[PATCH net-next 0/2] ipv4: per-datagram IP_TOS and IP_TTL via sendmsg()

[PATCH net-next 0/2] ipv4: per-datagram IP_TOS and IP_TTL via sendmsg()

[Francesco Fusco]

There is no way to set the IP_TOS field on a per-packet basis in IPv4, while
IPv6 has such a mechanism. Therefore one has to fall back to the setsockopt()
in case of IPv4. 

Using the existing per-socket option is not convenient particularly in the
situations where multiple threads have to use the same socket data requiring
per-thread TOS values. In fact this would involve calling setsockopt() before
sendmsg() every time.

An old patch was submitted to the netdev mailing list to add support for
setting TOS on a per-packet basis, but was never integrated into the kernel.
The old patch can be found here:
http://marc.info/?l=linux-netdev&m=118388241201593 

This patch contains the changes from the original patch, updated for the
current kernel.

Francesco Fusco (2):
  ipv4: IP_TOS and IP_TTL can be specified as ancillary data
  ipv4: processing ancillary IP_TOS or IP_TTL

 include/net/inet_sock.h |  3 +++
 include/net/ip.h        |  3 +++
 net/ipv4/icmp.c         | 11 ++++++-----
 net/ipv4/ip_output.c    | 17 ++++++++++++++---
 net/ipv4/ip_sockglue.c  | 20 +++++++++++++++++++-
 net/ipv4/raw.c          |  3 +++
 net/ipv4/udp.c          |  3 +++
 7 files changed, 51 insertions(+), 9 deletions(-)

-- 
1.8.3.1

[PATCH net-next 1/2] ipv4: IP_TOS and IP_TTL can be specified as ancillary data

[Francesco Fusco]

This patch enables the IP_TTL and IP_TOS values passed from userspace to
be stored in the ipcm_cookie struct.

Signed-off-by: Francesco Fusco <ffusco@redhat.com>
---
 include/net/ip.h       |  3 +++
 net/ipv4/ip_sockglue.c | 20 +++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index a68f838..bf63936 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -54,6 +54,9 @@ static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
 struct ipcm_cookie {
 	__be32			addr;
 	int			oif;
+	__s16			ttl;
+	__s16			tos;
+	__u32			priority;
 	struct ip_options_rcu	*opt;
 	__u8			tx_flags;
 };
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f11..56e3445 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(ip_cmsg_recv);
 
 int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
 {
-	int err;
+	int err, val;
 	struct cmsghdr *cmsg;
 
 	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
@@ -215,6 +215,24 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
 			ipc->addr = info->ipi_spec_dst.s_addr;
 			break;
 		}
+		case IP_TTL:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 1 || val > 255)
+				return -EINVAL;
+			ipc->ttl = val;
+			break;
+		case IP_TOS:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 0 || val > 255)
+				return -EINVAL;
+			ipc->tos = val;
+			ipc->priority = rt_tos2priority(ipc->tos);
+			break;
+
 		default:
 			return -EINVAL;
 		}
-- 
1.8.3.1

[PATCH net-next 2/2] ipv4: processing ancillary IP_TOS or IP_TTL

[Francesco Fusco]

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().

If there is a per-packet specified tos, the skb->priority is set accordingly.
The ipv4_is_multicast() function is used to fill in the right TTL value in case
of multicast destinations.

Signed-off-by: Francesco Fusco <ffusco@redhat.com>
---
 include/net/inet_sock.h |  3 +++
 net/ipv4/icmp.c         | 11 ++++++-----
 net/ipv4/ip_output.c    | 17 ++++++++++++++---
 net/ipv4/raw.c          |  3 +++
 net/ipv4/udp.c          |  3 +++
 5 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index b21a7f0..5e22c9e 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -101,6 +101,9 @@ struct inet_cork {
 	struct ip_options	*opt;
 	unsigned int		fragsize;
 	int			length; /* Total length of all frames */
+	__s16			ttl;
+	__s16			tos;
+	__u32			priority;
 	struct dst_entry	*dst;
 	u8			tx_flags;
 };
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5f7d11a..28bccce 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -348,9 +348,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 
 	icmp_param->data.icmph.checksum = 0;
 
-	inet->tos = ip_hdr(skb)->tos;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
+	ipc.tos = ip_hdr(skb)->tos;
+	ipc.ttl = ipv4_is_multicast(daddr) ? inet->mc_ttl : inet->uc_ttl;
+	ipc.priority = sk->sk_priority;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
 	if (icmp_param->replyopts.opt.opt.optlen) {
@@ -487,7 +489,6 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	__be32 saddr;
-	u8  tos;
 	struct net *net;
 	struct sock *sk;
 
@@ -586,7 +587,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		rcu_read_unlock();
 	}
 
-	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
+	ipc.tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
 					   IPTOS_PREC_INTERNETCONTROL) :
 					  iph->tos;
 
