp->fackets_out = cnt;
}
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
-
- clear_all_retrans_hints(tp);
+ /* Abort FRTO algorithm if one is in progress */
+ tp->frto_counter = 0;
}
static int tcp_check_sack_reneging(struct sock *sk)
static inline int tcp_fackets_out(struct tcp_sock *tp)
{
- return IsReno(tp) ? tp->sacked_out+1 : tp->fackets_out;
+ return tcp_is_reno(tp) ? tp->sacked_out+1 : tp->fackets_out;
}
static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb)
return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
}
-static inline int tcp_head_timedout(struct sock *sk, struct tcp_sock *tp)
+static inline int tcp_head_timedout(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
return tp->packets_out &&
tcp_skb_timedout(sk, tcp_write_queue_head(sk));
}
* Main question: may we further continue forward transmission
* with the same cwnd?
*/
-static int tcp_time_to_recover(struct sock *sk, struct tcp_sock *tp)
+static int tcp_time_to_recover(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
/* Do not perform any recovery during FRTO algorithm */
/* Trick#3 : when we use RFC2988 timer restart, fast
* retransmit can be triggered by timeout of queue head.
*/
- if (tcp_head_timedout(sk, tp))
+ if (tcp_head_timedout(sk))
return 1;
/* Trick#4: It is still not OK... But will it be useful to delay
packets_out = tp->packets_out;
if (packets_out <= tp->reordering &&
tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
- !tcp_may_send_now(sk, tp)) {
+ !tcp_may_send_now(sk)) {
/* We have nothing to send. This connection is limited
* either by receiver window or by application.
*/
return 0;
}
-/* If we receive more dupacks than we expected counting segments
- * in assumption of absent reordering, interpret this as reordering.
- * The only another reason could be bug in receiver TCP.
+/* RFC: This is from the original, I doubt that this is necessary at all:
+ * clear xmit_retrans hint if seq of this skb is beyond hint. How could we
+ * retransmitted past LOST markings in the first place? I'm not fully sure
+ * about undo and end of connection cases, which can cause R without L?
*/
-static void tcp_check_reno_reordering(struct sock *sk, const int addend)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- u32 holes;
-
- holes = max(tp->lost_out, 1U);
- holes = min(holes, tp->packets_out);
-
- if ((tp->sacked_out + holes) > tp->packets_out) {
- tp->sacked_out = tp->packets_out - holes;
- tcp_update_reordering(sk, tp->packets_out + addend, 0);
- }
-}
-
-/* Emulate SACKs for SACKless connection: account for a new dupack. */
-
-static void tcp_add_reno_sack(struct sock *sk)
+static void tcp_verify_retransmit_hint(struct tcp_sock *tp,
+ struct sk_buff *skb)
{
- struct tcp_sock *tp = tcp_sk(sk);
- tp->sacked_out++;
- tcp_check_reno_reordering(sk, 0);
- tcp_sync_left_out(tp);
-}
-
-/* Account for ACK, ACKing some data in Reno Recovery phase. */
-
-static void tcp_remove_reno_sacks(struct sock *sk, struct tcp_sock *tp, int acked)
-{
- if (acked > 0) {
- /* One ACK acked hole. The rest eat duplicate ACKs. */
- if (acked-1 >= tp->sacked_out)
- tp->sacked_out = 0;
- else
- tp->sacked_out -= acked-1;
- }
- tcp_check_reno_reordering(sk, acked);
- tcp_sync_left_out(tp);
-}
-
-static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
-{
- tp->sacked_out = 0;
- tp->left_out = tp->lost_out;
+ if ((tp->retransmit_skb_hint != NULL) &&
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+ tp->retransmit_skb_hint = NULL;
}
/* Mark head of queue up as lost. */
-static void tcp_mark_head_lost(struct sock *sk, struct tcp_sock *tp,
+static void tcp_mark_head_lost(struct sock *sk,
int packets, u32 high_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cnt;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
-
- /* clear xmit_retransmit_queue hints
- * if this is beyond hint */
- 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;
-
+ tcp_verify_retransmit_hint(tp, skb);
}
}
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
}
/* Account newly detected lost packet(s) */
-static void tcp_update_scoreboard(struct sock *sk, struct tcp_sock *tp)
+static void tcp_update_scoreboard(struct sock *sk)
{
- if (IsFack(tp)) {
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tcp_is_fack(tp)) {
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, tp, lost, tp->high_seq);
+ tcp_mark_head_lost(sk, lost, tp->high_seq);
} else {
- tcp_mark_head_lost(sk, tp, 1, tp->high_seq);
+ tcp_mark_head_lost(sk, 1, tp->high_seq);
}
/* New heuristics: it is possible only after we switched
* Hence, we can detect timed out packets during fast
* retransmit without falling to slow start.
