[PATCH v4 9/9] tcp, udp: Bind outbound listening sockets by interface instead of address

[David Gibson <david@gibson.dropbear.id.au>]

Currently, outbound forwards (-T, -U) are handled by sockets bound to the
loopback address.  Typically we create two sockets, one for 127.0.0.1 and
one for ::1.

This has some disadvantages:
 * The guest can't connect via 127.0.0.0/8 addresses other than 127.0.0.1
 * We can't use dual-stack sockets, we have to have separate sockets for
   IPv4 and IPv6.

The restriction exists for a reason though.  If the guest has any
interfaces other than pasta (e.g. a VPN tunnel) external hosts could reach
the host via the forwards.  Especially combined with -T auto / -U auto this
would make it very easy to make a mistake with nasty security implications.

We can achieve this a different way, however.  Don't bind to a specific
address, but _do_ use SO_BINDTODEVICE to restrict the sockets to the "lo"
interface.

Note that although traffic to a local but non-loopback address is passed
over the 'lo' interface (as seen by netfilter and dumpcap), it doesn't
count as attached to that interface for the purposes of SO_BINDTODEVICE
(information from the routing table overrides the "physical" interface).
So, this change doesn't help for bug 100.

It's also not a complete fix for bug 113, it does however:
 * Get us a step closer to fixing bug 113
 * Slightly simplify the code
 * Make things a bit easier to allow more flexible binding on the guest in
   in future

Link: https://bugs.passt.top/show_bug.cgi?id=100
Link: https://bugs.passt.top/show_bug.cgi?id=113

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 pif.c |  6 ------
 tcp.c | 19 ++-----------------
 udp.c | 10 +++-------
 3 files changed, 5 insertions(+), 30 deletions(-)

diff --git a/pif.c b/pif.c
index 85904f35..db447b4f 100644
--- a/pif.c
+++ b/pif.c
@@ -81,12 +81,6 @@ int pif_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif,
 
 	ASSERT(pif_is_socket(pif));
 
-	if (pif == PIF_SPLICE) {
-		/* Sanity checks */
-		ASSERT(!ifname);
-		ASSERT(addr && inany_is_loopback(addr));
-	}
-
 	if (!addr) {
 		ref.fd = sock_l4_dualstack(c, type, port, ifname);
 	} else {
diff --git a/tcp.c b/tcp.c
index 2abb8be4..bd25952f 100644
--- a/tcp.c
+++ b/tcp.c
@@ -2618,21 +2618,6 @@ int tcp_sock_init(const struct ctx *c, uint8_t pif,
 	return 0;
 }
 
-/**
- * tcp_ns_sock_init() - Init socket to listen for spliced outbound connections
- * @c:		Execution context
- * @port:	Port, host order
- */
-static void tcp_ns_sock_init(const struct ctx *c, in_port_t port)
-{
-	ASSERT(!c->no_tcp);
-
-	if (c->ifi4)
-		tcp_sock_init_one(c, PIF_SPLICE, &inany_loopback4, NULL, port);
-	if (c->ifi6)
-		tcp_sock_init_one(c, PIF_SPLICE, &inany_loopback6, NULL, port);
-}
-
 /**
  * tcp_ns_socks_init() - Bind sockets in namespace for outbound connections
  * @arg:	Execution context
@@ -2651,7 +2636,7 @@ static int tcp_ns_socks_init(void *arg)
 		if (!bitmap_isset(c->tcp.fwd_out.map, port))
 			continue;
 
-		tcp_ns_sock_init(c, port);
+		tcp_sock_init(c, PIF_SPLICE, NULL, "lo", port);
 	}
 
 	return 0;
@@ -2826,7 +2811,7 @@ static void tcp_port_rebind(struct ctx *c, bool outbound)
 		if ((c->ifi4 && socks[port][V4] == -1) ||
 		    (c->ifi6 && socks[port][V6] == -1)) {
 			if (outbound)
-				tcp_ns_sock_init(c, port);
+				tcp_sock_init(c, PIF_SPLICE, NULL, "lo", port);
 			else
 				tcp_sock_init(c, PIF_HOST, NULL, NULL, port);
 		}
diff --git a/udp.c b/udp.c
index 3d097fbb..f3d445cf 100644
--- a/udp.c
+++ b/udp.c
@@ -1213,14 +1213,10 @@ static void udp_port_rebind(struct ctx *c, bool outbound)
 
 		if ((c->ifi4 && socks[V4][port] == -1) ||
 		    (c->ifi6 && socks[V6][port] == -1)) {
-			if (outbound) {
-				udp_sock_init(c, PIF_SPLICE,
-					      &inany_loopback4, NULL, port);
-				udp_sock_init(c, PIF_SPLICE,
-					      &inany_loopback6, NULL, port);
-			} else {
+			if (outbound)
+				udp_sock_init(c, PIF_SPLICE, NULL, "lo", port);
+			else
 				udp_sock_init(c, PIF_HOST, NULL, NULL, port);
-			}
 		}
 	}
 }
-- 
2.51.1