aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c16
-rw-r--r--net/ipv4/arp.c20
-rw-r--r--net/ipv4/devinet.c3
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/ip_forward.c19
-rw-r--r--net/ipv4/ip_input.c39
-rw-r--r--net/ipv4/ip_output.c72
-rw-r--r--net/ipv4/ip_vti.c2
-rw-r--r--net/ipv4/ipmr.c15
-rw-r--r--net/ipv4/netfilter/arp_tables.c3
-rw-r--r--net/ipv4/netfilter/arptable_filter.c7
-rw-r--r--net/ipv4/netfilter/ip_tables.c11
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c4
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c6
-rw-r--r--net/ipv4/netfilter/ipt_rpfilter.c5
-rw-r--r--net/ipv4/netfilter/iptable_filter.c9
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c17
-rw-r--r--net/ipv4/netfilter/iptable_nat.c22
-rw-r--r--net/ipv4/netfilter/iptable_raw.c9
-rw-r--r--net/ipv4/netfilter/iptable_security.c10
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c12
-rw-r--r--net/ipv4/netfilter/nf_conntrack_proto_icmp.c4
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c4
-rw-r--r--net/ipv4/netfilter/nf_dup_ipv4.c23
-rw-r--r--net/ipv4/netfilter/nf_nat_l3proto_ipv4.c42
-rw-r--r--net/ipv4/netfilter/nf_tables_arp.c6
-rw-r--r--net/ipv4/netfilter/nf_tables_ipv4.c10
-rw-r--r--net/ipv4/netfilter/nft_chain_nat_ipv4.c22
-rw-r--r--net/ipv4/netfilter/nft_chain_route_ipv4.c6
-rw-r--r--net/ipv4/netfilter/nft_dup_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nft_masq_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nft_redir_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nft_reject_ipv4.c5
-rw-r--r--net/ipv4/raw.c5
-rw-r--r--net/ipv4/route.c109
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/tcp_cong.c12
-rw-r--r--net/ipv4/tcp_input.c30
-rw-r--r--net/ipv4/tcp_ipv4.c12
-rw-r--r--net/ipv4/tcp_minisocks.c32
-rw-r--r--net/ipv4/tcp_output.c62
-rw-r--r--net/ipv4/xfrm4_input.c7
-rw-r--r--net/ipv4/xfrm4_output.c11
-rw-r--r--net/ipv4/xfrm4_policy.c1
44 files changed, 359 insertions, 357 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1d0c3adb6f34..8a556643b874 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1043,22 +1043,16 @@ void inet_register_protosw(struct inet_protosw *p)
goto out_illegal;
/* If we are trying to override a permanent protocol, bail. */
- answer = NULL;
last_perm = &inetsw[p->type];
list_for_each(lh, &inetsw[p->type]) {
answer = list_entry(lh, struct inet_protosw, list);
-
/* Check only the non-wild match. */
- if (INET_PROTOSW_PERMANENT & answer->flags) {
- if (protocol == answer->protocol)
- break;
- last_perm = lh;
- }
-
- answer = NULL;
+ if ((INET_PROTOSW_PERMANENT & answer->flags) == 0)
+ break;
+ if (protocol == answer->protocol)
+ goto out_permanent;
+ last_perm = lh;
}
- if (answer)
- goto out_permanent;
/* Add the new entry after the last permanent entry if any, so that
* the new entry does not override a permanent entry when matched with
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index f03db8b7abee..01308e6e6127 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -624,14 +624,20 @@ out:
}
EXPORT_SYMBOL(arp_create);
+static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ return dev_queue_xmit(skb);
+}
+
/*
* Send an arp packet.
*/
void arp_xmit(struct sk_buff *skb)
{
/* Send it off, maybe filter it using firewalling first. */
- NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, NULL, skb,
- NULL, skb->dev, dev_queue_xmit_sk);
+ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT,
+ dev_net(skb->dev), NULL, skb, NULL, skb->dev,
+ arp_xmit_finish);
}
EXPORT_SYMBOL(arp_xmit);
@@ -639,7 +645,7 @@ EXPORT_SYMBOL(arp_xmit);
* Process an arp request.
*/
-static int arp_process(struct sock *sk, struct sk_buff *skb)
+static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -651,7 +657,6 @@ static int arp_process(struct sock *sk, struct sk_buff *skb)
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
- struct net *net = dev_net(dev);
struct dst_entry *reply_dst = NULL;
bool is_garp = false;
@@ -870,7 +875,7 @@ out:
static void parp_redo(struct sk_buff *skb)
{
- arp_process(NULL, skb);
+ arp_process(dev_net(skb->dev), NULL, skb);
}
@@ -903,8 +908,9 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
- return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, NULL, skb,
- dev, NULL, arp_process);
+ return NF_HOOK(NFPROTO_ARP, NF_ARP_IN,
+ dev_net(dev), NULL, skb, dev, NULL,
+ arp_process);
consumeskb:
consume_skb(skb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 2d9cb1748f81..735008472844 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1654,7 +1654,8 @@ static size_t inet_get_link_af_size(const struct net_device *dev)
return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */
}
-static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev)
+static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev,
+ u32 ext_filter_mask)
{
struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
struct nlattr *nla;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7bb9c39e0a4d..ba2f90d90cb5 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -408,7 +408,7 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
}
EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
-struct dst_entry *inet_csk_route_req(struct sock *sk,
+struct dst_entry *inet_csk_route_req(const struct sock *sk,
struct flowi4 *fl4,
const struct request_sock *req)
{
@@ -563,7 +563,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
req->num_timeout >= rskq_defer_accept - 1;
}
-int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
+int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
{
int err = req->rsk_ops->rtx_syn_ack(parent, req);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 2d3aa408fbdc..d66cfb35ba74 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -61,18 +61,18 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
}
-static int ip_forward_finish(struct sock *sk, struct sk_buff *skb)
+static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
- IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
- IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP_ADD_STATS_BH(net, IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
skb_sender_cpu_clear(skb);
- return dst_output_sk(sk, skb);
+ return dst_output(sk, skb);
}
int ip_forward(struct sk_buff *skb)
@@ -81,6 +81,7 @@ int ip_forward(struct sk_buff *skb)
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options *opt = &(IPCB(skb)->opt);
+ struct net *net;
/* that should never happen */
if (skb->pkt_type != PACKET_HOST)
@@ -99,6 +100,7 @@ int ip_forward(struct sk_buff *skb)
return NET_RX_SUCCESS;
skb_forward_csum(skb);
+ net = dev_net(skb->dev);
/*
* According to the RFC, we must first decrease the TTL field. If
@@ -119,7 +121,7 @@ int ip_forward(struct sk_buff *skb)
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
if (ip_exceeds_mtu(skb, mtu)) {
- IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
goto drop;
@@ -143,8 +145,9 @@ int ip_forward(struct sk_buff *skb)
skb->priority = rt_tos2priority(iph->tos);
- return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb,
- skb->dev, rt->dst.dev, ip_forward_finish);
+ return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
+ net, NULL, skb, skb->dev, rt->dst.dev,
+ ip_forward_finish);
sr_failed:
/*
@@ -155,7 +158,7 @@ sr_failed:
too_many_hops:
/* Tell the sender its packet died... */
- IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index f4fc8a77aaa7..7cc9f7bb7fb7 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -188,10 +188,8 @@ bool ip_call_ra_chain(struct sk_buff *skb)
return false;
}
-static int ip_local_deliver_finish(struct sock *sk, struct sk_buff *skb)
+static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net *net = dev_net(skb->dev);
-
__skb_pull(skb, skb_network_header_len(skb));
rcu_read_lock();
