#include <net/inet_common.h>
#include <linux/ipsec.h>
#include <asm/unaligned.h>
-#include <net/netdma.h>
+#include <linux/errqueue.h>
int sysctl_tcp_timestamps __read_mostly = 1;
int sysctl_tcp_window_scaling __read_mostly = 1;
}
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+ if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
!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 (tp->undo_marker && tp->undo_retrans &&
+ if (tp->undo_marker && tp->undo_retrans > 0 &&
after(end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
tp->lost_out = 0;
tp->undo_marker = 0;
- tp->undo_retrans = 0;
+ tp->undo_retrans = -1;
}
void tcp_clear_retrans(struct tcp_sock *tp)
tp->sacked_out = 0;
}
-/* Enter Loss state. If "how" is not zero, forget all SACK information
+/* Enter Loss state. If we detect SACK reneging, 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.
*/
-void tcp_enter_loss(struct sock *sk, int how)
+void tcp_enter_loss(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
bool new_recovery = false;
+ bool is_reneg; /* is receiver reneging on SACKs? */
/* Reduce ssthresh if it has not yet been made inside this window. */
if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
tcp_reset_reno_sack(tp);
tp->undo_marker = tp->snd_una;
- if (how) {
+
+ skb = tcp_write_queue_head(sk);
+ is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
+ if (is_reneg) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
tp->fackets_out = 0;
}
tp->undo_marker = 0;
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
+ if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
* remembered SACKs do not reflect real state of receiver i.e.
* receiver _host_ is heavily congested (or buggy).
*
- * Do processing similar to RTO timeout.
+ * To avoid big spurious retransmission bursts due to transient SACK
+ * scoreboard oddities that look like reneging, we give the receiver a
+ * little time (max(RTT/2, 10ms)) to send us some more ACKs that will
+ * restore sanity to the SACK scoreboard. If the apparent reneging
+ * persists until this RTO then we'll clear the SACK scoreboard.
*/
static bool tcp_check_sack_reneging(struct sock *sk, int flag)
{
if (flag & FLAG_SACK_RENEGING) {
- struct inet_connection_sock *icsk = inet_csk(sk);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
+ struct tcp_sock *tp = tcp_sk(sk);
+ unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
+ msecs_to_jiffies(10));
- tcp_enter_loss(sk, 1);
- icsk->icsk_retransmits++;
- tcp_retransmit_skb(sk, tcp_write_queue_head(sk));
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- icsk->icsk_rto, TCP_RTO_MAX);
+ delay, TCP_RTO_MAX);
return true;
}
return false;
* losses and/or application stalls), do not perform any further cwnd
* reductions, but instead slow start up to ssthresh.
*/
-static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
+static void tcp_init_cwnd_reduction(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->prior_cwnd = tp->snd_cwnd;
tp->prr_delivered = 0;
tp->prr_out = 0;
- if (set_ssthresh)
- tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk);
+ tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk);
TCP_ECN_queue_cwr(tp);
}
}
/* Enter CWR state. Disable cwnd undo since congestion is proven with ECN */
-void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
+void tcp_enter_cwr(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->prior_ssthresh = 0;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
tp->undo_marker = 0;
- tcp_init_cwnd_reduction(sk, set_ssthresh);
+ tcp_init_cwnd_reduction(sk);
tcp_set_ca_state(sk, TCP_CA_CWR);
}
}
tp->retrans_stamp = 0;
if (flag & FLAG_ECE)
- tcp_enter_cwr(sk, 1);
+ tcp_enter_cwr(sk);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
tcp_try_keep_open(sk);
tp->prior_ssthresh = 0;
tp->undo_marker = tp->snd_una;
- tp->undo_retrans = tp->retrans_out;
+ tp->undo_retrans = tp->retrans_out ? : -1;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
if (!ece_ack)
tp->prior_ssthresh = tcp_current_ssthresh(sk);
- tcp_init_cwnd_reduction(sk, true);
+ tcp_init_cwnd_reduction(sk);
}
tcp_set_ca_state(sk, TCP_CA_Recovery);
}
*/
static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
if (recovered) {
/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
- icsk->icsk_retransmits = 0;
tcp_try_undo_recovery(sk);
return;
}
- if (flag & FLAG_DATA_ACKED)
- icsk->icsk_retransmits = 0;
if (tcp_is_reno(tp)) {
/* A Reno DUPACK means new data in F-RTO step 2.b above are
* delivered. Lower inflight to clock out (re)tranmissions.
