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_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_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */
#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
tp->rx_opt.sack_ok &= ~2;
}
-/* Take a notice that peer is sending DSACKs */
+/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
tp->rx_opt.sack_ok |= 4;
* 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).
+ * it means that the receiver is rather inconsistent with itself reporting
+ * SACK reneging when it should advance SND.UNA. Such SACK block this is
+ * perfectly valid, however, in light of RFC2018 which explicitly states
+ * that "SACK block MUST reflect the newest segment. Even if the newest
+ * segment is going to be discarded ...", not that it looks very clever
+ * in case of head skb. Due to potentional receiver driven attacks, we
+ * choose to avoid immediate execution of a walk in write queue due to
+ * reneging and defer head skb's loss recovery to standard loss recovery
+ * procedure that will eventually trigger (nothing forbids us doing this).
*
* 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),
*
* 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
+ * again, D-SACK 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
if (!before(start_seq, tp->snd_nxt))
return 0;
- /* In outstanding window? ...This is valid exit for DSACKs too.
+ /* In outstanding window? ...This is valid exit for D-SACKs too.
* start_seq == snd_una is non-sensical (see comments above)
*/
if (after(start_seq, tp->snd_una))
return !before(start_seq, end_seq - tp->max_window);
}
+/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".
+ * Event "C". Later note: FACK people cheated me again 8), we have to account
+ * for reordering! Ugly, but should help.
+ *
+ * Search retransmitted skbs from write_queue that were sent when snd_nxt was
+ * less than what is now known to be received by the other end (derived from
+ * SACK blocks by the caller). Also calculate the lowest snd_nxt among the
+ * remaining retransmitted skbs to avoid some costly processing per ACKs.
+ */
+static int tcp_mark_lost_retrans(struct sock *sk, u32 received_upto)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+ int flag = 0;
+ int cnt = 0;
+ u32 new_low_seq = tp->snd_nxt;
+
+ tcp_for_write_queue(skb, sk) {
+ u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;
+
+ if (skb == tcp_send_head(sk))
+ break;
+ if (cnt == tp->retrans_out)
+ break;
+ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
+ continue;
+
+ 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))) {
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+ tp->retrans_out -= tcp_skb_pcount(skb);
+
+ /* clear lost hint */
+ tp->retransmit_skb_hint = NULL;
+
+ if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
+ tp->lost_out += tcp_skb_pcount(skb);
+ TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ flag |= FLAG_DATA_SACKED;
+ NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT);
+ }
+ } else {
+ if (before(ack_seq, new_low_seq))
+ new_low_seq = ack_seq;
+ cnt += tcp_skb_pcount(skb);
+ }
+ }
+
+ if (tp->retrans_out)
+ tp->lost_retrans_low = new_low_seq;
+
+ return flag;
+}
static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
struct tcp_sack_block_wire *sp, int num_sacks,
return dup_sack;
}
+/* Check if skb is fully within the SACK block. In presence of GSO skbs,
+ * the incoming SACK may not exactly match but we can find smaller MSS
+ * aligned portion of it that matches. Therefore we might need to fragment
+ * which may fail and creates some hassle (caller must handle error case
+ * returns).