*/
- if (!IsReno(tp) && tcp_head_timedout(sk, tp)) {
+ if (!tcp_is_reno(tp) && tcp_head_timedout(sk)) {
struct sk_buff *skb;
skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
-
- /* clear xmit_retrans hint */
- if (tp->retransmit_skb_hint &&
- before(TCP_SKB_CB(skb)->seq,
- TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
-
- tp->retransmit_skb_hint = NULL;
+ tcp_verify_retransmit_hint(tp, skb);
}
}
tp->scoreboard_skb_hint = skb;
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
}
}
}
/* Decrease cwnd each second ack. */
-static void tcp_cwnd_down(struct sock *sk)
+static void tcp_cwnd_down(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
int decr = tp->snd_cwnd_cnt + 1;
- tp->snd_cwnd_cnt = decr&1;
- decr >>= 1;
+ if ((flag&(FLAG_ANY_PROGRESS|FLAG_DSACKING_ACK)) ||
+ (tcp_is_reno(tp) && !(flag&FLAG_NOT_DUP))) {
+ tp->snd_cwnd_cnt = decr&1;
+ decr >>= 1;
- if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
- tp->snd_cwnd -= decr;
+ if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
+ tp->snd_cwnd -= decr;
- tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
- tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ }
}
/* Nothing was retransmitted or returned timestamp is less
/* Undo procedures. */
#if FASTRETRANS_DEBUG > 1
-static void DBGUNDO(struct sock *sk, struct tcp_sock *tp, const char *msg)
+static void DBGUNDO(struct sock *sk, const char *msg)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
+
printk(KERN_DEBUG "Undo %s %u.%u.%u.%u/%u c%u l%u ss%u/%u p%u\n",
msg,
NIPQUAD(inet->daddr), ntohs(inet->dport),
- tp->snd_cwnd, tp->left_out,
+ tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
}
/* There is something screwy going on with the retrans hints after
an undo */
- clear_all_retrans_hints(tp);
+ tcp_clear_all_retrans_hints(tp);
}
static inline int tcp_may_undo(struct tcp_sock *tp)
}
/* People celebrate: "We love our President!" */
-static int tcp_try_undo_recovery(struct sock *sk, struct tcp_sock *tp)
+static int tcp_try_undo_recovery(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tcp_may_undo(tp)) {
/* Happy end! We did not retransmit anything
* or our original transmission succeeded.
*/
- DBGUNDO(sk, tp, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
+ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
tcp_undo_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
NET_INC_STATS_BH(LINUX_MIB_TCPFULLUNDO);
tp->undo_marker = 0;
}
- if (tp->snd_una == tp->high_seq && IsReno(tp)) {
+ if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
* is ACKed. For Reno it is MUST to prevent false
* fast retransmits (RFC2582). SACK TCP is safe. */
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
-static void tcp_try_undo_dsack(struct sock *sk, struct tcp_sock *tp)
+static void tcp_try_undo_dsack(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tp->undo_marker && !tp->undo_retrans) {
- DBGUNDO(sk, tp, "D-SACK");
+ DBGUNDO(sk, "D-SACK");
tcp_undo_cwr(sk, 1);
tp->undo_marker = 0;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKUNDO);
/* Undo during fast recovery after partial ACK. */
-static int tcp_try_undo_partial(struct sock *sk, struct tcp_sock *tp,
- int acked)
+static int tcp_try_undo_partial(struct sock *sk, int acked)
{
+ struct tcp_sock *tp = tcp_sk(sk);
/* Partial ACK arrived. Force Hoe's retransmit. */
- int failed = IsReno(tp) || tp->fackets_out>tp->reordering;
+ int failed = tcp_is_reno(tp) || tp->fackets_out>tp->reordering;
if (tcp_may_undo(tp)) {
/* Plain luck! Hole if filled with delayed
tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
- DBGUNDO(sk, tp, "Hoe");
+ DBGUNDO(sk, "Hoe");
tcp_undo_cwr(sk, 0);
NET_INC_STATS_BH(LINUX_MIB_TCPPARTIALUNDO);
}
/* Undo during loss recovery after partial ACK. */
-static int tcp_try_undo_loss(struct sock *sk, struct tcp_sock *tp)
+static int tcp_try_undo_loss(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tcp_may_undo(tp)) {
struct sk_buff *skb;
tcp_for_write_queue(skb, sk) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
}
- clear_all_retrans_hints(tp);
+ tcp_clear_all_retrans_hints(tp);
- DBGUNDO(sk, tp, "partial loss");
+ DBGUNDO(sk, "partial loss");
tp->lost_out = 0;
- tp->left_out = tp->sacked_out;
tcp_undo_cwr(sk, 1);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
inet_csk(sk)->icsk_retransmits = 0;
tp->undo_marker = 0;
- if (!IsReno(tp))
+ if (tcp_is_sack(tp))
tcp_set_ca_state(sk, TCP_CA_Open);
return 1;
}
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
-static void tcp_try_to_open(struct sock *sk, struct tcp_sock *tp, int flag)
+static void tcp_try_to_open(struct sock *sk, int flag)
{
- tp->left_out = tp->sacked_out;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ tcp_verify_left_out(tp);
if (tp->retrans_out == 0)
tp->retrans_stamp = 0;
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
int state = TCP_CA_Open;
- if (tp->left_out || tp->retrans_out || tp->undo_marker)
+ if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
state = TCP_CA_Disorder;
if (inet_csk(sk)->icsk_ca_state != state) {
}
tcp_moderate_cwnd(tp);
} else {
- tcp_cwnd_down(sk);
+ tcp_cwnd_down(sk, flag);
}
}
* tcp_xmit_retransmit_queue().
