rtnetlink: Compute and store minimum ifinfo dump size

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>

3 files changed, 58 insertions, 19 deletions

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 008dc70b064b..e7ab0c0285b5 100644
--- a/net/core/fib_rules.c
+++ b/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)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 799f06e03a22..ceb505b1507c 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2909,12 +2909,13 @@ 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;
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index abd936d8a716..a798fc6f2aa1 100644
--- a/net/core/rtnetlink.c
+++ b/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);
@@ -1818,6 +1841,11 @@ 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;
@@ -1847,11 +1875,14 @@ 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() */
@@ -1902,14 +1933,20 @@ 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;
         }
@@ -2019,12 +2056,13 @@ 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);
 }