+ */
+static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
+ u32 start_seq, u32 end_seq)
+{
+ int in_sack, err;
+ unsigned int pkt_len;
+
+ in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
+ !before(end_seq, TCP_SKB_CB(skb)->end_seq);
+
+ if (tcp_skb_pcount(skb) > 1 && !in_sack &&
+ after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
+
+ in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);
+
+ if (!in_sack)
+ pkt_len = start_seq - TCP_SKB_CB(skb)->seq;
+ else
+ pkt_len = end_seq - TCP_SKB_CB(skb)->seq;
+ err = tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size);
+ if (err < 0)
+ return err;
+ }
+
+ return in_sack;
+}
+
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int reord = tp->packets_out;
int prior_fackets;
- u32 lost_retrans = 0;
+ u32 highest_sack_end_seq = tp->lost_retrans_low;
int flag = 0;
int found_dup_sack = 0;
int cached_fack_count;
int i;
int first_sack_index;
+ int force_one_sack;
if (!tp->sacked_out) {
- tp->fackets_out = 0;
+ if (WARN_ON(tp->fackets_out))
+ tp->fackets_out = 0;
tp->highest_sack = tp->snd_una;
}
prior_fackets = tp->fackets_out;
* if the only SACK change is the increase of the end_seq of
* the first block then only apply that SACK block
* and use retrans queue hinting otherwise slowpath */
- flag = 1;
+ force_one_sack = 1;
for (i = 0; i < num_sacks; i++) {
__be32 start_seq = sp[i].start_seq;
__be32 end_seq = sp[i].end_seq;
if (i == 0) {
if (tp->recv_sack_cache[i].start_seq != start_seq)
- flag = 0;
+ force_one_sack = 0;
} else {
if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
(tp->recv_sack_cache[i].end_seq != end_seq))
- flag = 0;
+ force_one_sack = 0;
}
tp->recv_sack_cache[i].start_seq = start_seq;
tp->recv_sack_cache[i].end_seq = end_seq;
}
first_sack_index = 0;
- if (flag)
+ if (force_one_sack)
num_sacks = 1;
else {
int j;
}
}
- /* clear flag as used for different purpose in following code */
- flag = 0;
-
/* Use SACK fastpath hint if valid */
cached_skb = tp->fastpath_skb_hint;
cached_fack_count = tp->fastpath_cnt_hint;
cached_fack_count = 0;
}
- for (i=0; i<num_sacks; i++, sp++) {
+ for (i = 0; i < num_sacks; i++) {
struct sk_buff *skb;
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
int dup_sack = (found_dup_sack && (i == first_sack_index));
+ int next_dup = (found_dup_sack && (i+1 == first_sack_index));
+
+ sp++;
if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) {
if (dup_sack) {
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDNOUNDO);
else
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDOLD);
- } else
+ } else {
+ /* Don't count olds caused by ACK reordering */
+ if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) &&
+ !after(end_seq, tp->snd_una))
+ continue;
NET_INC_STATS_BH(LINUX_MIB_TCPSACKDISCARD);
+ }
continue;
}
flag |= FLAG_DATA_LOST;
tcp_for_write_queue_from(skb, sk) {
- int in_sack, pcount;
+ int in_sack = 0;
u8 sacked;
if (skb == tcp_send_head(sk))
if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
- in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
- !before(end_seq, TCP_SKB_CB(skb)->end_seq);
+ dup_sack = (found_dup_sack && (i == first_sack_index));
- pcount = tcp_skb_pcount(skb);
+ /* Due to sorting DSACK may reside within this SACK block! */
+ if (next_dup) {
+ u32 dup_start = ntohl(sp->start_seq);
+ u32 dup_end = ntohl(sp->end_seq);
- if (pcount > 1 && !in_sack &&
- after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
- unsigned int pkt_len;
-
- in_sack = !after(start_seq,
- TCP_SKB_CB(skb)->seq);
-
- if (!in_sack)
- pkt_len = (start_seq -
- TCP_SKB_CB(skb)->seq);
- else
- pkt_len = (end_seq -
- TCP_SKB_CB(skb)->seq);
- if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
- break;
- pcount = tcp_skb_pcount(skb);
+ if (before(TCP_SKB_CB(skb)->seq, dup_end)) {
+ in_sack = tcp_match_skb_to_sack(sk, skb, dup_start, dup_end);
+ if (in_sack > 0)
+ dup_sack = 1;
+ }
}
- fack_count += pcount;
+ /* DSACK info lost if out-of-mem, try SACK still */
+ if (in_sack <= 0)
+ in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
+ if (in_sack < 0)
+ break;
+
+ fack_count += tcp_skb_pcount(skb);
sacked = TCP_SKB_CB(skb)->sacked;
continue;
}
- if ((sacked&TCPCB_SACKED_RETRANS) &&
- after(end_seq, TCP_SKB_CB(skb)->ack_seq) &&
- (!lost_retrans || after(end_seq, lost_retrans)))
- lost_retrans = end_seq;
-
if (!in_sack)
continue;
if (fack_count > tp->fackets_out)
tp->fackets_out = fack_count;
- if (after(TCP_SKB_CB(skb)->seq,
- tp->highest_sack))
+ if (after(TCP_SKB_CB(skb)->seq, tp->highest_sack)) {
tp->highest_sack = TCP_SKB_CB(skb)->seq;
+ highest_sack_end_seq = TCP_SKB_CB(skb)->end_seq;
+ }
} else {
if (dup_sack && (sacked&TCPCB_RETRANS))
reord = min(fack_count, reord);
}
}
- /* Check for lost retransmit. This superb idea is
- * borrowed from "ratehalving". Event "C".
