From 04dd17822334871b23ea2862f7798fb0e0007777 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 11 May 2024 08:53:19 +0000
Subject: [PATCH] change otg to host mode
---
kernel/net/ipv4/tcp_input.c | 1160 +++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 783 insertions(+), 377 deletions(-)
diff --git a/kernel/net/ipv4/tcp_input.c b/kernel/net/ipv4/tcp_input.c
index 757e1f6..46836e4 100644
--- a/kernel/net/ipv4/tcp_input.c
+++ b/kernel/net/ipv4/tcp_input.c
@@ -77,8 +77,10 @@
#include <asm/unaligned.h>
#include <linux/errqueue.h>
#include <trace/events/tcp.h>
-#include <linux/static_key.h>
+#include <linux/jump_label_ratelimit.h>
#include <net/busy_poll.h>
+#include <net/mptcp.h>
+#include <trace/hooks/net.h>
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
@@ -113,22 +115,91 @@
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
#if IS_ENABLED(CONFIG_TLS_DEVICE)
-static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled);
+static DEFINE_STATIC_KEY_DEFERRED_FALSE(clean_acked_data_enabled, HZ);
void clean_acked_data_enable(struct inet_connection_sock *icsk,
void (*cad)(struct sock *sk, u32 ack_seq))
{
icsk->icsk_clean_acked = cad;
- static_branch_inc(&clean_acked_data_enabled);
+ static_branch_deferred_inc(&clean_acked_data_enabled);
}
EXPORT_SYMBOL_GPL(clean_acked_data_enable);
void clean_acked_data_disable(struct inet_connection_sock *icsk)
{
- static_branch_dec(&clean_acked_data_enabled);
+ static_branch_slow_dec_deferred(&clean_acked_data_enabled);
icsk->icsk_clean_acked = NULL;
}
EXPORT_SYMBOL_GPL(clean_acked_data_disable);
+
+void clean_acked_data_flush(void)
+{
+ static_key_deferred_flush(&clean_acked_data_enabled);
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_flush);
+#endif
+
+#ifdef CONFIG_CGROUP_BPF
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+ bool unknown_opt = tcp_sk(sk)->rx_opt.saw_unknown &&
+ BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG);
+ bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+ struct bpf_sock_ops_kern sock_ops;
+
+ if (likely(!unknown_opt && !parse_all_opt))
+ return;
+
+ /* The skb will be handled in the
+ * bpf_skops_established() or
+ * bpf_skops_write_hdr_opt().
+ */
+ switch (sk->sk_state) {
+ case TCP_SYN_RECV:
+ case TCP_SYN_SENT:
+ case TCP_LISTEN:
+ return;
+ }
+
+ sock_owned_by_me(sk);
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+ sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB;
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+ BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+ struct sk_buff *skb)
+{
+ struct bpf_sock_ops_kern sock_ops;
+
+ sock_owned_by_me(sk);
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+ sock_ops.op = bpf_op;
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */
+ if (skb)
+ bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+ BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+#else
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+}
+
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+ struct sk_buff *skb)
+{
+}
#endif
static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
@@ -172,6 +243,19 @@
if (unlikely(len > icsk->icsk_ack.rcv_mss +
MAX_TCP_OPTION_SPACE))
tcp_gro_dev_warn(sk, skb, len);
+ /* If the skb has a len of exactly 1*MSS and has the PSH bit
+ * set then it is likely the end of an application write. So
+ * more data may not be arriving soon, and yet the data sender
+ * may be waiting for an ACK if cwnd-bound or using TX zero
+ * copy. So we set ICSK_ACK_PUSHED here so that
+ * tcp_cleanup_rbuf() will send an ACK immediately if the app
+ * reads all of the data and is not ping-pong. If len > MSS
+ * then this logic does not matter (and does not hurt) because
+ * tcp_cleanup_rbuf() will always ACK immediately if the app
+ * reads data and there is more than an MSS of unACKed data.
+ */
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH)
+ icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
@@ -216,15 +300,14 @@
icsk->icsk_ack.quick = quickacks;
}
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_incr_quickack(sk, max_quickacks);
- icsk->icsk_ack.pingpong = 0;
+ inet_csk_exit_pingpong_mode(sk);
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.
@@ -236,7 +319,7 @@
const struct dst_entry *dst = __sk_dst_get(sk);
return (dst && dst_metric(dst, RTAX_QUICKACK)) ||
- (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);
+ (icsk->icsk_ack.quick && !inet_csk_in_pingpong_mode(sk));
}
static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
@@ -354,7 +437,8 @@
sndmem *= nr_segs * per_mss;
if (sk->sk_sndbuf < sndmem)
- sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
+ WRITE_ONCE(sk->sk_sndbuf,
+ min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -383,12 +467,13 @@
*/
/* Slow part of check#2. */
-static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
+static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
+ unsigned int skbtruesize)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
- int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
- int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+ int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
+ int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
@@ -400,7 +485,27 @@
return 0;
}
-static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
+/* Even if skb appears to have a bad len/truesize ratio, TCP coalescing
+ * can play nice with us, as sk_buff and skb->head might be either
+ * freed or shared with up to MAX_SKB_FRAGS segments.
+ * Only give a boost to drivers using page frag(s) to hold the frame(s),
+ * and if no payload was pulled in skb->head before reaching us.
+ */
+static u32 truesize_adjust(bool adjust, const struct sk_buff *skb)
+{
+ u32 truesize = skb->truesize;
+
+ if (adjust && !skb_headlen(skb)) {
+ truesize -= SKB_TRUESIZE(skb_end_offset(skb));
+ /* paranoid check, some drivers might be buggy */
+ if (unlikely((int)truesize < (int)skb->len))
+ truesize = skb->truesize;
+ }
+ return truesize;
+}
+
+static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
+ bool adjust)
{
struct tcp_sock *tp = tcp_sk(sk);
int room;
@@ -409,15 +514,16 @@
/* Check #1 */
if (room > 0 && !tcp_under_memory_pressure(sk)) {
+ unsigned int truesize = truesize_adjust(adjust, skb);
int incr;
/* Check #2. Increase window, if skb with such overhead
* will fit to rcvbuf in future.
*/
- if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
+ if (tcp_win_from_space(sk, truesize) <= skb->len)
incr = 2 * tp->advmss;
else
- incr = __tcp_grow_window(sk, skb);
+ incr = __tcp_grow_window(sk, skb, truesize);
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
@@ -430,9 +536,9 @@
/* 3. Try to fixup all. It is made immediately after connection enters
* established state.
*/
-void tcp_init_buffer_space(struct sock *sk)
+static void tcp_init_buffer_space(struct sock *sk)
{
- int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+ int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -472,15 +578,17 @@
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
+ int rmem2;
icsk->icsk_ack.quick = 0;
+ rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
- if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+ if (sk->sk_rcvbuf < rmem2 &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
- sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
- net->ipv4.sysctl_tcp_rmem[2]);
+ WRITE_ONCE(sk->sk_rcvbuf,
+ min(atomic_read(&sk->sk_rmem_alloc), rmem2));
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -510,7 +618,7 @@
*
* The algorithm for RTT estimation w/o timestamps is based on
* Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL.
- * <http://public.lanl.gov/radiant/pubs.html#DRS>
+ * <https://public.lanl.gov/radiant/pubs.html#DRS>
*
* More detail on this code can be found at
* <http://staff.psc.edu/jheffner/>,
@@ -621,7 +729,7 @@
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -642,9 +750,9 @@
do_div(rcvwin, tp->advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
- sk->sk_rcvbuf = rcvbuf;
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
/* Make the window clamp follow along. */
tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
@@ -710,7 +818,7 @@
tcp_ecn_check_ce(sk, skb);
if (skb->len >= 128)
- tcp_grow_window(sk, skb);
+ tcp_grow_window(sk, skb, true);
}
/* Called to compute a smoothed rtt estimate. The data fed to this
@@ -774,6 +882,8 @@
tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
tp->rtt_seq = tp->snd_nxt;
tp->mdev_max_us = tcp_rto_min_us(sk);
+
+ tcp_bpf_rtt(sk);
}
} else {
/* no previous measure. */
@@ -782,6 +892,8 @@
tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
tp->mdev_max_us = tp->rttvar_us;
tp->rtt_seq = tp->snd_nxt;
+
+ tcp_bpf_rtt(sk);
}
tp->srtt_us = max(1U, srtt);
}
@@ -859,12 +971,54 @@
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
-/* Take a notice that peer is sending D-SACKs */
-static void tcp_dsack_seen(struct tcp_sock *tp)
+struct tcp_sacktag_state {
+ /* Timestamps for earliest and latest never-retransmitted segment
+ * that was SACKed. RTO needs the earliest RTT to stay conservative,
+ * but congestion control should still get an accurate delay signal.
