From: David Gibson <david@gibson.dropbear.id.au>
To: passt-dev@passt.top, Stefano Brivio <sbrivio@redhat.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH v2 19/32] inany: Helper functions for handling addresses which could be IPv4 or IPv6
Date: Thu, 17 Nov 2022 16:58:55 +1100 [thread overview]
Message-ID: <20221117055908.2782981-20-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20221117055908.2782981-1-david@gibson.dropbear.id.au>
struct tcp_conn stores an address which could be IPv6 or IPv4 using a
union. We can do this without an additional tag by encoding IPv4 addresses
as IPv4-mapped IPv6 addresses.
This approach is useful wider than the specific place in tcp_conn, so
expose a new 'union inany_addr' like this from a new inany.h. Along with
that create a number of helper functions to make working with these "inany"
addresses easier.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
Makefile | 6 ++--
inany.h | 68 ++++++++++++++++++++++++++++++++++++++++
tcp.c | 88 +++++++++++++++++++++++++---------------------------
tcp_conn.h | 15 ++-------
tcp_splice.c | 1 +
5 files changed, 117 insertions(+), 61 deletions(-)
create mode 100644 inany.h
diff --git a/Makefile b/Makefile
index a9b4f79..ce159e5 100644
--- a/Makefile
+++ b/Makefile
@@ -46,9 +46,9 @@ SRCS = $(PASST_SRCS) $(QRAP_SRCS)
MANPAGES = passt.1 pasta.1 qrap.1
PASST_HEADERS = arch.h arp.h checksum.h conf.h dhcp.h dhcpv6.h icmp.h \
- isolation.h lineread.h log.h ndp.h netlink.h packet.h passt.h pasta.h \
- pcap.h port_fwd.h siphash.h tap.h tcp.h tcp_conn.h tcp_splice.h udp.h \
- util.h
+ inany.h isolation.h lineread.h log.h ndp.h netlink.h packet.h passt.h \
+ pasta.h pcap.h port_fwd.h siphash.h tap.h tcp.h tcp_conn.h \
+ tcp_splice.h udp.h util.h
HEADERS = $(PASST_HEADERS) seccomp.h
# On gcc 11 and 12, with -O2 and -flto, tcp_hash() and siphash_20b(), if
diff --git a/inany.h b/inany.h
new file mode 100644
index 0000000..03e3e3f
--- /dev/null
+++ b/inany.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: AGPL-3.0-or-later
+ * Copyright Red Hat
+ * Author: David Gibson <david@gibson.dropbear.id.au>
+ *
+ * inany.h - Types and helpers for handling addresses which could be
+ * IPv6 or IPv4 (encoded as IPv4-mapped IPv6 addresses)
+ */
+
+#include <assert.h>
+
+/** union inany_addr - Represents either an IPv4 or IPv6 address
+ * @a6: Address as an IPv6 address, may be IPv4-mapped
+ * @v4mapped.zero: All zero-bits for an IPv4 address
+ * @v4mapped.one: All one-bits for an IPv4 address
+ * @v4mapped.a4: If @a6 is an IPv4 mapped address, the IPv4 address
+ *
+ * @v4mapped shouldn't be accessed except via helpers.
