From 5b4b62a169e10401cca34a6e7ac39161986f5605 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 3 Jun 2024 11:48:26 -0700 Subject: rtnetlink: make the "split" NLM_DONE handling generic Jaroslav reports Dell's OMSA Systems Management Data Engine expects NLM_DONE in a separate recvmsg(), both for rtnl_dump_ifinfo() and inet_dump_ifaddr(). We already added a similar fix previously in commit 460b0d33cf10 ("inet: bring NLM_DONE out to a separate recv() again") Instead of modifying all the dump handlers, and making them look different than modern for_each_netdev_dump()-based dump handlers - put the workaround in rtnetlink code. This will also help us move the custom rtnl-locking from af_netlink in the future (in net-next). Note that this change is not touching rtnl_dump_all(). rtnl_dump_all() is different kettle of fish and a potential problem. We now mix families in a single recvmsg(), but NLM_DONE is not coalesced. Tested: ./cli.py --dbg-small-recv 4096 --spec netlink/specs/rt_addr.yaml \ --dump getaddr --json '{"ifa-family": 2}' ./cli.py --dbg-small-recv 4096 --spec netlink/specs/rt_route.yaml \ --dump getroute --json '{"rtm-family": 2}' ./cli.py --dbg-small-recv 4096 --spec netlink/specs/rt_link.yaml \ --dump getlink Fixes: 3e41af90767d ("rtnetlink: use xarray iterator to implement rtnl_dump_ifinfo()") Fixes: cdb2f80f1c10 ("inet: use xa_array iterator to implement inet_dump_ifaddr()") Reported-by: Jaroslav Pulchart Link: https://lore.kernel.org/all/CAK8fFZ7MKoFSEzMBDAOjoUt+vTZRRQgLDNXEOfdCCXSoXXKE0g@mail.gmail.com Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 44 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 42 insertions(+), 2 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b86b0a87367d..4668d6718040 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -6484,6 +6484,46 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, /* Process one rtnetlink message. */ +static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + rtnl_dumpit_func dumpit = cb->data; + int err; + + /* Previous iteration have already finished, avoid calling->dumpit() + * again, it may not expect to be called after it reached the end. + */ + if (!dumpit) + return 0; + + err = dumpit(skb, cb); + + /* Old dump handlers used to send NLM_DONE as in a separate recvmsg(). + * Some applications which parse netlink manually depend on this. + */ + if (cb->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) { + if (err < 0 && err != -EMSGSIZE) + return err; + if (!err) + cb->data = NULL; + + return skb->len; + } + return err; +} + +static int rtnetlink_dump_start(struct sock *ssk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *control) +{ + if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) { + WARN_ON(control->data); + control->data = control->dump; + control->dump = rtnl_dumpit; + } + + return netlink_dump_start(ssk, skb, nlh, control); +} + static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -6548,7 +6588,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, .module = owner, .flags = flags, }; - err = netlink_dump_start(rtnl, skb, nlh, &c); + err = rtnetlink_dump_start(rtnl, skb, nlh, &c); /* netlink_dump_start() will keep a reference on * module if dump is still in progress. */ @@ -6694,7 +6734,7 @@ void __init rtnetlink_init(void) register_netdevice_notifier(&rtnetlink_dev_notifier); rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, - rtnl_dump_ifinfo, 0); + rtnl_dump_ifinfo, RTNL_FLAG_DUMP_SPLIT_NLM_DONE); rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, 0); rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, 0); -- cgit