summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c2
-rw-r--r--net/ipv4/devinet.c5
-rw-r--r--net/ipv4/ip_options.c7
-rw-r--r--net/ipv4/ipvs/ip_vs_xmit.c2
-rw-r--r--net/ipv4/netfilter/ipt_recent.c7
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c6
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c5
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c3
-rw-r--r--net/ipv4/netfilter/nf_nat_rule.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_standalone.c2
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_bic.c2
-rw-r--r--net/ipv4/tcp_cubic.c48
-rw-r--r--net/ipv4/tcp_htcp.c14
-rw-r--r--net/ipv4/tcp_illinois.c8
-rw-r--r--net/ipv4/tcp_input.c74
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_lp.c6
-rw-r--r--net/ipv4/tcp_vegas.c6
-rw-r--r--net/ipv4/tcp_vegas.h2
-rw-r--r--net/ipv4/tcp_veno.c6
-rw-r--r--net/ipv4/tcp_westwood.c7
-rw-r--r--net/ipv4/tcp_yeah.c4
25 files changed, 123 insertions, 107 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 06c08e5740fb..e68103475cca 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -831,7 +831,7 @@ const struct proto_ops inet_stream_ops = {
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
- .sendmsg = inet_sendmsg,
+ .sendmsg = tcp_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
.sendpage = tcp_sendpage,
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index abf6352f990f..5b77bdaa57dd 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1056,10 +1056,9 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
if (!in_dev) {
if (event == NETDEV_REGISTER) {
in_dev = inetdev_init(dev);
+ if (!in_dev)
+ return notifier_from_errno(-ENOMEM);
if (dev == &loopback_dev) {
- if (!in_dev)
- panic("devinet: "
- "Failed to create loopback\n");
IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
}
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 251346828cb4..2f14745a9e1f 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -513,11 +513,8 @@ void ip_options_undo(struct ip_options * opt)
static struct ip_options *ip_options_get_alloc(const int optlen)
{
- struct ip_options *opt = kmalloc(sizeof(*opt) + ((optlen + 3) & ~3),
- GFP_KERNEL);
- if (opt)
- memset(opt, 0, sizeof(*opt));
- return opt;
+ return kzalloc(sizeof(struct ip_options) + ((optlen + 3) & ~3),
+ GFP_KERNEL);
}
static int ip_options_get_finish(struct ip_options **optp,
diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c
index 900ce29db382..666e080a74a3 100644
--- a/net/ipv4/ipvs/ip_vs_xmit.c
+++ b/net/ipv4/ipvs/ip_vs_xmit.c
@@ -128,7 +128,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
#define IP_VS_XMIT(skb, rt) \
do { \
(skb)->ipvs_property = 1; \
- (skb)->ip_summed = CHECKSUM_NONE; \
+ skb_forward_csum(skb); \
NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, (skb), NULL, \
(rt)->u.dst.dev, dst_output); \
} while (0)
diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c
index 321804315659..6d0c0f7364ad 100644
--- a/net/ipv4/netfilter/ipt_recent.c
+++ b/net/ipv4/netfilter/ipt_recent.c
@@ -387,12 +387,17 @@ static int recent_seq_open(struct inode *inode, struct file *file)
st = kzalloc(sizeof(*st), GFP_KERNEL);
if (st == NULL)
return -ENOMEM;
+
ret = seq_open(file, &recent_seq_ops);
- if (ret)
+ if (ret) {
kfree(st);
+ goto out;
+ }
+
st->table = pde->data;
seq = file->private_data;
seq->private = st;
+out:
return ret;
}
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 64552afd01cb..d9b5177989c6 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -509,3 +509,9 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void)
module_init(nf_conntrack_l3proto_ipv4_init);
module_exit(nf_conntrack_l3proto_ipv4_fini);
+
+void need_ipv4_conntrack(void)
+{
+ return;
+}
+EXPORT_SYMBOL_GPL(need_ipv4_conntrack);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 27c7918e442a..b3dd5de9a258 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -294,15 +294,14 @@ static int exp_open(struct inode *inode, struct file *file)
struct ct_expect_iter_state *st;
int ret;
- st = kmalloc(sizeof(struct ct_expect_iter_state), GFP_KERNEL);
- if (st == NULL)
+ st = kzalloc(sizeof(struct ct_expect_iter_state), GFP_KERNEL);
+ if (!st)
return -ENOMEM;
ret = seq_open(file, &exp_seq_ops);
if (ret)
goto out_free;
seq = file->private_data;
seq->private = st;
- memset(st, 0, sizeof(struct ct_expect_iter_state));
return ret;
out_free:
kfree(st);
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index e848d8d6292f..deab27facbad 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -77,7 +77,8 @@ static inline unsigned int
hash_by_src(const struct nf_conntrack_tuple *tuple)
{
/* Original src, to ensure we map it consistently if poss. */
- return jhash_3words((__force u32)tuple->src.u3.ip, tuple->src.u.all,
