}
}
-static void tcp_incr_quickack(struct sock *sk)
+static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);
if (quickacks == 0)
quickacks = 2;
+ quickacks = min(quickacks, max_quickacks);
if (quickacks > icsk->icsk_ack.quick)
- icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
+ icsk->icsk_ack.quick = quickacks;
}
-static void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
- tcp_incr_quickack(sk);
+
+ tcp_incr_quickack(sk, max_quickacks);
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
{
- if (tcp_hdr(skb)->cwr)
+ if (tcp_hdr(skb)->cwr) {
tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+
+ /* If the sender is telling us it has entered CWR, then its
+ * cwnd may be very low (even just 1 packet), so we should ACK
+ * immediately.
+ */
+ tcp_enter_quickack_mode((struct sock *)tp, 2);
+ }
}
static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}
-static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
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 probably a retransmit.
*/
if (tp->ecn_flags & TCP_ECN_SEEN)
- tcp_enter_quickack_mode((struct sock *)tp);
+ tcp_enter_quickack_mode(sk, 2);
break;
case INET_ECN_CE:
- if (tcp_ca_needs_ecn((struct sock *)tp))
- tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+ if (tcp_ca_needs_ecn(sk))
+ tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
/* Better not delay acks, sender can have a very low cwnd */
- tcp_enter_quickack_mode((struct sock *)tp);
+ tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
tp->ecn_flags |= TCP_ECN_SEEN;
break;
default:
- if (tcp_ca_needs_ecn((struct sock *)tp))
- tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
+ if (tcp_ca_needs_ecn(sk))
+ tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
tp->ecn_flags |= TCP_ECN_SEEN;
break;
}
}
-static void tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
{
- if (tp->ecn_flags & TCP_ECN_OK)
- __tcp_ecn_check_ce(tp, skb);
+ if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK)
+ __tcp_ecn_check_ce(sk, skb);
}
static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 copied;
int time;
- int copied;
tcp_mstamp_refresh(tp);
time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- int rcvwin, rcvmem, rcvbuf;
+ int rcvmem, rcvbuf;
+ u64 rcvwin;
/* minimal window to cope with packet losses, assuming
* steady state. Add some cushion because of small variations.
*/
- rcvwin = (copied << 1) + 16 * tp->advmss;
+ rcvwin = ((u64)copied << 1) + 16 * tp->advmss;
/* If rate increased by 25%,
* assume slow start, rcvwin = 3 * copied
while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
rcvmem += 128;
- rcvbuf = min(rcvwin / tp->advmss * rcvmem,
+ do_div(rcvwin, tp->advmss);
+ rcvbuf = min_t(u64, rcvwin * rcvmem,
sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
if (rcvbuf > sk->sk_rcvbuf) {
sk->sk_rcvbuf = rcvbuf;
/* Make the window clamp follow along. */
- tp->window_clamp = rcvwin;
+ tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
}
}
tp->rcvq_space.space = copied;
/* The _first_ data packet received, initialize
* delayed ACK engine.
*/
- tcp_incr_quickack(sk);
+ tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
icsk->icsk_ack.ato = TCP_ATO_MIN;
} else {
int m = now - icsk->icsk_ack.lrcvtime;
/* Too long gap. Apparently sender failed to
* restart window, so that we send ACKs quickly.
*/
- tcp_incr_quickack(sk);
+ tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
sk_mem_reclaim(sk);
}
}
icsk->icsk_ack.lrcvtime = now;
- tcp_ecn_check_ce(tp, skb);
+ tcp_ecn_check_ce(sk, skb);
if (skb->len >= 128)
tcp_grow_window(sk, skb);
TCP_SKB_CB(skb)->seq += shifted;
tcp_skb_pcount_add(prev, pcount);
- BUG_ON(tcp_skb_pcount(skb) < pcount);
+ WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount);
tcp_skb_pcount_add(skb, -pcount);
/* When we're adding to gso_segs == 1, gso_size will be zero,
return !skb_headlen(skb) && skb_is_nonlinear(skb);
}
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from,
+ int pcount, int shiftlen)
+{
+ /* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE)
+ * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need
+ * to make sure not storing more than 65535 * 8 bytes per skb,
+ * even if current MSS is bigger.
+ */
+ if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE))
+ return 0;
+ if (unlikely(tcp_skb_pcount(to) + pcount > 65535))
+ return 0;
+ return skb_shift(to, from, shiftlen);
+}
+
/* Try collapsing SACK blocks spanning across multiple skbs to a single
* skb.
*/
if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
goto fallback;
- if (!skb_shift(prev, skb, len))
+ if (!tcp_skb_shift(prev, skb, pcount, len))
goto fallback;
if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
goto out;
goto out;
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),
+ pcount = tcp_skb_pcount(skb);
+ if (tcp_skb_shift(prev, skb, pcount, len))
+ tcp_shifted_skb(sk, prev, skb, state, pcount,
len, mss, 0);
- }
out:
return prev;
/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
- *
- * In theory F-RTO can be used repeatedly during loss recovery.
- * In practice this interacts badly with broken middle-boxes that
- * falsely raise the receive window, which results in repeated
- * timeouts and stop-and-go behavior.
*/
tp->frto = net->ipv4.sysctl_tcp_frto &&
(new_recovery || icsk->icsk_retransmits) &&
tcp_try_undo_loss(sk, false))
return;
- /* The ACK (s)acks some never-retransmitted data meaning not all
- * the data packets before the timeout were lost. Therefore we
- * undo the congestion window and state. This is essentially
- * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
- * a retransmitted skb is permantly marked, we can apply such an
- * operation even if F-RTO was not used.