*/
static void
-tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
- int prior_packets, int flag)
+tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int is_dupack = (tp->snd_una == prior_snd_una && !(flag&FLAG_NOT_DUP));
+ int is_dupack = !(flag&(FLAG_SND_UNA_ADVANCED|FLAG_NOT_DUP));
+ int do_lost = is_dupack || ((flag&FLAG_DATA_SACKED) &&
+ (tp->fackets_out > tp->reordering));
/* Some technical things:
* 1. Reno does not count dupacks (sacked_out) automatically. */
if (!tp->packets_out)
tp->sacked_out = 0;
- /* 2. SACK counts snd_fack in packets inaccurately. */
- if (tp->sacked_out == 0)
+
+ if (WARN_ON(!tp->sacked_out && tp->fackets_out))
tp->fackets_out = 0;
/* Now state machine starts.
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, tp->fackets_out-tp->reordering, tp->high_seq);
+ tcp_mark_head_lost(sk, tp->fackets_out-tp->reordering, tp->high_seq);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}
- /* D. Synchronize left_out to current state. */
- tcp_sync_left_out(tp);
+ /* D. Check consistency of the current state. */
+ tcp_verify_left_out(tp);
/* E. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Loss:
icsk->icsk_retransmits = 0;
- if (tcp_try_undo_recovery(sk, tp))
+ if (tcp_try_undo_recovery(sk))
return;
break;
break;
case TCP_CA_Disorder:
- tcp_try_undo_dsack(sk, tp);
+ tcp_try_undo_dsack(sk);
if (!tp->undo_marker ||
/* For SACK case do not Open to allow to undo
* catching for all duplicate ACKs. */
- IsReno(tp) || tp->snd_una != tp->high_seq) {
+ tcp_is_reno(tp) || tp->snd_una != tp->high_seq) {
tp->undo_marker = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
}
break;
case TCP_CA_Recovery:
- if (IsReno(tp))
+ if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
- if (tcp_try_undo_recovery(sk, tp))
+ if (tcp_try_undo_recovery(sk))
return;
tcp_complete_cwr(sk);
break;
/* F. Process state. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
- if (prior_snd_una == tp->snd_una) {
- if (IsReno(tp) && is_dupack)
+ if (!(flag & FLAG_SND_UNA_ADVANCED)) {
+ if (tcp_is_reno(tp) && is_dupack)
tcp_add_reno_sack(sk);
- } else {
- int acked = prior_packets - tp->packets_out;
- if (IsReno(tp))
- tcp_remove_reno_sacks(sk, tp, acked);
- is_dupack = tcp_try_undo_partial(sk, tp, acked);
- }
+ } else
+ do_lost = tcp_try_undo_partial(sk, pkts_acked);
break;
case TCP_CA_Loss:
if (flag&FLAG_DATA_ACKED)
icsk->icsk_retransmits = 0;
- if (!tcp_try_undo_loss(sk, tp)) {
+ if (!tcp_try_undo_loss(sk)) {
tcp_moderate_cwnd(tp);
tcp_xmit_retransmit_queue(sk);
return;
return;
/* Loss is undone; fall through to processing in Open state. */
default:
- if (IsReno(tp)) {
- if (tp->snd_una != prior_snd_una)
+ if (tcp_is_reno(tp)) {
+ if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
if (is_dupack)
tcp_add_reno_sack(sk);
}
if (icsk->icsk_ca_state == TCP_CA_Disorder)
- tcp_try_undo_dsack(sk, tp);
+ tcp_try_undo_dsack(sk);
- if (!tcp_time_to_recover(sk, tp)) {
- tcp_try_to_open(sk, tp, flag);
+ if (!tcp_time_to_recover(sk)) {
+ tcp_try_to_open(sk, flag);
return;
}
/* Otherwise enter Recovery state */
- if (IsReno(tp))
+ if (tcp_is_reno(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERY);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERY);
tcp_set_ca_state(sk, TCP_CA_Recovery);
}
- if (is_dupack || tcp_head_timedout(sk, tp))
- tcp_update_scoreboard(sk, tp);
- tcp_cwnd_down(sk);
+ if (do_lost || tcp_head_timedout(sk))
+ tcp_update_scoreboard(sk);
+ tcp_cwnd_down(sk, flag);
tcp_xmit_retransmit_queue(sk);
}
tcp_ack_no_tstamp(sk, seq_rtt, flag);
}
-static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt,
+static void tcp_cong_avoid(struct sock *sk, u32 ack,
u32 in_flight, int good)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
- icsk->icsk_ca_ops->cong_avoid(sk, ack, rtt, in_flight, good);
+ icsk->icsk_ca_ops->cong_avoid(sk, ack, in_flight, good);
tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
}
/* Restart timer after forward progress on connection.
