summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_frontend.c3
-rw-r--r--net/ipv4/fib_rules.c2
-rw-r--r--net/ipv4/fib_semantics.c4
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/ip_forward.c2
-rw-r--r--net/ipv4/ip_output.c4
-rw-r--r--net/ipv4/ip_vti.c4
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/route.c157
-rw-r--r--net/ipv4/sysctl_net_ipv4.c2
-rw-r--r--net/ipv4/tcp.c10
-rw-r--r--net/ipv4/tcp_input.c13
-rw-r--r--net/ipv4/tcp_ipv4.c8
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv4/tcp_timer.c4
-rw-r--r--net/ipv4/xfrm4_policy.c1
16 files changed, 133 insertions, 88 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 68c93d1bb03a..825c608826de 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -322,7 +322,8 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
{
int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
- if (!r && !fib_num_tclassid_users(dev_net(dev))) {
+ if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
+ (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
*itag = 0;
return 0;
}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 274309d3aded..26aa65d1fce4 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -262,7 +262,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
rt_cache_flush(ops->fro_net);
}
-static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = {
.family = AF_INET,
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3509065e409a..71b125cd5db1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -314,6 +314,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
nfi->fib_scope == fi->fib_scope &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
nfi->fib_priority == fi->fib_priority &&
+ nfi->fib_type == fi->fib_type &&
memcmp(nfi->fib_metrics, fi->fib_metrics,
sizeof(u32) * RTAX_MAX) == 0 &&
((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 &&
@@ -833,11 +834,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
fi->fib_flags = cfg->fc_flags;
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
+ fi->fib_type = cfg->fc_type;
fi->fib_nhs = nhs;
change_nexthops(fi) {
nexthop_nh->nh_parent = fi;
nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
+ if (!nexthop_nh->nh_pcpu_rth_output)
+ goto failure;
} endfor_nexthops(fi)
if (cfg->fc_mx) {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f0c5b9c1a957..d34ce2972c8f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -406,7 +406,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
return &rt->dst;
@@ -442,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
rcu_read_unlock();
return &rt->dst;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index ab09b126423c..694de3b7aebf 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -85,7 +85,7 @@ int ip_forward(struct sk_buff *skb)
rt = skb_rtable(skb);
- if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
+ if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 24a29a39e9a8..6537a408a4fb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -193,7 +193,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr;
+ nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
- if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
+ if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 978bca4818ae..1831092f999f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -374,7 +374,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- htonl(tunnel->parms.i_key), RT_TOS(tos),
+ be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
dst, tiph->saddr, 0, 0);
@@ -441,7 +441,7 @@ static int vti_tunnel_bind_dev(struct net_device *dev)
struct flowi4 fl4;
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- htonl(tunnel->parms.i_key),
+ be32_to_cpu(tunnel->parms.i_key),
RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
iph->daddr, iph->saddr, 0, 0);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1daa95c2a0ba..6168c4dc58b1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -221,7 +221,7 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
return 0;
}
-static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = {
.family = RTNL_FAMILY_IPMR,
.rule_size = sizeof(struct ipmr_rule),
.addr_size = sizeof(u32),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff622069fcef..a8c651216fa6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -802,7 +802,8 @@ void ip_rt_send_redirect(struct sk_buff *skb)
net = dev_net(rt->dst.dev);
peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
if (!peer) {
- icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+ icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
