summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_input.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r--net/ipv4/tcp_input.c107
1 files changed, 50 insertions, 57 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 52b5c2d0ecd..976034f8232 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -105,7 +105,6 @@ int sysctl_tcp_abc __read_mostly;
#define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */
#define FLAG_DATA_SACKED 0x20 /* New SACK. */
#define FLAG_ECE 0x40 /* ECE in this ACK */
-#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
@@ -322,7 +321,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_memory_pressure) {
+ !sk_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
@@ -411,8 +410,8 @@ static void tcp_clamp_window(struct sock *sk)
if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
- !tcp_memory_pressure &&
- atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+ !sk_under_memory_pressure(sk) &&
+ sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
sysctl_tcp_rmem[2]);
}
@@ -865,13 +864,13 @@ static void tcp_disable_fack(struct tcp_sock *tp)
/* RFC3517 uses different metric in lost marker => reset on change */
if (tcp_is_fack(tp))
tp->lost_skb_hint = NULL;
- tp->rx_opt.sack_ok &= ~2;
+ tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED;
}
/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
- tp->rx_opt.sack_ok |= 4;
+ tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
}
/* Initialize metrics on socket. */
@@ -1040,13 +1039,11 @@ static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp,
* These 6 states form finite state machine, controlled by the following events:
* 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue())
* 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue())
- * 3. Loss detection event of one of three flavors:
+ * 3. Loss detection event of two flavors:
* A. Scoreboard estimator decided the packet is lost.
* A'. Reno "three dupacks" marks head of queue lost.
- * A''. Its FACK modfication, head until snd.fack is lost.
- * B. SACK arrives sacking data transmitted after never retransmitted
- * hole was sent out.
- * C. SACK arrives sacking SND.NXT at the moment, when the
+ * A''. Its FACK modification, head until snd.fack is lost.
+ * B. SACK arrives sacking SND.NXT at the moment, when the
* segment was retransmitted.
* 4. D-SACK added new rule: D-SACK changes any tag to S.
*
@@ -1153,7 +1150,7 @@ static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack,
}
/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".
- * Event "C". Later note: FACK people cheated me again 8), we have to account
+ * Event "B". Later note: FACK people cheated me again 8), we have to account
* for reordering! Ugly, but should help.
*
* Search retransmitted skbs from write_queue that were sent when snd_nxt was
@@ -1844,10 +1841,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
if (found_dup_sack && ((i + 1) == first_sack_index))
next_dup = &sp[i + 1];
- /* Event "B" in the comment above. */
- if (after(end_seq, tp->high_seq))
- state.flag |= FLAG_DATA_LOST;
-
/* Skip too early cached blocks */
while (tcp_sack_cache_ok(tp, cache) &&
!before(start_seq, cache->end_seq))
@@ -2515,8 +2508,11 @@ static void tcp_timeout_skbs(struct sock *sk)
tcp_verify_left_out(tp);
}
-/* Mark head of queue up as lost. With RFC3517 SACK, the packets is
- * is against sacked "cnt", otherwise it's against facked "cnt"
+/* Detect loss in event "A" above by marking head of queue up as lost.
+ * For FACK or non-SACK(Reno) senders, the first "packets" number of segments
+ * are considered lost. 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.
*/
static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
@@ -2525,6 +2521,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
int cnt, oldcnt;
int err;
unsigned int mss;
+ /* 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;
WARN_ON(packets > tp->packets_out);
if (tp->lost_skb_hint) {
@@ -2546,7 +2544,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
tp->lost_skb_hint = skb;
tp->lost_cnt_hint = cnt;
- if (after(TCP_SKB_CB(skb)->end_seq, tp->high_seq))
+ if (after(TCP_SKB_CB(skb)->end_seq, loss_high))
break;
oldcnt = cnt;
@@ -2663,7 +2661,7 @@ static void DBGUNDO(struct sock *sk, const char *msg)
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
@@ -2858,7 +2856,7 @@ static void tcp_try_keep_open(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
int state = TCP_CA_Open;
- if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker)
+ if (tcp_left_out(tp) || tcp_any_retrans_done(sk))
state = TCP_CA_Disorder;
if (inet_csk(sk)->icsk_ca_state != state) {
@@ -2881,7 +2879,8 @@ static void tcp_try_to_open(struct sock *sk, int flag)
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
tcp_try_keep_open(sk);
- tcp_moderate_cwnd(tp);
+ if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+ tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_down(sk, flag);
}
@@ -3009,11 +3008,11 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked,
* tcp_xmit_retransmit_queue().
