aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/inet_timewait_sock.c6
-rw-r--r--net/ipv4/tcp.c1
-rw-r--r--net/ipv4/tcp_bbr.c12
-rw-r--r--net/ipv4/tcp_input.c12
-rw-r--r--net/ipv4/tcp_ipv4.c59
-rw-r--r--net/ipv4/tcp_minisocks.c6
-rw-r--r--net/ipv4/tcp_rate.c10
-rw-r--r--net/ipv4/tcp_recovery.c28
8 files changed, 90 insertions, 44 deletions
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index c690cd0d9b3f..b563e0c46bac 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -93,7 +93,7 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
}
/*
- * Enter the time wait state.
+ * Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
* from the SK, and mess with hash chains and list linkage.
*/
@@ -111,7 +111,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
- spin_lock_bh(&bhead->lock);
+ spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
@@ -137,7 +137,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
if (__sk_nulls_del_node_init_rcu(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- spin_unlock_bh(lock);
+ spin_unlock(lock);
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bf97317e6c97..f08eebe60446 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2412,6 +2412,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 69ee877574d0..8322f26e770e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -110,7 +110,8 @@ struct bbr {
u32 lt_last_lost; /* LT intvl start: tp->lost */
u32 pacing_gain:10, /* current gain for setting pacing rate */
cwnd_gain:10, /* current gain for setting cwnd */
- full_bw_cnt:3, /* number of rounds without large bw gains */
+ full_bw_reached:1, /* reached full bw in Startup? */
+ full_bw_cnt:2, /* number of rounds without large bw gains */
cycle_idx:3, /* current index in pacing_gain cycle array */
has_seen_rtt:1, /* have we seen an RTT sample yet? */
unused_b:5;
@@ -180,7 +181,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
{
const struct bbr *bbr = inet_csk_ca(sk);
- return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+ return bbr->full_bw_reached;
}
/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -717,6 +718,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
return;
}
++bbr->full_bw_cnt;
+ bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
}
/* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -850,6 +852,7 @@ static void bbr_init(struct sock *sk)
bbr->restore_cwnd = 0;
bbr->round_start = 0;
bbr->idle_restart = 0;
+ bbr->full_bw_reached = 0;
bbr->full_bw = 0;
bbr->full_bw_cnt = 0;
bbr->cycle_mstamp = 0;
@@ -871,6 +874,11 @@ static u32 bbr_sndbuf_expand(struct sock *sk)
*/
static u32 bbr_undo_cwnd(struct sock *sk)
{
+ struct bbr *bbr = inet_csk_ca(sk);
+
+ bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
+ bbr->full_bw_cnt = 0;
+ bbr_reset_lt_bw_sampling(sk);
return tcp_sk(sk)->snd_cwnd;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 734cfc8ff76e..9550cc42de2d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -579,6 +579,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
int time;
int copied;
+ tcp_mstamp_refresh(tp);
time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
return;
@@ -1941,6 +1942,8 @@ void tcp_enter_loss(struct sock *sk)
if (is_reneg) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
+ /* Mark SACK reneging until we recover from this loss event. */
+ tp->is_sack_reneg = 1;
}
tcp_clear_all_retrans_hints(tp);
@@ -2326,6 +2329,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
}
tp->snd_cwnd_stamp = tcp_jiffies32;
tp->undo_marker = 0;
+ tp->rack.advanced = 1; /* Force RACK to re-exam losses */
}
static inline bool tcp_may_undo(const struct tcp_sock *tp)
@@ -2364,6 +2368,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
return true;
}
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
return false;
}
@@ -2397,8 +2402,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- if (frto_undo || tcp_is_sack(tp))
+ if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
+ }
return true;
}
return false;
@@ -3495,6 +3502,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
struct tcp_sacktag_state sack_state;
struct rate_sample rs = { .prior_delivered = 0 };
u32 prior_snd_una = tp->snd_una;
+ 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;
@@ -3611,7 +3619,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
- tcp_rate_gen(sk, delivered, lost, sack_state.rate);
+ tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
tcp_xmit_recovery(sk, rexmit);
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c6bc0c4d19c6..77ea45da0fe9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1591,6 +1591,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_filter);
+static void tcp_v4_restore_cb(struct sk_buff *skb)
+{
+ memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4,
+ sizeof(struct inet_skb_parm));
+}
+
+static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
+ const struct tcphdr *th)
+{
+ /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+ * barrier() makes sure compiler wont play fool^Waliasing games.
+ */
+ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+ sizeof(struct inet_skb_parm));
+ barrier();
+
+ TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+ TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+ skb->len - th->doff * 4);
+ TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+ TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+ TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+ TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
+ TCP_SKB_CB(skb)->sacked = 0;
+ TCP_SKB_CB(skb)->has_rxtstamp =
+ skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+}
+
/*
* From tcp_input.c
*/
@@ -1631,24 +1659,6 @@ int tcp_v4_rcv(struct sk_buff *skb)
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
- /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
- * barrier() makes sure compiler wont play fool^Waliasing games.
