* [PATCH v7 01/13] dhcpv6: Fix reply destination to match client's source address
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 02/13] passt, pasta: Introduce unified multi-address data structures Jon Maloy
` (11 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
tap_ip6_daddr() selects the reply destination based on our source
address type (link-local), so it always returns addr_ll_seen. But if
the client sent from a global address, we would reply to an address
different from what the client is expecting. Since RFC 8415 allows
clients to use global addresses for DHCPv6, we now correct this, and
always respond to the address the client was using.
We also remove a redundant addr_ll_seen assignment, since this is
already done by tap.c when processing IPv6 packets.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
dhcpv6.c | 14 ++++++--------
dhcpv6.h | 2 +-
tap.c | 15 ---------------
tap.h | 2 --
4 files changed, 7 insertions(+), 26 deletions(-)
diff --git a/dhcpv6.c b/dhcpv6.c
index 97c04e2..2db0944 100644
--- a/dhcpv6.c
+++ b/dhcpv6.c
@@ -370,12 +370,14 @@ notonlink:
/**
* dhcpv6_send_ia_notonlink() - Send NotOnLink status
* @c: Execution context
+ * @saddr: Source address of client message (reply destination)
* @ia_base: Non-appropriate IA_NA or IA_TA base
* @client_id_base: Client ID message option base
* @len: Client ID length
* @xid: Transaction ID for message exchange
*/
static void dhcpv6_send_ia_notonlink(struct ctx *c,
+ const struct in6_addr *saddr,
const struct iov_tail *ia_base,
const struct iov_tail *client_id_base,
int len, uint32_t xid)
@@ -405,8 +407,7 @@ static void dhcpv6_send_ia_notonlink(struct ctx *c,
resp_not_on_link.hdr.xid = xid;
- tap_udp6_send(c, src, 547, tap_ip6_daddr(c, src), 546,
- xid, &resp_not_on_link, n);
+ tap_udp6_send(c, src, 547, saddr, 546, xid, &resp_not_on_link, n);
}
/**
@@ -543,7 +544,7 @@ static size_t dhcpv6_client_fqdn_fill(const struct iov_tail *data,
* dhcpv6() - Check if this is a DHCPv6 message, reply as needed
* @c: Execution context
* @data: Single packet starting from UDP header
- * @saddr: Source IPv6 address of original message
+ * @saddr: Source IPv6 address of original message (for reply destination)
* @daddr: Destination IPv6 address of original message
*
* Return: 0 if it's not a DHCPv6 message, 1 if handled, -1 on failure
@@ -590,8 +591,6 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
if (mlen + sizeof(*uh) != ntohs(uh->len) || mlen < sizeof(*mh))
return -1;
- c->ip6.addr_ll_seen = *saddr;
-
src = &c->ip6.our_tap_ll;
mh = IOV_REMOVE_HEADER(data, mh_storage);
@@ -630,7 +629,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
if (dhcpv6_ia_notonlink(data, &c->ip6.addr)) {
- dhcpv6_send_ia_notonlink(c, data, &client_id_base,
+ dhcpv6_send_ia_notonlink(c, saddr, data, &client_id_base,
ntohs(client_id->l), mh->xid);
return 1;
@@ -680,8 +679,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
resp.hdr.xid = mh->xid;
- tap_udp6_send(c, src, 547, tap_ip6_daddr(c, src), 546,
- mh->xid, &resp, n);
+ tap_udp6_send(c, src, 547, saddr, 546, mh->xid, &resp, n);
c->ip6.addr_seen = c->ip6.addr;
return 1;
diff --git a/dhcpv6.h b/dhcpv6.h
index c706dfd..1015a1a 100644
--- a/dhcpv6.h
+++ b/dhcpv6.h
@@ -7,7 +7,7 @@
#define DHCPV6_H
int dhcpv6(struct ctx *c, struct iov_tail *data,
- struct in6_addr *saddr, struct in6_addr *daddr);
+ const struct in6_addr *saddr, const struct in6_addr *daddr);
void dhcpv6_init(const struct ctx *c);
#endif /* DHCPV6_H */
diff --git a/tap.c b/tap.c
index eaa6111..59c45a3 100644
--- a/tap.c
+++ b/tap.c
@@ -161,21 +161,6 @@ void tap_send_single(const struct ctx *c, const void *data, size_t l2len)
}
}
-/**
- * tap_ip6_daddr() - Normal IPv6 destination address for inbound packets
- * @c: Execution context
- * @src: Source address
- *
- * Return: pointer to IPv6 address
- */
-const struct in6_addr *tap_ip6_daddr(const struct ctx *c,
- const struct in6_addr *src)
-{
- if (IN6_IS_ADDR_LINKLOCAL(src))
- return &c->ip6.addr_ll_seen;
- return &c->ip6.addr_seen;
-}
-
/**
* tap_push_l2h() - Build an L2 header for an inbound packet
* @c: Execution context
diff --git a/tap.h b/tap.h
index 07ca096..b335933 100644
--- a/tap.h
+++ b/tap.h
@@ -96,8 +96,6 @@ void tap_udp4_send(const struct ctx *c, struct in_addr src, in_port_t sport,
const void *in, size_t dlen);
void tap_icmp4_send(const struct ctx *c, struct in_addr src, struct in_addr dst,
const void *in, const void *src_mac, size_t l4len);
-const struct in6_addr *tap_ip6_daddr(const struct ctx *c,
- const struct in6_addr *src);
void *tap_push_ip6h(struct ipv6hdr *ip6h,
const struct in6_addr *src, const struct in6_addr *dst,
size_t l4len, uint8_t proto, uint32_t flow);
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 02/13] passt, pasta: Introduce unified multi-address data structures
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
2026-04-13 0:53 ` [PATCH v7 01/13] dhcpv6: Fix reply destination to match client's source address Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 03/13] fwd: Unify guest accessibility checks with unified address array Jon Maloy
` (10 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
As preparation for supporting multiple addresses per interface,
we replace the single addr/prefix_len fields with an array. The
array consists of a new struct inany_addr_entry containing an
address and prefix length, both in inany_addr format.
Despite a lot of code refactoring, there are only two real functional
changes:
- The indicated IPv6 prefix length is now properly stored, instead
of being ignored and overridden with the hardcoded value 64, as
has been the case until now.
- Since even IPv4 addresses now are stored in IPv6 format, we
also store the corresponding prefix length in that format,
i.e. using the range [96,128] instead of [0,32].
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v2: -Using inany_addr instead of protocol specific addresses as
entry address field.
v3: -Merging into one array, directly in struct ctx
-Changed prefix_len and flags fields in struct inany_addr_entry
to uint8_t, since that makes the struct directly migratable
v4: -Updated according to changes in previous commits
-Updated according to feedback from David G.
-Squashed IP4_MASK macro commit into this one
v6: -Renamed and moved some definitions
-Introduced fwd_set_addr() and fwd_get_addr() already in this commit
-Eliminated first_v4/v6() functions, replaced with fwd_get_addr()
-Some other changes as suggested by David G.
-I kept the flag CONF_ADDR_LINKLOCAL, since it will be
needed later in an address selection function.
v7: -Introduced CONF_ADDR_GENERATED flag
-Other fixes based on feedback from David and Stefano.
-I changed signature of inany_prefix_len(), but I did not change
its semantics, since the premise of David's comment is wrong: the
caller does *not* explicitly know he is dealing with an IPv4 address.
In fact, there are examples later in this series where it may be an
IPv6 address, and the caller just trusts he gets the return value in
the appropriate format.
-Introduced the inverse of inany_prefix_len(), called inany_prefix_len6()
which always returns the prefix in IPv6 or mapped IPv4 format.
The name of the function isn't great, but any alternative I came up
with became too long to be practical.
---
arp.c | 12 ++++-
conf.c | 143 ++++++++++++++++++++++++++++++-------------------------
dhcp.c | 14 ++++--
dhcpv6.c | 15 ++++--
fwd.c | 109 ++++++++++++++++++++++++++++++++++--------
fwd.h | 4 ++
inany.h | 41 ++++++++++++++++
ip.h | 2 +
ndp.c | 16 +++++--
passt.h | 67 ++++++++++++++++++++++----
pasta.c | 25 ++++++----
tap.c | 7 ++-
12 files changed, 340 insertions(+), 115 deletions(-)
diff --git a/arp.c b/arp.c
index bb042e9..a7fd82f 100644
--- a/arp.c
+++ b/arp.c
@@ -41,6 +41,8 @@
static bool ignore_arp(const struct ctx *c,
const struct arphdr *ah, const struct arpmsg *am)
{
+ const struct guest_addr *a;
+
if (ah->ar_hrd != htons(ARPHRD_ETHER) ||
ah->ar_pro != htons(ETH_P_IP) ||
ah->ar_hln != ETH_ALEN ||
@@ -54,7 +56,8 @@ static bool ignore_arp(const struct ctx *c,
return true;
/* Don't resolve the guest's assigned address, either. */
- if (!memcmp(am->tip, &c->ip4.addr, sizeof(am->tip)))
+ a = fwd_get_addr(c, AF_INET, 0, 0);
+ if (a && !memcmp(am->tip, inany_v4(&a->addr), sizeof(am->tip)))
return true;
return false;
@@ -123,12 +126,17 @@ int arp(const struct ctx *c, struct iov_tail *data)
*/
void arp_send_init_req(const struct ctx *c)
{
+ const struct guest_addr *a;
struct {
struct ethhdr eh;
struct arphdr ah;
struct arpmsg am;
} __attribute__((__packed__)) req;
+ a = fwd_get_addr(c, AF_INET, 0, 0);
+ if (!a)
+ return;
+
/* Ethernet header */
req.eh.h_proto = htons(ETH_P_ARP);
memcpy(req.eh.h_dest, MAC_BROADCAST, sizeof(req.eh.h_dest));
@@ -145,7 +153,7 @@ void arp_send_init_req(const struct ctx *c)
memcpy(req.am.sha, c->our_tap_mac, sizeof(req.am.sha));
memcpy(req.am.sip, &c->ip4.our_tap_addr, sizeof(req.am.sip));
memcpy(req.am.tha, MAC_BROADCAST, sizeof(req.am.tha));
- memcpy(req.am.tip, &c->ip4.addr, sizeof(req.am.tip));
+ memcpy(req.am.tip, inany_v4(&a->addr), sizeof(req.am.tip));
debug("Sending initial ARP request for guest MAC address");
tap_send_single(c, &req, sizeof(req));
diff --git a/conf.c b/conf.c
index f13fef6..591f561 100644
--- a/conf.c
+++ b/conf.c
@@ -728,13 +728,15 @@ static int conf_ip4_prefix(const char *arg)
/**
* conf_ip4() - Verify or detect IPv4 support, get relevant addresses
+ * @c: Execution context
* @ifi: Host interface to attempt (0 to determine one)
- * @ip4: IPv4 context (will be written)
*
* Return: interface index for IPv4, or 0 on failure.
*/
-static unsigned int conf_ip4(unsigned int ifi, struct ip4_ctx *ip4)
+static unsigned int conf_ip4(struct ctx *c, unsigned int ifi)
{
+ struct ip4_ctx *ip4 = &c->ip4;
+
if (!ifi)
ifi = nl_get_ext_if(nl_sock, AF_INET);
@@ -753,60 +755,57 @@ static unsigned int conf_ip4(unsigned int ifi, struct ip4_ctx *ip4)
}
}
- if (IN4_IS_ADDR_UNSPECIFIED(&ip4->addr)) {
+ if (!fwd_get_addr(c, AF_INET, 0, 0)) {
+ struct in_addr addr;
+ int prefix_len;
int rc = nl_addr_get(nl_sock, ifi, AF_INET,
- &ip4->addr, &ip4->prefix_len, NULL);
+ &addr, &prefix_len, NULL);
if (rc < 0) {
debug("Couldn't discover IPv4 address: %s",
strerror_(-rc));
return 0;
}
- }
+ if (IN4_IS_ADDR_UNSPECIFIED(&addr))
+ return 0;
- if (!ip4->prefix_len) {
- in_addr_t addr = ntohl(ip4->addr.s_addr);
- if (IN_CLASSA(addr))
- ip4->prefix_len = (32 - IN_CLASSA_NSHIFT);
- else if (IN_CLASSB(addr))
- ip4->prefix_len = (32 - IN_CLASSB_NSHIFT);
- else if (IN_CLASSC(addr))
- ip4->prefix_len = (32 - IN_CLASSC_NSHIFT);
- else
- ip4->prefix_len = 32;
+ fwd_set_addr(c, &inany_from_v4(addr), CONF_ADDR_HOST,
+ prefix_len);
+ ip4->addr_seen = addr;
}
- ip4->addr_seen = ip4->addr;
-
ip4->our_tap_addr = ip4->guest_gw;
- if (IN4_IS_ADDR_UNSPECIFIED(&ip4->addr))
- return 0;
-
return ifi;
}
/**
* conf_ip4_local() - Configure IPv4 addresses and attributes for local mode
- * @ip4: IPv4 context (will be written)
+ * @c: Execution context (will be written)
*/
-static void conf_ip4_local(struct ip4_ctx *ip4)
+static void conf_ip4_local(struct ctx *c)
{
- ip4->addr_seen = ip4->addr = IP4_LL_GUEST_ADDR;
- ip4->our_tap_addr = ip4->guest_gw = IP4_LL_GUEST_GW;
- ip4->prefix_len = IP4_LL_PREFIX_LEN;
+ struct ip4_ctx *ip4 = &c->ip4;
+ ip4->addr_seen = IP4_LL_GUEST_ADDR;
+ ip4->our_tap_addr = ip4->guest_gw = IP4_LL_GUEST_GW;
ip4->no_copy_addrs = ip4->no_copy_routes = true;
+ fwd_set_addr(c, &inany_from_v4(IP4_LL_GUEST_ADDR),
+ CONF_ADDR_GENERATED | CONF_ADDR_LINKLOCAL,
+ IP4_LL_PREFIX_LEN);
}
/**
* conf_ip6() - Verify or detect IPv6 support, get relevant addresses
+ * @c: Execution context
* @ifi: Host interface to attempt (0 to determine one)
- * @ip6: IPv6 context (will be written)
*
* Return: interface index for IPv6, or 0 on failure.
