[PATCH] net: implement IP_RECVHDRS option to get full headers through recvmsg cmsg.

["Maciej Żenczykowski" <zenczykowski@gmail.com>]

From: Luigi Rizzo <lrizzo@google.com>

We have all sorts of different ways to fetch pre-UDP payload metadata:
  IP_RECVTOS
  IP_RECVTTL
  IP_RECVOPTS
  IP_RETOPTS

But nothing generic which simply allows you to receive the entire packet header.

This is in similar vein to TCP_SAVE_SYN but for UDP and other datagram sockets.

This is envisioned as a way to get GUE extension metadata for encapsulated
packets, but implemented in a way to be much more future proof.

(Implemented by Luigi, who asked me to send it upstream)

Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
---
 include/net/inet_sock.h |  1 +
 include/uapi/linux/in.h |  1 +
 net/ipv4/ip_sockglue.c  | 26 ++++++++++++++++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 0a671c32d6b9..4299750c3bea 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -237,6 +237,7 @@ struct inet_sock {
 #define IP_CMSG_ORIGDSTADDR	BIT(6)
 #define IP_CMSG_CHECKSUM	BIT(7)
 #define IP_CMSG_RECVFRAGSIZE	BIT(8)
+#define IP_CMSG_RECVHDRS	BIT(9)
 
 /**
  * sk_to_full_sk - Access to a full socket
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 48e8a225b985..6dae3e1023cc 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -119,6 +119,7 @@ struct in_addr {
 #define IP_CHECKSUM	23
 #define IP_BIND_ADDRESS_NO_PORT	24
 #define IP_RECVFRAGSIZE	25
+#define IP_RECVHDRS	26
 
 /* IP_MTU_DISCOVER values */
 #define IP_PMTUDISC_DONT		0	/* Never send DF frames */
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5ad2d8ed3a3f..35c5f70daea9 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -71,6 +71,14 @@ static void ip_cmsg_recv_tos(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_TOS, 1, &ip_hdr(skb)->tos);
 }
 
+/* Return all headers */
+static void ip_cmsg_recv_headers(struct msghdr *msg, struct sk_buff *skb)
+{
+	int len = skb->data - skb_mac_header(skb);
+
+	put_cmsg(msg, SOL_IP, IP_RECVHDRS, len, eth_hdr(skb));
+}
+
 static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb)
 {
 	if (IPCB(skb)->opt.optlen == 0)
@@ -205,6 +213,14 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			return;
 	}
 
+	if (flags & IP_CMSG_RECVHDRS) {
+		ip_cmsg_recv_headers(msg, skb);
+
+		flags &= ~IP_CMSG_RECVHDRS;
+		if (!flags)
+			return;
+	}
+
 	if (flags & IP_CMSG_RETOPTS) {
 		ip_cmsg_recv_retopts(sock_net(sk), msg, skb);
 
@@ -597,6 +613,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	case IP_PKTINFO:
 	case IP_RECVTTL:
 	case IP_RECVOPTS:
+	case IP_RECVHDRS:
 	case IP_RECVTOS:
 	case IP_RETOPTS:
 	case IP_TOS:
@@ -701,6 +718,12 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		else
 			inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
 		break;
+	case IP_RECVHDRS:
+		if (val)
+			inet->cmsg_flags |=  IP_CMSG_RECVHDRS;
+		else
+			inet->cmsg_flags &= ~IP_CMSG_RECVHDRS;
+		break;
 	case IP_RETOPTS:
 		if (val)
 			inet->cmsg_flags |= IP_CMSG_RETOPTS;
@@ -1362,6 +1385,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVOPTS:
 		val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
 		break;
+	case IP_RECVHDRS:
+		val = (inet->cmsg_flags & IP_CMSG_RECVHDRS) != 0;
+		break;
 	case IP_RETOPTS:
 		val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
 		break;
-- 
2.17.0.rc1.321.gba9d0f2565-goog