- */
- if ((flag & FLAG_ORIG_SACK_ACKED) &&
- tcp_try_undo_loss(sk, tp->undo_marker))
- return;
-
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if ((flag & FLAG_ORIG_SACK_ACKED) &&
+ tcp_try_undo_loss(sk, true))
+ return;
+
if (after(tp->snd_nxt, tp->high_seq)) {
if (flag & FLAG_DATA_SACKED || is_dupack)
tp->frto = 0; /* Step 3.a. loss was real */
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
+
+ /* If any of the cumulatively ACKed segments was
+ * retransmitted, non-SACK case cannot confirm that
+ * progress was due to original transmission due to
+ * lack of TCPCB_SACKED_ACKED bits even if some of
+ * the packets may have been never retransmitted.
+ */
+ if (flag & FLAG_RETRANS_DATA_ACKED)
+ flag &= ~FLAG_ORIG_SACK_ACKED;
} else {
int delta;
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
/* This barrier is coupled with smp_rmb() in tcp_poll() */
smp_wmb();
+ tcp_write_queue_purge(sk);
tcp_done(sk);
if (!sock_flag(sk, SOCK_DEAD))
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
- tcp_enter_quickack_mode(sk);
+ tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
return true;
}
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+ struct sk_buff *to,
+ struct sk_buff *from,
+ bool *fragstolen)
+{
+ bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+ /* In case tcp_drop() is called later, update to->gso_segs */
+ if (res) {
+ u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+ max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+ skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+ }
+ return res;
+}
+
static void tcp_drop(struct sock *sk, struct sk_buff *skb)
{
sk_drops_add(sk, skb);
u32 seq, end_seq;
bool fragstolen;
- tcp_ecn_check_ce(tp, skb);
+ tcp_ecn_check_ce(sk, skb);
if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, tp->ooo_last_skb,
- skb, &fragstolen)) {
+ if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+ skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
kfree_skb_partial(skb, fragstolen);
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb);
+ tcp_drop(sk, skb);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb1);
+ tcp_drop(sk, skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, skb1,
- skb, &fragstolen)) {
+ } else if (tcp_ooo_try_coalesce(sk, skb1,
+ skb, &fragstolen)) {
goto coalesce_done;
}
p = &parent->rb_right;
tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
out_of_window:
- tcp_enter_quickack_mode(sk);
+ tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
inet_csk_schedule_ack(sk);
drop:
tcp_drop(sk, skb);
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
goto out_of_window;
- tcp_enter_quickack_mode(sk);
-
if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
/* Partial packet, seq < rcv_next < end_seq */
SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
static void tcp_collapse_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 range_truesize, sum_tiny = 0;
struct sk_buff *skb, *head;
u32 start, end;
}
start = TCP_SKB_CB(skb)->seq;
end = TCP_SKB_CB(skb)->end_seq;
+ range_truesize = skb->truesize;
for (head = skb;;) {
skb = skb_rb_next(skb);
if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
- tcp_collapse(sk, NULL, &tp->out_of_order_queue,
- head, skb, start, end);
+ /* Do not attempt collapsing tiny skbs */
+ if (range_truesize != head->truesize ||
+ end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+ tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+ head, skb, start, end);
+ } else {
+ sum_tiny += range_truesize;
+ if (sum_tiny > sk->sk_rcvbuf >> 3)
+ return;
+ }
goto new_range;
}
+ range_truesize += skb->truesize;
if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
start = TCP_SKB_CB(skb)->seq;
if (after(TCP_SKB_CB(skb)->end_seq, end))
* 2) not add too big latencies if thousands of packets sit there.
* (But if application shrinks SO_RCVBUF, we could still end up
* freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
*
* Return true if queue has shrunk.
*/
{
struct tcp_sock *tp = tcp_sk(sk);
struct rb_node *node, *prev;
+ int goal;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
return false;
NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+ goal = sk->sk_rcvbuf >> 3;
node = &tp->ooo_last_skb->rbnode;
do {
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
+ goal -= rb_to_skb(node)->truesize;
tcp_drop(sk, rb_to_skb(node));
- sk_mem_reclaim(sk);
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
- !tcp_under_memory_pressure(sk))
- break;
+ if (!prev || goal <= 0) {
+ sk_mem_reclaim(sk);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ !tcp_under_memory_pressure(sk))
+ break;
+ goal = sk->sk_rcvbuf >> 3;
+ }
node = prev;
} while (node);
tp->ooo_last_skb = rb_to_skb(prev);
else if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+ return 0;
+
tcp_collapse_ofo_queue(sk);
if (!skb_queue_empty(&sk->sk_receive_queue))
tcp_collapse(sk, &sk->sk_receive_queue, NULL,
* to stand against the temptation 8) --ANK
*/
inet_csk_schedule_ack(sk);
- tcp_enter_quickack_mode(sk);
+ tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
TCP_DELACK_MAX, TCP_RTO_MAX);
if (th->fin)
goto discard;
/* It is possible that we process SYN packets from backlog,
- * so we need to make sure to disable BH right there.
+ * so we need to make sure to disable BH and RCU right there.
*/
+ rcu_read_lock();
local_bh_disable();
acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
local_bh_enable();
+ rcu_read_unlock();
if (!acceptable)
return 1;