*/
-static unsigned int conf_ip6(unsigned int ifi, struct ip6_ctx *ip6)
+static unsigned int conf_ip6(struct ctx *c, unsigned int ifi)
{
+ struct ip6_ctx *ip6 = &c->ip6;
+ const struct guest_addr *a;
+ union inany_addr addr;
int prefix_len = 0;
int rc;
@@ -827,21 +826,28 @@ static unsigned int conf_ip6(unsigned int ifi, struct ip6_ctx *ip6)
}
}
- rc = nl_addr_get(nl_sock, ifi, AF_INET6,
- IN6_IS_ADDR_UNSPECIFIED(&ip6->addr) ? &ip6->addr : NULL,
+ rc = nl_addr_get(nl_sock, ifi, AF_INET6, &addr.a6,
&prefix_len, &ip6->our_tap_ll);
if (rc < 0) {
debug("Couldn't discover IPv6 address: %s", strerror_(-rc));
return 0;
}
- ip6->addr_seen = ip6->addr;
+ a = fwd_get_addr(c, AF_INET6, 0, 0);
+ if (!a) {
+ if (IN6_IS_ADDR_UNSPECIFIED(&addr))
+ return 0;
+
+ fwd_set_addr(c, &addr, CONF_ADDR_HOST, prefix_len);
+ ip6->addr_seen = addr.a6;
+ } else {
+ ip6->addr_seen = a->addr.a6;
+ }
if (IN6_IS_ADDR_LINKLOCAL(&ip6->guest_gw))
ip6->our_tap_ll = ip6->guest_gw;
- if (IN6_IS_ADDR_UNSPECIFIED(&ip6->addr) ||
- IN6_IS_ADDR_UNSPECIFIED(&ip6->our_tap_ll))
+ if (IN6_IS_ADDR_UNSPECIFIED(&ip6->our_tap_ll))
return 0;
return ifi;
@@ -849,13 +855,13 @@ static unsigned int conf_ip6(unsigned int ifi, struct ip6_ctx *ip6)
/**
* conf_ip6_local() - Configure IPv6 addresses and attributes for local mode
- * @ip6: IPv6 context (will be written)
+ * @c: Execution context (will be written)
*/
-static void conf_ip6_local(struct ip6_ctx *ip6)
+static void conf_ip6_local(struct ctx *c)
{
- ip6->our_tap_ll = ip6->guest_gw = IP6_LL_GUEST_GW;
+ c->ip6.our_tap_ll = c->ip6.guest_gw = IP6_LL_GUEST_GW;
- ip6->no_copy_addrs = ip6->no_copy_routes = true;
+ c->ip6.no_copy_addrs = c->ip6.no_copy_routes = true;
}
/**
@@ -1137,6 +1143,7 @@ enum passt_modes conf_mode(int argc, char *argv[])
static void conf_print(const struct ctx *c)
{
char buf[INANY_ADDRSTRLEN];
+ const struct guest_addr *a;
int i;
if (c->ifi4 > 0 || c->ifi6 > 0) {
@@ -1181,16 +1188,18 @@ static void conf_print(const struct ctx *c)
inet_ntop(AF_INET, &c->ip4.map_host_loopback,
buf, sizeof(buf)));
- if (!c->no_dhcp) {
+ a = fwd_get_addr(c, AF_INET, 0, 0);
+ if (a && !c->no_dhcp) {
uint32_t mask;
- mask = htonl(0xffffffff << (32 - c->ip4.prefix_len));
+ mask = IN4_MASK(inany_prefix_len(&a->addr,
+ a->prefix_len));
info("DHCP:");
info(" assign: %s",
- inet_ntop(AF_INET, &c->ip4.addr, buf, sizeof(buf)));
+ inany_ntop(&a->addr, buf, sizeof(buf)));
info(" mask: %s",
- inet_ntop(AF_INET, &mask, buf, sizeof(buf)));
+ inet_ntop(AF_INET, &mask, buf, sizeof(buf)));
info(" router: %s",
inet_ntop(AF_INET, &c->ip4.guest_gw,
buf, sizeof(buf)));
@@ -1201,8 +1210,8 @@ static void conf_print(const struct ctx *c)
break;
if (!i)
info("DNS:");
- inet_ntop(AF_INET, &c->ip4.dns[i], buf, sizeof(buf));
- info(" %s", buf);
+ info(" %s", inet_ntop(AF_INET, &c->ip4.dns[i],
+ buf, sizeof(buf)));
}
for (i = 0; *c->dns_search[i].n; i++) {
@@ -1227,13 +1236,14 @@ static void conf_print(const struct ctx *c)
else
goto dns6;
- info(" assign: %s",
- inet_ntop(AF_INET6, &c->ip6.addr, buf, sizeof(buf)));
+ a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
+ if (a)
+ info(" assign: %s",
+ inany_ntop(&a->addr, buf, sizeof(buf)));
info(" router: %s",
inet_ntop(AF_INET6, &c->ip6.guest_gw, buf, sizeof(buf)));
info(" our link-local: %s",
- inet_ntop(AF_INET6, &c->ip6.our_tap_ll,
- buf, sizeof(buf)));
+ inet_ntop(AF_INET6, &c->ip6.our_tap_ll, buf, sizeof(buf)));
dns6:
for (i = 0; i < ARRAY_SIZE(c->ip6.dns); i++) {
@@ -1241,8 +1251,10 @@ dns6:
break;
if (!i)
info("DNS:");
- inet_ntop(AF_INET6, &c->ip6.dns[i], buf, sizeof(buf));
- info(" %s", buf);
+ info(" %s",
+ inet_ntop(AF_INET6, &c->ip6.dns[i],
+ buf, sizeof(buf)));
+
}
for (i = 0; *c->dns_search[i].n; i++) {
@@ -1886,19 +1898,16 @@ void conf(struct ctx *c, int argc, char **argv)
IN6_IS_ADDR_V4COMPAT(&addr.a6))
die("Invalid address: %s", optarg);
- if (inany_v4(&addr)) {
- c->ip4.addr = *inany_v4(&addr);
- c->ip4.prefix_len = prefix_len - 96;
- if (c->mode == MODE_PASTA)
- c->ip4.no_copy_addrs = true;
- } else {
- c->ip6.addr = addr.a6;
- if (c->mode == MODE_PASTA)
- c->ip6.no_copy_addrs = true;
- }
+ /* Legacy behaviour: replace existing address if any */
+ fwd_set_addr(c, &addr, CONF_ADDR_USER, prefix_len);
+ if (inany_v4(&addr))
+ c->ip4.no_copy_addrs = true;
+ else
+ c->ip6.no_copy_addrs = true;
break;
}
case 'n': {
+ struct guest_addr *a;
int plen;
if (addr_has_prefix_len)
@@ -1908,8 +1917,12 @@ void conf(struct ctx *c, int argc, char **argv)
if (plen < 0)
die("Invalid prefix length: %s", optarg);
- prefix_len_from_opt = plen + 96;
- c->ip4.prefix_len = plen;
+ prefix_len_from_opt = plen;
+
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET) {
+ a->prefix_len = inany_prefix_len(&a->addr, plen);
+ break;
+ }
break;
}
case 'M':
@@ -2103,9 +2116,9 @@ void conf(struct ctx *c, int argc, char **argv)
nl_sock_init(c, false);
if (!v6_only && !c->splice_only)
- c->ifi4 = conf_ip4(ifi4, &c->ip4);
+ c->ifi4 = conf_ip4(c, ifi4);
if (!v4_only && !c->splice_only)
- c->ifi6 = conf_ip6(ifi6, &c->ip6);
+ c->ifi6 = conf_ip6(c, ifi6);
if (c->ifi4 && c->mtu < IPV4_MIN_MTU) {
warn("MTU %"PRIu16" is too small for IPv4 (minimum %u)",
@@ -2128,7 +2141,7 @@ void conf(struct ctx *c, int argc, char **argv)
if (!c->ifi4 && !v6_only) {
if (!c->splice_only) {
info("IPv4: no external interface as template, use local mode");
- conf_ip4_local(&c->ip4);
+ conf_ip4_local(c);
}
c->ifi4 = -1;
}
@@ -2136,7 +2149,7 @@ void conf(struct ctx *c, int argc, char **argv)
if (!c->ifi6 && !v4_only) {
if (!c->splice_only) {
info("IPv6: no external interface as template, use local mode");
- conf_ip6_local(&c->ip6);
+ conf_ip6_local(c);
}
c->ifi6 = -1;
}
@@ -2201,7 +2214,7 @@ void conf(struct ctx *c, int argc, char **argv)
if (!c->ifi6) {
c->no_ndp = 1;
c->no_dhcpv6 = 1;
- } else if (IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr)) {
+ } else if (!fwd_get_addr(c, AF_INET6, 0, 0)) {
c->no_dhcpv6 = 1;
}
diff --git a/dhcp.c b/dhcp.c
index 1ff8cba..f0fa212 100644
--- a/dhcp.c
+++ b/dhcp.c
@@ -303,6 +303,7 @@ static void opt_set_dns_search(const struct ctx *c, size_t max_len)
int dhcp(const struct ctx *c, struct iov_tail *data)
{
char macstr[ETH_ADDRSTRLEN];
+ const struct guest_addr *a;
size_t mlen, dlen, opt_len;
struct in_addr mask, dst;
struct ethhdr eh_storage;
@@ -313,6 +314,7 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
const struct udphdr *uh;
struct msg m_storage;
struct msg const *m;
+ struct in_addr addr;
struct msg reply;
unsigned int i;
@@ -344,6 +346,10 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
m->op != BOOTREQUEST)
return -1;
+ a = fwd_get_addr(c, AF_INET, 0, 0);
+ assert(a);
+ addr = *inany_v4(&a->addr);
+
reply.op = BOOTREPLY;
reply.htype = m->htype;
reply.hlen = m->hlen;
@@ -352,7 +358,7 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
reply.secs = 0;
reply.flags = m->flags;
reply.ciaddr = m->ciaddr;
- reply.yiaddr = c->ip4.addr;
+ reply.yiaddr = addr;
reply.siaddr = 0;
reply.giaddr = m->giaddr;
memcpy(&reply.chaddr, m->chaddr, sizeof(reply.chaddr));
@@ -404,7 +410,7 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
info(" from %s", eth_ntop(m->chaddr, macstr, sizeof(macstr)));
- mask.s_addr = htonl(0xffffffff << (32 - c->ip4.prefix_len));
+ mask.s_addr = IN4_MASK(inany_prefix_len(&a->addr, a->prefix_len));
memcpy(opts[1].s, &mask, sizeof(mask));
memcpy(opts[3].s, &c->ip4.guest_gw, sizeof(c->ip4.guest_gw));
memcpy(opts[54].s, &c->ip4.our_tap_addr, sizeof(c->ip4.our_tap_addr));
@@ -412,7 +418,7 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
/* If the gateway is not on the assigned subnet, send an option 121
* (Classless Static Routing) adding a dummy route to it.
*/
- if ((c->ip4.addr.s_addr & mask.s_addr)
+ if ((addr.s_addr & mask.s_addr)
!= (c->ip4.guest_gw.s_addr & mask.s_addr)) {
/* a.b.c.d/32:0.0.0.0, 0:a.b.c.d */
opts[121].slen = 14;
@@ -471,7 +477,7 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
if (m->flags & FLAG_BROADCAST)
dst = in4addr_broadcast;
else
- dst = c->ip4.addr;
+ dst = addr;
tap_udp4_send(c, c->ip4.our_tap_addr, 67, dst, 68, &reply, dlen);
diff --git a/dhcpv6.c b/dhcpv6.c
index 2db0944..0a064a9 100644
--- a/dhcpv6.c
+++ b/dhcpv6.c
@@ -318,7 +318,7 @@ static bool dhcpv6_opt(struct iov_tail *data, uint16_t type)
* false otherwise and @data is unmodified
*/
static bool dhcpv6_ia_notonlink(struct iov_tail *data,
- struct in6_addr *la)
+ const struct in6_addr *la)
{
int ia_types[2] = { OPT_IA_NA, OPT_IA_TA };
struct opt_ia_addr opt_addr_storage;
@@ -567,6 +567,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
struct opt_hdr client_id_storage;
/* cppcheck-suppress [variableScope,unmatchedSuppression] */
struct opt_ia_na ia_storage;
+ const struct guest_addr *a;
const struct in6_addr *src;
struct msg_hdr mh_storage;
const struct msg_hdr *mh;
@@ -574,6 +575,8 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
const struct udphdr *uh;
size_t mlen, n;
+ a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
+
uh = IOV_REMOVE_HEADER(data, uh_storage);
if (!uh)
return -1;
@@ -627,7 +630,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
if (mh->type == TYPE_CONFIRM && server_id)
return -1;
- if (dhcpv6_ia_notonlink(data, &c->ip6.addr)) {
+ if (a && dhcpv6_ia_notonlink(data, &a->addr.a6)) {
dhcpv6_send_ia_notonlink(c, saddr, data, &client_id_base,
ntohs(client_id->l), mh->xid);
@@ -680,7 +683,8 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
resp.hdr.xid = mh->xid;
tap_udp6_send(c, src, 547, saddr, 546, mh->xid, &resp, n);
- c->ip6.addr_seen = c->ip6.addr;
+ if (a)
+ c->ip6.addr_seen = a->addr.a6;
return 1;
}
@@ -691,6 +695,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
*/
void dhcpv6_init(const struct ctx *c)
{
+ const struct guest_addr *a;
time_t y2k = 946684800; /* Epoch to 2000-01-01T00:00:00Z, no mktime() */
uint32_t duid_time;
@@ -704,5 +709,7 @@ void dhcpv6_init(const struct ctx *c)
memcpy(resp_not_on_link.server_id.duid_lladdr,
c->our_tap_mac, sizeof(c->our_tap_mac));
- resp.ia_addr.addr = c->ip6.addr;
+ a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
+ if (a)
+ resp.ia_addr.addr = a->addr.a6;
}
diff --git a/fwd.c b/fwd.c
index bedbf98..14ce0a7 100644
--- a/fwd.c
+++ b/fwd.c
@@ -249,6 +249,61 @@ void fwd_neigh_table_init(const struct ctx *c)
fwd_neigh_table_update(c, &mga, c->our_tap_mac, true);
}
+/**
+ * fwd_set_addr() - Add or update an address in the unified address array
+ * @c: Execution context
+ * @addr: Address to add (IPv4-mapped or IPv6)
+ * @flags: CONF_ADDR_* flags for this address
+ * @prefix_len: Prefix length in IPv6 or IPv4 format
+ *
+ * Find the first existing entry of the same address family and
+ * overwrite it, or create a new one if none exists
+ */
+void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
+ uint8_t flags, int prefix_len)
+{
+ struct guest_addr *a;
+
+ for_each_addr(a, c->addrs, c->addr_count, inany_af(addr)) {
+ goto found;
+ }
+
+ if (c->addr_count >= MAX_GUEST_ADDRS)
+ return;
+
+ a = &c->addrs[c->addr_count++];
+
+found:
+ a->addr = *addr;
+ a->prefix_len = inany_prefix_len6(addr, prefix_len);
+ a->flags = flags;
+}
+
+/**
+ * fwd_get_addr() - Get guest address entry matching criteria
+ * @c: Execution context
+ * @af: Address family (AF_INET, AF_INET6, or 0 for any)
+ * @incl: Flags that must be present (any-match)
+ * @excl: Flags that must not be present
+ *
+ * Return: first address entry matching criteria, or NULL
+ */
+const struct guest_addr *fwd_get_addr(const struct ctx *c, sa_family_t af,
+ uint8_t incl, uint8_t excl)
+{
+ const struct guest_addr *a;
+
+ for_each_addr(a, c->addrs, c->addr_count, af) {
+ if (incl && !(a->flags & incl))
+ continue;
+ if (a->flags & excl)
+ continue;
+ return a;
+ }
+
+ return NULL;
+}
+
/** fwd_probe_ephemeral() - Determine what ports this host considers ephemeral
*
* Work out what ports the host thinks are emphemeral and record it for later
@@ -941,8 +996,10 @@ static bool is_dns_flow(uint8_t proto, const struct flowside *ini)
* translation, false otherwise
*/
static bool fwd_guest_accessible4(const struct ctx *c,
- const struct in_addr *addr)
+ const struct in_addr *addr)
{
+ const struct guest_addr *a;
+
if (IN4_IS_ADDR_LOOPBACK(addr))
return false;
@@ -957,7 +1014,8 @@ static bool fwd_guest_accessible4(const struct ctx *c,
/* For IPv4, addr_seen is initialised to addr, so is always a valid
* address
*/
- if (IN4_ARE_ADDR_EQUAL(addr, &c->ip4.addr) ||
+ a = fwd_get_addr(c, AF_INET, 0, 0);
+ if ((a && IN4_ARE_ADDR_EQUAL(addr, inany_v4(&a->addr))) ||
IN4_ARE_ADDR_EQUAL(addr, &c->ip4.addr_seen))
return false;
@@ -975,10 +1033,13 @@ static bool fwd_guest_accessible4(const struct ctx *c,
static bool fwd_guest_accessible6(const struct ctx *c,
const struct in6_addr *addr)
{
+ const struct guest_addr *a;
+
if (IN6_IS_ADDR_LOOPBACK(addr))
return false;
- if (IN6_ARE_ADDR_EQUAL(addr, &c->ip6.addr))
+ a = fwd_get_addr(c, AF_INET6, 0, 0);
+ if (a && IN6_ARE_ADDR_EQUAL(addr, &a->addr.a6))
return false;
/* For IPv6, addr_seen starts unspecified, because we don't know what LL
@@ -1023,16 +1084,21 @@ static bool fwd_guest_accessible(const struct ctx *c,
static void nat_outbound(const struct ctx *c, const union inany_addr *addr,
union inany_addr *translated)
{
- if (inany_equals4(addr, &c->ip4.map_host_loopback))
+ const struct guest_addr *ga;
+
+ if (inany_equals4(addr, &c->ip4.map_host_loopback)) {
*translated = inany_loopback4;
- else if (inany_equals6(addr, &c->ip6.map_host_loopback))
+ } else if (inany_equals6(addr, &c->ip6.map_host_loopback)) {
*translated = inany_loopback6;
- else if (inany_equals4(addr, &c->ip4.map_guest_addr))
- *translated = inany_from_v4(c->ip4.addr);
- else if (inany_equals6(addr, &c->ip6.map_guest_addr))
- translated->a6 = c->ip6.addr;
- else
+ } else if (inany_equals4(addr, &c->ip4.map_guest_addr)) {
+ ga = fwd_get_addr(c, AF_INET, 0, 0);
+ *translated = ga ? ga->addr : inany_any4;
+ } else if (inany_equals6(addr, &c->ip6.map_guest_addr)) {
+ ga = fwd_get_addr(c, AF_INET6, 0, 0);
+ translated->a6 = ga ? ga->addr.a6 : in6addr_any;
+ } else {
*translated = *addr;
+ }
}
/**
@@ -1137,16 +1203,21 @@ bool nat_inbound(const struct ctx *c, const union inany_addr *addr,
} else if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_host_loopback) &&
inany_equals6(addr, &in6addr_loopback)) {
translated->a6 = c->ip6.map_host_loopback;
- } else if (!IN4_IS_ADDR_UNSPECIFIED(&c->ip4.map_guest_addr) &&
- inany_equals4(addr, &c->ip4.addr)) {
- *translated = inany_from_v4(c->ip4.map_guest_addr);
- } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_guest_addr) &&
- inany_equals6(addr, &c->ip6.addr)) {
- translated->a6 = c->ip6.map_guest_addr;
- } else if (fwd_guest_accessible(c, addr)) {
- *translated = *addr;
} else {
- return false;
+ const struct guest_addr *ga4 = fwd_get_addr(c, AF_INET, 0, 0);
+ const struct guest_addr *ga6 = fwd_get_addr(c, AF_INET6, 0, 0);
+
+ if (!IN4_IS_ADDR_UNSPECIFIED(&c->ip4.map_guest_addr) &&
+ ga4 && inany_equals(addr, &ga4->addr)) {
+ *translated = inany_from_v4(c->ip4.map_guest_addr);
+ } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_guest_addr) &&
+ ga6 && inany_equals(addr, &ga6->addr)) {
+ translated->a6 = c->ip6.map_guest_addr;
+ } else if (fwd_guest_accessible(c, addr)) {
+ *translated = *addr;
+ } else {
+ return false;
+ }
}
return true;
diff --git a/fwd.h b/fwd.h
index 958eee2..c5a1068 100644
--- a/fwd.h
+++ b/fwd.h
@@ -23,6 +23,8 @@ struct flowside;
void fwd_probe_ephemeral(void);
bool fwd_port_is_ephemeral(in_port_t port);
+const struct guest_addr *fwd_get_addr(const struct ctx *c, sa_family_t af,
+ uint8_t incl, uint8_t excl);
/**
* struct fwd_rule - Forwarding rule governing a range of ports
@@ -141,5 +143,7 @@ void fwd_neigh_table_free(const struct ctx *c,
void fwd_neigh_mac_get(const struct ctx *c, const union inany_addr *addr,
uint8_t *mac);
void fwd_neigh_table_init(const struct ctx *c);
+void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
+ uint8_t flags, int prefix_len);
#endif /* FWD_H */
diff --git a/inany.h b/inany.h
index 9891ed6..0450c45 100644
--- a/inany.h
+++ b/inany.h