+ return jhash_3words((__force u32)tuple->src.u3.ip,
+ (__force u32)tuple->src.u.all,
tuple->dst.protonum, 0) % nf_nat_htable_size;
}
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index 0f45427e5fdc..76ec59ae524d 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -192,7 +192,7 @@ alloc_null_binding_confirmed(struct nf_conn *ct, unsigned int hooknum)
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip
: ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
- u_int16_t all
+ __be16 all
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all
: ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all);
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 332814dac503..46cc99def165 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -328,7 +328,7 @@ static int __init nf_nat_standalone_init(void)
{
int ret = 0;
- need_conntrack();
+ need_ipv4_conntrack();
#ifdef CONFIG_XFRM
BUG_ON(ip_nat_decode_session != NULL);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 24d7c9f31918..c6d71526f625 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -900,8 +900,9 @@ static int raw_seq_open(struct inode *inode, struct file *file)
{
struct seq_file *seq;
int rc = -ENOMEM;
- struct raw_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ struct raw_iter_state *s;
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
if (!s)
goto out;
rc = seq_open(file, &raw_seq_ops);
@@ -910,7 +911,6 @@ static int raw_seq_open(struct inode *inode, struct file *file)
seq = file->private_data;
seq->private = s;
- memset(s, 0, sizeof(*s));
out:
return rc;
out_kfree:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index df42b7fb3268..c7ca94bd152c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -374,8 +374,9 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
struct seq_file *seq;
int rc = -ENOMEM;
- struct rt_cache_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ struct rt_cache_iter_state *s;
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
if (!s)
goto out;
rc = seq_open(file, &rt_cache_seq_ops);
@@ -383,7 +384,6 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file)
goto out_kfree;
seq = file->private_data;
seq->private = s;
- memset(s, 0, sizeof(*s));
out:
return rc;
out_kfree:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index da4c0b6ab79a..7e740112b238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -658,9 +658,10 @@ static inline int select_size(struct sock *sk)
return tmp;
}
-int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
size_t size)
{
+ struct sock *sk = sock->sk;
struct iovec *iov;
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 519de091a94d..4586211e3757 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -206,7 +206,7 @@ static void bictcp_state(struct sock *sk, u8 new_state)
/* Track delayed acknowledgment ratio using sliding window
* ratio = (15*ratio + sample) / 16
*/
-static void bictcp_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index d17da30d82d6..485d7ea35f75 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -246,38 +246,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
ca->cnt = 1;
}
-
-/* Keep track of minimum rtt */
-static inline void measure_delay(struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- struct bictcp *ca = inet_csk_ca(sk);
- u32 delay;
-
- /* No time stamp */
- if (!(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) ||
- /* Discard delay samples right after fast recovery */
- (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
- return;
-
- delay = (tcp_time_stamp - tp->rx_opt.rcv_tsecr)<<3;
- if (delay == 0)
- delay = 1;
-
- /* first time call or link delay decreases */
- if (ca->delay_min == 0 || ca->delay_min > delay)
- ca->delay_min = delay;
-}
-
static void bictcp_cong_avoid(struct sock *sk, u32 ack,
u32 in_flight, int data_acked)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
- if (data_acked)
- measure_delay(sk);
-
if (!tcp_is_cwnd_limited(sk, in_flight))
return;
@@ -334,17 +308,33 @@ static void bictcp_state(struct sock *sk, u8 new_state)
/* Track delayed acknowledgment ratio using sliding window
* ratio = (15*ratio + sample) / 16
*/
-static void bictcp_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+ u32 delay;
if (cnt > 0 && icsk->icsk_ca_state == TCP_CA_Open) {
- struct bictcp *ca = inet_csk_ca(sk);
cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
ca->delayed_ack += cnt;
}
-}
+ /* Some calls are for duplicates without timetamps */
+ if (rtt_us < 0)
+ return;
+
+ /* Discard delay samples right after fast recovery */
+ if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
+ return;
+
+ delay = usecs_to_jiffies(rtt_us) << 3;
+ if (delay == 0)
+ delay = 1;
+