+ */
+ u64 first_sackt;
+ u64 last_sackt;
+ u32 reord;
+ u32 sack_delivered;
+ int flag;
+ unsigned int mss_now;
+ struct rate_sample *rate;
+};
+
+/* Take a notice that peer is sending D-SACKs. Skip update of data delivery
+ * and spurious retransmission information if this DSACK is unlikely caused by
+ * sender's action:
+ * - DSACKed sequence range is larger than maximum receiver's window.
+ * - Total no. of DSACKed segments exceed the total no. of retransmitted segs.
+ */
+static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
+ u32 end_seq, struct tcp_sacktag_state *state)
{
+ u32 seq_len, dup_segs = 1;
+
+ if (!before(start_seq, end_seq))
+ return 0;
+
+ seq_len = end_seq - start_seq;
+ /* Dubious DSACK: DSACKed range greater than maximum advertised rwnd */
+ if (seq_len > tp->max_window)
+ return 0;
+ if (seq_len > tp->mss_cache)
+ dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache);
+
+ tp->dsack_dups += dup_segs;
+ /* Skip the DSACK if dup segs weren't retransmitted by sender */
+ if (tp->dsack_dups > tp->total_retrans)
+ return 0;
+
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
tp->rack.dsack_seen = 1;
- tp->dsack_dups++;
+
+ state->flag |= FLAG_DSACKING_ACK;
+ /* A spurious retransmission is delivered */
+ state->sack_delivered += dup_segs;
+
+ return dup_segs;
}
/* It's reordering when higher sequence was delivered (i.e. sacked) before
@@ -893,7 +1047,7 @@
tp->undo_marker ? tp->undo_retrans : 0);
#endif
tp->reordering = min_t(u32, (metric + mss - 1) / mss,
- sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
}
/* This exciting event is worth to be remembered. 8) */
@@ -902,7 +1056,11 @@
ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
}
-/* This must be called before lost_out is incremented */
+ /* This must be called before lost_out or retrans_out are updated
+ * on a new loss, because we want to know if all skbs previously
+ * known to be lost have already been retransmitted, indicating
+ * that this newly lost skb is our next skb to retransmit.
+ */
static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
{
if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
@@ -912,42 +1070,46 @@
tp->retransmit_skb_hint = skb;
}
-/* Sum the number of packets on the wire we have marked as lost.
- * There are two cases we care about here:
- * a) Packet hasn't been marked lost (nor retransmitted),
- * and this is the first loss.
- * b) Packet has been marked both lost and retransmitted,
- * and this means we think it was lost again.
+/* Sum the number of packets on the wire we have marked as lost, and
+ * notify the congestion control module that the given skb was marked lost.
*/
-static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_notify_skb_loss_event(struct tcp_sock *tp, const struct sk_buff *skb)
+{
+ tp->lost += tcp_skb_pcount(skb);
+}
+
+void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
{
__u8 sacked = TCP_SKB_CB(skb)->sacked;
+ struct tcp_sock *tp = tcp_sk(sk);
- if (!(sacked & TCPCB_LOST) ||
- ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS)))
- tp->lost += tcp_skb_pcount(skb);
-}
+ if (sacked & TCPCB_SACKED_ACKED)
+ return;
-static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
-{
- if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
- tcp_verify_retransmit_hint(tp, skb);
-
- tp->lost_out += tcp_skb_pcount(skb);
- tcp_sum_lost(tp, skb);
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- }
-}
-
-void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
-{
tcp_verify_retransmit_hint(tp, skb);
-
- tcp_sum_lost(tp, skb);
- if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
+ if (sacked & TCPCB_LOST) {
+ if (sacked & TCPCB_SACKED_RETRANS) {
+ /* Account for retransmits that are lost again */
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+ tp->retrans_out -= tcp_skb_pcount(skb);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+ tcp_skb_pcount(skb));
+ tcp_notify_skb_loss_event(tp, skb);
+ }
+ } else {
tp->lost_out += tcp_skb_pcount(skb);
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ tcp_notify_skb_loss_event(tp, skb);
}
+}
+
+/* Updates the delivered and delivered_ce counts */
+static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
+ bool ece_ack)
+{
+ tp->delivered += delivered;
+ if (ece_ack)
+ tp->delivered_ce += delivered;
}
/* This procedure tags the retransmission queue when SACKs arrive.
@@ -1082,51 +1244,42 @@
static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
struct tcp_sack_block_wire *sp, int num_sacks,
- u32 prior_snd_una)
+ u32 prior_snd_una, struct tcp_sacktag_state *state)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq);
u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq);
- bool dup_sack = false;
+ u32 dup_segs;
if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
- dup_sack = true;
- tcp_dsack_seen(tp);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECV);
} else if (num_sacks > 1) {
u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq);
u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq);
- if (!after(end_seq_0, end_seq_1) &&
- !before(start_seq_0, start_seq_1)) {
- dup_sack = true;
- tcp_dsack_seen(tp);
- NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPDSACKOFORECV);
- }
+ if (after(end_seq_0, end_seq_1) || before(start_seq_0, start_seq_1))
+ return false;
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKOFORECV);
+ } else {
+ return false;
}
+ dup_segs = tcp_dsack_seen(tp, start_seq_0, end_seq_0, state);
+ if (!dup_segs) { /* Skip dubious DSACK */
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKIGNOREDDUBIOUS);
+ return false;
+ }
+
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECVSEGS, dup_segs);
+
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
+ if (tp->undo_marker && tp->undo_retrans > 0 &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
- tp->undo_retrans--;
+ tp->undo_retrans = max_t(int, 0, tp->undo_retrans - dup_segs);
- return dup_sack;
+ return true;
}
-
-struct tcp_sacktag_state {
- u32 reord;
- /* Timestamps for earliest and latest never-retransmitted segment
- * that was SACKed. RTO needs the earliest RTT to stay conservative,
- * but congestion control should still get an accurate delay signal.
- */
- u64 first_sackt;
- u64 last_sackt;
- struct rate_sample *rate;
- int flag;
- unsigned int mss_now;
-};
/* 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
@@ -1246,7 +1399,8 @@
sacked |= TCPCB_SACKED_ACKED;
state->flag |= FLAG_DATA_SACKED;
tp->sacked_out += pcount;
- tp->delivered += pcount; /* Out-of-order packets delivered */
+ /* Out-of-order packets delivered */
+ state->sack_delivered += pcount;
/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
if (tp->lost_skb_hint &&
@@ -1289,7 +1443,7 @@
*/
tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
start_seq, end_seq, dup_sack, pcount,
- skb->skb_mstamp);
+ tcp_skb_timestamp_us(skb));
tcp_rate_skb_delivered(sk, skb, state->rate);
if (skb == tp->lost_skb_hint)
@@ -1413,7 +1567,7 @@
if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
goto fallback;
- if (!tcp_skb_can_collapse_to(prev))
+ if (!tcp_skb_can_collapse(prev, skb))
goto fallback;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
@@ -1502,6 +1656,8 @@
(mss != tcp_skb_seglen(skb)))
goto out;
+ if (!tcp_skb_can_collapse(prev, skb))
+ goto out;
len = skb->len;
pcount = tcp_skb_pcount(skb);
if (tcp_skb_shift(prev, skb, pcount, len))
@@ -1578,7 +1734,7 @@
TCP_SKB_CB(skb)->end_seq,
dup_sack,
tcp_skb_pcount(skb),
- skb->skb_mstamp);
+ tcp_skb_timestamp_us(skb));
tcp_rate_skb_delivered(sk, skb, state->rate);
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
list_del_init(&skb->tcp_tsorted_anchor);
@@ -1591,9 +1747,7 @@
return skb;
}
-static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk,
- struct tcp_sacktag_state *state,
- u32 seq)
+static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk, u32 seq)
{
struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node;
struct sk_buff *skb;
@@ -1615,13 +1769,12 @@
}
static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
- struct tcp_sacktag_state *state,
u32 skip_to_seq)
{
if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq))
return skb;
- return tcp_sacktag_bsearch(sk, state, skip_to_seq);
+ return tcp_sacktag_bsearch(sk, skip_to_seq);
}
static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
@@ -1634,7 +1787,7 @@
return skb;