@@ -102,6 +102,16 @@ static inline struct in_addr *inany_v4(const union inany_addr *addr)
return (struct in_addr *)&addr->v4mapped.a4;
}
+/** inany_af - Get address family of IPv[46] address
+ * @addr: IPv4 or IPv6 address
+ *
+ * Return: AF_INET for IPv4, AF_INET6 for IPv6
+ */
+static inline sa_family_t inany_af(const union inany_addr *addr)
+{
+ return inany_v4(addr) ? AF_INET : AF_INET6;
+}
+
/** inany_default_prefix_len() - Get default prefix length for address
* @addr: IPv4 or iPv6 address
*
@@ -115,6 +125,37 @@ static inline int inany_default_prefix_len(const union inany_addr *addr)
return v4 ? ip4_class_prefix_len(v4) + 96 : 64;
}
+
+/** inany_prefix_len() - Convert prefix length to native format
+ * @addr: IPv4 or IPv6 address
+ * @prefix_len: prefix length (any format, auto-detected)
+ *
+ * Return: prefix length in native format (0-32 for IPv4, 0-128 for IPv6)
+ */
+static inline int inany_prefix_len(const union inany_addr *addr,
+ int prefix_len)
+{
+ if (inany_v4(addr) && prefix_len >= 96)
+ return prefix_len - 96;
+
+ return prefix_len;
+}
+
+/** inany_prefix_len6() - Convert prefix length to generic format
+ * @addr: IPv4 or IPv6 address
+ * @prefix_len: prefix length (any format, auto-detected)
+ *
+ * Return: prefix length in generic format (96-128 for IPv4, 0-128 for IPv6)
+ */
+static inline int inany_prefix_len6(const union inany_addr *addr,
+ int prefix_len)
+{
+ if (inany_v4(addr) && prefix_len && prefix_len <= 32)
+ return prefix_len + 96;
+
+ return prefix_len;
+}
+
/** inany_equals - Compare two IPv[46] addresses
* @a, @b: IPv[46] addresses
*
diff --git a/ip.h b/ip.h
index d0de6c8..933d98c 100644
--- a/ip.h
+++ b/ip.h
@@ -19,6 +19,8 @@
(ntohl(((struct in_addr *)(a))->s_addr) >> IN_CLASSA_NSHIFT == IN_LOOPBACKNET)
#define IN4_IS_ADDR_MULTICAST(a) \
(IN_MULTICAST(ntohl(((struct in_addr *)(a))->s_addr)))
+#define IN4_MASK(prefix) \
+ ((prefix) <= 0 ? 0 : htonl(0xffffffff << (32 - (prefix))))
#define IN4_ARE_ADDR_EQUAL(a, b) \
(((struct in_addr *)(a))->s_addr == ((struct in_addr *)b)->s_addr)
#define IN4ADDR_LOOPBACK_INIT \
diff --git a/ndp.c b/ndp.c
index 1f2bcb0..3750fc5 100644
--- a/ndp.c
+++ b/ndp.c
@@ -257,7 +257,6 @@ static void ndp_ra(const struct ctx *c, const struct in6_addr *dst)
.valid_lifetime = ~0U,
.pref_lifetime = ~0U,
},
- .prefix = c->ip6.addr,
.source_ll = {
.header = {
.type = OPT_SRC_L2_ADDR,
@@ -265,8 +264,13 @@ static void ndp_ra(const struct ctx *c, const struct in6_addr *dst)
},
},
};
+ const struct guest_addr *a = fwd_get_addr(c, AF_INET6, 0, 0);
unsigned char *ptr = NULL;
+ ASSERT(a);
+
+ ra.prefix = a->addr.a6;
+
ptr = &ra.var[0];
if (c->mtu) {
@@ -460,6 +464,7 @@ first:
*/
void ndp_send_init_req(const struct ctx *c)
{
+ const struct guest_addr *a = fwd_get_addr(c, AF_INET6, 0, 0);
struct ndp_ns ns = {
.ih = {
.icmp6_type = NS,
@@ -468,8 +473,13 @@ void ndp_send_init_req(const struct ctx *c)
.icmp6_solicited = 0, /* Reserved */
.icmp6_override = 0, /* Reserved */
},
- .target_addr = c->ip6.addr
+ .target_addr = IN6ADDR_ANY_INIT
};
+
+ if (!a)
+ return;
+
+ ns.target_addr = a->addr.a6;
debug("Sending initial NDP NS request for guest MAC address");
- ndp_send(c, &c->ip6.addr, &ns, sizeof(ns));
+ ndp_send(c, &a->addr.a6, &ns, sizeof(ns));
}
diff --git a/passt.h b/passt.h
index b614bdf..f75656d 100644
--- a/passt.h
+++ b/passt.h
@@ -64,11 +64,28 @@ enum passt_modes {
MODE_VU,
};
+/* Maximum number of addresses in context address array */
+#define MAX_GUEST_ADDRS 32
+
+/**
+ * struct guest_addr - Unified IPv4/IPv6 address entry
+ * @addr: IPv4 (as mapped) or IPv6 address
+ * @prefix_len: Prefix length in IPv6/IPv4-mapped [0,128]/[96,128] format
+ * @flags: CONF_ADDR_* flags
+ */
+struct guest_addr {
+ union inany_addr addr;
+ uint8_t prefix_len;
+ uint8_t flags;
+#define CONF_ADDR_USER BIT(0) /* User set via -a */
+#define CONF_ADDR_HOST BIT(1) /* From host interface */
+#define CONF_ADDR_GENERATED BIT(2) /* Generated by PASST/PASTA */
+#define CONF_ADDR_LINKLOCAL BIT(3) /* Link-local address */
+};
+
/**
* struct ip4_ctx - IPv4 execution context
- * @addr: IPv4 address assigned to guest
* @addr_seen: Latest IPv4 address seen as source from tap
- * @prefixlen: IPv4 prefix length (netmask)
* @guest_gw: IPv4 gateway as seen by the guest
* @map_host_loopback: Outbound connections to this address are NATted to the
* host's 127.0.0.1
@@ -84,10 +101,7 @@ enum passt_modes {
* @no_copy_addrs: Don't copy all addresses when configuring namespace
*/
struct ip4_ctx {
- /* PIF_TAP addresses */
- struct in_addr addr;
struct in_addr addr_seen;
- int prefix_len;
struct in_addr guest_gw;
struct in_addr map_host_loopback;
struct in_addr map_guest_addr;
@@ -107,7 +121,6 @@ struct ip4_ctx {
/**
* struct ip6_ctx - IPv6 execution context
- * @addr: IPv6 address assigned to guest
* @addr_seen: Latest IPv6 global/site address seen as source from tap
* @addr_ll_seen: Latest IPv6 link-local address seen as source from tap
* @guest_gw: IPv6 gateway as seen by the guest
@@ -125,8 +138,6 @@ struct ip4_ctx {
* @no_copy_addrs: Don't copy all addresses when configuring namespace
*/
struct ip6_ctx {
- /* PIF_TAP addresses */
- struct in6_addr addr;
struct in6_addr addr_seen;
struct in6_addr addr_ll_seen;
struct in6_addr guest_gw;
@@ -181,6 +192,8 @@ struct ip6_ctx {
* @fqdn: Guest FQDN
* @ifi6: Template interface for IPv6, -1: none, 0: IPv6 disabled
* @ip6: IPv6 configuration
+ * @addrs: Unified address array for both IPv4 (mapped) and IPv6
+ * @addr_count: Number of active entries in @addrs array
* @pasta_ifn: Name of namespace interface for pasta
* @pasta_ifi: Index of namespace interface for pasta
* @pasta_conf_ns: Configure namespace after creating it
@@ -260,6 +273,9 @@ struct ctx {
int ifi6;
struct ip6_ctx ip6;
+ struct guest_addr addrs[MAX_GUEST_ADDRS];
+ int addr_count;
+
char pasta_ifn[IF_NAMESIZE];
unsigned int pasta_ifi;
int pasta_conf_ns;
@@ -301,6 +317,41 @@ struct ctx {
bool migrate_exit;
};
+/**
+ * next_addr_idx_() - Find next address index matching family filter
+ * @addrs: Array of guest addresses
+ * @count: Number of addresses in array
+ * @i: Starting index
+ * @af: Address family filter: AF_INET, AF_INET6, or 0 for all
+ *
+ * Return: next matching index, or count if none found
+ */
+static inline int next_addr_idx_(const struct guest_addr *addrs, int count,
+ int i, sa_family_t af)
+{
+ for (; i < count; i++) {
+ sa_family_t entry_af;
+
+ entry_af = inany_v4(&addrs[i].addr) ? AF_INET : AF_INET6;
+
+ if (af == AF_UNSPEC || af == entry_af)
+ return i;
+ }
+ return i;
+}
+
+/**
+ * for_each_addr() - Iterate over addresses in array
+ * @a: Pointer variable for current entry (struct guest_addr *)
+ * @addrs: Array of guest addresses (e.g., c->addrs)
+ * @count: Number of addresses (e.g., c->addr_count)
+ * @af: Address family filter: AF_INET, AF_INET6, or 0 for all
+ */
+#define for_each_addr(a, addrs, count, af) \
+ for (int i_ = next_addr_idx_((addrs), (count), 0, (af)); \
+ i_ < (count) && ((a) = &(addrs)[i_], true); \
+ i_ = next_addr_idx_((addrs), (count), i_ + 1, (af)))
+
void proto_update_l2_buf(const unsigned char *eth_d);
#endif /* PASST_H */
diff --git a/pasta.c b/pasta.c
index bab945f..c51e4cd 100644
--- a/pasta.c
+++ b/pasta.c
@@ -330,6 +330,8 @@ void pasta_ns_conf(struct ctx *c)
if (c->pasta_conf_ns) {
unsigned int flags = IFF_UP;
+ const struct guest_addr *a;
+ int plen;
if (c->mtu)
nl_link_set_mtu(nl_sock_ns, c->pasta_ifi, c->mtu);
@@ -341,10 +343,15 @@ void pasta_ns_conf(struct ctx *c)
if (c->ifi4) {
if (c->ip4.no_copy_addrs) {
- rc = nl_addr_set(nl_sock_ns, c->pasta_ifi,
- AF_INET,
- &c->ip4.addr,
- c->ip4.prefix_len);
+ a = fwd_get_addr(c, AF_INET, 0, 0);
+ if (a) {
+ plen = inany_prefix_len(&a->addr,
+ a->prefix_len);
+ rc = nl_addr_set(nl_sock_ns,
+ c->pasta_ifi, AF_INET,
+ inany_v4(&a->addr),
+ plen);
+ }
} else {
rc = nl_addr_dup(nl_sock, c->ifi4,
nl_sock_ns, c->pasta_ifi,
@@ -397,11 +404,13 @@ ipv4_done:
0, IFF_NOARP);
if (c->ip6.no_copy_addrs) {
- if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr)) {
+ a = fwd_get_addr(c, AF_INET6, 0, 0);
+ if (a)
rc = nl_addr_set(nl_sock_ns,
- c->pasta_ifi, AF_INET6,
- &c->ip6.addr, 64);
- }
+ c->pasta_ifi,
+ AF_INET6,
+ &a->addr.a6,
+ a->prefix_len);
} else {
rc = nl_addr_dup(nl_sock, c->ifi6,
nl_sock_ns, c->pasta_ifi,
diff --git a/tap.c b/tap.c
index 59c45a3..eb93f74 100644
--- a/tap.c
+++ b/tap.c
@@ -936,8 +936,11 @@ resume:
c->ip6.addr_seen = *saddr;
}
- if (IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr))
- c->ip6.addr = *saddr;
+ if (!fwd_get_addr(c, AF_INET6, 0, 0)) {
+ union inany_addr addr = { .a6 = *saddr };
+
+ fwd_set_addr(c, &addr, CONF_ADDR_LINKLOCAL, 64);
+ }
} else if (!IN6_IS_ADDR_UNSPECIFIED(saddr)){
c->ip6.addr_seen = *saddr;
}
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 03/13] fwd: Unify guest accessibility checks with unified address array
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
2026-04-13 0:53 ` [PATCH v7 01/13] dhcpv6: Fix reply destination to match client's source address Jon Maloy
2026-04-13 0:53 ` [PATCH v7 02/13] passt, pasta: Introduce unified multi-address data structures Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 04/13] arp: Check all configured addresses in ARP filtering Jon Maloy
` (9 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We replace the fwd_guest_accessible4() and fwd_guest_accessible6()
functions with a unified fwd_guest_accessible() function that handles
both address families. With the unified address array, we can check
all configured addresses in a single pass using for_each_addr() with
family filter AF_UNSPEC.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v6: -Some fixes based on feedback from David Gibson
v7: -Added curly brackets to for_each_addr() in fwd_guest_accessible(),
as suggested by Stefano Brivio.
---
fwd.c | 69 +++++++++++++----------------------------------------------
1 file changed, 15 insertions(+), 54 deletions(-)
diff --git a/fwd.c b/fwd.c
index 14ce0a7..e676c18 100644
--- a/fwd.c
+++ b/fwd.c
@@ -988,19 +988,19 @@ static bool is_dns_flow(uint8_t proto, const struct flowside *ini)
}
/**
- * fwd_guest_accessible4() - Is IPv4 address guest-accessible
+ * fwd_guest_accessible() - Is address guest-accessible
* @c: Execution context
- * @addr: Host visible IPv4 address
+ * @addr: Host visible address (IPv4 or IPv6)
*
* Return: true if @addr on the host is accessible to the guest without
* translation, false otherwise
*/
-static bool fwd_guest_accessible4(const struct ctx *c,
- const struct in_addr *addr)
+static bool fwd_guest_accessible(const struct ctx *c,
+ const union inany_addr *addr)
{
const struct guest_addr *a;
- if (IN4_IS_ADDR_LOOPBACK(addr))
+ if (inany_is_loopback(addr))
return false;
/* In socket interfaces 0.0.0.0 generally means "any" or unspecified,
@@ -1008,38 +1008,18 @@ static bool fwd_guest_accessible4(const struct ctx *c,
* that has a different meaning for host and guest, we can't let it
* through untranslated.
*/
- if (IN4_IS_ADDR_UNSPECIFIED(addr))
+ if (inany_is_unspecified(addr))
return false;
- /* For IPv4, addr_seen is initialised to addr, so is always a valid
- * address
+ /* Check against all configured guest addresses */
+ for_each_addr(a, c->addrs, c->addr_count, AF_UNSPEC) {
+ if (inany_equals(addr, &a->addr))
+ return false;
+ }
+ /* Also check addr_seen: it tracks the address the guest is actually
+ * using, which may differ from configured addresses.
*/
- a = fwd_get_addr(c, AF_INET, 0, 0);
- if ((a && IN4_ARE_ADDR_EQUAL(addr, inany_v4(&a->addr))) ||
- IN4_ARE_ADDR_EQUAL(addr, &c->ip4.addr_seen))
- return false;
-
- return true;
-}
-
-/**
- * fwd_guest_accessible6() - Is IPv6 address guest-accessible
- * @c: Execution context
- * @addr: Host visible IPv6 address
- *
- * Return: true if @addr on the host is accessible to the guest without
- * translation, false otherwise
- */
-static bool fwd_guest_accessible6(const struct ctx *c,
- const struct in6_addr *addr)
-{
- const struct guest_addr *a;
-
- if (IN6_IS_ADDR_LOOPBACK(addr))
- return false;
-
- a = fwd_get_addr(c, AF_INET6, 0, 0);
- if (a && IN6_ARE_ADDR_EQUAL(addr, &a->addr.a6))
+ if (inany_equals4(addr, &c->ip4.addr_seen))
return false;
/* For IPv6, addr_seen starts unspecified, because we don't know what LL
@@ -1047,31 +1027,12 @@ static bool fwd_guest_accessible6(const struct ctx *c,
* if it has been set to a real address.
*/
if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr_seen) &&
- IN6_ARE_ADDR_EQUAL(addr, &c->ip6.addr_seen))
+ inany_equals6(addr, &c->ip6.addr_seen))
return false;
return true;
}
-/**
- * fwd_guest_accessible() - Is IPv[46] address guest-accessible
- * @c: Execution context
- * @addr: Host visible IPv[46] address
- *
- * Return: true if @addr on the host is accessible to the guest without
- * translation, false otherwise
- */
-static bool fwd_guest_accessible(const struct ctx *c,
- const union inany_addr *addr)
-{
- const struct in_addr *a4 = inany_v4(addr);
-
- if (a4)
- return fwd_guest_accessible4(c, a4);
-
- return fwd_guest_accessible6(c, &addr->a6);
-}
-
/**
* nat_outbound() - Apply address translation for outbound (TAP to HOST)
* @c: Execution context
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 04/13] arp: Check all configured addresses in ARP filtering
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (2 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 03/13] fwd: Unify guest accessibility checks with unified address array Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 05/13] conf: Allow multiple -a/--address options per address family Jon Maloy
` (8 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
As a preparation for handling multiple addresses, we update ignore_arp()
to check against all addresses in the unified addrs[] array using the
for_each_addr() macro.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
v3: -Adapted to single-array changes earlier in this series
v6: -Made loop in ignore_arp() a little more palatable,
but not entirely as suggested by David.
v7: -Curly brackets in ignore_arp(), as suggested by Stefano.
-I did not modify the for_each_addr(), macro, as Stefano suggested,
since it also would require us to add an extra parameter indicating
the array length.
---
arp.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/arp.c b/arp.c
index a7fd82f..a3fdeb6 100644
--- a/arp.c
+++ b/arp.c
@@ -42,6 +42,7 @@ static bool ignore_arp(const struct ctx *c,
const struct arphdr *ah, const struct arpmsg *am)
{
const struct guest_addr *a;
+ union inany_addr addr;
if (ah->ar_hrd != htons(ARPHRD_ETHER) ||
ah->ar_pro != htons(ETH_P_IP) ||
@@ -55,11 +56,12 @@ static bool ignore_arp(const struct ctx *c,
!memcmp(am->sip, am->tip, sizeof(am->sip)))
return true;
- /* Don't resolve the guest's assigned address, either. */
- a = fwd_get_addr(c, AF_INET, 0, 0);
- if (a && !memcmp(am->tip, inany_v4(&a->addr), sizeof(am->tip)))
- return true;
-
+ /* Don't resolve any of the guest's addresses */
+ inany_from_af(&addr, AF_INET, am->tip);
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET) {
+ if (inany_equals(&addr, &a->addr))
+ return true;
+ }
return false;
}
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 05/13] conf: Allow multiple -a/--address options per address family
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (3 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 04/13] arp: Check all configured addresses in ARP filtering Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 06/13] netlink, conf: Read all addresses from template interface at startup Jon Maloy
` (7 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
Allow specifying multiple addresses per family with -a/--address.
The first address of each family is used for DHCP/DHCPv6 assignment.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v2: - Adapted to previous code changes
v3: - Adapted to single-array strategy
- Changes according to feedback from S. Brivio and D. Gibson.
v4: - Stripped down and adapted after feedback from David G.
v6: - Adapted to previous changes in series
- Removed the "one address" limitation for -n option
v7: - Updated man page.