+ /* first time call or link delay decreases */
+ if (ca->delay_min == 0 || ca->delay_min > delay)
+ ca->delay_min = delay;
+}
static struct tcp_congestion_ops cubictcp = {
.init = bictcp_init,
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 08a02e6045c9..5215691f2760 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -76,20 +76,17 @@ static u32 htcp_cwnd_undo(struct sock *sk)
return max(tp->snd_cwnd, (tp->snd_ssthresh << 7) / ca->beta);
}
-static inline void measure_rtt(struct sock *sk)
+static inline void measure_rtt(struct sock *sk, u32 srtt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
- const struct tcp_sock *tp = tcp_sk(sk);
struct htcp *ca = inet_csk_ca(sk);
- u32 srtt = tp->srtt >> 3;
/* keep track of minimum RTT seen so far, minRTT is zero at first */
if (ca->minRTT > srtt || !ca->minRTT)
ca->minRTT = srtt;
/* max RTT */
- if (icsk->icsk_ca_state == TCP_CA_Open
- && tp->snd_ssthresh < 0xFFFF && htcp_ccount(ca) > 3) {
+ if (icsk->icsk_ca_state == TCP_CA_Open) {
if (ca->maxRTT < ca->minRTT)
ca->maxRTT = ca->minRTT;
if (ca->maxRTT < srtt
@@ -98,7 +95,7 @@ static inline void measure_rtt(struct sock *sk)
}
}
-static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, ktime_t last)
+static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
@@ -108,6 +105,9 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, ktime_t
if (icsk->icsk_ca_state == TCP_CA_Open)
ca->pkts_acked = pkts_acked;
+ if (rtt > 0)
+ measure_rtt(sk, usecs_to_jiffies(rtt));
+
if (!use_bandwidth_switch)
return;
@@ -237,8 +237,6 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack,
if (tp->snd_cwnd <= tp->snd_ssthresh)
tcp_slow_start(tp);
else {
- measure_rtt(sk);
-
/* In dangerous area, increase slowly.
* In theory this is tp->snd_cwnd += alpha / tp->snd_cwnd
*/
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index cc5de6f69d46..64f1cbaf96e8 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -83,18 +83,16 @@ static void tcp_illinois_init(struct sock *sk)
}
/* Measure RTT for each ack. */
-static void tcp_illinois_acked(struct sock *sk, u32 pkts_acked, ktime_t last)
+static void tcp_illinois_acked(struct sock *sk, u32 pkts_acked, s32 rtt)
{
struct illinois *ca = inet_csk_ca(sk);
- u32 rtt;
ca->acked = pkts_acked;
- if (ktime_equal(last, net_invalid_timestamp()))
+ /* dup ack, no rtt sample */
+ if (rtt < 0)
return;
- rtt = ktime_to_us(net_timedelta(last));
-
/* ignore bogus values, this prevents wraparound in alpha math */
if (rtt > RTT_MAX)
rtt = RTT_MAX;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fec8a7a4dbaf..f030435e0eb4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -102,11 +102,14 @@ int sysctl_tcp_abc __read_mostly;
#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) */
+#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained DSACK info */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE)
#define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED)
+#define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
#define IsReno(tp) ((tp)->rx_opt.sack_ok == 0)
#define IsFack(tp) ((tp)->rx_opt.sack_ok & 2)
@@ -964,12 +967,14 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
/* Check for D-SACK. */
if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) {
+ flag |= FLAG_DSACKING_ACK;
found_dup_sack = 1;
tp->rx_opt.sack_ok |= 4;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
} else if (num_sacks > 1 &&
!after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) &&
!before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) {
+ flag |= FLAG_DSACKING_ACK;
found_dup_sack = 1;
tp->rx_opt.sack_ok |= 4;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
@@ -1851,19 +1856,22 @@ static inline u32 tcp_cwnd_min(const struct sock *sk)
}
/* Decrease cwnd each second ack. */
-static void tcp_cwnd_down(struct sock *sk)
+static void tcp_cwnd_down(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
int decr = tp->snd_cwnd_cnt + 1;
- tp->snd_cwnd_cnt = decr&1;
- decr >>= 1;
+ if ((flag&(FLAG_ANY_PROGRESS|FLAG_DSACKING_ACK)) ||
+ (IsReno(tp) && !(flag&FLAG_NOT_DUP))) {
+ tp->snd_cwnd_cnt = decr&1;
+ decr >>= 1;
- if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
- tp->snd_cwnd -= decr;
+ if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
+ tp->snd_cwnd -= decr;
- tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
- tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ }
}
/* Nothing was retransmitted or returned timestamp is less
@@ -2060,7 +2068,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
}
tcp_moderate_cwnd(tp);
} else {
- tcp_cwnd_down(sk);
+ tcp_cwnd_down(sk, flag);
}
}
@@ -2104,12 +2112,13 @@ static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
* tcp_xmit_retransmit_queue().
