Merge branch 'rtnetlink-rework-handler-registration'

Florian Westphal says:

====================
rtnetlink: rework handler (un)registering

Peter Zijlstra reported (referring to commit 019a3169,
"rtnetlink: add reference counting to prevent module unload while dump is in progress"):

 1) it not in fact a refcount, so using refcount_t is silly
 2) there is a distinct lack of memory barriers, so we can easily
    observe the decrement while the msg_handler is still in progress.
 3) waiting with a schedule()/yield() loop is complete crap and subject
    life-locks, imagine doing that rtnl_unregister_all() from a RT task.

In ancient times rtnetlink exposed a statically-sized table with
preset doit/dumpit handlers to be called for a protocol/type pair.

Later the rtnl_register interface was added and the table was allocated
on demand.  Eventually these were also used by modules.

Problem is that nothing prevents module unload while a netlink dump
is in progress.  netlink dumps can be span multiple recv calls and
netlink core saves the to-be-repeated dumper address for later invocation.

To prevent rmmod the netlink core expects callers to pass in the owning
module so a reference can be taken.

So far rtnetlink wasn't doing this, add new interface to pass THIS_MODULE.
Moreover, when converting parts of the rtnetlink handling to rcu this code
gained way too many READ_ONCE spots, remove them and the extra refcounting.

Take a module reference when running dumpit and doit callbacks
and never alter content of rtnl_link structures after they have been
published via rcu_assign_pointer.

Based partially on earlier patch from Peter.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/rtnetlink.h

@@ -13,10 +13,10 @@ enum rtnl_link_flags {
 	RTNL_FLAG_DOIT_UNLOCKED = 1,
 };
 
-int __rtnl_register(int protocol, int msgtype,
-		    rtnl_doit_func, rtnl_dumpit_func, unsigned int flags);
 void rtnl_register(int protocol, int msgtype,
 		   rtnl_doit_func, rtnl_dumpit_func, unsigned int flags);
+int rtnl_register_module(struct module *owner, int protocol, int msgtype,
+			 rtnl_doit_func, rtnl_dumpit_func, unsigned int flags);
 int rtnl_unregister(int protocol, int msgtype);
 void rtnl_unregister_all(int protocol);
 

net/bridge/br_mdb.c

@@ -760,9 +760,9 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 void br_mdb_init(void)
 {
-	rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, 0);
-	rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, 0);
-	rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, 0);
+	rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, 0);
 }
 
 void br_mdb_uninit(void)

net/can/gw.c

@@ -1014,6 +1014,8 @@ static struct pernet_operations cangw_pernet_ops = {
 
 static __init int cgw_module_init(void)
 {
+	int ret;
+
 	/* sanitize given module parameter */
 	max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS);
 
@@ -1031,15 +1033,19 @@ static __init int cgw_module_init(void)
 	notifier.notifier_call = cgw_notifier;
 	register_netdevice_notifier(&notifier);
 
-	if (__rtnl_register(PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0)) {
+	ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE,
+				   NULL, cgw_dump_jobs, 0);
+	if (ret) {
 		unregister_netdevice_notifier(&notifier);
 		kmem_cache_destroy(cgw_cache);
 		return -ENOBUFS;
 	}
 
-	/* Only the first call to __rtnl_register can fail */
-	__rtnl_register(PF_CAN, RTM_NEWROUTE, cgw_create_job, NULL, 0);
-	__rtnl_register(PF_CAN, RTM_DELROUTE, cgw_remove_job, NULL, 0);
+	/* Only the first call to rtnl_register_module can fail */
+	rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE,
+			     cgw_create_job, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE,
+			     cgw_remove_job, NULL, 0);
 
 	return 0;
 }

net/decnet/dn_dev.c

@@ -1418,9 +1418,12 @@ void __init dn_dev_init(void)
 
 	dn_dev_devices_on();
 
-	rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL, 0);
-	rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, 0);
-	rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWADDR,
+			     dn_nl_newaddr, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELADDR,
+			     dn_nl_deladdr, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETADDR,
+			     NULL, dn_nl_dump_ifaddr, 0);
 
 	proc_create("decnet_dev", S_IRUGO, init_net.proc_net, &dn_dev_seq_fops);
 

net/decnet/dn_fib.c

@@ -792,8 +792,10 @@ void __init dn_fib_init(void)
 
 	register_dnaddr_notifier(&dn_fib_dnaddr_notifier);
 
-	rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL, 0);
-	rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWROUTE,
+			     dn_fib_rtm_newroute, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELROUTE,
+			     dn_fib_rtm_delroute, NULL, 0);
 }
 
 

net/decnet/dn_route.c

@@ -1923,11 +1923,11 @@ void __init dn_route_init(void)
 		    &dn_rt_cache_seq_fops);
 
 #ifdef CONFIG_DECNET_ROUTER
-	rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute,
-		      dn_fib_dump, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE,
+			     dn_cache_getroute, dn_fib_dump, 0);
 #else
-	rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute,
-		      dn_cache_dump, 0);
+	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE,
+			     dn_cache_getroute, dn_cache_dump, 0);
 #endif
 }
 

net/ipv6/addrconf.c

@@ -6595,27 +6595,43 @@ int __init addrconf_init(void)
 
 	rtnl_af_register(&inet6_ops);
 
-	err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo,
-			      0);
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETLINK,
+				   NULL, inet6_dump_ifinfo, 0);
 	if (err < 0)
 		goto errout;
 
