Re: [PATCH net-next v3 1/2] netlink: ipv4 igmp join notifications

[Roopa Prabhu <roopa@cumulusnetworks.com>]

On Thu, Sep 6, 2018 at 2:10 AM, Patrick Ruddy
<pruddy@vyatta.att-mail.com> wrote:
> Some userspace applications need to know about IGMP joins from the
> kernel for 2 reasons:
> 1. To allow the programming of multicast MAC filters in hardware
> 2. To form a multicast FORUS list for non link-local multicast
>    groups to be sent to the kernel and from there to the interested
>    party.
> (1) can be fulfilled but simply sending the hardware multicast MAC
> address to be programmed but (2) requires the L3 address to be sent
> since this cannot be constructed from the MAC address whereas the
> reverse translation is a standard library function.
>
> This commit provides addition and deletion of multicast addresses
> using the RTM_NEWMDB and RTM_DELMDB messages with AF_INET. It also
> provides the RTM_GETMDB extension to allow multicast join state to
> be read from the kernel.
>
> Signed-off-by: Patrick Ruddy <pruddy@vyatta.att-mail.com>
> ---
> v3 rework to use RTM_***MDB messages as per review comments.

Patrick, this version seems to be using RTM_***MDB msgs with the
RTM_*ADDR format.
We cant do that...because existing RTM_MDB users will be confused.

My request was to evaluate RTM_***MDB msg format. see
nlmsg_populate_mdb_fill for details.

If you can wait a day or two I can share some experimental code that
moves high level RTM_*MDB msg handling into net/core/rtnetlink.c
similar to RTM_*FDB



