summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/net/ip.h5
-rw-r--r--include/net/ip_fib.h3
-rw-r--r--include/net/route.h1
-rw-r--r--net/ipv4/fib_frontend.c38
-rw-r--r--net/ipv4/icmp.c6
-rw-r--r--net/ipv4/ip_options.c22
-rw-r--r--net/ipv4/ip_output.c9
-rw-r--r--net/ipv4/ip_sockglue.c7
-rw-r--r--net/ipv4/route.c38
-rw-r--r--net/ipv4/tcp_ipv4.c8
-rw-r--r--net/ipv4/xfrm4_policy.c1
11 files changed, 73 insertions, 65 deletions
diff --git a/include/net/ip.h b/include/net/ip.h
index 50841bd..ec5cfde 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -158,8 +158,9 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
}
-void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
- const struct ip_reply_arg *arg, unsigned int len);
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
+ __be32 saddr, const struct ip_reply_arg *arg,
+ unsigned int len);
struct ipv4_config {
int log_martians;
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 4b347c0..9e6c26d 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -230,9 +230,10 @@ extern struct fib_table *fib_get_table(struct net *net, u32 id);
/* Exported by fib_frontend.c */
extern const struct nla_policy rtm_ipv4_policy[];
extern void ip_fib_init(void);
+extern __be32 fib_compute_spec_dst(struct sk_buff *skb);
extern int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
- __be32 *spec_dst, u32 *itag);
+ u32 *itag);
extern void fib_select_default(struct fib_result *res);
/* Exported by fib_semantics.c */
diff --git a/include/net/route.h b/include/net/route.h
index 47eb25a..211e266 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -65,7 +65,6 @@ struct rtable {
__be32 rt_gateway;
/* Miscellaneous cached information */
- __be32 rt_spec_dst; /* RFC1122 specific destination */
u32 rt_peer_genid;
unsigned long _peer; /* long-living peer info */
struct fib_info *fi; /* for client ref to shared metrics */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3854411..63b11ca 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -180,6 +180,35 @@ unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
}
EXPORT_SYMBOL(inet_dev_addr_type);
+__be32 fib_compute_spec_dst(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ struct in_device *in_dev;
+ struct fib_result res;
+ struct flowi4 fl4;
+ struct net *net;
+
+ if (skb->pkt_type != PACKET_BROADCAST &&
+ skb->pkt_type != PACKET_MULTICAST)
+ return ip_hdr(skb)->daddr;
+
+ in_dev = __in_dev_get_rcu(dev);
+ BUG_ON(!in_dev);
+ fl4.flowi4_oif = 0;
+ fl4.flowi4_iif = 0;
+ fl4.daddr = ip_hdr(skb)->saddr;
+ fl4.saddr = ip_hdr(skb)->daddr;
+ fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
+ fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+ fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
+
+ net = dev_net(dev);
+ if (!fib_lookup(net, &fl4, &res))
+ return FIB_RES_PREFSRC(net, res);
+ else
+ return inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
+}
+
/* Given (packet source, input interface) and optional (dst, oif, tos):
* - (main) check, that source is valid i.e. not broadcast or our local
* address.
@@ -189,8 +218,7 @@ EXPORT_SYMBOL(inet_dev_addr_type);
* called with rcu_read_lock()
*/
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos,
- int oif, struct net_device *dev, __be32 *spec_dst,
- u32 *itag)
+ int oif, struct net_device *dev, u32 *itag)
{
struct in_device *in_dev;
struct flowi4 fl4;
@@ -229,7 +257,6 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos,
if (res.type != RTN_LOCAL || !accept_local)
goto e_inval;
}
- *spec_dst = FIB_RES_PREFSRC(net, res);
fib_combine_itag(itag, &res);
dev_match = false;
@@ -258,17 +285,14 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos,
ret = 0;
if (fib_lookup(net, &fl4, &res) == 0) {
- if (res.type == RTN_UNICAST) {
- *spec_dst = FIB_RES_PREFSRC(net, res);
+ if (res.type == RTN_UNICAST)
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
- }
}
return ret;
last_resort:
if (rpf)
goto e_rpf;
- *spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
*itag = 0;
return 0;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 49a74cc..4bce5a2 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -95,6 +95,7 @@
