summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-07-01 17:13:56 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-07-01 17:13:56 +0000
commit511e4ecd3211371086a9698ce4042700957cee33 (patch)
tree7e4c8dbd3f81844f362f480dd8c9244afd9e31dc /net/ipv4
parentAdding debian version 6.9.2-1~exp1. (diff)
downloadlinux-511e4ecd3211371086a9698ce4042700957cee33.tar.xz
linux-511e4ecd3211371086a9698ce4042700957cee33.zip
Merging upstream version 6.9.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c6
-rw-r--r--net/ipv4/cipso_ipv4.c12
-rw-r--r--net/ipv4/devinet.c22
-rw-r--r--net/ipv4/fib_frontend.c7
-rw-r--r--net/ipv4/icmp.c26
-rw-r--r--net/ipv4/ip_input.c2
-rw-r--r--net/ipv4/ip_output.c8
-rw-r--r--net/ipv4/ip_tunnel.c2
-rw-r--r--net/ipv4/netfilter/nf_tproxy_ipv4.c2
-rw-r--r--net/ipv4/route.c46
-rw-r--r--net/ipv4/tcp.c9
-rw-r--r--net/ipv4/tcp_ao.c19
-rw-r--r--net/ipv4/tcp_dctcp.c13
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c13
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv4/udp.c23
-rw-r--r--net/ipv4/xfrm4_policy.c2
18 files changed, 137 insertions, 82 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fafb123f7..5622ddd3b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -758,7 +758,9 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new
sock_rps_record_flow(newsk);
WARN_ON(!((1 << newsk->sk_state) &
(TCPF_ESTABLISHED | TCPF_SYN_RECV |
- TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+ TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 |
+ TCPF_CLOSING | TCPF_CLOSE_WAIT |
+ TCPF_CLOSE)));
if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
@@ -1306,8 +1308,8 @@ static int inet_sk_reselect_saddr(struct sock *sk)
int inet_sk_rebuild_header(struct sock *sk)
{
+ struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0));
struct inet_sock *inet = inet_sk(sk);
- struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
__be32 daddr;
struct ip_options_rcu *inet_opt;
struct flowi4 *fl4;
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 8b17d83e5..1eb98440c 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -2012,12 +2012,16 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr)
* from there we can determine the new total option length */
iter = 0;
optlen_new = 0;
- while (iter < opt->opt.optlen)
- if (opt->opt.__data[iter] != IPOPT_NOP) {
+ while (iter < opt->opt.optlen) {
+ if (opt->opt.__data[iter] == IPOPT_END) {
+ break;
+ } else if (opt->opt.__data[iter] == IPOPT_NOP) {
+ iter++;
+ } else {
iter += opt->opt.__data[iter + 1];
optlen_new = iter;
- } else
- iter++;
+ }
+ }
hdr_delta = opt->opt.optlen;
opt->opt.optlen = (optlen_new + 3) & ~3;
hdr_delta -= opt->opt.optlen;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 7a437f0d4..84b5d1ccf 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1683,6 +1683,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa,
struct nlmsghdr *nlh;
unsigned long tstamp;
u32 preferred, valid;
+ u32 flags;
nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm),
args->flags);
@@ -1692,7 +1693,13 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa,
ifm = nlmsg_data(nlh);
ifm->ifa_family = AF_INET;
ifm->ifa_prefixlen = ifa->ifa_prefixlen;
- ifm->ifa_flags = READ_ONCE(ifa->ifa_flags);
+
+ flags = READ_ONCE(ifa->ifa_flags);
+ /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits.
+ * The 32bit value is given in IFA_FLAGS attribute.