* RFC2988 recommends to restart timer to now+rto.
*/
-
-static void tcp_ack_packets_out(struct sock *sk, struct tcp_sock *tp)
+static void tcp_rearm_rto(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (!tp->packets_out) {
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
} else {
}
}
-static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb,
- __u32 now, __s32 *seq_rtt)
+/* If we get here, the whole TSO packet has not been acked. */
+static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- __u32 seq = tp->snd_una;
- __u32 packets_acked;
- int acked = 0;
+ u32 packets_acked;
- /* If we get here, the whole TSO packet has not been
- * acked.
- */
- BUG_ON(!after(scb->end_seq, seq));
+ BUG_ON(!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una));
packets_acked = tcp_skb_pcount(skb);
- if (tcp_trim_head(sk, skb, seq - scb->seq))
+ if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return 0;
packets_acked -= tcp_skb_pcount(skb);
if (packets_acked) {
- __u8 sacked = scb->sacked;
-
- acked |= FLAG_DATA_ACKED;
- if (sacked) {
- if (sacked & TCPCB_RETRANS) {
- if (sacked & TCPCB_SACKED_RETRANS)
- tp->retrans_out -= packets_acked;
- acked |= FLAG_RETRANS_DATA_ACKED;
- *seq_rtt = -1;
- } else if (*seq_rtt < 0)
- *seq_rtt = now - scb->when;
- if (sacked & TCPCB_SACKED_ACKED)
- tp->sacked_out -= packets_acked;
- if (sacked & TCPCB_LOST)
- tp->lost_out -= packets_acked;
- if (sacked & TCPCB_URG) {
- if (tp->urg_mode &&
- !before(seq, tp->snd_up))
- tp->urg_mode = 0;
- }
- } else if (*seq_rtt < 0)
- *seq_rtt = now - scb->when;
-
- if (tp->fackets_out) {
- __u32 dval = min(tp->fackets_out, packets_acked);
- tp->fackets_out -= dval;
- }
- tp->packets_out -= packets_acked;
-
BUG_ON(tcp_skb_pcount(skb) == 0);
- BUG_ON(!before(scb->seq, scb->end_seq));
+ BUG_ON(!before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq));
}
- return acked;
+ return packets_acked;
}
-static u32 tcp_usrtt(struct timeval *tv)
-{
- struct timeval now;
-
- do_gettimeofday(&now);
- return (now.tv_sec - tv->tv_sec) * 1000000 + (now.tv_usec - tv->tv_usec);
-}
-
-/* Remove acknowledged frames from the retransmission queue. */
-static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
+/* Remove acknowledged frames from the retransmission queue. If our packet
+ * is before the ack sequence we can discard it as it's confirmed to have
+ * arrived at the other end.
+ */
+static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb;
- __u32 now = tcp_time_stamp;
- int acked = 0;
- __s32 seq_rtt = -1;
- u32 pkts_acked = 0;
- void (*rtt_sample)(struct sock *sk, u32 usrtt)
- = icsk->icsk_ca_ops->rtt_sample;
- struct timeval tv = { .tv_sec = 0, .tv_usec = 0 };
-
- while ((skb = tcp_write_queue_head(sk)) &&
- skb != tcp_send_head(sk)) {
+ u32 now = tcp_time_stamp;
+ int fully_acked = 1;
+ int flag = 0;
+ int prior_packets = tp->packets_out;
+ s32 seq_rtt = -1;
+ ktime_t last_ackt = net_invalid_timestamp();
+
+ while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- __u8 sacked = scb->sacked;
+ u32 end_seq;
+ u32 packets_acked;
+ u8 sacked = scb->sacked;
- /* If our packet is before the ack sequence we can
- * discard it as it's confirmed to have arrived at
- * the other end.