if (before(next_dup->start_seq, skip_to_seq)) {
- skb = tcp_sacktag_skip(skb, sk, state, next_dup->start_seq);
+ skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq);
skb = tcp_sacktag_walk(skb, sk, NULL, state,
next_dup->start_seq, next_dup->end_seq,
1);
@@ -1672,11 +1825,7 @@
tcp_highest_sack_reset(sk);
found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
- num_sacks, prior_snd_una);
- if (found_dup_sack) {
- state->flag |= FLAG_DSACKING_ACK;
- tp->delivered++; /* A spurious retransmission is delivered */
- }
+ num_sacks, prior_snd_una, state);
/* Eliminate too old ACKs, but take into
* account more or less fresh ones, they can
@@ -1778,8 +1927,7 @@
/* Head todo? */
if (before(start_seq, cache->start_seq)) {
- skb = tcp_sacktag_skip(skb, sk, state,
- start_seq);
+ skb = tcp_sacktag_skip(skb, sk, start_seq);
skb = tcp_sacktag_walk(skb, sk, next_dup,
state,
start_seq,
@@ -1805,7 +1953,7 @@
goto walk;
}
- skb = tcp_sacktag_skip(skb, sk, state, cache->end_seq);
+ skb = tcp_sacktag_skip(skb, sk, cache->end_seq);
/* Check overlap against next cached too (past this one already) */
cache++;
continue;
@@ -1816,7 +1964,7 @@
if (!skb)
break;
}
- skb = tcp_sacktag_skip(skb, sk, state, start_seq);
+ skb = tcp_sacktag_skip(skb, sk, start_seq);
walk:
skb = tcp_sacktag_walk(skb, sk, next_dup, state,
@@ -1878,34 +2026,39 @@
return;
tp->reordering = min_t(u32, tp->packets_out + addend,
- sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
tp->reord_seen++;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
}
/* Emulate SACKs for SACKless connection: account for a new dupack. */
-static void tcp_add_reno_sack(struct sock *sk)
+static void tcp_add_reno_sack(struct sock *sk, int num_dupack, bool ece_ack)
{
- struct tcp_sock *tp = tcp_sk(sk);
- u32 prior_sacked = tp->sacked_out;
+ if (num_dupack) {
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 prior_sacked = tp->sacked_out;
+ s32 delivered;
- tp->sacked_out++;
- tcp_check_reno_reordering(sk, 0);
- if (tp->sacked_out > prior_sacked)
- tp->delivered++; /* Some out-of-order packet is delivered */
- tcp_verify_left_out(tp);
+ tp->sacked_out += num_dupack;
+ tcp_check_reno_reordering(sk, 0);
+ delivered = tp->sacked_out - prior_sacked;
+ if (delivered > 0)
+ tcp_count_delivered(tp, delivered, ece_ack);
+ 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)
+static void tcp_remove_reno_sacks(struct sock *sk, int acked, bool ece_ack)
{
struct tcp_sock *tp = tcp_sk(sk);
if (acked > 0) {
/* One ACK acked hole. The rest eat duplicate ACKs. */
- tp->delivered += max_t(int, acked - tp->sacked_out, 1);
+ tcp_count_delivered(tp, max_t(int, acked - tp->sacked_out, 1),
+ ece_ack);
if (acked - 1 >= tp->sacked_out)
tp->sacked_out = 0;
else
@@ -1938,7 +2091,8 @@
static bool tcp_is_rack(const struct sock *sk)
{
- return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+ return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_LOSS_DETECTION;
}
/* If we detect SACK reneging, forget all SACK information
@@ -1982,6 +2136,7 @@
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
+ u8 reordering;
tcp_timeout_mark_lost(sk);
@@ -2002,10 +2157,12 @@
/* Timeout in disordered state after receiving substantial DUPACKs
* suggests that the degree of reordering is over-estimated.
*/
+ reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering);
if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
- tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
+ tp->sacked_out >= reordering)
tp->reordering = min_t(unsigned int, tp->reordering,
- net->ipv4.sysctl_tcp_reordering);
+ reordering);
+
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
@@ -2014,7 +2171,7 @@
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
*/
- tp->frto = net->ipv4.sysctl_tcp_frto &&
+ tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
@@ -2031,7 +2188,8 @@
*/
static bool tcp_check_sack_reneging(struct sock *sk, int flag)
{
- if (flag & FLAG_SACK_RENEGING) {
+ if (flag & FLAG_SACK_RENEGING &&
+ flag & FLAG_SND_UNA_ADVANCED) {
struct tcp_sock *tp = tcp_sk(sk);
unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
msecs_to_jiffies(10));
@@ -2172,8 +2330,7 @@
}
/* Detect loss in event "A" above by marking head of queue up as lost.
- * For non-SACK(Reno) senders, the first "packets" number of segments
- * are considered lost. For RFC3517 SACK, a segment is considered lost if it
+ * For RFC3517 SACK, a segment is considered lost if it
* has at least tp->reordering SACKed seqments above it; "packets" refers to
* the maximum SACKed segments to pass before reaching this limit.
*/
@@ -2181,10 +2338,9 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt, oldcnt, lost;
- unsigned int mss;
+ int cnt;
/* Use SACK to deduce losses of new sequences sent during recovery */
- const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq;
+ const u32 loss_high = tp->snd_nxt;
WARN_ON(packets > tp->packets_out);
skb = tp->lost_skb_hint;
@@ -2207,28 +2363,14 @@
if (after(TCP_SKB_CB(skb)->end_seq, loss_high))
break;
- oldcnt = cnt;
- if (tcp_is_reno(tp) ||
- (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
cnt += tcp_skb_pcount(skb);
- if (cnt > packets) {
- if (tcp_is_sack(tp) ||
- (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
- (oldcnt >= packets))
- break;
+ if (cnt > packets)
+ break;
- mss = tcp_skb_mss(skb);
- /* If needed, chop off the prefix to mark as lost. */
- lost = (packets - oldcnt) * mss;
- if (lost < skb->len &&
- tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
- lost, mss, GFP_ATOMIC) < 0)
- break;
- cnt = packets;
- }
-
- tcp_skb_mark_lost(tp, skb);
+ if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST))
+ tcp_mark_skb_lost(sk, skb);
if (mark_head)
break;
@@ -2272,7 +2414,7 @@
*/
static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
- return !tp->retrans_stamp ||
+ return tp->retrans_stamp &&
tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
}
@@ -2368,6 +2510,21 @@
return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
}
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ 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. */
+ if (!tcp_any_retrans_done(sk))
+ tp->retrans_stamp = 0;
+ return true;
+ }
+ return false;
+}
+
/* People celebrate: "We love our President!" */
static bool tcp_try_undo_recovery(struct sock *sk)
{
@@ -2390,14 +2547,8 @@
} else if (tp->rack.reo_wnd_persist) {
tp->rack.reo_wnd_persist--;
}
- 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. */
- if (!tcp_any_retrans_done(sk))
- tp->retrans_stamp = 0;
+ if (tcp_is_non_sack_preventing_reopen(sk))
return true;
- }
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
return false;
@@ -2433,6 +2584,8 @@
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
+ if (tcp_is_non_sack_preventing_reopen(sk))
+ return true;
if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
@@ -2479,8 +2632,8 @@
u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
tp->prior_cwnd - 1;
sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
- } else if ((flag & FLAG_RETRANS_DATA_ACKED) &&
- !(flag & FLAG_LOST_RETRANS)) {
+ } else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) ==
+ FLAG_RETRANS_DATA_ACKED) {
sndcnt = min_t(int, delta,
max_t(int, tp->prr_delivered - tp->prr_out,
newly_acked_sacked) + 1);
@@ -2566,12 +2719,15 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ u64 val;
- /* FIXME: breaks with very large cwnd */
tp->prior_ssthresh = tcp_current_ssthresh(sk);
- tp->snd_cwnd = tp->snd_cwnd *
- tcp_mss_to_mtu(sk, tp->mss_cache) /
- icsk->icsk_mtup.probe_size;
+
+ val = (u64)tp->snd_cwnd * tcp_mss_to_mtu(sk, tp->mss_cache);
+ do_div(val, icsk->icsk_mtup.probe_size);
+ WARN_ON_ONCE((u32)val != val);
+ tp->snd_cwnd = max_t(u32, 1U, val);
+
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_jiffies32;
tp->snd_ssthresh = tcp_current_ssthresh(sk);
@@ -2594,14 +2750,8 @@
unsigned int mss = tcp_current_mss(sk);
skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
- if (tcp_skb_seglen(skb) > mss &&
- !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
- 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_skb_mark_lost_uncond_verify(tp, skb);
- }
+ if (tcp_skb_seglen(skb) > mss)
+ tcp_mark_skb_lost(sk, skb);
}
tcp_clear_retrans_hints_partial(tp);
@@ -2656,13 +2806,13 @@
/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
* recovered or spurious. Otherwise retransmits more on partial ACKs.