+ */
+ ifm->ifa_flags = (__u8)flags;
+
ifm->ifa_scope = ifa->ifa_scope;
ifm->ifa_index = ifa->ifa_dev->dev->ifindex;
@@ -1701,7 +1708,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa,
goto nla_put_failure;
tstamp = READ_ONCE(ifa->ifa_tstamp);
- if (!(ifm->ifa_flags & IFA_F_PERMANENT)) {
+ if (!(flags & IFA_F_PERMANENT)) {
preferred = READ_ONCE(ifa->ifa_preferred_lft);
valid = READ_ONCE(ifa->ifa_valid_lft);
if (preferred != INFINITY_LIFE_TIME) {
@@ -1732,7 +1739,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa,
nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
(ifa->ifa_proto &&
nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) ||
- nla_put_u32(skb, IFA_FLAGS, ifm->ifa_flags) ||
+ nla_put_u32(skb, IFA_FLAGS, flags) ||
(ifa->ifa_rt_priority &&
nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) ||
put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp,
@@ -1875,10 +1882,11 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
goto done;
if (fillargs.ifindex) {
- err = -ENODEV;
dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex);
- if (!dev)
+ if (!dev) {
+ err = -ENODEV;
goto done;
+ }
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
goto done;
@@ -1890,7 +1898,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
cb->seq = inet_base_seq(tgt_net);
- for_each_netdev_dump(net, dev, ctx->ifindex) {
+ for_each_netdev_dump(tgt_net, dev, ctx->ifindex) {
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
continue;
@@ -2793,7 +2801,7 @@ void __init devinet_init(void)
rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0);
rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0);
rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr,
- RTNL_FLAG_DUMP_UNLOCKED);
+ RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf,
inet_netconf_dump_devconf,
RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c484b1c0f..7ad2cafb9 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1050,11 +1050,6 @@ next:
e++;
}
}
-
- /* Don't let NLM_DONE coalesce into a message, even if it could.
- * Some user space expects NLM_DONE in a separate recv().
- */
- err = skb->len;
out:
cb->args[1] = e;
@@ -1665,5 +1660,5 @@ void __init ip_fib_init(void)
rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0);
rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0);
rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib,
- RTNL_FLAG_DUMP_UNLOCKED);
+ RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 437e782b9..207482d30 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -483,6 +483,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
struct icmp_bxm *param)
{
struct net_device *route_lookup_dev;
+ struct dst_entry *dst, *dst2;
struct rtable *rt, *rt2;
struct flowi4 fl4_dec;
int err;
@@ -508,16 +509,17 @@ static struct rtable *icmp_route_lookup(struct net *net,
/* No need to clone since we're just using its address. */
rt2 = rt;
- rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
- flowi4_to_flowi(fl4), NULL, 0);
- if (!IS_ERR(rt)) {
+ dst = xfrm_lookup(net, &rt->dst,
+ flowi4_to_flowi(fl4), NULL, 0);
+ rt = dst_rtable(dst);
+ if (!IS_ERR(dst)) {
if (rt != rt2)
return rt;
- } else if (PTR_ERR(rt) == -EPERM) {
+ } else if (PTR_ERR(dst) == -EPERM) {
rt = NULL;
- } else
+ } else {
return rt;
-
+ }
err = xfrm_decode_session_reverse(net, skb_in, flowi4_to_flowi(&fl4_dec), AF_INET);
if (err)
goto relookup_failed;
@@ -551,19 +553,19 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst,
- flowi4_to_flowi(&fl4_dec), NULL,
- XFRM_LOOKUP_ICMP);
- if (!IS_ERR(rt2)) {
+ dst2 = xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL,
+ XFRM_LOOKUP_ICMP);
+ rt2 = dst_rtable(dst2);
+ if (!IS_ERR(dst2)) {
dst_release(&rt->dst);
memcpy(fl4, &fl4_dec, sizeof(*fl4));
rt = rt2;
- } else if (PTR_ERR(rt2) == -EPERM) {
+ } else if (PTR_ERR(dst2) == -EPERM) {
if (rt)
dst_release(&rt->dst);
return rt2;
} else {
- err = PTR_ERR(rt2);
+ err = PTR_ERR(dst2);
goto relookup_failed;
}
return rt;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 5e9c81566..d6fbcbd23 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -616,7 +616,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
dst = skb_dst(skb);
if (curr_dst != dst) {
hint = ip_extract_route_hint(net, skb,
- ((struct rtable *)dst)->rt_type);
+ dst_rtable(dst)->rt_type);
/* dispatch old sublist */
if (!list_empty(&sublist))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 39229fd06..9500031a1 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -198,7 +198,7 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- struct rtable *rt = (struct rtable *)dst;
+ struct rtable *rt = dst_rtable(dst);
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
@@ -475,7 +475,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
goto packet_routed;
/* Make sure we can route this packet. */
