net-timestamp: allow reading recv cmsg on errqueue with origin tstamp

Allow reading of timestamps and cmsg at the same time on all relevant
socket families. One use is to correlate timestamps with egress
device, by asking for cmsg IP_PKTINFO.

on AF_INET sockets, call the relevant function (ip_cmsg_recv). To
avoid changing legacy expectations, only do so if the caller sets a
new timestamping flag SOF_TIMESTAMPING_OPT_CMSG.

on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already
returned for all origins. only change is to set ifindex, which is
not initialized for all error origins.

In both cases, only generate the pktinfo message if an ifindex is
known. This is not the case for ACK timestamps.

The difference between the protocol families is probably a historical
accident as a result of the different conditions for generating cmsg
in the relevant ip(v6)_recv_error function:

ipv4:        if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
ipv6:        if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {

At one time, this was the same test bar for the ICMP/ICMP6
distinction. This is no longer true.

Signed-off-by: Willem de Bruijn <willemb@google.com>

----

Changes
  v1 -> v2
    large rewrite
    - integrate with existing pktinfo cmsg generation code
    - on ipv4: only send with new flag, to maintain legacy behavior
    - on ipv6: send at most a single pktinfo cmsg
    - on ipv6: initialize fields if not yet initialized

The recv cmsg interfaces are also relevant to the discussion of
whether looping packet headers is problematic. For v6, cmsgs that
identify many headers are already returned. This patch expands
that to v4. If it sounds reasonable, I will follow with patches

1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY
   (http://patchwork.ozlabs.org/patch/366967/)
2. sysctl to conditionally drop all timestamps that have payload or
   cmsg from users without CAP_NET_RAW.
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/timestamping.txt

@@ -122,7 +122,7 @@ SOF_TIMESTAMPING_RAW_HARDWARE:
 
 1.3.3 Timestamp Options
 
-The interface supports one option
+The interface supports the options
 
 SOF_TIMESTAMPING_OPT_ID:
 
@@ -145,6 +145,16 @@ SOF_TIMESTAMPING_OPT_ID:
   stream sockets, it increments with every byte.
 
 
+SOF_TIMESTAMPING_OPT_CMSG:
+
+  Support recv() cmsg for all timestamped packets. Control messages
+  are already supported unconditionally on all packets with receive
+  timestamps and on IPv6 packets with transmit timestamp. This option
+  extends them to IPv4 packets with transmit timestamp. One use case
+  is to correlate packets with their egress device, by enabling socket
+  option IP_PKTINFO simultaneously.
+
+
 1.4 Bytestream Timestamps
 
 The SO_TIMESTAMPING interface supports timestamping of bytes in a

include/uapi/linux/net_tstamp.h

@@ -23,8 +23,9 @@ enum {
 	SOF_TIMESTAMPING_OPT_ID = (1<<7),
 	SOF_TIMESTAMPING_TX_SCHED = (1<<8),
 	SOF_TIMESTAMPING_TX_ACK = (1<<9),
+	SOF_TIMESTAMPING_OPT_CMSG = (1<<10),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_TX_ACK,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_CMSG,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };

net/ipv4/ip_sockglue.c

@@ -399,6 +399,22 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
+static bool ipv4_pktinfo_prepare_errqueue(const struct sock *sk,
+					  const struct sk_buff *skb,
+					  int ee_origin)
+{
+	struct in_pktinfo *info = PKTINFO_SKB_CB(skb);
+
+	if ((ee_origin != SO_EE_ORIGIN_TIMESTAMPING) ||
+	    (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
+	    (!skb->dev))
+		return false;
+
+	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
+	info->ipi_ifindex = skb->dev->ifindex;
+	return true;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -446,7 +462,9 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
 	sin->sin_family = AF_UNSPEC;
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
+
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	    ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin)) {
 		struct inet_sock *inet = inet_sk(sk);
 
 		sin->sin_family = AF_INET;
@@ -1051,7 +1069,7 @@ e_inval:
 }
 
 /**
- * ipv4_pktinfo_prepare - transfert some info from rtable to skb
+ * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
  *

net/ipv6/datagram.c

@@ -325,6 +325,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+static void ip6_datagram_prepare_pktinfo_errqueue(struct sk_buff *skb)
+{
+	int ifindex = skb->dev ? skb->dev->ifindex : -1;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		IP6CB(skb)->iif = ifindex;
+	else
+		PKTINFO_SKB_CB(skb)->ipi_ifindex = ifindex;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -388,8 +398,12 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
 		sin->sin6_port = 0;
-		if (np->rxopt.all)
+		if (np->rxopt.all) {
+			if (serr->ee.ee_origin != SO_EE_ORIGIN_ICMP &&
+			    serr->ee.ee_origin != SO_EE_ORIGIN_ICMP6)
+				ip6_datagram_prepare_pktinfo_errqueue(skb);
 			ip6_datagram_recv_common_ctl(sk, msg, skb);
+		}
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
@@ -491,7 +505,10 @@ void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
 					       &src_info.ipi6_addr);
 		}
-		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
+
+		if (src_info.ipi6_ifindex >= 0)
+			put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO,
+				 sizeof(src_info), &src_info);
 	}
 }