#include <net/checksum.h>
#include <net/xfrm.h>
#include <net/inet_common.h>
+#include <net/ip_fib.h>
/*
* Build xmit assembly blocks
@@ -333,7 +334,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
struct flowi4 fl4;
struct sock *sk;
struct inet_sock *inet;
- __be32 daddr;
+ __be32 daddr, saddr;
if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
return;
@@ -347,6 +348,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
inet->tos = ip_hdr(skb)->tos;
daddr = ipc.addr = ip_hdr(skb)->saddr;
+ saddr = fib_compute_spec_dst(skb);
ipc.opt = NULL;
ipc.tx_flags = 0;
if (icmp_param->replyopts.opt.opt.optlen) {
@@ -356,7 +358,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
}
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
- fl4.saddr = rt->rt_spec_dst;
+ fl4.saddr = saddr;
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 708b994..766dfe56 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -27,6 +27,7 @@
#include <net/icmp.h>
#include <net/route.h>
#include <net/cipso_ipv4.h>
+#include <net/ip_fib.h>
/*
* Write options to IP header, record destination address to
@@ -104,7 +105,7 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
sptr = skb_network_header(skb);
dptr = dopt->__data;
- daddr = skb_rtable(skb)->rt_spec_dst;
+ daddr = fib_compute_spec_dst(skb);
if (sopt->rr) {
optlen = sptr[sopt->rr+1];
@@ -250,15 +251,14 @@ void ip_options_fragment(struct sk_buff *skb)
int ip_options_compile(struct net *net,
struct ip_options *opt, struct sk_buff *skb)
{
- int l;
- unsigned char *iph;
- unsigned char *optptr;
- int optlen;
+ __be32 spec_dst = (__force __be32) 0;
unsigned char *pp_ptr = NULL;
- struct rtable *rt = NULL;
+ unsigned char *optptr;
+ unsigned char *iph;
+ int optlen, l;
if (skb != NULL) {
- rt = skb_rtable(skb);
+ spec_dst = fib_compute_spec_dst(skb);
optptr = (unsigned char *)&(ip_hdr(skb)[1]);
} else
optptr = opt->__data;
@@ -330,8 +330,8 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 2;
goto error;
}
- if (rt) {
- memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
+ if (skb) {
+ memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
opt->is_changed = 1;
}
optptr[2] += 4;
@@ -372,8 +372,8 @@ int ip_options_compile(struct net *net,
goto error;
}
opt->ts = optptr - iph;
- if (rt) {
- memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
+ if (skb) {
+ memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
timeptr = &optptr[optptr[2]+3];
}
opt->ts_needaddr = 1;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0f3185a..2630900 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1459,13 +1459,14 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
/*
* Generic function to send a packet as reply to another packet.
- * Used to send TCP resets so far. ICMP should use this function too.
+ * Used to send TCP resets so far.
*
* Should run single threaded per socket because it uses the sock
* structure to pass arguments.
*/
-void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
- const struct ip_reply_arg *arg, unsigned int len)
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
+ __be32 saddr, const struct ip_reply_arg *arg,
+ unsigned int len)
{
struct inet_sock *inet = inet_sk(sk);
struct ip_options_data replyopts;
@@ -1491,7 +1492,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
RT_TOS(arg->tos),
RT_SCOPE_UNIVERSE, sk->sk_protocol,
ip_reply_arg_flowi_flags(arg),
- daddr, rt->rt_spec_dst,
+ daddr, saddr,
tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 0d11f23..de29f46 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -40,6 +40,7 @@
#if IS_ENABLED(CONFIG_IPV6)
#include <net/transp_v6.h>
#endif
+#include <net/ip_fib.h>
#include <linux/errqueue.h>
#include <asm/uaccess.h>
@@ -1019,8 +1020,8 @@ e_inval:
* @sk: socket
* @skb: buffer
*
- * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst
- * in skb->cb[] before dst drop.
+ * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
+ * destination in skb->cb[] before dst drop.
* This way, receiver doesnt make cache line misses to read rtable.
