ipv4: processing ancillary IP_TOS or IP_TTL
If IP_TOS or IP_TTL are specified as ancillary data, then sendmsg() sends out
packets with the specified TTL or TOS overriding the socket values specified
with the traditional setsockopt().
The struct inet_cork stores the values of TOS, TTL and priority that are
passed through the struct ipcm_cookie. If there are user-specified TOS
(tos != -1) or TTL (ttl != 0) in the struct ipcm_cookie, these values are
used to override the per-socket values. In case of TOS also the priority
is changed accordingly.
Two helper functions get_rttos and get_rtconn_flags are defined to take
into account the presence of a user specified TOS value when computing
RT_TOS and RT_CONN_FLAGS.
Signed-off-by: Francesco Fusco <ffusco@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 636d203..f314177 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -103,6 +103,9 @@
int length; /* Total length of all frames */
struct dst_entry *dst;
u8 tx_flags;
+ __u8 ttl;
+ __s16 tos;
+ char priority;
};
struct inet_cork_full {
diff --git a/include/net/ip.h b/include/net/ip.h
index 0135f38..77b4f9b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -28,6 +28,7 @@
#include <linux/skbuff.h>
#include <net/inet_sock.h>
+#include <net/route.h>
#include <net/snmp.h>
#include <net/flow.h>
@@ -140,6 +141,16 @@
return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
}
+static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
+{
+ return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
+}
+
+static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
+{
+ return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk);
+}
+
/* datagram.c */
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
diff --git a/include/net/route.h b/include/net/route.h
index 6f572ca6..0ad8e01 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -39,6 +39,7 @@
#define RTO_ONLINK 0x01
#define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
+#define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
struct fib_nh;
struct fib_info;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5f7d11a..5c0e8bc 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,6 +353,9 @@
saddr = fib_compute_spec_dst(skb);
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
+
if (icmp_param->replyopts.opt.opt.optlen) {
ipc.opt = &icmp_param->replyopts.opt;
if (ipc.opt->opt.srr)
@@ -608,6 +611,8 @@
ipc.addr = iph->saddr;
ipc.opt = &icmp_param->replyopts.opt;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
type, code, icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a04d872..7d8357b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1060,6 +1060,9 @@
rt->dst.dev->mtu : dst_mtu(&rt->dst);
cork->dst = &rt->dst;
cork->length = 0;
+ cork->ttl = ipc->ttl;
+ cork->tos = ipc->tos;
+ cork->priority = ipc->priority;
cork->tx_flags = ipc->tx_flags;
return 0;
@@ -1311,7 +1314,9 @@
if (cork->flags & IPCORK_OPT)
opt = cork->opt;
- if (rt->rt_type == RTN_MULTICAST)
+ if (cork->ttl != 0)
+ ttl = cork->ttl;
+ else if (rt->rt_type == RTN_MULTICAST)
ttl = inet->mc_ttl;
else
ttl = ip_select_ttl(inet, &rt->dst);
@@ -1319,7 +1324,7 @@
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
- iph->tos = inet->tos;
+ iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
iph->frag_off = df;
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
@@ -1331,7 +1336,7 @@
ip_options_build(skb, opt, cork->addr, rt, 0);
}
- skb->priority = sk->sk_priority;
+ skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
skb->mark = sk->sk_mark;
/*
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1481,6 +1486,8 @@
ipc.addr = daddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
if (replyopts.opt.opt.optlen) {
ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index d7d9882..706d108e 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -713,6 +713,8 @@
ipc.opt = NULL;
ipc.oif = sk->sk_bound_dev_if;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
sock_tx_timestamp(sk, &ipc.tx_flags);
@@ -744,7 +746,7 @@
return -EINVAL;
faddr = ipc.opt->opt.faddr;
}
- tos = RT_TOS(inet->tos);
+ tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bfec521..a3fe534 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -517,6 +517,8 @@
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
@@ -556,7 +558,7 @@
daddr = ipc.opt->opt.faddr;
}
}
- tos = RT_CONN_FLAGS(sk);
+ tos = get_rtconn_flags(&ipc, sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 74d2c95..22462d94 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -855,6 +855,8 @@
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
@@ -938,7 +940,7 @@
faddr = ipc.opt->opt.faddr;
connected = 0;
}
- tos = RT_TOS(inet->tos);
+ tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {