net: add AF_PACKET multicast dumps

RTM_GETMULTICAST dumps IPv4 and IPv6 multicast group memberships, but
the device multicast list (dev->mc) is only available through
/proc/net/dev_mcast, so "ip maddr show" still has to parse procfs for
its link-layer entries.

Handle RTM_GETMULTICAST dumps with ifa_family set to AF_PACKET next to
the dev->mc helpers in dev_addr_lists.c and report every entry of
dev->mc in the existing ifaddrmsg format:

  - IFA_MULTICAST carries the raw link-layer address
  - IFA_MC_USERS carries the entry reference count
  - IFA_F_GLOBAL in IFA_FLAGS reports netdev_hw_addr::global_use, set
    by dev_mc_add_global() (SIOCADDMULTI) and dev_mc_add_excl()
    ("bridge fdb add ... self"), i.e. entries added explicitly rather
    than by a protocol join. This is the static column of
    /proc/net/dev_mcast
  - ifa_scope is RT_SCOPE_LINK

This covers every column of /proc/net/dev_mcast. AF_PACKET is the
family iproute2 already uses for link-layer addresses ("ip -0").

The default FDB dump also walks dev->mc, but only for Ethernet devices
and only if the driver uses it, vxlan for example does not, and it has
no users count or global_use bit. Extending it would change "bridge fdb
show" output and add NDA_* attributes.

Requests are always validated, there are no legacy users: prefixlen,
flags and scope must be zero, ifa_index selects one device and
IFA_TARGET_NETNSID is the only attribute accepted. The dump runs under
RCU and netif_addr_lock_bh() without RTNL. cb->seq is set from the
dev->mc generation counter and dev_base_seq before each round and
checked after it, so an entry added or removed since the previous
round sets NLM_F_DUMP_INTR. A round without a message skips the check
and cb->seq is set once more after the round, so the NLMSG_DONE check
reports a change made during the last round or before an empty one.

Signed-off-by: Yuyang Huang <sigefriedhyy@gmail.com>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://patch.msgid.link/20261012011707.3378-5-sigefriedhyy@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

4 files changed, 196 insertions, 0 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f52c46e28e3a..79f9ee0cf799 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5181,6 +5181,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from);
 void dev_mc_unsync(struct net_device *to, struct net_device *from);
 void dev_mc_flush(struct net_device *dev);
 void dev_mc_init(struct net_device *dev);
+int dev_mc_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
 /**
  *  __dev_mc_sync - Synchronize device's multicast list
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index 7fb630b7fe31..0a1ad9ebb47b 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -57,6 +57,7 @@ enum {
 #define IFA_F_NOPREFIXROUTE	0x200
 #define IFA_F_MCAUTOJOIN	0x400
 #define IFA_F_STABLE_PRIVACY	0x800
+#define IFA_F_GLOBAL		0x1000
 
 struct ifa_cacheinfo {
 	__u32	ifa_prefered;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 3ab053cbf8b9..d827cc21867b 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -10,8 +10,12 @@
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/export.h>
+#include <linux/if_addr.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <net/netlink.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
 #include <kunit/visibility.h>
 
 #include "dev.h"
@@ -1215,6 +1219,194 @@ void dev_mc_init(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_mc_init);
 