- */
if (after(scb->end_seq, tp->snd_una)) {
- if (tcp_skb_pcount(skb) > 1 &&
- after(tp->snd_una, scb->seq))
- acked |= tcp_tso_acked(sk, skb,
- now, &seq_rtt);
- break;
- }
+ if (tcp_skb_pcount(skb) == 1 ||
+ !after(tp->snd_una, scb->seq))
+ break;
- /* Initial outgoing SYN's get put onto the write_queue
- * just like anything else we transmit. It is not
- * true data, and if we misinform our callers that
- * this ACK acks real data, we will erroneously exit
- * connection startup slow start one packet too
- * quickly. This is severely frowned upon behavior.
- */
- if (!(scb->flags & TCPCB_FLAG_SYN)) {
- acked |= FLAG_DATA_ACKED;
- ++pkts_acked;
+ packets_acked = tcp_tso_acked(sk, skb);
+ if (!packets_acked)
+ break;
+
+ fully_acked = 0;
+ end_seq = tp->snd_una;
} else {
- acked |= FLAG_SYN_ACKED;
- tp->retrans_stamp = 0;
+ packets_acked = tcp_skb_pcount(skb);
+ end_seq = scb->end_seq;
}
/* MTU probing checks */
- if (icsk->icsk_mtup.probe_size) {
- if (!after(tp->mtu_probe.probe_seq_end, TCP_SKB_CB(skb)->end_seq)) {
- tcp_mtup_probe_success(sk, skb);
- }
+ 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) {
if (sacked & TCPCB_RETRANS) {
if (sacked & TCPCB_SACKED_RETRANS)
- tp->retrans_out -= tcp_skb_pcount(skb);
- acked |= FLAG_RETRANS_DATA_ACKED;
+ tp->retrans_out -= packets_acked;
+ flag |= FLAG_RETRANS_DATA_ACKED;
seq_rtt = -1;
+ if ((flag & FLAG_DATA_ACKED) ||
+ (packets_acked > 1))
+ flag |= FLAG_NONHEAD_RETRANS_ACKED;
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
- skb_get_timestamp(skb, &tv);
+ if (fully_acked)
+ last_ackt = skb->tstamp;
}
+
if (sacked & TCPCB_SACKED_ACKED)
- tp->sacked_out -= tcp_skb_pcount(skb);
+ tp->sacked_out -= packets_acked;
if (sacked & TCPCB_LOST)
- tp->lost_out -= tcp_skb_pcount(skb);
- if (sacked & TCPCB_URG) {
- if (tp->urg_mode &&
- !before(scb->end_seq, tp->snd_up))
- tp->urg_mode = 0;
- }
+ tp->lost_out -= packets_acked;
+
+ if ((sacked & TCPCB_URG) && tp->urg_mode &&
+ !before(end_seq, tp->snd_up))
+ tp->urg_mode = 0;
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
- skb_get_timestamp(skb, &tv);
+ if (fully_acked)
+ last_ackt = skb->tstamp;
}
- tcp_dec_pcount_approx(&tp->fackets_out, skb);
- tcp_packets_out_dec(tp, skb);
+ tp->packets_out -= packets_acked;
+
+ /* Initial outgoing SYN's get put onto the write_queue
+ * just like anything else we transmit. It is not
+ * true data, and if we misinform our callers that
+ * this ACK acks real data, we will erroneously exit
+ * connection startup slow start one packet too
+ * quickly. This is severely frowned upon behavior.