- */
- memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
- sizeof(struct inet_skb_parm));
- barrier();
-
- TCP_SKB_CB(skb)->seq = ntohl(th->seq);
- TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
- skb->len - th->doff * 4);
- TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
- TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
- TCP_SKB_CB(skb)->tcp_tw_isn = 0;
- TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
- TCP_SKB_CB(skb)->sacked = 0;
- TCP_SKB_CB(skb)->has_rxtstamp =
- skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
-
lookup:
sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
th->dest, sdif, &refcounted);
@@ -1679,14 +1689,19 @@ process:
sock_hold(sk);
refcounted = true;
nsk = NULL;
- if (!tcp_filter(sk, skb))
+ if (!tcp_filter(sk, skb)) {
+ th = (const struct tcphdr *)skb->data;
+ iph = ip_hdr(skb);
+ tcp_v4_fill_cb(skb, iph, th);
nsk = tcp_check_req(sk, skb, req, false);
+ }
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
+ tcp_v4_restore_cb(skb);
} else if (tcp_child_process(sk, nsk, skb)) {
tcp_v4_send_reset(nsk, skb);
goto discard_and_relse;
@@ -1712,6 +1727,7 @@ process:
goto discard_and_relse;
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
+ tcp_v4_fill_cb(skb, iph, th);
skb->dev = NULL;
@@ -1742,6 +1758,8 @@ no_tcp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
+ tcp_v4_fill_cb(skb, iph, th);
+
if (tcp_checksum_complete(skb)) {
csum_error:
__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
@@ -1768,6 +1786,8 @@ do_time_wait:
goto discard_it;
}
+ tcp_v4_fill_cb(skb, iph, th);
+
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
@@ -1784,6 +1804,7 @@ do_time_wait:
if (sk2) {
inet_twsk_deschedule_put(inet_twsk(sk));
sk = sk2;
+ tcp_v4_restore_cb(skb);
refcounted = false;
goto process;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e36eff0403f4..b079b619b60c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -310,10 +310,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
if (state == TCP_TIME_WAIT)
timeo = TCP_TIMEWAIT_LEN;
+ /* tw_timer is pinned, so we need to make sure BH are disabled
+ * in following section, otherwise timer handler could run before
+ * we complete the initialization.
+ */
+ local_bh_disable();
inet_twsk_schedule(tw, timeo);
/* Linkage updates. */
__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
inet_twsk_put(tw);
+ local_bh_enable();
} else {
/* Sorry, if we're out of memory, just CLOSE this
* socket up. We've got bigger problems than
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 3330a370d306..c61240e43923 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
/* Update the connection delivery information and generate a rate sample. */
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct rate_sample *rs)
+ bool is_sack_reneg, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
rs->acked_sacked = delivered; /* freshly ACKed or SACKed */
rs->losses = lost; /* freshly marked lost */
- /* Return an invalid sample if no timing information is available. */
- if (!rs->prior_mstamp) {
+ /* Return an invalid sample if no timing information is available or
+ * in recovery from loss with SACK reneging. Rate samples taken during
+ * a SACK reneging event may overestimate bw by including packets that
+ * were SACKed before the reneg.
+ */
+ if (!rs->prior_mstamp || is_sack_reneg) {
rs->delivered = -1;
rs->interval_us = -1;
return;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index d3ea89020c69..3a81720ac0c4 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -55,7 +55,8 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
* to queuing or delayed ACKs.
*/
reo_wnd = 1000;
- if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) {
+ if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) &&
+ min_rtt != ~0U) {
reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
}
@@ -79,12 +80,12 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
*/
remaining = tp->rack.rtt_us + reo_wnd -
tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
- if (remaining < 0) {
+ if (remaining <= 0) {
tcp_rack_mark_skb_lost(sk, skb);
list_del_init(&skb->tcp_tsorted_anchor);
} else {
- /* Record maximum wait time (+1 to avoid 0) */
- *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
+ /* Record maximum wait time */
+ *reo_timeout = max_t(u32, *reo_timeout, remaining);
}
}
}
@@ -116,13 +117,8 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
{
u32 rtt_us;
- if (tp->rack.mstamp &&
- !tcp_rack_sent_after(xmit_time, tp->rack.mstamp,
- end_seq, tp->rack.end_seq))
- return;
-
rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time);
- if (sacked & TCPCB_RETRANS) {
+ if (rtt_us < tcp_min_rtt(tp) && (sacked & TCPCB_RETRANS)) {
/* If the sacked packet was retransmitted, it's ambiguous
* whether the retransmission or the original (or the prior
* retransmission) was sacked.
@@ -133,13 +129,15 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
* so it's at least one RTT (i.e., retransmission is at least
* an RTT later).
*/
- if (rtt_us < tcp_min_rtt(tp))
- return;
+ return;
}
- tp->rack.rtt_us = rtt_us;
- tp->rack.mstamp = xmit_time;
- tp->rack.end_seq = end_seq;
tp->rack.advanced = 1;
+ tp->rack.rtt_us = rtt_us;
+ if (tcp_rack_sent_after(xmit_time, tp->rack.mstamp,
+ end_seq, tp->rack.end_seq)) {
+ tp->rack.mstamp = xmit_time;
+ tp->rack.end_seq = end_seq;
+ }
}
/* We have waited long enough to accommodate reordering. Mark the expired
generated by cgit (git 2.34.1) at 2025-06-02 05:05:21 +0000