+ rt_nexthop(rt, ip_hdr(skb)->daddr));
return;
}
@@ -827,7 +828,9 @@ void ip_rt_send_redirect(struct sk_buff *skb)
time_after(jiffies,
(peer->rate_last +
(ip_rt_redirect_load << peer->rate_tokens)))) {
- icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+ __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
+
+ icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
@@ -835,7 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
peer->rate_tokens == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
- &ip_hdr(skb)->daddr, &rt->rt_gateway);
+ &ip_hdr(skb)->daddr, &gw);
#endif
}
out_put_peer:
@@ -904,22 +907,32 @@ out: kfree_skb(skb);
return 0;
}
-static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
+static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
+ struct dst_entry *dst = &rt->dst;
struct fib_result res;
+ if (dst->dev->mtu < mtu)
+ return;
+
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
+ if (!rt->rt_pmtu) {
+ dst->obsolete = DST_OBSOLETE_KILL;
+ } else {
+ rt->rt_pmtu = mtu;
+ dst->expires = max(1UL, jiffies + ip_rt_mtu_expires);
+ }
+
rcu_read_lock();
- if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
+ if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
struct fib_nh *nh = &FIB_RES_NH(res);
update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
jiffies + ip_rt_mtu_expires);
}
rcu_read_unlock();
- return mtu;
}
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
@@ -929,14 +942,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb);
- mtu = __ip_rt_update_pmtu(rt, &fl4, mtu);
-
- if (!rt->rt_pmtu) {
- dst->obsolete = DST_OBSOLETE_KILL;
- } else {
- rt->rt_pmtu = mtu;
- rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
- }
+ __ip_rt_update_pmtu(rt, &fl4, mtu);
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
@@ -1120,7 +1126,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
- if (rt->rt_gateway && mtu > 576)
+ if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
@@ -1157,8 +1163,12 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
spin_lock_bh(&fnhe_lock);
if (daddr == fnhe->fnhe_daddr) {
- struct rtable *orig;
-
+ struct rtable *orig = rcu_dereference(fnhe->fnhe_rth);
+ if (orig && rt_is_expired(orig)) {
+ fnhe->fnhe_gw = 0;
+ fnhe->fnhe_pmtu = 0;
+ fnhe->fnhe_expires = 0;
+ }
if (fnhe->fnhe_pmtu) {
unsigned long expires = fnhe->fnhe_expires;
unsigned long diff = expires - jiffies;
@@ -1171,22 +1181,16 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
if (fnhe->fnhe_gw) {
rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_gateway = fnhe->fnhe_gw;
- }
+ rt->rt_uses_gateway = 1;
+ } else if (!rt->rt_gateway)
+ rt->rt_gateway = daddr;
- orig = rcu_dereference(fnhe->fnhe_rth);
rcu_assign_pointer(fnhe->fnhe_rth, rt);
if (orig)
rt_free(orig);
fnhe->fnhe_stamp = jiffies;
ret = true;
- } else {
- /* Routes we intend to cache in nexthop exception have
- * the DST_NOCACHE bit clear. However, if we are
- * unsuccessful at storing this route into the cache
- * we really need to set it.
- */
- rt->dst.flags |= DST_NOCACHE;
}
spin_unlock_bh(&fnhe_lock);
@@ -1201,8 +1205,6 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
if (rt_is_input_route(rt)) {
p = (struct rtable **)&nh->nh_rth_input;
} else {
- if (!nh->nh_pcpu_rth_output)
- goto nocache;
p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
}
orig = *p;
@@ -1211,16 +1213,8 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
if (prev == orig) {
if (orig)
rt_free(orig);
- } else {
- /* Routes we intend to cache in the FIB nexthop have
- * the DST_NOCACHE bit clear. However, if we are
- * unsuccessful at storing this route into the cache
- * we really need to set it.
- */
-nocache:
- rt->dst.flags |= DST_NOCACHE;
+ } else
ret = false;
- }
return ret;
}
@@ -1281,8 +1275,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
if (fi) {
struct fib_nh *nh = &FIB_RES_NH(*res);
- if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
+ if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) {
rt->rt_gateway = nh->nh_gw;
+ rt->rt_uses_gateway = 1;
+ }
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
@@ -1291,8 +1287,18 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
cached = rt_bind_exception(rt, fnhe, daddr);
else if (!(rt->dst.flags & DST_NOCACHE))
cached = rt_cache_route(nh, rt);
- }
- if (unlikely(!cached))
+ if (unlikely(!cached)) {
+ /* Routes we intend to cache in nexthop exception or
+ * FIB nexthop have the DST_NOCACHE bit clear.