+ */
+ if (!(scb->flags & TCPCB_FLAG_SYN)) {
+ flag |= FLAG_DATA_ACKED;
+ } else {
+ flag |= FLAG_SYN_ACKED;
+ tp->retrans_stamp = 0;
+ }
+
+ if (!fully_acked)
+ break;
+
tcp_unlink_write_queue(skb, sk);
sk_stream_free_skb(sk, skb);
- clear_all_retrans_hints(tp);
+ tcp_clear_all_retrans_hints(tp);
}
- if (acked&FLAG_ACKED) {
- tcp_ack_update_rtt(sk, acked, seq_rtt);
- tcp_ack_packets_out(sk, tp);
- if (rtt_sample && !(acked & FLAG_RETRANS_DATA_ACKED))
- (*rtt_sample)(sk, tcp_usrtt(&tv));
+ if (flag & FLAG_ACKED) {
+ u32 pkts_acked = prior_packets - tp->packets_out;
+ const struct tcp_congestion_ops *ca_ops
+ = inet_csk(sk)->icsk_ca_ops;
+
+ tcp_ack_update_rtt(sk, flag, seq_rtt);
+ tcp_rearm_rto(sk);
+
+ tp->fackets_out -= min(pkts_acked, tp->fackets_out);
+ /* hint's skb might be NULL but we don't need to care */
+ tp->fastpath_cnt_hint -= min_t(u32, pkts_acked,
+ tp->fastpath_cnt_hint);
+ if (tcp_is_reno(tp))
+ tcp_remove_reno_sacks(sk, pkts_acked);
+
+ if (ca_ops->pkts_acked) {
+ s32 rtt_us = -1;
+
+ /* Is the ACK triggering packet unambiguous? */
+ if (!(flag & FLAG_RETRANS_DATA_ACKED)) {
+ /* High resolution needed and available? */
+ if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
+ !ktime_equal(last_ackt,
+ net_invalid_timestamp()))
+ rtt_us = ktime_us_delta(ktime_get_real(),
+ last_ackt);
+ else if (seq_rtt > 0)
+ rtt_us = jiffies_to_usecs(seq_rtt);
+ }
- if (icsk->icsk_ca_ops->pkts_acked)
- icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked);
+ ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
+ }
}
#if FASTRETRANS_DEBUG > 0
BUG_TRAP((int)tp->sacked_out >= 0);
BUG_TRAP((int)tp->lost_out >= 0);
BUG_TRAP((int)tp->retrans_out >= 0);
- if (!tp->packets_out && tp->rx_opt.sack_ok) {
+ if (!tp->packets_out && tcp_is_sack(tp)) {
const struct inet_connection_sock *icsk = inet_csk(sk);
if (tp->lost_out) {
printk(KERN_DEBUG "Leak l=%u %d\n",
}
#endif
*seq_rtt_p = seq_rtt;
- return acked;
+ return flag;
}
static void tcp_ack_probe(struct sock *sk)
* Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
* and in FreeBSD. NetBSD's one is even worse.) is wrong.
*/
-static int tcp_ack_update_window(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb, u32 ack, u32 ack_seq)
+static int tcp_ack_update_window(struct sock *sk, struct sk_buff *skb, u32 ack,
+ u32 ack_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
int flag = 0;
- u32 nwin = ntohs(skb->h.th->window);
+ u32 nwin = ntohs(tcp_hdr(skb)->window);
- if (likely(!skb->h.th->syn))
+ if (likely(!tcp_hdr(skb)->syn))
nwin <<= tp->rx_opt.snd_wscale;
if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
* fast path is recovered for sending TCP.
*/
tp->pred_flags = 0;
- tcp_fast_path_check(sk, tp);
+ tcp_fast_path_check(sk);
if (nwin > tp->max_window) {
tp->max_window = nwin;
{
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_cnt = 0;
+ TCP_ECN_queue_cwr(tp);
tcp_moderate_cwnd(tp);
}
* algorithm is not part of the F-RTO detection algorithm
* given in RFC4138 but can be selected separately).
* Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
- * and TCP falls back to conventional RTO recovery.
+ * and TCP falls back to conventional RTO recovery. F-RTO allows overriding
+ * of Nagle, this is done using frto_counter states 2 and 3, when a new data
+ * segment of any size sent during F-RTO, state 2 is upgraded to 3.
*
* Rationale: if the RTO was spurious, new ACKs should arrive from the
* original window even after we transmit two new data segments.