@@ -254,8 +252,8 @@ int ip_local_deliver(struct sk_buff *skb)
return 0;
}
- return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, NULL, skb,
- skb->dev, NULL,
+ return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
+ dev_net(skb->dev), NULL, skb, skb->dev, NULL,
ip_local_deliver_finish);
}
@@ -311,7 +309,7 @@ drop:
int sysctl_ip_early_demux __read_mostly = 1;
EXPORT_SYMBOL(sysctl_ip_early_demux);
-static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb)
+static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
@@ -337,8 +335,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb)
iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EXDEV)
- NET_INC_STATS_BH(dev_net(skb->dev),
- LINUX_MIB_IPRPFILTER);
+ NET_INC_STATS_BH(net, LINUX_MIB_IPRPFILTER);
goto drop;
}
}
@@ -359,11 +356,9 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb)
rt = skb_rtable(skb);
if (rt->rt_type == RTN_MULTICAST) {
- IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST,
- skb->len);
+ IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_INMCAST, skb->len);
} else if (rt->rt_type == RTN_BROADCAST)
- IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST,
- skb->len);
+ IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_INBCAST, skb->len);
return dst_input(skb);
@@ -378,6 +373,7 @@ drop:
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
const struct iphdr *iph;
+ struct net *net;
u32 len;
/* When the interface is in promisc. mode, drop all the crap
@@ -387,11 +383,12 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
goto drop;
- IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len);
+ net = dev_net(dev);
+ IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_IN, skb->len);
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb) {
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INDISCARDS);
goto out;
}
@@ -417,7 +414,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
- IP_ADD_STATS_BH(dev_net(dev),
+ IP_ADD_STATS_BH(net,
IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
@@ -431,7 +428,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
len = ntohs(iph->tot_len);
if (skb->len < len) {
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
@@ -441,7 +438,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) {
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INDISCARDS);
goto drop;
}
@@ -453,14 +450,14 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
- return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb,
- dev, NULL,
+ return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+ net, NULL, skb, dev, NULL,
ip_rcv_finish);
csum_error:
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_CSUMERRORS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_CSUMERRORS);
inhdr_error:
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb(skb);
out:
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0138fada0951..06d2c87ed505 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -97,12 +97,14 @@ EXPORT_SYMBOL(ip_send_check);
static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
{
+ struct net *net = dev_net(skb_dst(skb)->dev);
struct iphdr *iph = ip_hdr(skb);
iph->tot_len = htons(skb->len);
ip_send_check(iph);
- return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, NULL,
- skb_dst(skb)->dev, dst_output_sk);
+ return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
+ net, sk, skb, NULL, skb_dst(skb)->dev,
+ dst_output_okfn);
}
int __ip_local_out(struct sk_buff *skb)
@@ -116,7 +118,7 @@ int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
err = __ip_local_out(skb);
if (likely(err == 1))
- err = dst_output_sk(sk, skb);
+ err = dst_output(sk, skb);
return err;
}
@@ -135,7 +137,7 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
* Add an ip header to a skbuff and send it out.
*
*/
-int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
+int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
__be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
{
struct inet_sock *inet = inet_sk(sk);
@@ -149,15 +151,17 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
iph->version = 4;
iph->ihl = 5;
iph->tos = inet->tos;
- if (ip_dont_fragment(sk, &rt->dst))
- iph->frag_off = htons(IP_DF);
- else
- iph->frag_off = 0;
iph->ttl = ip_select_ttl(inet, &rt->dst);
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
- ip_select_ident(sock_net(sk), skb, sk);
+ if (ip_dont_fragment(sk, &rt->dst)) {
+ iph->frag_off = htons(IP_DF);
+ iph->id = 0;
+ } else {
+ iph->frag_off = 0;
+ __ip_select_ident(sock_net(sk), iph, 1);
+ }
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
@@ -177,14 +181,15 @@ static int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
+ struct net *net = dev_net(dev);
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
u32 nexthop;
if (rt->rt_type == RTN_MULTICAST) {
- IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len);
+ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len);
} else if (rt->rt_type == RTN_BROADCAST)
- IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTBCAST, skb->len);
+ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len);
/* Be paranoid, rather than too clever. */
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
@@ -263,7 +268,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
return ret;
}
-static int ip_finish_output(struct sock *sk, struct sk_buff *skb)
+static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
unsigned int mtu;
@@ -271,7 +276,7 @@ static int ip_finish_output(struct sock *sk, struct sk_buff *skb)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
IPCB(skb)->flags |= IPSKB_REROUTED;
- return dst_output_sk(sk, skb);
+ return dst_output(sk, skb);
}
#endif
mtu = ip_skb_dst_mtu(skb);
@@ -288,11 +293,12 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
+ struct net *net = dev_net(dev);
/*
* If the indicated interface is up and running, send the packet.
*/
- IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
+ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
@@ -320,7 +326,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- sk, newskb, NULL, newskb->dev,
+ net, sk, newskb, NULL, newskb->dev,
dev_loopback_xmit);
}
@@ -335,26 +341,29 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
if (rt->rt_flags&RTCF_BROADCAST) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
- NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, newskb,
- NULL, newskb->dev, dev_loopback_xmit);
+ NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, newskb, NULL, newskb->dev,
+ dev_loopback_xmit);
}
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, NULL,
- skb->dev, ip_finish_output,
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, skb->dev,
+ ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
int ip_output(struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev;
+ struct net *net = dev_net(dev);
- IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
+ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb,
- NULL, dev,
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, dev,
ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
@@ -498,10 +507,9 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb,
if (unlikely(!skb->ignore_df ||
(IPCB(skb)->frag_max_size &&
IPCB(skb)->frag_max_size > mtu))) {
- struct rtable *rt = skb_rtable(skb);
- struct net_device *dev = rt->dst.dev;
+ struct net *net = dev_net(skb_rtable(skb)->dst.dev);
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
kfree_skb(skb);
@@ -529,9 +537,11 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
int offset;
__be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
+ struct net *net;
int err = 0;
dev = rt->dst.dev;
+ net = dev_net(dev);
/*
* Point into the IP datagram header.