-	/* Only the first call to __rtnl_register can fail */
-	__rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0);
-	__rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0);
-	__rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr,
-			inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED);
-	__rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL,
-			inet6_dump_ifmcaddr, 0);
-	__rtnl_register(PF_INET6, RTM_GETANYCAST, NULL,
-			inet6_dump_ifacaddr, 0);
-	__rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf,
-			inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED);
-
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDR,
+				   inet6_rtm_newaddr, NULL, 0);
+	if (err < 0)
+		goto errout;
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDR,
+				   inet6_rtm_deladdr, NULL, 0);
+	if (err < 0)
+		goto errout;
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR,
+				   inet6_rtm_getaddr, inet6_dump_ifaddr,
+				   RTNL_FLAG_DOIT_UNLOCKED);
+	if (err < 0)
+		goto errout;
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST,
+				   NULL, inet6_dump_ifmcaddr, 0);
+	if (err < 0)
+		goto errout;
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST,
+				   NULL, inet6_dump_ifacaddr, 0);
+	if (err < 0)
+		goto errout;
+	err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF,
+				   inet6_netconf_get_devconf,
+				   inet6_netconf_dump_devconf,
+				   RTNL_FLAG_DOIT_UNLOCKED);
+	if (err < 0)
+		goto errout;
 	ipv6_addr_label_rtnl_register();
 
 	return 0;
 errout:
+	rtnl_unregister_all(PF_INET6);
 	rtnl_af_unregister(&inet6_ops);
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:

net/ipv6/addrlabel.c

@@ -549,11 +549,10 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 void __init ipv6_addr_label_rtnl_register(void)
 {
-	__rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel,
+	rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel,
 		      NULL, RTNL_FLAG_DOIT_UNLOCKED);
-	__rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel,
+	rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel,
 		      NULL, RTNL_FLAG_DOIT_UNLOCKED);
-	__rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get,
+	rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get,
 		      ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED);
 }
-

net/ipv6/ip6_fib.c

@@ -2142,8 +2142,8 @@ int __init fib6_init(void)
 	if (ret)
 		goto out_kmem_cache_create;
 
-	ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib,
-			      0);
+	ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL,
+				   inet6_dump_fib, 0);
 	if (ret)
 		goto out_unregister_subsys;
 

net/ipv6/route.c

@@ -4772,11 +4772,20 @@ int __init ip6_route_init(void)
 	if (ret)
 		goto fib6_rules_init;
 
-	ret = -ENOBUFS;
-	if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, 0) ||
-	    __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, 0) ||
-	    __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL,
-			    RTNL_FLAG_DOIT_UNLOCKED))
+	ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWROUTE,
+				   inet6_rtm_newroute, NULL, 0);
+	if (ret < 0)
+		goto out_register_late_subsys;
+
+	ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELROUTE,
+				   inet6_rtm_delroute, NULL, 0);
+	if (ret < 0)
+		goto out_register_late_subsys;
+
+	ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE,
+				   inet6_rtm_getroute, NULL,
+				   RTNL_FLAG_DOIT_UNLOCKED);
+	if (ret < 0)
 		goto out_register_late_subsys;
 
 	ret = register_netdevice_notifier(&ip6_route_dev_notifier);
@@ -4794,6 +4803,7 @@ int __init ip6_route_init(void)
 	return ret;
 
 out_register_late_subsys:
+	rtnl_unregister_all(PF_INET6);
 	unregister_pernet_subsys(&ip6_route_net_late_ops);
 fib6_rules_init:
 	fib6_rules_cleanup();

net/mpls/af_mpls.c

@@ -2510,11 +2510,14 @@ static int __init mpls_init(void)
 
 	rtnl_af_register(&mpls_af_ops);
 
-	rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, 0);
-	rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, 0);
-	rtnl_register(PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes,
-		      0);
-	rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf,
+	rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_NEWROUTE,
+			     mpls_rtm_newroute, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_DELROUTE,
+			     mpls_rtm_delroute, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_GETROUTE,
+			     mpls_getroute, mpls_dump_routes, 0);
+	rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_GETNETCONF,
+			     mpls_netconf_get_devconf,
 			     mpls_netconf_dump_devconf, 0);
 	err = ipgre_tunnel_encap_add_mpls_ops();
 	if (err)

net/phonet/pn_netlink.c

@@ -299,16 +299,21 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 int __init phonet_netlink_register(void)
 {
-	int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit,
-				  NULL, 0);
+	int err = rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_NEWADDR,
+				       addr_doit, NULL, 0);
 	if (err)
 		return err;
 
-	/* Further __rtnl_register() cannot fail */
-	__rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL, 0);
-	__rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit, 0);
-	__rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL, 0);
-	__rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL, 0);
-	__rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit, 0);
+	/* Further rtnl_register_module() cannot fail */
+	rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_DELADDR,
+			     addr_doit, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_GETADDR,
+			     NULL, getaddr_dumpit, 0);
+	rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_NEWROUTE,
+			     route_doit, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_DELROUTE,
+			     route_doit, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_GETROUTE,
+			     NULL, route_dumpit, 0);
 	return 0;
 }

net/qrtr/qrtr.c

@@ -1116,9 +1116,13 @@ static int __init qrtr_proto_init(void)
 		return rc;
 	}
 
-	rtnl_register(PF_QIPCRTR, RTM_NEWADDR, qrtr_addr_doit, NULL, 0);
+	rc = rtnl_register_module(THIS_MODULE, PF_QIPCRTR, RTM_NEWADDR, qrtr_addr_doit, NULL, 0);
+	if (rc) {
+		sock_unregister(qrtr_family.family);
+		proto_unregister(&qrtr_proto);
+	}
 
-	return 0;
+	return rc;
 }
 postcore_initcall(qrtr_proto_init);