>
>  net/ipv4/igmp.c | 139 ++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 139 insertions(+)
>
> diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
> index 4da39446da2d..aed819e2ea93 100644
> --- a/net/ipv4/igmp.c
> +++ b/net/ipv4/igmp.c
> @@ -86,6 +86,7 @@
>  #include <linux/inetdevice.h>
>  #include <linux/igmp.h>
>  #include <linux/if_arp.h>
> +#include <net/netlink.h>
>  #include <linux/rtnetlink.h>
>  #include <linux/times.h>
>  #include <linux/pkt_sched.h>
> @@ -1385,6 +1386,91 @@ static void ip_mc_hash_remove(struct in_device *in_dev,
>  }
>
>
> +static int fill_addr(struct sk_buff *skb, struct net_device *dev, __be32 addr,
> +                    int type, unsigned int flags)
> +{
> +       struct nlmsghdr *nlh;
> +       struct ifaddrmsg *ifm;
> +
> +       nlh = nlmsg_put(skb, 0, 0, type, sizeof(*ifm), flags);
> +       if (!nlh)
> +               return -EMSGSIZE;
> +
> +       ifm = nlmsg_data(nlh);
> +       ifm->ifa_family = AF_INET;
> +       ifm->ifa_prefixlen = 32;
> +       ifm->ifa_flags = IFA_F_PERMANENT;
> +       ifm->ifa_scope = RT_SCOPE_LINK;
> +       ifm->ifa_index = dev->ifindex;
> +
> +       if (nla_put_in_addr(skb, IFA_ADDRESS, addr))
> +               goto nla_put_failure;
> +       nlmsg_end(skb, nlh);
> +       return 0;
> +
> +nla_put_failure:
> +       nlmsg_cancel(skb, nlh);
> +       return -EMSGSIZE;
> +}
> +
> +static inline size_t addr_nlmsg_size(void)
> +{
> +       return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
> +               + nla_total_size(sizeof(__be32));
> +}
> +
> +static void ip_mc_addr_notify(struct net_device *dev, __be32 addr, int type)
> +{
> +       struct net *net = dev_net(dev);
> +       struct sk_buff *skb;
> +       int err = -ENOBUFS;
> +
> +       skb = nlmsg_new(addr_nlmsg_size(), GFP_ATOMIC);
> +       if (!skb)
> +               goto errout;
> +
> +       err = fill_addr(skb, dev, addr, type, 0);
> +       if (err < 0) {
> +               WARN_ON(err == -EMSGSIZE);
> +               kfree_skb(skb);
> +               goto errout;
> +       }
> +       rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC);
> +       return;
> +errout:
> +       if (err < 0)
> +               rtnl_set_sk_err(net, RTNLGRP_MDB, err);
> +}
> +
> +int ip_mc_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb,
> +                     struct net_device *dev)
> +{
> +       int s_idx;
> +       int idx = 0;
> +       struct ip_mc_list *im;
> +       struct in_device *in_dev;
> +
> +       ASSERT_RTNL();
> +
> +       s_idx = cb->args[2];
> +       in_dev = __in_dev_get_rtnl(dev);
> +
> +       for_each_pmc_rtnl(in_dev, im) {
> +               if (idx < s_idx)
> +                       continue;
> +               if (fill_addr(skb, dev, im->multiaddr, RTM_NEWMDB,
> +                             NLM_F_MULTI) < 0)
> +                       goto done;
> +               nl_dump_check_consistent(cb, nlmsg_hdr(skb));
> +               idx++;
> +       }
> +
> + done:
> +       cb->args[2] = idx;
> +
> +       return skb->len;
> +}
> +
>  /*
>   *     A socket has joined a multicast group on device dev.
>   */
> @@ -1430,6 +1516,8 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr,
>         igmpv3_del_delrec(in_dev, im);
>  #endif
>         igmp_group_added(im);
> +
> +       ip_mc_addr_notify(in_dev->dev, addr, RTM_NEWMDB);
>         if (!in_dev->dead)
>                 ip_rt_multicast_event(in_dev);
>  out:
> @@ -1661,6 +1749,8 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr)
>                                 in_dev->mc_count--;
>                                 igmp_group_dropped(i);
>                                 ip_mc_clear_src(i);
> +                               ip_mc_addr_notify(in_dev->dev, addr,
> +                                                 RTM_DELMDB);
>
>                                 if (!in_dev->dead)
>                                         ip_rt_multicast_event(in_dev);
> @@ -3051,6 +3141,53 @@ static struct notifier_block igmp_notifier = {
>         .notifier_call = igmp_netdev_event,
>  };
>
> +static int igmp_mc_dump_ifaddrs(struct sk_buff *skb,
> +                               struct netlink_callback *cb)
> +{
> +       struct net *net = sock_net(skb->sk);
> +       int h, s_h;
> +       int idx, s_idx;
> +       struct net_device *dev;
> +       struct in_device *in_dev;
> +       struct hlist_head *head;
> +
> +       s_h = cb->args[0];
> +       idx = cb->args[1];
> +       s_idx = idx;
> +
> +       for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
> +               idx = 0;
> +               head = &net->dev_index_head[h];
> +               rcu_read_lock();
> +               cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
> +                         net->dev_base_seq;
> +               hlist_for_each_entry_rcu(dev, head, index_hlist) {
> +                       if (idx < s_idx)
> +                               goto cont;
> +                       if (h > s_h || idx > s_idx)
> +                               cb->args[2] = 0;
> +                       in_dev = __in_dev_get_rcu(dev);
> +                       if (!in_dev)
> +                               goto cont;
> +
> +                       /* loop over multicast addresses */
> +                       if (ip_mc_dump_ifaddr(skb, cb, dev) < 0) {
> +                               rcu_read_unlock();
> +                               goto done;
> +                       }
> +cont:
> +                       idx++;
> +               }
> +               rcu_read_unlock();
> +       }
> +
> +done:
> +       cb->args[0] = h;
> +       cb->args[1] = idx;
> +
> +       return skb->len;
> +}
> +
>  int __init igmp_mc_init(void)
>  {
>  #if defined(CONFIG_PROC_FS)
> @@ -3064,6 +3201,8 @@ int __init igmp_mc_init(void)
>                 goto reg_notif_fail;
>         return 0;
>
> +       rtnl_register(PF_INET, RTM_GETMDB, NULL, igmp_mc_dump_ifaddrs, 0);
> +
>  reg_notif_fail:
>         unregister_pernet_subsys(&igmp_net_ops);
>         return err;
> --
> 2.17.1
>