+ */
+union inany_addr {
+ struct in6_addr a6;
+ struct {
+ uint8_t zero[10];
+ uint8_t one[2];
+ struct in_addr a4;
+ } v4mapped;
+};
+
+/** inany_v4 - Extract IPv4 address, if present, from IPv[46] address
+ * @addr: IPv4 or IPv6 address
+ *
+ * Return: IPv4 address if @addr is IPv4, NULL otherwise
+ */
+static inline const struct in_addr *inany_v4(const union inany_addr *addr)
+{
+ if (!IN6_IS_ADDR_V4MAPPED(&addr->a6))
+ return NULL;
+ return &addr->v4mapped.a4;
+}
+
+/** inany_equals - Compare two IPv[46] addresses
+ * @a, @b: IPv[46] addresses
+ *
+ * Return: true if @a and @b are the same address
+ */
+static inline bool inany_equals(const union inany_addr *a,
+ const union inany_addr *b)
+{
+ return IN6_ARE_ADDR_EQUAL(&a->a6, &b->a6);
+}
+
+/** inany_from_af - Set IPv[46] address from IPv4 or IPv6 address
+ * @aa: Pointer to store IPv[46] address
+ * @af: Address family of @addr
+ * @addr: struct in_addr (IPv4) or struct in6_addr (IPv6)
+ */
+static inline void inany_from_af(union inany_addr *aa, int af, const void *addr)
+{
+ if (af == AF_INET6) {
+ aa->a6 = *((struct in6_addr *)addr);
+ } else if (af == AF_INET) {
+ memset(&aa->v4mapped.zero, 0, sizeof(aa->v4mapped.zero));
+ memset(&aa->v4mapped.one, 0xff, sizeof(aa->v4mapped.one));
+ aa->v4mapped.a4 = *((struct in_addr *)addr);
+ } else {
+ /* Not valid to call with other address families */
+ assert(0);
+ }
+}
diff --git a/tcp.c b/tcp.c
index e9803aa..d1008ae 100644
--- a/tcp.c
+++ b/tcp.c
@@ -301,6 +301,7 @@
#include "conf.h"
#include "tcp_splice.h"
#include "log.h"
+#include "inany.h"
#include "tcp_conn.h"
@@ -404,7 +405,7 @@ struct tcp6_l2_head { /* For MSS6 macro: keep in sync with tcp6_l2_buf_t */
#define OPT_SACK 5
#define OPT_TS 8
-#define CONN_V4(conn) IN6_IS_ADDR_V4MAPPED(&conn->a.a6)
+#define CONN_V4(conn) (!!inany_v4(&(conn)->addr))
#define CONN_V6(conn) (!CONN_V4(conn))
#define CONN_IS_CLOSING(conn) \
((conn->events & ESTABLISHED) && \
@@ -438,7 +439,7 @@ static int tcp_sock_init_ext [NUM_PORTS][IP_VERSIONS];
static int tcp_sock_ns [NUM_PORTS][IP_VERSIONS];
/* Table of destinations with very low RTT (assumed to be local), LRU */
-static struct in6_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
+static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
/* Static buffers */
@@ -861,7 +862,7 @@ static int tcp_rtt_dst_low(const struct tcp_tap_conn *conn)
int i;
for (i = 0; i < LOW_RTT_TABLE_SIZE; i++)
- if (IN6_ARE_ADDR_EQUAL(&conn->a.a6, low_rtt_dst + i))
+ if (inany_equals(&conn->addr, low_rtt_dst + i))
return 1;
return 0;
@@ -883,7 +884,7 @@ static void tcp_rtt_dst_check(const struct tcp_tap_conn *conn,
return;
for (i = 0; i < LOW_RTT_TABLE_SIZE; i++) {
- if (IN6_ARE_ADDR_EQUAL(&conn->a.a6, low_rtt_dst + i))
+ if (inany_equals(&conn->addr, low_rtt_dst + i))
return;
if (hole == -1 && IN6_IS_ADDR_UNSPECIFIED(low_rtt_dst + i))
hole = i;
@@ -895,10 +896,10 @@ static void tcp_rtt_dst_check(const struct tcp_tap_conn *conn,
if (hole == -1)
return;
- memcpy(low_rtt_dst + hole++, &conn->a.a6, sizeof(conn->a.a6));
+ low_rtt_dst[hole++] = conn->addr;
if (hole == LOW_RTT_TABLE_SIZE)
hole = 0;
- memcpy(low_rtt_dst + hole, &in6addr_any, sizeof(conn->a.a6));
+ inany_from_af(low_rtt_dst + hole, AF_INET6, &in6addr_any);