*/
static void
-tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
- int prior_packets, int flag)
+tcp_fastretrans_alert(struct sock *sk, int prior_packets, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int is_dupack = (tp->snd_una == prior_snd_una && !(flag&FLAG_NOT_DUP));
+ int is_dupack = !(flag&(FLAG_SND_UNA_ADVANCED|FLAG_NOT_DUP));
+ int do_lost = is_dupack || ((flag&FLAG_DATA_SACKED) &&
+ (tp->fackets_out > tp->reordering));
/* Some technical things:
* 1. Reno does not count dupacks (sacked_out) automatically. */
@@ -2186,14 +2195,14 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
/* F. Process state. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
- if (prior_snd_una == tp->snd_una) {
+ if (!(flag & FLAG_SND_UNA_ADVANCED)) {
if (IsReno(tp) && is_dupack)
tcp_add_reno_sack(sk);
} else {
int acked = prior_packets - tp->packets_out;
if (IsReno(tp))
tcp_remove_reno_sacks(sk, acked);
- is_dupack = tcp_try_undo_partial(sk, acked);
+ do_lost = tcp_try_undo_partial(sk, acked);
}
break;
case TCP_CA_Loss:
@@ -2209,7 +2218,7 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
/* Loss is undone; fall through to processing in Open state. */
default:
if (IsReno(tp)) {
- if (tp->snd_una != prior_snd_una)
+ if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
if (is_dupack)
tcp_add_reno_sack(sk);
@@ -2258,9 +2267,9 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
tcp_set_ca_state(sk, TCP_CA_Recovery);
}
- if (is_dupack || tcp_head_timedout(sk))
+ if (do_lost || tcp_head_timedout(sk))
tcp_update_scoreboard(sk);
- tcp_cwnd_down(sk);
+ tcp_cwnd_down(sk, flag);
tcp_xmit_retransmit_queue(sk);
}
@@ -2490,12 +2499,23 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
tcp_ack_update_rtt(sk, acked, seq_rtt);
tcp_ack_packets_out(sk);
- /* Is the ACK triggering packet unambiguous? */
- if (acked & FLAG_RETRANS_DATA_ACKED)
- last_ackt = net_invalid_timestamp();
+ if (ca_ops->pkts_acked) {
+ s32 rtt_us = -1;
+
+ /* Is the ACK triggering packet unambiguous? */
+ if (!(acked & FLAG_RETRANS_DATA_ACKED)) {
+ /* High resolution needed and available? */
+ if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
+ !ktime_equal(last_ackt,
+ net_invalid_timestamp()))
+ rtt_us = ktime_us_delta(ktime_get_real(),
+ last_ackt);
+ else if (seq_rtt > 0)
+ rtt_us = jiffies_to_usecs(seq_rtt);
+ }
- if (ca_ops->pkts_acked)
- ca_ops->pkts_acked(sk, pkts_acked, last_ackt);
+ ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
+ }
}
#if FASTRETRANS_DEBUG > 0
@@ -2667,7 +2687,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag)
* to prove that the RTO is indeed spurious. It transfers the control
* from F-RTO to the conventional RTO recovery
*/
-static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
+static int tcp_process_frto(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2687,8 +2707,7 @@ static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
* ACK isn't duplicate nor advances window, e.g., opposite dir
* data, winupdate
*/
- if ((tp->snd_una == prior_snd_una) && (flag&FLAG_NOT_DUP) &&
- !(flag&FLAG_FORWARD_PROGRESS))
+ if (!(flag&FLAG_ANY_PROGRESS) && (flag&FLAG_NOT_DUP))
return 1;
if (!(flag&FLAG_DATA_ACKED)) {
@@ -2768,6 +2787,9 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
if (before(ack, prior_snd_una))
goto old_ack;
+ if (after(ack, prior_snd_una))
+ flag |= FLAG_SND_UNA_ADVANCED;
+
if (sysctl_tcp_abc) {
if (icsk->icsk_ca_state < TCP_CA_CWR)
tp->bytes_acked += ack - prior_snd_una;
@@ -2820,14 +2842,14 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
flag |= tcp_clean_rtx_queue(sk, &seq_rtt);
if (tp->frto_counter)
- frto_cwnd = tcp_process_frto(sk, prior_snd_una, flag);
+ frto_cwnd = tcp_process_frto(sk, flag);
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight, 0);
- tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag);
+ tcp_fastretrans_alert(sk, prior_packets, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
tcp_cong_avoid(sk, ack, prior_in_flight, 1);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3f5f7423b95c..9c94627c8c7e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2425,7 +2425,6 @@ struct proto tcp_prot = {
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
- .sendmsg = tcp_sendmsg,
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v4_do_rcv,
.hash = tcp_v4_hash,
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 80e140e3ec2d..e7f5ef92cbd8 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -260,13 +260,13 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt)
* newReno in increase case.