---
conf.c | 7 ++++---
fwd.c | 4 +---
passt.1 | 7 +++----
pasta.c | 14 ++++++++------
4 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/conf.c b/conf.c
index 591f561..8b4a7a0 100644
--- a/conf.c
+++ b/conf.c
@@ -939,9 +939,11 @@ static void usage(const char *name, FILE *f, int status)
" default: 65520: maximum 802.3 MTU minus 802.3 header\n"
" length, rounded to 32 bits (IPv4 words)\n"
" -a, --address ADDR Assign IPv4 or IPv6 address ADDR[/PREFIXLEN]\n"
- " can be specified zero to two times (for IPv4 and IPv6)\n"
+ " can be specified up to a maximum of %d times\n"
" default: use addresses from interface with default route\n"
- " -n, --netmask MASK Assign IPv4 MASK, dot-decimal or bits\n"
+ " -n, --netmask MASK Assign IPv4 MASK, dot-decimal or bits\n",
+ MAX_GUEST_ADDRS);
+ FPRINTF(f,
" default: netmask from matching address on the host\n"
" -M, --mac-addr ADDR Use source MAC address ADDR\n"
" default: 9a:55:9a:55:9a:55 (locally administered)\n"
@@ -1898,7 +1900,6 @@ void conf(struct ctx *c, int argc, char **argv)
IN6_IS_ADDR_V4COMPAT(&addr.a6))
die("Invalid address: %s", optarg);
- /* Legacy behaviour: replace existing address if any */
fwd_set_addr(c, &addr, CONF_ADDR_USER, prefix_len);
if (inany_v4(&addr))
c->ip4.no_copy_addrs = true;
diff --git a/fwd.c b/fwd.c
index e676c18..d3f576a 100644
--- a/fwd.c
+++ b/fwd.c
@@ -250,14 +250,12 @@ void fwd_neigh_table_init(const struct ctx *c)
}
/**
- * fwd_set_addr() - Add or update an address in the unified address array
+ * fwd_set_addr() - Update address entry, adding one if needed
* @c: Execution context
* @addr: Address to add (IPv4-mapped or IPv6)
* @flags: CONF_ADDR_* flags for this address
* @prefix_len: Prefix length in IPv6 or IPv4 format
*
- * Find the first existing entry of the same address family and
- * overwrite it, or create a new one if none exists
*/
void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
uint8_t flags, int prefix_len)
diff --git a/passt.1 b/passt.1
index 13e8df9..12ec857 100644
--- a/passt.1
+++ b/passt.1
@@ -164,16 +164,13 @@ An optional /\fIprefix_len\fR (0-32 for IPv4, 0-128 for IPv6) can be
appended in CIDR notation (e.g. 192.0.2.1/24). This is an alternative to
using the \fB-n\fR, \fB--netmask\fR option. Mixing CIDR notation with
\fB-n\fR results in an error.
-If a prefix length is assigned to an IPv6 address using this method, it will
-in the current code version be overridden by the default value of 64.
-This option can be specified zero (for defaults) to two times (once for IPv4,
-once for IPv6).
By default, assigned IPv4 and IPv6 addresses are taken from the host interfaces
with the first default route, if any, for the corresponding IP version. If no
default routes are available and there is any interface with any route for a
given IP version, the first of these interfaces will be chosen instead. If no
such interface exists for a given IP version, the link-local address 169.254.2.1
is assigned for IPv4, and no additional address will be assigned for IPv6.
+This option can be given multiple times, indicating multiple different addresses.
.TP
.BR \-n ", " \-\-netmask " " \fImask
@@ -181,6 +178,8 @@ Assign IPv4 netmask \fImask\fR, expressed as dot-decimal or number of bits, via
DHCP (option 1). Alternatively, the prefix length can be specified using CIDR
notation with the \fB-a\fR, \fB--address\fR option (e.g. \fB-a\fR 192.0.2.1/24).
Mixing \fB-n\fR with CIDR notation results in an error.
+When indicated, this option sets the prefix length of the first configured
+IPv4 address only.
If no address is indicated, the netmask associated with the adopted host address,
if any, is used. If an address is indicated, but without a prefix length, the
netmask is determined based on the corresponding network class. In all other
diff --git a/pasta.c b/pasta.c
index c51e4cd..b3936f5 100644
--- a/pasta.c
+++ b/pasta.c
@@ -343,14 +343,15 @@ void pasta_ns_conf(struct ctx *c)
if (c->ifi4) {
if (c->ip4.no_copy_addrs) {
- a = fwd_get_addr(c, AF_INET, 0, 0);
- if (a) {
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET) {
plen = inany_prefix_len(&a->addr,
a->prefix_len);
rc = nl_addr_set(nl_sock_ns,
c->pasta_ifi, AF_INET,
inany_v4(&a->addr),
plen);
+ if (rc < 0)
+ break;
}
} else {
rc = nl_addr_dup(nl_sock, c->ifi4,
@@ -404,13 +405,14 @@ ipv4_done:
0, IFF_NOARP);
if (c->ip6.no_copy_addrs) {
- a = fwd_get_addr(c, AF_INET6, 0, 0);
- if (a)
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
rc = nl_addr_set(nl_sock_ns,
c->pasta_ifi,
- AF_INET6,
- &a->addr.a6,
+ AF_INET6, &a->addr.a6,
a->prefix_len);
+ if (rc < 0)
+ break;
+ }
} else {
rc = nl_addr_dup(nl_sock, c->ifi6,
nl_sock_ns, c->pasta_ifi,
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 06/13] netlink, conf: Read all addresses from template interface at startup
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (4 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 05/13] conf: Allow multiple -a/--address options per address family Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 07/13] netlink, pasta: refactor function pasta_ns_conf() Jon Maloy
` (6 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
Add nl_addr_get_all() to read all addresses from the template interface
into c->addrs[] array, rather than just selecting the "best" one.
This allows multi-address configurations where the template interface
has multiple IPv4 or IPv6 addresses assigned to it, all of which
will now be copied to the guest namespace when using --config-net.
For IPv6, the function also captures the link-local address into
c->ip6.our_tap_ll as a side effect.
Update conf_ip4() and conf_ip6() to use nl_addr_get_all() when no
user-specified addresses are present.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
v7: -Excluded all link local addresses from host to be added to array
-Minor comment change suggested by Stefano
---
conf.c | 51 ++++++++++++++++++++++++++-------------------------
netlink.c | 53 +++++++++++++++++++++++++++++------------------------
netlink.h | 3 +--
3 files changed, 56 insertions(+), 51 deletions(-)
diff --git a/conf.c b/conf.c
index 8b4a7a0..924ade2 100644
--- a/conf.c
+++ b/conf.c
@@ -736,6 +736,7 @@ static int conf_ip4_prefix(const char *arg)
static unsigned int conf_ip4(struct ctx *c, unsigned int ifi)
{
struct ip4_ctx *ip4 = &c->ip4;
+ const struct guest_addr *a;
if (!ifi)
ifi = nl_get_ext_if(nl_sock, AF_INET);
@@ -755,24 +756,24 @@ static unsigned int conf_ip4(struct ctx *c, unsigned int ifi)
}
}
- if (!fwd_get_addr(c, AF_INET, 0, 0)) {
- struct in_addr addr;
- int prefix_len;
- int rc = nl_addr_get(nl_sock, ifi, AF_INET,
- &addr, &prefix_len, NULL);
+ a = fwd_get_addr(c, AF_INET, CONF_ADDR_USER, 0);
+ if (!a) {
+ int rc = nl_addr_get_all(c, nl_sock, ifi, AF_INET);
+
if (rc < 0) {
- debug("Couldn't discover IPv4 address: %s",
+ debug("Couldn't discover IPv4 addresses: %s",
strerror_(-rc));
return 0;
}
- if (IN4_IS_ADDR_UNSPECIFIED(&addr))
+ if (!rc || !fwd_get_addr(c, AF_INET, 0, 0))
return 0;
- fwd_set_addr(c, &inany_from_v4(addr), CONF_ADDR_HOST,
- prefix_len);
- ip4->addr_seen = addr;
+ a = fwd_get_addr(c, AF_INET, CONF_ADDR_HOST, 0);
}
+ if (a)
+ ip4->addr_seen = *inany_v4(&a->addr);
+
ip4->our_tap_addr = ip4->guest_gw;
return ifi;
@@ -805,8 +806,6 @@ static unsigned int conf_ip6(struct ctx *c, unsigned int ifi)
{
struct ip6_ctx *ip6 = &c->ip6;
const struct guest_addr *a;
- union inany_addr addr;
- int prefix_len = 0;
int rc;
if (!ifi)
@@ -826,24 +825,26 @@ static unsigned int conf_ip6(struct ctx *c, unsigned int ifi)
}
}
- rc = nl_addr_get(nl_sock, ifi, AF_INET6, &addr.a6,
- &prefix_len, &ip6->our_tap_ll);
- if (rc < 0) {
- debug("Couldn't discover IPv6 address: %s", strerror_(-rc));
- return 0;
- }
-
- a = fwd_get_addr(c, AF_INET6, 0, 0);
+ a = fwd_get_addr(c, AF_INET6, CONF_ADDR_USER, 0);
if (!a) {
- if (IN6_IS_ADDR_UNSPECIFIED(&addr))
+ rc = nl_addr_get_all(c, nl_sock, ifi, AF_INET6);
+ if (rc < 0) {
+ debug("Couldn't discover IPv6 addresses: %s",
+ strerror_(-rc));
return 0;
-
- fwd_set_addr(c, &addr, CONF_ADDR_HOST, prefix_len);
- ip6->addr_seen = addr.a6;
+ }
+ a = fwd_get_addr(c, AF_INET6, CONF_ADDR_HOST, 0);
} else {
- ip6->addr_seen = a->addr.a6;
+ rc = nl_addr_get_ll(nl_sock, ifi, &ip6->our_tap_ll);
+ if (rc < 0) {
+ debug("Couldn't get link-local address: %s",
+ strerror_(-rc));
+ }
}
+ if (a)
+ ip6->addr_seen = a->addr.a6;
+
if (IN6_IS_ADDR_LINKLOCAL(&ip6->guest_gw))
ip6->our_tap_ll = ip6->guest_gw;
diff --git a/netlink.c b/netlink.c
index e07b47f..3f5a812 100644
--- a/netlink.c
+++ b/netlink.c
@@ -747,20 +747,20 @@ int nl_addr_set_ll_nodad(int s, unsigned int ifi)
}
/**
- * nl_addr_get() - Get most specific global address, given interface and family
+ * nl_addr_get_all() - Get all addresses for a given interface into ctx
+ * @c: Execution context
* @s: Netlink socket
- * @ifi: Interface index in outer network namespace
- * @af: Address family
- * @addr: Global address to fill
- * @prefix_len: Mask or prefix length, to fill
- * @addr_l: Link-scoped address to fill (for IPv6)
+ * @ifi: Interface index
+ * @af: Address family (AF_INET or AF_INET6)
*
- * Return: 0 on success, negative error code on failure
+ * Populates c->addrs[] with all non-deprecated addresses from the interface.
+ * For IPv6, also captures link-local address in c->ip6.our_tap_ll.
+ * Skips IPv6 link-local addresses for the main array.
+ *
+ * Return: number of addresses added, or negative error code on failure
*/
-int nl_addr_get(int s, unsigned int ifi, sa_family_t af,
- void *addr, int *prefix_len, void *addr_l)
+int nl_addr_get_all(struct ctx *c, int s, unsigned int ifi, sa_family_t af)
{
- uint8_t prefix_max = 0, prefix_max_ll = 0;
struct req_t {
struct nlmsghdr nlh;
struct ifaddrmsg ifa;
@@ -771,6 +771,7 @@ int nl_addr_get(int s, unsigned int ifi, sa_family_t af,
struct nlmsghdr *nh;
char buf[NLBUFSIZ];
ssize_t status;
+ int count = 0;
uint32_t seq;
seq = nl_send(s, &req, RTM_GETADDR, NLM_F_DUMP, sizeof(req));
@@ -784,27 +785,31 @@ int nl_addr_get(int s, unsigned int ifi, sa_family_t af,
for (rta = IFA_RTA(ifa), na = IFA_PAYLOAD(nh); RTA_OK(rta, na);
rta = RTA_NEXT(rta, na)) {
- if ((af == AF_INET && rta->rta_type != IFA_LOCAL) ||
- (af == AF_INET6 && rta->rta_type != IFA_ADDRESS))
- continue;
+ union inany_addr addr;
- if (ifa->ifa_prefixlen > prefix_max && addr &&
- (af == AF_INET || ifa->ifa_scope < RT_SCOPE_LINK)) {
- memcpy(addr, RTA_DATA(rta), RTA_PAYLOAD(rta));
+ if (af == AF_INET && rta->rta_type != IFA_LOCAL)
+ continue;
+ if (af == AF_INET6 && rta->rta_type != IFA_ADDRESS)
+ continue;
- prefix_max = *prefix_len = ifa->ifa_prefixlen;
+ /* Skip link-local addresses (kernel auto-configures) */
+ if (ifa->ifa_scope == RT_SCOPE_LINK) {
+ if (af == AF_INET)
+ continue;
+ memcpy(&c->ip6.our_tap_ll, RTA_DATA(rta),
+ sizeof(c->ip6.our_tap_ll));
+ continue;
}
- if (addr_l &&
- af == AF_INET6 && ifa->ifa_scope == RT_SCOPE_LINK &&
- ifa->ifa_prefixlen > prefix_max_ll) {
- memcpy(addr_l, RTA_DATA(rta), RTA_PAYLOAD(rta));
+ inany_from_af(&addr, af, RTA_DATA(rta));
+ fwd_set_addr(c, &addr, CONF_ADDR_HOST,
+ ifa->ifa_prefixlen);
- prefix_max_ll = ifa->ifa_prefixlen;
- }
+ count++;
}
}
- return status;
+
+ return status < 0 ? status : count;
}
/**
diff --git a/netlink.h b/netlink.h
index b22f485..3af6d58 100644
--- a/netlink.h
+++ b/netlink.h
@@ -19,8 +19,7 @@ int nl_route_get_def(int s, unsigned int ifi, sa_family_t af, void *gw);
int nl_route_set_def(int s, unsigned int ifi, sa_family_t af, const void *gw);
int nl_route_dup(int s_src, unsigned int ifi_src,
int s_dst, unsigned int ifi_dst, sa_family_t af);
-int nl_addr_get(int s, unsigned int ifi, sa_family_t af,
- void *addr, int *prefix_len, void *addr_l);
+int nl_addr_get_all(struct ctx *c, int s, unsigned int ifi, sa_family_t af);
bool nl_neigh_mac_get(int s, const union inany_addr *addr, int ifi,
unsigned char *mac);
int nl_addr_set(int s, unsigned int ifi, sa_family_t af,
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 07/13] netlink, pasta: refactor function pasta_ns_conf()
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (5 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 06/13] netlink, conf: Read all addresses from template interface at startup Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 08/13] conf, pasta: Track observed guest IPv4 addresses in unified address array Jon Maloy
` (5 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
After the previous changes in this series it becomes possible
to simplify the pasta_ns_conf() function.
We extract address and route configuration into helper functions
pasta_conf_addrs() and pasta_conf_routes(), reducing nesting
and improving readability.
To allow pasta_conf_addrs() to handle both address families
uniformly, we change nl_addr_set() to take a union inany_addr pointer
instead of void pointer, moving the address family handling into
the function itself.
We also fix a bug where the IPv6 code path incorrectly wrote to
req.set.a4.rta_l.rta_type instead of req.set.a6.rta_l.rta_type.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v7: -Removed redundant argument 'af' in nl_addr_set()
-Removed redundant label and 'goto's in pasta_ns_conf()
-Since I excluded addition of all LINKLOCAL addresses from host
address array in a previous commit I can now omit this test
in pasta_conf_addrs() as suggested by David.
-Here is the example of agnostic usage of inany_prefix_len()
I referred to in a previous commit.
---
netlink.c | 17 ++--
netlink.h | 4 +-
pasta.c | 232 ++++++++++++++++++++++++++----------------------------
3 files changed, 123 insertions(+), 130 deletions(-)
diff --git a/netlink.c b/netlink.c
index 3f5a812..3d25212 100644
--- a/netlink.c
+++ b/netlink.c
@@ -863,15 +863,15 @@ int nl_addr_get_ll(int s, unsigned int ifi, struct in6_addr *addr)
* nl_addr_set() - Set IP addresses for given interface and address family
* @s: Netlink socket
* @ifi: Interface index
- * @af: Address family
* @addr: Global address to set
* @prefix_len: Mask or prefix length to set
*
* Return: 0 on success, negative error code on failure
*/
-int nl_addr_set(int s, unsigned int ifi, sa_family_t af,
- const void *addr, int prefix_len)
+int nl_addr_set(int s, unsigned int ifi, const union inany_addr *addr,
+ int prefix_len)
{
+ sa_family_t af = inany_af(addr);
struct req_t {
struct nlmsghdr nlh;
struct ifaddrmsg ifa;
@@ -905,21 +905,22 @@ int nl_addr_set(int s, unsigned int ifi, sa_family_t af,
len = offsetof(struct req_t, set.a6) + sizeof(req.set.a6);
- memcpy(&req.set.a6.l, addr, sizeof(req.set.a6.l));
+ memcpy(&req.set.a6.l, &addr->a6, sizeof(req.set.a6.l));
req.set.a6.rta_l.rta_len = rta_len;
- req.set.a4.rta_l.rta_type = IFA_LOCAL;
- memcpy(&req.set.a6.a, addr, sizeof(req.set.a6.a));
+ req.set.a6.rta_l.rta_type = IFA_LOCAL;
+ memcpy(&req.set.a6.a, &addr->a6, sizeof(req.set.a6.a));
req.set.a6.rta_a.rta_len = rta_len;
req.set.a6.rta_a.rta_type = IFA_ADDRESS;
} else {
+ const struct in_addr *v4 = inany_v4(addr);
size_t rta_len = RTA_LENGTH(sizeof(req.set.a4.l));
len = offsetof(struct req_t, set.a4) + sizeof(req.set.a4);
- memcpy(&req.set.a4.l, addr, sizeof(req.set.a4.l));
+ memcpy(&req.set.a4.l, v4, sizeof(req.set.a4.l));
req.set.a4.rta_l.rta_len = rta_len;
req.set.a4.rta_l.rta_type = IFA_LOCAL;
- memcpy(&req.set.a4.a, addr, sizeof(req.set.a4.a));
+ memcpy(&req.set.a4.a, v4, sizeof(req.set.a4.a));
req.set.a4.rta_a.rta_len = rta_len;
req.set.a4.rta_a.rta_type = IFA_ADDRESS;
}
diff --git a/netlink.h b/netlink.h
index 3af6d58..ec859b7 100644
--- a/netlink.h
+++ b/netlink.h
@@ -22,8 +22,8 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
int nl_addr_get_all(struct ctx *c, int s, unsigned int ifi, sa_family_t af);
bool nl_neigh_mac_get(int s, const union inany_addr *addr, int ifi,
unsigned char *mac);
-int nl_addr_set(int s, unsigned int ifi, sa_family_t af,
- const void *addr, int prefix_len);
+int nl_addr_set(int s, unsigned int ifi, const union inany_addr *addr,
+ int prefix_len);
int nl_addr_get_ll(int s, unsigned int ifi, struct in6_addr *addr);
int nl_addr_set_ll_nodad(int s, unsigned int ifi);
int nl_addr_dup(int s_src, unsigned int ifi_src,
diff --git a/pasta.c b/pasta.c
index b3936f5..f949dc2 100644
--- a/pasta.c
+++ b/pasta.c
@@ -46,6 +46,7 @@
#include "util.h"
#include "passt.h"
+#include "conf.h"
#include "isolation.h"
#include "netlink.h"
#include "log.h"
@@ -303,13 +304,69 @@ void pasta_start_ns(struct ctx *c, uid_t uid, gid_t gid,
die_perror("Failed to join network namespace");
}
+/**
+ * pasta_conf_addrs() - Configure addresses for one address family in namespace
+ * @c: Execution context
+ * @af: Address family (AF_INET or AF_INET6)
+ * @ifi: Host interface index for this address family
+ * @no_copy: If true, set addresses from c->addrs; if false, copy from host
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int pasta_conf_addrs(struct ctx *c, sa_family_t af,
+ int ifi, bool no_copy)
+{
+ const struct guest_addr *a;
+
+ if (!ifi)
+ return 0;
+
+ if (!no_copy)
+ return nl_addr_dup(nl_sock, ifi, nl_sock_ns, c->pasta_ifi, af);
+
+ for_each_addr(a, c->addrs, c->addr_count, af) {
+ int rc;
+
+ rc = nl_addr_set(nl_sock_ns, c->pasta_ifi, &a->addr,
+ inany_prefix_len(&a->addr, a->prefix_len));
+ if (rc < 0)
+ return rc;
+ }
+ return 0;
+}
+
+/**
+ * pasta_conf_routes() - Configure routes for one address family in namespace
+ * @c: Execution context
+ * @af: Address family (AF_INET or AF_INET6)
+ * @ifi: Host interface index for this address family
+ * @no_copy: If true, set default route; if false, copy routes from host
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int pasta_conf_routes(struct ctx *c, sa_family_t af, int ifi,
+ bool no_copy)
+{
+ const void *gw = (af == AF_INET) ?
