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>

5 files changed, 24 insertions, 6 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5f7d11a45871..5c0e8bc6e5ba 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,6 +353,9 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
         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 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
         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 a04d872c54f9..7d8357bb2ba6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1060,6 +1060,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
                          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 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
         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 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
         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 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
                 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 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
         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 d7d9882d4cae..706d108e128c 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -713,6 +713,8 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         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 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                         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 bfec521c717f..a3fe534c968e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -517,6 +517,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         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 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                         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 74d2c95db57f..22462d947750 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -855,6 +855,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
         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 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                 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)) {