@@ -624,7 +634,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
err = output(sk, skb);
if (!err)
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
@@ -634,7 +644,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
}
if (err == 0) {
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return 0;
}
@@ -643,7 +653,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
kfree_skb(frag);
frag = skb;
}
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
slow_path_clean:
@@ -765,15 +775,15 @@ slow_path:
if (err)
goto fail;
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
}
consume_skb(skb);
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
}
EXPORT_SYMBOL(ip_do_fragment);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 0c152087ca15..3b87ec5178f9 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -197,7 +197,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
- err = dst_output(skb);
+ err = dst_output(skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = skb->len;
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 866ee89f5254..cfcb996ec51b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1678,17 +1678,18 @@ static void ip_encap(struct net *net, struct sk_buff *skb,
nf_reset(skb);
}
-static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb)
+static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
- IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
- IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP_ADD_STATS_BH(net, IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
- return dst_output_sk(sk, skb);
+ return dst_output(sk, skb);
}
/*
@@ -1745,7 +1746,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
* to blackhole.
*/
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_FRAGFAILS);
ip_rt_put(rt);
goto out_free;
}
@@ -1787,8 +1788,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
* not mrouter) cannot join to more than one interface - it will
* result in receiving multiple packets.
*/
- NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb,
- skb->dev, dev,
+ NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
+ net, NULL, skb, skb->dev, dev,
ipmr_forward_finish);
return;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 8f87fc38ccde..2dad3e1c5f11 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -247,10 +247,10 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry)
}
unsigned int arpt_do_table(struct sk_buff *skb,
- unsigned int hook,
const struct nf_hook_state *state,
struct xt_table *table)
{
+ unsigned int hook = state->hook;
static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
unsigned int verdict = NF_DROP;
const struct arphdr *arp;
@@ -285,6 +285,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
*/
e = get_entry(table_base, private->hook_entry[hook]);
+ acpar.net = state->net;
acpar.in = state->in;
acpar.out = state->out;
acpar.hooknum = hook;
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index 93876d03120c..1897ee160920 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -27,13 +27,10 @@ static const struct xt_table packet_filter = {
/* The work comes in here from netfilter.c */
static unsigned int
-arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+arptable_filter_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- const struct net *net = dev_net(state->in ? state->in : state->out);
-
- return arpt_do_table(skb, ops->hooknum, state,
- net->ipv4.arptable_filter);
+ return arpt_do_table(skb, state, state->net->ipv4.arptable_filter);
}
static struct nf_hook_ops *arpfilter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index b0a86e73451c..42d0946956db 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -246,7 +246,8 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
return 0;
}
-static void trace_packet(const struct sk_buff *skb,
+static void trace_packet(struct net *net,
+ const struct sk_buff *skb,
unsigned int hook,
const struct net_device *in,
const struct net_device *out,
@@ -258,7 +259,6 @@ static void trace_packet(const struct sk_buff *skb,
const char *hookname, *chainname, *comment;
const struct ipt_entry *iter;
unsigned int rulenum = 0;
- struct net *net = dev_net(in ? in : out);
root = get_entry(private->entries, private->hook_entry[hook]);
@@ -285,10 +285,10 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry)
/* Returns one of the generic firewall policies, like NF_ACCEPT. */
unsigned int
ipt_do_table(struct sk_buff *skb,
- unsigned int hook,
const struct nf_hook_state *state,
struct xt_table *table)
{
+ unsigned int hook = state->hook;
static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
const struct iphdr *ip;
/* Initializing verdict to NF_DROP keeps gcc happy. */
@@ -315,6 +315,7 @@ ipt_do_table(struct sk_buff *skb,
acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
acpar.thoff = ip_hdrlen(skb);
acpar.hotdrop = false;
+ acpar.net = state->net;
acpar.in = state->in;
acpar.out = state->out;
acpar.family = NFPROTO_IPV4;
@@ -378,8 +379,8 @@ ipt_do_table(struct sk_buff *skb,
#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
/* The packet is traced: log it */
if (unlikely(skb->nf_trace))
- trace_packet(skb, hook, state->in, state->out,
- table->name, private, e);
+ trace_packet(state->net, skb, hook, state->in,
+ state->out, table->name, private, e);
#endif
/* Standard target? */
if (!t->u.kernel.target->target) {
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 45cb16a6a4a3..3f32c03e8b2e 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -507,14 +507,14 @@ static void arp_print(struct arp_payload *payload)
#endif
static unsigned int
-arp_mangle(const struct nf_hook_ops *ops,
+arp_mangle(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct arphdr *arp = arp_hdr(skb);
struct arp_payload *payload;
struct clusterip_config *c;
- struct net *net = dev_net(state->in ? state->in : state->out);
+ struct net *net = state->net;
/* we don't care about non-ethernet and non-ipv4 ARP */
if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 95ea633e8356..d7021f28c3f0 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -258,7 +258,7 @@ static unsigned int
synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_synproxy_info *info = par->targinfo;
- struct synproxy_net *snet = synproxy_pernet(dev_net(par->in));
+ struct synproxy_net *snet = synproxy_pernet(par->net);
struct synproxy_options opts = {};
struct tcphdr *th, _th;
@@ -299,11 +299,11 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
return XT_CONTINUE;
}
-static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops,
+static unsigned int ipv4_synproxy_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *nhs)
{
- struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out));
+ struct synproxy_net *snet = synproxy_pernet(nhs->net);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct nf_conn_synproxy *synproxy;
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 8618fd150c96..74dd6671b66d 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -32,12 +32,11 @@ static __be32 rpfilter_get_saddr(__be32 addr)
return addr;
}
-static bool rpfilter_lookup_reverse(struct flowi4 *fl4,
+static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4,
const struct net_device *dev, u8 flags)
{
struct fib_result res;
bool dev_match;
- struct net *net = dev_net(dev);
int ret __maybe_unused;
if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE))
@@ -98,7 +97,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
flow.flowi4_tos = RT_TOS(iph->tos);
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
- return rpfilter_lookup_reverse(&flow, par->in, info->flags) ^ invert;
+ return rpfilter_lookup_reverse(par->net, &flow, par->in, info->flags) ^ invert;
}
static int rpfilter_check(const struct xt_mtchk_param *par)
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index a0f3beca52d2..397ef2dd133e 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -33,19 +33,16 @@ static const struct xt_table packet_filter = {
};
static unsigned int
-iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+iptable_filter_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- const struct net *net;
-
- if (ops->hooknum == NF_INET_LOCAL_OUT &&
+ if (state->hook == NF_INET_LOCAL_OUT &&
(skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr)))
/* root is playing with raw sockets. */
return NF_ACCEPT;
- net = dev_net(state->in ? state->in : state->out);
- return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_filter);
+ return ipt_do_table(skb, state, state->net->ipv4.iptable_filter);
}
static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 62cbb8c5f4a8..2d6fc911866f 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -39,7 +39,6 @@ static const struct xt_table packet_mangler = {
static unsigned int
ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
{
- struct net_device *out = state->out;
unsigned int ret;
const struct iphdr *iph;
u_int8_t tos;
@@ -59,8 +58,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
daddr = iph->daddr;
tos = iph->tos;
- ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, state,
- dev_net(out)->ipv4.iptable_mangle);
+ ret = ipt_do_table(skb, state, state->net->ipv4.iptable_mangle);
/* Reroute for ANY change. */
if (ret != NF_DROP && ret != NF_STOLEN) {
iph = ip_hdr(skb);
@@ -80,18 +78,17 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
/* The work comes in here from netfilter.c. */
static unsigned int
-iptable_mangle_hook(const struct nf_hook_ops *ops,
+iptable_mangle_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- if (ops->hooknum == NF_INET_LOCAL_OUT)
+ if (state->hook == NF_INET_LOCAL_OUT)
return ipt_mangle_out(skb, state);
- if (ops->hooknum == NF_INET_POST_ROUTING)
- return ipt_do_table(skb, ops->hooknum, state,
- dev_net(state->out)->ipv4.iptable_mangle);
+ if (state->hook == NF_INET_POST_ROUTING)
+ return ipt_do_table(skb, state,
+ state->net->ipv4.iptable_mangle);
/* PREROUTING/INPUT/FORWARD: */
- return ipt_do_table(skb, ops->hooknum, state,
- dev_net(state->in)->ipv4.iptable_mangle);
+ return ipt_do_table(skb, state, state->net->ipv4.iptable_mangle);
}
static struct nf_hook_ops *mangle_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 0d4d9cdf98a4..3a2e4d830a0b 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -28,42 +28,40 @@ static const struct xt_table nf_nat_ipv4_table = {
.af = NFPROTO_IPV4,
};
-static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops,
+static unsigned int iptable_nat_do_chain(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct)
{
- struct net *net = nf_ct_net(ct);
-
- return ipt_do_table(skb, ops->hooknum, state, net->ipv4.nat_table);
+ return ipt_do_table(skb, state, state->net->ipv4.nat_table);
}
-static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops,
+static unsigned int iptable_nat_ipv4_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_fn(ops, skb, state, iptable_nat_do_chain);
+ return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain);
}
-static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops,
+static unsigned int iptable_nat_ipv4_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_in(ops, skb, state, iptable_nat_do_chain);
+ return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain);
}
-static unsigned int iptable_nat_ipv4_out(const struct nf_hook_ops *ops,
+static unsigned int iptable_nat_ipv4_out(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_out(ops, skb, state, iptable_nat_do_chain);
+ return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain);
}
-static unsigned int iptable_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+static unsigned int iptable_nat_ipv4_local_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_local_fn(ops, skb, state, iptable_nat_do_chain);
+ return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain);
}
static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 0356e6da4bb7..1ba02811acb0 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -20,19 +20,16 @@ static const struct xt_table packet_raw = {
/* The work comes in here from netfilter.c. */
static unsigned int
-iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+iptable_raw_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- const struct net *net;
-
- if (ops->hooknum == NF_INET_LOCAL_OUT &&
+ if (state->hook == NF_INET_LOCAL_OUT &&
(skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr)))
/* root is playing with raw sockets. */
return NF_ACCEPT;
- net = dev_net(state->in ? state->in : state->out);
- return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_raw);
+ return ipt_do_table(skb, state, state->net->ipv4.iptable_raw);
}
static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index 4bce3980ccd9..f534e2f05bad 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -37,20 +37,16 @@ static const struct xt_table security_table = {
};
static unsigned int
-iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+iptable_security_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- const struct net *net;
-
- if (ops->hooknum == NF_INET_LOCAL_OUT &&
+ if (state->hook == NF_INET_LOCAL_OUT &&
(skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr)))
/* Somebody is playing with raw sockets. */
return NF_ACCEPT;
- net = dev_net(state->in ? state->in : state->out);
- return ipt_do_table(skb, ops->hooknum, state,
- net->ipv4.iptable_security);
+ return ipt_do_table(skb, state, state->net->ipv4.iptable_security);
}
static struct nf_hook_ops *sectbl_ops __read_mostly;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 8a2caaf3940b..752fb40adcf8 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -92,7 +92,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
return NF_ACCEPT;
}
-static unsigned int ipv4_helper(const struct nf_hook_ops *ops,
+static unsigned int ipv4_helper(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
@@ -119,7 +119,7 @@ static unsigned int ipv4_helper(const struct nf_hook_ops *ops,
ct, ctinfo);
}
-static unsigned int ipv4_confirm(const struct nf_hook_ops *ops,
+static unsigned int ipv4_confirm(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
@@ -143,14 +143,14 @@ out:
return nf_conntrack_confirm(skb);
}
-static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops,
+static unsigned int ipv4_conntrack_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_conntrack_in(dev_net(state->in), PF_INET, ops->hooknum, skb);
+ return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}
-static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops,
+static unsigned int ipv4_conntrack_local(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
@@ -158,7 +158,7 @@ static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops,
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- return nf_conntrack_in(dev_net(state->out), PF_INET, ops->hooknum, skb);
+ return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}
/* Connection tracking may drop packets, but never alters them, so
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index cdde3ec496e9..c567e1b5d799 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -30,7 +30,7 @@ static inline struct nf_icmp_net *icmp_pernet(struct net *net)
}
static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
- struct nf_conntrack_tuple *tuple)
+ struct net *net, struct nf_conntrack_tuple *tuple)
{
const struct icmphdr *hp;
struct icmphdr _hdr;
@@ -144,7 +144,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
if (!nf_ct_get_tuplepr(skb,
skb_network_offset(skb) + ip_hdrlen(skb)
+ sizeof(struct icmphdr),
- PF_INET, &origtuple)) {
+ PF_INET, net, &origtuple)) {
pr_debug("icmp_error_message: failed to get tuple\n");
return -NF_ACCEPT;
}
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 9306ec4fab41..b246346ee849 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -61,7 +61,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
return IP_DEFRAG_CONNTRACK_OUT + zone_id;
}
-static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
+static unsigned int ipv4_conntrack_defrag(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
@@ -83,7 +83,7 @@ static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
/* Gather fragments. */
if (ip_is_fragment(ip_hdr(skb))) {
enum ip_defrag_users user =
- nf_ct_defrag_user(ops->hooknum, skb);
+ nf_ct_defrag_user(state->hook, skb);
if (nf_ct_ipv4_gather_frags(skb, user))
return NF_STOLEN;
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index 2d79e6e8d934..ce2a59e5c665 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -23,25 +23,10 @@
#include <net/netfilter/nf_conntrack.h>
#endif
-static struct net *pick_net(struct sk_buff *skb)
-{
-#ifdef CONFIG_NET_NS
- const struct dst_entry *dst;
-
- if (skb->dev != NULL)
- return dev_net(skb->dev);
- dst = skb_dst(skb);
- if (dst != NULL && dst->dev != NULL)
- return dev_net(dst->dev);
-#endif
- return &init_net;
-}
-
-static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw,
- int oif)
+static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb,
+ const struct in_addr *gw, int oif)
{
const struct iphdr *iph = ip_hdr(skb);
- struct net *net = pick_net(skb);
struct rtable *rt;
struct flowi4 fl4;
@@ -65,7 +50,7 @@ static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw,
return true;
}
-void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum,
+void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
const struct in_addr *gw, int oif)
{
struct iphdr *iph;
@@ -105,7 +90,7 @@ void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum,
--iph->ttl;
ip_send_check(iph);
- if (nf_dup_ipv4_route(skb, gw, oif)) {
+ if (nf_dup_ipv4_route(net, skb, gw, oif)) {
__this_cpu_write(nf_skb_duplicated, true);
ip_local_out(skb);
__this_cpu_write(nf_skb_duplicated, false);
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 22f4579b0c2a..bc3b9dcbf080 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -255,9 +255,9 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
unsigned int
-nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
- unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+ unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
@@ -266,7 +266,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
/* maniptype == SRC for postrouting. */
- enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+ enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
/* We never see fragments: conntrack defrags on pre-routing
* and local-out, and nf_nat_out protects post-routing.