- * Later note: FACK people cheated me again 8),
- * we have to account for reordering! Ugly,
- * but should help.
- */
- if (lost_retrans && icsk->icsk_ca_state == TCP_CA_Recovery) {
- struct sk_buff *skb;
-
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- if (after(TCP_SKB_CB(skb)->seq, lost_retrans))
- break;
- if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- continue;
- if ((TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) &&
- after(lost_retrans, TCP_SKB_CB(skb)->ack_seq) &&
- (tcp_is_fack(tp) ||
- !before(lost_retrans,
- TCP_SKB_CB(skb)->ack_seq + tp->reordering *
- tp->mss_cache))) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
- tp->retrans_out -= tcp_skb_pcount(skb);
-
- /* clear lost hint */
- tp->retransmit_skb_hint = NULL;
-
- if (!(TCP_SKB_CB(skb)->sacked&(TCPCB_LOST|TCPCB_SACKED_ACKED))) {
- tp->lost_out += tcp_skb_pcount(skb);
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- flag |= FLAG_DATA_SACKED;
- NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT);
- }
- }
- }
- }
+ if (tp->retrans_out &&
+ after(highest_sack_end_seq, tp->lost_retrans_low) &&
+ icsk->icsk_ca_state == TCP_CA_Recovery)
+ flag |= tcp_mark_lost_retrans(sk, highest_sack_end_seq);
tcp_verify_left_out(tp);
return flag;
}
-/* 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)
+/* 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.
*/
static void tcp_check_reno_reordering(struct sock *sk, const int addend)
{
tp->sacked_out = 0;
}
+/* 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)
+ */
int tcp_use_frto(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
!icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
/* Our state is too optimistic in ssthresh() call because cwnd
- * is not reduced until tcp_enter_frto_loss() when previous FRTO
+ * is not reduced until tcp_enter_frto_loss() when previous F-RTO
* recovery has not yet completed. Pattern would be this: RTO,
* Cumulative ACK, RTO (2xRTO for the same segment does not end
* up here twice).
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->frto_counter = 0;
+ tp->bytes_acked = 0;
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
tp->high_seq = tp->frto_highmark;
TCP_ECN_queue_cwr(tp);
- tcp_clear_all_retrans_hints(tp);
+ tcp_clear_retrans_hints_partial(tp);
}
-void tcp_clear_retrans(struct tcp_sock *tp)
+static void tcp_clear_retrans_partial(struct tcp_sock *tp)
{
tp->retrans_out = 0;
-
- tp->fackets_out = 0;
- tp->sacked_out = 0;
tp->lost_out = 0;
tp->undo_marker = 0;
tp->undo_retrans = 0;
}
+void tcp_clear_retrans(struct tcp_sock *tp)
+{
+ tcp_clear_retrans_partial(tp);
+
+ tp->fackets_out = 0;
+ tp->sacked_out = 0;
+}
+
/* Enter Loss state. If "how" is not zero, forget all SACK information
* and reset tags completely, otherwise preserve SACKs. If receiver
* dropped its ofo queue, we will know this due to reneging detection.