#else
(void)conn;
(void)tinfo;
@@ -1187,13 +1188,14 @@ static int tcp_hash_match(const struct tcp_tap_conn *conn,
int af, const void *addr,
in_port_t tap_port, in_port_t sock_port)
{
- if (af == AF_INET && CONN_V4(conn) &&
- !memcmp(&conn->a.a4.a, addr, sizeof(conn->a.a4.a)) &&
+ const struct in_addr *a4 = inany_v4(&conn->addr);
+
+ if (af == AF_INET && a4 && !memcmp(a4, addr, sizeof(*a4)) &&
conn->tap_port == tap_port && conn->sock_port == sock_port)
return 1;
if (af == AF_INET6 &&
- IN6_ARE_ADDR_EQUAL(&conn->a.a6, addr) &&
+ IN6_ARE_ADDR_EQUAL(&conn->addr.a6, addr) &&
conn->tap_port == tap_port && conn->sock_port == sock_port)
return 1;
@@ -1253,11 +1255,13 @@ static unsigned int tcp_hash(const struct ctx *c, int af, const void *addr,
static unsigned int tcp_conn_hash(const struct ctx *c,
const struct tcp_tap_conn *conn)
{
- if (CONN_V6(conn))
- return tcp_hash(c, AF_INET6, &conn->a.a6,
+ const struct in_addr *a4 = inany_v4(&conn->addr);
+
+ if (a4)
+ return tcp_hash(c, AF_INET, a4,
conn->tap_port, conn->sock_port);
else
- return tcp_hash(c, AF_INET, &conn->a.a4.a,
+ return tcp_hash(c, AF_INET6, &conn->addr.a6,
conn->tap_port, conn->sock_port);
}
@@ -1582,6 +1586,7 @@ static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
void *p, size_t plen,
const uint16_t *check, uint32_t seq)
{
+ const struct in_addr *a4 = inany_v4(&conn->addr);
size_t ip_len, eth_len;
#define SET_TCP_HEADER_COMMON_V4_V6(b, conn, seq) \
@@ -1599,13 +1604,33 @@ do { \
} \
} while (0)
- if (CONN_V6(conn)) {
+ if (a4) {
+ struct tcp4_l2_buf_t *b = (struct tcp4_l2_buf_t *)p;
+
+ ip_len = plen + sizeof(struct iphdr) + sizeof(struct tcphdr);
+ b->iph.tot_len = htons(ip_len);
+ b->iph.saddr = a4->s_addr;
+ b->iph.daddr = c->ip4.addr_seen.s_addr;
+
+ if (check)
+ b->iph.check = *check;
+ else
+ tcp_update_check_ip4(b);
+
+ SET_TCP_HEADER_COMMON_V4_V6(b, conn, seq);
+
+ tcp_update_check_tcp4(b);
+
+ eth_len = ip_len + sizeof(struct ethhdr);
+ if (c->mode == MODE_PASST)
+ b->vnet_len = htonl(eth_len);
+ } else {
struct tcp6_l2_buf_t *b = (struct tcp6_l2_buf_t *)p;
ip_len = plen + sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
b->ip6h.payload_len = htons(plen + sizeof(struct tcphdr));
- b->ip6h.saddr = conn->a.a6;
+ b->ip6h.saddr = conn->addr.a6;
if (IN6_IS_ADDR_LINKLOCAL(&b->ip6h.saddr))
b->ip6h.daddr = c->ip6.addr_ll_seen;
else
@@ -1621,26 +1646,6 @@ do { \
b->ip6h.flow_lbl[1] = (conn->sock >> 8) & 0xff;
b->ip6h.flow_lbl[2] = (conn->sock >> 0) & 0xff;
- eth_len = ip_len + sizeof(struct ethhdr);
- if (c->mode == MODE_PASST)
- b->vnet_len = htonl(eth_len);
- } else {
- struct tcp4_l2_buf_t *b = (struct tcp4_l2_buf_t *)p;
-
- ip_len = plen + sizeof(struct iphdr) + sizeof(struct tcphdr);
- b->iph.tot_len = htons(ip_len);
- b->iph.saddr = conn->a.a4.a.s_addr;
- b->iph.daddr = c->ip4.addr_seen.s_addr;
-
- if (check)
- b->iph.check = *check;
- else
- tcp_update_check_ip4(b);
-
- SET_TCP_HEADER_COMMON_V4_V6(b, conn, seq);
-
- tcp_update_check_tcp4(b);
-
eth_len = ip_len + sizeof(struct ethhdr);
if (c->mode == MODE_PASST)
b->vnet_len = htonl(eth_len);
@@ -2144,18 +2149,14 @@ static void tcp_conn_from_tap(struct ctx *c, int af, const void *addr,
if (!(conn->wnd_from_tap = (htons(th->window) >> conn->ws_from_tap)))
