rtnetlink: Compute and store minimum ifinfo dump size

commit c7ac867 upstream.

The message size allocated for rtnl ifinfo dumps was limited to
a single page.  This is not enough for additional interface info
available with devices that support SR-IOV and caused a bug in
which VF info would not be displayed if more than approximately
40 VFs were created per interface.

Implement a new function pointer for the rtnl_register service that will
calculate the amount of data required for the ifinfo dump and allocate
enough data to satisfy the request.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/infiniband/core/netlink.c

@@ -148,7 +148,7 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				return -EINVAL;
 			return netlink_dump_start(nls, skb, nlh,
 						  client->cb_table[op].dump,
-						  NULL);
+						  NULL, 0);
 		}
 	}
 

include/linux/netlink.h

@@ -221,7 +221,8 @@ struct netlink_callback {
 	int			(*dump)(struct sk_buff * skb,
 					struct netlink_callback *cb);
 	int			(*done)(struct netlink_callback *cb);
-	int			family;
+	u16			family;
+	u16			min_dump_alloc;
 	long			args[6];
 };
 
@@ -259,7 +260,8 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags)
 extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      int (*dump)(struct sk_buff *skb, struct netlink_callback*),
-			      int (*done)(struct netlink_callback*));
+			      int (*done)(struct netlink_callback*),
+			      u16 min_dump_alloc);
 
 
 #define NL_NONROOT_RECV 0x1

include/net/rtnetlink.h

@@ -6,11 +6,14 @@
 
 typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, void *);
 typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
+typedef u16 (*rtnl_calcit_func)(struct sk_buff *);
 
 extern int	__rtnl_register(int protocol, int msgtype,
-				rtnl_doit_func, rtnl_dumpit_func);
+				rtnl_doit_func, rtnl_dumpit_func,
+				rtnl_calcit_func);
 extern void	rtnl_register(int protocol, int msgtype,
-			      rtnl_doit_func, rtnl_dumpit_func);
+			      rtnl_doit_func, rtnl_dumpit_func,
+			      rtnl_calcit_func);
 extern int	rtnl_unregister(int protocol, int msgtype);
 extern void	rtnl_unregister_all(int protocol);
 

net/bridge/br_netlink.c

@@ -219,19 +219,24 @@ int __init br_netlink_init(void)
 	if (err < 0)
 		goto err1;
 
-	err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, br_dump_ifinfo);
+	err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL,
+			      br_dump_ifinfo, NULL);
 	if (err)
 		goto err2;
-	err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, br_rtm_setlink, NULL);
+	err = __rtnl_register(PF_BRIDGE, RTM_SETLINK,
+			      br_rtm_setlink, NULL, NULL);
 	if (err)
 		goto err3;
-	err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, br_fdb_add, NULL);
+	err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH,
+			      br_fdb_add, NULL, NULL);
 	if (err)
 		goto err3;
-	err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, br_fdb_delete, NULL);
+	err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH,
+			      br_fdb_delete, NULL, NULL);
 	if (err)
 		goto err3;
-	err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, br_fdb_dump);
+	err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH,
+			      NULL, br_fdb_dump, NULL);
 	if (err)
 		goto err3;
 

net/core/fib_rules.c

@@ -740,9 +740,9 @@ static struct pernet_operations fib_rules_net_ops = {
 static int __init fib_rules_init(void)
 {
 	int err;
-	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule);
+	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL);
 
 	err = register_pernet_subsys(&fib_rules_net_ops);
 	if (err < 0)

net/core/neighbour.c

@@ -2918,12 +2918,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister);
 
 static int __init neigh_init(void)
 {
-	rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info);
+	rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL);
 
-	rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info);
-	rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info,
+		      NULL);
+	rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL);
 
 	return 0;
 }

net/core/rtnetlink.c

@@ -56,9 +56,11 @@
 struct rtnl_link {
 	rtnl_doit_func		doit;
 	rtnl_dumpit_func	dumpit;
+	rtnl_calcit_func 	calcit;
 };
 
 static DEFINE_MUTEX(rtnl_mutex);
+static u16 min_ifinfo_dump_size;
 
 void rtnl_lock(void)
 {
@@ -144,12 +146,28 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
 	return tab ? tab[msgindex].dumpit : NULL;
 }
 
+static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
+{
+	struct rtnl_link *tab;
+
+	if (protocol <= RTNL_FAMILY_MAX)
+		tab = rtnl_msg_handlers[protocol];
+	else
+		tab = NULL;
+
+	if (tab == NULL || tab[msgindex].calcit == NULL)
+		tab = rtnl_msg_handlers[PF_UNSPEC];
+
+	return tab ? tab[msgindex].calcit : NULL;
+}
+
 /**
  * __rtnl_register - Register a rtnetlink message type
  * @protocol: Protocol family or PF_UNSPEC
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
+ * @calcit: Function pointer to calc size of dump message
  *
  * Registers the specified function pointers (at least one of them has
  * to be non-NULL) to be called whenever a request message for the
@@ -162,7 +180,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
  * Returns 0 on success or a negative error code.
  */
 int __rtnl_register(int protocol, int msgtype,
-		    rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+		    rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+		    rtnl_calcit_func calcit)
 {
 	struct rtnl_link *tab;
 	int msgindex;
@@ -185,6 +204,9 @@ int __rtnl_register(int protocol, int msgtype,
 	if (dumpit)
 		tab[msgindex].dumpit = dumpit;
 