@@ -295,7 +295,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
case IP_CT_RELATED_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
- ops->hooknum))
+ state->hook))
return NF_DROP;
else
return NF_ACCEPT;
@@ -308,21 +308,21 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
- ret = do_chain(ops, skb, state, ct);
+ ret = do_chain(priv, skb, state, ct);
if (ret != NF_ACCEPT)
return ret;
- if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+ if (nf_nat_initialized(ct, HOOK2MANIP(state->hook)))
break;
- ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+ ret = nf_nat_alloc_null_binding(ct, state->hook);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
- if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat,
+ if (nf_nat_oif_changed(state->hook, ctinfo, nat,
state->out))
goto oif_changed;
}
@@ -332,11 +332,11 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == IP_CT_ESTABLISHED_REPLY);
- if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out))
+ if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
goto oif_changed;
}
- return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+ return nf_nat_packet(ct, ctinfo, state->hook, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
@@ -345,9 +345,9 @@ oif_changed:
EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
unsigned int
-nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
- unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+ unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
@@ -355,7 +355,7 @@ nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
unsigned int ret;
__be32 daddr = ip_hdr(skb)->daddr;
- ret = nf_nat_ipv4_fn(ops, skb, state, do_chain);
+ ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
if (ret != NF_DROP && ret != NF_STOLEN &&
daddr != ip_hdr(skb)->daddr)
skb_dst_drop(skb);
@@ -365,9 +365,9 @@ nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
EXPORT_SYMBOL_GPL(nf_nat_ipv4_in);
unsigned int
-nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
- unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+ unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
@@ -384,7 +384,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- ret = nf_nat_ipv4_fn(ops, skb, state, do_chain);
+ ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
#ifdef CONFIG_XFRM
if (ret != NF_DROP && ret != NF_STOLEN &&
!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -396,7 +396,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
(ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.src.u.all !=
ct->tuplehash[!dir].tuple.dst.u.all)) {
- err = nf_xfrm_me_harder(skb, AF_INET);
+ err = nf_xfrm_me_harder(state->net, skb, AF_INET);
if (err < 0)
ret = NF_DROP_ERR(err);
}
@@ -407,9 +407,9 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
unsigned int
-nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
- unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+ unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
@@ -424,7 +424,7 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- ret = nf_nat_ipv4_fn(ops, skb, state, do_chain);
+ ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
if (ret != NF_DROP && ret != NF_STOLEN &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -440,7 +440,7 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.dst.u.all !=
ct->tuplehash[!dir].tuple.src.u.all) {
- err = nf_xfrm_me_harder(skb, AF_INET);
+ err = nf_xfrm_me_harder(state->net, skb, AF_INET);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index 8412268bbad1..9d09d4f59545 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -15,15 +15,15 @@
#include <net/netfilter/nf_tables.h>
static unsigned int
-nft_do_chain_arp(const struct nf_hook_ops *ops,
+nft_do_chain_arp(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nft_pktinfo pkt;
- nft_set_pktinfo(&pkt, ops, skb, state);
+ nft_set_pktinfo(&pkt, skb, state);
- return nft_do_chain(&pkt, ops);
+ return nft_do_chain(&pkt, priv);
}
static struct nft_af_info nft_af_arp __read_mostly = {
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index aa180d3a69a5..ca9dc3c46c4f 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -18,18 +18,18 @@
#include <net/ip.h>
#include <net/netfilter/nf_tables_ipv4.h>
-static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops,
+static unsigned int nft_do_chain_ipv4(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nft_pktinfo pkt;
- nft_set_pktinfo_ipv4(&pkt, ops, skb, state);
+ nft_set_pktinfo_ipv4(&pkt, skb, state);
- return nft_do_chain(&pkt, ops);
+ return nft_do_chain(&pkt, priv);
}
-static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
+static unsigned int nft_ipv4_output(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
@@ -41,7 +41,7 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
return NF_ACCEPT;
}
- return nft_do_chain_ipv4(ops, skb, state);
+ return nft_do_chain_ipv4(priv, skb, state);
}
struct nft_af_info nft_af_ipv4 __read_mostly = {
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index bf5c30ae14e4..f5c66a7a4bf2 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -26,44 +26,44 @@
#include <net/netfilter/nf_nat_l3proto.h>
#include <net/ip.h>
-static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_do_chain(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct)
{
struct nft_pktinfo pkt;
- nft_set_pktinfo_ipv4(&pkt, ops, skb, state);
+ nft_set_pktinfo_ipv4(&pkt, skb, state);
- return nft_do_chain(&pkt, ops);
+ return nft_do_chain(&pkt, priv);
}
-static unsigned int nft_nat_ipv4_fn(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv4_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_fn(ops, skb, state, nft_nat_do_chain);
+ return nf_nat_ipv4_fn(priv, skb, state, nft_nat_do_chain);
}
-static unsigned int nft_nat_ipv4_in(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv4_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_in(ops, skb, state, nft_nat_do_chain);
+ return nf_nat_ipv4_in(priv, skb, state, nft_nat_do_chain);
}
-static unsigned int nft_nat_ipv4_out(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv4_out(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_out(ops, skb, state, nft_nat_do_chain);
+ return nf_nat_ipv4_out(priv, skb, state, nft_nat_do_chain);
}
-static unsigned int nft_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv4_local_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- return nf_nat_ipv4_local_fn(ops, skb, state, nft_nat_do_chain);
+ return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain);
}
static const struct nf_chain_type nft_chain_nat_ipv4 = {
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index e335b0afdaf3..9f486b302108 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -21,7 +21,7 @@
#include <net/route.h>
#include <net/ip.h>
-static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+static unsigned int nf_route_table_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
@@ -37,7 +37,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- nft_set_pktinfo_ipv4(&pkt, ops, skb, state);
+ nft_set_pktinfo_ipv4(&pkt, skb, state);
mark = skb->mark;
iph = ip_hdr(skb);
@@ -45,7 +45,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
daddr = iph->daddr;
tos = iph->tos;
- ret = nft_do_chain(&pkt, ops);
+ ret = nft_do_chain(&pkt, priv);
if (ret != NF_DROP && ret != NF_QUEUE) {
iph = ip_hdr(skb);
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index b45932d43b69..bf855e64fc45 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -30,7 +30,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr,
};
int oif = regs->data[priv->sreg_dev];
- nf_dup_ipv4(pkt->skb, pkt->ops->hooknum, &gw, oif);
+ nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif);
}
static int nft_dup_ipv4_init(const struct nft_ctx *ctx,
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index 40e414c4ca56..b72ffc58e255 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -26,7 +26,7 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
- regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
+ regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->hook,
&range, pkt->out);
}
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index d8d795df9c13..c09d4381427e 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -36,7 +36,7 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
mr.range[0].flags |= priv->flags;
regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr,
- pkt->ops->hooknum);
+ pkt->hook);
}
static struct nft_expr_type nft_redir_ipv4_type;
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index b07e58b51158..c1582e03b628 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -27,11 +27,10 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr,
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nf_send_unreach(pkt->skb, priv->icmp_code,
- pkt->ops->hooknum);
+ nf_send_unreach(pkt->skb, priv->icmp_code, pkt->hook);
break;
case NFT_REJECT_TCP_RST:
- nf_send_reset(pkt->skb, pkt->ops->hooknum);
+ nf_send_reset(pkt->skb, pkt->hook);
break;
default:
break;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 561cd4b8fc6e..28ef8a913130 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -411,8 +411,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
- err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb,
- NULL, rt->dst.dev, dst_output_sk);
+ err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
+ net, sk, skb, NULL, rt->dst.dev,
+ dst_output_okfn);
if (err > 0)
err = net_xmit_errno(err);
if (err)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c6ad99ad0ffb..6bab84503cd9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1438,12 +1438,34 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
}
static struct rtable *rt_dst_alloc(struct net_device *dev,
+ unsigned int flags, u16 type,
bool nopolicy, bool noxfrm, bool will_cache)
{
- return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
- (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) |
- (nopolicy ? DST_NOPOLICY : 0) |
- (noxfrm ? DST_NOXFRM : 0));
+ struct rtable *rt;
+
+ rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
+ (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) |
+ (nopolicy ? DST_NOPOLICY : 0) |
+ (noxfrm ? DST_NOXFRM : 0));
+
+ if (rt) {
+ rt->rt_genid = rt_genid_ipv4(dev_net(dev));
+ rt->rt_flags = flags;
+ rt->rt_type = type;
+ rt->rt_is_input = 0;
+ rt->rt_iif = 0;
+ rt->rt_pmtu = 0;
+ rt->rt_gateway = 0;
+ rt->rt_uses_gateway = 0;
+ rt->rt_table_id = 0;
+ INIT_LIST_HEAD(&rt->rt_uncached);
+
+ rt->dst.output = ip_output;
+ if (flags & RTCF_LOCAL)
+ rt->dst.input = ip_local_deliver;
+ }
+
+ return rt;
}
/* called in rcu_read_lock() section */
@@ -1452,6 +1474,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
{
struct rtable *rth;
struct in_device *in_dev = __in_dev_get_rcu(dev);
+ unsigned int flags = RTCF_MULTICAST;
u32 itag = 0;
int err;
@@ -1477,7 +1500,10 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (err < 0)
goto e_err;
}
- rth = rt_dst_alloc(dev_net(dev)->loopback_dev,
+ if (our)
+ flags |= RTCF_LOCAL;
+
+ rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
if (!rth)
goto e_nobufs;
@@ -1486,20 +1512,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->dst.tclassid = itag;
#endif
rth->dst.output = ip_rt_bug;
-
- rth->rt_genid = rt_genid_ipv4(dev_net(dev));
- rth->rt_flags = RTCF_MULTICAST;
- rth->rt_type = RTN_MULTICAST;
rth->rt_is_input= 1;
- 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;
- rth->rt_flags |= RTCF_LOCAL;
- }
#ifdef CONFIG_IP_MROUTE
if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
@@ -1608,7 +1621,7 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
- rth = rt_dst_alloc(out_dev->dev,
+ rth = rt_dst_alloc(out_dev->dev, 0, res->type,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache);
if (!rth) {
@@ -1616,19 +1629,12 @@ static int __mkroute_input(struct sk_buff *skb,
goto cleanup;
}
- rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev));
- rth->rt_flags = 0;
- rth->rt_type = res->type;
rth->rt_is_input = 1;
- 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->table)
+ rth->rt_table_id = res->table->tb_id;
RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
- rth->dst.output = ip_output;
rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
@@ -1706,6 +1712,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
goto martian_source;
res.fi = NULL;
+ res.table = NULL;
if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
goto brd_input;
@@ -1795,26 +1802,18 @@ local_input:
}
}
- rth = rt_dst_alloc(net->loopback_dev,
+ rth = rt_dst_alloc(net->loopback_dev, flags | RTCF_LOCAL, res.type,
IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache);
if (!rth)
goto e_nobufs;
- rth->dst.input= ip_local_deliver;
rth->dst.output= ip_rt_bug;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
-
- rth->rt_genid = rt_genid_ipv4(net);
- rth->rt_flags = flags|RTCF_LOCAL;
- rth->rt_type = res.type;
rth->rt_is_input = 1;
- 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.table)
+ rth->rt_table_id = res.table->tb_id;
RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
@@ -1836,6 +1835,7 @@ no_route:
RT_CACHE_STAT_INC(in_no_route);
res.type = RTN_UNREACHABLE;
res.fi = NULL;
+ res.table = NULL;
goto local_input;
/*
@@ -1987,28 +1987,19 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
}
add:
- rth = rt_dst_alloc(dev_out,
+ rth = rt_dst_alloc(dev_out, flags, type,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM),
do_cache);
if (!rth)
return ERR_PTR(-ENOBUFS);
- rth->dst.output = ip_output;
-
- rth->rt_genid = rt_genid_ipv4(dev_net(dev_out));
- rth->rt_flags = flags;
- rth->rt_type = type;
- rth->rt_is_input = 0;
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);
+ if (res->table)
+ rth->rt_table_id = res->table->tb_id;
+
RT_CACHE_STAT_INC(out_slow_tot);
- if (flags & RTCF_LOCAL)
- rth->dst.input = ip_local_deliver;
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
@@ -2302,7 +2293,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
}
struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
- struct sock *sk)
+ const struct sock *sk)
{
struct rtable *rt = __ip_route_output_key(net, flp4);
@@ -2318,7 +2309,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
u32 seq, int event, int nowait, unsigned int flags)
{