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt = 0;
/* Reduce ssthresh if it has not yet been made inside this window. */
if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->bytes_acked = 0;
- tcp_clear_retrans(tp);
+ tcp_clear_retrans_partial(tp);
- /* Push undo marker, if it was plain RTO and nothing
- * was retransmitted. */
- if (!how)
+ if (tcp_is_reno(tp))
+ tcp_reset_reno_sack(tp);
+
+ 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 {
+ tp->sacked_out = 0;
+ tp->fackets_out = 0;
+ tcp_clear_all_retrans_hints(tp);
+ }
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
- cnt += tcp_skb_pcount(skb);
+
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
tp->undo_marker = 0;
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
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;
}
}
tcp_verify_left_out(tp);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
- /* Abort FRTO algorithm if one is in progress */
+ /* Abort F-RTO algorithm if one is in progress */
tp->frto_counter = 0;
-
- tcp_clear_all_retrans_hints(tp);
}
static int tcp_check_sack_reneging(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
- /* Do not perform any recovery during FRTO algorithm */
+ /* Do not perform any recovery during F-RTO algorithm */
if (tp->frto_counter)
return 0;
}
/* Mark head of queue up as lost. */
-static void tcp_mark_head_lost(struct sock *sk,
- int packets, u32 high_seq)
+static void tcp_mark_head_lost(struct sock *sk, int packets)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
tp->lost_skb_hint = skb;
tp->lost_cnt_hint = cnt;
cnt += tcp_skb_pcount(skb);
- if (cnt > packets || after(TCP_SKB_CB(skb)->end_seq, high_seq))
+ if (cnt > packets || after(TCP_SKB_CB(skb)->end_seq, tp->high_seq))
break;
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
+ if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_SACKED_ACKED|TCPCB_LOST))) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
tcp_verify_retransmit_hint(tp, skb);
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, lost, tp->high_seq);
+ tcp_mark_head_lost(sk, lost);
} else {
- tcp_mark_head_lost(sk, 1, tp->high_seq);
+ tcp_mark_head_lost(sk, 1);
}
/* New heuristics: it is possible only after we switched
if (!tcp_skb_timedout(sk, skb))
break;
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
+ if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_SACKED_ACKED|TCPCB_LOST))) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
tcp_verify_retransmit_hint(tp, skb);
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, tp->high_seq);
+ tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}
BUG_TRAP((int)tp->lost_out >= 0);
BUG_TRAP((int)tp->retrans_out >= 0);
if (!tp->packets_out && tcp_is_sack(tp)) {
- const struct inet_connection_sock *icsk = inet_csk(sk);
+ icsk = inet_csk(sk);
if (tp->lost_out) {
printk(KERN_DEBUG "Leak l=%u %d\n",
tp->lost_out, icsk->icsk_ca_state);
{
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_cnt = 0;
+ tp->bytes_acked = 0;
TCP_ECN_queue_cwr(tp);
tcp_moderate_cwnd(tp);
}
}
if (tp->frto_counter == 1) {
- /* Sending of the next skb must be allowed or no FRTO */
+ /* Sending of the next skb must be allowed or no F-RTO */
if (!tcp_send_head(sk) ||
after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
}
tp->frto_counter = 0;
tp->undo_marker = 0;
+ NET_INC_STATS_BH(LINUX_MIB_TCPSPURIOUSRTOS);
}
return 0;
}
/* See if we can take anything off of the retransmit queue. */
flag |= tcp_clean_rtx_queue(sk, &seq_rtt);
+ /* Guarantee sacktag reordering detection against wrap-arounds */
+ if (before(tp->frto_highmark, tp->snd_una))
+ tp->frto_highmark = 0;
if (tp->frto_counter)
frto_cwnd = tcp_process_frto(sk, flag);
while (before(start, end)) {
struct sk_buff *nskb;
- int header = skb_headroom(skb);
+ unsigned int header = skb_headroom(skb);
int copy = SKB_MAX_ORDER(header, 0);
/* Too big header? This can happen with IPv6. */
projects / linux-2.6 / blobdiff