* to prove that the RTO is indeed spurious. It transfers the control
* from F-RTO to the conventional RTO recovery
*/
-static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
+static int tcp_process_frto(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
/* Duplicate the behavior from Loss state (fastretrans_alert) */
if (flag&FLAG_DATA_ACKED)
inet_csk(sk)->icsk_retransmits = 0;
+ if ((flag & FLAG_NONHEAD_RETRANS_ACKED) ||
+ ((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED)))
+ tp->undo_marker = 0;
+
if (!before(tp->snd_una, tp->frto_highmark)) {
- tcp_enter_frto_loss(sk, tp->frto_counter + 1, flag);
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
return 1;
}
- if (!IsSackFrto() || IsReno(tp)) {
+ if (!IsSackFrto() || tcp_is_reno(tp)) {
/* RFC4138 shortcoming in step 2; should also have case c):
* ACK isn't duplicate nor advances window, e.g., opposite dir
* data, winupdate
*/
- if ((tp->snd_una == prior_snd_una) && (flag&FLAG_NOT_DUP) &&
- !(flag&FLAG_FORWARD_PROGRESS))
+ if (!(flag&FLAG_ANY_PROGRESS) && (flag&FLAG_NOT_DUP))
return 1;
if (!(flag&FLAG_DATA_ACKED)) {
return 1;
}
- if ((tp->frto_counter == 2) &&
+ if ((tp->frto_counter >= 2) &&
(!(flag&FLAG_FORWARD_PROGRESS) ||
((flag&FLAG_DATA_SACKED) && !(flag&FLAG_ONLY_ORIG_SACKED)))) {
/* RFC4138 shortcoming (see comment above) */
}
if (tp->frto_counter == 1) {
+ /* Sending of the next skb must be allowed or no FRTO */
+ if (!tcp_send_head(sk) ||
+ after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
+ tp->snd_una + tp->snd_wnd)) {
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3),
+ flag);
+ return 1;
+ }
+
tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
tp->frto_counter = 2;
return 1;
- } else /* frto_counter == 2 */ {
+ } else {
switch (sysctl_tcp_frto_response) {
case 2:
tcp_undo_spur_to_response(sk, flag);
default:
tcp_ratehalving_spur_to_response(sk);
break;
- };
+ }
tp->frto_counter = 0;
+ tp->undo_marker = 0;
}
return 0;
}
if (before(ack, prior_snd_una))
goto old_ack;
+ if (after(ack, prior_snd_una))
+ flag |= FLAG_SND_UNA_ADVANCED;
+
if (sysctl_tcp_abc) {
if (icsk->icsk_ca_state < TCP_CA_CWR)
tp->bytes_acked += ack - prior_snd_una;
else
NET_INC_STATS_BH(LINUX_MIB_TCPPUREACKS);
- flag |= tcp_ack_update_window(sk, tp, skb, ack, ack_seq);
+ flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);
if (TCP_SKB_CB(skb)->sacked)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- if (TCP_ECN_rcv_ecn_echo(tp, skb->h.th))
+ if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
flag |= tcp_clean_rtx_queue(sk, &seq_rtt);
if (tp->frto_counter)
- frto_cwnd = tcp_process_frto(sk, prior_snd_una, flag);
+ frto_cwnd = tcp_process_frto(sk, flag);
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
tcp_may_raise_cwnd(sk, flag))
- tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 0);
- tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag);
+ tcp_cong_avoid(sk, ack, prior_in_flight, 0);
+ tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
- tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 1);
+ tcp_cong_avoid(sk, ack, prior_in_flight, 1);
}
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag&FLAG_NOT_DUP))
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab)
{
unsigned char *ptr;
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
int length=(th->doff*4)-sizeof(struct tcphdr);
ptr = (unsigned char *)(th + 1);
opt_rx->sack_ok) {
TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
}
+ break;
#ifdef CONFIG_TCP_MD5SIG
case TCPOPT_MD5SIG:
/*
*/
break;
#endif
- };
+ }
+
ptr+=opsize-2;
length-=opsize;
- };
+ }
}
}
static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
u32 seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
__FUNCTION__, sk->sk_state);
break;
- };
+ }
/* It _is_ possible, that we have something out-of-order _after_ FIN.
* Probably, we should reset in this case. For now drop them.
*/
__skb_queue_purge(&tp->out_of_order_queue);
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
sk_stream_mem_reclaim(sk);
static void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
- if (tp->rx_opt.sack_ok && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
if (before(seq, tp->rcv_nxt))
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOLDSENT);
else
NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk);
- if (tp->rx_opt.sack_ok && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
__skb_unlink(skb, &tp->out_of_order_queue);
__skb_queue_tail(&sk->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
- if (skb->h.th->fin)
- tcp_fin(skb, sk, skb->h.th);
+ if (tcp_hdr(skb)->fin)
+ tcp_fin(skb, sk, tcp_hdr(skb));
}
}
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
struct tcp_sock *tp = tcp_sk(sk);
int eaten = -1;
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (skb->len)
- tcp_event_data_recv(sk, tp, skb);
+ tcp_event_data_recv(sk, skb);
if (th->fin)
tcp_fin(skb, sk, th);
if (tp->rx_opt.num_sacks)
tcp_sack_remove(tp);
- tcp_fast_path_check(sk, tp);
+ tcp_fast_path_check(sk);
if (eaten > 0)
__kfree_skb(skb);
if (!skb_peek(&tp->out_of_order_queue)) {
/* Initial out of order segment, build 1 SACK. */
- if (tp->rx_opt.sack_ok) {
+ if (tcp_is_sack(tp)) {
tp->rx_opt.num_sacks = 1;
tp->rx_opt.dsack = 0;
tp->rx_opt.eff_sacks = 1;
}
add_sack:
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
tcp_sack_new_ofo_skb(sk, seq, end_seq);
}
}
* - bloated or contains data before "start" or
* overlaps to the next one.
