public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: David Gibson <david@gibson.dropbear.id.au>
To: Stefano Brivio <sbrivio@redhat.com>, passt-dev@passt.top
Cc: David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH 02/16] tcp, udp: Don't precompute port remappings in epoll references
Date: Mon, 29 Jan 2024 15:35:43 +1100	[thread overview]
Message-ID: <20240129043557.823451-3-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240129043557.823451-1-david@gibson.dropbear.id.au>

The epoll references for both TCP listening sockets and UDP sockets
includes a port number.  This gives the destination port that traffic to
that socket will be sent to on the other side.  That will usually be the
same as the socket's bound port, but might not if the -t, -u, -T or -U
options are given with different original and forwarded port numbers.

As we move towards a more flexible forwarding model for passt, it's going
to become possible for that destination port to vary depending on more
things (for example the source or destination address).  So, it will no
longer make sense to have a fixed value for a listening socket.

Change to simpler semantics where this field in the reference gives the
bound port of the socket.  We apply the translations to the correct
destination port later on, when we're actually forwarding.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 tcp.c        |  8 ++++----
 tcp.h        |  2 +-
 tcp_splice.c |  4 ++++
 udp.c        | 14 ++++++++------
 4 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/tcp.c b/tcp.c
index fdf56713..cd833728 100644
--- a/tcp.c
+++ b/tcp.c
@@ -2676,7 +2676,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c,
 	conn_event(c, conn, SOCK_ACCEPTED);
 
 	inany_from_sockaddr(&conn->faddr, &conn->fport, sa);
-	conn->eport = ref.port;
+	conn->eport = ref.port + c->tcp.fwd_in.delta[ref.port];
 
 	tcp_snat_inbound(c, &conn->faddr);
 
@@ -2861,7 +2861,7 @@ static int tcp_sock_init_af(const struct ctx *c, sa_family_t af, in_port_t port,
 			    const void *addr, const char *ifname)
 {
 	union tcp_listen_epoll_ref tref = {
-		.port = port + c->tcp.fwd_in.delta[port],
+		.port = port,
 		.pif = PIF_HOST,
 	};
 	int s;
@@ -2923,7 +2923,7 @@ int tcp_sock_init(const struct ctx *c, sa_family_t af, const void *addr,
 static void tcp_ns_sock_init4(const struct ctx *c, in_port_t port)
 {
 	union tcp_listen_epoll_ref tref = {
-		.port = port + c->tcp.fwd_out.delta[port],
+		.port = port,
 		.pif = PIF_SPLICE,
 	};
 	struct in_addr loopback = IN4ADDR_LOOPBACK_INIT;
@@ -2949,7 +2949,7 @@ static void tcp_ns_sock_init4(const struct ctx *c, in_port_t port)
 static void tcp_ns_sock_init6(const struct ctx *c, in_port_t port)
 {
 	union tcp_listen_epoll_ref tref = {
-		.port = port + c->tcp.fwd_out.delta[port],
+		.port = port,
 		.pif = PIF_SPLICE,
 	};
 	int s;
diff --git a/tcp.h b/tcp.h
index 875006ed..5e6756d4 100644
--- a/tcp.h
+++ b/tcp.h
@@ -37,7 +37,7 @@ union tcp_epoll_ref {
 
 /**
  * union tcp_listen_epoll_ref - epoll reference portion for TCP listening
- * @port:	Port number we're forwarding *to* (listening port plus delta)
+ * @port:	Bound port number of the socket
  * @pif:	pif in which the socket is listening
  * @u32:	Opaque u32 value of reference
  */
diff --git a/tcp_splice.c b/tcp_splice.c
index cc9745e8..b8d64eba 100644
--- a/tcp_splice.c
+++ b/tcp_splice.c
@@ -401,6 +401,8 @@ static int tcp_splice_new(const struct ctx *c, struct tcp_splice_conn *conn,
 		int *p = CONN_V6(conn) ? init_sock_pool6 : init_sock_pool4;
 		sa_family_t af = CONN_V6(conn) ? AF_INET6 : AF_INET;
 
+		port += c->tcp.fwd_out.delta[port];
+
 		s = tcp_conn_pool_sock(p);
 		if (s < 0)
 			s = tcp_conn_new_sock(c, af);
@@ -409,6 +411,8 @@ static int tcp_splice_new(const struct ctx *c, struct tcp_splice_conn *conn,
 
 		ASSERT(pif == PIF_HOST);
 
+		port += c->tcp.fwd_in.delta[port];
+
 		/* If pool is empty, refill it first */
 		if (p[TCP_SOCK_POOL_SIZE-1] < 0)
 			NS_CALL(tcp_sock_refill_ns, c);
diff --git a/udp.c b/udp.c
index c839e269..02cb7889 100644
--- a/udp.c
+++ b/udp.c
@@ -762,6 +762,11 @@ void udp_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events,
 	if (c->no_udp || !(events & EPOLLIN))
 		return;
 