*/
-static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
+static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
int *rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
- if ((flag & FLAG_SND_UNA_ADVANCED) &&
+ if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
tcp_try_undo_loss(sk, false))
return;
@@ -2675,7 +2825,7 @@
return;
if (after(tp->snd_nxt, tp->high_seq)) {
- if (flag & FLAG_DATA_SACKED || is_dupack)
+ if (flag & FLAG_DATA_SACKED || num_dupack)
tp->frto = 0; /* Step 3.a. loss was real */
} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
tp->high_seq = tp->snd_nxt;
@@ -2701,16 +2851,25 @@
/* A Reno DUPACK means new data in F-RTO step 2.b above are
* delivered. Lower inflight to clock out (re)tranmissions.
*/
- if (after(tp->snd_nxt, tp->high_seq) && is_dupack)
- tcp_add_reno_sack(sk);
+ if (after(tp->snd_nxt, tp->high_seq) && num_dupack)
+ tcp_add_reno_sack(sk, num_dupack, flag & FLAG_ECE);
else if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
}
*rexmit = REXMIT_LOST;
}
+static bool tcp_force_fast_retransmit(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ return after(tcp_highest_sack_seq(tp),
+ tp->snd_una + tp->reordering * tp->mss_cache);
+}
+
/* Undo during fast recovery after partial ACK. */
-static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
+static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una,
+ bool *do_lost)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2735,7 +2894,9 @@
tcp_undo_cwnd_reduction(sk, true);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
tcp_try_keep_open(sk);
- return true;
+ } else {
+ /* Partial ACK arrived. Force fast retransmit. */
+ *do_lost = tcp_force_fast_retransmit(sk);
}
return false;
}
@@ -2759,14 +2920,6 @@
}
}
-static bool tcp_force_fast_retransmit(struct sock *sk)
-{
- struct tcp_sock *tp = tcp_sk(sk);
-
- return after(tcp_highest_sack_seq(tp),
- tp->snd_una + tp->reordering * tp->mss_cache);
-}
-
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
@@ -2780,20 +2933,21 @@
* tcp_xmit_retransmit_queue().
*/
static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
- bool is_dupack, int *ack_flag, int *rexmit)
+ int num_dupack, int *ack_flag, int *rexmit)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int fast_rexmit = 0, flag = *ack_flag;
- bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
- tcp_force_fast_retransmit(sk));
+ bool ece_ack = flag & FLAG_ECE;
+ bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) &&
+ tcp_force_fast_retransmit(sk));
if (!tp->packets_out && tp->sacked_out)
tp->sacked_out = 0;
/* Now state machine starts.
* A. ECE, hence prohibit cwnd undoing, the reduction is required. */
- if (flag & FLAG_ECE)
+ if (ece_ack)
tp->prior_ssthresh = 0;
/* B. In all the states check for reneging SACKs. */
@@ -2833,35 +2987,37 @@
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
- if (tcp_is_reno(tp) && is_dupack)
- tcp_add_reno_sack(sk);
- } else {
- if (tcp_try_undo_partial(sk, prior_snd_una))
- return;
- /* Partial ACK arrived. Force fast retransmit. */
- do_lost = tcp_is_reno(tp) ||
- tcp_force_fast_retransmit(sk);
- }
- if (tcp_try_undo_dsack(sk)) {
- tcp_try_keep_open(sk);
+ if (tcp_is_reno(tp))
+ tcp_add_reno_sack(sk, num_dupack, ece_ack);
+ } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost))
return;
- }
+
+ if (tcp_try_undo_dsack(sk))
+ tcp_try_keep_open(sk);
+
tcp_identify_packet_loss(sk, ack_flag);
+ if (icsk->icsk_ca_state != TCP_CA_Recovery) {
+ if (!tcp_time_to_recover(sk, flag))
+ return;
+ /* Undo reverts the recovery state. If loss is evident,
+ * starts a new recovery (e.g. reordering then loss);
+ */
+ tcp_enter_recovery(sk, ece_ack);
+ }
break;
case TCP_CA_Loss:
- tcp_process_loss(sk, flag, is_dupack, rexmit);
+ tcp_process_loss(sk, flag, num_dupack, rexmit);
tcp_identify_packet_loss(sk, ack_flag);
if (!(icsk->icsk_ca_state == TCP_CA_Open ||
(*ack_flag & FLAG_LOST_RETRANS)))
return;
/* Change state if cwnd is undone or retransmits are lost */
- /* fall through */
+ fallthrough;
default:
if (tcp_is_reno(tp)) {
if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
- if (is_dupack)
- tcp_add_reno_sack(sk);
+ tcp_add_reno_sack(sk, num_dupack, ece_ack);
}
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
@@ -2885,7 +3041,7 @@
}
/* Otherwise enter Recovery state */
- tcp_enter_recovery(sk, (flag & FLAG_ECE));
+ tcp_enter_recovery(sk, ece_ack);
fast_rexmit = 1;
}
@@ -2896,7 +3052,7 @@
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
- u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+ u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
struct tcp_sock *tp = tcp_sk(sk);
if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -2935,6 +3091,8 @@
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+ if (!delta)
+ delta = 1;
seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
ca_rtt_us = seq_rtt_us;
}
@@ -2988,7 +3146,7 @@
/* If the retrans timer is currently being used by Fast Open
* for SYN-ACK retrans purpose, stay put.
*/
- if (tp->fastopen_rsk)
+ if (rcu_access_pointer(tp->fastopen_rsk))
return;
if (!tp->packets_out) {
@@ -3004,8 +3162,8 @@
*/
rto = usecs_to_jiffies(max_t(int, delta_us, 1));
}
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
- TCP_RTO_MAX);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
+ TCP_RTO_MAX);
}
}
@@ -3061,7 +3219,7 @@
*/
static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
u32 prior_snd_una,
- struct tcp_sacktag_state *sack)
+ struct tcp_sacktag_state *sack, bool ece_ack)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u64 first_ackt, last_ackt;
@@ -3086,8 +3244,6 @@
u8 sacked = scb->sacked;
u32 acked_pcount;
- tcp_ack_tstamp(sk, skb, prior_snd_una);
-
/* 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 ||
@@ -3107,7 +3263,7 @@
tp->retrans_out -= acked_pcount;
flag |= FLAG_RETRANS_DATA_ACKED;
} else if (!(sacked & TCPCB_SACKED_ACKED)) {
- last_ackt = skb->skb_mstamp;
+ last_ackt = tcp_skb_timestamp_us(skb);
WARN_ON_ONCE(last_ackt == 0);
if (!first_ackt)
first_ackt = last_ackt;
@@ -3122,10 +3278,10 @@
if (sacked & TCPCB_SACKED_ACKED) {
tp->sacked_out -= acked_pcount;
} else if (tcp_is_sack(tp)) {
- tp->delivered += acked_pcount;
+ tcp_count_delivered(tp, acked_pcount, ece_ack);
if (!tcp_skb_spurious_retrans(tp, skb))
tcp_rack_advance(tp, sacked, scb->end_seq,
- skb->skb_mstamp);
+ tcp_skb_timestamp_us(skb));
}
if (sacked & TCPCB_LOST)
tp->lost_out -= acked_pcount;
@@ -3151,6 +3307,8 @@
if (!fully_acked)
break;
+ tcp_ack_tstamp(sk, skb, prior_snd_una);
+
next = skb_rb_next(skb);
if (unlikely(skb == tp->retransmit_skb_hint))
tp->retransmit_skb_hint = NULL;
@@ -3166,8 +3324,11 @@
if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
tp->snd_up = tp->snd_una;
- if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
- flag |= FLAG_SACK_RENEGING;
+ if (skb) {
+ tcp_ack_tstamp(sk, skb, prior_snd_una);
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+ flag |= FLAG_SACK_RENEGING;
+ }
if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt);
@@ -3199,7 +3360,7 @@
}
if (tcp_is_reno(tp)) {
- tcp_remove_reno_sacks(sk, pkts_acked);
+ tcp_remove_reno_sacks(sk, pkts_acked, ece_ack);
/* If any of the cumulatively ACKed segments was
* retransmitted, non-SACK case cannot confirm that
@@ -3220,7 +3381,8 @@
tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
}
} else if (skb && rtt_update && sack_rtt_us >= 0 &&
- sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) {
+ sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp,
+ tcp_skb_timestamp_us(skb))) {
/* Do not re-arm RTO if the sack RTT is measured from data sent
* after when the head was last (re)transmitted. Otherwise the
* timeout may continue to extend in loss recovery.
@@ -3273,6 +3435,7 @@
return;
if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
icsk->icsk_backoff = 0;
+ icsk->icsk_probes_tstamp = 0;
inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
/* Socket must be waked up by subsequent tcp_data_snd_check().