@@ -604,12 +605,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	icmp_param->data.icmph.checksum	 = 0;
 	icmp_param->skb	  = skb_in;
 	icmp_param->offset = skb_network_offset(skb_in);
-	inet_sk(sk)->tos = tos;
+	ipc.ttl = -1;
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param->replyopts.opt;
 	ipc.tx_flags = 0;
 
-	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
+	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, ipc.tos,
 			       type, code, icmp_param);
 	if (IS_ERR(rt))
 		goto out_unlock;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4bcabf3..bf46730 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1068,6 +1068,9 @@ 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;
@@ -1319,7 +1322,9 @@ 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 != -1)
+		ttl = cork->ttl;
+	else if (rt->rt_type == RTN_MULTICAST)
 		ttl = inet->mc_ttl;
 	else
 		ttl = ip_select_ttl(inet, &rt->dst);
@@ -1327,7 +1332,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph = (struct iphdr *)skb->data;
 	iph->version = 4;
 	iph->ihl = 5;
-	iph->tos = inet->tos;
+	iph->tos = (cork->tos != inet->tos) ? cork->tos : inet->tos;
 	iph->frag_off = df;
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
@@ -1339,7 +1344,8 @@ 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 != inet->tos) ? 
+		cork->priority : sk->sk_priority;
 	skb->mark = sk->sk_mark;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1511,6 +1517,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	inet = &get_cpu_var(unicast_sock);
 
 	inet->tos = arg->tos;
+
+	ipc.tos = ip_hdr(skb)->tos;
+	ipc.ttl = inet->uc_ttl;
+	ipc.priority = skb->priority;
+
 	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dd44e0a..68a9423 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -518,6 +518,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
 	ipc.oif = sk->sk_bound_dev_if;
+	ipc.ttl = ipv4_is_multicast(daddr) ? inet->mc_ttl : inet->uc_ttl;
+	ipc.tos = inet->tos;
+	ipc.priority = sk->sk_priority;
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9e88af0..2d72ce8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -904,6 +904,9 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	}
 	ipc.addr = inet->inet_saddr;
 
+	ipc.ttl = ipv4_is_multicast(daddr) ? inet->mc_ttl : inet->uc_ttl;
+	ipc.tos = inet->tos;
+	ipc.priority = sk->sk_priority;
 	ipc.oif = sk->sk_bound_dev_if;
 
 	sock_tx_timestamp(sk, &ipc.tx_flags);
-- 
1.8.3.1

Re: [PATCH net-next 1/2] ipv4: IP_TOS and IP_TTL can be specified as ancillary data

[David Miller]

From: Francesco Fusco <ffusco@redhat.com>
Date: Wed, 14 Aug 2013 17:48:38 +0200

> +	__s16			ttl;
> +	__s16			tos;

You're range validating these values to make sure they are always
between 1 and 255, inclusive.

Why use a 16-bit value, and in particular a signed one?  That makes
absolutely no sense at all.

These fit perfectly in a "u8" so use that instead.

Re: [PATCH net-next 2/2] ipv4: processing ancillary IP_TOS or IP_TTL

[Eric Dumazet]

On Wed, 2013-08-14 at 17:48 +0200, Francesco Fusco wrote:
> 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().
> 
> If there is a per-packet specified tos, the skb->priority is set accordingly.
> The ipv4_is_multicast() function is used to fill in the right TTL value in case
> of multicast destinations.
> 
> Signed-off-by: Francesco Fusco <ffusco@redhat.com>
> ---

> @@ -1327,7 +1332,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
>  	iph = (struct iphdr *)skb->data;
>  	iph->version = 4;
>  	iph->ihl = 5;
> -	iph->tos = inet->tos;
> +	iph->tos = (cork->tos != inet->tos) ? cork->tos : inet->tos;

Strange construct, as the following has same meaning.

	iph->tos = cork->tos;

Re: [PATCH net-next 2/2] ipv4: processing ancillary IP_TOS or IP_TTL

[Eric Dumazet]

On Wed, 2013-08-14 at 17:48 +0200, Francesco Fusco wrote:

> @@ -1511,6 +1517,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
>  	inet = &get_cpu_var(unicast_sock);
>  
>  	inet->tos = arg->tos;
> +
> +	ipc.tos = ip_hdr(skb)->tos;

Why both inet->tos and ipc.tos must be set ?

This is very confusing, as if you were not 100% sure of your patch.


> +	ipc.ttl = inet->uc_ttl;

	ipc.ttl = -1;

> +	ipc.priority = skb->priority;
> +
>  	sk = &inet->sk;
>  	sk->sk_priority = skb->priority;

Why both sk->sk_priority and ipc.priority must be set ?

>  	sk->sk_protocol = ip_hdr(skb)->protocol;