+	if (ref.udp.pif == PIF_SPLICE)
+		dstport += c->udp.fwd_out.f.delta[dstport];
+	else if (ref.udp.pif == PIF_HOST)
+		dstport += c->udp.fwd_in.f.delta[dstport];
+
 	if (v6) {
 		mmh_recv = udp6_l2_mh_sock;
 		udp6_localname.sin6_port = htons(dstport);
@@ -989,16 +994,13 @@ int udp_sock_init(const struct ctx *c, int ns, sa_family_t af,
 		  const void *addr, const char *ifname, in_port_t port)
 {
 	union udp_epoll_ref uref = { .splice = (c->mode == MODE_PASTA),
-				     .orig = true };
+				     .orig = true, .port = port };
 	int s, r4 = FD_REF_MAX + 1, r6 = FD_REF_MAX + 1;
 
-	if (ns) {
+	if (ns)
 		uref.pif = PIF_SPLICE;
-		uref.port = (in_port_t)(port + c->udp.fwd_out.f.delta[port]);
-	} else {
+	else
 		uref.pif = PIF_HOST;
-		uref.port = (in_port_t)(port + c->udp.fwd_in.f.delta[port]);
-	}
 
 	if ((af == AF_INET || af == AF_UNSPEC) && c->ifi4) {
 		uref.v6 = 0;
-- 
@@ -762,6 +762,11 @@ void udp_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events,
 	if (c->no_udp || !(events & EPOLLIN))
 		return;
 
+	if (ref.udp.pif == PIF_SPLICE)
+		dstport += c->udp.fwd_out.f.delta[dstport];
+	else if (ref.udp.pif == PIF_HOST)
+		dstport += c->udp.fwd_in.f.delta[dstport];
+
 	if (v6) {
 		mmh_recv = udp6_l2_mh_sock;
 		udp6_localname.sin6_port = htons(dstport);
@@ -989,16 +994,13 @@ int udp_sock_init(const struct ctx *c, int ns, sa_family_t af,
 		  const void *addr, const char *ifname, in_port_t port)
 {
 	union udp_epoll_ref uref = { .splice = (c->mode == MODE_PASTA),
-				     .orig = true };
+				     .orig = true, .port = port };
 	int s, r4 = FD_REF_MAX + 1, r6 = FD_REF_MAX + 1;
 
-	if (ns) {
+	if (ns)
 		uref.pif = PIF_SPLICE;
-		uref.port = (in_port_t)(port + c->udp.fwd_out.f.delta[port]);
-	} else {
+	else
 		uref.pif = PIF_HOST;
-		uref.port = (in_port_t)(port + c->udp.fwd_in.f.delta[port]);
-	}
 
 	if ((af == AF_INET || af == AF_UNSPEC) && c->ifi4) {
 		uref.v6 = 0;
-- 
2.43.0


  parent reply	other threads:[~2024-01-29  4:36 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-29  4:35 [PATCH 00/16] More flow table preliminaries: address handling improvements David Gibson
2024-01-29  4:35 ` [PATCH 01/16] treewide: Use sa_family_t for address family variables David Gibson
2024-01-29  4:35 ` David Gibson [this message]
2024-01-29  4:35 ` [PATCH 03/16] flow: Add helper to determine a flow's protocol David Gibson
2024-01-29  4:35 ` [PATCH 04/16] tcp_splice: Simplify clean up logic David Gibson
2024-01-29  4:35 ` [PATCH 05/16] inany: Helper to test for IPv4 or IPv6 loopback address David Gibson
2024-01-29  4:35 ` [PATCH 06/16] tcp, tcp_splice: Helpers for getting sockets from the pools David Gibson
2024-01-29  4:35 ` [PATCH 07/16] tcp_splice: More specific variable names in new splice path David Gibson
2024-01-29  4:35 ` [PATCH 08/16] tcp_splice: Fix incorrect parameter comment for tcp_splice_connect() David Gibson
2024-01-29  4:35 ` [PATCH 09/16] tcp_splice: Merge tcp_splice_new() into its caller David Gibson
2024-01-29  4:35 ` [PATCH 10/16] tcp_splice: Improve error reporting on connect path David Gibson
2024-01-29  4:35 ` [PATCH 11/16] inany: Add inany_ntop() helper David Gibson
2024-01-29  4:35 ` [PATCH 12/16] tcp_splice: Improve logic deciding when to splice David Gibson
2024-01-29  4:35 ` [PATCH 13/16] util: Provide global constants for IPv4 loopback and unspecified address David Gibson
2024-01-29  4:35 ` [PATCH 14/16] inany: Introduce union sockaddr_inany David Gibson
2024-01-29  4:35 ` [PATCH 15/16] tcp, tcp_splice: Better construction of IPv4 or IPv6 sockaddrs David Gibson
2024-01-29  4:35 ` [PATCH 16/16] inany: Extend inany_from_af to easily set unspecified addresses David Gibson
2024-01-29  9:02 ` [PATCH 00/16] More flow table preliminaries: address handling improvements David Gibson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240129043557.823451-3-david@gibson.dropbear.id.au \
    --to=david@gibson.dropbear.id.au \
    --cc=passt-dev@passt.top \
    --cc=sbrivio@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).