conn->wnd_from_tap = 1;
+ inany_from_af(&conn->addr, af, addr);
+
if (af == AF_INET) {
sa = (struct sockaddr *)&addr4;
sl = sizeof(addr4);
-
- memset(&conn->a.a4.zero, 0, sizeof(conn->a.a4.zero));
- memset(&conn->a.a4.one, 0xff, sizeof(conn->a.a4.one));
- memcpy(&conn->a.a4.a, addr, sizeof(conn->a.a4.a));
} else {
sa = (struct sockaddr *)&addr6;
sl = sizeof(addr6);
-
- memcpy(&conn->a.a6, addr, sizeof(conn->a.a6));
}
conn->sock_port = ntohs(th->dest);
@@ -2808,7 +2809,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c, union epoll_ref ref,
memcpy(&sa6.sin6_addr, src, sizeof(*src));
}
- memcpy(&conn->a.a6, &sa6.sin6_addr, sizeof(conn->a.a6));
+ inany_from_af(&conn->addr, AF_INET6, &sa6.sin6_addr);
conn->sock_port = ntohs(sa6.sin6_port);
conn->tap_port = ref.r.p.tcp.tcp.index;
@@ -2824,15 +2825,12 @@ static void tcp_tap_conn_from_sock(struct ctx *c, union epoll_ref ref,
memcpy(&sa4, sa, sizeof(sa4));
- memset(&conn->a.a4.zero, 0, sizeof(conn->a.a4.zero));
- memset(&conn->a.a4.one, 0xff, sizeof(conn->a.a4.one));
-
if (IN4_IS_ADDR_LOOPBACK(&sa4.sin_addr) ||
IN4_IS_ADDR_UNSPECIFIED(&sa4.sin_addr) ||
IN4_ARE_ADDR_EQUAL(&sa4.sin_addr, &c->ip4.addr_seen))
sa4.sin_addr = c->ip4.gw;
- conn->a.a4.a = sa4.sin_addr;
+ inany_from_af(&conn->addr, AF_INET, &sa4.sin_addr);
conn->sock_port = ntohs(sa4.sin_port);
conn->tap_port = ref.r.p.tcp.tcp.index;
diff --git a/tcp_conn.h b/tcp_conn.h
index 4bffe9a..bf50e1c 100644
--- a/tcp_conn.h
+++ b/tcp_conn.h
@@ -35,10 +35,7 @@ extern const char *tcp_common_flag_str[];
* @ws_to_tap: Window scaling factor advertised to tap/guest
* @sndbuf: Sending buffer in kernel, rounded to 2 ^ SNDBUF_BITS
* @seq_dup_ack_approx: Last duplicate ACK number sent to tap
- * @a.a6: IPv6 remote address, can be IPv4-mapped
- * @a.a4.zero: Zero prefix for IPv4-mapped, see RFC 6890, Table 20
- * @a.a4.one: Ones prefix for IPv4-mapped
- * @a.a4.a: IPv4 address
+ * @addr: Remote address (IPv4 or IPv6)
* @tap_port: Guest-facing tap port
* @sock_port: Remote, socket-facing port
* @wnd_from_tap: Last window size from tap, unscaled (as received)
@@ -108,15 +105,7 @@ struct tcp_tap_conn {
uint8_t seq_dup_ack_approx;
- union {
- struct in6_addr a6;
- struct {
- uint8_t zero[10];
- uint8_t one[2];
- struct in_addr a;
- } a4;
- } a;
-
+ union inany_addr addr;
in_port_t tap_port;
in_port_t sock_port;
diff --git a/tcp_splice.c b/tcp_splice.c
index bfcf63d..2be9b77 100644
--- a/tcp_splice.c
+++ b/tcp_splice.c
@@ -52,6 +52,7 @@
#include "passt.h"
#include "log.h"
#include "tcp_splice.h"
+#include "inany.h"
#include "tcp_conn.h"
--
@@ -52,6 +52,7 @@
#include "passt.h"
#include "log.h"
#include "tcp_splice.h"
+#include "inany.h"
#include "tcp_conn.h"
--
2.38.1
next prev parent reply other threads:[~2022-11-17 5:59 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-17 5:58 [PATCH v2 00/32] Use dual stack sockets to listen for inbound TCP connections David Gibson
2022-11-17 5:58 ` [PATCH v2 01/32] clang-tidy: Suppress warning about assignments in if statements David Gibson
2022-11-17 5:58 ` [PATCH v2 02/32] style: Minor corrections to function comments David Gibson
2022-11-17 5:58 ` [PATCH v2 03/32] tcp_splice: #include tcp_splice.h in tcp_splice.c David Gibson