- rt = (struct rtable *)__sk_dst_check(sk, 0);
+ rt = dst_rtable(__sk_dst_check(sk, 0));
if (!rt) {
__be32 daddr;
@@ -971,7 +971,7 @@ static int __ip_append_data(struct sock *sk,
bool zc = false;
unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
int csummode = CHECKSUM_NONE;
- struct rtable *rt = (struct rtable *)cork->dst;
+ struct rtable *rt = dst_rtable(cork->dst);
bool paged, hold_tskey, extra_uref = false;
unsigned int wmem_alloc_delta = 0;
u32 tskey = 0;
@@ -1390,7 +1390,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct ip_options *opt = NULL;
- struct rtable *rt = (struct rtable *)cork->dst;
+ struct rtable *rt = dst_rtable(cork->dst);
struct iphdr *iph;
u8 pmtudisc, ttl;
__be16 df = 0;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 1b8d8ff9a..0e4bd5284 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -543,7 +543,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
struct rt6_info *rt6;
__be32 daddr;
- rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) :
+ rt6 = skb_valid_dst(skb) ? dst_rt6_info(skb_dst(skb)) :
NULL;
daddr = md ? dst : tunnel->parms.iph.daddr;
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index 69e331799..73e66a088 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
laddr = 0;
indev = __in_dev_get_rcu(skb->dev);
+ if (!indev)
+ return daddr;
in_dev_for_each_ifa_rcu(ifa, indev) {
if (ifa->ifa_flags & IFA_F_SECONDARY)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b814fdab1..3fcf084fb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -132,7 +132,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
INDIRECT_CALLABLE_SCOPE
unsigned int ipv4_mtu(const struct dst_entry *dst);
-static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
+static void ipv4_negative_advice(struct sock *sk,
+ struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
@@ -831,28 +832,21 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
u32 mark = skb->mark;
__u8 tos = iph->tos;
- rt = (struct rtable *) dst;
+ rt = dst_rtable(dst);
__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
-static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
+static void ipv4_negative_advice(struct sock *sk,
+ struct dst_entry *dst)
{
- struct rtable *rt = (struct rtable *)dst;
- struct dst_entry *ret = dst;
+ struct rtable *rt = dst_rtable(dst);
- if (rt) {
- if (dst->obsolete > 0) {
- ip_rt_put(rt);
- ret = NULL;
- } else if ((rt->rt_flags & RTCF_REDIRECTED) ||
- rt->dst.expires) {
- ip_rt_put(rt);
- ret = NULL;
- }
- }
- return ret;
+ if ((dst->obsolete > 0) ||
+ (rt->rt_flags & RTCF_REDIRECTED) ||
+ rt->dst.expires)
+ sk_dst_reset(sk);
}
/*
@@ -1056,7 +1050,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
- struct rtable *rt = (struct rtable *) dst;
+ struct rtable *rt = dst_rtable(dst);
struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb);
@@ -1127,7 +1121,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
__build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
- rt = (struct rtable *)odst;
+ rt = dst_rtable(odst);
if (odst->obsolete && !odst->ops->check(odst, 0)) {
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt))
@@ -1136,7 +1130,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
new = true;
}
- __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
+ __ip_rt_update_pmtu(dst_rtable(xfrm_dst_path(&rt->dst)), &fl4, mtu);
if (!dst_check(&rt->dst, 0)) {
if (new)
@@ -1193,7 +1187,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_redirect);
INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst,
u32 cookie)
{
- struct rtable *rt = (struct rtable *) dst;
+ struct rtable *rt = dst_rtable(dst);
/* All IPV4 dsts are created with ->obsolete set to the value
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
@@ -1528,10 +1522,8 @@ void rt_del_uncached_list(struct rtable *rt)
static void ipv4_dst_destroy(struct dst_entry *dst)
{
- struct rtable *rt = (struct rtable *)dst;
-
ip_dst_metrics_put(dst);
- rt_del_uncached_list(rt);
+ rt_del_uncached_list(dst_rtable(dst));
}
void rt_flush_dev(struct net_device *dev)
@@ -2832,7 +2824,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rtable *ort = (struct rtable *) dst_orig;
+ struct rtable *ort = dst_rtable(dst_orig);
struct rtable *rt;
rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0);
@@ -2877,9 +2869,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
if (flp4->flowi4_proto) {
flp4->flowi4_oif = rt->dst.dev->ifindex;
- rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst,
- flowi4_to_flowi(flp4),
- sk, 0);
+ rt = dst_rtable(xfrm_lookup_route(net, &rt->dst,
+ flowi4_to_flowi(flp4),
+ sk, 0));
}
return rt;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 66d77faca..77ee1eda3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1159,6 +1159,9 @@ new_segment:
process_backlog++;
+#ifdef CONFIG_SKB_DECRYPTED
+ skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
tcp_skb_entail(sk, skb);
copy = size_goal;
@@ -2637,6 +2640,10 @@ void tcp_set_state(struct sock *sk, int state)
if (oldstate != TCP_ESTABLISHED)
TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
break;
+ case TCP_CLOSE_WAIT:
+ if (oldstate == TCP_SYN_RECV)
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
+ break;
case TCP_CLOSE:
if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
@@ -2648,7 +2655,7 @@ void tcp_set_state(struct sock *sk, int state)
inet_put_port(sk);
fallthrough;
default:
- if (oldstate == TCP_ESTABLISHED)
+ if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT)
TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
}
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 781b67a52..09c0fa675 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -933,6 +933,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
struct tcp_ao_key *key;
__be32 sisn, disn;
u8 *traffic_key;
+ int state;
u32 sne = 0;
info = rcu_dereference(tcp_sk(sk)->ao_info);
@@ -948,8 +949,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
disn = 0;
}
+ state = READ_ONCE(sk->sk_state);
/* Fast-path */
- if (likely((1 << sk->sk_state) & TCP_AO_ESTABLISHED)) {
+ if (likely((1 << state) & TCP_AO_ESTABLISHED)) {
enum skb_drop_reason err;
struct tcp_ao_key *current_key;
@@ -988,6 +990,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
return SKB_NOT_DROPPED_YET;
}
+ if (unlikely(state == TCP_CLOSE))
+ return SKB_DROP_REASON_TCP_CLOSE;
+
/* Lookup key based on peer address and keyid.
* current_key and rnext_key must not be used on tcp listen
* sockets as otherwise:
@@ -1001,7 +1006,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
if (th->syn && !th->ack)
goto verify_hash;
- if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) {
+ if ((1 << state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) {
/* Make the initial syn the likely case here */
if (unlikely(req)) {
sne = tcp_ao_compute_sne(0, tcp_rsk(req)->rcv_isn,
@@ -1018,14 +1023,14 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
/* no way to figure out initial sisn/disn - drop */
return SKB_DROP_REASON_TCP_FLAGS;
}
- } else if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+ } else if ((1 << state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
disn = info->lisn;
if (th->syn || th->rst)
sisn = th->seq;
else
sisn = info->risn;
} else {
- WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", sk->sk_state);
+ WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", state);
return SKB_DROP_REASON_TCP_AOFAILURE;
}
verify_hash:
@@ -1963,8 +1968,10 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family,
first = true;
}
- if (cmd.ao_required && tcp_ao_required_verify(sk))
- return -EKEYREJECTED;
+ if (cmd.ao_required && tcp_ao_required_verify(sk)) {
+ err = -EKEYREJECTED;
+ goto out;
+ }
/* For sockets in TCP_CLOSED it's possible set keys that aren't
* matching the future peer (address/port/VRF/etc),
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index e33fbe493..b00428085 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -58,7 +58,18 @@ struct dctcp {
};
static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
-module_param(dctcp_shift_g, uint, 0644);
+
+static int dctcp_shift_g_set(const char *val, const struct kernel_param *kp)
+{
+ return param_set_uint_minmax(val, kp, 0, 10);
+}
+
+static const struct kernel_param_ops dctcp_shift_g_ops = {
+ .set = dctcp_shift_g_set,
+ .get = param_get_uint,
+};
+
+module_param_cb(dctcp_shift_g, &dctcp_shift_g_ops, &dctcp_shift_g, 0644);
MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");
static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a140d9f7a..1054a4403 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6289,6 +6289,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
skb_rbtree_walk_from(data)
tcp_mark_skb_lost(sk, data);
tcp_xmit_retransmit_queue(sk);
+ tp->retrans_stamp = 0;
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
return true;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e0cef75f8..92511b7fd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2001,7 +2001,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
enum skb_drop_reason *reason)
{
- u32 limit, tail_gso_size, tail_gso_segs;
+ u32 tail_gso_size, tail_gso_segs;
struct skb_shared_info *shinfo;
const struct tcphdr *th;
struct tcphdr *thtail;
@@ -2010,6 +2010,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
bool fragstolen;
u32 gso_segs;
u32 gso_size;
+ u64 limit;
int delta;
/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
@@ -2107,7 +2108,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
__skb_push(skb, hdrlen);
no_coalesce:
- limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+ /* sk->sk_backlog.len is reset only at the end of __release_sock().
+ * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach
+ * sk_rcvbuf in normal conditions.
+ */
+ limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1;
+
+ limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1;
/* Only socket owner can try to collapse/prune rx queues
* to reduce memory overhead, so add a little headroom here.
@@ -2115,6 +2122,8 @@ no_coalesce:
*/
limit += 64 * 1024;
+ limit = min_t(u64, limit, UINT_MAX);
+
if (unlikely(sk_add_backlog(sk, skb, limit))) {
bh_unlock_sock(sk);
*reason = SKB_DROP_REASON_SOCKET_BACKLOG;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d1ad20ce1..f96f68cf7 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -483,8 +483,12 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
{
const struct tcp_sock *tp = tcp_sk(sk);
const int timeout = TCP_RTO_MAX * 2;
- u32 rcv_delta;
+ s32 rcv_delta;
+ /* Note: timer interrupt might have been delayed by at least one jiffy,
+ * and tp->rcv_tstamp might very well have been written recently.
+ * rcv_delta can thus be negative.
+ */
rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
if (rcv_delta <= timeout)
return false;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b32cf2eee..72d3bf136 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -427,15 +427,21 @@ static struct sock *udp4_lib_lookup2(struct net *net,
{
struct sock *sk, *result;
int score, badness;
+ bool need_rescore;
result = NULL;
badness = 0;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- score = compute_score(sk, net, saddr, sport,
- daddr, hnum, dif, sdif);
+ need_rescore = false;
+rescore:
+ score = compute_score(need_rescore ? result : sk, net, saddr,
+ sport, daddr, hnum, dif, sdif);
if (score > badness) {
badness = score;
+ if (need_rescore)
+ continue;
+
if (sk->sk_state == TCP_ESTABLISHED) {
result = sk;
continue;
@@ -456,9 +462,14 @@ static struct sock *udp4_lib_lookup2(struct net *net,
if (IS_ERR(result))
continue;
- badness = compute_score(result, net, saddr, sport,
- daddr, hnum, dif, sdif);
-
+ /* compute_score is too long of a function to be
+ * inlined, and calling it again here yields
+ * measureable overhead for some
+ * workloads. Work around it by jumping
+ * backwards to rescore 'result'.
+ */
+ need_rescore = true;
+ goto rescore;
}
}
return result;
@@ -1207,7 +1218,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if (connected)
- rt = (struct rtable *)sk_dst_check(sk, 0);
+ rt = dst_rtable(sk_dst_check(sk, 0));
if (!rt) {
struct net *net = sock_net(sk);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index c33bca2c3..1853a8415 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -69,7 +69,7 @@ static int xfrm4_get_saddr(struct net *net, int oif,
static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
- struct rtable *rt = (struct rtable *)xdst->route;
+ struct rtable *rt = dst_rtable(xdst->route);
const struct flowi4 *fl4 = &fl->u.ip4;
xdst->u.rt.rt_iif = fl4->flowi4_iif;