@@ -2338,8 +2329,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
r->rtm_tos = fl4->flowi4_tos;
- r->rtm_table = RT_TABLE_MAIN;
- if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN))
+ r->rtm_table = table_id;
+ if (nla_put_u32(skb, RTA_TABLE, table_id))
goto nla_put_failure;
r->rtm_type = rt->rt_type;
r->rtm_scope = RT_SCOPE_UNIVERSE;
@@ -2444,6 +2435,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
int err;
int mark;
struct sk_buff *skb;
+ u32 table_id = RT_TABLE_MAIN;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2513,7 +2505,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(net, dst, src, &fl4, skb,
+ if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
+ table_id = rt->rt_table_id;
+
+ err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err < 0)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index d70b1f603692..6595affded20 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -345,7 +345,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
ireq->wscale_ok = tcp_opt.wscale_ok;
ireq->tstamp_ok = tcp_opt.saw_tstamp;
req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
- treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0;
+ treq->snt_synack.v64 = 0;
treq->tfo_listener = false;
ireq->ir_iif = sk->sk_bound_dev_if;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 93c4dc3ab23f..882caa4e72bc 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -173,6 +173,10 @@ out:
*/
if (ca->get_info)
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+ if (ca->flags & TCP_CONG_NEEDS_ECN)
+ INET_ECN_xmit(sk);
+ else
+ INET_ECN_dontxmit(sk);
}
void tcp_init_congestion_control(struct sock *sk)
@@ -181,6 +185,10 @@ void tcp_init_congestion_control(struct sock *sk)
if (icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
+ if (tcp_ca_needs_ecn(sk))
+ INET_ECN_xmit(sk);
+ else
+ INET_ECN_dontxmit(sk);
}
static void tcp_reinit_congestion_control(struct sock *sk,
@@ -192,8 +200,8 @@ static void tcp_reinit_congestion_control(struct sock *sk,
icsk->icsk_ca_ops = ca;
icsk->icsk_ca_setsockopt = 1;
- if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
- icsk->icsk_ca_ops->init(sk);
+ if (sk->sk_state != TCP_CLOSE)
+ tcp_init_congestion_control(sk);
}
/* Manage refcounts on socket close. */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a8f515bb19c4..497adf58a6b8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2953,21 +2953,21 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
}
/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
-static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
+void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
{
- struct tcp_sock *tp = tcp_sk(sk);
- long seq_rtt_us = -1L;
+ long rtt_us = -1L;
- if (synack_stamp && !tp->total_retrans)
- seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp);
+ if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) {
+ struct skb_mstamp now;
- /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets
- * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack()
- */
- if (!tp->srtt_us)
- tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L);
+ skb_mstamp_get(&now);
+ rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack);
+ }
+
+ tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L);
}
+
static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -5706,7 +5706,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
struct request_sock *req;
int queued = 0;
bool acceptable;
- u32 synack_stamp;
tp->rx_opt.saw_tstamp = 0;
@@ -5785,15 +5784,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
if (!acceptable)
return 1;
+ if (!tp->srtt_us)
+ tcp_synack_rtt_meas(sk, req);
+
/* Once we leave TCP_SYN_RECV, we no longer need req
* so release it.
*/
if (req) {
- synack_stamp = tcp_rsk(req)->snt_synack;
tp->total_retrans = req->num_retrans;
reqsk_fastopen_remove(sk, req, false);
} else {
- synack_stamp = tp->lsndtime;
/* Make sure socket is routed, for correct metrics. */
icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_congestion_control(sk);
@@ -5816,7 +5816,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
- tcp_synack_rtt_meas(sk, synack_stamp);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
@@ -6027,7 +6026,7 @@ static void tcp_openreq_init(struct request_sock *req,
req->cookie_ts = 0;
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
- tcp_rsk(req)->snt_synack = tcp_time_stamp;
+ skb_mstamp_get(&tcp_rsk(req)->snt_synack);
tcp_rsk(req)->last_oow_ack_time = 0;
req->mss = rx_opt->mss_clamp;
req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
@@ -6228,6 +6227,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
}
tcp_rsk(req)->snt_isn = isn;
+ tcp_rsk(req)->txhash = net_tx_rndhash();
tcp_openreq_init_rwin(req, sk, dst);
fastopen = !want_cookie &&
tcp_try_fastopen(sk, skb, req, &foc, dst);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 93898e093d4e..a23ba7daecbf 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -818,7 +818,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
* This still operates on a request_sock only, not on a big
* socket.
*/
-static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
+static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl,
struct request_sock *req,
u16 queue_mapping,
@@ -865,7 +865,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
*/
/* Find the Key structure for an address. */
-struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
const union tcp_md5_addr *addr,
int family)
{
@@ -877,7 +877,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
/* caller either holds rcu_read_lock() or socket lock */
md5sig = rcu_dereference_check(tp->md5sig_info,
sock_owned_by_user(sk) ||
- lockdep_is_held(&sk->sk_lock.slock));
+ lockdep_is_held((spinlock_t *)&sk->sk_lock.slock));
if (!md5sig)
return NULL;
#if IS_ENABLED(CONFIG_IPV6)
@@ -894,7 +894,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
}
EXPORT_SYMBOL(tcp_md5_do_lookup);
-struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
+struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
const struct sock *addr_sk)
{
const union tcp_md5_addr *addr;
@@ -1168,7 +1168,8 @@ static bool tcp_v4_inbound_md5_hash(struct sock *sk,
}
#endif
-static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener,
+static void tcp_v4_init_req(struct request_sock *req,
+ const struct sock *sk_listener,
struct sk_buff *skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
@@ -1277,7 +1278,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newinet->mc_ttl = ip_hdr(skb)->ttl;
newinet->rcv_tos = ip_hdr(skb)->tos;
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- sk_set_txhash(newsk);
if (inet_opt)
inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
newinet->inet_id = newtp->write_seq ^ jiffies;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index def765911ff8..e4fe62b6b106 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -361,27 +361,35 @@ void tcp_twsk_destructor(struct sock *sk)
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
+/* Warning : This function is called without sk_listener being locked.
+ * Be sure to read socket fields once, as their value could change under us.