first_ackt.v64 = 0;
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
u8 sacked = scb->sacked;
u32 acked_pcount;
+ if (unlikely(shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
+ between(shinfo->tskey, prior_snd_una, tp->snd_una - 1))
+ __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+
/* Determine how many packets and what bytes were acked, tso and else */
if (after(scb->end_seq, tp->snd_una)) {
if (tcp_skb_pcount(skb) == 1 ||
tp->tlp_high_seq = 0;
/* Don't reduce cwnd if DSACK arrives for TLP retrans. */
if (!(flag & FLAG_DSACKING_ACK)) {
- tcp_init_cwnd_reduction(sk, true);
+ tcp_init_cwnd_reduction(sk);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
tcp_try_keep_open(sk);
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
- if (after(ack, prior_snd_una))
+ if (after(ack, prior_snd_una)) {
flag |= FLAG_SND_UNA_ADVANCED;
+ icsk->icsk_retransmits = 0;
+ }
prior_fackets = tp->fackets_out;
__tcp_checksum_complete_user(sk, skb);
}
-#ifdef CONFIG_NET_DMA
-static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
- int hlen)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- int chunk = skb->len - hlen;
- int dma_cookie;
- bool copied_early = false;
-
- if (tp->ucopy.wakeup)
- return false;
-
- if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = net_dma_find_channel();
-
- 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);
-
- if (dma_cookie < 0)
- goto out;
-
- tp->ucopy.dma_cookie = dma_cookie;
- copied_early = true;
-
- tp->ucopy.len -= chunk;
- tp->copied_seq += chunk;
- tcp_rcv_space_adjust(sk);
-
- if ((tp->ucopy.len == 0) ||
- (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);
- }
- } else if (chunk > 0) {
- tp->ucopy.wakeup = 1;
- sk->sk_data_ready(sk);
- }
-out:
- return copied_early;
-}
-#endif /* CONFIG_NET_DMA */
-
/* Does PAWS and seqno based validation of an incoming segment, flags will
* play significant role here.
*/
}
} else {
int eaten = 0;
- int copied_early = 0;
bool fragstolen = false;
- if (tp->copied_seq == tp->rcv_nxt &&
- len - tcp_header_len <= tp->ucopy.len) {
-#ifdef CONFIG_NET_DMA
- if (tp->ucopy.task == current &&
- sock_owned_by_user(sk) &&
- tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
- copied_early = 1;
- eaten = 1;
- }
-#endif
- if (tp->ucopy.task == current &&
- sock_owned_by_user(sk) && !copied_early) {
- __set_current_state(TASK_RUNNING);
+ if (tp->ucopy.task == current &&
+ tp->copied_seq == tp->rcv_nxt &&
+ len - tcp_header_len <= tp->ucopy.len &&
+ sock_owned_by_user(sk)) {
+ __set_current_state(TASK_RUNNING);
- if (!tcp_copy_to_iovec(sk, skb, tcp_header_len))
- eaten = 1;
- }
- if (eaten) {
+ if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) {
/* Predicted packet is in window by definition.
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
__skb_pull(skb, tcp_header_len);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
+ eaten = 1;
}
- if (copied_early)
- tcp_cleanup_rbuf(sk, skb->len);
}
if (!eaten) {
if (tcp_checksum_complete_user(sk, skb))
goto no_ack;
}
- if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
- __tcp_ack_snd_check(sk, 0);
+ __tcp_ack_snd_check(sk, 0);
no_ack:
-#ifdef CONFIG_NET_DMA
- if (copied_early)
- __skb_queue_tail(&sk->sk_async_wait_queue, skb);
- else
-#endif
if (eaten)
kfree_skb_partial(skb, fragstolen);
sk->sk_data_ready(sk);
return 0;
}
EXPORT_SYMBOL(tcp_rcv_state_process);
+
+static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
+{
+ struct inet_request_sock *ireq = inet_rsk(req);
+
+ if (family == AF_INET)
+ LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"),
+ &ireq->ir_rmt_addr, port);
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (family == AF_INET6)
+ LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI6/%u\n"),
+ &ireq->ir_v6_rmt_addr, port);
+#endif
+}
+
+int tcp_conn_request(struct request_sock_ops *rsk_ops,
+ const struct tcp_request_sock_ops *af_ops,
+ struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_options_received tmp_opt;
+ struct request_sock *req;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct dst_entry *dst = NULL;
+ __u32 isn = TCP_SKB_CB(skb)->when;
+ bool want_cookie = false, fastopen;
+ struct flowi fl;
+ struct tcp_fastopen_cookie foc = { .len = -1 };
+ int err;
+
+
+ /* TW buckets are converted to open requests without
+ * limitations, they conserve resources and peer is
+ * evidently real one.