*/
void ipv4_pktinfo_prepare(struct sk_buff *skb)
@@ -1030,7 +1031,7 @@ void ipv4_pktinfo_prepare(struct sk_buff *skb)
if (rt) {
pktinfo->ipi_ifindex = rt->rt_iif;
- pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst;
+ pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
} else {
pktinfo->ipi_ifindex = 0;
pktinfo->ipi_spec_dst.s_addr = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 81533e3..83d56a0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -440,7 +440,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
r->rt_key_tos,
-1,
HHUptod,
- r->rt_spec_dst, &len);
+ 0, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
}
@@ -1978,7 +1978,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
{
unsigned int hash;
struct rtable *rth;
- __be32 spec_dst;
struct in_device *in_dev = __in_dev_get_rcu(dev);
u32 itag = 0;
int err;
@@ -1999,10 +1998,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (ipv4_is_zeronet(saddr)) {
if (!ipv4_is_local_multicast(daddr))
goto e_inval;
- spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
} else {
- err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst,
- &itag);
+ err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &itag);
if (err < 0)
goto e_err;
}
@@ -2029,7 +2026,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
- rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
rt_init_peer(rth, dev_net(dev)->ipv4.peers);
rth->fi = NULL;
@@ -2093,7 +2089,6 @@ static int __mkroute_input(struct sk_buff *skb,
int err;
struct in_device *out_dev;
unsigned int flags = 0;
- __be32 spec_dst;
u32 itag;
/* get a working reference to the output device */
@@ -2105,7 +2100,7 @@ static int __mkroute_input(struct sk_buff *skb,
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
- in_dev->dev, &spec_dst, &itag);
+ in_dev->dev, &itag);
if (err < 0) {
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
@@ -2157,7 +2152,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
- rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
rt_init_peer(rth, &res->table->tb_peers);
rth->fi = NULL;
@@ -2223,7 +2217,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u32 itag = 0;
struct rtable *rth;
unsigned int hash;
- __be32 spec_dst;
int err = -EINVAL;
struct net *net = dev_net(dev);
@@ -2281,12 +2274,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (res.type == RTN_LOCAL) {
err = fib_validate_source(skb, saddr, daddr, tos,
net->loopback_dev->ifindex,
- dev, &spec_dst, &itag);
+ dev, &itag);
if (err < 0)
goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
- spec_dst = daddr;
goto local_input;
}
@@ -2302,11 +2294,8 @@ brd_input:
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
- if (ipv4_is_zeronet(saddr))
- spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
- else {
- err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst,
- &itag);
+ if (!ipv4_is_zeronet(saddr)) {
+ err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &itag);
if (err < 0)
goto martian_source_keep_err;
if (err)
@@ -2344,7 +2333,6 @@ local_input:
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
- rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
rt_init_peer(rth, net->ipv4.peers);
rth->fi = NULL;
@@ -2362,7 +2350,6 @@ local_input:
no_route:
RT_CACHE_STAT_INC(in_no_route);
- spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
res.type = RTN_UNREACHABLE;
if (err == -ESRCH)
err = -ENETUNREACH;
@@ -2545,7 +2532,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_oif = orig_oif;
rth->rt_mark = fl4->flowi4_mark;
rth->rt_gateway = fl4->daddr;
- rth->rt_spec_dst= fl4->saddr;
rth->rt_peer_genid = 0;
rt_init_peer(rth, (res->table ?
&res->table->tb_peers :
@@ -2554,12 +2540,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
RT_CACHE_STAT_INC(out_slow_tot);
- if (flags & RTCF_LOCAL) {
+ if (flags & RTCF_LOCAL)
rth->dst.input = ip_local_deliver;
- rth->rt_spec_dst = fl4->daddr;
- }
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
- rth->rt_spec_dst = fl4->saddr;
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
rth->dst.output = ip_mc_output;
@@ -2890,7 +2873,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_dst = ort->rt_dst;
rt->rt_src = ort->rt_src;
rt->rt_gateway = ort->rt_gateway;
- rt->rt_spec_dst = ort->rt_spec_dst;
rt_transfer_peer(rt, ort);
rt->fi = ort->fi;
if (rt->fi)
@@ -2965,10 +2947,8 @@ static int rt_fill_info(struct net *net,
nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
goto nla_put_failure;
#endif
- if (rt_is_input_route(rt)) {
- if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst))
- goto nla_put_failure;
- } else if (rt->rt_src != rt->rt_key_src) {
+ if (!rt_is_input_route(rt) &&
+ rt->rt_src != rt->rt_key_src) {
if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src))
goto nla_put_failure;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b4ae1c1..64568fa 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -698,8 +698,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
net = dev_net(skb_dst(skb)->dev);
arg.tos = ip_hdr(skb)->tos;
- ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
- &arg, arg.iov[0].iov_len);
+ ip_send_unicast_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
@@ -781,8 +781,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
if (oif)
arg.bound_dev_if = oif;
arg.tos = tos;
- ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
- &arg, arg.iov[0].iov_len);
+ ip_send_unicast_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 8855d82..9815ea0 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,7 +100,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_src = rt->rt_src;
xdst->u.rt.rt_dst = rt->rt_dst;
xdst->u.rt.rt_gateway = rt->rt_gateway;
- xdst->u.rt.rt_spec_dst = rt->rt_spec_dst;
return 0;
}
OpenPOWER on IntegriCloud