* We work it out by following the idea from TCP-LP's paper directly
*/
-static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, ktime_t last)
+static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
{
struct tcp_sock *tp = tcp_sk(sk);
struct lp *lp = inet_csk_ca(sk);
- if (!ktime_equal(last, net_invalid_timestamp()))
- tcp_lp_rtt_sample(sk, ktime_to_us(net_timedelta(last)));
+ if (rtt_us > 0)
+ tcp_lp_rtt_sample(sk, rtt_us);
/* calc inference */
if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 914e0307f7af..b49dedcda52d 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -112,16 +112,16 @@ EXPORT_SYMBOL_GPL(tcp_vegas_init);
* o min-filter RTT samples from a much longer window (forever for now)
* to find the propagation delay (baseRTT)
*/
-void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, ktime_t last)
+void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us)
{
struct vegas *vegas = inet_csk_ca(sk);
u32 vrtt;
- if (ktime_equal(last, net_invalid_timestamp()))
+ if (rtt_us < 0)
return;
/* Never allow zero rtt or baseRTT */
- vrtt = ktime_to_us(net_timedelta(last)) + 1;
+ vrtt = rtt_us + 1;
/* Filter to find propagation delay: */
if (vrtt < vegas->baseRTT)
diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h
index 502fa8183634..6c0eea2f8249 100644
--- a/net/ipv4/tcp_vegas.h
+++ b/net/ipv4/tcp_vegas.h
@@ -17,7 +17,7 @@ struct vegas {
extern void tcp_vegas_init(struct sock *sk);
extern void tcp_vegas_state(struct sock *sk, u8 ca_state);
-extern void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, ktime_t last);
+extern void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
extern void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
extern void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 7a55ddf86032..8fb2aee0b1a4 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -69,16 +69,16 @@ static void tcp_veno_init(struct sock *sk)
}
/* Do rtt sampling needed for Veno. */
-static void tcp_veno_pkts_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void tcp_veno_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us)
{
struct veno *veno = inet_csk_ca(sk);
u32 vrtt;
- if (ktime_equal(last, net_invalid_timestamp()))
+ if (rtt_us < 0)
return;
/* Never allow zero rtt or baseRTT */
- vrtt = ktime_to_us(net_timedelta(last)) + 1;
+ vrtt = rtt_us + 1;
/* Filter to find propagation delay: */
if (vrtt < veno->basertt)
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index e61e09dd513e..20151d6a6241 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -100,11 +100,12 @@ static void westwood_filter(struct westwood *w, u32 delta)
* Called after processing group of packets.
* but all westwood needs is the last sample of srtt.
*/
-static void tcp_westwood_pkts_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void tcp_westwood_pkts_acked(struct sock *sk, u32 cnt, s32 rtt)
{
struct westwood *w = inet_csk_ca(sk);
- if (cnt > 0)
- w->rtt = tcp_sk(sk)->srtt >> 3;
+
+ if (rtt > 0)
+ w->rtt = usecs_to_jiffies(rtt);
}
/*
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index c04b7c6ec702..c107fba7430e 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -58,7 +58,7 @@ static void tcp_yeah_init(struct sock *sk)
}
-static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, ktime_t last)
+static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct yeah *yeah = inet_csk_ca(sk);
@@ -66,7 +66,7 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, ktime_t last)
if (icsk->icsk_ca_state == TCP_CA_Open)
yeah->pkts_acked = pkts_acked;
- tcp_vegas_pkts_acked(sk, pkts_acked, last);
+ tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us);
}
static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack,
generated by cgit v1.2.3 (git 2.0.4) at 2025-01-23 04:06:47 +0000