*/
- if (!skb->h.th->syn && !skb->h.th->fin &&
+ if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
(tcp_win_from_space(skb->truesize) > skb->len ||
before(TCP_SKB_CB(skb)->seq, start) ||
(skb->next != tail &&
start = TCP_SKB_CB(skb)->end_seq;
skb = skb->next;
}
- if (skb == tail || skb->h.th->syn || skb->h.th->fin)
+ if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
return;
while (before(start, end)) {
if (!nskb)
return;
- skb_set_mac_header(nskb, skb->mac.raw - skb->head);
- nskb->nh.raw = nskb->data + (skb->nh.raw - skb->head);
- nskb->h.raw = nskb->data + (skb->h.raw - skb->head);
-
+ skb_set_mac_header(nskb, skb_mac_header(skb) - skb->head);
+ skb_set_network_header(nskb, (skb_network_header(skb) -
+ skb->head));
+ skb_set_transport_header(nskb, (skb_transport_header(skb) -
+ skb->head));
skb_reserve(nskb, header);
memcpy(nskb->head, skb->head, header);
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
__kfree_skb(skb);
NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
skb = next;
- if (skb == tail || skb->h.th->syn || skb->h.th->fin)
+ if (skb == tail ||
+ tcp_hdr(skb)->syn ||
+ tcp_hdr(skb)->fin)
return;
}
}
NET_INC_STATS_BH(LINUX_MIB_PRUNECALLED);
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
- tcp_clamp_window(sk, tp);
+ tcp_clamp_window(sk);
else if (tcp_memory_pressure)
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
* is in a sad state like this, we care only about integrity
* of the connection not performance.
*/
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
sk_stream_mem_reclaim(sk);
}
tp->snd_cwnd_stamp = tcp_time_stamp;
}
-static int tcp_should_expand_sndbuf(struct sock *sk, struct tcp_sock *tp)
+static int tcp_should_expand_sndbuf(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
/* If the user specified a specific send buffer setting, do
* not modify it.
*/
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_should_expand_sndbuf(sk, tp)) {
+ 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,
}
}
-static inline void tcp_data_snd_check(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_data_snd_check(struct sock *sk)
{
- tcp_push_pending_frames(sk, tp);
+ tcp_push_pending_frames(sk);
tcp_check_space(sk);
}
int err;
local_bh_enable();
- if (skb->ip_summed==CHECKSUM_UNNECESSARY)
+ if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk);
else
err = skb_copy_and_csum_datagram_iovec(skb, hlen,
static inline int tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
{
- return skb->ip_summed != CHECKSUM_UNNECESSARY &&
+ return !skb_csum_unnecessary(skb) &&
__tcp_checksum_complete_user(sk, skb);
}
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
tp->ucopy.dma_chan = get_softnet_dma();
- if (tp->ucopy.dma_chan && skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
dma_cookie = dma_skb_copy_datagram_iovec(tp->ucopy.dma_chan,
skb, hlen, tp->ucopy.iov, chunk, tp->ucopy.pinned_list);
tcp_rcv_space_adjust(sk);
if ((tp->ucopy.len == 0) ||
- (tcp_flag_word(skb->h.th) & TCP_FLAG_PSH) ||
+ (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
(atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
tp->ucopy.wakeup = 1;
sk->sk_data_ready(sk, 0);
*/
tcp_ack(sk, skb, 0);
__kfree_skb(skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
return 0;
} else { /* Header too small */
TCP_INC_STATS_BH(TCP_MIB_INERRS);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
}
- tcp_event_data_recv(sk, tp, skb);
+ tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
/* Well, only one small jumplet in fast path... */
tcp_ack(sk, skb, FLAG_DATA);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
if (!inet_csk_ack_scheduled(sk))
goto no_ack;
}
/* step 7: process the segment text */
tcp_data_queue(sk, skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
return 0;
tp->tcp_header_len = sizeof(struct tcphdr);
}
- if (tp->rx_opt.sack_ok && sysctl_tcp_fack)
- tp->rx_opt.sack_ok |= 2;
+ if (tcp_is_sack(tp) && sysctl_tcp_fack)
+ tcp_enable_fack(tp);
tcp_mtup_init(sk);
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
/* Do step6 onward by hand. */
tcp_urg(sk, skb, th);
__kfree_skb(skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
return 0;
}
/* tcp_data could move socket to TIME-WAIT */
if (sk->sk_state != TCP_CLOSE) {
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
}