* This function is not for random using!
@@ -3280,8 +3443,8 @@
} else {
unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
- when, TCP_RTO_MAX);
+ when = tcp_clamp_probe0_to_user_timeout(sk, when);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX);
}
}
@@ -3300,7 +3463,8 @@
* new SACK or ECE mark may first advance cwnd here and later reduce
* cwnd in tcp_fastretrans_alert() based on more states.
*/
- if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
+ if (tcp_sk(sk)->reordering >
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering))
return flag & FLAG_FORWARD_PROGRESS;
return flag & FLAG_DATA_ACKED;
@@ -3409,16 +3573,23 @@
static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
u32 *last_oow_ack_time)
{
- if (*last_oow_ack_time) {
- s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
+ /* Paired with the WRITE_ONCE() in this function. */
+ u32 val = READ_ONCE(*last_oow_ack_time);
- if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+ if (val) {
+ s32 elapsed = (s32)(tcp_jiffies32 - val);
+
+ if (0 <= elapsed &&
+ elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
}
- *last_oow_ack_time = tcp_jiffies32;
+ /* Paired with the prior READ_ONCE() and with itself,
+ * as we might be lockless.
+ */
+ WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32);
return false; /* not rate-limited: go ahead, send dupack now! */
}
@@ -3459,11 +3630,11 @@
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
- if (now != challenge_timestamp) {
- u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ if (now != READ_ONCE(challenge_timestamp)) {
+ u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
u32 half = (ack_limit + 1) >> 1;
- challenge_timestamp = now;
+ WRITE_ONCE(challenge_timestamp, now);
WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
}
count = READ_ONCE(challenge_count);
@@ -3544,10 +3715,10 @@
{
struct tcp_sock *tp = tcp_sk(sk);
- if (rexmit == REXMIT_NONE)
+ if (rexmit == REXMIT_NONE || sk->sk_state == TCP_SYN_SENT)
return;
- if (unlikely(rexmit == 2)) {
+ if (unlikely(rexmit == REXMIT_NEW)) {
__tcp_push_pending_frames(sk, tcp_current_mss(sk),
TCP_NAGLE_OFF);
if (after(tp->snd_nxt, tp->high_seq))
@@ -3566,10 +3737,9 @@
delivered = tp->delivered - prior_delivered;
NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
- if (flag & FLAG_ECE) {
- tp->delivered_ce += delivered;
+ if (flag & FLAG_ECE)
NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
- }
+
return delivered;
}
@@ -3584,7 +3754,7 @@
bool is_sack_reneg = tp->is_sack_reneg;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
- bool is_dupack = false;
+ int num_dupack = 0;
int prior_packets = tp->packets_out;
u32 delivered = tp->delivered;
u32 lost = tp->lost;
@@ -3593,6 +3763,7 @@
sack_state.first_sackt = 0;
sack_state.rate = &rs;
+ sack_state.sack_delivered = 0;
/* We very likely will need to access rtx queue. */
prefetch(sk->tcp_rtx_queue.rb_node);
@@ -3614,14 +3785,14 @@
* this segment (RFC793 Section 3.9).
*/
if (after(ack, tp->snd_nxt))
- goto invalid_ack;
+ return -1;
if (after(ack, prior_snd_una)) {
flag |= FLAG_SND_UNA_ADVANCED;
icsk->icsk_retransmits = 0;
#if IS_ENABLED(CONFIG_TLS_DEVICE)
- if (static_branch_unlikely(&clean_acked_data_enabled))
+ if (static_branch_unlikely(&clean_acked_data_enabled.key))
if (icsk->icsk_clean_acked)
icsk->icsk_clean_acked(sk, ack);
#endif
@@ -3636,7 +3807,8 @@
if (flag & FLAG_UPDATE_TS_RECENT)
tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
- if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
+ if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) ==
+ FLAG_SND_UNA_ADVANCED) {
/* Window is constant, pure forward advance.
* No more checks are required.
* Note, we use the fact that SND.UNA>=SND.WL2.
@@ -3667,6 +3839,10 @@
ack_ev_flags |= CA_ACK_ECE;
}
+ if (sack_state.sack_delivered)
+ tcp_count_delivered(tp, sack_state.sack_delivered,
+ flag & FLAG_ECE);
+
if (flag & FLAG_WIN_UPDATE)
ack_ev_flags |= CA_ACK_WIN_UPDATE;
@@ -3692,7 +3868,8 @@
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state);
+ flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state,
+ flag & FLAG_ECE);
tcp_rack_update_reo_wnd(sk, &rs);
@@ -3700,8 +3877,14 @@
tcp_process_tlp_ack(sk, ack, flag);
if (tcp_ack_is_dubious(sk, flag)) {
- is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+ if (!(flag & (FLAG_SND_UNA_ADVANCED |
+ FLAG_NOT_DUP | FLAG_DSACKING_ACK))) {
+ num_dupack = 1;
+ /* Consider if pure acks were aggregated in tcp_add_backlog() */
+ if (!(flag & FLAG_DATA))
+ num_dupack = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+ }
+ tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
}
@@ -3723,7 +3906,7 @@
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK) {
- tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+ tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
tcp_newly_delivered(sk, delivered, flag);
}
@@ -3737,10 +3920,6 @@
tcp_process_tlp_ack(sk, ack, flag);
return 1;
-invalid_ack:
- SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
- return -1;
-
old_ack:
/* If data was SACKed, tag it and see if we should send more data.
* If data was DSACKed, see if we can undo a cwnd reduction.
@@ -3748,13 +3927,12 @@
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_state);
- tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+ tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
tcp_newly_delivered(sk, delivered, flag);
tcp_xmit_recovery(sk, rexmit);
}
- SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
return 0;
}
@@ -3775,7 +3953,7 @@
foc->exp = exp_opt;
}
-static void smc_parse_options(const struct tcphdr *th,
+static bool smc_parse_options(const struct tcphdr *th,
struct tcp_options_received *opt_rx,
const unsigned char *ptr,
int opsize)
@@ -3784,10 +3962,56 @@
if (static_branch_unlikely(&tcp_have_smc)) {
if (th->syn && !(opsize & 1) &&
opsize >= TCPOLEN_EXP_SMC_BASE &&
- get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+ get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) {
opt_rx->smc_ok = 1;
+ return true;
+ }
}
#endif
+ return false;
+}
+
+/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
+ * value on success.
+ */
+static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
+{
+ const unsigned char *ptr = (const unsigned char *)(th + 1);
+ int length = (th->doff * 4) - sizeof(struct tcphdr);
+ u16 mss = 0;
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ switch (opcode) {
+ case TCPOPT_EOL:
+ return mss;
+ case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
+ length--;
+ continue;
+ default:
+ if (length < 2)
+ return mss;
+ opsize = *ptr++;
+ if (opsize < 2) /* "silly options" */
+ return mss;
+ if (opsize > length)
+ return mss; /* fail on partial options */
+ if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) {
+ u16 in_mss = get_unaligned_be16(ptr);
+
+ if (in_mss) {
+ if (user_mss && user_mss < in_mss)
+ in_mss = user_mss;
+ mss = in_mss;
+ }
+ }
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+ }
+ return mss;
}
/* Look for tcp options. Normally only called on SYN and SYNACK packets.