+ */
void tcp_openreq_init_rwin(struct request_sock *req,
- struct sock *sk, struct dst_entry *dst)
+ const struct sock *sk_listener,
+ const struct dst_entry *dst)
{
struct inet_request_sock *ireq = inet_rsk(req);
- struct tcp_sock *tp = tcp_sk(sk);
- __u8 rcv_wscale;
+ const struct tcp_sock *tp = tcp_sk(sk_listener);
+ u16 user_mss = READ_ONCE(tp->rx_opt.user_mss);
+ int full_space = tcp_full_space(sk_listener);
int mss = dst_metric_advmss(dst);
+ u32 window_clamp;
+ __u8 rcv_wscale;
- if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
- mss = tp->rx_opt.user_mss;
+ if (user_mss && user_mss < mss)
+ mss = user_mss;
+ window_clamp = READ_ONCE(tp->window_clamp);
/* Set this up on the first call only */
- req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+ req->window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
/* limit the window selection if the user enforce a smaller rx buffer */
- if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
- (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
- req->window_clamp = tcp_full_space(sk);
+ if (sk_listener->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->window_clamp > full_space || req->window_clamp == 0))
+ req->window_clamp = full_space;
/* tcp_full_space because it is guaranteed to be the first packet */
- tcp_select_initial_window(tcp_full_space(sk),
+ tcp_select_initial_window(full_space,
mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
&req->rcv_wnd,
&req->window_clamp,
@@ -469,7 +477,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tcp_enable_early_retrans(newtp);
newtp->tlp_high_seq = 0;
- newtp->lsndtime = treq->snt_synack;
+ newtp->lsndtime = treq->snt_synack.stamp_jiffies;
+ newsk->sk_txhash = treq->txhash;
newtp->last_oow_ack_time = 0;
newtp->total_retrans = req->num_retrans;
@@ -759,6 +768,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
+ tcp_synack_rtt_meas(child, req);
inet_csk_reqsk_queue_drop(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
/* Warning: caller must not call reqsk_put(req);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1100ffe4a722..9e53dd9bfcad 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -357,14 +357,10 @@ static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
}
static void
-tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
- struct sock *sk)
+tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
{
- if (inet_rsk(req)->ecn_ok) {
+ if (inet_rsk(req)->ecn_ok)
th->ece = 1;
- if (tcp_ca_needs_ecn(sk))
- INET_ECN_xmit(sk);
- }
}
/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
@@ -612,12 +608,11 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
}
/* Set up TCP options for SYN-ACKs. */
-static unsigned int tcp_synack_options(struct sock *sk,
- struct request_sock *req,
- unsigned int mss, struct sk_buff *skb,
- struct tcp_out_options *opts,
- const struct tcp_md5sig_key *md5,
- struct tcp_fastopen_cookie *foc)
+static unsigned int tcp_synack_options(struct request_sock *req,
+ unsigned int mss, struct sk_buff *skb,
+ struct tcp_out_options *opts,
+ const struct tcp_md5sig_key *md5,
+ struct tcp_fastopen_cookie *foc)
{
struct inet_request_sock *ireq = inet_rsk(req);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -2165,7 +2160,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
/* Don't do any loss probe on a Fast Open connection before 3WHS
* finishes.
*/
- if (sk->sk_state == TCP_SYN_RECV)
+ if (tp->fastopen_rsk)
return false;
/* TLP is only scheduled when next timer event is RTO. */
@@ -2175,7 +2170,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
/* Schedule a loss probe in 2*RTT for SACK capable connections
* in Open state, that are either limited by cwnd or application.
*/
- if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out ||
+ if (sysctl_tcp_early_retrans < 3 || !tp->packets_out ||
!tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
return false;
@@ -2184,9 +2179,10 @@ bool tcp_schedule_loss_probe(struct sock *sk)
return false;
/* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
- * for delayed ack when there's one outstanding packet.
+ * for delayed ack when there's one outstanding packet. If no RTT
+ * sample is available then probe after TCP_TIMEOUT_INIT.
*/
- timeout = rtt << 1;
+ timeout = rtt << 1 ? : TCP_TIMEOUT_INIT;
if (tp->packets_out == 1)
timeout = max_t(u32, timeout,
(rtt + (rtt >> 1) + TCP_DELACK_MAX));
@@ -2949,20 +2945,25 @@ int tcp_send_synack(struct sock *sk)
* Allocate one skb and build a SYNACK packet.
* @dst is consumed : Caller should not use it again.
*/
-struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
+struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct tcp_fastopen_cookie *foc)
{
- struct tcp_out_options opts;
struct inet_request_sock *ireq = inet_rsk(req);
- struct tcp_sock *tp = tcp_sk(sk);
- struct tcphdr *th;
- struct sk_buff *skb;
+ const struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_key *md5 = NULL;
+ struct tcp_out_options opts;
+ struct sk_buff *skb;
int tcp_header_size;
+ struct tcphdr *th;
+ u16 user_mss;
int mss;
- skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC);
+ /* sk is a const pointer, because we want to express multiple cpus
+ * might call us concurrently.
+ * sock_wmalloc() will change sk->sk_wmem_alloc in an atomic way.
+ */
+ skb = sock_wmalloc((struct sock *)sk, MAX_TCP_HEADER, 1, GFP_ATOMIC);
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
@@ -2973,8 +2974,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
skb_dst_set(skb, dst);
mss = dst_metric_advmss(dst);
- if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
- mss = tp->rx_opt.user_mss;
+ user_mss = READ_ONCE(tp->rx_opt.user_mss);
+ if (user_mss && user_mss < mss)
+ mss = user_mss;
memset(&opts, 0, sizeof(opts));
#ifdef CONFIG_SYN_COOKIES
@@ -2988,8 +2990,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
rcu_read_lock();
md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
#endif
- tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
- foc) + sizeof(*th);
+ skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+ tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
+ sizeof(*th);
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
@@ -2998,7 +3001,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
memset(th, 0, sizeof(struct tcphdr));
th->syn = 1;
th->ack = 1;
- tcp_ecn_make_synack(req, th, sk);
+ tcp_ecn_make_synack(req, th);
th->source = htons(ireq->ir_num);
th->dest = ireq->ir_rmt_port;
/* Setting of flags are superfluous here for callers (and ECE is
@@ -3013,7 +3016,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(min(req->rcv_wnd, 65535U));
- tcp_options_write((__be32 *)(th + 1), tp, &opts);
+ tcp_options_write((__be32 *)(th + 1), NULL, &opts);
th->doff = (tcp_header_size >> 2);
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
@@ -3500,12 +3503,13 @@ void tcp_send_probe0(struct sock *sk)
TCP_RTO_MAX);
}
-int tcp_rtx_synack(struct sock *sk, struct request_sock *req)
+int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
{
const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific;
struct flowi fl;
int res;
+ tcp_rsk(req)->txhash = net_tx_rndhash();
res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL);
if (!res) {
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 60b032f58ccc..62e1e72db461 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -22,7 +22,8 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb)
return xfrm4_extract_header(skb);
}
-static inline int xfrm4_rcv_encap_finish(struct sock *sk, struct sk_buff *skb)
+static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
{
if (!skb_dst(skb)) {
const struct iphdr *iph = ip_hdr(skb);
@@ -52,8 +53,8 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
iph->tot_len = htons(skb->len);
ip_send_check(iph);
- NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb,
- skb->dev, NULL,
+ NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+ dev_net(skb->dev), NULL, skb, skb->dev, NULL,
xfrm4_rcv_encap_finish);
return 0;
}
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 2878dbfffeb7..cd6be736e19f 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -80,14 +80,14 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
return xfrm_output(sk, skb);
}
-static int __xfrm4_output(struct sock *sk, struct sk_buff *skb)
+static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct xfrm_state *x = skb_dst(skb)->xfrm;
#ifdef CONFIG_NETFILTER
if (!x) {
IPCB(skb)->flags |= IPSKB_REROUTED;
- return dst_output_sk(sk, skb);
+ return dst_output(sk, skb);
}
#endif
@@ -96,8 +96,11 @@ static int __xfrm4_output(struct sock *sk, struct sk_buff *skb)
int xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb,
- NULL, skb_dst(skb)->dev, __xfrm4_output,
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, skb_dst(skb)->dev,
+ __xfrm4_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index c10a9ee68433..0304d1680ca2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -97,6 +97,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
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;
+ xdst->u.rt.rt_table_id = rt->rt_table_id;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
return 0;