Thread (14 messages) flat view 14 messages, 4 authors, 5d ago
COOLING5d

Revision v3 of 5 in this series.

Revisions (5)
  1. v1 [diff vs current]
  2. v2 [diff vs current]
  3. v3 current
  4. v4 [diff vs current]
  5. v5 [diff vs current]

[PATCH net-next v3 2/4] rtnetlink: add AF_PACKET multicast dumps

From: Yuyang Huang <hidden>
Date: 2026-09-09 13:33:06
Also in: linux-kselftest, lkml
Subsystem: networking drivers, networking [general], the rest · Maintainers: Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds

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 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"), and
AF_UNSPEC keeps its "all families" meaning from RTM_GETADDR.

The default FDB dump also walks dev->mc, but only for Ethernet devices
without an ndo_fdb_dump of their own, so bridge, vxlan or macvlan
devices never show their multicast filter there, and it has no users
count or global_use bit. Extending it would change "bridge fdb show"
output and add NDA_* attributes.

There are no legacy users of AF_PACKET requests, so they are always
validated: prefixlen, flags and scope must be zero and a non-zero
ifa_index restricts the dump to that device. IFA_TARGET_NETNSID selects
another netns like the IPv4 and IPv6 dumps and is the only attribute
accepted. The dump runs under RCU and netif_addr_lock_bh() and does not
need RTNL.

Signed-off-by: Yuyang Huang <redacted>
---
 include/uapi/linux/if_addr.h |   1 +
 net/core/rtnetlink.c         | 165 +++++++++++++++++++++++++++++++++++
 2 files changed, 166 insertions(+)
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/rtnetlink.c b/net/core/rtnetlink.c
index 81c5a6104dea..f54e9cb3bf30 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4566,6 +4566,169 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len ? : ret;
 }
 
+static int rtnl_fill_mcaddr(struct sk_buff *skb, const struct net_device *dev,
+			    const struct netdev_hw_addr *ha, u32 portid,
+			    u32 seq, unsigned int flags, int netnsid)
+{
+	u32 ifa_flags = ha->global_use ? IFA_F_GLOBAL : 0;
+	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 holds 8 bits, the full value is in IFA_FLAGS */
+	ifm->ifa_flags = (__u8)ifa_flags;
+	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, ifa_flags)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int rtnl_dump_mcaddr_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 = rtnl_fill_mcaddr(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 rtnl_mcaddr_dump_filter {
+	struct net *tgt_net;
+	int netnsid;
+	int ifindex;
+};
+
+static const struct nla_policy rtnl_mcaddr_dump_policy[IFA_MAX + 1] = {
+	[IFA_TARGET_NETNSID]	= { .type = NLA_S32 },
+};
+
+static int rtnl_valid_dump_mcaddr_req(const struct nlmsghdr *nlh,
+				      struct sock *sk,
+				      struct rtnl_mcaddr_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,
+			  rtnl_mcaddr_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);
+		}
+		filter->tgt_net = net;
+	}
+
+	filter->ifindex = ifm->ifa_index;
+
+	return 0;
+}
+
+static int rtnl_dump_mcaddr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct rtnl_mcaddr_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;
+	struct net_device *dev;
+	int err;
+
+	err = rtnl_valid_dump_mcaddr_req(cb->nlh, skb->sk, &filter,
+					 cb->extack);
+	if (err < 0)
+		return err;
+
+	rcu_read_lock();
+
+	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 = -ENODEV;
+			goto out;
+		}
+		err = rtnl_dump_mcaddr_dev(dev, skb, cb, &ctx->addr_idx, flags,
+					   filter.netnsid);
+		goto out;
+	}
+
+	for_each_netdev_dump(filter.tgt_net, dev, ctx->ifindex) {
+		err = rtnl_dump_mcaddr_dev(dev, skb, cb, &ctx->addr_idx, flags,
+					   filter.netnsid);
+		if (err < 0)
+			break;
+	}
+out:
+	rcu_read_unlock();
+	if (filter.netnsid >= 0)
+		put_net(filter.tgt_net);
+	return err;
+}
+
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 				       unsigned int change,
 				       u32 event, gfp_t flags, int *new_nsid,
@@ -7251,6 +7414,8 @@ 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 = rtnl_dump_mcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED},
 	{.protocol = PF_BRIDGE, .msgtype = RTM_GETLINK,
 	 .dumpit = rtnl_bridge_getlink},
 	{.protocol = PF_BRIDGE, .msgtype = RTM_DELLINK,
-- 
2.43.0
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help