@@ -3805,6 +4029,7 @@
ptr = (const unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
+ opt_rx->saw_unknown = 0;
while (length > 0) {
int opcode = *ptr++;
@@ -3817,6 +4042,8 @@
length--;
continue;
default:
+ if (length < 2)
+ return;
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
@@ -3836,7 +4063,7 @@
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && net->ipv4.sysctl_tcp_window_scaling) {
+ !estab && READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > TCP_MAX_WSCALE) {
@@ -3852,7 +4079,7 @@
case TCPOPT_TIMESTAMP:
if ((opsize == TCPOLEN_TIMESTAMP) &&
((estab && opt_rx->tstamp_ok) ||
- (!estab && net->ipv4.sysctl_tcp_timestamps))) {
+ (!estab && READ_ONCE(net->ipv4.sysctl_tcp_timestamps)))) {
opt_rx->saw_tstamp = 1;
opt_rx->rcv_tsval = get_unaligned_be32(ptr);
opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -3860,7 +4087,7 @@
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && net->ipv4.sysctl_tcp_sack) {
+ !estab && READ_ONCE(net->ipv4.sysctl_tcp_sack)) {
opt_rx->sack_ok = TCP_SACK_SEEN;
tcp_sack_reset(opt_rx);
}
@@ -3893,15 +4120,21 @@
*/
if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE &&
get_unaligned_be16(ptr) ==
- TCPOPT_FASTOPEN_MAGIC)
+ TCPOPT_FASTOPEN_MAGIC) {
tcp_parse_fastopen_option(opsize -
TCPOLEN_EXP_FASTOPEN_BASE,
ptr + 2, th->syn, foc, true);
- else
- smc_parse_options(th, opt_rx, ptr,
- opsize);
+ break;
+ }
+
+ if (smc_parse_options(th, opt_rx, ptr, opsize))
+ break;
+
+ opt_rx->saw_unknown = 1;
break;
+ default:
+ opt_rx->saw_unknown = 1;
}
ptr += opsize-2;
length -= opsize;
@@ -4109,7 +4342,7 @@
inet_csk_schedule_ack(sk);
- sk->sk_shutdown |= RCV_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
sock_set_flag(sk, SOCK_DONE);
switch (sk->sk_state) {
@@ -4117,7 +4350,7 @@
case TCP_ESTABLISHED:
/* Move to CLOSE_WAIT */
tcp_set_state(sk, TCP_CLOSE_WAIT);
- inet_csk(sk)->icsk_ack.pingpong = 1;
+ inet_csk_enter_pingpong_mode(sk);
break;
case TCP_CLOSE_WAIT:
@@ -4189,7 +4422,7 @@
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4215,6 +4448,18 @@
tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
}
+static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
+{
+ /* When the ACK path fails or drops most ACKs, the sender would
+ * timeout and spuriously retransmit the same segment repeatedly.
+ * The receiver remembers and reflects via DSACKs. Leverage the
+ * DSACK state and change the txhash to re-route speculatively.
+ */
+ if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq &&
+ sk_rethink_txhash(sk))
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
+}
+
static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -4224,9 +4469,10 @@
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_spurious_retrans(sk, skb);
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
end_seq = tp->rcv_nxt;
tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq);
@@ -4260,9 +4506,37 @@
sp[i] = sp[i + 1];
continue;
}
- this_sack++, swalk++;
+ this_sack++;
+ swalk++;
}
}
+
+static void tcp_sack_compress_send_ack(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tp->compressed_ack)
+ return;
+
+ if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
+ __sock_put(sk);
+
+ /* Since we have to send one ack finally,
+ * substract one from tp->compressed_ack to keep
+ * LINUX_MIB_TCPACKCOMPRESSED accurate.
+ */
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
+ tp->compressed_ack - 1);
+
+ tp->compressed_ack = 0;
+ tcp_send_ack(sk);
+}
+
+/* Reasonable amount of sack blocks included in TCP SACK option
+ * The max is 4, but this becomes 3 if TCP timestamps are there.
+ * Given that SACK packets might be lost, be conservative and use 2.
+ */
+#define TCP_SACK_BLOCKS_EXPECTED 2
static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
{
@@ -4276,6 +4550,8 @@
for (this_sack = 0; this_sack < cur_sacks; this_sack++, sp++) {
if (tcp_sack_extend(sp, seq, end_seq)) {
+ if (this_sack >= TCP_SACK_BLOCKS_EXPECTED)
+ tcp_sack_compress_send_ack(sk);
/* Rotate this_sack to the first one. */
for (; this_sack > 0; this_sack--, sp--)
swap(*sp, *(sp - 1));
@@ -4285,6 +4561,9 @@
}
}
+ if (this_sack >= TCP_SACK_BLOCKS_EXPECTED)
+ tcp_sack_compress_send_ack(sk);
+
/* Could not find an adjacent existing SACK, build a new one,
* put it at the front, and shift everyone else down. We
* always know there is at least one SACK present already here.
@@ -4292,8 +4571,6 @@
* If the sack array is full, forget about the last one.
*/
if (this_sack >= TCP_NUM_SACKS) {
- if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
- tcp_send_ack(sk);
this_sack--;
tp->rx_opt.num_sacks--;
sp--;
@@ -4345,7 +4622,6 @@
/**
* tcp_try_coalesce - try to merge skb to prior one
* @sk: socket
- * @dest: destination queue
* @to: prior buffer
* @from: buffer to add in queue
* @fragstolen: pointer to boolean
@@ -4367,6 +4643,9 @@
/* Its possible this segment overlaps with prior segment in queue */
if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
+ return false;
+
+ if (!mptcp_skb_can_collapse(to, from))
return false;
#ifdef CONFIG_TLS_DEVICE
@@ -4412,6 +4691,7 @@
static void tcp_drop(struct sock *sk, struct sk_buff *skb)
{
+ trace_android_vh_kfree_skb(skb);
sk_drops_add(sk, skb);
__kfree_skb(skb);
}
@@ -4443,13 +4723,9 @@
rb_erase(&skb->rbnode, &tp->out_of_order_queue);
if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
- SOCK_DEBUG(sk, "ofo packet was already received\n");
tcp_drop(sk, skb);
continue;
}
- SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
- tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
- TCP_SKB_CB(skb)->end_seq);
tail = skb_peek_tail(&sk->sk_receive_queue);
eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
@@ -4511,11 +4787,10 @@
tp->pred_flags = 0;
inet_csk_schedule_ack(sk);
+ tp->rcv_ooopack += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE);
seq = TCP_SKB_CB(skb)->seq;
end_seq = TCP_SKB_CB(skb)->end_seq;
- SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
- tp->rcv_nxt, seq, end_seq);
p = &tp->out_of_order_queue.rb_node;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
@@ -4541,7 +4816,7 @@
* and trigger fast retransmit.
*/
if (tcp_is_sack(tp))
- tcp_grow_window(sk, skb);
+ tcp_grow_window(sk, skb, true);
kfree_skb_partial(skb, fragstolen);
skb = NULL;
goto add_sack;
@@ -4629,19 +4904,18 @@
* and trigger fast retransmit.
*/
if (tcp_is_sack(tp))
- tcp_grow_window(sk, skb);
+ tcp_grow_window(sk, skb, false);
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
}
-static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen,
- bool *fragstolen)
+static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
+ bool *fragstolen)
{
int eaten;
struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue);
- __skb_pull(skb, hdrlen);
eaten = (tail &&
tcp_try_coalesce(sk, tail,
skb, fragstolen)) ? 1 : 0;
@@ -4692,7 +4966,7 @@
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
- if (tcp_queue_rcv(sk, skb, 0, &fragstolen)) {
+ if (tcp_queue_rcv(sk, skb, &fragstolen)) {
WARN_ON_ONCE(fragstolen); /* should not happen */
__kfree_skb(skb);
}
@@ -4724,6 +4998,9 @@
bool fragstolen;
int eaten;
+ if (sk_is_mptcp(sk))
+ mptcp_incoming_options(sk, skb);
+
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
__kfree_skb(skb);
return;
@@ -4753,7 +5030,7 @@
goto drop;
}
- eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
+ eaten = tcp_queue_rcv(sk, skb, &fragstolen);
if (skb->len)
tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -4782,6 +5059,7 @@
}
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
+ tcp_rcv_spurious_retrans(sk, skb);
/* A retransmit, 2nd most common case. Force an immediate ack. */
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
@@ -4800,10 +5078,6 @@
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",
- tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
- TCP_SKB_CB(skb)->end_seq);
-
tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, tp->rcv_nxt);
/* If window is closed, drop tail of packet. But after
@@ -4897,7 +5171,7 @@
/* The first skb to collapse is:
* - not SYN/FIN and
* - bloated or contains data before "start" or
- * overlaps to the next one.
+ * overlaps to the next one and mptcp allow collapsing.
*/
if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
(tcp_win_from_space(sk, skb->truesize) > skb->len ||
@@ -4906,7 +5180,7 @@
break;
}
- if (n && n != tail &&
+ if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&
TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
end_of_skbs = false;
break;
@@ -4939,6 +5213,7 @@
else
__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */
skb_set_owner_r(nskb, sk);
+ mptcp_skb_ext_move(nskb, skb);
/* Copy data, releasing collapsed skbs. */
while (copy > 0) {
@@ -4958,6 +5233,7 @@
skb = tcp_collapse_one(sk, skb, list, root);
if (!skb ||
skb == tail ||
+ !mptcp_skb_can_collapse(nskb, skb) ||
(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
goto end;
#ifdef CONFIG_TLS_DEVICE
@@ -5082,8 +5358,6 @@
{
struct tcp_sock *tp = tcp_sk(sk);
- SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq);
-
NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED);
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
@@ -5149,12 +5423,6 @@
return true;
}
-/* When incoming ACK allowed to free some skb from write_queue,
- * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket
- * on the exit from tcp input handler.
- *
- * PROBLEM: sndbuf expansion does not work well with largesend.