2022-11-17 5:58 ` [PATCH v2 04/32] tcp: Remove unused TCP_MAX_SOCKS constant David Gibson
2022-11-17 5:58 ` [PATCH v2 05/32] tcp: Better helpers for converting between connection pointer and index David Gibson
2022-11-17 5:58 ` [PATCH v2 06/32] tcp_splice: Helpers for converting from index to/from tcp_splice_conn David Gibson
2022-11-17 5:58 ` [PATCH v2 07/32] tcp: Move connection state structures into a shared header David Gibson
2022-11-17 5:58 ` [PATCH v2 08/32] tcp: Add connection union type David Gibson
2022-11-18 0:25 ` Stefano Brivio
2022-11-18 1:10 ` David Gibson
2022-11-19 8:39 ` Stefano Brivio
2022-11-17 5:58 ` [PATCH v2 09/32] tcp: Improved helpers to update connections after moving David Gibson
2022-11-17 5:58 ` [PATCH v2 10/32] tcp: Unify spliced and non-spliced connection tables David Gibson
2022-11-17 5:58 ` [PATCH v2 11/32] tcp: Unify tcp_defer_handler and tcp_splice_defer_handler() David Gibson
2022-11-17 5:58 ` [PATCH v2 12/32] tcp: Partially unify tcp_timer() and tcp_splice_timer() David Gibson
2022-11-17 5:58 ` [PATCH v2 13/32] tcp: Unify the IN_EPOLL flag David Gibson
2022-11-17 5:58 ` [PATCH v2 14/32] tcp: Separate helpers to create ns listening sockets David Gibson
2022-11-17 5:58 ` [PATCH v2 15/32] tcp: Unify part of spliced and non-spliced conn_from_sock path David Gibson
2022-11-17 5:58 ` [PATCH v2 16/32] tcp: Use the same sockets to listen for spliced and non-spliced connections David Gibson
2022-11-17 5:58 ` [PATCH v2 17/32] tcp: Remove splice from tcp_epoll_ref David Gibson
2022-11-17 5:58 ` [PATCH v2 18/32] tcp: Don't store hash bucket in connection structures David Gibson
2022-11-17 5:58 ` David Gibson [this message]
2022-11-17 5:58 ` [PATCH v2 20/32] tcp: Hash IPv4 and IPv4-mapped-IPv6 addresses the same David Gibson
2022-11-17 5:58 ` [PATCH v2 21/32] tcp: Take tcp_hash_insert() address from struct tcp_conn David Gibson
2022-11-17 5:58 ` [PATCH v2 22/32] tcp: Simplify tcp_hash_match() to take an inany_addr David Gibson
2022-11-17 5:58 ` [PATCH v2 23/32] tcp: Unify initial sequence number calculation for IPv4 and IPv6 David Gibson
2022-11-17 5:59 ` [PATCH v2 24/32] tcp: Have tcp_seq_init() take its parameters from struct tcp_conn David Gibson
2022-11-17 5:59 ` [PATCH v2 25/32] tcp: Fix small errors in tcp_seq_init() time handling David Gibson
2022-11-17 5:59 ` [PATCH v2 26/32] tcp: Remove v6 flag from tcp_epoll_ref David Gibson
2022-11-17 5:59 ` [PATCH v2 27/32] tcp: NAT IPv4-mapped IPv6 addresses like IPv4 addresses David Gibson
2022-11-17 5:59 ` [PATCH v2 28/32] tcp_splice: Allow splicing of connections from IPv4-mapped loopback David Gibson
2022-11-17 5:59 ` [PATCH v2 29/32] tcp: Consolidate tcp_sock_init[46] David Gibson
2022-11-17 5:59 ` [PATCH v2 30/32] util: Allow sock_l4() to open dual stack sockets David Gibson
2022-11-17 5:59 ` [PATCH v2 31/32] util: Always return -1 on error in sock_l4() David Gibson
2022-11-17 5:59 ` [PATCH v2 32/32] tcp: Use dual stack sockets for port forwarding when possible David Gibson
2022-11-25 9:22 ` [PATCH v2 00/32] Use dual stack sockets to listen for inbound TCP connections Stefano Brivio
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=20221117055908.2782981-20-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).