+ */
+ if ((sysctl_tcp_syncookies == 2 ||
+ inet_csk_reqsk_queue_is_full(sk)) && !isn) {
+ want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
+ if (!want_cookie)
+ goto drop;
+ }
+
+
+ /* Accept backlog is full. If we have already queued enough
+ * of warm entries in syn queue, drop request. It is better than
+ * clogging syn queue with openreqs with exponentially increasing
+ * timeout.
+ */
+ if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+ goto drop;
+ }
+
+ req = inet_reqsk_alloc(rsk_ops);
+ if (!req)
+ goto drop;
+
+ tcp_rsk(req)->af_specific = af_ops;
+
+ tcp_clear_options(&tmp_opt);
+ tmp_opt.mss_clamp = af_ops->mss_clamp;
+ tmp_opt.user_mss = tp->rx_opt.user_mss;
+ tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
+
+ if (want_cookie && !tmp_opt.saw_tstamp)
+ tcp_clear_options(&tmp_opt);
+
+ tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
+ tcp_openreq_init(req, &tmp_opt, skb, sk);
+
+ af_ops->init_req(req, sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
+ if (!want_cookie || tmp_opt.tstamp_ok)
+ TCP_ECN_create_request(req, skb, sock_net(sk));
+
+ if (want_cookie) {
+ isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
+ req->cookie_ts = tmp_opt.tstamp_ok;
+ } else if (!isn) {
+ /* VJ's idea. We save last timestamp seen
+ * from the destination in peer table, when entering
+ * state TIME-WAIT, and check against it before
+ * accepting new connection request.
+ *
+ * If "isn" is not zero, this request hit alive
+ * timewait bucket, so that all the necessary checks
+ * are made in the function processing timewait state.
+ */
+ if (tcp_death_row.sysctl_tw_recycle) {
+ bool strict;
+
+ dst = af_ops->route_req(sk, &fl, req, &strict);
+
+ if (dst && strict &&
+ !tcp_peer_is_proven(req, dst, true,
+ tmp_opt.saw_tstamp)) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
+ goto drop_and_release;
+ }
+ }
+ /* Kill the following clause, if you dislike this way. */
+ else if (!sysctl_tcp_syncookies &&
+ (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+ (sysctl_max_syn_backlog >> 2)) &&
+ !tcp_peer_is_proven(req, dst, false,
+ tmp_opt.saw_tstamp)) {
+ /* Without syncookies last quarter of
+ * backlog is filled with destinations,
+ * proven to be alive.
+ * It means that we continue to communicate
+ * to destinations, already remembered
+ * to the moment of synflood.
+ */
+ pr_drop_req(req, ntohs(tcp_hdr(skb)->source),
+ rsk_ops->family);
+ goto drop_and_release;
+ }
+
+ isn = af_ops->init_seq(skb);
+ }
+ if (!dst) {
+ dst = af_ops->route_req(sk, &fl, req, NULL);
+ if (!dst)
+ goto drop_and_free;
+ }
+
+ tcp_rsk(req)->snt_isn = isn;
+ tcp_openreq_init_rwin(req, sk, dst);
+ fastopen = !want_cookie &&
+ tcp_try_fastopen(sk, skb, req, &foc, dst);
+ err = af_ops->send_synack(sk, dst, &fl, req,
+ skb_get_queue_mapping(skb), &foc);
+ if (!fastopen) {
+ if (err || want_cookie)
+ goto drop_and_free;
+
+ tcp_rsk(req)->listener = NULL;
+ af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ }
+
+ return 0;
+
+drop_and_release:
+ dst_release(dst);
+drop_and_free:
+ reqsk_free(req);
+drop:
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+ return 0;
+}
+EXPORT_SYMBOL(tcp_conn_request);