- */
static void tcp_new_space(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -5167,18 +5435,25 @@
sk->sk_write_space(sk);
}
-static void tcp_check_space(struct sock *sk)
+/* Caller made space either from:
+ * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced)
+ * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt)
+ *
+ * We might be able to generate EPOLLOUT to the application if:
+ * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2
+ * 2) notsent amount (tp->write_seq - tp->snd_nxt) became
+ * small enough that tcp_stream_memory_free() decides it
+ * is time to generate EPOLLOUT.
+ */
+void tcp_check_space(struct sock *sk)
{
- if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
- sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
- /* pairs with tcp_poll() */
- smp_mb();
- if (sk->sk_socket &&
- test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
- tcp_new_space(sk);
- if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
- tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
- }
+ /* pairs with tcp_poll() */
+ smp_mb();
+ if (sk->sk_socket &&
+ test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+ tcp_new_space(sk);
+ if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
+ tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
}
@@ -5220,20 +5495,18 @@
}
if (!tcp_is_sack(tp) ||
- tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+ tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
goto send_now;
if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
tp->compressed_ack_rcv_nxt = tp->rcv_nxt;
- if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
- NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
- tp->compressed_ack - TCP_FASTRETRANS_THRESH);
- tp->compressed_ack = 0;
+ tp->dup_ack_counter = 0;
}
-
- if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH)
+ if (tp->dup_ack_counter < TCP_FASTRETRANS_THRESH) {
+ tp->dup_ack_counter++;
goto send_now;
-
+ }
+ tp->compressed_ack++;
if (hrtimer_is_queued(&tp->compressed_ack_timer))
return;
@@ -5243,11 +5516,13 @@
if (tp->srtt_us && tp->srtt_us < rtt)
rtt = tp->srtt_us;
- delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+ delay = min_t(unsigned long,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
rtt * (NSEC_PER_USEC >> 3)/20);
sock_hold(sk);
- hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
- HRTIMER_MODE_REL_PINNED_SOFT);
+ hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
+ HRTIMER_MODE_REL_PINNED_SOFT);
}
static inline void tcp_ack_snd_check(struct sock *sk)
@@ -5274,7 +5549,7 @@
struct tcp_sock *tp = tcp_sk(sk);
u32 ptr = ntohs(th->urg_ptr);
- if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
+ if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg))
ptr--;
ptr += ntohl(th->seq);
@@ -5328,7 +5603,7 @@
}
tp->urg_data = TCP_URG_NOTYET;
- tp->urg_seq = ptr;
+ WRITE_ONCE(tp->urg_seq, ptr);
/* Disable header prediction. */
tp->pred_flags = 0;
@@ -5481,6 +5756,8 @@
goto discard;
}
+ bpf_skops_parse_hdr(sk, skb);
+
return true;
discard:
@@ -5521,7 +5798,7 @@
trace_tcp_probe(sk, skb);
tcp_mstamp_refresh(tp);
- if (unlikely(!sk->sk_rx_dst))
+ if (unlikely(!rcu_access_pointer(sk->sk_rx_dst)))
inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
/*
* Header prediction.
@@ -5628,8 +5905,8 @@
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
/* Bulk data transfer: receiver */
- eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
- &fragstolen);
+ __skb_pull(skb, tcp_header_len);
+ eaten = tcp_queue_rcv(sk, skb, &fragstolen);
tcp_event_data_recv(sk, skb);
@@ -5691,6 +5968,34 @@
}
EXPORT_SYMBOL(tcp_rcv_established);
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ tcp_mtup_init(sk);
+ icsk->icsk_af_ops->rebuild_header(sk);
+ tcp_init_metrics(sk);
+
+ /* Initialize the congestion window to start the transfer.
+ * Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
+ * retransmitted. In light of RFC6298 more aggressive 1sec
+ * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
+ * retransmission has occurred.
+ */
+ if (tp->total_retrans > 1 && tp->undo_marker)
+ tp->snd_cwnd = 1;
+ else
+ tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
+ tp->snd_cwnd_stamp = tcp_jiffies32;
+
+ bpf_skops_established(sk, bpf_op, skb);
+ /* Initialize congestion control unless BPF initialized it already: */
+ if (!icsk->icsk_ca_initialized)
+ tcp_init_congestion_control(sk);
+ tcp_init_buffer_space(sk);
+}
+
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -5705,7 +6010,7 @@
sk_mark_napi_id(sk, skb);
}
- tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
+ tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb);
/* Prevent spurious tcp_cwnd_restart() on first data
* packet.
@@ -5760,6 +6065,10 @@
tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
if (data) { /* Retransmit unacked data in SYN */
+ if (tp->total_retrans)
+ tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED;
+ else
+ tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
skb_rbtree_walk_from(data) {
if (__tcp_retransmit_skb(sk, data, 1))
break;
@@ -5792,6 +6101,21 @@
#endif
}
+static void tcp_try_undo_spurious_syn(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 syn_stamp;
+
+ /* undo_marker is set when SYN or SYNACK times out. The timeout is
+ * spurious if the ACK's timestamp option echo value matches the
+ * original SYN timestamp.
+ */
+ syn_stamp = tp->retrans_stamp;
+ if (tp->undo_marker && syn_stamp && tp->rx_opt.saw_tstamp &&
+ syn_stamp == tp->rx_opt.rcv_tsecr)
+ tp->undo_marker = 0;
+}
+
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th)
{
@@ -5815,8 +6139,14 @@
* the segment and return)"
*/
if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) ||
- after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt))
+ after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
+ /* Previous FIN/ACK or RST/ACK might be ignored. */
+ if (icsk->icsk_retransmits == 0)
+ inet_csk_reset_xmit_timer(sk,
+ ICSK_TIME_RETRANS,
+ TCP_TIMEOUT_MIN, TCP_RTO_MAX);
goto reset_and_undo;
+ }
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
!between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp,
@@ -5859,6 +6189,7 @@
tcp_ecn_rcv_synack(tp, th);
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
+ tcp_try_undo_spurious_syn(sk);
tcp_ack(sk, skb, FLAG_SLOWPATH);
/* Ok.. it's good. Set up sequence numbers and
@@ -5912,7 +6243,7 @@
return -1;
if (sk->sk_write_pending ||
icsk->icsk_accept_queue.rskq_defer_accept ||
- icsk->icsk_ack.pingpong) {
+ inet_csk_in_pingpong_mode(sk)) {
/* Save one ACK. Data will be ready after
* several ticks, if write_pending is set.
*
@@ -6017,6 +6348,38 @@
return 1;
}
+static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
+{
+ struct request_sock *req;
+
+ /* If we are still handling the SYNACK RTO, see if timestamp ECR allows
+ * undo. If peer SACKs triggered fast recovery, we can't undo here.
+ */
+ if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
+ tcp_try_undo_loss(sk, false);
+
+ /* Reset rtx states to prevent spurious retransmits_timed_out() */
+ tcp_sk(sk)->retrans_stamp = 0;
+ inet_csk(sk)->icsk_retransmits = 0;
+
+ /* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
+ * we no longer need req so release it.
+ */
+ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+ lockdep_sock_is_held(sk));
+ reqsk_fastopen_remove(sk, req, false);
+
+ /* Re-arm the timer because data may have been sent out.
+ * This is similar to the regular data transmission case
+ * when new data has just been ack'ed.
+ *
+ * (TFO) - we could try to be more aggressive and
+ * retransmitting any data sooner based on when they
+ * are sent out.
+ */
+ tcp_rearm_rto(sk);
+}
+
/*
* This function implements the receiving procedure of RFC 793 for
* all states except ESTABLISHED and TIME_WAIT.
@@ -6079,7 +6442,8 @@
tcp_mstamp_refresh(tp);
tp->rx_opt.saw_tstamp = 0;
- req = tp->fastopen_rsk;
+ req = rcu_dereference_protected(tp->fastopen_rsk,
+ lockdep_sock_is_held(sk));
if (req) {
bool req_stolen;
@@ -6113,23 +6477,13 @@
if (!tp->srtt_us)
tcp_synack_rtt_meas(sk, req);
- /* Once we leave TCP_SYN_RECV, we no longer need req
- * so release it.
- */
if (req) {
- inet_csk(sk)->icsk_retransmits = 0;
- reqsk_fastopen_remove(sk, req, false);
- /* Re-arm the timer because data may have been sent out.
- * This is similar to the regular data transmission case
- * when new data has just been ack'ed.
- *
- * (TFO) - we could try to be more aggressive and
- * retransmitting any data sooner based on when they
- * are sent out.