+ (const void *)&c->ip4.guest_gw : (const void *)&c->ip6.guest_gw;
+
+ if (!ifi)
+ return 0;
+
+ if (no_copy)
+ return nl_route_set_def(nl_sock_ns, c->pasta_ifi, af, gw);
+
+ return nl_route_dup(nl_sock, ifi, nl_sock_ns, c->pasta_ifi, af);
+}
+
/**
* pasta_ns_conf() - Set up loopback and tap interfaces in namespace as needed
* @c: Execution context
*/
void pasta_ns_conf(struct ctx *c)
{
- int rc = 0;
+ unsigned int flags = IFF_UP;
+ int rc;
rc = nl_link_set_flags(nl_sock_ns, 1 /* lo */, IFF_UP, IFF_UP);
if (rc < 0)
@@ -328,127 +385,62 @@ void pasta_ns_conf(struct ctx *c)
die("Couldn't set MAC address in namespace: %s",
strerror_(-rc));
- if (c->pasta_conf_ns) {
- unsigned int flags = IFF_UP;
- const struct guest_addr *a;
- int plen;
-
- if (c->mtu)
- nl_link_set_mtu(nl_sock_ns, c->pasta_ifi, c->mtu);
-
- if (c->ifi6) /* Avoid duplicate address detection on link up */
- flags |= IFF_NOARP;
-
- nl_link_set_flags(nl_sock_ns, c->pasta_ifi, flags, flags);
-
- if (c->ifi4) {
- if (c->ip4.no_copy_addrs) {
- for_each_addr(a, c->addrs, c->addr_count, AF_INET) {
- plen = inany_prefix_len(&a->addr,
- a->prefix_len);
- rc = nl_addr_set(nl_sock_ns,
- c->pasta_ifi, AF_INET,
- inany_v4(&a->addr),
- plen);
- if (rc < 0)
- break;
- }
- } else {
- rc = nl_addr_dup(nl_sock, c->ifi4,
- nl_sock_ns, c->pasta_ifi,
- AF_INET);
- }
-
- if (c->ifi4 == -1 && rc == -ENOTSUP) {
- warn("IPv4 not supported, disabling");
- c->ifi4 = 0;
- goto ipv4_done;
- }
-
- if (rc < 0) {
- die("Couldn't set IPv4 address(es) in namespace: %s",
- strerror_(-rc));
- }
-
- if (c->ip4.no_copy_routes) {
- rc = nl_route_set_def(nl_sock_ns, c->pasta_ifi,
- AF_INET,
- &c->ip4.guest_gw);
- } else {
- rc = nl_route_dup(nl_sock, c->ifi4, nl_sock_ns,
- c->pasta_ifi, AF_INET);
- }
-
- if (rc < 0) {
- die("Couldn't set IPv4 route(s) in guest: %s",
- strerror_(-rc));
- }
- }
-ipv4_done:
-
- if (c->ifi6) {
- rc = nl_addr_get_ll(nl_sock_ns, c->pasta_ifi,
- &c->ip6.addr_ll_seen);
- if (rc < 0) {
- warn("Can't get LL address from namespace: %s",
- strerror_(-rc));
- }
-
- rc = nl_addr_set_ll_nodad(nl_sock_ns, c->pasta_ifi);
- if (rc < 0) {
- warn("Can't set nodad for LL in namespace: %s",
- strerror_(-rc));
- }
-
- /* We dodged DAD: re-enable neighbour solicitations */
- nl_link_set_flags(nl_sock_ns, c->pasta_ifi,
- 0, IFF_NOARP);
-
- if (c->ip6.no_copy_addrs) {
- for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
- rc = nl_addr_set(nl_sock_ns,
- c->pasta_ifi,
- AF_INET6, &a->addr.a6,
- a->prefix_len);
- if (rc < 0)
- break;
- }
- } else {
- rc = nl_addr_dup(nl_sock, c->ifi6,
- nl_sock_ns, c->pasta_ifi,
- AF_INET6);
- }
-
- if (rc < 0) {
- die("Couldn't set IPv6 address(es) in namespace: %s",
- strerror_(-rc));
- }
-
- if (c->ip6.no_copy_routes) {
- rc = nl_route_set_def(nl_sock_ns, c->pasta_ifi,
- AF_INET6,
- &c->ip6.guest_gw);
- } else {
- rc = nl_route_dup(nl_sock, c->ifi6,
- nl_sock_ns, c->pasta_ifi,
- AF_INET6);
- }
-
- if (c->ifi6 == -1 && rc == -ENOTSUP) {
- warn("IPv6 not supported, disabling");
- c->ifi6 = 0;
- goto ipv6_done;
- }
-
- if (rc < 0) {
- die("Couldn't set IPv6 route(s) in guest: %s",
- strerror_(-rc));
- }
- }
+ proto_update_l2_buf(c->guest_mac);
+
+ if (!c->pasta_conf_ns)
+ return;
+
+ if (c->mtu)
+ nl_link_set_mtu(nl_sock_ns, c->pasta_ifi, c->mtu);
+
+ if (c->ifi6) /* Avoid duplicate address detection on link up */
+ flags |= IFF_NOARP;
+
+ nl_link_set_flags(nl_sock_ns, c->pasta_ifi, flags, flags);
+
+ /* IPv4 configuration */
+ rc = pasta_conf_addrs(c, AF_INET, c->ifi4, c->ip4.no_copy_addrs);
+ if (c->ifi4 == -1 && rc == -ENOTSUP) {
+ warn("IPv4 not supported, disabling");
+ c->ifi4 = 0;
+ } else if (rc < 0) {
+ die("Couldn't set IPv4 address(es): %s", strerror_(-rc));
+ } else if (c->ifi4) {
+ rc = pasta_conf_routes(c, AF_INET, c->ifi4,
+ c->ip4.no_copy_routes);
+ if (rc < 0)
+ die("Couldn't set IPv4 route(s): %s", strerror_(-rc));
}
-ipv6_done:
- proto_update_l2_buf(c->guest_mac);
+ if (!c->ifi6)
+ return;
+
+ rc = nl_addr_get_ll(nl_sock_ns, c->pasta_ifi,
+ &c->ip6.addr_ll_seen);
+ if (rc < 0)
+ warn("Can't get LL address from namespace: %s",
+ strerror_(-rc));
+
+ rc = nl_addr_set_ll_nodad(nl_sock_ns, c->pasta_ifi);
+ if (rc < 0)
+ warn("Can't set nodad for LL in namespace: %s",
+ strerror_(-rc));
+
+ /* We dodged DAD: re-enable neighbour solicitations */
+ nl_link_set_flags(nl_sock_ns, c->pasta_ifi, 0, IFF_NOARP);
+
+ rc = pasta_conf_addrs(c, AF_INET6, c->ifi6, c->ip6.no_copy_addrs);
+ if (c->ifi6 == -1 && rc == -ENOTSUP) {
+ warn("IPv6 not supported, disabling");
+ c->ifi6 = 0;
+ } else if (rc < 0) {
+ die("Couldn't set IPv6 address(es): %s", strerror_(-rc));
+ } else {
+ rc = pasta_conf_routes(c, AF_INET6, c->ifi6,
+ c->ip6.no_copy_routes);
+ if (rc < 0)
+ die("Couldn't set IPv6 route(s): %s", strerror_(-rc));
+ }
}
/**
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 08/13] conf, pasta: Track observed guest IPv4 addresses in unified address array
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (6 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 07/13] netlink, pasta: refactor function pasta_ns_conf() Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 09/13] conf, pasta: Track observed guest IPv6 " Jon Maloy
` (4 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We remove the addr_seen field in struct ip4_ctx and replace it by
setting a new CONF_ADDR_OBSERVED flag in the corresponding entry
in the unified address array.
The observed IPv4 address is always added at or moved to position 0,
increasing chances for a fast lookup.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v4: - Removed migration protocol update, to be added in later commit
- Allow only one OBSERVED address at a time
- Some other changes based on feedback from David G
v5: - Allowing multiple observed IPv4 addresses
v6: - Refactored fwd_set_addr(), notably:
o Limited number of allowed observed addresses to four per protocol
o I kept the memmove() calls, since I find no more elegant way to
do this. Performance cost should be minimal, since these parts
of the code will execute only very exceptionally. Note that
removing the 'oldest' entry implicitly means removing the least
used one, since the latter will migrate to the highest position
after a few iterations of remove/add.
o Also kept the prefix_len update. Not sure about this, but I
cannot see how the current approach can cause any harm.
- Other changes suggested by David G, notably reversing some
residues after an accidental merge/re-split with the next
commit.
v7: - Changed fwd_set_addr() to only accept keeping one observed-only
address per protocol, as suggested by David.
- Eliminated redundant tap_check_src_addr4() call level.
- I keep fwd_select_addr() for the same pragmatic reason it was
introduced: to avoid ugly, deeply indented code that tends
to wrap across several lines.
---
conf.c | 6 ---
fwd.c | 124 +++++++++++++++++++++++++++++++++++++++++++++++-------
fwd.h | 4 ++
migrate.c | 17 +++++++-
passt.h | 6 +--
tap.c | 8 +++-
6 files changed, 136 insertions(+), 29 deletions(-)
diff --git a/conf.c b/conf.c
index 924ade2..f503d0f 100644
--- a/conf.c
+++ b/conf.c
@@ -767,13 +767,8 @@ static unsigned int conf_ip4(struct ctx *c, unsigned int ifi)
}
if (!rc || !fwd_get_addr(c, AF_INET, 0, 0))
return 0;
-
- a = fwd_get_addr(c, AF_INET, CONF_ADDR_HOST, 0);
}
- if (a)
- ip4->addr_seen = *inany_v4(&a->addr);
-
ip4->our_tap_addr = ip4->guest_gw;
return ifi;
@@ -787,7 +782,6 @@ static void conf_ip4_local(struct ctx *c)
{
struct ip4_ctx *ip4 = &c->ip4;
- ip4->addr_seen = IP4_LL_GUEST_ADDR;
ip4->our_tap_addr = ip4->guest_gw = IP4_LL_GUEST_GW;
ip4->no_copy_addrs = ip4->no_copy_routes = true;
fwd_set_addr(c, &inany_from_v4(IP4_LL_GUEST_ADDR),
diff --git a/fwd.c b/fwd.c
index d3f576a..8c7bf91 100644
--- a/fwd.c
+++ b/fwd.c
@@ -28,6 +28,7 @@
#include "inany.h"
#include "fwd.h"
#include "passt.h"
+#include "conf.h"
#include "lineread.h"
#include "flow_table.h"
#include "netlink.h"
@@ -260,21 +261,68 @@ void fwd_neigh_table_init(const struct ctx *c)
void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
uint8_t flags, int prefix_len)
{
- struct guest_addr *a;
+ struct guest_addr *a, *arr = &c->addrs[0], *rm = NULL;
+ int count = c->addr_count;
+ int af_cnt = 0;
- for_each_addr(a, c->addrs, c->addr_count, inany_af(addr)) {
- goto found;
+ for_each_addr(a, c->addrs, c->addr_count, AF_UNSPEC) {
+ if (!inany_equals(&a->addr, addr))
+ continue;
+
+ /* Adjust and update prefix_len if provided and applicable */
+ if (prefix_len && !(a->flags & CONF_ADDR_USER))
+ a->prefix_len = inany_prefix_len(addr, prefix_len);
+
+ /* Nothing more to change */
+ if ((a->flags & flags) == flags)
+ return;
+
+ a->flags |= flags;
+ if (!(flags & CONF_ADDR_OBSERVED))
+ return;
+
+ /* Observed address moves to position 0: remove, re-add later */
+ prefix_len = a->prefix_len;
+ memmove(a, a + 1, (&arr[count] - (a + 1)) * sizeof(*a));
+ c->addr_count = --count;
+ break;
}
- if (c->addr_count >= MAX_GUEST_ADDRS)
+ if (count >= MAX_GUEST_ADDRS) {
+ debug("Address table full, can't add address");
return;
+ }
- a = &c->addrs[c->addr_count++];
-
-found:
+ /* Add to head or tail, depending on flag */
+ if (flags & CONF_ADDR_OBSERVED) {
+ a = &arr[0];
+ memmove(&arr[1], a, count * sizeof(*a));
+ } else {
+ a = &arr[count];
+ }
+ c->addr_count = ++count;
a->addr = *addr;
a->prefix_len = inany_prefix_len6(addr, prefix_len);
a->flags = flags;
+
+ if (!(flags & CONF_ADDR_OBSERVED))
+ return;
+
+ /* Remove excess observed-only address if more than one */
+ for (int i = count - 1; i >= 0; i--) {
+ a = &arr[i];
+ if (inany_af(&a->addr) != inany_af(addr))
+ continue;
+ if (a->flags != CONF_ADDR_OBSERVED)
+ continue;
+ if (!rm)
+ rm = a;
+ af_cnt++;
+ }
+ if (af_cnt > 1) {
+ memmove(rm, rm + 1, (&arr[count] - (rm + 1)) * sizeof(*rm));
+ c->addr_count--;
+ }
}
/**
@@ -985,6 +1033,38 @@ static bool is_dns_flow(uint8_t proto, const struct flowside *ini)
((ini->oport == 53) || (ini->oport == 853));
}
+/**
+ * fwd_select_addr() - Select address with priority-based search
+ * @c: Execution context
+ * @af: Address family (AF_INET or AF_INET6)
+ * @primary: Primary flags to match (or 0 to skip)
+ * @secondary: Secondary flags to match (or 0 to skip)
+ * @skip: Flags to exclude from search
+ *
+ * Search for address entries in priority order.
+ *
+ * Return: pointer to selected address entry, or NULL if none found
+ */
+const struct guest_addr *fwd_select_addr(const struct ctx *c, int af,
+ int primary, int secondary, int skip)
+{
+ const struct guest_addr *a;
+
+ if (primary) {
+ a = fwd_get_addr(c, af, primary, skip);
+ if (a)
+ return a;
+ }
+
+ if (secondary) {
+ a = fwd_get_addr(c, af, secondary, skip);
+ if (a)
+ return a;
+ }
+
+ return NULL;
+}
+
/**
* fwd_guest_accessible() - Is address guest-accessible
* @c: Execution context
@@ -1014,11 +1094,6 @@ static bool fwd_guest_accessible(const struct ctx *c,
if (inany_equals(addr, &a->addr))
return false;
}
- /* Also check addr_seen: it tracks the address the guest is actually
- * using, which may differ from configured addresses.
- */
- if (inany_equals4(addr, &c->ip4.addr_seen))
- return false;
/* For IPv6, addr_seen starts unspecified, because we don't know what LL
* address the guest will take until we see it. Only check against it
@@ -1214,10 +1289,20 @@ uint8_t fwd_nat_from_host(const struct ctx *c,
* match.