+static int dev_mc_fill_addr(struct sk_buff *skb, const struct net_device *dev,
+			    const struct netdev_hw_addr *ha, u32 portid,
+			    u32 seq, unsigned int flags, int netnsid)
+{
+	struct ifaddrmsg *ifm;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(skb, portid, seq, RTM_GETMULTICAST, sizeof(*ifm),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	ifm = nlmsg_data(nlh);
+	ifm->ifa_family = AF_PACKET;
+	ifm->ifa_prefixlen = 0;
+	ifm->ifa_flags = 0;
+	ifm->ifa_scope = RT_SCOPE_LINK;
+	ifm->ifa_index = dev->ifindex;
+
+	if ((netnsid >= 0 &&
+	     nla_put_s32(skb, IFA_TARGET_NETNSID, netnsid)) ||
+	    nla_put(skb, IFA_MULTICAST, dev->addr_len, ha->addr) ||
+	    nla_put_u32(skb, IFA_MC_USERS, ha->refcount) ||
+	    nla_put_u32(skb, IFA_FLAGS, ha->global_use ? IFA_F_GLOBAL : 0)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+/* Combine dev_mc_genid and dev_base_seq to detect changes, like
+ * inet_base_seq().
+ */
+static u32 dev_mc_base_seq(const struct net *net)
+{
+	u32 res = atomic_read(&net->dev_mc_genid) +
+		  READ_ONCE(net->dev_base_seq);
+
+	/* Must not return 0 (see nl_dump_check_consistent()). */
+	if (!res)
+		res = 0x80000000;
+	return res;
+}
+
+static int dev_mc_dump_dev(struct net_device *dev, struct sk_buff *skb,
+			   struct netlink_callback *cb, int *s_addr_idx,
+			   unsigned int flags, int netnsid)
+{
+	struct netdev_hw_addr *ha;
+	int addr_idx = 0;
+	int err = 0;
+
+	netif_addr_lock_bh(dev);
+	netdev_for_each_mc_addr(ha, dev) {
+		if (addr_idx < *s_addr_idx) {
+			addr_idx++;
+			continue;
+		}
+		err = dev_mc_fill_addr(skb, dev, ha, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, flags, netnsid);
+		if (err < 0)
+			break;
+		addr_idx++;
+	}
+	netif_addr_unlock_bh(dev);
+
+	*s_addr_idx = err < 0 ? addr_idx : 0;
+
+	return err;
+}
+
+struct dev_mc_dump_filter {
+	struct net *tgt_net;
+	netns_tracker ns_tracker;
+	int netnsid;
+	int ifindex;
+};
+
+static const struct nla_policy dev_mc_dump_policy[IFA_MAX + 1] = {
+	[IFA_TARGET_NETNSID]	= { .type = NLA_S32 },
+};
+
+static int dev_mc_valid_dump_req(const struct nlmsghdr *nlh, struct sock *sk,
+				 struct dev_mc_dump_filter *filter,
+				 struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFA_MAX + 1];
+	struct ifaddrmsg *ifm;
+	int err;
+
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid header for multicast dump request");
+		return -EINVAL;
+	}
+
+	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid values in multicast dump header");
+		return -EINVAL;
+	}
+
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX,
+			  dev_mc_dump_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (tb[IFA_TARGET_NETNSID]) {
+		struct net *net;
+
+		filter->netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
+		net = rtnl_get_net_ns_capable(sk, filter->netnsid);
+		if (IS_ERR(net)) {
+			NL_SET_ERR_MSG(extack,
+				       "Invalid target network namespace id");
+			return PTR_ERR(net);
+		}
+		netns_tracker_alloc(net, &filter->ns_tracker, GFP_KERNEL);
+		filter->tgt_net = net;
+	}
+
+	filter->ifindex = ifm->ifa_index;
+
+	return 0;
+}
+
+int dev_mc_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct dev_mc_dump_filter filter = {
+		.tgt_net = sock_net(skb->sk),
+		.netnsid = -1,
+	};
+	unsigned int flags = NLM_F_MULTI;
+	struct {
+		unsigned long ifindex;
+		int addr_idx;
+	} *ctx = (void *)cb->ctx;
+	unsigned long s_ifindex;
+	struct net_device *dev;
+	int err;
+
+	err = dev_mc_valid_dump_req(cb->nlh, skb->sk, &filter, cb->extack);
+	if (err < 0)
+		return err;
+
+	rcu_read_lock();
+
+	cb->seq = dev_mc_base_seq(filter.tgt_net);
+	if (filter.ifindex) {
+		cb->answer_flags |= NLM_F_DUMP_FILTERED;
+		flags |= NLM_F_DUMP_FILTERED;
+		dev = dev_get_by_index_rcu(filter.tgt_net, filter.ifindex);
+		if (dev)
+			err = dev_mc_dump_dev(dev, skb, cb, &ctx->addr_idx,
+					      flags, filter.netnsid);
+		else
+			err = -ENODEV;
+	} else {
+		s_ifindex = ctx->ifindex;
+		for_each_netdev_dump(filter.tgt_net, dev, ctx->ifindex) {
+			/* The device the dump stopped at is gone, do not
+			 * skip entries of the next one.
+			 */
+			if (dev->ifindex != s_ifindex)
+				ctx->addr_idx = 0;
+			err = dev_mc_dump_dev(dev, skb, cb, &ctx->addr_idx,
+					      flags, filter.netnsid);
+			if (err < 0)
+				break;
+		}
+	}
+	/* A round without a message has nothing to flag, the NLMSG_DONE
+	 * check then compares against the previous round.
+	 */
+	if (skb->len)
+		nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+	/* Let the NLMSG_DONE check see changes made during the last round */
+	cb->seq = dev_mc_base_seq(filter.tgt_net);
+
+	rcu_read_unlock();
+	if (filter.netnsid >= 0)
+		put_net_track(filter.tgt_net, &filter.ns_tracker);
+	return err;
+}
+
 static int netif_addr_lists_snapshot(struct net_device *dev,
 				     struct netdev_hw_addr_list *uc_snap,
 				     struct netdev_hw_addr_list *mc_snap,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d73dbc2c8ba0..e141340172ce 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -7288,6 +7288,8 @@ static const struct rtnl_msg_handler rtnetlink_rtnl_msg_handlers[] __initconst =
 	{.msgtype = RTM_SETSTATS, .doit = rtnl_stats_set},
 	{.msgtype = RTM_NEWLINKPROP, .doit = rtnl_newlinkprop},
 	{.msgtype = RTM_DELLINKPROP, .doit = rtnl_dellinkprop},
+	{.protocol = PF_PACKET, .msgtype = RTM_GETMULTICAST,
+	 .dumpit = dev_mc_dump, .flags = RTNL_FLAG_DUMP_UNLOCKED},
 	{.protocol = PF_BRIDGE, .msgtype = RTM_GETLINK,
 	 .dumpit = rtnl_bridge_getlink},
 	{.protocol = PF_BRIDGE, .msgtype = RTM_DELLINK,