*/
static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
- int newly_acked_sacked, int flag)
+ int newly_acked_sacked, bool is_dupack,
+ int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
int fast_rexmit = 0, mib_idx;
@@ -3032,19 +3031,10 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (tcp_check_sack_reneging(sk, flag))
return;
- /* C. Process data loss notification, provided it is valid. */
- if (tcp_is_fack(tp) && (flag & FLAG_DATA_LOST) &&
- before(tp->snd_una, tp->high_seq) &&
- icsk->icsk_ca_state != TCP_CA_Open &&
- tp->fackets_out > tp->reordering) {
- tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering, 0);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSS);
- }
-
- /* D. Check consistency of the current state. */
+ /* C. Check consistency of the current state. */
tcp_verify_left_out(tp);
- /* E. Check state exit conditions. State can be terminated
+ /* D. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
if (icsk->icsk_ca_state == TCP_CA_Open) {
WARN_ON(tp->retrans_out != 0);
@@ -3066,17 +3056,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
}
break;
- case TCP_CA_Disorder:
- tcp_try_undo_dsack(sk);
- if (!tp->undo_marker ||
- /* For SACK case do not Open to allow to undo
- * catching for all duplicate ACKs. */
- tcp_is_reno(tp) || tp->snd_una != tp->high_seq) {
- tp->undo_marker = 0;
- tcp_set_ca_state(sk, TCP_CA_Open);
- }
- break;
-
case TCP_CA_Recovery:
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
@@ -3087,7 +3066,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
}
}
- /* F. Process state. */
+ /* E. Process state. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
@@ -3117,7 +3096,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
tcp_add_reno_sack(sk);
}
- if (icsk->icsk_ca_state == TCP_CA_Disorder)
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk)) {
@@ -3681,10 +3660,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
u32 prior_snd_una = tp->snd_una;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
+ bool is_dupack = false;
u32 prior_in_flight;
u32 prior_fackets;
int prior_packets;
int prior_sacked = tp->sacked_out;
+ int pkts_acked = 0;
int newly_acked_sacked = 0;
int frto_cwnd = 0;
@@ -3757,6 +3738,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
/* See if we can take anything off of the retransmit queue. */
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
+ pkts_acked = prior_packets - tp->packets_out;
newly_acked_sacked = (prior_packets - prior_sacked) -
(tp->packets_out - tp->sacked_out);
@@ -3771,8 +3753,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
- tcp_fastretrans_alert(sk, prior_packets - tp->packets_out,
- newly_acked_sacked, flag);
+ is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
+ tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ is_dupack, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
tcp_cong_avoid(sk, ack, prior_in_flight);
@@ -3784,6 +3767,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
return 1;
no_queue:
+ /* If data was DSACKed, see if we can undo a cwnd reduction. */
+ if (flag & FLAG_DSACKING_ACK)
+ tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ is_dupack, flag);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
@@ -3797,10 +3784,14 @@ invalid_ack:
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.
+ */
if (TCP_SKB_CB(skb)->sacked) {
- tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- if (icsk->icsk_ca_state == TCP_CA_Open)
- tcp_try_keep_open(sk);
+ flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+ newly_acked_sacked = tp->sacked_out - prior_sacked;
+ tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ is_dupack, flag);
}
SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
@@ -3876,7 +3867,7 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
!estab && sysctl_tcp_sack) {
- opt_rx->sack_ok = 1;
+ opt_rx->sack_ok = TCP_SACK_SEEN;
tcp_sack_reset(opt_rx);
}
break;
@@ -4864,7 +4855,7 @@ static int tcp_prune_queue(struct sock *sk)
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
tcp_clamp_window(sk);
- else if (tcp_memory_pressure)
+ else if (sk_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tcp_collapse_ofo_queue(sk);
@@ -4930,11 +4921,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk)
return 0;
/* If we are under global TCP memory pressure, do not expand. */
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
return 0;
/* If we are under soft global TCP memory pressure, do not expand. */
- if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+ if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
return 0;
/* If we filled the congestion window, do not expand. */
@@ -5809,6 +5800,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
goto discard;
if (th->syn) {
+ if (th->fin)
+ goto discard;
if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
return 1;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-19 00:47:06 +0000