*/
if (inany_v4(&ini->eaddr)) {
- if (c->host_lo_to_ns_lo)
+ if (c->host_lo_to_ns_lo) {
tgt->eaddr = inany_loopback4;
- else
- tgt->eaddr = inany_from_v4(c->ip4.addr_seen);
+ } else {
+ const struct guest_addr *a;
+
+ a = fwd_select_addr(c, AF_INET,
+ CONF_ADDR_OBSERVED,
+ CONF_ADDR_USER |
+ CONF_ADDR_HOST, 0);
+ if (!a)
+ return PIF_NONE;
+
+ tgt->eaddr = a->addr;
+ }
tgt->oaddr = inany_any4;
} else {
if (c->host_lo_to_ns_lo)
@@ -1252,7 +1337,14 @@ uint8_t fwd_nat_from_host(const struct ctx *c,
tgt->oport = ini->eport;
if (inany_v4(&tgt->oaddr)) {
- tgt->eaddr = inany_from_v4(c->ip4.addr_seen);
+ const struct guest_addr *a;
+
+ a = fwd_select_addr(c, AF_INET, CONF_ADDR_OBSERVED,
+ CONF_ADDR_USER | CONF_ADDR_HOST, 0);
+ if (!a)
+ return PIF_NONE;
+
+ tgt->eaddr = a->addr;
} else {
if (inany_is_linklocal6(&tgt->oaddr))
tgt->eaddr.a6 = c->ip6.addr_ll_seen;
diff --git a/fwd.h b/fwd.h
index c5a1068..9893856 100644
--- a/fwd.h
+++ b/fwd.h
@@ -25,6 +25,10 @@ void fwd_probe_ephemeral(void);
bool fwd_port_is_ephemeral(in_port_t port);
const struct guest_addr *fwd_get_addr(const struct ctx *c, sa_family_t af,
uint8_t incl, uint8_t excl);
+const struct guest_addr *fwd_select_addr(const struct ctx *c, int af,
+ int primary, int secondary, int skip);
+void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
+ uint8_t flags, int prefix_len);
/**
* struct fwd_rule - Forwarding rule governing a range of ports
diff --git a/migrate.c b/migrate.c
index 1e8858a..1e02720 100644
--- a/migrate.c
+++ b/migrate.c
@@ -18,6 +18,8 @@
#include "util.h"
#include "ip.h"
#include "passt.h"
+#include "conf.h"
+#include "fwd.h"
#include "inany.h"
#include "flow.h"
#include "flow_table.h"
@@ -57,11 +59,18 @@ static int seen_addrs_source_v2(struct ctx *c,
struct migrate_seen_addrs_v2 addrs = {
.addr6 = c->ip6.addr_seen,
.addr6_ll = c->ip6.addr_ll_seen,
- .addr4 = c->ip4.addr_seen,
};
+ const struct guest_addr *a;
(void)stage;
+ /* IPv4 observed address, with fallback to configured address */
+ a = fwd_select_addr(c, AF_INET, CONF_ADDR_OBSERVED,
+ CONF_ADDR_USER | CONF_ADDR_HOST,
+ CONF_ADDR_LINKLOCAL);
+ if (a)
+ addrs.addr4 = *inany_v4(&a->addr);
+
memcpy(addrs.mac, c->guest_mac, sizeof(addrs.mac));
if (write_all_buf(fd, &addrs, sizeof(addrs)))
@@ -90,7 +99,11 @@ static int seen_addrs_target_v2(struct ctx *c,
c->ip6.addr_seen = addrs.addr6;
c->ip6.addr_ll_seen = addrs.addr6_ll;
- c->ip4.addr_seen = addrs.addr4;
+
+ if (addrs.addr4.s_addr)
+ fwd_set_addr(c, &inany_from_v4(addrs.addr4),
+ CONF_ADDR_OBSERVED, 0);
+
memcpy(c->guest_mac, addrs.mac, sizeof(c->guest_mac));
return 0;
diff --git a/passt.h b/passt.h
index f75656d..5da1d55 100644
--- a/passt.h
+++ b/passt.h
@@ -64,8 +64,9 @@ enum passt_modes {
MODE_VU,
};
-/* Maximum number of addresses in context address array */
+/* Limits on number of addresses in context address array */
#define MAX_GUEST_ADDRS 32
+#define MAX_OBSERVED_ADDRS 4
/**
* struct guest_addr - Unified IPv4/IPv6 address entry
@@ -81,11 +82,11 @@ struct guest_addr {
#define CONF_ADDR_HOST BIT(1) /* From host interface */
#define CONF_ADDR_GENERATED BIT(2) /* Generated by PASST/PASTA */
#define CONF_ADDR_LINKLOCAL BIT(3) /* Link-local address */
+#define CONF_ADDR_OBSERVED BIT(4) /* Seen in guest traffic */
};
/**
* struct ip4_ctx - IPv4 execution context
- * @addr_seen: Latest IPv4 address seen as source from tap
* @guest_gw: IPv4 gateway as seen by the guest
* @map_host_loopback: Outbound connections to this address are NATted to the
* host's 127.0.0.1
@@ -101,7 +102,6 @@ struct guest_addr {
* @no_copy_addrs: Don't copy all addresses when configuring namespace
*/
struct ip4_ctx {
- struct in_addr addr_seen;
struct in_addr guest_gw;
struct in_addr map_host_loopback;
struct in_addr map_guest_addr;
diff --git a/tap.c b/tap.c
index eb93f74..7f04e12 100644
--- a/tap.c
+++ b/tap.c
@@ -47,6 +47,7 @@
#include "ip.h"
#include "iov.h"
#include "passt.h"
+#include "fwd.h"
#include "arp.h"
#include "dhcp.h"
#include "ndp.h"
@@ -756,9 +757,12 @@ resume:
continue;
}
- if (iph->saddr && c->ip4.addr_seen.s_addr != iph->saddr)
- c->ip4.addr_seen.s_addr = iph->saddr;
+ if (iph->saddr) {
+ const union inany_addr *addr;
+ addr = &inany_from_v4(*(struct in_addr *) &iph->saddr);
+ fwd_set_addr(c, addr, CONF_ADDR_OBSERVED, 0);
+ }
if (!iov_drop_header(&data, hlen))
continue;
if (iov_tail_size(&data) != l4len)
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 09/13] conf, pasta: Track observed guest IPv6 addresses in unified address array
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (7 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 08/13] conf, pasta: Track observed guest IPv4 addresses in unified address array Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 10/13] migrate: Update protocol to v3 for multi-address support Jon Maloy
` (3 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We remove the addr_seen and addr_ll_seen fields in struct ip6_ctx
and replace them by setting CONF_ADDR_OBSERVED and CONF_ADDR_LINKLOCAL
flags in the corresponding entry in the unified address array.
The observed IPv6 address is always added/moved to position 0
in the array, improving chances for fast lookup.
The separate check against addr_seen in fwd_guest_accessible() can now
be removed because the observed address is now in the unified array,
and the existing for_each_addr() loop already checks against all
addresses, including this one.
This completes the unification of address storage for both IPv4 and
IPv6, enabling future support for multiple guest addresses per family.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v5: - Made to use same algorithm and function as IPv4 for inserting
observed into the array.
v6: - Re-introduced code that by accident had been moved to the
previous commit.
- Some fixes based on feedback from David G.
v7: - Added a commit at the beginning of the series addressing
Stefano's concern about DHCPv6 reply addresses.
- Some other updates based on feedback from David and Stefano.
---
conf.c | 4 ----
dhcpv6.c | 4 +---
fwd.c | 38 +++++++++++++++++++++++---------------
inany.h | 3 +++
migrate.c | 37 +++++++++++++++++++++++++++----------
passt.h | 4 ----
pasta.c | 11 +++++++----
tap.c | 17 +++++------------
8 files changed, 66 insertions(+), 52 deletions(-)
diff --git a/conf.c b/conf.c
index f503d0f..3cb3553 100644
--- a/conf.c
+++ b/conf.c
@@ -827,7 +827,6 @@ static unsigned int conf_ip6(struct ctx *c, unsigned int ifi)
strerror_(-rc));
return 0;
}
- a = fwd_get_addr(c, AF_INET6, CONF_ADDR_HOST, 0);
} else {
rc = nl_addr_get_ll(nl_sock, ifi, &ip6->our_tap_ll);
if (rc < 0) {
@@ -836,9 +835,6 @@ static unsigned int conf_ip6(struct ctx *c, unsigned int ifi)
}
}
- if (a)
- ip6->addr_seen = a->addr.a6;
-
if (IN6_IS_ADDR_LINKLOCAL(&ip6->guest_gw))
ip6->our_tap_ll = ip6->guest_gw;
diff --git a/dhcpv6.c b/dhcpv6.c
index 0a064a9..447aaba 100644
--- a/dhcpv6.c
+++ b/dhcpv6.c
@@ -567,8 +567,8 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
struct opt_hdr client_id_storage;
/* cppcheck-suppress [variableScope,unmatchedSuppression] */
struct opt_ia_na ia_storage;
- const struct guest_addr *a;
const struct in6_addr *src;
+ const struct guest_addr *a;
struct msg_hdr mh_storage;
const struct msg_hdr *mh;
struct udphdr uh_storage;
@@ -683,8 +683,6 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
resp.hdr.xid = mh->xid;
tap_udp6_send(c, src, 547, saddr, 546, mh->xid, &resp, n);
- if (a)
- c->ip6.addr_seen = a->addr.a6;
return 1;
}
diff --git a/fwd.c b/fwd.c
index 8c7bf91..b177be9 100644
--- a/fwd.c
+++ b/fwd.c
@@ -1095,14 +1095,6 @@ static bool fwd_guest_accessible(const struct ctx *c,
return false;
}
- /* For IPv6, addr_seen starts unspecified, because we don't know what LL
- * address the guest will take until we see it. Only check against it
- * if it has been set to a real address.
- */
- if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr_seen) &&
- inany_equals6(addr, &c->ip6.addr_seen))
- return false;
-
return true;
}
@@ -1305,10 +1297,20 @@ uint8_t fwd_nat_from_host(const struct ctx *c,
}
tgt->oaddr = inany_any4;
} else {
- if (c->host_lo_to_ns_lo)
+ if (c->host_lo_to_ns_lo) {
tgt->eaddr = inany_loopback6;
- else
- tgt->eaddr.a6 = c->ip6.addr_seen;
+ } else {
+ const struct guest_addr *a;
+
+ a = fwd_select_addr(c, AF_INET6,
+ CONF_ADDR_OBSERVED,
+ CONF_ADDR_USER |
+ CONF_ADDR_HOST,
+ CONF_ADDR_LINKLOCAL);
+ if (!a)
+ return PIF_NONE;
+ tgt->eaddr = a->addr;
+ }
tgt->oaddr = inany_any6;
}
@@ -1346,10 +1348,16 @@ uint8_t fwd_nat_from_host(const struct ctx *c,
tgt->eaddr = a->addr;
} else {
- if (inany_is_linklocal6(&tgt->oaddr))
- tgt->eaddr.a6 = c->ip6.addr_ll_seen;
- else
- tgt->eaddr.a6 = c->ip6.addr_seen;
+ bool ll = inany_is_linklocal6(&tgt->oaddr);
+ uint8_t excl = ll ? ~CONF_ADDR_LINKLOCAL : CONF_ADDR_LINKLOCAL;
+ const struct guest_addr *a;
+
+ a = fwd_select_addr(c, AF_INET6, CONF_ADDR_OBSERVED,
+ CONF_ADDR_USER | CONF_ADDR_HOST, excl);
+ if (!a)
+ return PIF_NONE;
+
+ tgt->eaddr = a->addr;
}
return PIF_TAP;
diff --git a/inany.h b/inany.h
index 0450c45..ddcf93d 100644
--- a/inany.h
+++ b/inany.h
@@ -60,6 +60,9 @@ extern const union inany_addr inany_any4;
#define inany_from_v4(a4) \
((union inany_addr)INANY_INIT4((a4)))
+#define inany_from_v6(v6) \
+ ((union inany_addr){ .a6 = (v6) })
+
/** union sockaddr_inany - Either a sockaddr_in or a sockaddr_in6
* @sa_family: Address family, AF_INET or AF_INET6
* @sa: Plain struct sockaddr (useful to avoid casts)
diff --git a/migrate.c b/migrate.c
index 1e02720..2dc4dd9 100644
--- a/migrate.c
+++ b/migrate.c
@@ -56,21 +56,30 @@ struct migrate_seen_addrs_v2 {
static int seen_addrs_source_v2(struct ctx *c,
const struct migrate_stage *stage, int fd)
{
- struct migrate_seen_addrs_v2 addrs = {
- .addr6 = c->ip6.addr_seen,
- .addr6_ll = c->ip6.addr_ll_seen,
- };
+ struct migrate_seen_addrs_v2 addrs = { 0 };
const struct guest_addr *a;
(void)stage;
- /* IPv4 observed address, with fallback to configured address */
+ /* IPv4 observed address, with fallback to any other non-LL address */
a = fwd_select_addr(c, AF_INET, CONF_ADDR_OBSERVED,
CONF_ADDR_USER | CONF_ADDR_HOST,
CONF_ADDR_LINKLOCAL);
if (a)
addrs.addr4 = *inany_v4(&a->addr);
+ /* IPv6 observed address, with fallback to any other non-LL address */
+ a = fwd_select_addr(c, AF_INET6, CONF_ADDR_OBSERVED,
+ CONF_ADDR_USER | CONF_ADDR_HOST,
+ CONF_ADDR_LINKLOCAL);
+ if (a)
+ addrs.addr6 = a->addr.a6;
+
+ /* IPv6 link-local address */
+ a = fwd_get_addr(c, AF_INET6, CONF_ADDR_LINKLOCAL, 0);
+ if (a)
+ addrs.addr6_ll = a->addr.a6;
+
memcpy(addrs.mac, c->guest_mac, sizeof(addrs.mac));
if (write_all_buf(fd, &addrs, sizeof(addrs)))
@@ -91,19 +100,27 @@ static int seen_addrs_target_v2(struct ctx *c,
const struct migrate_stage *stage, int fd)
{
struct migrate_seen_addrs_v2 addrs;
+ struct in6_addr addr6, addr6_ll;
(void)stage;
if (read_all_buf(fd, &addrs, sizeof(addrs)))
return errno;
- c->ip6.addr_seen = addrs.addr6;
- c->ip6.addr_ll_seen = addrs.addr6_ll;
-
- if (addrs.addr4.s_addr)
+ if (addrs.addr4.s_addr) {
fwd_set_addr(c, &inany_from_v4(addrs.addr4),
CONF_ADDR_OBSERVED, 0);
-
+ }
+ addr6 = addrs.addr6;
+ if (!IN6_IS_ADDR_UNSPECIFIED(&addr6)) {
+ fwd_set_addr(c, &inany_from_v6(addr6),
+ CONF_ADDR_OBSERVED, 0);
+ }
+ addr6_ll = addrs.addr6_ll;
+ if (!IN6_IS_ADDR_UNSPECIFIED(&addr6_ll)) {
+ fwd_set_addr(c, &inany_from_v6(addr6_ll),
+ CONF_ADDR_OBSERVED | CONF_ADDR_LINKLOCAL, 0);
+ }
memcpy(c->guest_mac, addrs.mac, sizeof(c->guest_mac));
return 0;
diff --git a/passt.h b/passt.h
index 5da1d55..3ef84eb 100644
--- a/passt.h
+++ b/passt.h
@@ -121,8 +121,6 @@ struct ip4_ctx {
/**
* struct ip6_ctx - IPv6 execution context
- * @addr_seen: Latest IPv6 global/site address seen as source from tap
- * @addr_ll_seen: Latest IPv6 link-local address seen as source from tap
* @guest_gw: IPv6 gateway as seen by the guest
* @map_host_loopback: Outbound connections to this address are NATted to the
* host's [::1]
@@ -138,8 +136,6 @@ struct ip4_ctx {
* @no_copy_addrs: Don't copy all addresses when configuring namespace
*/
struct ip6_ctx {
- struct in6_addr addr_seen;
- struct in6_addr addr_ll_seen;
struct in6_addr guest_gw;
struct in6_addr map_host_loopback;
struct in6_addr map_guest_addr;
diff --git a/pasta.c b/pasta.c
index f949dc2..f7f1e07 100644
--- a/pasta.c
+++ b/pasta.c
@@ -366,6 +366,7 @@ static int pasta_conf_routes(struct ctx *c, sa_family_t af, int ifi,
void pasta_ns_conf(struct ctx *c)
{
unsigned int flags = IFF_UP;
+ struct in6_addr addr_ll;
int rc;
rc = nl_link_set_flags(nl_sock_ns, 1 /* lo */, IFF_UP, IFF_UP);
@@ -415,12 +416,14 @@ void pasta_ns_conf(struct ctx *c)
if (!c->ifi6)
return;
- rc = nl_addr_get_ll(nl_sock_ns, c->pasta_ifi,
- &c->ip6.addr_ll_seen);
- if (rc < 0)
+ rc = nl_addr_get_ll(nl_sock_ns, c->pasta_ifi, &addr_ll);
+ if (rc < 0) {
warn("Can't get LL address from namespace: %s",
strerror_(-rc));
-
+ } else {
+ fwd_set_addr(c, &inany_from_v6(addr_ll),
+ CONF_ADDR_LINKLOCAL | CONF_ADDR_OBSERVED, 0);
+ }
rc = nl_addr_set_ll_nodad(nl_sock_ns, c->pasta_ifi);
if (rc < 0)
warn("Can't set nodad for LL in namespace: %s",
diff --git a/tap.c b/tap.c
index 7f04e12..7f7f0ce 100644
--- a/tap.c
+++ b/tap.c
@@ -933,20 +933,13 @@ resume:
continue;
}
- if (IN6_IS_ADDR_LINKLOCAL(saddr)) {
- c->ip6.addr_ll_seen = *saddr;
+ if (!IN6_IS_ADDR_UNSPECIFIED(saddr)) {
+ uint8_t flags = CONF_ADDR_OBSERVED;
- if (IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr_seen)) {
- c->ip6.addr_seen = *saddr;
- }
-
- if (!fwd_get_addr(c, AF_INET6, 0, 0)) {
- union inany_addr addr = { .a6 = *saddr };
+ if (IN6_IS_ADDR_LINKLOCAL(saddr))
+ flags |= CONF_ADDR_LINKLOCAL;
- fwd_set_addr(c, &addr, CONF_ADDR_LINKLOCAL, 64);
- }
- } else if (!IN6_IS_ADDR_UNSPECIFIED(saddr)){
- c->ip6.addr_seen = *saddr;
+ fwd_set_addr(c, &inany_from_v6(*saddr), flags, 0);
}
if (proto == IPPROTO_ICMPV6) {
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 10/13] migrate: Update protocol to v3 for multi-address support
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (8 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 09/13] conf, pasta: Track observed guest IPv6 " Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 11/13] dhcp: Select address for DHCP distribution Jon Maloy
` (2 subsequent siblings)
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We update the migration protocol to version 3 to support distributing
multiple addresses from the unified address array. The new protocol
migrates all address entries in the array, along with their prefix
lengths and flags, and leaves it to the receiver to filter which
ones he wants to apply.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v4: - Broke out as separate commit
- Made number of transferable addresses variable
v6: - Separated internal and wire transfer format
v7: - Using uint32_t instead of uint8_t for fields in migration format
- Replaced term "wire format" with "migration format"
- Some other minor changes after feedback from Stefano.