+	if (calcit)
+		tab[msgindex].calcit = calcit;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__rtnl_register);
@@ -199,9 +221,10 @@ EXPORT_SYMBOL_GPL(__rtnl_register);
  * of memory implies no sense in continuing.
  */
 void rtnl_register(int protocol, int msgtype,
-		   rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+		   rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+		   rtnl_calcit_func calcit)
 {
-	if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0)
+	if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0)
 		panic("Unable to register rtnetlink message handler, "
 		      "protocol = %d, message type = %d\n",
 		      protocol, msgtype);
@@ -1825,6 +1848,11 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	return err;
 }
 
+static u16 rtnl_calcit(struct sk_buff *skb)
+{
+	return min_ifinfo_dump_size;
+}
+
 static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	int idx;
@@ -1854,11 +1882,14 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
+	size_t if_info_size;
 
-	skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
+	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL);
 	if (skb == NULL)
 		goto errout;
 
+	min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size);
+
 	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
@@ -1909,14 +1940,20 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
+		rtnl_calcit_func calcit;
+		u16 min_dump_alloc = 0;
 
 		dumpit = rtnl_get_dumpit(family, type);
 		if (dumpit == NULL)
 			return -EOPNOTSUPP;
+		calcit = rtnl_get_calcit(family, type);
+		if (calcit)
+			min_dump_alloc = calcit(skb);
 
 		__rtnl_unlock();
 		rtnl = net->rtnl;
-		err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
+		err = netlink_dump_start(rtnl, skb, nlh, dumpit,
+					 NULL, min_dump_alloc);
 		rtnl_lock();
 		return err;
 	}
@@ -2026,12 +2063,13 @@ void __init rtnetlink_init(void)
 	netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV);
 	register_netdevice_notifier(&rtnetlink_dev_notifier);
 
-	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo);
-	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL);
-	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
+		      rtnl_dump_ifinfo, rtnl_calcit);
+	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL);
 
-	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all);
-	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);
+	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
 }
 

net/dcb/dcbnl.c

@@ -1819,8 +1819,8 @@ static int __init dcbnl_init(void)
 {
 	INIT_LIST_HEAD(&dcb_app_list);
 
-	rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL);
-	rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, NULL);
 
 	return 0;
 }

net/decnet/dn_dev.c

@@ -1414,9 +1414,9 @@ void __init dn_dev_init(void)
 
 	dn_dev_devices_on();
 
-	rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL);
-	rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL);
-	rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr);
+	rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL, NULL);
+	rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, NULL);
+	rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, NULL);
 
 	proc_net_fops_create(&init_net, "decnet_dev", S_IRUGO, &dn_dev_seq_fops);
 

net/decnet/dn_fib.c

@@ -763,8 +763,8 @@ void __init dn_fib_init(void)
 
 	register_dnaddr_notifier(&dn_fib_dnaddr_notifier);
 
-	rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL);
-	rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL);
+	rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL, NULL);
 }
 
 

net/decnet/dn_route.c

@@ -1843,10 +1843,11 @@ void __init dn_route_init(void)
 	proc_net_fops_create(&init_net, "decnet_cache", S_IRUGO, &dn_rt_cache_seq_fops);
 
 #ifdef CONFIG_DECNET_ROUTER
-	rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, dn_fib_dump);
+	rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute,
+		      dn_fib_dump, NULL);
 #else
 	rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute,
-		      dn_cache_dump);
+		      dn_cache_dump, NULL);
 #endif
 }
 

net/ipv4/devinet.c

@@ -1838,8 +1838,8 @@ void __init devinet_init(void)
 
 	rtnl_af_register(&inet_af_ops);
 
-	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL);
-	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL);
-	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr);
+	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL);
 }
 

net/ipv4/fib_frontend.c

@@ -1124,9 +1124,9 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib);
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
 
 	register_pernet_subsys(&fib_net_ops);
 	register_netdevice_notifier(&fib_netdev_notifier);

net/ipv4/inet_diag.c

@@ -869,7 +869,7 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 
 		return netlink_dump_start(idiagnl, skb, nlh,
-					  inet_diag_dump, NULL);
+					  inet_diag_dump, NULL, 0);
 	}
 
 	return inet_diag_get_exact(skb, nlh);

net/ipv4/ipmr.c

@@ -2554,7 +2554,8 @@ int __init ip_mr_init(void)
 		goto add_proto_fail;
 	}
 #endif
-	rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute);
+	rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE,
+		      NULL, ipmr_rtm_dumproute, NULL);
 	return 0;
 
 #ifdef CONFIG_IP_PIMSM_V2

net/ipv4/route.c

@@ -3454,7 +3454,7 @@ int __init ip_rt_init(void)
 	xfrm_init();
 	xfrm4_init(ip_rt_max_size);
 #endif
-	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
 
 #ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&sysctl_route_ops);

net/ipv6/addrconf.c

@@ -4694,16 +4694,20 @@ int __init addrconf_init(void)
 	if (err < 0)
 		goto errout_af;
 
-	err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo);
+	err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo,
+			      NULL);
 	if (err < 0)
 		goto errout;
 
 	/* Only the first call to __rtnl_register can fail */
-	__rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL);
-	__rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL);
-	__rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr);
-	__rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr);
-	__rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr);
+	__rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, NULL);
+	__rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, NULL);
+	__rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr,
+			inet6_dump_ifaddr, NULL);
+	__rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL,
+			inet6_dump_ifmcaddr, NULL);
+	__rtnl_register(PF_INET6, RTM_GETANYCAST, NULL,
+			inet6_dump_ifacaddr, NULL);
 
 	ipv6_addr_label_rtnl_register();
 

net/ipv6/addrlabel.c

@@ -592,8 +592,11 @@ 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, NULL);
-	__rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, NULL);
-	__rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, ip6addrlbl_dump);
+	__rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel,
+			NULL, NULL);
+	__rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel,
+			NULL, NULL);
+	__rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get,
+			ip6addrlbl_dump, NULL);
 }