+ * However, if we are unsuccessful at storing this
+ * route into the cache we really need to set it.
+ */
+ rt->dst.flags |= DST_NOCACHE;
+ if (!rt->rt_gateway)
+ rt->rt_gateway = daddr;
+ rt_add_uncached_list(rt);
+ }
+ } else
rt_add_uncached_list(rt);
#ifdef CONFIG_IP_ROUTE_CLASSID
@@ -1360,6 +1366,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
if (our) {
rth->dst.input= ip_local_deliver;
@@ -1429,7 +1436,6 @@ static int __mkroute_input(struct sk_buff *skb,
return -EINVAL;
}
-
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, in_dev, &itag);
if (err < 0) {
@@ -1439,10 +1445,13 @@ static int __mkroute_input(struct sk_buff *skb,
goto cleanup;
}
- if (out_dev == in_dev && err &&
+ do_cache = res->fi && !itag;
+ if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
- inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+ inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
flags |= RTCF_DOREDIRECT;
+ do_cache = false;
+ }
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1459,15 +1468,11 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
- do_cache = false;
- if (res->fi) {
- if (!itag) {
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
- if (rt_cache_valid(rth)) {
- skb_dst_set_noref(skb, &rth->dst);
- goto out;
- }
- do_cache = true;
+ if (do_cache) {
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+ if (rt_cache_valid(rth)) {
+ skb_dst_set_noref(skb, &rth->dst);
+ goto out;
}
}
@@ -1486,6 +1491,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
rth->dst.input = ip_forward;
@@ -1656,6 +1662,7 @@ local_input:
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
@@ -1758,6 +1765,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
+ bool do_cache;
in_dev = __in_dev_get_rcu(dev_out);
if (!in_dev)
@@ -1794,24 +1802,36 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
}
fnhe = NULL;
+ do_cache = fi != NULL;
if (fi) {
struct rtable __rcu **prth;
+ struct fib_nh *nh = &FIB_RES_NH(*res);
- fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
+ fnhe = find_exception(nh, fl4->daddr);
if (fnhe)
prth = &fnhe->fnhe_rth;
- else
- prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+ else {
+ if (unlikely(fl4->flowi4_flags &
+ FLOWI_FLAG_KNOWN_NH &&
+ !(nh->nh_gw &&
+ nh->nh_scope == RT_SCOPE_LINK))) {
+ do_cache = false;
+ goto add;
+ }
+ prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+ }
rth = rcu_dereference(*prth);
if (rt_cache_valid(rth)) {
dst_hold(&rth->dst);
return rth;
}
}
+
+add:
rth = rt_dst_alloc(dev_out,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM),
- fi);
+ do_cache);
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -1824,6 +1844,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_iif = orig_oif ? : 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2102,6 +2123,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
+ rt->rt_uses_gateway = ort->rt_uses_gateway;
INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2180,28 +2202,31 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (rt->rt_gateway &&
+ if (rt->rt_uses_gateway &&
nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
goto nla_put_failure;
+ expires = rt->dst.expires;
+ if (expires) {
+ unsigned long now = jiffies;
+
+ if (time_before(now, expires))
+ expires -= now;
+ else
+ expires = 0;
+ }
+
memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
- if (rt->rt_pmtu)
+ if (rt->rt_pmtu && expires)
metrics[RTAX_MTU - 1] = rt->rt_pmtu;
if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
if (fl4->flowi4_mark &&
- nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark))
+ nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
error = rt->dst.error;
- expires = rt->dst.expires;
- if (expires) {
- if (time_before(jiffies, expires))
- expires -= jiffies;
- else
- expires = 0;
- }
if (rt_is_input_route(rt)) {
if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9205e492dc9d..63d4eccc674d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -248,6 +248,8 @@ int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
ctxt = rcu_dereference(tcp_fastopen_ctx);
if (ctxt)
memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+ else