---
migrate.c | 179 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 179 insertions(+)
diff --git a/migrate.c b/migrate.c
index 2dc4dd9..93f67ae 100644
--- a/migrate.c
+++ b/migrate.c
@@ -44,6 +44,71 @@ struct migrate_seen_addrs_v2 {
unsigned char mac[ETH_ALEN];
} __attribute__((packed));
+/**
+ * Migration format flags for address migration (v3)
+ * These are stable values - do not change existing assignments
+ */
+#define MIGRATE_ADDR_USER BIT(0)
+#define MIGRATE_ADDR_HOST BIT(1)
+#define MIGRATE_ADDR_LINKLOCAL BIT(2)
+#define MIGRATE_ADDR_OBSERVED BIT(3)
+
+/**
+ * struct migrate_addr_v3 - Migration format for a single address entry
+ * @addr: IPv6 or IPv4-mapped address (16 bytes)
+ * @prefix_len: Prefix length
+ * @flags: MIGRATE_ADDR_* flags (migration format)
+ */
+struct migrate_addr_v3 {
+ struct in6_addr addr;
+ uint32_t prefix_len;
+ uint32_t flags;
+} __attribute__((__packed__));
+
+/**
+ * flags_to_migration() - Convert internal flags to stable migration format
+ * @flags: Internal CONF_ADDR_* flags
+ *
+ * Return: Migration format MIGRATE_ADDR_* flags
+ */
+static uint8_t flags_to_migration(uint8_t flags)
+{
+ uint8_t migration = 0;
+
+ if (flags & CONF_ADDR_USER)
+ migration |= MIGRATE_ADDR_USER;
+ if (flags & CONF_ADDR_HOST)
+ migration |= MIGRATE_ADDR_HOST;
+ if (flags & CONF_ADDR_LINKLOCAL)
+ migration |= MIGRATE_ADDR_LINKLOCAL;
+ if (flags & CONF_ADDR_OBSERVED)
+ migration |= MIGRATE_ADDR_OBSERVED;
+
+ return migration;
+}
+
+/**
+ * flags_from_migration() - Convert migration format flags to internal format
+ * @migration: Migration format MIGRATE_ADDR_* flags
+ *
+ * Return: Internal CONF_ADDR_* flags
+ */
+static uint8_t flags_from_migration(uint8_t migration)
+{
+ uint8_t flags = 0;
+
+ if (migration & MIGRATE_ADDR_USER)
+ flags |= CONF_ADDR_USER;
+ if (migration & MIGRATE_ADDR_HOST)
+ flags |= CONF_ADDR_HOST;
+ if (migration & MIGRATE_ADDR_LINKLOCAL)
+ flags |= CONF_ADDR_LINKLOCAL;
+ if (migration & MIGRATE_ADDR_OBSERVED)
+ flags |= CONF_ADDR_OBSERVED;
+
+ return flags;
+}
+
/**
* seen_addrs_source_v2() - Copy and send guest observed addresses from source
* @c: Execution context
@@ -126,6 +191,99 @@ static int seen_addrs_target_v2(struct ctx *c,
return 0;
}
+/**
+ * addrs_source_v3() - Send all addresses with flags from source
+ * @c: Execution context
+ * @stage: Migration stage, unused
+ * @fd: File descriptor for state transfer
+ *
+ * Send all address entries using a stable migration format. Each field is
+ * serialised explicitly to avoid coupling the migration format to internal
+ * structure layout or flag bit assignments.
+ *
+ * Return: 0 on success, positive error code on failure
+ */
+/* cppcheck-suppress [constParameterCallback, unmatchedSuppression] */
+static int addrs_source_v3(struct ctx *c,
+ const struct migrate_stage *stage, int fd)
+{
+ uint8_t addr_count = c->addr_count;
+ const struct guest_addr *a;
+
+ (void)stage;
+
+ /* Send count first */
+ if (write_all_buf(fd, &addr_count, sizeof(addr_count)))
+ return errno;
+
+ /* Send each address in stable migration format */
+ for_each_addr(a, c->addrs, c->addr_count, 0) {
+ struct migrate_addr_v3 migration = {
+ .addr = a->addr.a6,
+ .prefix_len = htonl(a->prefix_len),
+ .flags = htonl(flags_to_migration(a->flags)),
+ };
+
+ if (write_all_buf(fd, &migration, sizeof(migration)))
+ return errno;
+ }
+
+ /* Send MAC address */
+ if (write_all_buf(fd, c->guest_mac, ETH_ALEN))
+ return errno;
+
+ return 0;
+}
+
+/**
+ * addrs_target_v3() - Receive addresses on target
+ * @c: Execution context
+ * @stage: Migration stage, unused
+ * @fd: File descriptor for state transfer
+ *
+ * Receive address entries from the stable migration format and merge only
+ * observed addresses into local array. Source sends all addresses for
+ * forward compatibility, but target only applies those marked as observed.
+ *
+ * Return: 0 on success, positive error code on failure
+ */
+static int addrs_target_v3(struct ctx *c,
+ const struct migrate_stage *stage, int fd)
+{
+ uint8_t addr_count, i;
+
+ (void)stage;
+
+ if (read_all_buf(fd, &addr_count, sizeof(addr_count)))
+ return errno;
+
+ if (addr_count > MAX_GUEST_ADDRS)
+ addr_count = MAX_GUEST_ADDRS;
+
+ /* Read each address from stable migration format */
+ for (i = 0; i < addr_count; i++) {
+ struct migrate_addr_v3 migration;
+ struct guest_addr addr;
+
+ if (read_all_buf(fd, &migration, sizeof(migration)))
+ return errno;
+
+ addr.addr.a6 = migration.addr;
+ addr.prefix_len = ntohl(migration.prefix_len);
+ addr.flags = flags_from_migration(ntohl(migration.flags));
+
+ if (addr.flags & CONF_ADDR_OBSERVED) {
+ fwd_set_addr(c, &addr.addr, addr.flags,
+ addr.prefix_len);
+ }
+ }
+
+ if (read_all_buf(fd, c->guest_mac, ETH_ALEN))
+ return errno;
+
+ return 0;
+}
+
/* Stages for version 2 */
static const struct migrate_stage stages_v2[] = {
{
@@ -146,8 +304,29 @@ static const struct migrate_stage stages_v2[] = {
{ 0 },
};
+/* Stages for version 3 (all addresses, with flags) */
+static const struct migrate_stage stages_v3[] = {
+ {
+ .name = "addresses",
+ .source = addrs_source_v3,
+ .target = addrs_target_v3,
+ },
+ {
+ .name = "prepare flows",
+ .source = flow_migrate_source_pre,
+ .target = NULL,
+ },
+ {
+ .name = "transfer flows",
+ .source = flow_migrate_source,
+ .target = flow_migrate_target,
+ },
+ { 0 },
+};
+
/* Supported encoding versions, from latest (most preferred) to oldest */
static const struct migrate_version versions[] = {
+ { 3, stages_v3, },
{ 2, stages_v2, },
/* v1 was released, but not widely used. It had bad endianness for the
* MSS and omitted timestamps, which meant it usually wouldn't work.
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 11/13] dhcp: Select address for DHCP distribution
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (9 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 10/13] migrate: Update protocol to v3 for multi-address support Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 12/13] dhcpv6: Select addresses for DHCPv6 distribution Jon Maloy
2026-04-13 0:53 ` [PATCH v7 13/13] ndp: Support advertising multiple prefixes in Router Advertisements Jon Maloy
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We introduce a CONF_ADDR_DHCP flag to mark if an added address is
eligible for DHCP advertisement. By doing this once and for all
in the fwd_set_addr() function, the DHCP code only needs to check
for this flag to know that all criteria for advertisement are
fulfilled. Hence, we update the code in dhcp.c correspondingly.
We also let the conf_print() function use this flag to determine
and print the selected address.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v6: -Split off from a commit handling both DHCP and DHCPv6
v7: -Modified DHCP advertisement eligibility criteria IPv4 addresses:
We now permit link local addresses to be eligible if they were
configured by the user.
-Adapted to previous changes in this series
---
conf.c | 5 +++--
dhcp.c | 14 +++++++++-----
fwd.c | 8 ++++++++
migrate.c | 5 +++++
passt.h | 1 +
5 files changed, 26 insertions(+), 7 deletions(-)
diff --git a/conf.c b/conf.c
index 3cb3553..612df07 100644
--- a/conf.c
+++ b/conf.c
@@ -46,6 +46,7 @@
#include "lineread.h"
#include "isolation.h"
#include "log.h"
+#include "fwd.h"
#include "vhost_user.h"
#define NETNS_RUN_DIR "/run/netns"
@@ -1181,8 +1182,8 @@ static void conf_print(const struct ctx *c)
inet_ntop(AF_INET, &c->ip4.map_host_loopback,
buf, sizeof(buf)));
- a = fwd_get_addr(c, AF_INET, 0, 0);
- if (a && !c->no_dhcp) {
+ a = fwd_get_addr(c, AF_INET, CONF_ADDR_DHCP, 0);
+ if (a) {
uint32_t mask;
mask = IN4_MASK(inany_prefix_len(&a->addr,
diff --git a/dhcp.c b/dhcp.c
index f0fa212..0f98cfc 100644
--- a/dhcp.c
+++ b/dhcp.c
@@ -31,6 +31,8 @@
#include "passt.h"
#include "tap.h"
#include "log.h"
+#include "fwd.h"
+#include "conf.h"
#include "dhcp.h"
/**
@@ -302,19 +304,18 @@ static void opt_set_dns_search(const struct ctx *c, size_t max_len)
*/
int dhcp(const struct ctx *c, struct iov_tail *data)
{
+ struct in_addr addr, mask, dst;
char macstr[ETH_ADDRSTRLEN];
const struct guest_addr *a;
size_t mlen, dlen, opt_len;
- struct in_addr mask, dst;
struct ethhdr eh_storage;
struct iphdr iph_storage;
struct udphdr uh_storage;
+ const struct udphdr *uh;
const struct ethhdr *eh;
const struct iphdr *iph;
- const struct udphdr *uh;
struct msg m_storage;
struct msg const *m;
- struct in_addr addr;
struct msg reply;
unsigned int i;
@@ -346,8 +347,11 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
m->op != BOOTREQUEST)
return -1;
- a = fwd_get_addr(c, AF_INET, 0, 0);
- assert(a);
+ /* Select address to offer */
+ a = fwd_get_addr(c, AF_INET, CONF_ADDR_DHCP, 0);
+ if (!a)
+ return -1;
+
addr = *inany_v4(&a->addr);
reply.op = BOOTREPLY;
diff --git a/fwd.c b/fwd.c
index b177be9..39e52c4 100644
--- a/fwd.c
+++ b/fwd.c
@@ -293,6 +293,14 @@ void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
return;
}
+ /* Determine advertisement eligibility */
+ if (inany_v4(addr)) {
+ if ((flags & CONF_ADDR_USER) ||
+ (flags & CONF_ADDR_HOST && !(flags & CONF_ADDR_LINKLOCAL)))
+ if (!c->no_dhcp)
+ flags |= CONF_ADDR_DHCP;
+ }
+
/* Add to head or tail, depending on flag */
if (flags & CONF_ADDR_OBSERVED) {
a = &arr[0];
diff --git a/migrate.c b/migrate.c
index 93f67ae..afdc8b4 100644
--- a/migrate.c
+++ b/migrate.c
@@ -52,6 +52,7 @@ struct migrate_seen_addrs_v2 {
#define MIGRATE_ADDR_HOST BIT(1)
#define MIGRATE_ADDR_LINKLOCAL BIT(2)
#define MIGRATE_ADDR_OBSERVED BIT(3)
+#define MIGRATE_ADDR_DHCP BIT(4)
/**
* struct migrate_addr_v3 - Migration format for a single address entry
@@ -83,6 +84,8 @@ static uint8_t flags_to_migration(uint8_t flags)
migration |= MIGRATE_ADDR_LINKLOCAL;
if (flags & CONF_ADDR_OBSERVED)
migration |= MIGRATE_ADDR_OBSERVED;
+ if (flags & CONF_ADDR_DHCP)
+ migration |= MIGRATE_ADDR_DHCP;
return migration;
}
@@ -105,6 +108,8 @@ static uint8_t flags_from_migration(uint8_t migration)
flags |= CONF_ADDR_LINKLOCAL;
if (migration & MIGRATE_ADDR_OBSERVED)
flags |= CONF_ADDR_OBSERVED;
+ if (migration & MIGRATE_ADDR_DHCP)
+ flags |= CONF_ADDR_DHCP;
return flags;
}
diff --git a/passt.h b/passt.h
index 3ef84eb..9508c2a 100644
--- a/passt.h
+++ b/passt.h
@@ -83,6 +83,7 @@ struct guest_addr {
#define CONF_ADDR_GENERATED BIT(2) /* Generated by PASST/PASTA */
#define CONF_ADDR_LINKLOCAL BIT(3) /* Link-local address */
#define CONF_ADDR_OBSERVED BIT(4) /* Seen in guest traffic */
+#define CONF_ADDR_DHCP BIT(5) /* Advertise via DHCP (IPv4) */
};
/**
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 12/13] dhcpv6: Select addresses for DHCPv6 distribution
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (10 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 11/13] dhcp: Select address for DHCP distribution Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
2026-04-13 0:53 ` [PATCH v7 13/13] ndp: Support advertising multiple prefixes in Router Advertisements Jon Maloy
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We introduce a CONF_ADDR_DHCPV6 flag to mark if an added address is
eligible for DHCP advertisement. By doing this once and for all
in the fwd_set_addr() function, the DHCPv6 code only needs to check
for this flag to know that all criteria for advertisement are fulfilled.
We update the code in dhcpv6.c both to use the new flag and to make
it possible to send multiple addresses in a single reply message,
per RFC 8415.
We also let the conf_print() function use this flag to identify and
print the eligible addresses.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v6: -Refactored the DHCPv6 response structure to use a variable-length
buffer for IA_ADDR options, hopefully making this part of the code
slightly clearer.
v7: -Adapted to previous changes in this series
-Some minor changes based on feedback
---
conf.c | 35 ++++++++++++++++----
dhcpv6.c | 96 ++++++++++++++++++++++++++++++++-----------------------
fwd.c | 3 ++
migrate.c | 5 +++
passt.h | 1 +
5 files changed, 93 insertions(+), 47 deletions(-)
diff --git a/conf.c b/conf.c
index 612df07..7c705de 100644
--- a/conf.c
+++ b/conf.c
@@ -1216,21 +1216,42 @@ static void conf_print(const struct ctx *c)
}
if (c->ifi6) {
+ bool has_dhcpv6 = false;
+ const char *head;
+
if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_host_loopback))
info(" NAT to host ::1: %s",
inet_ntop(AF_INET6, &c->ip6.map_host_loopback,
buf, sizeof(buf)));
- if (!c->no_ndp && !c->no_dhcpv6)
- info("NDP/DHCPv6:");
- else if (!c->no_dhcpv6)
- info("DHCPv6:");
- else if (!c->no_ndp)
- info("NDP:");
- else
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
+ if (a->flags & CONF_ADDR_DHCPV6)
+ has_dhcpv6 = true;
+ }
+
+ if (c->no_ndp && !has_dhcpv6)
goto dns6;
a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
+ if (!c->no_ndp && a) {
+ info("NDP:");
+ info(" assign: %s",
+ inany_ntop(&a->addr, buf, sizeof(buf)));
+ }
+
+ if (has_dhcpv6) {
+ info("DHCPv6:");
+ head = "assign: ";
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
+ if (!(a->flags & CONF_ADDR_DHCPV6))
+ continue;
+ info(" %s: %s/%d", head,
+ inany_ntop(&a->addr, buf, sizeof(buf)),
+ a->prefix_len);
+ head = " ";
+ }
+ }
+
if (a)
info(" assign: %s",
inany_ntop(&a->addr, buf, sizeof(buf)));
diff --git a/dhcpv6.c b/dhcpv6.c
index 447aaba..546a3ea 100644
--- a/dhcpv6.c
+++ b/dhcpv6.c
@@ -31,6 +31,8 @@
#include "passt.h"
#include "tap.h"
#include "log.h"
+#include "fwd.h"
+#include "conf.h"
/**
* struct opt_hdr - DHCPv6 option header
@@ -202,56 +204,35 @@ struct msg_hdr {
uint32_t xid:24;
} __attribute__((__packed__));
+/* Maximum variable part size: ia_addrs + client_id + dns + search + fqdn */
+#define RESP_VAR_MAX (MAX_GUEST_ADDRS * sizeof(struct opt_ia_addr) + \
+ sizeof(struct opt_client_id) + \
+ sizeof(struct opt_dns_servers) + \
+ sizeof(struct opt_dns_search) + \
+ sizeof(struct opt_client_fqdn))
+
/**
* struct resp_t - Normal advertise and reply message
* @hdr: DHCP message header
* @server_id: Server Identifier option
* @ia_na: Non-temporary Address option
- * @ia_addr: Address for IA_NA
- * @client_id: Client Identifier, variable length
- * @dns_servers: DNS Recursive Name Server, here just for storage size
- * @dns_search: Domain Search List, here just for storage size
- * @client_fqdn: Client FQDN, variable length
+ * @var: Variable part: IA_ADDRs, client_id, dns, search, fqdn
*/
static struct resp_t {
struct msg_hdr hdr;
struct opt_server_id server_id;
struct opt_ia_na ia_na;
- struct opt_ia_addr ia_addr;
- struct opt_client_id client_id;
- struct opt_dns_servers dns_servers;
- struct opt_dns_search dns_search;
- struct opt_client_fqdn client_fqdn;
+ uint8_t var[RESP_VAR_MAX];
} __attribute__((__packed__)) resp = {
{ 0 },
SERVER_ID,
- { { OPT_IA_NA, OPT_SIZE_CONV(sizeof(struct opt_ia_na) +
- sizeof(struct opt_ia_addr) -
- sizeof(struct opt_hdr)) },
+ { { OPT_IA_NA, 0 }, /* Length set dynamically */
1, (uint32_t)~0U, (uint32_t)~0U
},
- { { OPT_IAAADR, OPT_SIZE(ia_addr) },
- IN6ADDR_ANY_INIT, (uint32_t)~0U, (uint32_t)~0U
- },
-
- { { OPT_CLIENTID, 0, },
- { 0 }
- },
-
- { { OPT_DNS_SERVERS, 0, },
- { IN6ADDR_ANY_INIT }
- },
-
- { { OPT_DNS_SEARCH, 0, },
- { 0 },
- },
-
- { { OPT_CLIENT_FQDN, 0, },
- 0, { 0 },
- },
+ { 0 }, /* Variable part filled dynamically */
};
static const struct opt_status_code sc_not_on_link = {
@@ -540,6 +521,42 @@ static size_t dhcpv6_client_fqdn_fill(const struct iov_tail *data,
return offset + sizeof(struct opt_hdr) + opt_len;
}
+/**
+ * dhcpv6_ia_addr_fill() - Fill IA_ADDR options for all suitable addresses
+ * @c: Execution context
+ *
+ * Fills IA_ADDRs in resp.var with all non-linklocal host or user-provided
+ * addresses and updates resp.ia_na.hdr.l with the correct length.