- */
- tcp_rearm_rto(sk);
+ tcp_rcv_synrecv_state_fastopen(sk);
} else {
- tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+ tcp_try_undo_spurious_syn(sk);
+ tp->retrans_stamp = 0;
+ tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,
+ skb);
WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
}
smp_mb();
@@ -6163,21 +6517,14 @@
case TCP_FIN_WAIT1: {
int tmo;
- /* If we enter the TCP_FIN_WAIT1 state and we are a
- * Fast Open socket and this is the first acceptable
- * ACK we have received, this would have acknowledged
- * our SYNACK so stop the SYNACK timer.
- */
- if (req) {
- /* We no longer need the request sock. */
- reqsk_fastopen_remove(sk, req, false);
- tcp_rearm_rto(sk);
- }
+ if (req)
+ tcp_rcv_synrecv_state_fastopen(sk);
+
if (tp->snd_una != tp->write_seq)
break;
tcp_set_state(sk, TCP_FIN_WAIT2);
- sk->sk_shutdown |= SEND_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
sk_dst_confirm(sk);
@@ -6244,9 +6591,12 @@
case TCP_CLOSE_WAIT:
case TCP_CLOSING:
case TCP_LAST_ACK:
- if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
+ if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
+ if (sk_is_mptcp(sk))
+ mptcp_incoming_options(sk, skb);
break;
- /* fall through */
+ }
+ fallthrough;
case TCP_FIN_WAIT1:
case TCP_FIN_WAIT2:
/* RFC 793 says to queue data in these states,
@@ -6261,7 +6611,7 @@
return 1;
}
}
- /* Fall through */
+ fallthrough;
case TCP_ESTABLISHED:
tcp_data_queue(sk, skb);
queued = 1;
@@ -6307,6 +6657,11 @@
* congestion control: Linux DCTCP asserts ECT on all packets,
* including SYN, which is most optimal solution; however,
* others, such as FreeBSD do not.
+ *
+ * Exception: At least one of the reserved bits of the TCP header (th->res1) is
+ * set, indicating the use of a future TCP extension (such as AccECN). See
+ * RFC8311 ยง4.3 which updates RFC3168 to allow the development of such
+ * extensions.
*/
static void tcp_ecn_create_request(struct request_sock *req,
const struct sk_buff *skb,
@@ -6326,7 +6681,7 @@
ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
- if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
+ if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
(ecn_ok_dst & DST_FEATURE_ECN_CA) ||
tcp_bpf_ca_needs_ecn((struct sock *)req))
inet_rsk(req)->ecn_ok = 1;
@@ -6339,10 +6694,9 @@
struct inet_request_sock *ireq = inet_rsk(req);
req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */
- req->cookie_ts = 0;
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
- tcp_rsk(req)->snt_synack = tcp_clock_us();
+ tcp_rsk(req)->snt_synack = 0;
tcp_rsk(req)->last_oow_ack_time = 0;
req->mss = rx_opt->mss_clamp;
req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
@@ -6387,17 +6741,18 @@
/*
* Return true if a syncookie should be sent
*/
-static bool tcp_syn_flood_action(const struct sock *sk,
- const struct sk_buff *skb,
- const char *proto)
+static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
{
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
const char *msg = "Dropping request";
- bool want_cookie = false;
struct net *net = sock_net(sk);
+ bool want_cookie = false;
+ u8 syncookies;
+
+ syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
#ifdef CONFIG_SYN_COOKIES
- if (net->ipv4.sysctl_tcp_syncookies) {
+ if (syncookies) {
msg = "Sending cookies";
want_cookie = true;
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
@@ -6405,11 +6760,10 @@
#endif
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
- if (!queue->synflood_warned &&
- net->ipv4.sysctl_tcp_syncookies != 2 &&
+ if (!queue->synflood_warned && syncookies != 2 &&
xchg(&queue->synflood_warned, 1) == 0)
net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n",
- proto, ntohs(tcp_hdr(skb)->dest), msg);
+ proto, sk->sk_num, msg);
return want_cookie;
}
@@ -6420,16 +6774,60 @@
{
if (tcp_sk(sk)->save_syn) {
u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
- u32 *copy;
+ struct saved_syn *saved_syn;
+ u32 mac_hdrlen;
+ void *base;
- copy = kmalloc(len + sizeof(u32), GFP_ATOMIC);
- if (copy) {
- copy[0] = len;
- memcpy(©[1], skb_network_header(skb), len);
- req->saved_syn = copy;
+ if (tcp_sk(sk)->save_syn == 2) { /* Save full header. */
+ base = skb_mac_header(skb);
+ mac_hdrlen = skb_mac_header_len(skb);
+ len += mac_hdrlen;
+ } else {
+ base = skb_network_header(skb);
+ mac_hdrlen = 0;
+ }
+
+ saved_syn = kmalloc(struct_size(saved_syn, data, len),
+ GFP_ATOMIC);
+ if (saved_syn) {
+ saved_syn->mac_hdrlen = mac_hdrlen;
+ saved_syn->network_hdrlen = skb_network_header_len(skb);
+ saved_syn->tcp_hdrlen = tcp_hdrlen(skb);
+ memcpy(saved_syn->data, base, len);
+ req->saved_syn = saved_syn;
}
}
}
+
+/* If a SYN cookie is required and supported, returns a clamped MSS value to be
+ * used for SYN cookie generation.
+ */
+u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
+ const struct tcp_request_sock_ops *af_ops,
+ struct sock *sk, struct tcphdr *th)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u16 mss;
+
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 &&
+ !inet_csk_reqsk_queue_is_full(sk))
+ return 0;
+
+ if (!tcp_syn_flood_action(sk, rsk_ops->slab_name))
+ return 0;
+
+ if (sk_acceptq_is_full(sk)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+ return 0;
+ }
+
+ mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss);
+ if (!mss)
+ mss = af_ops->mss_clamp;
+
+ return mss;
+}
+EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss);
int tcp_conn_request(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
@@ -6445,14 +6843,16 @@
bool want_cookie = false;
struct dst_entry *dst;
struct flowi fl;
+ u8 syncookies;
+
+ syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
/* TW buckets are converted to open requests without
* limitations, they conserve resources and peer is
* evidently real one.
*/
- if ((net->ipv4.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 ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) {
+ want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
if (!want_cookie)
goto drop;
}
@@ -6466,8 +6866,12 @@
if (!req)
goto drop;
+ req->syncookie = want_cookie;
tcp_rsk(req)->af_specific = af_ops;
tcp_rsk(req)->ts_off = 0;
+#if IS_ENABLED(CONFIG_MPTCP)
+ tcp_rsk(req)->is_mptcp = 0;
+#endif
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = af_ops->mss_clamp;
@@ -6501,10 +6905,12 @@
goto drop_and_free;
if (!want_cookie && !isn) {
+ int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
+
/* Kill the following clause, if you dislike this way. */
- if (!net->ipv4.sysctl_tcp_syncookies &&
- (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
- (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
+ if (!syncookies &&
+ (max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+ (max_syn_backlog >> 2)) &&
!tcp_peer_is_proven(req, dst)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,
@@ -6525,13 +6931,13 @@
if (want_cookie) {
isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
- req->cookie_ts = tmp_opt.tstamp_ok;
if (!tmp_opt.tstamp_ok)
inet_rsk(req)->ecn_ok = 0;
}
tcp_rsk(req)->snt_isn = isn;
tcp_rsk(req)->txhash = net_tx_rndhash();
+ tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
tcp_openreq_init_rwin(req, sk, dst);
sk_rx_queue_set(req_to_sk(req), skb);
if (!want_cookie) {
@@ -6540,14 +6946,13 @@
}
if (fastopen_sk) {
af_ops->send_synack(fastopen_sk, dst, &fl, req,
- &foc, TCP_SYNACK_FASTOPEN);
+ &foc, TCP_SYNACK_FASTOPEN, skb);
/* Add the child socket directly into the accept queue */
if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
reqsk_fastopen_remove(fastopen_sk, req, false);
bh_unlock_sock(fastopen_sk);
sock_put(fastopen_sk);
- reqsk_put(req);
- goto drop;
+ goto drop_and_free;
}
sk->sk_data_ready(sk);
bh_unlock_sock(fastopen_sk);
@@ -6559,7 +6964,8 @@
tcp_timeout_init((struct sock *)req));
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :
- TCP_SYNACK_COOKIE);
+ TCP_SYNACK_COOKIE,
+ skb);
if (want_cookie) {
reqsk_free(req);
return 0;
@@ -6571,7 +6977,7 @@
drop_and_release:
dst_release(dst);
drop_and_free:
- reqsk_free(req);
+ __reqsk_free(req);
drop:
tcp_listendrop(sk);
return 0;
--
Gitblit v1.6.2