+ memset(user_key, 0, sizeof(user_key));
rcu_read_unlock();
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f32c02e2a543..197c0008503c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -549,14 +549,12 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
!tp->urg_data ||
before(tp->urg_seq, tp->copied_seq) ||
!before(tp->urg_seq, tp->rcv_nxt)) {
- struct sk_buff *skb;
answ = tp->rcv_nxt - tp->copied_seq;
- /* Subtract 1, if FIN is in queue. */
- skb = skb_peek_tail(&sk->sk_receive_queue);
- if (answ && skb)
- answ -= tcp_hdr(skb)->fin;
+ /* Subtract 1, if FIN was received */
+ if (answ && sock_flag(sk, SOCK_DONE))
+ answ--;
} else
answ = tp->urg_seq - tp->copied_seq;
release_sock(sk);
@@ -2766,6 +2764,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
info->tcpi_options |= TCPI_OPT_ECN;
if (tp->ecn_flags & TCP_ECN_SEEN)
info->tcpi_options |= TCPI_OPT_ECN_SEEN;
+ if (tp->syn_data_acked)
+ info->tcpi_options |= TCPI_OPT_SYN_DATA;
info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 432c36649db3..1db663983587 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5646,6 +5646,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
tcp_rearm_rto(sk);
return true;
}
+ tp->syn_data_acked = tp->syn_data;
return false;
}
@@ -5963,7 +5964,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
req = tp->fastopen_rsk;
if (req != NULL) {
- BUG_ON(sk->sk_state != TCP_SYN_RECV &&
+ WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
sk->sk_state != TCP_FIN_WAIT1);
if (tcp_check_req(sk, skb, req, NULL, true) == NULL)
@@ -6052,7 +6053,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
* ACK we have received, this would have acknowledged
* our SYNACK so stop the SYNACK timer.
*/
- if (acceptable && req != NULL) {
+ if (req != NULL) {
+ /* Return RST if ack_seq is invalid.
+ * Note that RFC793 only says to generate a
+ * DUPACK for it but for TCP Fast Open it seems
+ * better to treat this case like TCP_SYN_RECV
+ * above.
+ */
+ if (!acceptable)
+ return 1;
/* We no longer need the request sock. */
reqsk_fastopen_remove(sk, req, false);
tcp_rearm_rto(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 75735c9a6a9d..0c4a64355603 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -708,10 +708,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
/* When socket is gone, all binding information is lost.
- * routing might fail in this case. using iif for oif to
- * make sure we can deliver it
+ * routing might fail in this case. No choice here, if we choose to force
+ * input interface, we will misroute in case of asymmetric route.
*/
- arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb);
+ if (sk)
+ arg.bound_dev_if = sk->sk_bound_dev_if;
net = dev_net(skb_dst(skb)->dev);
arg.tos = ip_hdr(skb)->tos;
@@ -1460,6 +1461,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
skb_set_owner_r(skb, child);
__skb_queue_tail(&child->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tp->syn_data_acked = 1;
}
sk->sk_data_ready(sk, 0);
bh_unlock_sock(child);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 27536ba16c9d..a7302d974f32 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -510,6 +510,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rx_opt.mss_clamp = req->mss;
TCP_ECN_openreq_child(newtp, req);
newtp->fastopen_rsk = NULL;
+ newtp->syn_data_acked = 0;
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index fc04711e80c8..d47c1b4421a3 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -347,8 +347,8 @@ void tcp_retransmit_timer(struct sock *sk)
return;
}
if (tp->fastopen_rsk) {
- BUG_ON(sk->sk_state != TCP_SYN_RECV &&
- sk->sk_state != TCP_FIN_WAIT1);
+ WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
+ sk->sk_state != TCP_FIN_WAIT1);
tcp_fastopen_synack_timer(sk);
/* Before we receive ACK to our SYN-ACK don't retransmit
* anything else (e.g., data or FIN segments).
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 681ea2f413e2..05c5ab8d983c 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,6 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_gateway = rt->rt_gateway;
+ xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);