+ *
+ * Return: number of addresses filled
+ */
+static int dhcpv6_ia_addr_fill(const struct ctx *c)
+{
+ struct opt_ia_addr *ia_addr = (struct opt_ia_addr *)resp.var;
+ const struct guest_addr *e;
+ int count = 0;
+
+ for_each_addr(e, c->addrs, c->addr_count, AF_INET6) {
+ if (!(e->flags & CONF_ADDR_DHCPV6))
+ continue;
+
+ ia_addr[count].hdr.t = OPT_IAAADR;
+ ia_addr[count].hdr.l = htons(sizeof(struct opt_ia_addr) -
+ sizeof(struct opt_hdr));
+ ia_addr[count].addr = e->addr.a6;
+ ia_addr[count].pref_lifetime = (uint32_t)~0U;
+ ia_addr[count].valid_lifetime = (uint32_t)~0U;
+ count++;
+ }
+
+ /* Update IA_NA length: header fields + all IA_ADDRs */
+ resp.ia_na.hdr.l = htons(sizeof(struct opt_ia_na) -
+ sizeof(struct opt_hdr) +
+ count * sizeof(struct opt_ia_addr));
+
+ return count;
+}
+
/**
* dhcpv6() - Check if this is a DHCPv6 message, reply as needed
* @c: Execution context
@@ -573,6 +590,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
const struct msg_hdr *mh;
struct udphdr uh_storage;
const struct udphdr *uh;
+ int addr_count;
size_t mlen, n;
a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
@@ -618,6 +636,7 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
if (ia && ntohs(ia->hdr.l) < MIN(OPT_VSIZE(ia_na), OPT_VSIZE(ia_ta)))
return -1;
+ addr_count = dhcpv6_ia_addr_fill(c);
resp.hdr.type = TYPE_REPLY;
switch (mh->type) {
case TYPE_REQUEST:
@@ -671,12 +690,14 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
if (ia)
resp.ia_na.iaid = ((struct opt_ia_na *)ia)->iaid;
+ /* Client_id goes right after the used IA_ADDRs */
+ n = offsetof(struct resp_t, var) +
+ addr_count * sizeof(struct opt_ia_addr);
iov_to_buf(&client_id_base.iov[0], client_id_base.cnt,
- client_id_base.off, &resp.client_id,
+ client_id_base.off, (char *)&resp + n,
ntohs(client_id->l) + sizeof(struct opt_hdr));
- n = offsetof(struct resp_t, client_id) +
- sizeof(struct opt_hdr) + ntohs(client_id->l);
+ n += sizeof(struct opt_hdr) + ntohs(client_id->l);
n = dhcpv6_dns_fill(c, (char *)&resp, n);
n = dhcpv6_client_fqdn_fill(data, c, (char *)&resp, n);
@@ -693,7 +714,6 @@ int dhcpv6(struct ctx *c, struct iov_tail *data,
*/
void dhcpv6_init(const struct ctx *c)
{
- const struct guest_addr *a;
time_t y2k = 946684800; /* Epoch to 2000-01-01T00:00:00Z, no mktime() */
uint32_t duid_time;
@@ -706,8 +726,4 @@ void dhcpv6_init(const struct ctx *c)
c->our_tap_mac, sizeof(c->our_tap_mac));
memcpy(resp_not_on_link.server_id.duid_lladdr,
c->our_tap_mac, sizeof(c->our_tap_mac));
-
- a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
- if (a)
- resp.ia_addr.addr = a->addr.a6;
}
diff --git a/fwd.c b/fwd.c
index 39e52c4..2b444fb 100644
--- a/fwd.c
+++ b/fwd.c
@@ -299,6 +299,9 @@ void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
(flags & CONF_ADDR_HOST && !(flags & CONF_ADDR_LINKLOCAL)))
if (!c->no_dhcp)
flags |= CONF_ADDR_DHCP;
+ } else if (!(flags & CONF_ADDR_LINKLOCAL)) {
+ if (!c->no_dhcpv6)
+ flags |= CONF_ADDR_DHCPV6;
}
/* Add to head or tail, depending on flag */
diff --git a/migrate.c b/migrate.c
index afdc8b4..adcbc63 100644
--- a/migrate.c
+++ b/migrate.c
@@ -53,6 +53,7 @@ struct migrate_seen_addrs_v2 {
#define MIGRATE_ADDR_LINKLOCAL BIT(2)
#define MIGRATE_ADDR_OBSERVED BIT(3)
#define MIGRATE_ADDR_DHCP BIT(4)
+#define MIGRATE_ADDR_DHCPV6 BIT(5)
/**
* struct migrate_addr_v3 - Migration format for a single address entry
@@ -86,6 +87,8 @@ static uint8_t flags_to_migration(uint8_t flags)
migration |= MIGRATE_ADDR_OBSERVED;
if (flags & CONF_ADDR_DHCP)
migration |= MIGRATE_ADDR_DHCP;
+ if (flags & CONF_ADDR_DHCPV6)
+ migration |= MIGRATE_ADDR_DHCPV6;
return migration;
}
@@ -110,6 +113,8 @@ static uint8_t flags_from_migration(uint8_t migration)
flags |= CONF_ADDR_OBSERVED;
if (migration & MIGRATE_ADDR_DHCP)
flags |= CONF_ADDR_DHCP;
+ if (migration & MIGRATE_ADDR_DHCPV6)
+ flags |= CONF_ADDR_DHCPV6;
return flags;
}
diff --git a/passt.h b/passt.h
index 9508c2a..028eb7c 100644
--- a/passt.h
+++ b/passt.h
@@ -84,6 +84,7 @@ struct guest_addr {
#define CONF_ADDR_LINKLOCAL BIT(3) /* Link-local address */
#define CONF_ADDR_OBSERVED BIT(4) /* Seen in guest traffic */
#define CONF_ADDR_DHCP BIT(5) /* Advertise via DHCP (IPv4) */
+#define CONF_ADDR_DHCPV6 BIT(6) /* Advertise via DHCPv6 (IPv6) */
};
/**
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v7 13/13] ndp: Support advertising multiple prefixes in Router Advertisements
2026-04-13 0:53 [PATCH v7 00/13] Introduce multiple addresses and late binding Jon Maloy
` (11 preceding siblings ...)
2026-04-13 0:53 ` [PATCH v7 12/13] dhcpv6: Select addresses for DHCPv6 distribution Jon Maloy
@ 2026-04-13 0:53 ` Jon Maloy
12 siblings, 0 replies; 14+ messages in thread
From: Jon Maloy @ 2026-04-13 0:53 UTC (permalink / raw)
To: sbrivio, david, jmaloy, passt-dev
We extend NDP to advertise all suitable IPv6 prefixes in Router
Advertisements, per RFC 4861. Observed and link-local addresses,
plus addresses with a prefix length != 64, are excluded.
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
v6: -Adapted to previous changes in series
v7: -Adapted to previous changes in series
-Use struct initializer for source link-layer address option
-Other minor fixes based on feedback from Stefano
---
conf.c | 19 ++++++---
fwd.c | 4 ++
migrate.c | 5 +++
ndp.c | 123 +++++++++++++++++++++++++++++++++++++-----------------
passt.h | 3 +-
5 files changed, 108 insertions(+), 46 deletions(-)
diff --git a/conf.c b/conf.c
index 7c705de..97c66c9 100644
--- a/conf.c
+++ b/conf.c
@@ -1216,7 +1216,7 @@ static void conf_print(const struct ctx *c)
}
if (c->ifi6) {
- bool has_dhcpv6 = false;
+ bool has_ndp = false, has_dhcpv6 = false;
const char *head;
if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_host_loopback))
@@ -1225,18 +1225,25 @@ static void conf_print(const struct ctx *c)
buf, sizeof(buf)));
for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
+ if (a->flags & CONF_ADDR_SLAAC)
+ has_ndp = true;
if (a->flags & CONF_ADDR_DHCPV6)
has_dhcpv6 = true;
}
- if (c->no_ndp && !has_dhcpv6)
+ if (!has_ndp && !has_dhcpv6)
goto dns6;
- a = fwd_get_addr(c, AF_INET6, 0, CONF_ADDR_LINKLOCAL);
- if (!c->no_ndp && a) {
+ if (has_ndp) {
info("NDP:");
- info(" assign: %s",
- inany_ntop(&a->addr, buf, sizeof(buf)));
+ head = "assign: ";
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
+ if (!(a->flags & CONF_ADDR_SLAAC))
+ continue;
+ inany_ntop(&a->addr, buf, sizeof(buf));
+ info(" %s: %s/%d", head, buf, a->prefix_len);
+ head = " ";
+ }
}
if (has_dhcpv6) {
diff --git a/fwd.c b/fwd.c
index 2b444fb..2bc8e33 100644
--- a/fwd.c
+++ b/fwd.c
@@ -302,6 +302,10 @@ void fwd_set_addr(struct ctx *c, const union inany_addr *addr,
} else if (!(flags & CONF_ADDR_LINKLOCAL)) {
if (!c->no_dhcpv6)
flags |= CONF_ADDR_DHCPV6;
+
+ /* NDP/RA only if prefix is /64 */
+ if (!c->no_ndp && prefix_len == 64)
+ flags |= CONF_ADDR_SLAAC;
}
/* Add to head or tail, depending on flag */
diff --git a/migrate.c b/migrate.c
index adcbc63..f019924 100644
--- a/migrate.c
+++ b/migrate.c
@@ -54,6 +54,7 @@ struct migrate_seen_addrs_v2 {
#define MIGRATE_ADDR_OBSERVED BIT(3)
#define MIGRATE_ADDR_DHCP BIT(4)
#define MIGRATE_ADDR_DHCPV6 BIT(5)
+#define MIGRATE_ADDR_SLAAC BIT(6)
/**
* struct migrate_addr_v3 - Migration format for a single address entry
@@ -89,6 +90,8 @@ static uint8_t flags_to_migration(uint8_t flags)
migration |= MIGRATE_ADDR_DHCP;
if (flags & CONF_ADDR_DHCPV6)
migration |= MIGRATE_ADDR_DHCPV6;
+ if (flags & CONF_ADDR_SLAAC)
+ migration |= MIGRATE_ADDR_SLAAC;
return migration;
}
@@ -115,6 +118,8 @@ static uint8_t flags_from_migration(uint8_t migration)
flags |= CONF_ADDR_DHCP;
if (migration & MIGRATE_ADDR_DHCPV6)
flags |= CONF_ADDR_DHCPV6;
+ if (migration & MIGRATE_ADDR_SLAAC)
+ flags |= CONF_ADDR_SLAAC;
return flags;
}
diff --git a/ndp.c b/ndp.c
index 3750fc5..bb8374a 100644
--- a/ndp.c
+++ b/ndp.c
@@ -32,6 +32,8 @@
#include "passt.h"
#include "tap.h"
#include "log.h"
+#include "fwd.h"
+#include "conf.h"
#define RT_LIFETIME 65535
@@ -99,6 +101,16 @@ struct opt_prefix_info {
uint32_t reserved;
} __attribute__((packed));
+/**
+ * struct ndp_prefix - Prefix Information option with prefix
+ * @info: Prefix Information option header
+ * @prefix: IPv6 prefix
+ */
+struct ndp_prefix {
+ struct opt_prefix_info info;
+ struct in6_addr prefix;
+} __attribute__((__packed__));
+
/**
* struct opt_mtu - Maximum transmission unit (MTU) option
* @header: Option header
@@ -140,27 +152,23 @@ struct opt_dnssl {
} __attribute__((packed));
/**
- * struct ndp_ra - NDP Router Advertisement (RA) message
+ * struct ndp_ra_hdr - NDP Router Advertisement fixed header
* @ih: ICMPv6 header
* @reachable: Reachability time, after confirmation (ms)
* @retrans: Time between retransmitted NS messages (ms)
- * @prefix_info: Prefix Information option
- * @prefix: IPv6 prefix
- * @mtu: MTU option
- * @source_ll: Target link-layer address
- * @var: Variable fields
*/
-struct ndp_ra {
+struct ndp_ra_hdr {
struct icmp6hdr ih;
uint32_t reachable;
uint32_t retrans;
- struct opt_prefix_info prefix_info;
- struct in6_addr prefix;
- struct opt_l2_addr source_ll;
+} __attribute__((__packed__));
- unsigned char var[sizeof(struct opt_mtu) + sizeof(struct opt_rdnss) +
- sizeof(struct opt_dnssl)];
-} __attribute__((packed, aligned(__alignof__(struct in6_addr))));
+/* Maximum RA message size: hdr + prefixes + source_ll + mtu + rdnss + dnssl */
+#define NDP_RA_MAX_SIZE (sizeof(struct ndp_ra_hdr) + \
+ MAX_GUEST_ADDRS * sizeof(struct ndp_prefix) + \
+ sizeof(struct opt_l2_addr) + \
+ sizeof(struct opt_mtu) + sizeof(struct opt_rdnss) + \
+ sizeof(struct opt_dnssl))
/**
* struct ndp_ns - NDP Neighbor Solicitation (NS) message
@@ -231,6 +239,42 @@ void ndp_unsolicited_na(const struct ctx *c, const struct in6_addr *addr)
ndp_na(c, &in6addr_ll_all_nodes, addr);
}
+/**
+ * ndp_prefix_fill() - Fill prefix options for all suitable addresses
+ * @c: Execution context
+ * @buf: Buffer to write prefix options into
+ *
+ * Fills buffer with Prefix Information options for all non-linklocal,
+ * non-observed addresses with prefix_len == 64
+ *
+ * Return: number of bytes written
+ */
+static size_t ndp_prefix_fill(const struct ctx *c, unsigned char *buf)
+{
+ const struct guest_addr *a;
+ struct ndp_prefix *p;
+ size_t offset = 0;
+
+ for_each_addr(a, c->addrs, c->addr_count, AF_INET6) {
+ if (!(a->flags & CONF_ADDR_SLAAC))
+ continue;
+
+ p = (struct ndp_prefix *)(buf + offset);
+ p->info.header.type = OPT_PREFIX_INFO;
+ p->info.header.len = 4; /* 4 * 8 = 32 bytes */
+ p->info.prefix_len = 64;
+ p->info.prefix_flags = 0xc0; /* L, A flags */
+ p->info.valid_lifetime = ~0U;
+ p->info.pref_lifetime = ~0U;
+ p->info.reserved = 0;
+ p->prefix = a->addr.a6;
+
+ offset += sizeof(struct ndp_prefix);
+ }
+
+ return offset;
+}
+
/**
* ndp_ra() - Send an NDP Router Advertisement (RA) message
* @c: Execution context
@@ -238,7 +282,15 @@ void ndp_unsolicited_na(const struct ctx *c, const struct in6_addr *addr)
*/
static void ndp_ra(const struct ctx *c, const struct in6_addr *dst)
{
- struct ndp_ra ra = {
+ unsigned char buf[NDP_RA_MAX_SIZE]
+ __attribute__((__aligned__(__alignof__(struct in6_addr))));
+ struct ndp_ra_hdr *hdr = (struct ndp_ra_hdr *)buf;
+ struct opt_l2_addr *source_ll;
+ unsigned char *ptr;
+ size_t prefix_len;
+
+ /* Build RA header */
+ *hdr = (struct ndp_ra_hdr){
.ih = {
.icmp6_type = RA,
.icmp6_code = 0,
@@ -247,31 +299,26 @@ static void ndp_ra(const struct ctx *c, const struct in6_addr *dst)
.icmp6_rt_lifetime = htons_constant(RT_LIFETIME),
.icmp6_addrconf_managed = 1,
},
- .prefix_info = {
- .header = {
- .type = OPT_PREFIX_INFO,
- .len = 4,
- },
- .prefix_len = 64,
- .prefix_flags = 0xc0, /* prefix flags: L, A */
- .valid_lifetime = ~0U,
- .pref_lifetime = ~0U,
- },
- .source_ll = {
- .header = {
- .type = OPT_SRC_L2_ADDR,
- .len = 1,
- },
- },
};
- const struct guest_addr *a = fwd_get_addr(c, AF_INET6, 0, 0);
- unsigned char *ptr = NULL;
- ASSERT(a);
-
- ra.prefix = a->addr.a6;
+ /* Fill prefix options */
+ prefix_len = ndp_prefix_fill(c, (unsigned char *)(hdr + 1));
+ if (prefix_len == 0) {
+ /* No suitable prefixes to advertise */
+ return;
+ }
- ptr = &ra.var[0];
+ /* Add source link-layer address option */
+ ptr = (unsigned char *)(hdr + 1) + prefix_len;
+ source_ll = (struct opt_l2_addr *)ptr;
+ *source_ll = (struct opt_l2_addr) {
+ .header = {
+ .type = OPT_SRC_L2_ADDR,
+ .len = 1,
+ },
+ };
+ memcpy(source_ll->mac, c->our_tap_mac, ETH_ALEN);
+ ptr += sizeof(struct opt_l2_addr);
if (c->mtu) {
struct opt_mtu *mtu = (struct opt_mtu *)ptr;
@@ -345,10 +392,8 @@ static void ndp_ra(const struct ctx *c, const struct in6_addr *dst)
}
}
- memcpy(&ra.source_ll.mac, c->our_tap_mac, ETH_ALEN);
-
/* NOLINTNEXTLINE(clang-analyzer-security.PointerSub) */
- ndp_send(c, dst, &ra, ptr - (unsigned char *)&ra);
+ ndp_send(c, dst, buf, ptr - buf);
}
/**
diff --git a/passt.h b/passt.h
index 028eb7c..2c633e4 100644
--- a/passt.h
+++ b/passt.h
@@ -84,7 +84,8 @@ struct guest_addr {
#define CONF_ADDR_LINKLOCAL BIT(3) /* Link-local address */
#define CONF_ADDR_OBSERVED BIT(4) /* Seen in guest traffic */
#define CONF_ADDR_DHCP BIT(5) /* Advertise via DHCP (IPv4) */
-#define CONF_ADDR_DHCPV6 BIT(6) /* Advertise via DHCPv6 (IPv6) */
+#define CONF_ADDR_DHCPV6 BIT(6) /* Advertise via DHCPv6 */
+#define CONF_ADDR_SLAAC BIT(7) /* Advertise via NDP/RA (/64) */
};
/**
--
2.52.0
^ permalink raw reply [flat|nested] 14+ messages in thread